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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 /* SPDX-License-Identifier: GPL-2.0 */ /* * Block data types and constants. Directly include this file only to * break include dependency loop. */ #ifndef __LINUX_BLK_TYPES_H #define __LINUX_BLK_TYPES_H #include <linux/types.h> #include <linux/bvec.h> #include <linux/ktime.h> struct bio_set; struct bio; struct bio_integrity_payload; struct page; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; struct block_device { dev_t bd_dev; int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; struct mutex bd_mutex; /* open/close mutex */ void * bd_claiming; void * bd_holder; int bd_holders; bool bd_write_holder; #ifdef CONFIG_SYSFS struct list_head bd_holder_disks; #endif struct block_device * bd_contains; u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; /* The counter of freeze processes */ int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; } __randomize_layout; /* * Block error status values. See block/blk-core:blk_errors for the details. * Alpha cannot write a byte atomically, so we need to use 32-bit value. */ #if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) typedef u32 __bitwise blk_status_t; #else typedef u8 __bitwise blk_status_t; #endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) #define BLK_STS_NOSPC ((__force blk_status_t)3) #define BLK_STS_TRANSPORT ((__force blk_status_t)4) #define BLK_STS_TARGET ((__force blk_status_t)5) #define BLK_STS_NEXUS ((__force blk_status_t)6) #define BLK_STS_MEDIUM ((__force blk_status_t)7) #define BLK_STS_PROTECTION ((__force blk_status_t)8) #define BLK_STS_RESOURCE ((__force blk_status_t)9) #define BLK_STS_IOERR ((__force blk_status_t)10) /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) #define BLK_STS_AGAIN ((__force blk_status_t)12) /* * BLK_STS_DEV_RESOURCE is returned from the driver to the block layer if * device related resources are unavailable, but the driver can guarantee * that the queue will be rerun in the future once resources become * available again. This is typically the case for device specific * resources that are consumed for IO. If the driver fails allocating these * resources, we know that inflight (or pending) IO will free these * resource upon completion. * * This is different from BLK_STS_RESOURCE in that it explicitly references * a device specific resource. For resources of wider scope, allocation * failure can happen without having pending IO. This means that we can't * rely on request completions freeing these resources, as IO may not be in * flight. Examples of that are kernel memory allocations, DMA mappings, or * any other system wide resources. */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone * related resources are unavailable, but the driver can guarantee the queue * will be rerun in the future once the resources become available again. * * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references * a zone specific resource and IO to a different zone on the same device could * still be served. Examples of that are zones that are write-locked, but a read * to the same zone could be served. */ #define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ #define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently active. The same command should be successful if resubmitted * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with * * Description: * This classifies block error status into non-retryable errors and ones * that may be successful if retried on a failover path. * * Return: * %false - retrying failover path will not help * %true - may succeed if retried */ static inline bool blk_path_error(blk_status_t error) { switch (error) { case BLK_STS_NOTSUPP: case BLK_STS_NOSPC: case BLK_STS_TARGET: case BLK_STS_NEXUS: case BLK_STS_MEDIUM: case BLK_STS_PROTECTION: return false; } /* Anything else could be a path failure, so should be retried */ return true; } /* * From most significant bit: * 1 bit: reserved for other usage, see below * 12 bits: original size of bio * 51 bits: issue time of bio */ #define BIO_ISSUE_RES_BITS 1 #define BIO_ISSUE_SIZE_BITS 12 #define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS) #define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS) #define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1) #define BIO_ISSUE_SIZE_MASK \ (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT) #define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1)) /* Reserved bit for blk-throtl */ #define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63) struct bio_issue { u64 value; }; static inline u64 __bio_issue_time(u64 time) { return time & BIO_ISSUE_TIME_MASK; } static inline u64 bio_issue_time(struct bio_issue *issue) { return __bio_issue_time(issue->value); } static inline sector_t bio_issue_size(struct bio_issue *issue) { return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT); } static inline void bio_issue_init(struct bio_issue *issue, sector_t size) { size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1; issue->value = ((issue->value & BIO_ISSUE_RES_MASK) | (ktime_get_ns() & BIO_ISSUE_TIME_MASK) | ((u64)size << BIO_ISSUE_SIZE_SHIFT)); } /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { struct bio *bi_next; /* request queue link */ struct gendisk *bi_disk; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. */ unsigned short bi_flags; /* status, etc and bvec pool number */ unsigned short bi_ioprio; unsigned short bi_write_hint; blk_status_t bi_status; u8 bi_partno; atomic_t __bi_remaining; struct bvec_iter bi_iter; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP /* * Represents the association of the css and request_queue for the bio. * If a bio goes direct to device, it will not have a blkg as it will * not have a request_queue associated with it. The reference is put * on release of the bio. */ struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #ifdef CONFIG_BLK_CGROUP_IOCOST u64 bi_iocost_cost; #endif #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *bi_crypt_context; #endif union { #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif }; unsigned short bi_vcnt; /* how many bio_vec's */ /* * Everything starting with bi_max_vecs will be preserved by bio_reset() */ unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ atomic_t __bi_cnt; /* pin count */ struct bio_vec *bi_io_vec; /* the actual vec list */ struct bio_set *bi_pool; /* * We can inline a number of vecs at the end of the bio, to avoid * double allocations for a small number of bio_vecs. This member * MUST obviously be kept at the very end of the bio. */ struct bio_vec bi_inline_vecs[]; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) /* * bio flags */ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ BIO_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_FLAG_LAST }; /* See BVEC_POOL_OFFSET below before adding new flags */ /* * We support 6 different bvec pools, the last one is magic in that it * is backed by a mempool. */ #define BVEC_POOL_NR 6 #define BVEC_POOL_MAX (BVEC_POOL_NR - 1) /* * Top 3 bits of bio flags indicate the pool the bvecs came from. We add * 1 to the actual index so that 0 indicates that there are no bvecs to be * freed. */ #define BVEC_POOL_BITS (3) #define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) #define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) #if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1) # error "BVEC_POOL_BITS is too small" #endif /* * Flags starting here get preserved by bio_reset() - this includes * only BVEC_POOL_IDX() */ #define BIO_RESET_BITS BVEC_POOL_OFFSET typedef __u32 __bitwise blk_mq_req_flags_t; /* * Operations and flags common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. * * The least significant bit of the operation number indicates the data * transfer direction: * * - if the least significant bit is set transfers are TO the device * - if the least significant bit is not set transfers are FROM the device * * If a operation does not transfer data the least significant bit has no * meaning. */ #define REQ_OP_BITS 8 #define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) #define REQ_FLAG_BITS 24 enum req_opf { /* read sectors from the device */ REQ_OP_READ = 0, /* write sectors to the device */ REQ_OP_WRITE = 1, /* flush the volatile write cache */ REQ_OP_FLUSH = 2, /* discard sectors */ REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ REQ_OP_ZONE_OPEN = 10, /* Close a zone */ REQ_OP_ZONE_CLOSE = 11, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = 12, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = 13, /* reset a zone write pointer */ REQ_OP_ZONE_RESET = 15, /* reset all the zone present on the device */ REQ_OP_ZONE_RESET_ALL = 17, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, REQ_OP_SCSI_OUT = 33, /* Driver private requests */ REQ_OP_DRV_IN = 34, REQ_OP_DRV_OUT = 35, REQ_OP_LAST, }; enum req_flag_bits { __REQ_FAILFAST_DEV = /* no driver retries of device errors */ REQ_OP_BITS, __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ __REQ_NOMERGE, /* don't touch this for merging */ __REQ_IDLE, /* anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread * can be trapped waiting for that cgroup. CGROUP_PUNT flag makes * submit_bio() punt the actual issuing to a dedicated per-blkcg * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ __REQ_HIPRI, /* for driver use */ __REQ_DRV, __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; #define REQ_FAILFAST_DEV (1ULL << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT (1ULL << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER (1ULL << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (1ULL << __REQ_SYNC) #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) #define REQ_NOMERGE (1ULL << __REQ_NOMERGE) #define REQ_IDLE (1ULL << __REQ_IDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_HIPRI (1ULL << __REQ_HIPRI) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, STAT_FLUSH, NR_STAT_GROUPS }; #define bio_op(bio) \ ((bio)->bi_opf & REQ_OP_MASK) #define req_op(req) \ ((req)->cmd_flags & REQ_OP_MASK) /* obsolete, don't use in new code */ static inline void bio_set_op_attrs(struct bio *bio, unsigned op, unsigned op_flags) { bio->bi_opf = op | op_flags; } static inline bool op_is_write(unsigned int op) { return (op & 1); } /* * Check if the bio or request is one that needs special treatment in the * flush state machine. */ static inline bool op_is_flush(unsigned int op) { return op & (REQ_FUA | REQ_PREFLUSH); } /* * Reads are always treated as synchronous, as are requests with the FUA or * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. */ static inline bool op_is_sync(unsigned int op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } static inline bool op_is_discard(unsigned int op) { return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } /* * Check if a bio or request operation is a zone management operation, with * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case * due to its different handling in the block layer and device response in * case of command failure. */ static inline bool op_is_zone_mgmt(enum req_opf op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: return true; default: return false; } } static inline int op_stat_group(unsigned int op) { if (op_is_discard(op)) return STAT_DISCARD; return op_is_write(op); } typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) { return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT; } static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) { return cookie & ((1u << BLK_QC_T_SHIFT) - 1); } static inline bool blk_qc_t_is_internal(blk_qc_t cookie) { return (cookie & BLK_QC_T_INTERNAL) != 0; } struct blk_rq_stat { u64 mean; u64 min; u64 max; u32 nr_samples; u64 batch; }; #endif /* __LINUX_BLK_TYPES_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/lcm.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* the slots are sorted by free bytes left, 1-31 bytes share the same slot */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; EXPORT_SYMBOL_GPL(pcpu_base_addr); static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* chunks which need their map areas extended, protected by pcpu_lock */ static LIST_HEAD(pcpu_map_extend_chunks); /* * The number of empty populated pages by chunk type, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES]; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_nr_slots - 1; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->index = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->index; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { struct list_head *pcpu_slot; pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); if (move_front) list_move(&chunk->list, &pcpu_slot[slot]); else list_move_tail(&chunk->list, &pcpu_slot[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk) pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int rs, re, start; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ bitmap_for_each_clear_region(alloc_map, rs, re, start, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, rs, re); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int page_start, page_end, rs, re; page_start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); page_end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); rs = page_start; bitmap_next_clear_region(chunk->populated, &rs, &re, page_end); if (rs >= page_end) return true; *next_off = re * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * Check to see if the allocation can fit in the chunk's contig hint. * This is an optimization to prevent scanning by assuming if it * cannot fit in the global hint, there is memory pressure and creating * a new chunk would happen soon. */ bit_off = ALIGN(chunk_md->contig_hint_start, align) - chunk_md->contig_hint_start; if (bit_off + alloc_bits > chunk_md->contig_hint) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr, lcm_align; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; /* * Align the end of the region with the LCM of PAGE_SIZE and * PCPU_BITMAP_BLOCK_SIZE. One of these constants is a multiple of * the other. */ lcm_align = lcm(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE); region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->alloc_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->bound_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->md_blocks) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); #ifdef CONFIG_MEMCG_KMEM /* first chunk isn't memcg-aware */ chunk->obj_cgroups = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef CONFIG_MEMCG_KMEM if (pcpu_is_memcg_chunk(type)) { chunk->obj_cgroups = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct obj_cgroup *), gfp); if (!chunk->obj_cgroups) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef CONFIG_MEMCG_KMEM objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef CONFIG_MEMCG_KMEM pcpu_mem_free(chunk->obj_cgroups); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. * * If this is @for_alloc, do not increment pcpu_nr_empty_pop_pages because it * is to serve an allocation in that area. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG_KMEM static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT)) return PCPU_CHUNK_ROOT; objcg = get_obj_cgroup_from_current(); if (!objcg) return PCPU_CHUNK_ROOT; if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) { obj_cgroup_put(objcg); return PCPU_FAIL_ALLOC; } *objcgp = objcg; return PCPU_CHUNK_MEMCG; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (chunk) { chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, size * num_possible_cpus()); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, size * num_possible_cpus()); obj_cgroup_put(objcg); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))) return; objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; obj_cgroup_uncharge(objcg, size * num_possible_cpus()); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -(size * num_possible_cpus())); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG_KMEM */ static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return PCPU_CHUNK_ROOT; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG_KMEM */ /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; enum pcpu_chunk_type type; struct list_head *pcpu_slot; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg); if (unlikely(type == PCPU_FAIL_ALLOC)) return NULL; pcpu_slot = pcpu_chunk_list(type); if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; } } spin_unlock_irqrestore(&pcpu_lock, flags); /* * No space left. Create a new chunk. We don't want multiple * tasks to create chunks simultaneously. Serialize and create iff * there's still no empty chunk after grabbing the mutex. */ if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { chunk = pcpu_create_chunk(type, pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_start, page_end, rs, re; page_start = PFN_DOWN(off); page_end = PFN_UP(off + size); bitmap_for_each_clear_region(chunk->populated, rs, re, page_start, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(reserved, is_atomic, size, align, chunk->base_addr, off, ptr); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (!is_atomic && do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n"); } if (is_atomic) { /* see the flag handling in pcpu_blance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } /** * __alloc_percpu_gfp - allocate dynamic percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @gfp: allocation flags * * Allocate zero-filled percpu area of @size bytes aligned at @align. If * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can * be called from any context but is a lot more likely to fail. If @gfp * has __GFP_NOWARN then no warning will be triggered on invalid or failed * allocation requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) { return pcpu_alloc(size, align, false, gfp); } EXPORT_SYMBOL_GPL(__alloc_percpu_gfp); /** * __alloc_percpu - allocate dynamic percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL). */ void __percpu *__alloc_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, false, GFP_KERNEL); } EXPORT_SYMBOL_GPL(__alloc_percpu); /** * __alloc_reserved_percpu - allocate reserved percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * * Allocate zero-filled percpu area of @size bytes aligned at @align * from reserved percpu area if arch has set it up; otherwise, * allocation is served from the same dynamic area. Might sleep. * Might trigger writeouts. * * CONTEXT: * Does GFP_KERNEL allocation. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, true, GFP_KERNEL); } /** * __pcpu_balance_workfn - manage the amount of free chunks and populated pages * @type: chunk type * * Reclaim all fully free chunks except for the first one. This is also * responsible for maintaining the pool of empty populated pages. However, * it is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. */ static void __pcpu_balance_workfn(enum pcpu_chunk_type type) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; LIST_HEAD(to_free); struct list_head *pcpu_slot = pcpu_chunk_list(type); struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1]; struct pcpu_chunk *chunk, *next; int slot, nr_to_pop, ret; /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; list_move(&chunk->list, &to_free); } spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; bitmap_for_each_set_region(chunk->populated, rs, re, 0, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages[type], 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; spin_lock_irq(&pcpu_lock); list_for_each_entry(chunk, &pcpu_slot[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } spin_unlock_irq(&pcpu_lock); if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ bitmap_for_each_clear_region(chunk->populated, rs, re, 0, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); if (!ret) { nr_to_pop -= nr; spin_lock_irq(&pcpu_lock); pcpu_chunk_populated(chunk, rs, rs + nr); spin_unlock_irq(&pcpu_lock); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ chunk = pcpu_create_chunk(type, gfp); if (chunk) { spin_lock_irq(&pcpu_lock); pcpu_chunk_relocate(chunk, -1); spin_unlock_irq(&pcpu_lock); goto retry_pop; } } mutex_unlock(&pcpu_alloc_mutex); } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * Call __pcpu_balance_workfn() for each chunk type. */ static void pcpu_balance_workfn(struct work_struct *work) { enum pcpu_chunk_type type; for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) __pcpu_balance_workfn(type); } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; struct list_head *pcpu_slot; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); spin_lock_irqsave(&pcpu_lock, flags); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; size = pcpu_free_area(chunk, off); pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); pcpu_memcg_free_hook(chunk, off, size); /* if there are more than one fully free chunks, wake up grim reaper */ if (chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) if (pos != chunk) { need_balance = true; break; } } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free_early(__pa(ai), ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; struct pcpu_chunk *chunk; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; int map_size; unsigned long tmp_addr; size_t alloc_size; enum pcpu_chunk_type type; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!ai->dyn_size); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_offsets) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_sizes) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_off) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size(chunk, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The additional last slot is for * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * PCPU_NR_CHUNK_TYPES, SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * PCPU_NR_CHUNK_TYPES); for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk. * If the reserved_size is non-zero, this initializes the reserved * chunk. If the reserved_size is zero, the reserved chunk is NULL * and the dynamic region is initialized here. The first chunk, * pcpu_first_chunk, will always point to the chunk that serves * the dynamic region. */ tmp_addr = (unsigned long)base_addr + static_size; map_size = ai->reserved_size ?: dyn_size; chunk = pcpu_alloc_first_chunk(tmp_addr, map_size); /* init dynamic chunk if necessary */ if (ai->reserved_size) { pcpu_reserved_chunk = chunk; tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; map_size = dyn_size; chunk = pcpu_alloc_first_chunk(tmp_addr, map_size); } /* link the first chunk in */ pcpu_first_chunk = chunk; pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; /* group cpus according to their proximity */ for_each_possible_cpu(cpu) { group = 0; next_group: for_each_possible_cpu(tcpu) { if (cpu == tcpu) break; if (group_map[tcpu] == group && cpu_distance_fn && (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE || cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) { group++; nr_groups = max(nr_groups, group + 1); goto next_group; } } group_map[cpu] = group; group_cnt[group]++; } /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @alloc_fn: function to allocate percpu page * @free_fn: function to free percpu page * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling @alloc_fn and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using @free_fn. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_free(ptr); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ free_fn(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); free_fn(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) free_fn(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free_early(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE * @free_fn: function to free percpu page, always called with PAGE_SIZE * @populate_pte_fn: function to populate pte * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); if (!pages) panic("%s: Failed to allocate %zu bytes\n", __func__, pages_size); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_free(ptr); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); /* * FIXME: Archs with virtual cache should flush local * cache for the linear mapping here - something * equivalent to flush_cache_vmap() on the local cpu. * flush_cache_vmap() can't be used as most supporting * data structures are not set up yet. */ /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free_early(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align) { return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS)); } static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { memblock_free_early(__pa(ptr), size); } void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_free(fc); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return pcpu_nr_populated * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Functions used by both the SCSI initiator code and the SCSI target code. */ #ifndef _SCSI_COMMON_H_ #define _SCSI_COMMON_H_ #include <linux/types.h> #include <scsi/scsi_proto.h> static inline unsigned scsi_varlen_cdb_length(const void *hdr) { return ((struct scsi_varlen_cdb_hdr *)hdr)->additional_cdb_length + 8; } extern const unsigned char scsi_command_size_tbl[8]; #define COMMAND_SIZE(opcode) scsi_command_size_tbl[((opcode) >> 5) & 7] static inline unsigned scsi_command_size(const unsigned char *cmnd) { return (cmnd[0] == VARIABLE_LENGTH_CMD) ? scsi_varlen_cdb_length(cmnd) : COMMAND_SIZE(cmnd[0]); } static inline unsigned char scsi_command_control(const unsigned char *cmnd) { return (cmnd[0] == VARIABLE_LENGTH_CMD) ? cmnd[1] : cmnd[COMMAND_SIZE(cmnd[0]) - 1]; } /* Returns a human-readable name for the device */ extern const char *scsi_device_type(unsigned type); extern void int_to_scsilun(u64, struct scsi_lun *); extern u64 scsilun_to_int(struct scsi_lun *); /* * This is a slightly modified SCSI sense "descriptor" format header. * The addition is to allow the 0x70 and 0x71 response codes. The idea * is to place the salient data from either "fixed" or "descriptor" sense * format into one structure to ease application processing. * * The original sense buffer should be kept around for those cases * in which more information is required (e.g. the LBA of a MEDIUM ERROR). */ struct scsi_sense_hdr { /* See SPC-3 section 4.5 */ u8 response_code; /* permit: 0x0, 0x70, 0x71, 0x72, 0x73 */ u8 sense_key; u8 asc; u8 ascq; u8 byte4; u8 byte5; u8 byte6; u8 additional_length; /* always 0 for fixed sense format */ }; static inline bool scsi_sense_valid(const struct scsi_sense_hdr *sshdr) { if (!sshdr) return false; return (sshdr->response_code & 0x70) == 0x70; } extern bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len, struct scsi_sense_hdr *sshdr); extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq); int scsi_set_sense_information(u8 *buf, int buf_len, u64 info); int scsi_set_sense_field_pointer(u8 *buf, int buf_len, u16 fp, u8 bp, bool cd); extern const u8 * scsi_sense_desc_find(const u8 * sense_buffer, int sb_len, int desc_type); #endif /* _SCSI_COMMON_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 _NET_DST_OPS_H #define _NET_DST_OPS_H #include <linux/types.h> #include <linux/percpu_counter.h> #include <linux/cache.h> struct dst_entry; struct kmem_cachep; struct net_device; struct sk_buff; struct sock; struct net; struct dst_ops { unsigned short family; unsigned int gc_thresh; int (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*mtu)(const struct dst_entry *); u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); void (*confirm_neigh)(const struct dst_entry *dst, const void *daddr); struct kmem_cache *kmem_cachep; struct percpu_counter pcpuc_entries ____cacheline_aligned_in_smp; }; static inline int dst_entries_get_fast(struct dst_ops *dst) { return percpu_counter_read_positive(&dst->pcpuc_entries); } static inline int dst_entries_get_slow(struct dst_ops *dst) { return percpu_counter_sum_positive(&dst->pcpuc_entries); } #define DST_PERCPU_COUNTER_BATCH 32 static inline void dst_entries_add(struct dst_ops *dst, int val) { percpu_counter_add_batch(&dst->pcpuc_entries, val, DST_PERCPU_COUNTER_BATCH); } static inline int dst_entries_init(struct dst_ops *dst) { return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL); } static inline void dst_entries_destroy(struct dst_ops *dst) { percpu_counter_destroy(&dst->pcpuc_entries); } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_LOCAL_H #define _ASM_X86_LOCAL_H #include <linux/percpu.h> #include <linux/atomic.h> #include <asm/asm.h> typedef struct { atomic_long_t a; } local_t; #define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } #define local_read(l) atomic_long_read(&(l)->a) #define local_set(l, i) atomic_long_set(&(l)->a, (i)) static inline void local_inc(local_t *l) { asm volatile(_ASM_INC "%0" : "+m" (l->a.counter)); } static inline void local_dec(local_t *l) { asm volatile(_ASM_DEC "%0" : "+m" (l->a.counter)); } static inline void local_add(long i, local_t *l) { asm volatile(_ASM_ADD "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } static inline void local_sub(long i, local_t *l) { asm volatile(_ASM_SUB "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } /** * local_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @l: pointer to type local_t * * Atomically subtracts @i from @l and returns * true if the result is zero, or false for all * other cases. */ static inline bool local_sub_and_test(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i); } /** * local_dec_and_test - decrement and test * @l: pointer to type local_t * * Atomically decrements @l by 1 and * returns true if the result is 0, or false for all other * cases. */ static inline bool local_dec_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e); } /** * local_inc_and_test - increment and test * @l: pointer to type local_t * * Atomically increments @l by 1 * and returns true if the result is zero, or false for all * other cases. */ static inline bool local_inc_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e); } /** * local_add_negative - add and test if negative * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static inline bool local_add_negative(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i); } /** * local_add_return - add and return * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns @i + @l */ static inline long local_add_return(long i, local_t *l) { long __i = i; asm volatile(_ASM_XADD "%0, %1;" : "+r" (i), "+m" (l->a.counter) : : "memory"); return i + __i; } static inline long local_sub_return(long i, local_t *l) { return local_add_return(-i, l); } #define local_inc_return(l) (local_add_return(1, l)) #define local_dec_return(l) (local_sub_return(1, l)) #define local_cmpxchg(l, o, n) \ (cmpxchg_local(&((l)->a.counter), (o), (n))) /* Always has a lock prefix */ #define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) /** * local_add_unless - add unless the number is a given value * @l: pointer of type local_t * @a: the amount to add to l... * @u: ...unless l is equal to u. * * Atomically adds @a to @l, so long as it was not @u. * Returns non-zero if @l was not @u, and zero otherwise. */ #define local_add_unless(l, a, u) \ ({ \ long c, old; \ c = local_read((l)); \ for (;;) { \ if (unlikely(c == (u))) \ break; \ old = local_cmpxchg((l), c, c + (a)); \ if (likely(old == c)) \ break; \ c = old; \ } \ c != (u); \ }) #define local_inc_not_zero(l) local_add_unless((l), 1, 0) /* On x86_32, these are no better than the atomic variants. * On x86-64 these are better than the atomic variants on SMP kernels * because they dont use a lock prefix. */ #define __local_inc(l) local_inc(l) #define __local_dec(l) local_dec(l) #define __local_add(i, l) local_add((i), (l)) #define __local_sub(i, l) local_sub((i), (l)) #endif /* _ASM_X86_LOCAL_H */
1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> static struct vfsmount *anon_inode_mnt __read_mostly; static struct inode *anon_inode_inode; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { struct file *file; if (IS_ERR(anon_inode_inode)) return ERR_PTR(-ENODEV); if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); /* * We know the anon_inode inode count is always greater than zero, * so ihold() is safe. */ ihold(anon_inode_inode); file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err; file->f_mapping = anon_inode_inode->i_mapping; file->private_data = priv; return file; err: iput(anon_inode_inode); module_put(fops->owner); return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfd - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfd() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns new descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = anon_inode_getfile(name, fops, priv, flags); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } EXPORT_SYMBOL_GPL(anon_inode_getfd); static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); return 0; } fs_initcall(anon_inode_init);
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static void flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); #define CSD_LOCK_TIMEOUT (5ULL * NSEC_PER_SEC) static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void csd_lock_record(struct __call_single_data *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline int csd_lock_wait_getcpu(struct __call_single_data *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static __always_inline bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->flags); if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); return true; } ts2 = sched_clock(); ts_delta = ts2 - *ts1; if (likely(ts_delta <= CSD_LOCK_TIMEOUT)) return false; firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0, cpu, csd->func, csd->info); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (!trigger_single_cpu_backtrace(cpu)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static __always_inline void csd_lock_wait(struct __call_single_data *csd) { int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = sched_clock(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } #else static void csd_lock_record(struct __call_single_data *csd) { } static __always_inline void csd_lock_wait(struct __call_single_data *csd) { smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(struct __call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(struct __call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * The list addition should be visible before sending the IPI * handler locks the list to pull the entry off it because of * normal cache coherency rules implied by spinlocks. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, struct __call_single_data *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); func(info); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { flush_smp_call_function_queue(true); } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; lockdep_assert_irqs_disabled(); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && !llist_empty(head))) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->llist; } else { entry = &csd_next->llist; } csd_lock_record(csd); func(info); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->llist; } else { entry = &csd_next->llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); func(info); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) sched_ttwu_pending(entry); } void flush_smp_call_function_from_idle(void) { unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq(); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->src = smp_processor_id(); csd->dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async(): Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { int err = 0; preempt_disable(); if (csd->flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait, smp_cond_func_t cond_func) { struct call_function_data *cfd; int cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress && !early_boot_irqs_disabled); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); /* No online cpus? We're done. */ if (cpu >= nr_cpu_ids) return; /* Do we have another CPU which isn't us? */ next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (next_cpu == this_cpu) next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); /* Fastpath: do that cpu by itself. */ if (next_cpu >= nr_cpu_ids) { if (!cond_func || cond_func(cpu, info)) smp_call_function_single(cpu, func, info, wait); return; } cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ if (unlikely(!cpumask_weight(cfd->cpumask))) return; cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) continue; csd_lock(csd); if (wait) csd->flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->src = smp_processor_id(); csd->dst = cpu; #endif if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) __cpumask_set_cpu(cpu, cfd->cpumask_ipi); } /* Send a message to all CPUs in the map */ arch_send_call_function_ipi_mask(cfd->cpumask_ipi); if (wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of other CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) nr_cpu_ids = nr_cpus; return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * Call a function on all processors. May be used during early boot while * early_boot_irqs_disabled is set. Use local_irq_save/restore() instead * of local_irq_disable/enable(). */ void on_each_cpu(smp_call_func_t func, void *info, int wait) { unsigned long flags; preempt_disable(); smp_call_function(func, info, wait); local_irq_save(flags); func(info); local_irq_restore(flags); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu); /** * on_each_cpu_mask(): Run a function on processors specified by * cpumask, which may include the local processor. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. The * exception is that it may be used during early boot while * early_boot_irqs_disabled is set. */ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { int cpu = get_cpu(); smp_call_function_many(mask, func, info, wait); if (cpumask_test_cpu(cpu, mask)) { unsigned long flags; local_irq_save(flags); func(info); local_irq_restore(flags); } put_cpu(); } EXPORT_SYMBOL(on_each_cpu_mask); /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { int cpu = get_cpu(); smp_call_function_many_cond(mask, func, info, wait, cond_func); if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) { unsigned long flags; local_irq_save(flags); func(info); local_irq_restore(flags); } put_cpu(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait) { on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } EXPORT_SYMBOL(on_each_cpu_cond); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; preempt_disable(); for_each_online_cpu(cpu) { if (cpu == smp_processor_id()) continue; wake_up_if_idle(cpu); } preempt_enable(); } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * smp_call_on_cpu - Call a function on a specific cpu * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu);
1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; unsigned long low, min; long delta; if (!c->parent) return; min = READ_ONCE(c->min); if (min || atomic_long_read(&c->min_usage)) { protected = min(usage, min); old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } low = READ_ONCE(c->low); if (low || atomic_long_read(&c->low_usage)) { protected = min(usage, low); old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); propagate_protected_usage(counter, new); /* More uncharges than charges? */ WARN_ON_ONCE(new < 0); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = atomic_long_read(&counter->usage); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (atomic_long_read(&counter->usage) <= usage) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 /* SPDX-License-Identifier: GPL-2.0+ */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rseq #if !defined(_TRACE_RSEQ_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RSEQ_H #include <linux/tracepoint.h> #include <linux/types.h> TRACE_EVENT(rseq_update, TP_PROTO(struct task_struct *t), TP_ARGS(t), TP_STRUCT__entry( __field(s32, cpu_id) ), TP_fast_assign( __entry->cpu_id = raw_smp_processor_id(); ), TP_printk("cpu_id=%d", __entry->cpu_id) ); TRACE_EVENT(rseq_ip_fixup, TP_PROTO(unsigned long regs_ip, unsigned long start_ip, unsigned long post_commit_offset, unsigned long abort_ip), TP_ARGS(regs_ip, start_ip, post_commit_offset, abort_ip), TP_STRUCT__entry( __field(unsigned long, regs_ip) __field(unsigned long, start_ip) __field(unsigned long, post_commit_offset) __field(unsigned long, abort_ip) ), TP_fast_assign( __entry->regs_ip = regs_ip; __entry->start_ip = start_ip; __entry->post_commit_offset = post_commit_offset; __entry->abort_ip = abort_ip; ), TP_printk("regs_ip=0x%lx start_ip=0x%lx post_commit_offset=%lu abort_ip=0x%lx", __entry->regs_ip, __entry->start_ip, __entry->post_commit_offset, __entry->abort_ip) ); #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux NET3: Internet Group Management Protocol [IGMP] * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Extended to talk the BSD extended IGMP protocol of mrouted 3.6 */ #ifndef _LINUX_IGMP_H #define _LINUX_IGMP_H #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/refcount.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) { return (struct igmphdr *)skb_transport_header(skb); } static inline struct igmpv3_report * igmpv3_report_hdr(const struct sk_buff *skb) { return (struct igmpv3_report *)skb_transport_header(skb); } static inline struct igmpv3_query * igmpv3_query_hdr(const struct sk_buff *skb) { return (struct igmpv3_query *)skb_transport_header(skb); } struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; __be32 sl_addr[]; }; #define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ (count) * sizeof(__be32)) #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; this list never used in fast path code */ struct ip_mc_socklist { struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip_sf_list { struct ip_sf_list *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; struct ip_mc_list __rcu *next_rcu; }; struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; char unsolicit_count; char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; struct rcu_head rcu; }; /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ ((value) < (thresh) ? (value) : \ ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant))) << \ (IGMPV3_MASK((value) >> (nbmant), nbexp) + (nbexp)))) #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ip_transport_len(skb) < len) return 0; return pskb_may_pull(skb, len); } extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage __user *p); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); } extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for inet_sock * * Authors: Many, reorganised here by * Arnaldo Carvalho de Melo <acme@mandriva.com> */ #ifndef _INET_SOCK_H #define _INET_SOCK_H #include <linux/bitops.h> #include <linux/string.h> #include <linux/types.h> #include <linux/jhash.h> #include <linux/netdevice.h> #include <net/flow.h> #include <net/sock.h> #include <net/request_sock.h> #include <net/netns/hash.h> #include <net/tcp_states.h> #include <net/l3mdev.h> /** struct ip_options - IP Options * * @faddr - Saved first hop address * @nexthop - Saved nexthop address in LSRR and SSRR * @is_strictroute - Strict source route * @srr_is_hit - Packet destination addr was our one * @is_changed - IP checksum more not valid * @rr_needaddr - Need to record addr of outgoing dev * @ts_needtime - Need to record timestamp * @ts_needaddr - Need to record addr of outgoing dev */ struct ip_options { __be32 faddr; __be32 nexthop; unsigned char optlen; unsigned char srr; unsigned char rr; unsigned char ts; unsigned char is_strictroute:1, srr_is_hit:1, is_changed:1, rr_needaddr:1, ts_needtime:1, ts_needaddr:1; unsigned char router_alert; unsigned char cipso; unsigned char __pad2; unsigned char __data[]; }; struct ip_options_rcu { struct rcu_head rcu; struct ip_options opt; }; struct ip_options_data { struct ip_options_rcu opt; char data[40]; }; struct inet_request_sock { struct request_sock req; #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_rmt_addr req.__req_common.skc_daddr #define ir_num req.__req_common.skc_num #define ir_rmt_port req.__req_common.skc_dport #define ir_v6_rmt_addr req.__req_common.skc_v6_daddr #define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr #define ir_iif req.__req_common.skc_bound_dev_if #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state #define ireq_family req.__req_common.skc_family u16 snd_wscale : 4, rcv_wscale : 4, tstamp_ok : 1, sack_ok : 1, wscale_ok : 1, ecn_ok : 1, acked : 1, no_srccheck: 1, smc_ok : 1; u32 ir_mark; union { struct ip_options_rcu __rcu *ireq_opt; #if IS_ENABLED(CONFIG_IPV6) struct { struct ipv6_txoptions *ipv6_opt; struct sk_buff *pktopts; }; #endif }; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) { return (struct inet_request_sock *)sk; } static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) return skb->mark; return sk->sk_mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif return sk->sk_bound_dev_if; } static inline int inet_sk_bound_l3mdev(const struct sock *sk) { #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!net->ipv4.sysctl_tcp_l3mdev_accept) return l3mdev_master_ifindex_by_index(net, sk->sk_bound_dev_if); #endif return 0; } static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, int dif, int sdif) { if (!bound_dev_if) return !sdif || l3mdev_accept; return bound_dev_if == dif || bound_dev_if == sdif; } struct inet_cork { unsigned int flags; __be32 addr; struct ip_options *opt; unsigned int fragsize; int length; /* Total length of all frames */ struct dst_entry *dst; u8 tx_flags; __u8 ttl; __s16 tos; char priority; __u16 gso_size; u64 transmit_time; u32 mark; }; struct inet_cork_full { struct inet_cork base; struct flowi fl; }; struct ip_mc_socklist; struct ipv6_pinfo; struct rtable; /** struct inet_sock - representation of INET sockets * * @sk - ancestor class * @pinet6 - pointer to IPv6 control block * @inet_daddr - Foreign IPv4 addr * @inet_rcv_saddr - Bound local IPv4 addr * @inet_dport - Destination port * @inet_num - Local port * @inet_saddr - Sending source * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? * @uc_index - Unicast outgoing device index * @mc_index - Multicast device index * @mc_list - Group array * @cork - info to build ip hdr on each ip frag while socket is corked */ struct inet_sock { /* sk and pinet6 has to be the first two members of inet_sock */ struct sock sk; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ #define inet_daddr sk.__sk_common.skc_daddr #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport #define inet_num sk.__sk_common.skc_num __be32 inet_saddr; __s16 uc_ttl; __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; struct ip_options_rcu __rcu *inet_opt; int rx_dst_ifindex; __u8 tos; __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; __u8 recverr:1, is_icsk:1, freebind:1, hdrincl:1, mc_loop:1, transparent:1, mc_all:1, nodefrag:1; __u8 bind_address_no_port:1, recverr_rfc4884:1, defer_connect:1; /* Indicates that fastopen_connect is set * and cookie exists so we defer connect * until first data frame is written */ __u8 rcv_tos; __u8 convert_csum; int uc_index; int mc_index; __be32 mc_addr; struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ #define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */ /* cmsg flags for inet */ #define IP_CMSG_PKTINFO BIT(0) #define IP_CMSG_TTL BIT(1) #define IP_CMSG_TOS BIT(2) #define IP_CMSG_RECVOPTS BIT(3) #define IP_CMSG_RETOPTS BIT(4) #define IP_CMSG_PASSSEC BIT(5) #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) #define IP_CMSG_RECVFRAGSIZE BIT(8) /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket * * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ static inline struct sock *sk_to_full_sk(struct sock *sk) { #ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; #endif return sk; } /* sk_to_full_sk() variant with a const argument */ static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) { #ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = ((const struct request_sock *)sk)->rsk_listener; #endif return sk; } static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) { return sk_to_full_sk(skb->sk); } static inline struct inet_sock *inet_sk(const struct sock *sk) { return (struct inet_sock *)sk; } static inline void __inet_sk_copy_descendant(struct sock *sk_to, const struct sock *sk_from, const int ancestor_size) { memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } int inet_sk_rebuild_header(struct sock *sk); /** * inet_sk_state_load - read sk->sk_state for lockless contexts * @sk: socket pointer * * Paired with inet_sk_state_store(). Used in places we don't hold socket lock: * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... */ static inline int inet_sk_state_load(const struct sock *sk) { /* state change might impact lockless readers. */ return smp_load_acquire(&sk->sk_state); } /** * inet_sk_state_store - update sk->sk_state * @sk: socket pointer * @newstate: new state * * Paired with inet_sk_state_load(). Should be used in contexts where * state change might impact lockless readers. */ void inet_sk_state_store(struct sock *sk, int newstate); void inet_sk_set_state(struct sock *sk, int state); static inline unsigned int __inet_ehashfn(const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport, u32 initval) { return jhash_3words((__force __u32) laddr, (__force __u32) faddr, ((__u32) lport) << 16 | (__force __u32)fport, initval); } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl) flags |= FLOWI_FLAG_ANYSRC; return flags; } static inline void inet_inc_convert_csum(struct sock *sk) { inet_sk(sk)->convert_csum++; } static inline void inet_dec_convert_csum(struct sock *sk) { if (inet_sk(sk)->convert_csum > 0) inet_sk(sk)->convert_csum--; } static inline bool inet_get_convert_csum(struct sock *sk) { return !!inet_sk(sk)->convert_csum; } static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv4.sysctl_ip_nonlocal_bind || inet->freebind || inet->transparent; } #endif /* _INET_SOCK_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) { unsigned long start = 0UL, end = TLB_FLUSH_ALL; unsigned int stride_shift = tlb_get_unmap_shift(tlb); if (!tlb->fullmm && !tlb->need_flush_all) { start = tlb->start; end = tlb->end; } flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); } /* * While x86 architecture in general requires an IPI to perform TLB * shootdown, enablement code for several hypervisors overrides * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing * a hypercall. To keep software pagetable walkers safe in this case we * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h * for more details. */ static inline void __tlb_remove_table(void *table) { free_page_and_swap_cache(table); } #endif /* _ASM_X86_TLB_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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2016 Qualcomm Atheros, Inc * * Based on net/sched/sch_fq_codel.c */ #ifndef __NET_SCHED_FQ_IMPL_H #define __NET_SCHED_FQ_IMPL_H #include <net/fq.h> /* functions that are embedded into includer */ static void fq_adjust_removal(struct fq *fq, struct fq_flow *flow, struct sk_buff *skb) { struct fq_tin *tin = flow->tin; tin->backlog_bytes -= skb->len; tin->backlog_packets--; flow->backlog -= skb->len; fq->backlog--; fq->memory_usage -= skb->truesize; } static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow) { struct fq_flow *i; if (flow->backlog == 0) { list_del_init(&flow->backlogchain); } else { i = flow; list_for_each_entry_continue(i, &fq->backlogs, backlogchain) if (i->backlog < flow->backlog) break; list_move_tail(&flow->backlogchain, &i->backlogchain); } } static struct sk_buff *fq_flow_dequeue(struct fq *fq, struct fq_flow *flow) { struct sk_buff *skb; lockdep_assert_held(&fq->lock); skb = __skb_dequeue(&flow->queue); if (!skb) return NULL; fq_adjust_removal(fq, flow, skb); fq_rejigger_backlog(fq, flow); return skb; } static struct sk_buff *fq_tin_dequeue(struct fq *fq, struct fq_tin *tin, fq_tin_dequeue_t dequeue_func) { struct fq_flow *flow; struct list_head *head; struct sk_buff *skb; lockdep_assert_held(&fq->lock); begin: head = &tin->new_flows; if (list_empty(head)) { head = &tin->old_flows; if (list_empty(head)) return NULL; } flow = list_first_entry(head, struct fq_flow, flowchain); if (flow->deficit <= 0) { flow->deficit += fq->quantum; list_move_tail(&flow->flowchain, &tin->old_flows); goto begin; } skb = dequeue_func(fq, tin, flow); if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &tin->new_flows) && !list_empty(&tin->old_flows)) { list_move_tail(&flow->flowchain, &tin->old_flows); } else { list_del_init(&flow->flowchain); flow->tin = NULL; } goto begin; } flow->deficit -= skb->len; tin->tx_bytes += skb->len; tin->tx_packets++; return skb; } static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) { u32 hash = skb_get_hash(skb); return reciprocal_scale(hash, fq->flows_cnt); } static struct fq_flow *fq_flow_classify(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_flow_get_default_t get_default_func) { struct fq_flow *flow; lockdep_assert_held(&fq->lock); flow = &fq->flows[idx]; if (flow->tin && flow->tin != tin) { flow = get_default_func(fq, tin, idx, skb); tin->collisions++; fq->collisions++; } if (!flow->tin) tin->flows++; return flow; } static void fq_recalc_backlog(struct fq *fq, struct fq_tin *tin, struct fq_flow *flow) { struct fq_flow *i; if (list_empty(&flow->backlogchain)) list_add_tail(&flow->backlogchain, &fq->backlogs); i = flow; list_for_each_entry_continue_reverse(i, &fq->backlogs, backlogchain) if (i->backlog > flow->backlog) break; list_move(&flow->backlogchain, &i->backlogchain); } static void fq_tin_enqueue(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_skb_free_t free_func, fq_flow_get_default_t get_default_func) { struct fq_flow *flow; bool oom; lockdep_assert_held(&fq->lock); flow = fq_flow_classify(fq, tin, idx, skb, get_default_func); flow->tin = tin; flow->backlog += skb->len; tin->backlog_bytes += skb->len; tin->backlog_packets++; fq->memory_usage += skb->truesize; fq->backlog++; fq_recalc_backlog(fq, tin, flow); if (list_empty(&flow->flowchain)) { flow->deficit = fq->quantum; list_add_tail(&flow->flowchain, &tin->new_flows); } __skb_queue_tail(&flow->queue, skb); oom = (fq->memory_usage > fq->memory_limit); while (fq->backlog > fq->limit || oom) { flow = list_first_entry_or_null(&fq->backlogs, struct fq_flow, backlogchain); if (!flow) return; skb = fq_flow_dequeue(fq, flow); if (!skb) return; free_func(fq, flow->tin, flow, skb); flow->tin->overlimit++; fq->overlimit++; if (oom) { fq->overmemory++; oom = (fq->memory_usage > fq->memory_limit); } } } static void fq_flow_filter(struct fq *fq, struct fq_flow *flow, fq_skb_filter_t filter_func, void *filter_data, fq_skb_free_t free_func) { struct fq_tin *tin = flow->tin; struct sk_buff *skb, *tmp; lockdep_assert_held(&fq->lock); skb_queue_walk_safe(&flow->queue, skb, tmp) { if (!filter_func(fq, tin, flow, skb, filter_data)) continue; __skb_unlink(skb, &flow->queue); fq_adjust_removal(fq, flow, skb); free_func(fq, tin, flow, skb); } fq_rejigger_backlog(fq, flow); } static void fq_tin_filter(struct fq *fq, struct fq_tin *tin, fq_skb_filter_t filter_func, void *filter_data, fq_skb_free_t free_func) { struct fq_flow *flow; lockdep_assert_held(&fq->lock); list_for_each_entry(flow, &tin->new_flows, flowchain) fq_flow_filter(fq, flow, filter_func, filter_data, free_func); list_for_each_entry(flow, &tin->old_flows, flowchain) fq_flow_filter(fq, flow, filter_func, filter_data, free_func); } static void fq_flow_reset(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) { struct sk_buff *skb; while ((skb = fq_flow_dequeue(fq, flow))) free_func(fq, flow->tin, flow, skb); if (!list_empty(&flow->flowchain)) list_del_init(&flow->flowchain); if (!list_empty(&flow->backlogchain)) list_del_init(&flow->backlogchain); flow->tin = NULL; WARN_ON_ONCE(flow->backlog); } static void fq_tin_reset(struct fq *fq, struct fq_tin *tin, fq_skb_free_t free_func) { struct list_head *head; struct fq_flow *flow; for (;;) { head = &tin->new_flows; if (list_empty(head)) { head = &tin->old_flows; if (list_empty(head)) break; } flow = list_first_entry(head, struct fq_flow, flowchain); fq_flow_reset(fq, flow, free_func); } WARN_ON_ONCE(tin->backlog_bytes); WARN_ON_ONCE(tin->backlog_packets); } static void fq_flow_init(struct fq_flow *flow) { INIT_LIST_HEAD(&flow->flowchain); INIT_LIST_HEAD(&flow->backlogchain); __skb_queue_head_init(&flow->queue); } static void fq_tin_init(struct fq_tin *tin) { INIT_LIST_HEAD(&tin->new_flows); INIT_LIST_HEAD(&tin->old_flows); } static int fq_init(struct fq *fq, int flows_cnt) { int i; memset(fq, 0, sizeof(fq[0])); INIT_LIST_HEAD(&fq->backlogs); spin_lock_init(&fq->lock); fq->flows_cnt = max_t(u32, flows_cnt, 1); fq->quantum = 300; fq->limit = 8192; fq->memory_limit = 16 << 20; /* 16 MBytes */ fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); if (!fq->flows) return -ENOMEM; for (i = 0; i < fq->flows_cnt; i++) fq_flow_init(&fq->flows[i]); return 0; } static void fq_reset(struct fq *fq, fq_skb_free_t free_func) { int i; for (i = 0; i < fq->flows_cnt; i++) fq_flow_reset(fq, &fq->flows[i], free_func); kvfree(fq->flows); fq->flows = NULL; } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/vm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_* entry. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 2 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #else #define SWP_DEVICE_NUM 0 #endif /* * NUMA node memory migration support */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 2 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { unsigned long reclaimed_slab; }; #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A list of swap extents maps the entire swapfile. (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file. Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ SWP_VALID = (1 << 13), /* swap is valid to be operated on? */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The data field stores next cluster if the cluster is free or cluster usage * counter otherwise. The flags field determines if a cluster is free. This is * protected by swap_info_struct.lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * and swap_info_struct->swap_map * elements correspond to the swap * cluster */ unsigned int data:24; unsigned int flags:8; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ #define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { struct swap_cluster_info index; /* Current cluster index */ unsigned int next; /* Likely next allocation offset */ }; struct swap_cluster_list { struct swap_cluster_info head; struct swap_cluster_info tail; }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct swap_cluster_list free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ #ifdef CONFIG_FRONTSWAP unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ #endif spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct swap_cluster_list discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; #ifdef CONFIG_64BIT #define SWAP_RA_ORDER_CEILING 5 #else /* Avoid stack overflow, because we need to save part of page table */ #define SWAP_RA_ORDER_CEILING 3 #define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) #endif struct vma_swap_readahead { unsigned short win; unsigned short offset; unsigned short nr_pte; #ifdef CONFIG_64BIT pte_t *ptes; #else pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; #endif }; /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); #define mapping_set_update(xas, mapping) do { \ if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ xas_set_update(xas, workingset_update_node); \ } while (0) /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; extern unsigned long nr_free_buffer_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); extern void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); extern int __isolate_lru_page(struct page *page, isolate_mode_t mode); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif extern void check_move_unevictable_pages(struct pagevec *pvec); extern int kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP #include <linux/blk_types.h> /* for bio_end_io_t */ /* linux/mm/page_io.c */ extern int swap_readpage(struct page *page, bool do_poll); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func); extern int swap_set_page_dirty(struct page *page); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); /* linux/mm/swap_state.c */ /* One swap address space for each 64M swap space */ #define SWAP_ADDRESS_SPACE_SHIFT 14 #define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) extern struct address_space *swapper_spaces[]; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern void *get_shadow_from_swap_cache(swp_entry_t entry); extern int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp, void **shadowp); extern void __delete_from_swap_cache(struct page *page, swp_entry_t entry, void *shadow); extern void delete_from_swap_cache(struct page *); extern void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool do_poll); extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated); extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(struct page *page); extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern int free_swap_and_cache(swp_entry_t); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_page_sector(struct page *page); static inline void put_swap_device(struct swap_info_struct *si) { rcu_read_unlock(); } #else /* CONFIG_SWAP */ static inline int swap_readpage(struct page *page, bool do_poll) { return 0; } static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } #define swap_address_space(entry) (NULL) #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void show_swap_cache_info(void) { } #define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) #define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline void swap_free(swp_entry_t swp) { } static inline void put_swap_page(struct page *page, swp_entry_t swp) { } static inline struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { return NULL; } static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, struct vm_fault *vmf) { return NULL; } static inline int swap_writepage(struct page *p, struct writeback_control *wbc) { return 0; } static inline struct page *lookup_swap_cache(swp_entry_t swp, struct vm_area_struct *vma, unsigned long addr) { return NULL; } static inline struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) { return find_get_page(mapping, index); } static inline int add_to_swap(struct page *page) { return 0; } static inline void *get_shadow_from_swap_cache(swp_entry_t entry) { return NULL; } static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask, void **shadowp) { return -1; } static inline void __delete_from_swap_cache(struct page *page, swp_entry_t entry, void *shadow) { } static inline void delete_from_swap_cache(struct page *page) { } static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end) { } static inline int page_swapcount(struct page *page) { return 0; } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int __swp_swapcount(swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } #define reuse_swap_page(page, total_map_swapcount) \ (page_trans_huge_mapcount(page, total_map_swapcount) == 1) static inline int try_to_free_swap(struct page *page) { return 0; } static inline swp_entry_t get_swap_page(struct page *page) { swp_entry_t entry; entry.val = 0; return entry; } #endif /* CONFIG_SWAP */ #ifdef CONFIG_THP_SWAP extern int split_swap_cluster(swp_entry_t entry); #else static inline int split_swap_cluster(swp_entry_t entry) { return 0; } #endif #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return vm_swappiness; /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return vm_swappiness; return memcg->swappiness; } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return vm_swappiness; } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); #else static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct page *page); #else static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct page *page) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib #if !defined(_TRACE_FIB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <net/ip_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib_table_lookup, TP_PROTO(u32 tb_id, const struct flowi4 *flp, const struct fib_nh_common *nhc, int err), TP_ARGS(tb_id, flp, nhc, err), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( u8, proto ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 4 ) __array( __u8, dst, 4 ) __array( __u8, gw4, 4 ) __array( __u8, gw6, 16 ) __field( u16, sport ) __field( u16, dport ) __dynamic_array(char, name, IFNAMSIZ ) ), TP_fast_assign( struct in6_addr in6_zero = {}; struct net_device *dev; struct in6_addr *in6; __be32 *p32; __entry->tb_id = tb_id; __entry->err = err; __entry->oif = flp->flowi4_oif; __entry->iif = flp->flowi4_iif; __entry->tos = flp->flowi4_tos; __entry->scope = flp->flowi4_scope; __entry->flags = flp->flowi4_flags; p32 = (__be32 *) __entry->src; *p32 = flp->saddr; p32 = (__be32 *) __entry->dst; *p32 = flp->daddr; __entry->proto = flp->flowi4_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl4_sport); __entry->dport = ntohs(flp->fl4_dport); } else { __entry->sport = 0; __entry->dport = 0; } dev = nhc ? nhc->nhc_dev : NULL; __assign_str(name, dev ? dev->name : "-"); if (nhc) { if (nhc->nhc_gw_family == AF_INET) { p32 = (__be32 *) __entry->gw4; *p32 = nhc->nhc_gw.ipv4; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6_zero; } else if (nhc->nhc_gw_family == AF_INET6) { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = nhc->nhc_gw.ipv6; } } else { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6_zero; } ), TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4/%pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __get_str(name), __entry->gw4, __entry->gw6, __entry->err) ); #endif /* _TRACE_FIB_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 #undef TRACE_SYSTEM #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_QDISC_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/pkt_sched.h> #include <net/sch_generic.h> TRACE_EVENT(qdisc_dequeue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, int packets, struct sk_buff *skb), TP_ARGS(qdisc, txq, packets, skb), TP_STRUCT__entry( __field( struct Qdisc *, qdisc ) __field(const struct netdev_queue *, txq ) __field( int, packets ) __field( void *, skbaddr ) __field( int, ifindex ) __field( u32, handle ) __field( u32, parent ) __field( unsigned long, txq_state) ), /* skb==NULL indicate packets dequeued was 0, even when packets==1 */ TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->packets = skb ? packets : 0; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; __entry->txq_state = txq->state; ), TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); TRACE_EVENT(qdisc_reset, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_destroy, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_create, TP_PROTO(const struct Qdisc_ops *ops, struct net_device *dev, u32 parent), TP_ARGS(ops, dev, parent), TP_STRUCT__entry( __string( dev, dev->name ) __string( kind, ops->id ) __field( u32, parent ) ), TP_fast_assign( __assign_str(dev, dev->name); __assign_str(kind, ops->id); __entry->parent = parent; ), TP_printk("dev=%s kind=%s parent=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent)) ); #endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/xattr.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> * * Fix by Harrison Xing <harrison@mountainviewdata.com>. * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>. * Extended attributes for symlinks and special files added per * suggestion of Luka Renko <luka.renko@hermes.si>. * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, * Red Hat Inc. * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz * and Andreas Gruenbacher <agruen@suse.de>. */ /* * Extended attributes are stored directly in inodes (on file systems with * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl * field contains the block number if an inode uses an additional block. All * attributes must fit in the inode and one additional block. Blocks that * contain the identical set of attributes may be shared among several inodes. * Identical blocks are detected by keeping a cache of blocks that have * recently been accessed. * * The attributes in inodes and on blocks have a different header; the entries * are stored in the same format: * * +------------------+ * | header | * | entry 1 | | * | entry 2 | | growing downwards * | entry 3 | v * | four null bytes | * | . . . | * | value 1 | ^ * | value 3 | | growing upwards * | value 2 | | * +------------------+ * * The header is followed by multiple entry descriptors. In disk blocks, the * entry descriptors are kept sorted. In inodes, they are unsorted. The * attribute values are aligned to the end of the block in no specific order. * * Locking strategy * ---------------- * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem. * EA blocks are only changed if they are exclusive to an inode, so * holding xattr_sem also means that nothing but the EA block's reference * count can change. Multiple writers to the same block are synchronized * by the buffer lock. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "acl.h" #ifdef EXT4_XATTR_DEBUG # define ea_idebug(inode, fmt, ...) \ printk(KERN_DEBUG "inode %s:%lu: " fmt "\n", \ inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) \ printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \ bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__) #else # define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif static void ext4_xattr_block_cache_insert(struct mb_cache *, struct buffer_head *); static struct buffer_head * ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count); static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, #ifdef CONFIG_EXT4_FS_POSIX_ACL [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler, [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler, #endif [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler, #endif [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; const struct xattr_handler *ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_POSIX_ACL &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, #endif #ifdef CONFIG_EXT4_FS_SECURITY &ext4_xattr_security_handler, #endif &ext4_xattr_hurd_handler, NULL }; #define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_block_cache) #define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_inode_cache) static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode); #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { lockdep_set_subclass(&ea_inode->i_rwsem, 1); } #endif static __le32 ext4_xattr_block_csum(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le64 dsk_block_nr = cpu_to_le64(block_nr); __u32 dummy_csum = 0; int offset = offsetof(struct ext4_xattr_header, h_checksum); csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr, sizeof(dsk_block_nr)); csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset); csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset, EXT4_BLOCK_SIZE(inode->i_sb) - offset); return cpu_to_le32(csum); } static int ext4_xattr_block_csum_verify(struct inode *inode, struct buffer_head *bh) { struct ext4_xattr_header *hdr = BHDR(bh); int ret = 1; if (ext4_has_metadata_csum(inode->i_sb)) { lock_buffer(bh); ret = (hdr->h_checksum == ext4_xattr_block_csum(inode, bh->b_blocknr, hdr)); unlock_buffer(bh); } return ret; } static void ext4_xattr_block_csum_set(struct inode *inode, struct buffer_head *bh) { if (ext4_has_metadata_csum(inode->i_sb)) BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode, bh->b_blocknr, BHDR(bh)); } static inline const struct xattr_handler * ext4_xattr_handler(int name_index) { const struct xattr_handler *handler = NULL; if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map)) handler = ext4_xattr_handler_map[name_index]; return handler; } static int ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end, void *value_start) { struct ext4_xattr_entry *e = entry; /* Find the end of the names list */ while (!IS_LAST_ENTRY(e)) { struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) return -EFSCORRUPTED; if (strnlen(e->e_name, e->e_name_len) != e->e_name_len) return -EFSCORRUPTED; e = next; } /* Check the values */ while (!IS_LAST_ENTRY(entry)) { u32 size = le32_to_cpu(entry->e_value_size); if (size > EXT4_XATTR_SIZE_MAX) return -EFSCORRUPTED; if (size != 0 && entry->e_value_inum == 0) { u16 offs = le16_to_cpu(entry->e_value_offs); void *value; /* * The value cannot overlap the names, and the value * with padding cannot extend beyond 'end'. Check both * the padded and unpadded sizes, since the size may * overflow to 0 when adding padding. */ if (offs > end - value_start) return -EFSCORRUPTED; value = value_start + offs; if (value < (void *)e + sizeof(u32) || size > end - value || EXT4_XATTR_SIZE(size) > end - value) return -EFSCORRUPTED; } entry = EXT4_XATTR_NEXT(entry); } return 0; } static inline int __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh, const char *function, unsigned int line) { int error = -EFSCORRUPTED; if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) goto errout; if (buffer_verified(bh)) return 0; error = -EFSBADCRC; if (!ext4_xattr_block_csum_verify(inode, bh)) goto errout; error = ext4_xattr_check_entries(BFIRST(bh), bh->b_data + bh->b_size, bh->b_data); errout: if (error) __ext4_error_inode(inode, function, line, 0, -error, "corrupted xattr block %llu", (unsigned long long) bh->b_blocknr); else set_buffer_verified(bh); return error; } #define ext4_xattr_check_block(inode, bh) \ __ext4_xattr_check_block((inode), (bh), __func__, __LINE__) static int __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, void *end, const char *function, unsigned int line) { int error = -EFSCORRUPTED; if (end - (void *)header < sizeof(*header) + sizeof(u32) || (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC))) goto errout; error = ext4_xattr_check_entries(IFIRST(header), end, IFIRST(header)); errout: if (error) __ext4_error_inode(inode, function, line, 0, -error, "corrupted in-inode xattr"); return error; } #define xattr_check_inode(inode, header, end) \ __xattr_check_inode((inode), (header), (end), __func__, __LINE__) static int xattr_find_entry(struct inode *inode, struct ext4_xattr_entry **pentry, void *end, int name_index, const char *name, int sorted) { struct ext4_xattr_entry *entry, *next; size_t name_len; int cmp = 1; if (name == NULL) return -EINVAL; name_len = strlen(name); for (entry = *pentry; !IS_LAST_ENTRY(entry); entry = next) { next = EXT4_XATTR_NEXT(entry); if ((void *) next >= end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); return -EFSCORRUPTED; } cmp = name_index - entry->e_name_index; if (!cmp) cmp = name_len - entry->e_name_len; if (!cmp) cmp = memcmp(name, entry->e_name, name_len); if (cmp <= 0 && (sorted || cmp == 0)) break; } *pentry = entry; return cmp ? -ENODATA : 0; } static u32 ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) { return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size); } static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) { return ((u64)ea_inode->i_ctime.tv_sec << 32) | (u32) inode_peek_iversion_raw(ea_inode); } static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) { ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32); inode_set_iversion_raw(ea_inode, ref_count & 0xffffffff); } static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) { return (u32)ea_inode->i_atime.tv_sec; } static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) { ea_inode->i_atime.tv_sec = hash; } /* * Read the EA value from an inode. */ static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size) { int blocksize = 1 << ea_inode->i_blkbits; int bh_count = (size + blocksize - 1) >> ea_inode->i_blkbits; int tail_size = (size % blocksize) ?: blocksize; struct buffer_head *bhs_inline[8]; struct buffer_head **bhs = bhs_inline; int i, ret; if (bh_count > ARRAY_SIZE(bhs_inline)) { bhs = kmalloc_array(bh_count, sizeof(*bhs), GFP_NOFS); if (!bhs) return -ENOMEM; } ret = ext4_bread_batch(ea_inode, 0 /* block */, bh_count, true /* wait */, bhs); if (ret) goto free_bhs; for (i = 0; i < bh_count; i++) { /* There shouldn't be any holes in ea_inode. */ if (!bhs[i]) { ret = -EFSCORRUPTED; goto put_bhs; } memcpy((char *)buf + blocksize * i, bhs[i]->b_data, i < bh_count - 1 ? blocksize : tail_size); } ret = 0; put_bhs: for (i = 0; i < bh_count; i++) brelse(bhs[i]); free_bhs: if (bhs != bhs_inline) kfree(bhs); return ret; } #define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec) static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, u32 ea_inode_hash, struct inode **ea_inode) { struct inode *inode; int err; inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, "error while reading EA inode %lu err=%d", ea_ino, err); return err; } if (is_bad_inode(inode)) { ext4_error(parent->i_sb, "error while reading EA inode %lu is_bad_inode", ea_ino); err = -EIO; goto error; } if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { ext4_error(parent->i_sb, "EA inode %lu does not have EXT4_EA_INODE_FL flag", ea_ino); err = -EINVAL; goto error; } ext4_xattr_inode_set_class(inode); /* * Check whether this is an old Lustre-style xattr inode. Lustre * implementation does not have hash validation, rather it has a * backpointer from ea_inode to the parent inode. */ if (ea_inode_hash != ext4_xattr_inode_get_hash(inode) && EXT4_XATTR_INODE_GET_PARENT(inode) == parent->i_ino && inode->i_generation == parent->i_generation) { ext4_set_inode_state(inode, EXT4_STATE_LUSTRE_EA_INODE); ext4_xattr_inode_set_ref(inode, 1); } else { inode_lock(inode); inode->i_flags |= S_NOQUOTA; inode_unlock(inode); } *ea_inode = inode; return 0; error: iput(inode); return err; } static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { u32 hash; /* Verify stored hash matches calculated hash. */ hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size); if (hash != ext4_xattr_inode_get_hash(ea_inode)) return -EFSCORRUPTED; if (entry) { __le32 e_hash, tmp_data; /* Verify entry hash. */ tmp_data = cpu_to_le32(hash); e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, &tmp_data, 1); if (e_hash != entry->e_hash) return -EFSCORRUPTED; } return 0; } /* * Read xattr value from the EA inode. */ static int ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); struct inode *ea_inode; int err; err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ea_inode = NULL; goto out; } if (i_size_read(ea_inode) != size) { ext4_warning_inode(ea_inode, "ea_inode file size=%llu entry size=%zu", i_size_read(ea_inode), size); err = -EFSCORRUPTED; goto out; } err = ext4_xattr_inode_read(ea_inode, buffer, size); if (err) goto out; if (!ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) { err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size); if (err) { ext4_warning_inode(ea_inode, "EA inode hash validation failed"); goto out; } if (ea_inode_cache) mb_cache_entry_create(ea_inode_cache, GFP_NOFS, ext4_xattr_inode_get_hash(ea_inode), ea_inode->i_ino, true /* reusable */); } out: iput(ea_inode); return err; } static int ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct buffer_head *bh = NULL; struct ext4_xattr_entry *entry; size_t size; void *end; int error; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return -ENODATA; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(ea_block_cache, bh); entry = BFIRST(bh); end = bh->b_data + bh->b_size; error = xattr_find_entry(inode, &entry, end, name_index, name, 1); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = bh->b_data + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(bh); return error; } int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; struct ext4_iloc iloc; size_t size; void *end; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return -ENODATA; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; error = xattr_check_inode(inode, header, end); if (error) goto cleanup; entry = IFIRST(header); error = xattr_find_entry(inode, &entry, end, name_index, name, 0); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = (void *)IFIRST(header) + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(iloc.bh); return error; } /* * ext4_xattr_get() * * Copy an extended attribute into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ int ext4_xattr_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { int error; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; if (strlen(name) > 255) return -ERANGE; down_read(&EXT4_I(inode)->xattr_sem); error = ext4_xattr_ibody_get(inode, name_index, name, buffer, buffer_size); if (error == -ENODATA) error = ext4_xattr_block_get(inode, name_index, name, buffer, buffer_size); up_read(&EXT4_I(inode)->xattr_sem); return error; } static int ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, char *buffer, size_t buffer_size) { size_t rest = buffer_size; for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { const struct xattr_handler *handler = ext4_xattr_handler(entry->e_name_index); if (handler && (!handler->list || handler->list(dentry))) { const char *prefix = handler->prefix ?: handler->name; size_t prefix_len = strlen(prefix); size_t size = prefix_len + entry->e_name_len + 1; if (buffer) { if (size > rest) return -ERANGE; memcpy(buffer, prefix, prefix_len); buffer += prefix_len; memcpy(buffer, entry->e_name, entry->e_name_len); buffer += entry->e_name_len; *buffer++ = 0; } rest -= size; } } return buffer_size - rest; /* total size */ } static int ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return 0; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: brelse(bh); return error; } static int ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; struct ext4_iloc iloc; void *end; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return 0; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; error = xattr_check_inode(inode, header, end); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), buffer, buffer_size); cleanup: brelse(iloc.bh); return error; } /* * Inode operation listxattr() * * d_inode(dentry)->i_rwsem: don't care * * Copy a list of attribute names into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ ssize_t ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { int ret, ret2; down_read(&EXT4_I(d_inode(dentry))->xattr_sem); ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; if (buffer) { buffer += ret; buffer_size -= ret; } ret = ext4_xattr_block_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; ret += ret2; errout: up_read(&EXT4_I(d_inode(dentry))->xattr_sem); return ret; } /* * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is * not set, set it. */ static void ext4_xattr_update_super_block(handle_t *handle, struct super_block *sb) { if (ext4_has_feature_xattr(sb)) return; BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { ext4_set_feature_xattr(sb); ext4_handle_dirty_super(handle, sb); } } int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) { struct ext4_iloc iloc = { .bh = NULL }; struct buffer_head *bh = NULL; struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; qsize_t ea_inode_refs = 0; void *end; int ret; lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem); if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; ret = xattr_check_inode(inode, header, end); if (ret) goto out; for (entry = IFIRST(header); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { ret = PTR_ERR(bh); bh = NULL; goto out; } ret = ext4_xattr_check_block(inode, bh); if (ret) goto out; for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } *usage = ea_inode_refs + 1; ret = 0; out: brelse(iloc.bh); brelse(bh); return ret; } static inline size_t round_up_cluster(struct inode *inode, size_t length) { struct super_block *sb = inode->i_sb; size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits + inode->i_blkbits); size_t mask = ~(cluster_size - 1); return (length + cluster_size - 1) & mask; } static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len) { int err; err = dquot_alloc_inode(inode); if (err) return err; err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len)); if (err) dquot_free_inode(inode); return err; } static void ext4_xattr_inode_free_quota(struct inode *parent, struct inode *ea_inode, size_t len) { if (ea_inode && ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) return; dquot_free_space_nodirty(parent, round_up_cluster(parent, len)); dquot_free_inode(parent); } int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, struct buffer_head *block_bh, size_t value_len, bool is_create) { int credits; int blocks; /* * 1) Owner inode update * 2) Ref count update on old xattr block * 3) new xattr block * 4) block bitmap update for new xattr block * 5) group descriptor for new xattr block * 6) block bitmap update for old xattr block * 7) group descriptor for old block * * 6 & 7 can happen if we have two racing threads T_a and T_b * which are each trying to set an xattr on inodes I_a and I_b * which were both initially sharing an xattr block. */ credits = 7; /* Quota updates. */ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb); /* * In case of inline data, we may push out the data to a block, * so we need to reserve credits for this eventuality */ if (inode && ext4_has_inline_data(inode)) credits += ext4_writepage_trans_blocks(inode) + 1; /* We are done if ea_inode feature is not enabled. */ if (!ext4_has_feature_ea_inode(sb)) return credits; /* New ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks. */ blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; /* Blocks themselves. */ credits += blocks; if (!is_create) { /* Dereference ea_inode holding old xattr value. * Old ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks for old ea_inode. */ blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree for old * ea_inode. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; } /* We may need to clone the existing xattr block in which case we need * to increment ref counts for existing ea_inodes referenced by it. */ if (block_bh) { struct ext4_xattr_entry *entry = BFIRST(block_bh); for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) /* Ref count update on ea_inode. */ credits += 1; } return credits; } static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); struct ext4_iloc iloc; s64 ref_count; u32 hash; int ret; inode_lock(ea_inode); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); if (ret) goto out; ref_count = ext4_xattr_inode_get_ref(ea_inode); ref_count += ref_change; ext4_xattr_inode_set_ref(ea_inode, ref_count); if (ref_change > 0) { WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld", ea_inode->i_ino, ref_count); if (ref_count == 1) { WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); if (ea_inode_cache) { hash = ext4_xattr_inode_get_hash(ea_inode); mb_cache_entry_create(ea_inode_cache, GFP_NOFS, hash, ea_inode->i_ino, true /* reusable */); } } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", ea_inode->i_ino, ref_count); if (ref_count == 0) { WARN_ONCE(ea_inode->i_nlink != 1, "EA inode %lu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); if (ea_inode_cache) { hash = ext4_xattr_inode_get_hash(ea_inode); mb_cache_entry_delete(ea_inode_cache, hash, ea_inode->i_ino); } } } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: inode_unlock(ea_inode); return ret; } static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, 1); } static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, -1); } static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent, struct ext4_xattr_entry *first) { struct inode *ea_inode; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *failed_entry; unsigned int ea_ino; int err, saved_err; for (entry = first; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) goto cleanup; err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "inc ref error %d", err); iput(ea_inode); goto cleanup; } iput(ea_inode); } return 0; cleanup: saved_err = err; failed_entry = entry; for (entry = first; entry != failed_entry; entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ext4_warning(parent->i_sb, "cleanup ea_ino %u iget error %d", ea_ino, err); continue; } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); iput(ea_inode); } return saved_err; } static int ext4_xattr_restart_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh, bool block_csum, bool dirty) { int error; if (bh && dirty) { if (block_csum) ext4_xattr_block_csum_set(inode, bh); error = ext4_handle_dirty_metadata(handle, NULL, bh); if (error) { ext4_warning(inode->i_sb, "Handle metadata (error %d)", error); return error; } } return 0; } static void ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, struct buffer_head *bh, struct ext4_xattr_entry *first, bool block_csum, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits, bool skip_quota) { struct inode *ea_inode; struct ext4_xattr_entry *entry; bool dirty = false; unsigned int ea_ino; int err; int credits; /* One credit for dec ref on ea_inode, one for orphan list addition, */ credits = 2 + extra_credits; for (entry = first; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) continue; err = ext4_expand_inode_array(ea_inode_array, ea_inode); if (err) { ext4_warning_inode(ea_inode, "Expand inode array err=%d", err); iput(ea_inode); continue; } err = ext4_journal_ensure_credits_fn(handle, credits, credits, ext4_free_metadata_revoke_credits(parent->i_sb, 1), ext4_xattr_restart_fn(handle, parent, bh, block_csum, dirty)); if (err < 0) { ext4_warning_inode(ea_inode, "Ensure credits err=%d", err); continue; } if (err > 0) { err = ext4_journal_get_write_access(handle, bh); if (err) { ext4_warning_inode(ea_inode, "Re-get write access err=%d", err); continue; } } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d", err); continue; } if (!skip_quota) ext4_xattr_inode_free_quota(parent, ea_inode, le32_to_cpu(entry->e_value_size)); /* * Forget about ea_inode within the same transaction that * decrements the ref count. This avoids duplicate decrements in * case the rest of the work spills over to subsequent * transactions. */ entry->e_value_inum = 0; entry->e_value_size = 0; dirty = true; } if (dirty) { /* * Note that we are deliberately skipping csum calculation for * the final update because we do not expect any journal * restarts until xattr block is freed. */ err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) ext4_warning_inode(parent, "handle dirty metadata err=%d", err); } } /* * Release the xattr block BH: If the reference count is > 1, decrement it; * otherwise free the block. */ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, struct buffer_head *bh, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits) { struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); u32 hash, ref; int error = 0; BUFFER_TRACE(bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bh); if (error) goto out; lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); if (ref == 1) { ea_bdebug(bh, "refcount now=0; freeing"); /* * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ if (ea_block_cache) mb_cache_entry_delete(ea_block_cache, hash, bh->b_blocknr); get_bh(bh); unlock_buffer(bh); if (ext4_has_feature_ea_inode(inode->i_sb)) ext4_xattr_inode_dec_ref_all(handle, inode, bh, BFIRST(bh), true /* block_csum */, ea_inode_array, extra_credits, true /* skip_quota */); ext4_free_blocks(handle, inode, bh, 0, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } else { ref--; BHDR(bh)->h_refcount = cpu_to_le32(ref); if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) { struct mb_cache_entry *ce; if (ea_block_cache) { ce = mb_cache_entry_get(ea_block_cache, hash, bh->b_blocknr); if (ce) { ce->e_reusable = 1; mb_cache_entry_put(ea_block_cache, ce); } } } ext4_xattr_block_csum_set(inode, bh); /* * Beware of this ugliness: Releasing of xattr block references * from different inodes can race and so we have to protect * from a race where someone else frees the block (and releases * its journal_head) before we are done dirtying the buffer. In * nojournal mode this race is harmless and we actually cannot * call ext4_handle_dirty_metadata() with locked buffer as * that function can call sync_dirty_buffer() so for that case * we handle the dirtying after unlocking the buffer. */ if (ext4_handle_valid(handle)) error = ext4_handle_dirty_metadata(handle, inode, bh); unlock_buffer(bh); if (!ext4_handle_valid(handle)) error = ext4_handle_dirty_metadata(handle, inode, bh); if (IS_SYNC(inode)) ext4_handle_sync(handle); dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1)); ea_bdebug(bh, "refcount now=%d; releasing", le32_to_cpu(BHDR(bh)->h_refcount)); } out: ext4_std_error(inode->i_sb, error); return; } /* * Find the available free space for EAs. This also returns the total number of * bytes used by EA entries. */ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, size_t *min_offs, void *base, int *total) { for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < *min_offs) *min_offs = offs; } if (total) *total += EXT4_XATTR_LEN(last->e_name_len); } return (*min_offs - ((void *)last - base) - sizeof(__u32)); } /* * Write the value of the EA in an inode. */ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, const void *buf, int bufsize) { struct buffer_head *bh = NULL; unsigned long block = 0; int blocksize = ea_inode->i_sb->s_blocksize; int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits; int csize, wsize = 0; int ret = 0, ret2 = 0; int retries = 0; retry: while (ret >= 0 && ret < max_blocks) { struct ext4_map_blocks map; map.m_lblk = block += ret; map.m_len = max_blocks -= ret; ret = ext4_map_blocks(handle, ea_inode, &map, EXT4_GET_BLOCKS_CREATE); if (ret <= 0) { ext4_mark_inode_dirty(handle, ea_inode); if (ret == -ENOSPC && ext4_should_retry_alloc(ea_inode->i_sb, &retries)) { ret = 0; goto retry; } break; } } if (ret < 0) return ret; block = 0; while (wsize < bufsize) { brelse(bh); csize = (bufsize - wsize) > blocksize ? blocksize : bufsize - wsize; bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) { WARN_ON_ONCE(1); EXT4_ERROR_INODE(ea_inode, "ext4_getblk() return bh = NULL"); return -EFSCORRUPTED; } ret = ext4_journal_get_write_access(handle, bh); if (ret) goto out; memcpy(bh->b_data, buf, csize); set_buffer_uptodate(bh); ext4_handle_dirty_metadata(handle, ea_inode, bh); buf += csize; wsize += csize; block += 1; } inode_lock(ea_inode); i_size_write(ea_inode, wsize); ext4_update_i_disksize(ea_inode, wsize); inode_unlock(ea_inode); ret2 = ext4_mark_inode_dirty(handle, ea_inode); if (unlikely(ret2 && !ret)) ret = ret2; out: brelse(bh); return ret; } /* * Create an inode to store the value of a large EA. */ static struct inode *ext4_xattr_inode_create(handle_t *handle, struct inode *inode, u32 hash) { struct inode *ea_inode = NULL; uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. */ ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG | 0600, NULL, inode->i_ino + 1, owner, EXT4_EA_INODE_FL); if (!IS_ERR(ea_inode)) { ea_inode->i_op = &ext4_file_inode_operations; ea_inode->i_fop = &ext4_file_operations; ext4_set_aops(ea_inode); ext4_xattr_inode_set_class(ea_inode); unlock_new_inode(ea_inode); ext4_xattr_inode_set_ref(ea_inode, 1); ext4_xattr_inode_set_hash(ea_inode, hash); err = ext4_mark_inode_dirty(handle, ea_inode); if (!err) err = ext4_inode_attach_jinode(ea_inode); if (err) { iput(ea_inode); return ERR_PTR(err); } /* * Xattr inodes are shared therefore quota charging is performed * at a higher level. */ dquot_free_inode(ea_inode); dquot_drop(ea_inode); inode_lock(ea_inode); ea_inode->i_flags |= S_NOQUOTA; inode_unlock(ea_inode); } return ea_inode; } static struct inode * ext4_xattr_inode_cache_find(struct inode *inode, const void *value, size_t value_len, u32 hash) { struct inode *ea_inode; struct mb_cache_entry *ce; struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); void *ea_data; if (!ea_inode_cache) return NULL; ce = mb_cache_entry_find_first(ea_inode_cache, hash); if (!ce) return NULL; WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && !(current->flags & PF_MEMALLOC_NOFS)); ea_data = kvmalloc(value_len, GFP_KERNEL); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); return NULL; } while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, EXT4_IGET_NORMAL); if (!IS_ERR(ea_inode) && !is_bad_inode(ea_inode) && (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && !memcmp(value, ea_data, value_len)) { mb_cache_entry_touch(ea_inode_cache, ce); mb_cache_entry_put(ea_inode_cache, ce); kvfree(ea_data); return ea_inode; } if (!IS_ERR(ea_inode)) iput(ea_inode); ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); return NULL; } /* * Add value of the EA in an inode. */ static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, const void *value, size_t value_len, struct inode **ret_inode) { struct inode *ea_inode; u32 hash; int err; hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len); ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash); if (ea_inode) { err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) { iput(ea_inode); return err; } *ret_inode = ea_inode; return 0; } /* Create an inode for the EA value */ ea_inode = ext4_xattr_inode_create(handle, inode, hash); if (IS_ERR(ea_inode)) return PTR_ERR(ea_inode); err = ext4_xattr_inode_write(handle, ea_inode, value, value_len); if (err) { ext4_xattr_inode_dec_ref(handle, ea_inode); iput(ea_inode); return err; } if (EA_INODE_CACHE(inode)) mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash, ea_inode->i_ino, true /* reusable */); *ret_inode = ea_inode; return 0; } /* * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode * feature is enabled. */ #define EXT4_XATTR_BLOCK_RESERVE(inode) min(i_blocksize(inode)/8, 1024U) static int ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s, handle_t *handle, struct inode *inode, bool is_block) { struct ext4_xattr_entry *last, *next; struct ext4_xattr_entry *here = s->here; size_t min_offs = s->end - s->base, name_len = strlen(i->name); int in_inode = i->in_inode; struct inode *old_ea_inode = NULL; struct inode *new_ea_inode = NULL; size_t old_size, new_size; int ret; /* Space used by old and new values. */ old_size = (!s->not_found && !here->e_value_inum) ? EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0; new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0; /* * Optimization for the simple case when old and new values have the * same padded sizes. Not applicable if external inodes are involved. */ if (new_size && new_size == old_size) { size_t offs = le16_to_cpu(here->e_value_offs); void *val = s->base + offs; here->e_value_size = cpu_to_le32(i->value_len); if (i->value == EXT4_ZERO_XATTR_VALUE) { memset(val, 0, new_size); } else { memcpy(val, i->value, i->value_len); /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } goto update_hash; } /* Compute min_offs and last. */ last = s->first; for (; !IS_LAST_ENTRY(last); last = next) { next = EXT4_XATTR_NEXT(last); if ((void *)next >= s->end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); ret = -EFSCORRUPTED; goto out; } if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) min_offs = offs; } } /* Check whether we have enough space. */ if (i->value) { size_t free; free = min_offs - ((void *)last - s->base) - sizeof(__u32); if (!s->not_found) free += EXT4_XATTR_LEN(name_len) + old_size; if (free < EXT4_XATTR_LEN(name_len) + new_size) { ret = -ENOSPC; goto out; } /* * If storing the value in an external inode is an option, * reserve space for xattr entries/names in the external * attribute block so that a long value does not occupy the * whole space and prevent futher entries being added. */ if (ext4_has_feature_ea_inode(inode->i_sb) && new_size && is_block && (min_offs + old_size - new_size) < EXT4_XATTR_BLOCK_RESERVE(inode)) { ret = -ENOSPC; goto out; } } /* * Getting access to old and new ea inodes is subject to failures. * Finish that work before doing any modifications to the xattr data. */ if (!s->not_found && here->e_value_inum) { ret = ext4_xattr_inode_iget(inode, le32_to_cpu(here->e_value_inum), le32_to_cpu(here->e_hash), &old_ea_inode); if (ret) { old_ea_inode = NULL; goto out; } } if (i->value && in_inode) { WARN_ON_ONCE(!i->value_len); ret = ext4_xattr_inode_alloc_quota(inode, i->value_len); if (ret) goto out; ret = ext4_xattr_inode_lookup_create(handle, inode, i->value, i->value_len, &new_ea_inode); if (ret) { new_ea_inode = NULL; ext4_xattr_inode_free_quota(inode, NULL, i->value_len); goto out; } } if (old_ea_inode) { /* We are ready to release ref count on the old_ea_inode. */ ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode); if (ret) { /* Release newly required ref count on new_ea_inode. */ if (new_ea_inode) { int err; err = ext4_xattr_inode_dec_ref(handle, new_ea_inode); if (err) ext4_warning_inode(new_ea_inode, "dec ref new_ea_inode err=%d", err); ext4_xattr_inode_free_quota(inode, new_ea_inode, i->value_len); } goto out; } ext4_xattr_inode_free_quota(inode, old_ea_inode, le32_to_cpu(here->e_value_size)); } /* No failures allowed past this point. */ if (!s->not_found && here->e_value_size && !here->e_value_inum) { /* Remove the old value. */ void *first_val = s->base + min_offs; size_t offs = le16_to_cpu(here->e_value_offs); void *val = s->base + offs; memmove(first_val + old_size, first_val, val - first_val); memset(first_val, 0, old_size); min_offs += old_size; /* Adjust all value offsets. */ last = s->first; while (!IS_LAST_ENTRY(last)) { size_t o = le16_to_cpu(last->e_value_offs); if (!last->e_value_inum && last->e_value_size && o < offs) last->e_value_offs = cpu_to_le16(o + old_size); last = EXT4_XATTR_NEXT(last); } } if (!i->value) { /* Remove old name. */ size_t size = EXT4_XATTR_LEN(name_len); last = ENTRY((void *)last - size); memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len); size_t rest = (void *)last - (void *)here + sizeof(__u32); memmove((void *)here + size, here, rest); memset(here, 0, size); here->e_name_index = i->name_index; here->e_name_len = name_len; memcpy(here->e_name, i->name, name_len); } else { /* This is an update, reset value info. */ here->e_value_inum = 0; here->e_value_offs = 0; here->e_value_size = 0; } if (i->value) { /* Insert new value. */ if (in_inode) { here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino); } else if (i->value_len) { void *val = s->base + min_offs - new_size; here->e_value_offs = cpu_to_le16(min_offs - new_size); if (i->value == EXT4_ZERO_XATTR_VALUE) { memset(val, 0, new_size); } else { memcpy(val, i->value, i->value_len); /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } } here->e_value_size = cpu_to_le32(i->value_len); } update_hash: if (i->value) { __le32 hash = 0; /* Entry hash calculation. */ if (in_inode) { __le32 crc32c_hash; /* * Feed crc32c hash instead of the raw value for entry * hash calculation. This is to avoid walking * potentially long value buffer again. */ crc32c_hash = cpu_to_le32( ext4_xattr_inode_get_hash(new_ea_inode)); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, &crc32c_hash, 1); } else if (is_block) { __le32 *value = s->base + le16_to_cpu( here->e_value_offs); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, value, new_size >> 2); } here->e_hash = hash; } if (is_block) ext4_xattr_rehash((struct ext4_xattr_header *)s->base); ret = 0; out: iput(old_ea_inode); iput(new_ea_inode); return ret; } struct ext4_xattr_block_find { struct ext4_xattr_search s; struct buffer_head *bh; }; static int ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_block_find *bs) { struct super_block *sb = inode->i_sb; int error; ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld", i->name_index, i->name, i->value, (long)i->value_len); if (EXT4_I(inode)->i_file_acl) { /* The inode already has an extended attribute block. */ bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bs->bh)) { error = PTR_ERR(bs->bh); bs->bh = NULL; return error; } ea_bdebug(bs->bh, "b_count=%d, refcount=%d", atomic_read(&(bs->bh->b_count)), le32_to_cpu(BHDR(bs->bh)->h_refcount)); error = ext4_xattr_check_block(inode, bs->bh); if (error) return error; /* Find the named attribute. */ bs->s.base = BHDR(bs->bh); bs->s.first = BFIRST(bs->bh); bs->s.end = bs->bh->b_data + bs->bh->b_size; bs->s.here = bs->s.first; error = xattr_find_entry(inode, &bs->s.here, bs->s.end, i->name_index, i->name, 1); if (error && error != -ENODATA) return error; bs->s.not_found = error; } return 0; } static int ext4_xattr_block_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_block_find *bs) { struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; struct ext4_xattr_search s_copy = bs->s; struct ext4_xattr_search *s = &s_copy; struct mb_cache_entry *ce = NULL; int error = 0; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); struct inode *ea_inode = NULL, *tmp_inode; size_t old_ea_inode_quota = 0; unsigned int ea_ino; #define header(x) ((struct ext4_xattr_header *)(x)) if (s->base) { BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) goto cleanup; lock_buffer(bs->bh); if (header(s->base)->h_refcount == cpu_to_le32(1)) { __u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash); /* * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect modified * block */ if (ea_block_cache) mb_cache_entry_delete(ea_block_cache, hash, bs->bh->b_blocknr); ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) goto bad_block; if (!error) error = ext4_handle_dirty_metadata(handle, inode, bs->bh); if (error) goto cleanup; goto inserted; } else { int offset = (char *)s->here - bs->bh->b_data; unlock_buffer(bs->bh); ea_bdebug(bs->bh, "cloning"); s->base = kmalloc(bs->bh->b_size, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; memcpy(s->base, BHDR(bs->bh), bs->bh->b_size); s->first = ENTRY(header(s->base)+1); header(s->base)->h_refcount = cpu_to_le32(1); s->here = ENTRY(s->base + offset); s->end = s->base + bs->bh->b_size; /* * If existing entry points to an xattr inode, we need * to prevent ext4_xattr_set_entry() from decrementing * ref count on it because the reference belongs to the * original block. In this case, make the entry look * like it has an empty value. */ if (!s->not_found && s->here->e_value_inum) { ea_ino = le32_to_cpu(s->here->e_value_inum); error = ext4_xattr_inode_iget(inode, ea_ino, le32_to_cpu(s->here->e_hash), &tmp_inode); if (error) goto cleanup; if (!ext4_test_inode_state(tmp_inode, EXT4_STATE_LUSTRE_EA_INODE)) { /* * Defer quota free call for previous * inode until success is guaranteed. */ old_ea_inode_quota = le32_to_cpu( s->here->e_value_size); } iput(tmp_inode); s->here->e_value_inum = 0; s->here->e_value_size = 0; } } } else { /* Allocate a buffer where we construct the new block. */ s->base = kzalloc(sb->s_blocksize, GFP_NOFS); /* assert(header == s->base) */ error = -ENOMEM; if (s->base == NULL) goto cleanup; header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); header(s->base)->h_blocks = cpu_to_le32(1); header(s->base)->h_refcount = cpu_to_le32(1); s->first = ENTRY(header(s->base)+1); s->here = ENTRY(header(s->base)+1); s->end = s->base + sb->s_blocksize; } error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; if (i->value && s->here->e_value_inum) { /* * A ref count on ea_inode has been taken as part of the call to * ext4_xattr_set_entry() above. We would like to drop this * extra ref but we have to wait until the xattr block is * initialized and has its own ref count on the ea_inode. */ ea_ino = le32_to_cpu(s->here->e_value_inum); error = ext4_xattr_inode_iget(inode, ea_ino, le32_to_cpu(s->here->e_hash), &ea_inode); if (error) { ea_inode = NULL; goto cleanup; } } inserted: if (!IS_LAST_ENTRY(s->first)) { new_bh = ext4_xattr_block_cache_find(inode, header(s->base), &ce); if (new_bh) { /* We found an identical block in the cache. */ if (new_bh == bs->bh) ea_bdebug(new_bh, "keeping"); else { u32 ref; WARN_ON_ONCE(dquot_initialize_needed(inode)); /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); if (error) goto cleanup; BUFFER_TRACE(new_bh, "get_write_access"); error = ext4_journal_get_write_access(handle, new_bh); if (error) goto cleanup_dquot; lock_buffer(new_bh); /* * We have to be careful about races with * freeing, rehashing or adding references to * xattr block. Once we hold buffer lock xattr * block's state is stable so we can check * whether the block got freed / rehashed or * not. Since we unhash mbcache entry under * buffer lock when freeing / rehashing xattr * block, checking whether entry is still * hashed is reliable. Same rules hold for * e_reusable handling. */ if (hlist_bl_unhashed(&ce->e_hash_list) || !ce->e_reusable) { /* * Undo everything and check mbcache * again. */ unlock_buffer(new_bh); dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); brelse(new_bh); mb_cache_entry_put(ea_block_cache, ce); ce = NULL; new_bh = NULL; goto inserted; } ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; BHDR(new_bh)->h_refcount = cpu_to_le32(ref); if (ref >= EXT4_XATTR_REFCOUNT_MAX) ce->e_reusable = 0; ea_bdebug(new_bh, "reusing; refcount now=%d", ref); ext4_xattr_block_csum_set(inode, new_bh); unlock_buffer(new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) goto cleanup_dquot; } mb_cache_entry_touch(ea_block_cache, ce); mb_cache_entry_put(ea_block_cache, ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ ea_bdebug(bs->bh, "keeping this block"); ext4_xattr_block_cache_insert(ea_block_cache, bs->bh); new_bh = bs->bh; get_bh(new_bh); } else { /* We need to allocate a new block */ ext4_fsblk_t goal, block; WARN_ON_ONCE(dquot_initialize_needed(inode)); goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); /* non-extent files can't have physical blocks past 2^32 */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; block = ext4_new_meta_blocks(handle, inode, goal, 0, NULL, &error); if (error) goto cleanup; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS); ea_idebug(inode, "creating block %llu", (unsigned long long)block); new_bh = sb_getblk(sb, block); if (unlikely(!new_bh)) { error = -ENOMEM; getblk_failed: ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA); goto cleanup; } error = ext4_xattr_inode_inc_ref_all(handle, inode, ENTRY(header(s->base)+1)); if (error) goto getblk_failed; if (ea_inode) { /* Drop the extra ref on ea_inode. */ error = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error) ext4_warning_inode(ea_inode, "dec ref error=%d", error); iput(ea_inode); ea_inode = NULL; } lock_buffer(new_bh); error = ext4_journal_get_create_access(handle, new_bh); if (error) { unlock_buffer(new_bh); error = -EIO; goto getblk_failed; } memcpy(new_bh->b_data, s->base, new_bh->b_size); ext4_xattr_block_csum_set(inode, new_bh); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); ext4_xattr_block_cache_insert(ea_block_cache, new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) goto cleanup; } } if (old_ea_inode_quota) ext4_xattr_inode_free_quota(inode, NULL, old_ea_inode_quota); /* Update the inode. */ EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; /* Drop the previous xattr block. */ if (bs->bh && bs->bh != new_bh) { struct ext4_xattr_inode_array *ea_inode_array = NULL; ext4_xattr_release_block(handle, inode, bs->bh, &ea_inode_array, 0 /* extra_credits */); ext4_xattr_inode_array_free(ea_inode_array); } error = 0; cleanup: if (ea_inode) { int error2; error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error2) ext4_warning_inode(ea_inode, "dec ref error=%d", error2); /* If there was an error, revert the quota charge. */ if (error) ext4_xattr_inode_free_quota(inode, ea_inode, i_size_read(ea_inode)); iput(ea_inode); } if (ce) mb_cache_entry_put(ea_block_cache, ce); brelse(new_bh); if (!(bs->bh && s->base == bs->bh->b_data)) kfree(s->base); return error; cleanup_dquot: dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); goto cleanup; bad_block: EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); goto cleanup; #undef header } int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; int error; if (EXT4_I(inode)->i_extra_isize == 0) return 0; raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); is->s.here = is->s.first; is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { error = xattr_check_inode(inode, header, is->s.end); if (error) return error; /* Find the named attribute. */ error = xattr_find_entry(inode, &is->s.here, is->s.end, i->name_index, i->name, 0); if (error && error != -ENODATA) return error; is->s.not_found = error; } return 0; } int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_search *s = &is->s; int error; if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); ext4_set_inode_state(inode, EXT4_STATE_XATTR); } else { header->h_magic = cpu_to_le32(0); ext4_clear_inode_state(inode, EXT4_STATE_XATTR); } return 0; } static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_search *s = &is->s; int error; if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); ext4_set_inode_state(inode, EXT4_STATE_XATTR); } else { header->h_magic = cpu_to_le32(0); ext4_clear_inode_state(inode, EXT4_STATE_XATTR); } return 0; } static int ext4_xattr_value_same(struct ext4_xattr_search *s, struct ext4_xattr_info *i) { void *value; /* When e_value_inum is set the value is stored externally. */ if (s->here->e_value_inum) return 0; if (le32_to_cpu(s->here->e_value_size) != i->value_len) return 0; value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs); return !memcmp(value, i->value, i->value_len); } static struct buffer_head *ext4_xattr_get_block(struct inode *inode) { struct buffer_head *bh; int error; if (!EXT4_I(inode)->i_file_acl) return NULL; bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return bh; error = ext4_xattr_check_block(inode, bh); if (error) { brelse(bh); return ERR_PTR(error); } return bh; } /* * ext4_xattr_set_handle() * * Create, replace or remove an extended attribute for this inode. Value * is NULL to remove an existing extended attribute, and non-NULL to * either replace an existing extended attribute, or create a new extended * attribute. The flags XATTR_REPLACE and XATTR_CREATE * specify that an extended attribute must exist and must not exist * previous to the call, respectively. * * Returns 0, or a negative error number on failure. */ int ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { struct ext4_xattr_info i = { .name_index = name_index, .name = name, .value = value, .value_len = value_len, .in_inode = 0, }; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_block_find bs = { .s = { .not_found = -ENODATA, }, }; int no_expand; int error; if (!name) return -EINVAL; if (strlen(name) > 255) return -ERANGE; ext4_write_lock_xattr(inode, &no_expand); /* Check journal credits under write lock. */ if (ext4_handle_valid(handle)) { struct buffer_head *bh; int credits; bh = ext4_xattr_get_block(inode); if (IS_ERR(bh)) { error = PTR_ERR(bh); goto cleanup; } credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, value_len, flags & XATTR_CREATE); brelse(bh); if (jbd2_handle_buffer_credits(handle) < credits) { error = -ENOSPC; goto cleanup; } WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } error = ext4_reserve_inode_write(handle, inode, &is.iloc); if (error) goto cleanup; if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) { struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc); memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); ext4_clear_inode_state(inode, EXT4_STATE_NEW); } error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto cleanup; if (is.s.not_found) error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; if (is.s.not_found && bs.s.not_found) { error = -ENODATA; if (flags & XATTR_REPLACE) goto cleanup; error = 0; if (!value) goto cleanup; } else { error = -EEXIST; if (flags & XATTR_CREATE) goto cleanup; } if (!value) { if (!is.s.not_found) error = ext4_xattr_ibody_set(handle, inode, &i, &is); else if (!bs.s.not_found) error = ext4_xattr_block_set(handle, inode, &i, &bs); } else { error = 0; /* Xattr value did not change? Save us some work and bail out */ if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i)) goto cleanup; if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i)) goto cleanup; if (ext4_has_feature_ea_inode(inode->i_sb) && (EXT4_XATTR_SIZE(i.value_len) > EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize))) i.in_inode = 1; retry_inode: error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (!error && !bs.s.not_found) { i.value = NULL; error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { brelse(bs.bh); bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; } error = ext4_xattr_block_set(handle, inode, &i, &bs); if (!error && !is.s.not_found) { i.value = NULL; error = ext4_xattr_ibody_set(handle, inode, &i, &is); } else if (error == -ENOSPC) { /* * Xattr does not fit in the block, store at * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; } } } } if (!error) { ext4_xattr_update_super_block(handle, inode->i_sb); inode->i_ctime = current_time(inode); if (!value) no_expand = 0; error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); /* * The bh is consumed by ext4_mark_iloc_dirty, even with * error != 0. */ is.iloc.bh = NULL; if (IS_SYNC(inode)) ext4_handle_sync(handle); } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); cleanup: brelse(is.iloc.bh); brelse(bs.bh); ext4_write_unlock_xattr(inode, &no_expand); return error; } int ext4_xattr_set_credits(struct inode *inode, size_t value_len, bool is_create, int *credits) { struct buffer_head *bh; int err; *credits = 0; if (!EXT4_SB(inode->i_sb)->s_journal) return 0; down_read(&EXT4_I(inode)->xattr_sem); bh = ext4_xattr_get_block(inode); if (IS_ERR(bh)) { err = PTR_ERR(bh); } else { *credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, value_len, is_create); brelse(bh); err = 0; } up_read(&EXT4_I(inode)->xattr_sem); return err; } /* * ext4_xattr_set() * * Like ext4_xattr_set_handle, but start from an inode. This extended * attribute modification is a filesystem transaction by itself. * * Returns 0, or a negative error number on failure. */ int ext4_xattr_set(struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { handle_t *handle; struct super_block *sb = inode->i_sb; int error, retries = 0; int credits; error = dquot_initialize(inode); if (error) return error; retry: error = ext4_xattr_set_credits(inode, value_len, flags & XATTR_CREATE, &credits); if (error) return error; handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) { error = PTR_ERR(handle); } else { int error2; error = ext4_xattr_set_handle(handle, inode, name_index, name, value, value_len, flags); error2 = ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) goto retry; if (error == 0) error = error2; } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); return error; } /* * Shift the EA entries in the inode to create space for the increased * i_extra_isize. */ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry, int value_offs_shift, void *to, void *from, size_t n) { struct ext4_xattr_entry *last = entry; int new_offs; /* We always shift xattr headers further thus offsets get lower */ BUG_ON(value_offs_shift > 0); /* Adjust the value offsets of the entries */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { if (!last->e_value_inum && last->e_value_size) { new_offs = le16_to_cpu(last->e_value_offs) + value_offs_shift; last->e_value_offs = cpu_to_le16(new_offs); } } /* Shift the entries by n bytes */ memmove(to, from, n); } /* * Move xattr pointed to by 'entry' from inode into external xattr block */ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, struct ext4_inode *raw_inode, struct ext4_xattr_entry *entry) { struct ext4_xattr_ibody_find *is = NULL; struct ext4_xattr_block_find *bs = NULL; char *buffer = NULL, *b_entry_name = NULL; size_t value_size = le32_to_cpu(entry->e_value_size); struct ext4_xattr_info i = { .value = NULL, .value_len = 0, .name_index = entry->e_name_index, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); buffer = kmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); if (!is || !bs || !buffer || !b_entry_name) { error = -ENOMEM; goto out; } is->s.not_found = -ENODATA; bs->s.not_found = -ENODATA; is->iloc.bh = NULL; bs->bh = NULL; /* Save the entry name and the entry value */ if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); } memcpy(b_entry_name, entry->e_name, entry->e_name_len); b_entry_name[entry->e_name_len] = '\0'; i.name = b_entry_name; error = ext4_get_inode_loc(inode, &is->iloc); if (error) goto out; error = ext4_xattr_ibody_find(inode, &i, is); if (error) goto out; /* Remove the chosen entry from the inode */ error = ext4_xattr_ibody_set(handle, inode, &i, is); if (error) goto out; i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; /* Add entry which was removed from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; error = 0; out: kfree(b_entry_name); kfree(buffer); if (is) brelse(is->iloc.bh); if (bs) brelse(bs->bh); kfree(is); kfree(bs); return error; } static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, struct ext4_inode *raw_inode, int isize_diff, size_t ifree, size_t bfree, int *total_ino) { struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); struct ext4_xattr_entry *small_entry; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *last; unsigned int entry_size; /* EA entry size */ unsigned int total_size; /* EA entry size + value size */ unsigned int min_total_size; int error; while (isize_diff > ifree) { entry = NULL; small_entry = NULL; min_total_size = ~0U; last = IFIRST(header); /* Find the entry best suited to be pushed into EA block */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { /* never move system.data out of the inode */ if ((last->e_name_len == 4) && (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) && !memcmp(last->e_name, "data", 4)) continue; total_size = EXT4_XATTR_LEN(last->e_name_len); if (!last->e_value_inum) total_size += EXT4_XATTR_SIZE( le32_to_cpu(last->e_value_size)); if (total_size <= bfree && total_size < min_total_size) { if (total_size + ifree < isize_diff) { small_entry = last; } else { entry = last; min_total_size = total_size; } } } if (entry == NULL) { if (small_entry == NULL) return -ENOSPC; entry = small_entry; } entry_size = EXT4_XATTR_LEN(entry->e_name_len); total_size = entry_size; if (!entry->e_value_inum) total_size += EXT4_XATTR_SIZE( le32_to_cpu(entry->e_value_size)); error = ext4_xattr_move_to_block(handle, inode, raw_inode, entry); if (error) return error; *total_ino -= entry_size; ifree += total_size; bfree -= total_size; } return 0; } /* * Expand an inode by new_extra_isize bytes when EAs are present. * Returns 0 on success or negative error number on failure. */ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; size_t ifree, bfree; int total_ino; void *base, *end; int error = 0, tried_min_extra_isize = 0; int s_min_extra_isize = le16_to_cpu(sbi->s_es->s_min_extra_isize); int isize_diff; /* How much do we need to grow i_extra_isize */ retry: isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) return 0; header = IHDR(inode, raw_inode); /* * Check if enough free space is available in the inode to shift the * entries ahead by new_extra_isize. */ base = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; min_offs = end - base; total_ino = sizeof(struct ext4_xattr_ibody_header) + sizeof(u32); error = xattr_check_inode(inode, header, end); if (error) goto cleanup; ifree = ext4_xattr_free_space(base, &min_offs, base, &total_ino); if (ifree >= isize_diff) goto shift; /* * Enough free space isn't available in the inode, check if * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { struct buffer_head *bh; bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); goto cleanup; } error = ext4_xattr_check_block(inode, bh); if (error) { brelse(bh); goto cleanup; } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base, NULL); brelse(bh); if (bfree + ifree < isize_diff) { if (!tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; goto retry; } error = -ENOSPC; goto cleanup; } } else { bfree = inode->i_sb->s_blocksize; } error = ext4_xattr_make_inode_space(handle, inode, raw_inode, isize_diff, ifree, bfree, &total_ino); if (error) { if (error == -ENOSPC && !tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; goto retry; } goto cleanup; } shift: /* Adjust the offsets and shift the remaining entries ahead */ ext4_xattr_shift_entries(IFIRST(header), EXT4_I(inode)->i_extra_isize - new_extra_isize, (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize, (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", inode->i_ino); mnt_count = le16_to_cpu(sbi->s_es->s_mnt_count); } return error; } #define EIA_INCR 16 /* must be 2^n */ #define EIA_MASK (EIA_INCR - 1) /* Add the large xattr @inode into @ea_inode_array for deferred iput(). * If @ea_inode_array is new or full it will be grown and the old * contents copied over. */ static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode) { if (*ea_inode_array == NULL) { /* * Start with 15 inodes, so it fits into a power-of-two size. * If *ea_inode_array is NULL, this is essentially offsetof() */ (*ea_inode_array) = kmalloc(offsetof(struct ext4_xattr_inode_array, inodes[EIA_MASK]), GFP_NOFS); if (*ea_inode_array == NULL) return -ENOMEM; (*ea_inode_array)->count = 0; } else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) { /* expand the array once all 15 + n * 16 slots are full */ struct ext4_xattr_inode_array *new_array = NULL; int count = (*ea_inode_array)->count; /* if new_array is NULL, this is essentially offsetof() */ new_array = kmalloc( offsetof(struct ext4_xattr_inode_array, inodes[count + EIA_INCR]), GFP_NOFS); if (new_array == NULL) return -ENOMEM; memcpy(new_array, *ea_inode_array, offsetof(struct ext4_xattr_inode_array, inodes[count])); kfree(*ea_inode_array); *ea_inode_array = new_array; } (*ea_inode_array)->inodes[(*ea_inode_array)->count++] = inode; return 0; } /* * ext4_xattr_delete_inode() * * Free extended attribute resources associated with this inode. Traverse * all entries and decrement reference on any xattr inodes associated with this * inode. This is called immediately before an inode is freed. We have exclusive * access to the inode. If an orphan inode is deleted it will also release its * references on xattr block and xattr inodes. */ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits) { struct buffer_head *bh = NULL; struct ext4_xattr_ibody_header *header; struct ext4_iloc iloc = { .bh = NULL }; struct ext4_xattr_entry *entry; struct inode *ea_inode; int error; error = ext4_journal_ensure_credits(handle, extra_credits, ext4_free_metadata_revoke_credits(inode->i_sb, 1)); if (error < 0) { EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error); goto cleanup; } if (ext4_has_feature_ea_inode(inode->i_sb) && ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { error = ext4_get_inode_loc(inode, &iloc); if (error) { EXT4_ERROR_INODE(inode, "inode loc (error %d)", error); goto cleanup; } error = ext4_journal_get_write_access(handle, iloc.bh); if (error) { EXT4_ERROR_INODE(inode, "write access (error %d)", error); goto cleanup; } header = IHDR(inode, ext4_raw_inode(&iloc)); if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC)) ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh, IFIRST(header), false /* block_csum */, ea_inode_array, extra_credits, false /* skip_quota */); } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); if (error == -EIO) { EXT4_ERROR_INODE_ERR(inode, EIO, "block %llu read error", EXT4_I(inode)->i_file_acl); } bh = NULL; goto cleanup; } error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; if (ext4_has_feature_ea_inode(inode->i_sb)) { for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; error = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (error) continue; ext4_xattr_inode_free_quota(inode, ea_inode, le32_to_cpu(entry->e_value_size)); iput(ea_inode); } } ext4_xattr_release_block(handle, inode, bh, ea_inode_array, extra_credits); /* * Update i_file_acl value in the same transaction that releases * block. */ EXT4_I(inode)->i_file_acl = 0; error = ext4_mark_inode_dirty(handle, inode); if (error) { EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)", error); goto cleanup; } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); } error = 0; cleanup: brelse(iloc.bh); brelse(bh); return error; } void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array) { int idx; if (ea_inode_array == NULL) return; for (idx = 0; idx < ea_inode_array->count; ++idx) iput(ea_inode_array->inodes[idx]); kfree(ea_inode_array); } /* * ext4_xattr_block_cache_insert() * * Create a new entry in the extended attribute block cache, and insert * it unless such an entry is already in the cache. * * Returns 0, or a negative error number on failure. */ static void ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache, struct buffer_head *bh) { struct ext4_xattr_header *header = BHDR(bh); __u32 hash = le32_to_cpu(header->h_hash); int reusable = le32_to_cpu(header->h_refcount) < EXT4_XATTR_REFCOUNT_MAX; int error; if (!ea_block_cache) return; error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash, bh->b_blocknr, reusable); if (error) { if (error == -EBUSY) ea_bdebug(bh, "already in cache"); } else ea_bdebug(bh, "inserting [%x]", (int)hash); } /* * ext4_xattr_cmp() * * Compare two extended attribute blocks for equality. * * Returns 0 if the blocks are equal, 1 if they differ, and * a negative error number on errors. */ static int ext4_xattr_cmp(struct ext4_xattr_header *header1, struct ext4_xattr_header *header2) { struct ext4_xattr_entry *entry1, *entry2; entry1 = ENTRY(header1+1); entry2 = ENTRY(header2+1); while (!IS_LAST_ENTRY(entry1)) { if (IS_LAST_ENTRY(entry2)) return 1; if (entry1->e_hash != entry2->e_hash || entry1->e_name_index != entry2->e_name_index || entry1->e_name_len != entry2->e_name_len || entry1->e_value_size != entry2->e_value_size || entry1->e_value_inum != entry2->e_value_inum || memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) return 1; if (!entry1->e_value_inum && memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), (char *)header2 + le16_to_cpu(entry2->e_value_offs), le32_to_cpu(entry1->e_value_size))) return 1; entry1 = EXT4_XATTR_NEXT(entry1); entry2 = EXT4_XATTR_NEXT(entry2); } if (!IS_LAST_ENTRY(entry2)) return 1; return 0; } /* * ext4_xattr_block_cache_find() * * Find an identical extended attribute block. * * Returns a pointer to the block found, or NULL if such a block was * not found or an error occurred. */ static struct buffer_head * ext4_xattr_block_cache_find(struct inode *inode, struct ext4_xattr_header *header, struct mb_cache_entry **pce) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (!ea_block_cache) return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { if (PTR_ERR(bh) == -ENOMEM) return NULL; bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { *pce = ce; return bh; } brelse(bh); ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } #define NAME_HASH_SHIFT 5 #define VALUE_HASH_SHIFT 16 /* * ext4_xattr_hash_entry() * * Compute the hash of an extended attribute. */ static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count) { __u32 hash = 0; while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ *name++; } while (value_count--) { hash = (hash << VALUE_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ le32_to_cpu(*value++); } return cpu_to_le32(hash); } #undef NAME_HASH_SHIFT #undef VALUE_HASH_SHIFT #define BLOCK_HASH_SHIFT 16 /* * ext4_xattr_rehash() * * Re-compute the extended attribute hash value after an entry has changed. */ static void ext4_xattr_rehash(struct ext4_xattr_header *header) { struct ext4_xattr_entry *here; __u32 hash = 0; here = ENTRY(header+1); while (!IS_LAST_ENTRY(here)) { if (!here->e_hash) { /* Block is not shared if an entry's hash value == 0 */ hash = 0; break; } hash = (hash << BLOCK_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^ le32_to_cpu(here->e_hash); here = EXT4_XATTR_NEXT(here); } header->h_hash = cpu_to_le32(hash); } #undef BLOCK_HASH_SHIFT #define HASH_BUCKET_BITS 10 struct mb_cache * ext4_xattr_create_cache(void) { return mb_cache_create(HASH_BUCKET_BITS); } void ext4_xattr_destroy_cache(struct mb_cache *cache) { if (cache) mb_cache_destroy(cache); }
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 #ifndef _LINUX_PSI_H #define _LINUX_PSI_H #include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> struct seq_file; struct css_set; #ifdef CONFIG_PSI extern struct static_key_false psi_disabled; extern struct psi_group psi_system; void psi_init(void); void psi_task_change(struct task_struct *task, int clear, int set); void psi_task_switch(struct task_struct *prev, struct task_struct *next, bool sleep); void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #endif #else /* CONFIG_PSI */ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} #ifdef CONFIG_CGROUPS static inline int psi_cgroup_alloc(struct cgroup *cgrp) { return 0; } static inline void psi_cgroup_free(struct cgroup *cgrp) { } static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } #endif #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: fully on the stack (when can't do frame-checking) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { WARN_ONCE(1, "Bad or missing usercopy whitelist? Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); } void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } /* Checks for allocs that are marked in some way as spanning multiple pages. */ static inline void check_page_span(const void *ptr, unsigned long n, struct page *page, bool to_user) { #ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN const void *end = ptr + n - 1; struct page *endpage; bool is_reserved, is_cma; /* * Sometimes the kernel data regions are not marked Reserved (see * check below). And sometimes [_sdata,_edata) does not cover * rodata and/or bss, so check each range explicitly. */ /* Allow reads of kernel rodata region (if not marked as Reserved). */ if (ptr >= (const void *)__start_rodata && end <= (const void *)__end_rodata) { if (!to_user) usercopy_abort("rodata", NULL, to_user, 0, n); return; } /* Allow kernel data region (if not marked as Reserved). */ if (ptr >= (const void *)_sdata && end <= (const void *)_edata) return; /* Allow kernel bss region (if not marked as Reserved). */ if (ptr >= (const void *)__bss_start && end <= (const void *)__bss_stop) return; /* Is the object wholly within one base page? */ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == ((unsigned long)end & (unsigned long)PAGE_MASK))) return; /* Allow if fully inside the same compound (__GFP_COMP) page. */ endpage = virt_to_head_page(end); if (likely(endpage == page)) return; /* * Reject if range is entirely either Reserved (i.e. special or * device memory), or CMA. Otherwise, reject since the object spans * several independently allocated pages. */ is_reserved = PageReserved(page); is_cma = is_migrate_cma_page(page); if (!is_reserved && !is_cma) usercopy_abort("spans multiple pages", NULL, to_user, 0, n); for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { page = virt_to_head_page(ptr); if (is_reserved && !PageReserved(page)) usercopy_abort("spans Reserved and non-Reserved pages", NULL, to_user, 0, n); if (is_cma && !is_migrate_cma_page(page)) usercopy_abort("spans CMA and non-CMA pages", NULL, to_user, 0, n); } #endif } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { struct page *page; if (!virt_addr_valid(ptr)) return; /* * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the * highmem page or fallback to virt_to_page(). The following * is effectively a highmem-aware virt_to_head_page(). */ page = compound_head(kmap_to_page((void *)ptr)); if (PageSlab(page)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, page, to_user); } else { /* Verify object does not incorrectly span multiple pages. */ check_page_span(ptr, n, page, to_user); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, 0, n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { return strtobool(str, &enable_checks); } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy);
1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0-or-later /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/minmax.h> #if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ !defined(find_next_and_bit) /* * This is a common helper function for find_next_bit, find_next_zero_bit, and * find_next_and_bit. The differences are: * - The "invert" argument, which is XORed with each fetched word before * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ static unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { unsigned long tmp, mask; if (unlikely(start >= nbits)) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; /* Handle 1st word. */ mask = BITMAP_FIRST_WORD_MASK(start); if (le) mask = swab(mask); tmp &= mask; start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; } if (le) tmp = swab(tmp); return min(start + __ffs(tmp), nbits); } #endif #ifndef find_next_bit /* * Find the next set bit in a memory region. */ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_bit); #endif #ifndef find_next_zero_bit unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } EXPORT_SYMBOL(find_next_zero_bit); #endif #if !defined(find_next_and_bit) unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_and_bit); #endif #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx]) return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx] != ~0UL) return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_zero_bit); #endif #ifndef find_last_bit unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(find_last_bit); #endif #ifdef __BIG_ENDIAN #ifndef find_next_zero_bit_le unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif #ifndef find_next_bit_le unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 1); } EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { offset = find_next_bit(addr, size, offset); if (offset == size) return size; offset = round_down(offset, 8); *clump = bitmap_get_value8(addr, offset); return offset; } EXPORT_SYMBOL(find_next_clump8);
1 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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_NULLS_H #define _LINUX_LIST_NULLS_H #include <linux/poison.h> #include <linux/const.h> /* * Special version of lists, where end of list is not a NULL pointer, * but a 'nulls' marker, which can have many different values. * (up to 2^31 different values guaranteed on all platforms) * * In the standard hlist, termination of a list is the NULL pointer. * In this special 'nulls' variant, we use the fact that objects stored in * a list are aligned on a word (4 or 8 bytes alignment). * We therefore use the last significant bit of 'ptr' : * Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1) * Set to 0 : This is a pointer to some object (ptr) */ struct hlist_nulls_head { struct hlist_nulls_node *first; }; struct hlist_nulls_node { struct hlist_nulls_node *next, **pprev; }; #define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_nulls_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested * */ static inline int is_a_nulls(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr & 1); } /** * get_nulls_value - Get the 'nulls' value of the end of chain * @ptr: end of chain * * Should be called only if is_a_nulls(ptr); */ static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr) >> 1; } /** * hlist_nulls_unhashed - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. */ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) { return !h->pprev; } /** * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this * function may be used locklessly. */ static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) { return !READ_ONCE(h->pprev); } static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) { struct hlist_nulls_node *next = n->next; struct hlist_nulls_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry(tpos, pos, head, member) \ for (pos = (head)->first; \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry_from(tpos, pos, member) \ for (; (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CLEANCACHE_H #define _LINUX_CLEANCACHE_H #include <linux/fs.h> #include <linux/exportfs.h> #include <linux/mm.h> #define CLEANCACHE_NO_POOL -1 #define CLEANCACHE_NO_BACKEND -2 #define CLEANCACHE_NO_BACKEND_SHARED -3 #define CLEANCACHE_KEY_MAX 6 /* * cleancache requires every file with a page in cleancache to have a * unique key unless/until the file is removed/truncated. For some * filesystems, the inode number is unique, but for "modern" filesystems * an exportable filehandle is required (see exportfs.h) */ struct cleancache_filekey { union { ino_t ino; __u32 fh[CLEANCACHE_KEY_MAX]; u32 key[CLEANCACHE_KEY_MAX]; } u; }; struct cleancache_ops { int (*init_fs)(size_t); int (*init_shared_fs)(uuid_t *uuid, size_t); int (*get_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*put_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); void (*invalidate_inode)(int, struct cleancache_filekey); void (*invalidate_fs)(int); }; extern int cleancache_register_ops(const struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(struct super_block *); extern int __cleancache_get_page(struct page *); extern void __cleancache_put_page(struct page *); extern void __cleancache_invalidate_page(struct address_space *, struct page *); extern void __cleancache_invalidate_inode(struct address_space *); extern void __cleancache_invalidate_fs(struct super_block *); #ifdef CONFIG_CLEANCACHE #define cleancache_enabled (1) static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) { return mapping->host->i_sb->cleancache_poolid >= 0; } static inline bool cleancache_fs_enabled(struct page *page) { return cleancache_fs_enabled_mapping(page->mapping); } #else #define cleancache_enabled (0) #define cleancache_fs_enabled(_page) (0) #define cleancache_fs_enabled_mapping(_page) (0) #endif /* * The shim layer provided by these inline functions allows the compiler * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE * is disabled, to a single global variable check if CONFIG_CLEANCACHE * is enabled but no cleancache "backend" has dynamically enabled it, * and, for the most frequent cleancache ops, to a single global variable * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled * and a cleancache backend has dynamically enabled cleancache, but the * filesystem referenced by that cleancache op has not enabled cleancache. * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially * no measurable performance impact. */ static inline void cleancache_init_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_init_fs(sb); } static inline void cleancache_init_shared_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_init_shared_fs(sb); } static inline int cleancache_get_page(struct page *page) { if (cleancache_enabled && cleancache_fs_enabled(page)) return __cleancache_get_page(page); return -1; } static inline void cleancache_put_page(struct page *page) { if (cleancache_enabled && cleancache_fs_enabled(page)) __cleancache_put_page(page); } static inline void cleancache_invalidate_page(struct address_space *mapping, struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) __cleancache_invalidate_page(mapping, page); } static inline void cleancache_invalidate_inode(struct address_space *mapping) { if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) __cleancache_invalidate_inode(mapping); } static inline void cleancache_invalidate_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_invalidate_fs(sb); } #endif /* _LINUX_CLEANCACHE_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 #ifndef _CRYPTO_GCM_H #define _CRYPTO_GCM_H #include <linux/errno.h> #define GCM_AES_IV_SIZE 12 #define GCM_RFC4106_IV_SIZE 8 #define GCM_RFC4543_IV_SIZE 8 /* * validate authentication tag for GCM */ static inline int crypto_gcm_check_authsize(unsigned int authsize) { switch (authsize) { case 4: case 8: case 12: case 13: case 14: case 15: case 16: break; default: return -EINVAL; } return 0; } /* * validate authentication tag for RFC4106 */ static inline int crypto_rfc4106_check_authsize(unsigned int authsize) { switch (authsize) { case 8: case 12: case 16: break; default: return -EINVAL; } return 0; } /* * validate assoclen for RFC4106/RFC4543 */ static inline int crypto_ipsec_check_assoclen(unsigned int assoclen) { switch (assoclen) { case 16: case 20: break; default: return -EINVAL; } return 0; } #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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM exceptions #if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> #include <asm/trace/common.h> extern int trace_pagefault_reg(void); extern void trace_pagefault_unreg(void); DECLARE_EVENT_CLASS(x86_exceptions, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code), TP_STRUCT__entry( __field( unsigned long, address ) __field( unsigned long, ip ) __field( unsigned long, error_code ) ), TP_fast_assign( __entry->address = address; __entry->ip = regs->ip; __entry->error_code = error_code; ), TP_printk("address=%ps ip=%ps error_code=0x%lx", (void *)__entry->address, (void *)__entry->ip, __entry->error_code) ); #define DEFINE_PAGE_FAULT_EVENT(name) \ DEFINE_EVENT_FN(x86_exceptions, name, \ TP_PROTO(unsigned long address, struct pt_regs *regs, \ unsigned long error_code), \ TP_ARGS(address, regs, error_code), \ trace_pagefault_reg, trace_pagefault_unreg); DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); #undef TRACE_INCLUDE_PATH #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE exceptions #endif /* _TRACE_PAGE_FAULT_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 // SPDX-License-Identifier: GPL-2.0-only /* * Lock-less NULL terminated single linked list * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/llist.h> /** * llist_add_batch - add several linked entries in batch * @new_first: first entry in batch to be added * @new_last: last entry in batch to be added * @head: the head for your lock-less list * * Return whether list is empty before adding. */ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head) { struct llist_node *first; do { new_last->next = first = READ_ONCE(head->first); } while (cmpxchg(&head->first, first, new_first) != first); return !first; } EXPORT_SYMBOL_GPL(llist_add_batch); /** * llist_del_first - delete the first entry of lock-less list * @head: the head for your lock-less list * * If list is empty, return NULL, otherwise, return the first entry * deleted, this is the newest added one. * * Only one llist_del_first user can be used simultaneously with * multiple llist_add users without lock. Because otherwise * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, * llist_add) sequence in another user may change @head->first->next, * but keep @head->first. If multiple consumers are needed, please * use llist_del_all or use lock between consumers. */ struct llist_node *llist_del_first(struct llist_head *head) { struct llist_node *entry, *old_entry, *next; entry = smp_load_acquire(&head->first); for (;;) { if (entry == NULL) return NULL; old_entry = entry; next = READ_ONCE(entry->next); entry = cmpxchg(&head->first, old_entry, next); if (entry == old_entry) break; } return entry; } EXPORT_SYMBOL_GPL(llist_del_first); /** * llist_reverse_order - reverse order of a llist chain * @head: first item of the list to be reversed * * Reverse the order of a chain of llist entries and return the * new first entry. */ struct llist_node *llist_reverse_order(struct llist_node *head) { struct llist_node *new_head =