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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Authentication token and access key management * * Copyright (C) 2004, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/security/keys/core.rst for information on keys/keyrings. */ #ifndef _LINUX_KEY_H #define _LINUX_KEY_H #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include <linux/sysctl.h> #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/assoc_array.h> #include <linux/refcount.h> #include <linux/time64.h> #ifdef __KERNEL__ #include <linux/uidgid.h> /* key handle serial number */ typedef int32_t key_serial_t; /* key handle permissions mask */ typedef uint32_t key_perm_t; struct key; struct net; #ifdef CONFIG_KEYS #undef KEY_DEBUGGING #define KEY_POS_VIEW 0x01000000 /* possessor can view a key's attributes */ #define KEY_POS_READ 0x02000000 /* possessor can read key payload / view keyring */ #define KEY_POS_WRITE 0x04000000 /* possessor can update key payload / add link to keyring */ #define KEY_POS_SEARCH 0x08000000 /* possessor can find a key in search / search a keyring */ #define KEY_POS_LINK 0x10000000 /* possessor can create a link to a key/keyring */ #define KEY_POS_SETATTR 0x20000000 /* possessor can set key attributes */ #define KEY_POS_ALL 0x3f000000 #define KEY_USR_VIEW 0x00010000 /* user permissions... */ #define KEY_USR_READ 0x00020000 #define KEY_USR_WRITE 0x00040000 #define KEY_USR_SEARCH 0x00080000 #define KEY_USR_LINK 0x00100000 #define KEY_USR_SETATTR 0x00200000 #define KEY_USR_ALL 0x003f0000 #define KEY_GRP_VIEW 0x00000100 /* group permissions... */ #define KEY_GRP_READ 0x00000200 #define KEY_GRP_WRITE 0x00000400 #define KEY_GRP_SEARCH 0x00000800 #define KEY_GRP_LINK 0x00001000 #define KEY_GRP_SETATTR 0x00002000 #define KEY_GRP_ALL 0x00003f00 #define KEY_OTH_VIEW 0x00000001 /* third party permissions... */ #define KEY_OTH_READ 0x00000002 #define KEY_OTH_WRITE 0x00000004 #define KEY_OTH_SEARCH 0x00000008 #define KEY_OTH_LINK 0x00000010 #define KEY_OTH_SETATTR 0x00000020 #define KEY_OTH_ALL 0x0000003f #define KEY_PERM_UNDEF 0xffffffff /* * The permissions required on a key that we're looking up. */ enum key_need_perm { KEY_NEED_UNSPECIFIED, /* Needed permission unspecified */ KEY_NEED_VIEW, /* Require permission to view attributes */ KEY_NEED_READ, /* Require permission to read content */ KEY_NEED_WRITE, /* Require permission to update / modify */ KEY_NEED_SEARCH, /* Require permission to search (keyring) or find (key) */ KEY_NEED_LINK, /* Require permission to link */ KEY_NEED_SETATTR, /* Require permission to change attributes */ KEY_NEED_UNLINK, /* Require permission to unlink key */ KEY_SYSADMIN_OVERRIDE, /* Special: override by CAP_SYS_ADMIN */ KEY_AUTHTOKEN_OVERRIDE, /* Special: override by possession of auth token */ KEY_DEFER_PERM_CHECK, /* Special: permission check is deferred */ }; struct seq_file; struct user_struct; struct signal_struct; struct cred; struct key_type; struct key_owner; struct key_tag; struct keyring_list; struct keyring_name; struct key_tag { struct rcu_head rcu; refcount_t usage; bool removed; /* T when subject removed */ }; struct keyring_index_key { /* [!] If this structure is altered, the union in struct key must change too! */ unsigned long hash; /* Hash value */ union { struct { #ifdef __LITTLE_ENDIAN /* Put desc_len at the LSB of x */ u16 desc_len; char desc[sizeof(long) - 2]; /* First few chars of description */ #else char desc[sizeof(long) - 2]; /* First few chars of description */ u16 desc_len; #endif }; unsigned long x; }; struct key_type *type; struct key_tag *domain_tag; /* Domain of operation */ const char *description; }; union key_payload { void __rcu *rcu_data0; void *data[4]; }; /*****************************************************************************/ /* * key reference with possession attribute handling * * NOTE! key_ref_t is a typedef'd pointer to a type that is not actually * defined. This is because we abuse the bottom bit of the reference to carry a * flag to indicate whether the calling process possesses that key in one of * its keyrings. * * the key_ref_t has been made a separate type so that the compiler can reject * attempts to dereference it without proper conversion. * * the three functions are used to assemble and disassemble references */ typedef struct __key_reference_with_attributes *key_ref_t; static inline key_ref_t make_key_ref(const struct key *key, bool possession) { return (key_ref_t) ((unsigned long) key | possession); } static inline struct key *key_ref_to_ptr(const key_ref_t key_ref) { return (struct key *) ((unsigned long) key_ref & ~1UL); } static inline bool is_key_possessed(const key_ref_t key_ref) { return (unsigned long) key_ref & 1UL; } typedef int (*key_restrict_link_func_t)(struct key *dest_keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key); struct key_restriction { key_restrict_link_func_t check; struct key *key; struct key_type *keytype; }; enum key_state { KEY_IS_UNINSTANTIATED, KEY_IS_POSITIVE, /* Positively instantiated */ }; /*****************************************************************************/ /* * authentication token / access credential / keyring * - types of key include: * - keyrings * - disk encryption IDs * - Kerberos TGTs and tickets */ struct key { refcount_t usage; /* number of references */ key_serial_t serial; /* key serial number */ union { struct list_head graveyard_link; struct rb_node serial_node; }; #ifdef CONFIG_KEY_NOTIFICATIONS struct watch_list *watchers; /* Entities watching this key for changes */ #endif struct rw_semaphore sem; /* change vs change sem */ struct key_user *user; /* owner of this key */ void *security; /* security data for this key */ union { time64_t expiry; /* time at which key expires (or 0) */ time64_t revoked_at; /* time at which key was revoked */ }; time64_t last_used_at; /* last time used for LRU keyring discard */ kuid_t uid; kgid_t gid; key_perm_t perm; /* access permissions */ unsigned short quotalen; /* length added to quota */ unsigned short datalen; /* payload data length * - may not match RCU dereferenced payload * - payload should contain own length */ short state; /* Key state (+) or rejection error (-) */ #ifdef KEY_DEBUGGING unsigned magic; #define KEY_DEBUG_MAGIC 0x18273645u #endif unsigned long flags; /* status flags (change with bitops) */ #define KEY_FLAG_DEAD 0 /* set if key type has been deleted */ #define KEY_FLAG_REVOKED 1 /* set if key had been revoked */ #define KEY_FLAG_IN_QUOTA 2 /* set if key consumes quota */ #define KEY_FLAG_USER_CONSTRUCT 3 /* set if key is being constructed in userspace */ #define KEY_FLAG_ROOT_CAN_CLEAR 4 /* set if key can be cleared by root without permission */ #define KEY_FLAG_INVALIDATED 5 /* set if key has been invalidated */ #define KEY_FLAG_BUILTIN 6 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 8 /* set if key should not be removed */ #define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria * - it should be a printable string * - eg: for krb5 AFS, this might be "afs@REDHAT.COM" */ union { struct keyring_index_key index_key; struct { unsigned long hash; unsigned long len_desc; struct key_type *type; /* type of key */ struct key_tag *domain_tag; /* Domain of operation */ char *description; }; }; /* key data * - this is used to hold the data actually used in cryptography or * whatever */ union { union key_payload payload; struct { /* Keyring bits */ struct list_head name_link; struct assoc_array keys; }; }; /* This is set on a keyring to restrict the addition of a link to a key * to it. If this structure isn't provided then it is assumed that the * keyring is open to any addition. It is ignored for non-keyring * keys. Only set this value using keyring_restrict(), keyring_alloc(), * or key_alloc(). * * This is intended for use with rings of trusted keys whereby addition * to the keyring needs to be controlled. KEY_ALLOC_BYPASS_RESTRICTION * overrides this, allowing the kernel to add extra keys without * restriction. */ struct key_restriction *restrict_link; }; extern struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link); #define KEY_ALLOC_IN_QUOTA 0x0000 /* add to quota, reject if would overrun */ #define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */ #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ #define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ #define KEY_ALLOC_SET_KEEP 0x0020 /* Set the KEEP flag on the key/keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); extern void key_put(struct key *key); extern bool key_put_tag(struct key_tag *tag); extern void key_remove_domain(struct key_tag *domain_tag); static inline struct key *__key_get(struct key *key) { refcount_inc(&key->usage); return key; } static inline struct key *key_get(struct key *key) { return key ? __key_get(key) : key; } static inline void key_ref_put(key_ref_t key_ref) { key_put(key_ref_to_ptr(key_ref)); } extern struct key *request_key_tag(struct key_type *type, const char *description, struct key_tag *domain_tag, const char *callout_info); extern struct key *request_key_rcu(struct key_type *type, const char *description, struct key_tag *domain_tag); extern struct key *request_key_with_auxdata(struct key_type *type, const char *description, struct key_tag *domain_tag, const void *callout_info, size_t callout_len, void *aux); /** * request_key - Request a key and wait for construction * @type: Type of key. * @description: The searchable description of the key. * @callout_info: The data to pass to the instantiation upcall (or NULL). * * As for request_key_tag(), but with the default global domain tag. */ static inline struct key *request_key(struct key_type *type, const char *description, const char *callout_info) { return request_key_tag(type, description, NULL, callout_info); } #ifdef CONFIG_NET /** * request_key_net - Request a key for a net namespace and wait for construction * @type: Type of key. * @description: The searchable description of the key. * @net: The network namespace that is the key's domain of operation. * @callout_info: The data to pass to the instantiation upcall (or NULL). * * As for request_key() except that it does not add the returned key to a * keyring if found, new keys are always allocated in the user's quota, the * callout_info must be a NUL-terminated string and no auxiliary data can be * passed. Only keys that operate the specified network namespace are used. * * Furthermore, it then works as wait_for_key_construction() to wait for the * completion of keys undergoing construction with a non-interruptible wait. */ #define request_key_net(type, description, net, callout_info) \ request_key_tag(type, description, net->key_domain, callout_info); /** * request_key_net_rcu - Request a key for a net namespace under RCU conditions * @type: Type of key. * @description: The searchable description of the key. * @net: The network namespace that is the key's domain of operation. * * As for request_key_rcu() except that only keys that operate the specified * network namespace are used. */ #define request_key_net_rcu(type, description, net) \ request_key_rcu(type, description, net->key_domain); #endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); extern int key_validate(const struct key *key); extern key_ref_t key_create_or_update(key_ref_t keyring, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags); extern int key_update(key_ref_t key, const void *payload, size_t plen); extern int key_link(struct key *keyring, struct key *key); extern int key_move(struct key *key, struct key *from_keyring, struct key *to_keyring, unsigned int flags); extern int key_unlink(struct key *keyring, struct key *key); extern struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link, struct key *dest); extern int restrict_link_reject(struct key *keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key); extern int keyring_clear(struct key *keyring); extern key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, const char *description, bool recurse); extern int keyring_add_key(struct key *keyring, struct key *key); extern int keyring_restrict(key_ref_t keyring, const char *type, const char *restriction); extern struct key *key_lookup(key_serial_t id); static inline key_serial_t key_serial(const struct key *key) { return key ? key->serial : 0; } extern void key_set_timeout(struct key *, unsigned); extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, enum key_need_perm need_perm); extern void key_free_user_ns(struct user_namespace *); static inline short key_read_state(const struct key *key) { /* Barrier versus mark_key_instantiated(). */ return smp_load_acquire(&key->state); } /** * key_is_positive - Determine if a key has been positively instantiated * @key: The key to check. * * Return true if the specified key has been positively instantiated, false * otherwise. */ static inline bool key_is_positive(const struct key *key) { return key_read_state(key) == KEY_IS_POSITIVE; } static inline bool key_is_negative(const struct key *key) { return key_read_state(key) < 0; } #define dereference_key_rcu(KEY) \ (rcu_dereference((KEY)->payload.rcu_data0)) #define dereference_key_locked(KEY) \ (rcu_dereference_protected((KEY)->payload.rcu_data0, \ rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ do { \ rcu_assign_pointer((KEY)->payload.rcu_data0, (PAYLOAD)); \ } while (0) #ifdef CONFIG_SYSCTL extern struct ctl_table key_sysctls[]; #endif /* * the userspace interface */ extern int install_thread_keyring_to_cred(struct cred *cred); extern void key_fsuid_changed(struct cred *new_cred); extern void key_fsgid_changed(struct cred *new_cred); extern void key_init(void); #else /* CONFIG_KEYS */ #define key_validate(k) 0 #define key_serial(k) 0 #define key_get(k) ({ NULL; }) #define key_revoke(k) do { } while(0) #define key_invalidate(k) do { } while(0) #define key_put(k) do { } while(0) #define key_ref_put(k) do { } while(0) #define make_key_ref(k, p) NULL #define key_ref_to_ptr(k) NULL #define is_key_possessed(k) 0 #define key_fsuid_changed(c) do { } while(0) #define key_fsgid_changed(c) do { } while(0) #define key_init() do { } while(0) #define key_free_user_ns(ns) do { } while(0) #define key_remove_domain(d) do { } while(0) #endif /* CONFIG_KEYS */ #endif /* __KERNEL__ */ #endif /* _LINUX_KEY_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SMP_H #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ #include <linux/cpumask.h> #include <asm/percpu.h> #include <asm/thread_info.h> #include <asm/cpumask.h> extern int smp_num_siblings; extern unsigned int num_processors; DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); /* cpus sharing the last level cache: */ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); } DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid); #endif struct task_struct; struct smp_ops { void (*smp_prepare_boot_cpu)(void); void (*smp_prepare_cpus)(unsigned max_cpus); void (*smp_cpus_done)(unsigned max_cpus); void (*stop_other_cpus)(int wait); void (*crash_stop_other_cpus)(void); void (*smp_send_reschedule)(int cpu); int (*cpu_up)(unsigned cpu, struct task_struct *tidle); int (*cpu_disable)(void); void (*cpu_die)(unsigned int cpu); void (*play_dead)(void); void (*send_call_func_ipi)(const struct cpumask *mask); void (*send_call_func_single_ipi)(int cpu); }; /* Globals due to paravirt */ extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP extern struct smp_ops smp_ops; static inline void smp_send_stop(void) { smp_ops.stop_other_cpus(0); } static inline void stop_other_cpus(void) { smp_ops.stop_other_cpus(1); } static inline void smp_prepare_boot_cpu(void) { smp_ops.smp_prepare_boot_cpu(); } static inline void smp_prepare_cpus(unsigned int max_cpus) { smp_ops.smp_prepare_cpus(max_cpus); } static inline void smp_cpus_done(unsigned int max_cpus) { smp_ops.smp_cpus_done(max_cpus); } static inline int __cpu_up(unsigned int cpu, struct task_struct *tidle) { return smp_ops.cpu_up(cpu, tidle); } static inline int __cpu_disable(void) { return smp_ops.cpu_disable(); } static inline void __cpu_die(unsigned int cpu) { smp_ops.cpu_die(cpu); } static inline void play_dead(void) { smp_ops.play_dead(); } static inline void smp_send_reschedule(int cpu) { smp_ops.smp_send_reschedule(cpu); } static inline void arch_send_call_function_single_ipi(int cpu) { smp_ops.send_call_func_single_ipi(cpu); } static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { smp_ops.send_call_func_ipi(mask); } void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); void hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); void cond_wakeup_cpu0(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); asmlinkage __visible void smp_reboot_interrupt(void); __visible void smp_reschedule_interrupt(struct pt_regs *regs); __visible void smp_call_function_interrupt(struct pt_regs *regs); __visible void smp_call_function_single_interrupt(struct pt_regs *r); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu) /* * This function is needed by all SMP systems. It must _always_ be valid * from the initial startup. We map APIC_BASE very early in page_setup(), * so this is correct in the x86 case. */ #define raw_smp_processor_id() this_cpu_read(cpu_number) #define __smp_processor_id() __this_cpu_read(cpu_number) #ifdef CONFIG_X86_32 extern int safe_smp_processor_id(void); #else # define safe_smp_processor_id() smp_processor_id() #endif #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) { wbinvd(); return 0; } #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; #ifdef CONFIG_X86_LOCAL_APIC extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ #define hard_smp_processor_id() 0 #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_DEBUG_NMI_SELFTEST extern void nmi_selftest(void); #else #define nmi_selftest() do { } while (0) #endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMP_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BLOCK_BLK_PM_H_ #define _BLOCK_BLK_PM_H_ #include <linux/pm_runtime.h> #ifdef CONFIG_PM static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { if (!q->dev || !blk_queue_pm_only(q)) return 1; /* Nothing to do */ if (pm && q->rpm_status != RPM_SUSPENDED) return 1; /* Request allowed */ pm_request_resume(q->dev); return 0; } static inline void blk_pm_mark_last_busy(struct request *rq) { if (rq->q->dev && !(rq->rq_flags & RQF_PM)) pm_runtime_mark_last_busy(rq->q->dev); } static inline void blk_pm_requeue_request(struct request *rq) { lockdep_assert_held(&rq->q->queue_lock); if (rq->q->dev && !(rq->rq_flags & RQF_PM)) rq->q->nr_pending--; } static inline void blk_pm_add_request(struct request_queue *q, struct request *rq) { lockdep_assert_held(&q->queue_lock); if (q->dev && !(rq->rq_flags & RQF_PM)) q->nr_pending++; } static inline void blk_pm_put_request(struct request *rq) { lockdep_assert_held(&rq->q->queue_lock); if (rq->q->dev && !(rq->rq_flags & RQF_PM)) --rq->q->nr_pending; } #else static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { return 1; } static inline void blk_pm_mark_last_busy(struct request *rq) { } static inline void blk_pm_requeue_request(struct request *rq) { } static inline void blk_pm_add_request(struct request_queue *q, struct request *rq) { } static inline void blk_pm_put_request(struct request *rq) { } #endif #endif /* _BLOCK_BLK_PM_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 /* 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); extern int kstrtobool(const char *s, bool *res); static inline int strtobool(const char *s, bool *res) { return kstrtobool(s, res); } 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 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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_LWTUNNEL_H #define __NET_LWTUNNEL_H 1 #include <linux/lwtunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/route.h> #define LWTUNNEL_HASH_BITS 7 #define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS) /* lw tunnel state flags */ #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0) #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) #define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) enum { LWTUNNEL_XMIT_DONE, LWTUNNEL_XMIT_CONTINUE, }; struct lwtunnel_state { __u16 type; __u16 flags; __u16 headroom; atomic_t refcnt; int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); struct rcu_head rcu; __u8 data[]; }; struct lwtunnel_encap_ops { int (*build_state)(struct net *net, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack); void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); struct module *owner; }; #ifdef CONFIG_LWTUNNEL void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { if (lws) atomic_inc(&lws->refcnt); return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { if (!lws) return; if (atomic_dec_and_test(&lws->refcnt)) lwtstate_free(lws); } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_INPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT)) return true; return false; } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { if ((lwtunnel_xmit_redirect(lwtstate) || lwtunnel_output_redirect(lwtstate)) && lwtstate->headroom < mtu) return lwtstate->headroom; return 0; } int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress); static inline void lwtunnel_set_redirect(struct dst_entry *dst) { if (lwtunnel_output_redirect(dst->lwtstate)) { dst->lwtstate->orig_output = dst->output; dst->output = lwtunnel_output; } if (lwtunnel_input_redirect(dst->lwtstate)) { dst->lwtstate->orig_input = dst->input; dst->input = lwtunnel_input; } } #else static inline void lwtstate_free(struct lwtunnel_state *lws) { } static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline void lwtunnel_set_redirect(struct dst_entry *dst) { } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { return 0; } static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. */ return 0; } static inline int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static inline int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { return 0; } static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { return 0; } static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len) { return NULL; } static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { return 0; } static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_input(struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_xmit(struct sk_buff *skb) { return -EOPNOTSUPP; } #endif /* CONFIG_LWTUNNEL */ #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) #endif /* __NET_LWTUNNEL_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DESC_H #define _ASM_X86_DESC_H #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> #include <asm/fixmap.h> #include <asm/irq_vectors.h> #include <asm/cpu_entry_area.h> #include <linux/smp.h> #include <linux/percpu.h> static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info) { desc->limit0 = info->limit & 0x0ffff; desc->base0 = (info->base_addr & 0x0000ffff); desc->base1 = (info->base_addr & 0x00ff0000) >> 16; desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; /* Set the ACCESS bit so it can be mapped RO */ desc->type |= 1; desc->s = 1; desc->dpl = 0x3; desc->p = info->seg_not_present ^ 1; desc->limit1 = (info->limit & 0xf0000) >> 16; desc->avl = info->useable; desc->d = info->seg_32bit; desc->g = info->limit_in_pages; desc->base2 = (info->base_addr & 0xff000000) >> 24; /* * Don't allow setting of the lm bit. It would confuse * user_64bit_mode and would get overridden by sysret anyway. */ desc->l = 0; } struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); /* Provide the original GDT */ static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) { return per_cpu(gdt_page, cpu).gdt; } /* Provide the current original GDT */ static inline struct desc_struct *get_current_gdt_rw(void) { return this_cpu_ptr(&gdt_page)->gdt; } /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ static inline struct desc_struct *get_current_gdt_ro(void) { return get_cpu_gdt_ro(smp_processor_id()); } /* Provide the physical address of the GDT page. */ static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) { return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); } static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, unsigned dpl, unsigned ist, unsigned seg) { gate->offset_low = (u16) func; gate->bits.p = 1; gate->bits.dpl = dpl; gate->bits.zero = 0; gate->bits.type = type; gate->offset_middle = (u16) (func >> 16); #ifdef CONFIG_X86_64 gate->segment = __KERNEL_CS; gate->bits.ist = ist; gate->reserved = 0; gate->offset_high = (u32) (func >> 32); #else gate->segment = seg; gate->bits.ist = 0; #endif } static inline int desc_empty(const void *ptr) { const u32 *desc = ptr; return !(desc[0] | desc[1]); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define load_TR_desc() native_load_tr_desc() #define load_gdt(dtr) native_load_gdt(dtr) #define load_idt(dtr) native_load_idt(dtr) #define load_tr(tr) asm volatile("ltr %0"::"m" (tr)) #define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) #define store_gdt(dtr) native_store_gdt(dtr) #define store_tr(tr) (tr = native_store_tr()) #define load_TLS(t, cpu) native_load_tls(t, cpu) #define set_ldt native_set_ldt #define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc) #define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type) #define write_idt_entry(dt, entry, g) native_write_idt_entry(dt, entry, g) static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { } static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { } #endif /* CONFIG_PARAVIRT_XXL */ #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) { memcpy(&idt[entry], gate, sizeof(*gate)); } static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc) { memcpy(&ldt[entry], desc, 8); } static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type) { unsigned int size; switch (type) { case DESC_TSS: size = sizeof(tss_desc); break; case DESC_LDT: size = sizeof(ldt_desc); break; default: size = sizeof(*gdt); break; } memcpy(&gdt[entry], desc, size); } static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size) { struct ldttss_desc *desc = d; memset(desc, 0, sizeof(*desc)); desc->limit0 = (u16) size; desc->base0 = (u16) addr; desc->base1 = (addr >> 16) & 0xFF; desc->type = type; desc->p = 1; desc->limit1 = (size >> 16) & 0xF; desc->base2 = (addr >> 24) & 0xFF; #ifdef CONFIG_X86_64 desc->base3 = (u32) (addr >> 32); #endif } static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } #define set_tss_desc(cpu, addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr) static inline void native_set_ldt(const void *addr, unsigned int entries) { if (likely(entries == 0)) asm volatile("lldt %w0"::"q" (0)); else { unsigned cpu = smp_processor_id(); ldt_desc ldt; set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, entries * LDT_ENTRY_SIZE - 1); write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, &ldt, DESC_LDT); asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); } } static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); } static __always_inline void native_load_idt(const struct desc_ptr *dtr) { asm volatile("lidt %0"::"m" (*dtr)); } static inline void native_store_gdt(struct desc_ptr *dtr) { asm volatile("sgdt %0":"=m" (*dtr)); } static inline void store_idt(struct desc_ptr *dtr) { asm volatile("sidt %0":"=m" (*dtr)); } /* * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is * a read-only remapping. To prevent a page fault, the GDT is switched to the * original writeable version when needed. */ #ifdef CONFIG_X86_64 static inline void native_load_tr_desc(void) { struct desc_ptr gdt; int cpu = raw_smp_processor_id(); bool restore = 0; struct desc_struct *fixmap_gdt; native_store_gdt(&gdt); fixmap_gdt = get_cpu_gdt_ro(cpu); /* * If the current GDT is the read-only fixmap, swap to the original * writeable version. Swap back at the end. */ if (gdt.address == (unsigned long)fixmap_gdt) { load_direct_gdt(cpu); restore = 1; } asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); if (restore) load_fixmap_gdt(cpu); } #else static inline void native_load_tr_desc(void) { asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } #endif static inline unsigned long native_store_tr(void) { unsigned long tr; asm volatile("str %0":"=r" (tr)); return tr; } static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) { struct desc_struct *gdt = get_cpu_gdt_rw(cpu); unsigned int i; for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } DECLARE_PER_CPU(bool, __tss_limit_invalid); static inline void force_reload_TR(void) { struct desc_struct *d = get_current_gdt_rw(); tss_desc tss; memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); /* * LTR requires an available TSS, and the TSS is currently * busy. Make it be available so that LTR will work. */ tss.type = DESC_TSS; write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); load_TR_desc(); this_cpu_write(__tss_limit_invalid, false); } /* * Call this if you need the TSS limit to be correct, which should be the case * if and only if you have TIF_IO_BITMAP set or you're switching to a task * with TIF_IO_BITMAP set. */ static inline void refresh_tss_limit(void) { DEBUG_LOCKS_WARN_ON(preemptible()); if (unlikely(this_cpu_read(__tss_limit_invalid))) force_reload_TR(); } /* * If you do something evil that corrupts the cached TSS limit (I'm looking * at you, VMX exits), call this function. * * The optimization here is that the TSS limit only matters for Linux if the * IO bitmap is in use. If the TSS limit gets forced to its minimum value, * everything works except that IO bitmap will be ignored and all CPL 3 IO * instructions will #GP, which is exactly what we want for normal tasks. */ static inline void invalidate_tss_limit(void) { DEBUG_LOCKS_WARN_ON(preemptible()); if (unlikely(test_thread_flag(TIF_IO_BITMAP))) force_reload_TR(); else this_cpu_write(__tss_limit_invalid, true); } /* This intentionally ignores lm, since 32-bit apps don't have that field. */ #define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ (info)->read_exec_only == 1 && \ (info)->seg_32bit == 0 && \ (info)->limit_in_pages == 0 && \ (info)->seg_not_present == 1 && \ (info)->useable == 0) /* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ static inline bool LDT_zero(const struct user_desc *info) { return (info->base_addr == 0 && info->limit == 0 && info->contents == 0 && info->read_exec_only == 0 && info->seg_32bit == 0 && info->limit_in_pages == 0 && info->seg_not_present == 0 && info->useable == 0); } static inline void clear_LDT(void) { set_ldt(NULL, 0); } static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); } static inline void set_desc_base(struct desc_struct *desc, unsigned long base) { desc->base0 = base & 0xffff; desc->base1 = (base >> 16) & 0xff; desc->base2 = (base >> 24) & 0xff; } static inline unsigned long get_desc_limit(const struct desc_struct *desc) { return desc->limit0 | (desc->limit1 << 16); } static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) { desc->limit0 = limit & 0xffff; desc->limit1 = (limit >> 16) & 0xf; } void alloc_intr_gate(unsigned int n, const void *addr); static inline void init_idt_data(struct idt_data *data, unsigned int n, const void *addr) { BUG_ON(n > 0xFF); memset(data, 0, sizeof(*data)); data->vector = n; data->addr = addr; data->segment = __KERNEL_CS; data->bits.type = GATE_INTERRUPT; data->bits.p = 1; } static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) { unsigned long addr = (unsigned long) d->addr; gate->offset_low = (u16) addr; gate->segment = (u16) d->segment; gate->bits = d->bits; gate->offset_middle = (u16) (addr >> 16); #ifdef CONFIG_X86_64 gate->offset_high = (u32) (addr >> 32); gate->reserved = 0; #endif } extern unsigned long system_vectors[]; extern void load_current_idt(void); extern void idt_setup_early_handler(void); extern void idt_setup_early_traps(void); extern void idt_setup_traps(void); extern void idt_setup_apic_and_irq_gates(void); extern bool idt_is_f00f_address(unsigned long address); #ifdef CONFIG_X86_64 extern void idt_setup_early_pf(void); extern void idt_setup_ist_traps(void); #else static inline void idt_setup_early_pf(void) { } static inline void idt_setup_ist_traps(void) { } #endif extern void idt_invalidate(void *addr); #endif /* _ASM_X86_DESC_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_CRASH_DUMP_H #define LINUX_CRASH_DUMP_H #include <linux/kexec.h> #include <linux/proc_fs.h> #include <linux/elf.h> #include <linux/pgtable.h> #include <uapi/linux/vmcore.h> #include <linux/pgtable.h> /* for pgprot_t */ #ifdef CONFIG_CRASH_DUMP #define ELFCORE_ADDR_MAX (-1ULL) #define ELFCORE_ADDR_ERR (-2ULL) extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); extern void elfcorehdr_free(unsigned long long addr); extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf); void vmcore_cleanup(void); /* Architecture code defines this if there are other possible ELF * machine types, e.g. on bi-arch capable hardware. */ #ifndef vmcore_elf_check_arch_cross #define vmcore_elf_check_arch_cross(x) 0 #endif /* * Architecture code can redefine this if there are any special checks * needed for 32-bit ELF or 64-bit ELF vmcores. In case of 32-bit * only architecture, vmcore_elf64_check_arch can be set to zero. */ #ifndef vmcore_elf32_check_arch #define vmcore_elf32_check_arch(x) elf_check_arch(x) #endif #ifndef vmcore_elf64_check_arch #define vmcore_elf64_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) #endif /* * is_kdump_kernel() checks whether this kernel is booting after a panic of * previous kernel or not. This is determined by checking if previous kernel * has passed the elf core header address on command line. * * This is not just a test if CONFIG_CRASH_DUMP is enabled or not. It will * return true if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic * of previous kernel. */ static inline bool is_kdump_kernel(void) { return elfcorehdr_addr != ELFCORE_ADDR_MAX; } /* is_vmcore_usable() checks if the kernel is booting after a panic and * the vmcore region is usable. * * This makes use of the fact that due to alignment -2ULL is not * a valid pointer, much in the vain of IS_ERR(), except * dealing directly with an unsigned long long rather than a pointer. */ static inline int is_vmcore_usable(void) { return is_kdump_kernel() && elfcorehdr_addr != ELFCORE_ADDR_ERR ? 1 : 0; } /* vmcore_unusable() marks the vmcore as unusable, * without disturbing the logic of is_kdump_kernel() */ static inline void vmcore_unusable(void) { if (is_kdump_kernel()) elfcorehdr_addr = ELFCORE_ADDR_ERR; } #define HAVE_OLDMEM_PFN_IS_RAM 1 extern int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)); extern void unregister_oldmem_pfn_is_ram(void); #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ /* Device Dump information to be filled by drivers */ struct vmcoredd_data { char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */ unsigned int size; /* Size of the dump */ /* Driver's registered callback to be invoked to collect dump */ int (*vmcoredd_callback)(struct vmcoredd_data *data, void *buf); }; #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP int vmcore_add_device_dump(struct vmcoredd_data *data); #else static inline int vmcore_add_device_dump(struct vmcoredd_data *data) { return -EOPNOTSUPP; } #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #ifdef CONFIG_PROC_VMCORE ssize_t read_from_oldmem(char *buf, size_t count, u64 *ppos, int userbuf, bool encrypted); #else static inline ssize_t read_from_oldmem(char *buf, size_t count, u64 *ppos, int userbuf, bool encrypted) { return -EOPNOTSUPP; } #endif /* CONFIG_PROC_VMCORE */ #endif /* LINUX_CRASHDUMP_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2009-2019 Christoph Hellwig * * NOTE: none of these tracepoints shall be consider a stable kernel ABI * as they can change at any time. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM iomap #if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _IOMAP_TRACE_H #include <linux/tracepoint.h> struct inode; DECLARE_EVENT_CLASS(iomap_readpage_class, TP_PROTO(struct inode *inode, int nr_pages), TP_ARGS(inode, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(int, nr_pages) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_pages = nr_pages; ), TP_printk("dev %d:%d ino 0x%llx nr_pages %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_pages) ) #define DEFINE_READPAGE_EVENT(name) \ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, unsigned long off, unsigned int len), TP_ARGS(inode, off, len), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, size) __field(unsigned long, offset) __field(unsigned int, length) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->size = i_size_read(inode); __entry->offset = off; __entry->length = len; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset %lx " "length %x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->length) ) #define DEFINE_RANGE_EVENT(name) \ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, unsigned long off, unsigned int len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writepage); DEFINE_RANGE_EVENT(iomap_releasepage); DEFINE_RANGE_EVENT(iomap_invalidatepage); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ { IOMAP_DELALLOC, "DELALLOC" }, \ { IOMAP_MAPPED, "MAPPED" }, \ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ { IOMAP_INLINE, "INLINE" } #define IOMAP_FLAGS_STRINGS \ { IOMAP_WRITE, "WRITE" }, \ { IOMAP_ZERO, "ZERO" }, \ { IOMAP_REPORT, "REPORT" }, \ { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ { IOMAP_F_DIRTY, "DIRTY" }, \ { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr %lld offset %lld " "length %llu type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) ) #define DEFINE_IOMAP_EVENT(name) \ DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_apply_dstmap); DEFINE_IOMAP_EVENT(iomap_apply_srcmap); TRACE_EVENT(iomap_apply, TP_PROTO(struct inode *inode, loff_t pos, loff_t length, unsigned int flags, const void *ops, void *actor, unsigned long caller), TP_ARGS(inode, pos, length, flags, ops, actor, caller), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, pos) __field(loff_t, length) __field(unsigned int, flags) __field(const void *, ops) __field(void *, actor) __field(unsigned long, caller) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->length = length; __entry->flags = flags; __entry->ops = ops; __entry->actor = actor; __entry->caller = caller; ), TP_printk("dev %d:%d ino 0x%llx pos %lld length %lld flags %s (0x%x) " "ops %ps caller %pS actor %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->length, __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), __entry->flags, __entry->ops, (void *)__entry->caller, __entry->actor) ); #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE trace #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 /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/relay.h * * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com) * * CONFIG_RELAY definitions and declarations */ #ifndef _LINUX_RELAY_H #define _LINUX_RELAY_H #include <linux/types.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/irq_work.h> #include <linux/bug.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/kref.h> #include <linux/percpu.h> /* * Tracks changes to rchan/rchan_buf structs */ #define RELAYFS_CHANNEL_VERSION 7 /* * Per-cpu relay channel buffer */ struct rchan_buf { void *start; /* start of channel buffer */ void *data; /* start of current sub-buffer */ size_t offset; /* current offset into sub-buffer */ size_t subbufs_produced; /* count of sub-buffers produced */ size_t subbufs_consumed; /* count of sub-buffers consumed */ struct rchan *chan; /* associated channel */ wait_queue_head_t read_wait; /* reader wait queue */ struct irq_work wakeup_work; /* reader wakeup */ struct dentry *dentry; /* channel file dentry */ struct kref kref; /* channel buffer refcount */ struct page **page_array; /* array of current buffer pages */ unsigned int page_count; /* number of current buffer pages */ unsigned int finalized; /* buffer has been finalized */ size_t *padding; /* padding counts per sub-buffer */ size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ } ____cacheline_aligned; /* * Relay channel data structure */ struct rchan { u32 version; /* the version of this struct */ size_t subbuf_size; /* sub-buffer size */ size_t n_subbufs; /* number of sub-buffers per buffer */ size_t alloc_size; /* total buffer size allocated */ struct rchan_callbacks *cb; /* client callbacks */ struct kref kref; /* channel refcount */ void *private_data; /* for user-defined data */ size_t last_toobig; /* tried to log event > subbuf size */ struct rchan_buf * __percpu *buf; /* per-cpu channel buffers */ int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ struct dentry *parent; /* parent dentry passed to open */ int has_base_filename; /* has a filename associated? */ char base_filename[NAME_MAX]; /* saved base filename */ }; /* * Relay channel client callbacks */ struct rchan_callbacks { /* * subbuf_start - called on buffer-switch to a new sub-buffer * @buf: the channel buffer containing the new sub-buffer * @subbuf: the start of the new sub-buffer * @prev_subbuf: the start of the previous sub-buffer * @prev_padding: unused space at the end of previous sub-buffer * * The client should return 1 to continue logging, 0 to stop * logging. * * NOTE: subbuf_start will also be invoked when the buffer is * created, so that the first sub-buffer can be initialized * if necessary. In this case, prev_subbuf will be NULL. * * NOTE: the client can reserve bytes at the beginning of the new * sub-buffer by calling subbuf_start_reserve() in this callback. */ int (*subbuf_start) (struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding); /* * buf_mapped - relay buffer mmap notification * @buf: the channel buffer * @filp: relay file pointer * * Called when a relay file is successfully mmapped */ void (*buf_mapped)(struct rchan_buf *buf, struct file *filp); /* * buf_unmapped - relay buffer unmap notification * @buf: the channel buffer * @filp: relay file pointer * * Called when a relay file is successfully unmapped */ void (*buf_unmapped)(struct rchan_buf *buf, struct file *filp); /* * create_buf_file - create file to represent a relay channel buffer * @filename: the name of the file to create * @parent: the parent of the file to create * @mode: the mode of the file to create * @buf: the channel buffer * @is_global: outparam - set non-zero if the buffer should be global * * Called during relay_open(), once for each per-cpu buffer, * to allow the client to create a file to be used to * represent the corresponding channel buffer. If the file is * created outside of relay, the parent must also exist in * that filesystem. * * The callback should return the dentry of the file created * to represent the relay buffer. * * Setting the is_global outparam to a non-zero value will * cause relay_open() to create a single global buffer rather * than the default set of per-cpu buffers. * * See Documentation/filesystems/relay.rst for more info. */ struct dentry *(*create_buf_file)(const char *filename, struct dentry *parent, umode_t mode, struct rchan_buf *buf, int *is_global); /* * remove_buf_file - remove file representing a relay channel buffer * @dentry: the dentry of the file to remove * * Called during relay_close(), once for each per-cpu buffer, * to allow the client to remove a file used to represent a * channel buffer. * * The callback should return 0 if successful, negative if not. */ int (*remove_buf_file)(struct dentry *dentry); }; /* * CONFIG_RELAY kernel API, kernel/relay.c */ struct rchan *relay_open(const char *base_filename, struct dentry *parent, size_t subbuf_size, size_t n_subbufs, struct rchan_callbacks *cb, void *private_data); extern int relay_late_setup_files(struct rchan *chan, const char *base_filename, struct dentry *parent); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); extern void relay_subbufs_consumed(struct rchan *chan, unsigned int cpu, size_t consumed); extern void relay_reset(struct rchan *chan); extern int relay_buf_full(struct rchan_buf *buf); extern size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length); /** * relay_write - write data into the channel * @chan: relay channel * @data: data to be written * @length: number of bytes to write * * Writes data into the current cpu's channel buffer. * * Protects the buffer by disabling interrupts. Use this * if you might be logging from interrupt context. Try * __relay_write() if you know you won't be logging from * interrupt context. */ static inline void relay_write(struct rchan *chan, const void *data, size_t length) { unsigned long flags; struct rchan_buf *buf; local_irq_save(flags); buf = *this_cpu_ptr(chan->buf); if (unlikely(buf->offset + length > chan->subbuf_size)) length = relay_switch_subbuf(buf, length); memcpy(buf->data + buf->offset, data, length); buf->offset += length; local_irq_restore(flags); } /** * __relay_write - write data into the channel * @chan: relay channel * @data: data to be written * @length: number of bytes to write * * Writes data into the current cpu's channel buffer. * * Protects the buffer by disabling preemption. Use * relay_write() if you might be logging from interrupt * context. */ static inline void __relay_write(struct rchan *chan, const void *data, size_t length) { struct rchan_buf *buf; buf = *get_cpu_ptr(chan->buf); if (unlikely(buf->offset + length > buf->chan->subbuf_size)) length = relay_switch_subbuf(buf, length); memcpy(buf->data + buf->offset, data, length); buf->offset += length; put_cpu_ptr(chan->buf); } /** * relay_reserve - reserve slot in channel buffer * @chan: relay channel * @length: number of bytes to reserve * * Returns pointer to reserved slot, NULL if full. * * Reserves a slot in the current cpu's channel buffer. * Does not protect the buffer at all - caller must provide * appropriate synchronization. */ static inline void *relay_reserve(struct rchan *chan, size_t length) { void *reserved = NULL; struct rchan_buf *buf = *get_cpu_ptr(chan->buf); if (unlikely(buf->offset + length > buf->chan->subbuf_size)) { length = relay_switch_subbuf(buf, length); if (!length) goto end; } reserved = buf->data + buf->offset; buf->offset += length; end: put_cpu_ptr(chan->buf); return reserved; } /** * subbuf_start_reserve - reserve bytes at the start of a sub-buffer * @buf: relay channel buffer * @length: number of bytes to reserve * * Helper function used to reserve bytes at the beginning of * a sub-buffer in the subbuf_start() callback. */ static inline void subbuf_start_reserve(struct rchan_buf *buf, size_t length) { BUG_ON(length >= buf->chan->subbuf_size - 1); buf->offset = length; } /* * exported relay file operations, kernel/relay.c */ extern const struct file_operations relay_file_operations; #ifdef CONFIG_RELAY int relay_prepare_cpu(unsigned int cpu); #else #define relay_prepare_cpu NULL #endif #endif /* _LINUX_RELAY_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Routines to manage notifier chains for passing status changes to any * interested routines. We need this instead of hard coded call lists so * that modules can poke their nose into the innards. The network devices * needed them so here they are for the rest of you. * * Alan Cox <Alan.Cox@linux.org> */ #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include <linux/errno.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/srcu.h> /* * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. * Blocking notifier chains: Chain callbacks run in process context. * Callouts are allowed to block. * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. * SRCU notifier chains: A variant of blocking notifier chains, with * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, * but blocking_notifier_chain_register() and srcu_notifier_chain_register() * must be called from a process context. Ditto for the corresponding * _unregister() routines. * * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), * and srcu_notifier_chain_unregister() _must not_ be called from within * the call chain. * * SRCU notifier chains are an alternative form of blocking notifier chains. * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for * protection of the chain links. This means there is _very_ low overhead * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very * often but notifier_blocks will seldom be removed. */ struct notifier_block; typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); struct notifier_block { notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; struct notifier_block __rcu *head; }; struct raw_notifier_head { struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_struct srcu; struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ init_rwsem(&(name)->rwsem); \ (name)->head = NULL; \ } while (0) #define RAW_INIT_NOTIFIER_HEAD(name) do { \ (name)->head = NULL; \ } while (0) /* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ ATOMIC_NOTIFIER_INIT(name) #define BLOCKING_NOTIFIER_HEAD(name) \ struct blocking_notifier_head name = \ BLOCKING_NOTIFIER_INIT(name) #define RAW_NOTIFIER_HEAD(name) \ struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) #else #define _SRCU_NOTIFIER_HEAD(name, mod) \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name) #endif #define SRCU_NOTIFIER_HEAD(name) \ _SRCU_NOTIFIER_HEAD(name, /* not static */) #define SRCU_NOTIFIER_HEAD_STATIC(name) \ _SRCU_NOTIFIER_HEAD(name, static) #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ #define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ #define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK) /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err); return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ static inline int notifier_to_errno(int ret) { ret &= ~NOTIFY_STOP_MASK; return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0; } /* * Declared notifiers so far. I can imagine quite a few more chains * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ /* reboot notifiers are defined in include/linux/reboot.h. */ /* Hibernation and suspend events are defined in include/linux/suspend.h. */ /* Virtual Terminal events are defined in include/linux/vt.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and * KBD_KEYSYM. */ #define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ #define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ #define KBD_UNICODE 0x0003 /* Keyboard unicode */ #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ extern struct blocking_notifier_head reboot_notifier_list; #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Internal header to deal with irq_desc->status which will be renamed * to irq_desc->settings. */ enum { _IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS, _IRQ_PER_CPU = IRQ_PER_CPU, _IRQ_LEVEL = IRQ_LEVEL, _IRQ_NOPROBE = IRQ_NOPROBE, _IRQ_NOREQUEST = IRQ_NOREQUEST, _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, _IRQ_IS_POLLED = IRQ_IS_POLLED, _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQ_HIDDEN = IRQ_HIDDEN, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; #define IRQ_PER_CPU GOT_YOU_MORON #define IRQ_NO_BALANCING GOT_YOU_MORON #define IRQ_LEVEL GOT_YOU_MORON #define IRQ_NOPROBE GOT_YOU_MORON #define IRQ_NOREQUEST GOT_YOU_MORON #define IRQ_NOTHREAD GOT_YOU_MORON #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON #define IRQ_IS_POLLED GOT_YOU_MORON #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #define IRQ_HIDDEN GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON static inline void irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) { desc->status_use_accessors &= ~(clr & _IRQF_MODIFY_MASK); desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); } static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU; } static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU_DEVID; } static inline void irq_settings_set_per_cpu(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_PER_CPU; } static inline void irq_settings_set_no_balancing(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NO_BALANCING; } static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NO_BALANCING; } static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc) { return desc->status_use_accessors & IRQ_TYPE_SENSE_MASK; } static inline void irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask) { desc->status_use_accessors &= ~IRQ_TYPE_SENSE_MASK; desc->status_use_accessors |= mask & IRQ_TYPE_SENSE_MASK; } static inline bool irq_settings_is_level(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_LEVEL; } static inline void irq_settings_clr_level(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_LEVEL; } static inline void irq_settings_set_level(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_LEVEL; } static inline bool irq_settings_can_request(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOREQUEST); } static inline void irq_settings_clr_norequest(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOREQUEST; } static inline void irq_settings_set_norequest(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOREQUEST; } static inline bool irq_settings_can_thread(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOTHREAD); } static inline void irq_settings_clr_nothread(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOTHREAD; } static inline void irq_settings_set_nothread(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOTHREAD; } static inline bool irq_settings_can_probe(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOPROBE); } static inline void irq_settings_clr_noprobe(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOPROBE; } static inline void irq_settings_set_noprobe(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOPROBE; } static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_MOVE_PCNTXT; } static inline bool irq_settings_can_autoenable(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOAUTOEN); } static inline bool irq_settings_is_nested_thread(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NESTED_THREAD; } static inline bool irq_settings_is_polled(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_IS_POLLED; } static inline bool irq_settings_disable_unlazy(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_DISABLE_UNLAZY; } static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY; } static inline bool irq_settings_is_hidden(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_HIDDEN; }
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 // 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 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 /* SPDX-License-Identifier: GPL-2.0 OR MIT */ #ifndef __LINUX_OVERFLOW_H #define __LINUX_OVERFLOW_H #include <linux/compiler.h> #include <linux/limits.h> /* * In the fallback code below, we need to compute the minimum and * maximum values representable in a given type. These macros may also * be useful elsewhere, so we provide them outside the * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. * * It would seem more obvious to do something like * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) * * Unfortunately, the middle expressions, strictly speaking, have * undefined behaviour, and at least some versions of gcc warn about * the type_max expression (but not if -fsanitize=undefined is in * effect; in that case, the warning is deferred to runtime...). * * The slightly excessive casting in type_min is to make sure the * macros also produce sensible values for the exotic type _Bool. [The * overflow checkers only almost work for _Bool, but that's * a-feature-not-a-bug, since people shouldn't be doing arithmetic on * _Bools. Besides, the gcc builtins don't allow _Bool* as third * argument.] * * Idea stolen from * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html - * credit to Christian Biere. */ #define is_signed_type(type) (((type)(-1)) < (type)1) #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) /* * Avoids triggering -Wtype-limits compilation warning, * while using unsigned data types to check a < 0. */ #define is_non_negative(a) ((a) > 0 || (a) == 0) #define is_negative(a) (!(is_non_negative(a))) /* * Allows for effectively applying __must_check to a macro so we can have * both the type-agnostic benefits of the macros while also being able to * enforce that the return value is, in fact, checked. */ static inline bool __must_check __must_check_overflow(bool overflow) { return unlikely(overflow); } #ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() * macros), whereas gcc's type-generic overflow checkers accept * different types. Hence we don't just make check_add_overflow an * alias for __builtin_add_overflow, but add type checks similar to * below. */ #define check_add_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_add_overflow(__a, __b, __d); \ })) #define check_sub_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_sub_overflow(__a, __b, __d); \ })) #define check_mul_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_mul_overflow(__a, __b, __d); \ })) #else /* Checking for unsigned overflow is relatively easy without causing UB. */ #define __unsigned_add_overflow(a, b, d) ({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ *__d = __a + __b; \ *__d < __a; \ }) #define __unsigned_sub_overflow(a, b, d) ({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ *__d = __a - __b; \ __a < __b; \ }) /* * If one of a or b is a compile-time constant, this avoids a division. */ #define __unsigned_mul_overflow(a, b, d) ({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ *__d = __a * __b; \ __builtin_constant_p(__b) ? \ __b > 0 && __a > type_max(typeof(__a)) / __b : \ __a > 0 && __b > type_max(typeof(__b)) / __a; \ }) /* * For signed types, detecting overflow is much harder, especially if * we want to avoid UB. But the interface of these macros is such that * we must provide a result in *d, and in fact we must produce the * result promised by gcc's builtins, which is simply the possibly * wrapped-around value. Fortunately, we can just formally do the * operations in the widest relevant unsigned type (u64) and then * truncate the result - gcc is smart enough to generate the same code * with and without the (u64) casts. */ /* * Adding two signed integers can overflow only if they have the same * sign, and overflow has happened iff the result has the opposite * sign. */ #define __signed_add_overflow(a, b, d) ({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ *__d = (u64)__a + (u64)__b; \ (((~(__a ^ __b)) & (*__d ^ __a)) \ & type_min(typeof(__a))) != 0; \ }) /* * Subtraction is similar, except that overflow can now happen only * when the signs are opposite. In this case, overflow has happened if * the result has the opposite sign of a. */ #define __signed_sub_overflow(a, b, d) ({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ *__d = (u64)__a - (u64)__b; \ ((((__a ^ __b)) & (*__d ^ __a)) \ & type_min(typeof(__a))) != 0; \ }) /* * Signed multiplication is rather hard. gcc always follows C99, so * division is truncated towards 0. This means that we can write the * overflow check like this: * * (a > 0 && (b > MAX/a || b < MIN/a)) || * (a < -1 && (b > MIN/a || b < MAX/a) || * (a == -1 && b == MIN) * * The redundant casts of -1 are to silence an annoying -Wtype-limits * (included in -Wextra) warning: When the type is u8 or u16, the * __b_c_e in check_mul_overflow obviously selects * __unsigned_mul_overflow, but unfortunately gcc still parses this * code and warns about the limited range of __b. */ #define __signed_mul_overflow(a, b, d) ({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ typeof(a) __tmax = type_max(typeof(a)); \ typeof(a) __tmin = type_min(typeof(a)); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ *__d = (u64)__a * (u64)__b; \ (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ (__b == (typeof(__b))-1 && __a == __tmin); \ }) #define check_add_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_add_overflow(a, b, d), \ __unsigned_add_overflow(a, b, d))) #define check_sub_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_sub_overflow(a, b, d), \ __unsigned_sub_overflow(a, b, d))) #define check_mul_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_mul_overflow(a, b, d), \ __unsigned_mul_overflow(a, b, d))) #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ /** check_shl_overflow() - Calculate a left-shifted value and check overflow * * @a: Value to be shifted * @s: How many bits left to shift * @d: Pointer to where to store the result * * Computes *@d = (@a << @s) * * Returns true if '*d' cannot hold the result or when 'a << s' doesn't * make sense. Example conditions: * - 'a << s' causes bits to be lost when stored in *d. * - 's' is garbage (e.g. negative) or so large that the result of * 'a << s' is guaranteed to be 0. * - 'a' is negative. * - 'a << s' sets the sign bit, if any, in '*d'. * * '*d' will hold the results of the attempted shift, but is not * considered "safe for use" if false is returned. */ #define check_shl_overflow(a, s, d) __must_check_overflow(({ \ typeof(a) _a = a; \ typeof(s) _s = s; \ typeof(d) _d = d; \ u64 _a_full = _a; \ unsigned int _to_shift = \ is_non_negative(_s) && _s < 8 * sizeof(*d) ? _s : 0; \ *_d = (_a_full << _to_shift); \ (_to_shift != _s || is_negative(*_d) || is_negative(_a) || \ (*_d >> _to_shift) != _a); \ })) /** * array_size() - Calculate size of 2-dimensional array. * * @a: dimension one * @b: dimension two * * Calculates size of 2-dimensional array: @a * @b. * * Returns: number of bytes needed to represent the array or SIZE_MAX on * overflow. */ static inline __must_check size_t array_size(size_t a, size_t b) { size_t bytes; if (check_mul_overflow(a, b, &bytes)) return SIZE_MAX; return bytes; } /** * array3_size() - Calculate size of 3-dimensional array. * * @a: dimension one * @b: dimension two * @c: dimension three * * Calculates size of 3-dimensional array: @a * @b * @c. * * Returns: number of bytes needed to represent the array or SIZE_MAX on * overflow. */ static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) { size_t bytes; if (check_mul_overflow(a, b, &bytes)) return SIZE_MAX; if (check_mul_overflow(bytes, c, &bytes)) return SIZE_MAX; return bytes; } /* * Compute a*b+c, returning SIZE_MAX on overflow. Internal helper for * struct_size() below. */ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) { size_t bytes; if (check_mul_overflow(a, b, &bytes)) return SIZE_MAX; if (check_add_overflow(bytes, c, &bytes)) return SIZE_MAX; return bytes; } /** * struct_size() - Calculate size of structure with trailing array. * @p: Pointer to the structure. * @member: Name of the array member. * @count: Number of elements in the array. * * Calculates size of memory needed for structure @p followed by an * array of @count number of @member elements. * * Return: number of bytes needed or SIZE_MAX on overflow. */ #define struct_size(p, member, count) \ __ab_c_size(count, \ sizeof(*(p)->member) + __must_be_array((p)->member),\ sizeof(*(p))) /** * flex_array_size() - Calculate size of a flexible array member * within an enclosing structure. * * @p: Pointer to the structure. * @member: Name of the flexible array member. * @count: Number of elements in the array. * * Calculates size of a flexible array of @count number of @member * elements, at the end of structure @p. * * Return: number of bytes needed or SIZE_MAX on overflow. */ #define flex_array_size(p, member, count) \ array_size(count, \ sizeof(*(p)->member) + __must_be_array((p)->member)) #endif /* __LINUX_OVERFLOW_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_COMPACTION_H #define _LINUX_COMPACTION_H /* * Determines how hard direct compaction should try to succeed. * Lower value means higher priority, analogically to reclaim priority. */ enum compact_priority { COMPACT_PRIO_SYNC_FULL, MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL, COMPACT_PRIO_SYNC_LIGHT, MIN_COMPACT_COSTLY_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, COMPACT_PRIO_ASYNC, INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC }; /* Return values for compact_zone() and try_to_compact_pages() */ /* When adding new states, please adjust include/trace/events/compaction.h */ enum compact_result { /* For more detailed tracepoint output - internal to compaction */ COMPACT_NOT_SUITABLE_ZONE, /* * compaction didn't start as it was not possible or direct reclaim * was more suitable */ COMPACT_SKIPPED, /* compaction didn't start as it was deferred due to past failures */ COMPACT_DEFERRED, /* For more detailed tracepoint output - internal to compaction */ COMPACT_NO_SUITABLE_PAGE, /* compaction should continue to another pageblock */ COMPACT_CONTINUE, /* * The full zone was compacted scanned but wasn't successfull to compact * suitable pages. */ COMPACT_COMPLETE, /* * direct compaction has scanned part of the zone but wasn't successfull * to compact suitable pages. */ COMPACT_PARTIAL_SKIPPED, /* compaction terminated prematurely due to lock contentions */ COMPACT_CONTENDED, /* * direct compaction terminated after concluding that the allocation * should now succeed */ COMPACT_SUCCESS, }; struct alloc_context; /* in mm/internal.h */ /* * Number of free order-0 pages that should be available above given watermark * to make sure compaction has reasonable chance of not running out of free * pages that it needs to isolate as migration target during its work. */ static inline unsigned long compact_gap(unsigned int order) { /* * Although all the isolations for migration are temporary, compaction * free scanner may have up to 1 << order pages on its list and then * try to split an (order - 1) free page. At that point, a gap of * 1 << order might not be enough, so it's safer to require twice that * amount. Note that the number of pages on the list is also * effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum * that the migrate scanner can have isolated on migrate list, and free * scanner is only invoked when the number of isolated free pages is * lower than that. But it's not worth to complicate the formula here * as a bigger gap for higher orders than strictly necessary can also * improve chances of compaction success. */ return 2UL << order; } #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, int highest_zoneidx); extern void defer_compaction(struct zone *zone, int order); extern bool compaction_deferred(struct zone *zone, int order); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); extern bool compaction_restarting(struct zone *zone, int order); /* Compaction has made some progress and retrying makes sense */ static inline bool compaction_made_progress(enum compact_result result) { /* * Even though this might sound confusing this in fact tells us * that the compaction successfully isolated and migrated some * pageblocks. */ if (result == COMPACT_SUCCESS) return true; return false; } /* Compaction has failed and it doesn't make much sense to keep retrying. */ static inline bool compaction_failed(enum compact_result result) { /* All zones were scanned completely and still not result. */ if (result == COMPACT_COMPLETE) return true; return false; } /* Compaction needs reclaim to be performed first, so it can continue. */ static inline bool compaction_needs_reclaim(enum compact_result result) { /* * Compaction backed off due to watermark checks for order-0 * so the regular reclaim has to try harder and reclaim something. */ if (result == COMPACT_SKIPPED) return true; return false; } /* * Compaction has backed off for some reason after doing some work or none * at all. It might be throttling or lock contention. Retrying might be still * worthwhile, but with a higher priority if allowed. */ static inline bool compaction_withdrawn(enum compact_result result) { /* * If compaction is deferred for high-order allocations, it is * because sync compaction recently failed. If this is the case * and the caller requested a THP allocation, we do not want * to heavily disrupt the system, so we fail the allocation * instead of entering direct reclaim. */ if (result == COMPACT_DEFERRED) return true; /* * If compaction in async mode encounters contention or blocks higher * priority task we back off early rather than cause stalls. */ if (result == COMPACT_CONTENDED) return true; /* * Page scanners have met but we haven't scanned full zones so this * is a back off in fact. */ if (result == COMPACT_PARTIAL_SKIPPED) return true; return false; } bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); extern int kcompactd_run(int nid); extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); #else static inline void reset_isolation_suitable(pg_data_t *pgdat) { } static inline enum compact_result compaction_suitable(struct zone *zone, int order, int alloc_flags, int highest_zoneidx) { return COMPACT_SKIPPED; } static inline void defer_compaction(struct zone *zone, int order) { } static inline bool compaction_deferred(struct zone *zone, int order) { return true; } static inline bool compaction_made_progress(enum compact_result result) { return false; } static inline bool compaction_failed(enum compact_result result) { return false; } static inline bool compaction_needs_reclaim(enum compact_result result) { return false; } static inline bool compaction_withdrawn(enum compact_result result) { return true; } static inline int kcompactd_run(int nid) { return 0; } static inline void kcompactd_stop(int nid) { } static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) { } #endif /* CONFIG_COMPACTION */ struct node; #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) extern int compaction_register_node(struct node *node); extern void compaction_unregister_node(struct node *node); #else static inline int compaction_register_node(struct node *node) { return 0; } static inline void compaction_unregister_node(struct node *node) { } #endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */ #endif /* _LINUX_COMPACTION_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // 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 (hweight32(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; } /* 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); /* * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ wb_get(wb); 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 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; 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; 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)) 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 (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return 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);
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 /* 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 void fsnotify_name(struct inode *dir, __u32 mask, struct inode *child, const struct qstr *name, u32 cookie) { fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { 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 (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, d_inode(dentry), FSNOTIFY_EVENT_INODE); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path = &file->f_path; if (file->f_mode & FMODE_NONOTIFY) 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; const struct qstr *new_name = &moved->d_name; if (old_dir == new_dir) old_dir_mask |= FS_DN_RENAME; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; } fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); fsnotify_name(new_dir, new_dir_mask, source, 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 */ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) { audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(inode, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * 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(dir, FS_CREATE, inode, &new_dentry->d_name, 0); } /* * 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) { /* Expected to be called before d_delete() */ WARN_ON_ONCE(d_is_negative(dentry)); fsnotify_dirent(dir, dentry, FS_DELETE); } /* * fsnotify_mkdir - directory 'name' was created */ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) { audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(inode, 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) { /* Expected to be called before d_delete() */ WARN_ON_ONCE(d_is_negative(dentry)); fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR); } /* * 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); } #endif /* _LINUX_FS_NOTIFY_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 /* 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> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" #define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ #include <asm/alternative-asm.h> #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__ */ #include <asm/alternative.h> #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 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 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 // 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/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->vm_flags & VM_SHARED) 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(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->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->vm_flags & VM_SHARED) 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: vma_adjust_trans_huge(orig_vma, start, end, adjust_next); 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(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 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); 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? */ if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY)) 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; } 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; } if (vm_flags & VM_SHARED) { error = mapping_map_writable(file->f_mapping); if (error) goto allow_write_and_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 = call_mmap(file, vma); if (error) goto unmap_and_free_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); addr = vma->vm_start; /* If vm_flags changed after call_mmap(), 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); } /* Allow architectures to sanity-check the vm_flags */ if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) goto unmap_and_free_vma; else goto free_vma; } vma_link(mm, vma, prev, rb_link, rb_parent); /* Once vma denies write, undo our temporary denial count */ if (file) { unmap_writable: if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); 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_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); charged = 0; if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); allow_write_and_free_vma: 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; } #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif /* 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 0; } __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; lru_add_drain(); tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); 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. */ if (new->vm_ops && new->vm_ops->close) new->vm_ops->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); } 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 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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* delayacct.h - per-task delay accounting * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 */ #ifndef _LINUX_DELAYACCT_H #define _LINUX_DELAYACCT_H #include <uapi/linux/taskstats.h> /* * Per-task flags relevant to delay accounting * maintained privately to avoid exhausting similar flags in sched.h:PF_* * Used to set current->delays->flags */ #define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ #define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately * * struct timespec XXX_start, XXX_end; * u64 XXX_delay; * u32 XXX_count; * * Atomicity of updates to XXX_delay, XXX_count protected by * single lock above (split into XXX_lock if contention is an issue). */ /* * XXX_count is incremented on every XXX operation, the delay * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ u64 blkio_start; /* Shared by blkio, swapin */ u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_delay; /* wait for swapin block io completion */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ u32 swapin_count; /* total count of the number of swapin block */ /* io operations performed */ u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ }; #endif #include <linux/sched.h> #include <linux/slab.h> #ifdef CONFIG_TASK_DELAY_ACCT extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); extern void __delayacct_blkio_end(struct task_struct *); extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { if (p->delays) return (p->delays->flags & DELAYACCT_PF_BLKIO); else return 0; } static inline void delayacct_set_flag(int flag) { if (current->delays) current->delays->flags |= flag; } static inline void delayacct_clear_flag(int flag) { if (current->delays) current->delays->flags &= ~flag; } static inline void delayacct_tsk_init(struct task_struct *tsk) { /* reinitialize in case parent's non-null pointer was dup'ed*/ tsk->delays = NULL; if (delayacct_on) __delayacct_tsk_init(tsk); } /* Free tsk->delays. Called from bad fork and __put_task_struct * where there's no risk of tsk->delays being accessed elsewhere */ static inline void delayacct_tsk_free(struct task_struct *tsk) { if (tsk->delays) kmem_cache_free(delayacct_cache, tsk->delays); tsk->delays = NULL; } static inline void delayacct_blkio_start(void) { delayacct_set_flag(DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } static inline void delayacct_blkio_end(struct task_struct *p) { if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } static inline int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { if (!delayacct_on || !tsk->delays) return 0; return __delayacct_add_tsk(d, tsk); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { if (tsk->delays) return __delayacct_blkio_ticks(tsk); return 0; } static inline void delayacct_freepages_start(void) { if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { if (current->delays) __delayacct_freepages_end(); } static inline void delayacct_thrashing_start(void) { if (current->delays) __delayacct_thrashing_start(); } static inline void delayacct_thrashing_end(void) { if (current->delays) __delayacct_thrashing_end(); } #else static inline void delayacct_set_flag(int flag) {} static inline void delayacct_clear_flag(int flag) {} static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) {} static inline void delayacct_tsk_free(struct task_struct *tsk) {} static inline void delayacct_blkio_start(void) {} static inline void delayacct_blkio_end(struct task_struct *p) {} static inline int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { return 0; } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { return 0; } static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { return 0; } static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} static inline void delayacct_thrashing_start(void) {} static inline void delayacct_thrashing_end(void) {} #endif /* CONFIG_TASK_DELAY_ACCT */ #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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_CLOCK_H #define _LINUX_SCHED_CLOCK_H #include <linux/smp.h> /* * Do not use outside of architecture code which knows its limitations. * * sched_clock() has no promise of monotonicity or bounded drift between * CPUs, use (which you should not) requires disabling IRQs. * * Please use one of the three interfaces below. */ extern unsigned long long notrace sched_clock(void); /* * See the comment in kernel/sched/clock.c */ extern u64 running_clock(void); extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) { } static inline void clear_sched_clock_stable(void) { } static inline void sched_clock_idle_sleep_event(void) { } static inline void sched_clock_idle_wakeup_event(void) { } static inline u64 cpu_clock(int cpu) { return sched_clock(); } static inline u64 local_clock(void) { return sched_clock(); } #else extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); /* * When sched_clock_stable(), __sched_clock_offset provides the offset * between local_clock() and sched_clock(). */ extern u64 __sched_clock_offset; extern void sched_clock_tick(void); extern void sched_clock_tick_stable(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(void); /* * As outlined in clock.c, provides a fast, high resolution, nanosecond * time source that is monotonic per cpu argument and has bounded drift * between cpus. * * ######################### BIG FAT WARNING ########################## * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # * # go backwards !! # * #################################################################### */ static inline u64 cpu_clock(int cpu) { return sched_clock_cpu(cpu); } static inline u64 local_clock(void) { return sched_clock_cpu(raw_smp_processor_id()); } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* * An i/f to runtime opt-in for irq time accounting based off of sched_clock. * The reason for this explicit opt-in is not to have perf penalty with * slow sched_clocks. */ extern void enable_sched_clock_irqtime(void); extern void disable_sched_clock_irqtime(void); #else static inline void enable_sched_clock_irqtime(void) {} static inline void disable_sched_clock_irqtime(void) {} #endif #endif /* _LINUX_SCHED_CLOCK_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 /* 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); } /* 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_update_child_dentry_flags(struct inode *inode); /* allocate and destroy and event holder to attach events to notification/access queues */ extern struct fsnotify_event_holder *fsnotify_alloc_event_holder(void); extern void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder); extern struct kmem_cache *fsnotify_mark_connector_cachep; #endif /* __FS_NOTIFY_FSNOTIFY_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { const unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; }; /* * Specialize ZONE_DEVICE memory into multiple types each having differents * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/vm/hmm.rst. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the page refcount reaches 1. (ZONE_DEVICE pages never * reach 0 refcount unless there is a refcount bug. This allows the * device driver to implement its own memory management.) */ void (*page_free)(struct page *page); /* * Transition the refcount in struct dev_pagemap to the dead state. */ void (*kill)(struct dev_pagemap *pgmap); /* * Wait for refcount in struct dev_pagemap to be idle and reap it. */ void (*cleanup)(struct dev_pagemap *pgmap); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @internal_ref: internal reference if @ref is not provided by the caller * @done: completion for @internal_ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref *ref; struct percpu_ref internal_ref; struct completion done; enum memory_type type; unsigned int flags; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; struct range ranges[0]; }; }; static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } #ifdef CONFIG_ZONE_DEVICE void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(pgmap->ref); } #endif /* _LINUX_MEMREMAP_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 // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagevec.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); /* * see if a page needs releasing upon read_cache_pages() failure * - the caller of read_cache_pages() may have set PG_private or PG_fscache * before calling, such as the NFS fs marking pages that are cached locally * on disk, thus we need to give the fs a chance to clean up in the event of * an error */ static void read_cache_pages_invalidate_page(struct address_space *mapping, struct page *page) { if (page_has_private(page)) { if (!trylock_page(page)) BUG(); page->mapping = mapping; do_invalidatepage(page, 0, PAGE_SIZE); page->mapping = NULL; unlock_page(page); } put_page(page); } /* * release a list of pages, invalidating them first if need be */ static void read_cache_pages_invalidate_pages(struct address_space *mapping, struct list_head *pages) { struct page *victim; while (!list_empty(pages)) { victim = lru_to_page(pages); list_del(&victim->lru); read_cache_pages_invalidate_page(mapping, victim); } } /** * read_cache_pages - populate an address space with some pages & start reads against them * @mapping: the address_space * @pages: The address of a list_head which contains the target pages. These * pages have their ->index populated and are otherwise uninitialised. * @filler: callback routine for filling a single page. * @data: private data for the callback routine. * * Hides the details of the LRU cache etc from the filesystems. * * Returns: %0 on success, error return by @filler otherwise */ int read_cache_pages(struct address_space *mapping, struct list_head *pages, int (*filler)(void *, struct page *), void *data) { struct page *page; int ret = 0; while (!list_empty(pages)) { page = lru_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, readahead_gfp_mask(mapping))) { read_cache_pages_invalidate_page(mapping, page); continue; } put_page(page); ret = filler(data, page); if (unlikely(ret)) { read_cache_pages_invalidate_pages(mapping, pages); break; } task_io_account_read(PAGE_SIZE); } return ret; } EXPORT_SYMBOL(read_cache_pages); static void read_pages(struct readahead_control *rac, struct list_head *pages, bool skip_page) { const struct address_space_operations *aops = rac->mapping->a_ops; struct page *page; struct blk_plug plug; if (!readahead_count(rac)) goto out; blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining pages */ while ((page = readahead_page(rac))) { unlock_page(page); put_page(page); } } else if (aops->readpages) { aops->readpages(rac->file, rac->mapping, pages, readahead_count(rac)); /* Clean up the remaining pages */ put_pages_list(pages); rac->_index += rac->_nr_pages; rac->_nr_pages = 0; } else { while ((page = readahead_page(rac))) { aops->readpage(rac->file, page); put_page(page); } } blk_finish_plug(&plug); BUG_ON(!list_empty(pages)); BUG_ON(readahead_count(rac)); out: if (skip_page) rac->_index++; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); LIST_HEAD(page_pool); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long i; /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); /* * Preallocate as many pages as we will need. */ for (i = 0; i < nr_to_read; i++) { struct page *page = xa_load(&mapping->i_pages, index + i); BUG_ON(index + i != ractl->_index + ractl->_nr_pages); if (page && !xa_is_value(page)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl, &page_pool, true); continue; } page = __page_cache_alloc(gfp_mask); if (!page) break; if (mapping->a_ops->readpages) { page->index = index + i; list_add(&page->lru, &page_pool); } else if (add_to_page_cache_lru(page, mapping, index + i, gfp_mask) < 0) { put_page(page); read_pages(ractl, &page_pool, true); continue; } if (i == nr_to_read - lookahead_size) SetPageReadahead(page); ractl->_nr_pages++; } /* * Now start the IO. We ignore I/O errors - if the page is not * uptodate then the caller will launch readpage again, and * will then handle the error. */ read_pages(ractl, &page_pool, false); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, struct file_ra_state *ra, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages, index; if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ index = readahead_index(ractl); max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; ractl->_index = index; do_page_cache_ra(ractl, this_chunk, 0); index += this_chunk; nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-8 page = 32k initial, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ /* * Count contiguously cached pages from @index-1 to @index-@max, * this count is a conservative estimation of * - length of the sequential read sequence, or * - thrashing threshold in memory tight systems */ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t index, unsigned long max) { pgoff_t head; rcu_read_lock(); head = page_cache_prev_miss(mapping, index - 1, max); rcu_read_unlock(); return index - 1 - head; } /* * page cache context based read-ahead */ static int try_context_readahead(struct address_space *mapping, struct file_ra_state *ra, pgoff_t index, unsigned long req_size, unsigned long max) { pgoff_t size; size = count_history_pages(mapping, index, max); /* * not enough history pages: * it could be a random read */ if (size <= req_size) return 0; /* * starts from beginning of file: * it is a strong indication of long-run stream (or whole-file-read) */ if (size >= index) size *= 2; ra->start = index; ra->size = min(size + req_size, max); ra->async_size = 1; return 1; } /* * A minimal readahead algorithm for trivial sequential/random reads. */ static void ondemand_readahead(struct readahead_control *ractl, struct file_ra_state *ra, bool hit_readahead_marker, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ra->ra_pages; unsigned long add_pages; unsigned long index = readahead_index(ractl); pgoff_t prev_index; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); /* * start of file */ if (!index) goto initial_readahead; /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ if ((index == (ra->start + ra->size - ra->async_size) || index == (ra->start + ra->size))) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * Hit a marked page without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ if (hit_readahead_marker) { pgoff_t start; rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * oversize read */ if (req_size > max_pages) goto initial_readahead; /* * sequential cache miss * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; if (index - prev_index <= 1UL) goto initial_readahead; /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ if (try_context_readahead(ractl->mapping, ra, index, req_size, max_pages)) goto readit; /* * standalone, small random read * Read as is, and do not pollute the readahead state. */ do_page_cache_ra(ractl, req_size, 0); return; initial_readahead: ra->start = index; ra->size = get_init_ra_size(req_size, max_pages); ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; readit: /* * Will this read hit the readahead marker made by itself? * If so, trigger the readahead marker hit now, and merge * the resulted next readahead window into the current one. * Take care of maximum IO pages as above. */ if (index == ra->start && ra->size == ra->async_size) { add_pages = get_next_ra_size(ra, max_pages); if (ra->size + add_pages <= max_pages) { ra->async_size = add_pages; ra->size += add_pages; } else { ra->size = max_pages; ra->async_size = max_pages >> 1; } } ractl->_index = ra->start; do_page_cache_ra(ractl, ra->size, ra->async_size); } void page_cache_sync_ra(struct readahead_control *ractl, struct file_ra_state *ra, unsigned long req_count) { bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); /* * Even if read-ahead is disabled, issue this request as read-ahead * as we'll need it to satisfy the requested range. The forced * read-ahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, ra, req_count); return; } /* do read-ahead */ ondemand_readahead(ractl, ra, false, req_count); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct file_ra_state *ra, struct page *page, unsigned long req_count) { /* no read-ahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (PageWriteback(page)) return; ClearPageReadahead(page); /* * Defer asynchronous read-ahead on IO congestion. */ if (inode_read_congested(ractl->mapping->host)) return; if (blk_cgroup_congested()) return; /* do read-ahead */ ondemand_readahead(ractl, ra, true, req_count); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; struct fd f; ret = -EBADF; f = fdget(fd); if (!f.file || !(f.file->f_mode & FMODE_READ)) goto out; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ ret = -EINVAL; if (!f.file->f_mapping || !f.file->f_mapping->a_ops || !S_ISREG(file_inode(f.file)->i_mode)) goto out; ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); out: fdput(f); return ret; } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); }
2 2 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * SELinux NetLabel Support * * This file provides the necessary glue to tie NetLabel into the SELinux * subsystem. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2007, 2008 */ #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/gfp.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/sock.h> #include <net/netlabel.h> #include <net/ip.h> #include <net/ipv6.h> #include "objsec.h" #include "security.h" #include "netlabel.h" /** * selinux_netlbl_sidlookup_cached - Cache a SID lookup * @skb: the packet * @secattr: the NetLabel security attributes * @sid: the SID * * Description: * Query the SELinux security server to lookup the correct SID for the given * security attributes. If the query is successful, cache the result to speed * up future lookups. Returns zero on success, negative values on failure. * */ static int selinux_netlbl_sidlookup_cached(struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr, u32 *sid) { int rc; rc = security_netlbl_secattr_to_sid(&selinux_state, secattr, sid); if (rc == 0 && (secattr->flags & NETLBL_SECATTR_CACHEABLE) && (secattr->flags & NETLBL_SECATTR_CACHE)) netlbl_cache_add(skb, family, secattr); return rc; } /** * selinux_netlbl_sock_genattr - Generate the NetLabel socket secattr * @sk: the socket * * Description: * Generate the NetLabel security attributes for a socket, making full use of * the socket's attribute cache. Returns a pointer to the security attributes * on success, NULL on failure. * */ static struct netlbl_lsm_secattr *selinux_netlbl_sock_genattr(struct sock *sk) { int rc; struct sk_security_struct *sksec = sk->sk_security; struct netlbl_lsm_secattr *secattr; if (sksec->nlbl_secattr != NULL) return sksec->nlbl_secattr; secattr = netlbl_secattr_alloc(GFP_ATOMIC); if (secattr == NULL) return NULL; rc = security_netlbl_sid_to_secattr(&selinux_state, sksec->sid, secattr); if (rc != 0) { netlbl_secattr_free(secattr); return NULL; } sksec->nlbl_secattr = secattr; return secattr; } /** * selinux_netlbl_sock_getattr - Get the cached NetLabel secattr * @sk: the socket * @sid: the SID * * Query the socket's cached secattr and if the SID matches the cached value * return the cache, otherwise return NULL. * */ static struct netlbl_lsm_secattr *selinux_netlbl_sock_getattr( const struct sock *sk, u32 sid) { struct sk_security_struct *sksec = sk->sk_security; struct netlbl_lsm_secattr *secattr = sksec->nlbl_secattr; if (secattr == NULL) return NULL; if ((secattr->flags & NETLBL_SECATTR_SECID) && (secattr->attr.secid == sid)) return secattr; return NULL; } /** * selinux_netlbl_cache_invalidate - Invalidate the NetLabel cache * * Description: * Invalidate the NetLabel security attribute mapping cache. * */ void selinux_netlbl_cache_invalidate(void) { netlbl_cache_invalidate(); } /** * selinux_netlbl_err - Handle a NetLabel packet error * @skb: the packet * @error: the error code * @gateway: true if host is acting as a gateway, false otherwise * * Description: * When a packet is dropped due to a call to avc_has_perm() pass the error * code to the NetLabel subsystem so any protocol specific processing can be * done. This is safe to call even if you are unsure if NetLabel labeling is * present on the packet, NetLabel is smart enough to only act when it should. * */ void selinux_netlbl_err(struct sk_buff *skb, u16 family, int error, int gateway) { netlbl_skbuff_err(skb, family, error, gateway); } /** * selinux_netlbl_sk_security_free - Free the NetLabel fields * @sksec: the sk_security_struct * * Description: * Free all of the memory in the NetLabel fields of a sk_security_struct. * */ void selinux_netlbl_sk_security_free(struct sk_security_struct *sksec) { if (sksec->nlbl_secattr != NULL) netlbl_secattr_free(sksec->nlbl_secattr); } /** * selinux_netlbl_sk_security_reset - Reset the NetLabel fields * @sksec: the sk_security_struct * @family: the socket family * * Description: * Called when the NetLabel state of a sk_security_struct needs to be reset. * The caller is responsible for all the NetLabel sk_security_struct locking. * */ void selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec) { sksec->nlbl_state = NLBL_UNSET; } /** * selinux_netlbl_skbuff_getsid - Get the sid of a packet using NetLabel * @skb: the packet * @family: protocol family * @type: NetLabel labeling protocol type * @sid: the SID * * Description: * Call the NetLabel mechanism to get the security attributes of the given * packet and use those attributes to determine the correct context/SID to * assign to the packet. Returns zero on success, negative values on failure. * */ int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, u16 family, u32 *type, u32 *sid) { int rc; struct netlbl_lsm_secattr secattr; if (!netlbl_enabled()) { *sid = SECSID_NULL; return 0; } netlbl_secattr_init(&secattr); rc = netlbl_skbuff_getattr(skb, family, &secattr); if (rc == 0 && secattr.flags != NETLBL_SECATTR_NONE) rc = selinux_netlbl_sidlookup_cached(skb, family, &secattr, sid); else *sid = SECSID_NULL; *type = secattr.type; netlbl_secattr_destroy(&secattr); return rc; } /** * selinux_netlbl_skbuff_setsid - Set the NetLabel on a packet given a sid * @skb: the packet * @family: protocol family * @sid: the SID * * Description * Call the NetLabel mechanism to set the label of a packet using @sid. * Returns zero on success, negative values on failure. * */ int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family, u32 sid) { int rc; struct netlbl_lsm_secattr secattr_storage; struct netlbl_lsm_secattr *secattr = NULL; struct sock *sk; /* if this is a locally generated packet check to see if it is already * being labeled by it's parent socket, if it is just exit */ sk = skb_to_full_sk(skb); if (sk != NULL) { struct sk_secur