1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Copyright (C) 2003 Tresys Technology, LLC * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation, version 2. * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" static struct kmem_cache *avtab_node_cachep; static struct kmem_cache *avtab_xperms_cachep; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ static inline int avtab_hash(struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; static const u32 r1 = 15; static const u32 r2 = 13; static const u32 m = 5; static const u32 n = 0xe6546b64; u32 hash = 0; #define mix(input) { \ u32 v = input; \ v *= c1; \ v = (v << r1) | (v >> (32 - r1)); \ v *= c2; \ hash ^= v; \ hash = (hash << r2) | (hash >> (32 - r2)); \ hash = hash * m + n; \ } mix(keyp->target_class); mix(keyp->target_type); mix(keyp->source_type); #undef mix hash ^= hash >> 16; hash *= 0x85ebca6b; hash ^= hash >> 13; hash *= 0xc2b2ae35; hash ^= hash >> 16; return hash & mask; } static struct avtab_node* avtab_insert_node(struct avtab *h, int hvalue, struct avtab_node *prev, struct avtab_node *cur, struct avtab_key *key, struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } if (prev) { newnode->next = prev->next; prev->next = newnode; } else { struct avtab_node **n = &h->htable[hvalue]; newnode->next = *n; *n = newnode; } h->nel++; return newnode; } static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur, *newnode; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) { /* extended perms may not be unique */ if (specified & AVTAB_XPERMS) break; return -EEXIST; } if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } newnode = avtab_insert_node(h, hvalue, prev, cur, key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node * avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) break; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return avtab_insert_node(h, hvalue, prev, cur, key, datum); } struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *key) { int hvalue; struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) return &cur->datum; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return NULL; } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node* avtab_search_node(struct avtab *h, struct avtab_key *key) { int hvalue; struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) return cur; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return NULL; } struct avtab_node* avtab_search_node_next(struct avtab_node *node, int specified) { struct avtab_node *cur; if (!node) return NULL; specified &= ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); for (cur = node->next; cur; cur = cur->next) { if (node->key.source_type == cur->key.source_type && node->key.target_type == cur->key.target_type && node->key.target_class == cur->key.target_class && (specified & cur->key.specified)) return cur; if (node->key.source_type < cur->key.source_type) break; if (node->key.source_type == cur->key.source_type && node->key.target_type < cur->key.target_type) break; if (node->key.source_type == cur->key.source_type && node->key.target_type == cur->key.target_type && node->key.target_class < cur->key.target_class) break; } return NULL; } void avtab_destroy(struct avtab *h) { int i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { u32 shift = 1; u32 work = nrules >> 3; while (work) { work >>= 1; shift++; } nslot = 1 << shift; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } void avtab_hash_eval(struct avtab *h, char *tag) { int i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } static uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, int (*insertf)(struct avtab *a, struct avtab_key *k, struct avtab_datum *d, void *p), void *p) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, vers = pol->policyvers; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int i, rc; unsigned set; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32)*items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16)*4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = 0; for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (key.specified & spec_order[i]) set++; } if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, void *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, void *fp) { unsigned int i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = kmem_cache_create("avtab_node", sizeof(struct avtab_node), 0, SLAB_PANIC, NULL); avtab_xperms_cachep = kmem_cache_create("avtab_extended_perms", sizeof(struct avtab_extended_perms), 0, SLAB_PANIC, NULL); }
1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/internal.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <linux/hardirq.h> #include <linux/pkeys.h> #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ union fpregs_state init_fpstate __read_mostly; /* * Track whether the kernel is using the FPU state * currently. * * This flag is used: * * - by IRQ context code to potentially use the FPU * if it's unused. * * - to debug kernel_fpu_begin()/end() correctness */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); static bool kernel_fpu_disabled(void) { return this_cpu_read(in_kernel_fpu); } static bool interrupted_kernel_fpu_idle(void) { return !kernel_fpu_disabled(); } /* * Were we in user mode (or vm86 mode) when we were * interrupted? * * Doing kernel_fpu_begin/end() is ok if we are running * in an interrupt context from user mode - we'll just * save the FPU state as required. */ static bool interrupted_user_mode(void) { struct pt_regs *regs = get_irq_regs(); return regs && user_mode(regs); } /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? * * It's always ok in process context (ie "not interrupt") * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { return !in_interrupt() || interrupted_user_mode() || interrupted_kernel_fpu_idle(); } EXPORT_SYMBOL(irq_fpu_usable); /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact and we can * keep registers active. * * The legacy FNSAVE instruction cleared all FPU state * unconditionally, so registers are essentially destroyed. * Modern FPU state can be kept in registers, if there are * no pending FP exceptions. */ int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); /* * AVX512 state is tracked here because its use is * known to slow the max clock speed of the core. */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; return 1; } if (likely(use_fxsr())) { copy_fxregs_to_kernel(fpu); return 1; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to mark them inactive: */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); return 0; } EXPORT_SYMBOL(copy_fpregs_to_fpstate); void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); WARN_ON_FPU(!irq_fpu_usable()); WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, true); if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); /* * Ignore return value -- we don't care if reg state * is clobbered. */ copy_fpregs_to_fpstate(&current->thread.fpu); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, false); preempt_enable(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Save the FPU state (mark it for reload if necessary): * * This only ever gets called for the current task. */ void fpu__save(struct fpu *fpu) { WARN_ON_FPU(fpu != &current->thread.fpu); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } } trace_x86_fpu_after_save(fpu); fpregs_unlock(); } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fregs_state *fp) { fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; fp->fos = 0xffff0000u; } void fpstate_init(union fpregs_state *state) { if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, fpu_kernel_xstate_size); if (static_cpu_has(X86_FEATURE_XSAVES)) fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); } EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct task_struct *dst, struct task_struct *src) { struct fpu *dst_fpu = &dst->thread.fpu; struct fpu *src_fpu = &src->thread.fpu; dst_fpu->last_cpu = -1; if (!static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != &current->thread.fpu); /* * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: */ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* * If the FPU registers are not current just memcpy() the state. * Otherwise save current FPU registers directly into the child's FPU * context, without any memory-to-memory copying. * * ( The function 'fails' in the FNSAVE case, which destroys * register contents so we have to load them back. ) */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); else if (!copy_fpregs_to_fpstate(dst_fpu)) copy_kernel_to_fpregs(&dst_fpu->state); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * Activate the current task's in-memory FPU context, * if it has not been used before: */ static void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != &current->thread.fpu); set_thread_flag(TIF_NEED_FPU_LOAD); fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); } /* * This function must be called before we read a task's fpstate. * * There's two cases where this gets called: * * - for the current task (when coredumping), in which case we have * to save the latest FPU registers into the fpstate, * * - or it's called for stopped tasks (ptrace), in which case the * registers were already saved by the context-switch code when * the task scheduled out. * * If the task has used the FPU before then save it. */ void fpu__prepare_read(struct fpu *fpu) { if (fpu == &current->thread.fpu) fpu__save(fpu); } /* * This function must be called before we write a task's fpstate. * * Invalidate any cached FPU registers. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU * state in the fpstate buffer: */ WARN_ON_FPU(fpu == &current->thread.fpu); /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct fpu *fpu) { preempt_disable(); if (fpu == &current->thread.fpu) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); } /* * Clear the FPU state back to init state. * * Called by sys_execve(), by the signal handler code and by various * error paths. */ static void fpu__clear(struct fpu *fpu, bool user_only) { WARN_ON_FPU(fpu != &current->thread.fpu); if (!static_cpu_has(X86_FEATURE_FPU)) { fpu__drop(fpu); fpu__initialize(fpu); return; } fpregs_lock(); if (user_only) { if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) copy_kernel_to_xregs(&fpu->state.xsave, xfeatures_mask_supervisor()); copy_init_fpstate_to_fpregs(xfeatures_mask_user()); } else { copy_init_fpstate_to_fpregs(xfeatures_mask_all); } fpregs_mark_activate(); fpregs_unlock(); } void fpu__clear_user_states(struct fpu *fpu) { fpu__clear(fpu, true); } void fpu__clear_all(struct fpu *fpu) { fpu__clear(fpu, false); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; __fpregs_load_activate(); } EXPORT_SYMBOL_GPL(switch_fpu_return); #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = &current->thread.fpu; if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = &current->thread.fpu; fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } EXPORT_SYMBOL_GPL(fpregs_mark_activate); /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->state.fxsave.cwd; swd = fpu->state.fxsave.swd; } else { cwd = (unsigned short)fpu->state.fsave.cwd; swd = (unsigned short)fpu->state.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->state.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_GETORDER_H #define __ASM_GENERIC_GETORDER_H #ifndef __ASSEMBLY__ #include <linux/compiler.h> #include <linux/log2.h> /** * get_order - Determine the allocation order of a memory size * @size: The size for which to get the order * * Determine the allocation order of a particular sized block of memory. This * is on a logarithmic scale, where: * * 0 -> 2^0 * PAGE_SIZE and below * 1 -> 2^1 * PAGE_SIZE to 2^0 * PAGE_SIZE + 1 * 2 -> 2^2 * PAGE_SIZE to 2^1 * PAGE_SIZE + 1 * 3 -> 2^3 * PAGE_SIZE to 2^2 * PAGE_SIZE + 1 * 4 -> 2^4 * PAGE_SIZE to 2^3 * PAGE_SIZE + 1 * ... * * The order returned is used to find the smallest allocation granule required * to hold an object of the specified size. * * The result is undefined if the size is 0. */ static inline __attribute_const__ int get_order(unsigned long size) { if (__builtin_constant_p(size)) { if (!size) return BITS_PER_LONG - PAGE_SHIFT; if (size < (1UL << PAGE_SHIFT)) return 0; return ilog2((size) - 1) - PAGE_SHIFT + 1; } size--; size >>= PAGE_SHIFT; #if BITS_PER_LONG == 32 return fls(size); #else return fls64(size); #endif } #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_GETORDER_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_DST_METADATA_H #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> #include <net/ip_tunnels.h> #include <net/dst.h> enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, }; struct hw_port_info { struct net_device *lower_dev; u32 port_id; }; struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; } u; }; static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb) { struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); if (md_dst && md_dst->dst.flags & DST_METADATA) return md_dst; return NULL; } static inline struct ip_tunnel_info * skb_tunnel_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_IP_TUNNEL) return &md_dst->u.tun_info; dst = skb_dst(skb); if (dst && dst->lwtstate && (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; } static inline bool skb_valid_dst(const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); return dst && !(dst->flags & DST_METADATA); } static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { const struct metadata_dst *a, *b; if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) return 0; a = (const struct metadata_dst *) skb_dst(skb_a); b = (const struct metadata_dst *) skb_dst(skb_b); if (!a != !b || a->type != b->type) return 1; switch (a->type) { case METADATA_HW_PORT_MUX: return memcmp(&a->u.port_info, &b->u.port_info, sizeof(a->u.port_info)); case METADATA_IP_TUNNEL: return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); default: return 1; } } void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); static inline struct metadata_dst *tun_rx_dst(int md_size) { struct metadata_dst *tun_dst; tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!tun_dst) return NULL; tun_dst->u.tun_info.options_len = 0; tun_dst->u.tun_info.mode = 0; return tun_dst; } static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); int md_size; struct metadata_dst *new_md; if (!md_dst || md_dst->type != METADATA_IP_TUNNEL) return ERR_PTR(-EINVAL); md_size = md_dst->u.tun_info.options_len; new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!new_md) return ERR_PTR(-ENOMEM); memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, sizeof(struct ip_tunnel_info) + md_size); skb_dst_drop(skb); dst_hold(&new_md->dst); skb_dst_set(skb, &new_md->dst); return new_md; } static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) { struct metadata_dst *dst; dst = tun_dst_unclone(skb); if (IS_ERR(dst)) return NULL; return &dst->u.tun_info; } static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; ip_tunnel_key_init(&tun_dst->u.tun_info.key, saddr, daddr, tos, ttl, 0, 0, tp_dst, tunnel_id, flags); return tun_dst; } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { const struct iphdr *iph = ip_hdr(skb); return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, 0, flags, tunnel_id, md_size); } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; info->key.tun_flags = flags; info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; info->key.u.ipv6.src = *saddr; info->key.u.ipv6.dst = *daddr; info->key.tos = tos; info->key.ttl = ttl; info->key.label = label; return tun_dst; } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr, ipv6_get_dsfield(ip6h), ip6h->hop_limit, 0, ip6_flowlabel(ip6h), flags, tunnel_id, md_size); } #endif /* __NET_DST_METADATA_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* overloaded: * - notify group_exit_task when ->count is equal to notify_count * - everyone except group_exit_task is stopped during signal delivery * of fatal signals, group_exit_task processes the signal. */ int notify_count; struct task_struct *group_exit_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ int posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ #define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { return (sig->flags & SIGNAL_GROUP_EXIT) || (sig->group_exit_task != NULL); } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *task, sigset_t *mask, kernel_siginfo_t *info); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(task, &task->blocked, &__info); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(&current->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) set_special_state(TASK_STOPPED); spin_unlock_irq(&current->sighand->siglock); schedule(); } #ifdef __ARCH_SI_TRAPNO # define ___ARCH_SI_TRAPNO(_a1) , _a1 #else # define ___ARCH_SI_TRAPNO(_a1) #endif #ifdef __ia64__ # define ___ARCH_SI_IA64(_a1, _a2, _a3) , _a1, _a2, _a3 #else # define ___ARCH_SI_IA64(_a1, _a2, _a3) #endif int force_sig_fault_to_task(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)); int send_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int signal_pending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return signal_pending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(long state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending_and_wake(struct task_struct *t); extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool resume) { signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { signal_wake_up_state(t, resume ? __TASK_TRACED : 0); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(&current->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!test_thread_flag(TIF_SIGPENDING)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = &current->blocked; if (unlikely(test_restore_sigmask())) res = &current->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Careful: do_each_thread/while_each_thread is a double loop so * 'break' will not work as expected - use goto instead. */ #define do_each_thread(g, t) \ for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } static inline struct task_struct *next_thread(const struct task_struct *p) { return list_entry_rcu(p->thread_group.next, struct task_struct, thread_group); } static inline int thread_group_empty(struct task_struct *p) { return list_empty(&p->thread_group); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern bool thread_group_exited(struct pid *pid); extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) { struct sighand_struct *ret; ret = __lock_task_sighand(task, flags); (void)__cond_lock(&task->sighand->siglock, ret); return ret; } static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_STACK_H #define _LINUX_SCHED_TASK_STACK_H /* * task->stack (kernel stack) handling interfaces: */ #include <linux/sched.h> #include <linux/magic.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * When accessing the stack of a non-current task that might exit, use * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ static inline void *task_stack_page(const struct task_struct *task) { return task->stack; } #define setup_thread_stack(new,old) do { } while(0) static inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; #else return task->stack; #endif } #elif !defined(__HAVE_THREAD_FUNCTIONS) #define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { *task_thread_info(p) = *task_thread_info(org); task_thread_info(p)->task = p; } /* * Return the address of the last usable long on the stack. * * When the stack grows down, this is just above the thread * info struct. Going any lower will corrupt the threadinfo. * * When the stack grows up, this is the highest address. * Beyond that position, we corrupt data on the next page. */ static inline unsigned long *end_of_stack(struct task_struct *p) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; #else return (unsigned long *)(task_thread_info(p) + 1); #endif } #endif #ifdef CONFIG_THREAD_INFO_IN_TASK static inline void *try_get_task_stack(struct task_struct *tsk) { return refcount_inc_not_zero(&tsk->stack_refcount) ? task_stack_page(tsk) : NULL; } extern void put_task_stack(struct task_struct *tsk); #else static inline void *try_get_task_stack(struct task_struct *tsk) { return task_stack_page(tsk); } static inline void put_task_stack(struct task_struct *tsk) {} #endif #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE static inline unsigned long stack_not_used(struct task_struct *p) { unsigned long *n = end_of_stack(p); do { /* Skip over canary */ # ifdef CONFIG_STACK_GROWSUP n--; # else n++; # endif } while (!*n); # ifdef CONFIG_STACK_GROWSUP return (unsigned long)end_of_stack(p) - (unsigned long)n; # else return (unsigned long)n - (unsigned long)end_of_stack(p); # endif } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); #ifndef __HAVE_ARCH_KSTACK_END static inline int kstack_end(void *addr) { /* Reliable end of stack detection: * Some APM bios versions misalign the stack */ return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); } #endif #endif /* _LINUX_SCHED_TASK_STACK_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_RT_H #define _LINUX_SCHED_RT_H #include <linux/sched.h> struct task_struct; static inline int rt_prio(int prio) { if (unlikely(prio < MAX_RT_PRIO)) return 1; return 0; } static inline int rt_task(struct task_struct *p) { return rt_prio(p->prio); } static inline bool task_is_realtime(struct task_struct *tsk) { int policy = tsk->policy; if (policy == SCHED_FIFO || policy == SCHED_RR) return true; if (policy == SCHED_DEADLINE) return true; return false; } #ifdef CONFIG_RT_MUTEXES /* * Must hold either p->pi_lock or task_rq(p)->lock. */ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) { return p->pi_top_task; } extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) { return tsk->pi_blocked_on != NULL; } #else static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; } # define rt_mutex_adjust_pi(p) do { } while (0) static inline bool tsk_is_pi_blocked(struct task_struct *tsk) { return false; } #endif extern void normalize_rt_tasks(void); /* * default timeslice is 100 msecs (used only for SCHED_RR tasks). * Timeslices get refilled after they expire. */ #define RR_TIMESLICE (100 * HZ / 1000) #endif /* _LINUX_SCHED_RT_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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008 Intel Corporation * Author: Matthew Wilcox <willy@linux.intel.com> * * Please see kernel/locking/semaphore.c for documentation of these functions */ #ifndef __LINUX_SEMAPHORE_H #define __LINUX_SEMAPHORE_H #include <linux/list.h> #include <linux/spinlock.h> /* Please don't access any members of this structure directly */ struct semaphore { raw_spinlock_t lock; unsigned int count; struct list_head wait_list; }; #define __SEMAPHORE_INITIALIZER(name, n) \ { \ .lock = __RAW_SPIN_LOCK_UNLOCKED((name).lock), \ .count = n, \ .wait_list = LIST_HEAD_INIT((name).wait_list), \ } #define DEFINE_SEMAPHORE(name) \ struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) static inline void sema_init(struct semaphore *sem, int val) { static struct lock_class_key __key; *sem = (struct semaphore) __SEMAPHORE_INITIALIZER(*sem, val); lockdep_init_map(&sem->lock.dep_map, "semaphore->lock", &__key, 0); } extern void down(struct semaphore *sem); extern int __must_check down_interruptible(struct semaphore *sem); extern int __must_check down_killable(struct semaphore *sem); extern int __must_check down_trylock(struct semaphore *sem); extern int __must_check down_timeout(struct semaphore *sem, long jiffies); extern void up(struct semaphore *sem); #endif /* __LINUX_SEMAPHORE_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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2020 Christoph Hellwig. * * Support for "universal" pointers that can point to either kernel or userspace * memory. */ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H #include <linux/slab.h> #include <linux/uaccess.h> typedef struct { union { void *kernel; void __user *user; }; bool is_kernel : 1; } sockptr_t; static inline bool sockptr_is_kernel(sockptr_t sockptr) { return sockptr.is_kernel; } static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } static inline sockptr_t USER_SOCKPTR(void __user *p) { return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) { if (sockptr_is_kernel(sockptr)) return !sockptr.kernel; return !sockptr.user; } static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); memcpy(dst, src.kernel + offset, size); return 0; } static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { if (!sockptr_is_kernel(dst)) return copy_to_user(dst.user + offset, src, size); memcpy(dst.kernel + offset, src, size); return 0; } static inline void *memdup_sockptr(sockptr_t src, size_t len) { void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) { char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { size_t len = min(strnlen(src.kernel, count - 1) + 1, count); memcpy(dst, src.kernel, len); return len; } return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_SOCKPTR_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/transaction.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * Generic filesystem transaction handling code; part of the ext2fs * journaling system. * * This file manages transactions (compound commits managed by the * journaling code) and handles (individual atomic operations by the * filesystem). */ #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/hrtimer.h> #include <linux/backing-dev.h> #include <linux/bug.h> #include <linux/module.h> #include <linux/sched/mm.h> #include <trace/events/jbd2.h> static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); static void __jbd2_journal_unfile_buffer(struct journal_head *jh); static struct kmem_cache *transaction_cache; int __init jbd2_journal_init_transaction_cache(void) { J_ASSERT(!transaction_cache); transaction_cache = kmem_cache_create("jbd2_transaction_s", sizeof(transaction_t), 0, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY, NULL); if (!transaction_cache) { pr_emerg("JBD2: failed to create transaction cache\n"); return -ENOMEM; } return 0; } void jbd2_journal_destroy_transaction_cache(void) { kmem_cache_destroy(transaction_cache); transaction_cache = NULL; } void jbd2_journal_free_transaction(transaction_t *transaction) { if (unlikely(ZERO_OR_NULL_PTR(transaction))) return; kmem_cache_free(transaction_cache, transaction); } /* * Base amount of descriptor blocks we reserve for each transaction. */ static int jbd2_descriptor_blocks_per_trans(journal_t *journal) { int tag_space = journal->j_blocksize - sizeof(journal_header_t); int tags_per_block; /* Subtract UUID */ tag_space -= 16; if (jbd2_journal_has_csum_v2or3(journal)) tag_space -= sizeof(struct jbd2_journal_block_tail); /* Commit code leaves a slack space of 16 bytes at the end of block */ tags_per_block = (tag_space - 16) / journal_tag_bytes(journal); /* * Revoke descriptors are accounted separately so we need to reserve * space for commit block and normal transaction descriptor blocks. */ return 1 + DIV_ROUND_UP(journal->j_max_transaction_buffers, tags_per_block); } /* * jbd2_get_transaction: obtain a new transaction_t object. * * Simply initialise a new transaction. Initialize it in * RUNNING state and add it to the current journal (which should not * have an existing running transaction: we only make a new transaction * once we have started to commit the old one). * * Preconditions: * The journal MUST be locked. We don't perform atomic mallocs on the * new transaction and we can't block without protecting against other * processes trying to touch the journal while it is in transition. * */ static void jbd2_get_transaction(journal_t *journal, transaction_t *transaction) { transaction->t_journal = journal; transaction->t_state = T_RUNNING; transaction->t_start_time = ktime_get(); transaction->t_tid = journal->j_transaction_sequence++; transaction->t_expires = jiffies + journal->j_commit_interval; spin_lock_init(&transaction->t_handle_lock); atomic_set(&transaction->t_updates, 0); atomic_set(&transaction->t_outstanding_credits, jbd2_descriptor_blocks_per_trans(journal) + atomic_read(&journal->j_reserved_credits)); atomic_set(&transaction->t_outstanding_revokes, 0); atomic_set(&transaction->t_handle_count, 0); INIT_LIST_HEAD(&transaction->t_inode_list); INIT_LIST_HEAD(&transaction->t_private_list); /* Set up the commit timer for the new transaction. */ journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires); add_timer(&journal->j_commit_timer); J_ASSERT(journal->j_running_transaction == NULL); journal->j_running_transaction = transaction; transaction->t_max_wait = 0; transaction->t_start = jiffies; transaction->t_requested = 0; } /* * Handle management. * * A handle_t is an object which represents a single atomic update to a * filesystem, and which tracks all of the modifications which form part * of that one update. */ /* * Update transaction's maximum wait time, if debugging is enabled. * * In order for t_max_wait to be reliable, it must be protected by a * lock. But doing so will mean that start_this_handle() can not be * run in parallel on SMP systems, which limits our scalability. So * unless debugging is enabled, we no longer update t_max_wait, which * means that maximum wait time reported by the jbd2_run_stats * tracepoint will always be zero. */ static inline void update_t_max_wait(transaction_t *transaction, unsigned long ts) { #ifdef CONFIG_JBD2_DEBUG if (jbd2_journal_enable_debug && time_after(transaction->t_start, ts)) { ts = jbd2_time_diff(ts, transaction->t_start); spin_lock(&transaction->t_handle_lock); if (ts > transaction->t_max_wait) transaction->t_max_wait = ts; spin_unlock(&transaction->t_handle_lock); } #endif } /* * Wait until running transaction passes to T_FLUSH state and new transaction * can thus be started. Also starts the commit if needed. The function expects * running transaction to exist and releases j_state_lock. */ static void wait_transaction_locked(journal_t *journal) __releases(journal->j_state_lock) { DEFINE_WAIT(wait); int need_to_start; tid_t tid = journal->j_running_transaction->t_tid; prepare_to_wait(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); jbd2_might_wait_for_commit(journal); schedule(); finish_wait(&journal->j_wait_transaction_locked, &wait); } /* * Wait until running transaction transitions from T_SWITCH to T_FLUSH * state and new transaction can thus be started. The function releases * j_state_lock. */ static void wait_transaction_switching(journal_t *journal) __releases(journal->j_state_lock) { DEFINE_WAIT(wait); if (WARN_ON(!journal->j_running_transaction || journal->j_running_transaction->t_state != T_SWITCH)) { read_unlock(&journal->j_state_lock); return; } prepare_to_wait(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); /* * We don't call jbd2_might_wait_for_commit() here as there's no * waiting for outstanding handles happening anymore in T_SWITCH state * and handling of reserved handles actually relies on that for * correctness. */ schedule(); finish_wait(&journal->j_wait_transaction_locked, &wait); } static void sub_reserved_credits(journal_t *journal, int blocks) { atomic_sub(blocks, &journal->j_reserved_credits); wake_up(&journal->j_wait_reserved); } /* * Wait until we can add credits for handle to the running transaction. Called * with j_state_lock held for reading. Returns 0 if handle joined the running * transaction. Returns 1 if we had to wait, j_state_lock is dropped, and * caller must retry. */ static int add_transaction_credits(journal_t *journal, int blocks, int rsv_blocks) { transaction_t *t = journal->j_running_transaction; int needed; int total = blocks + rsv_blocks; /* * If the current transaction is locked down for commit, wait * for the lock to be released. */ if (t->t_state != T_RUNNING) { WARN_ON_ONCE(t->t_state >= T_FLUSH); wait_transaction_locked(journal); return 1; } /* * If there is not enough space left in the log to write all * potential buffers requested by this operation, we need to * stall pending a log checkpoint to free some more log space. */ needed = atomic_add_return(total, &t->t_outstanding_credits); if (needed > journal->j_max_transaction_buffers) { /* * If the current transaction is already too large, * then start to commit it: we can then go back and * attach this handle to a new transaction. */ atomic_sub(total, &t->t_outstanding_credits); /* * Is the number of reserved credits in the current transaction too * big to fit this handle? Wait until reserved credits are freed. */ if (atomic_read(&journal->j_reserved_credits) + total > journal->j_max_transaction_buffers) { read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); wait_event(journal->j_wait_reserved, atomic_read(&journal->j_reserved_credits) + total <= journal->j_max_transaction_buffers); return 1; } wait_transaction_locked(journal); return 1; } /* * The commit code assumes that it can get enough log space * without forcing a checkpoint. This is *critical* for * correctness: a checkpoint of a buffer which is also * associated with a committing transaction creates a deadlock, * so commit simply cannot force through checkpoints. * * We must therefore ensure the necessary space in the journal * *before* starting to dirty potentially checkpointed buffers * in the new transaction. */ if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) { atomic_sub(total, &t->t_outstanding_credits); read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); write_lock(&journal->j_state_lock); if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) __jbd2_log_wait_for_space(journal); write_unlock(&journal->j_state_lock); return 1; } /* No reservation? We are done... */ if (!rsv_blocks) return 0; needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits); /* We allow at most half of a transaction to be reserved */ if (needed > journal->j_max_transaction_buffers / 2) { sub_reserved_credits(journal, rsv_blocks); atomic_sub(total, &t->t_outstanding_credits); read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); wait_event(journal->j_wait_reserved, atomic_read(&journal->j_reserved_credits) + rsv_blocks <= journal->j_max_transaction_buffers / 2); return 1; } return 0; } /* * start_this_handle: Given a handle, deal with any locking or stalling * needed to make sure that there is enough journal space for the handle * to begin. Attach the handle to a transaction and set up the * transaction's buffer credits. */ static int start_this_handle(journal_t *journal, handle_t *handle, gfp_t gfp_mask) { transaction_t *transaction, *new_transaction = NULL; int blocks = handle->h_total_credits; int rsv_blocks = 0; unsigned long ts = jiffies; if (handle->h_rsv_handle) rsv_blocks = handle->h_rsv_handle->h_total_credits; /* * Limit the number of reserved credits to 1/2 of maximum transaction * size and limit the number of total credits to not exceed maximum * transaction size per operation. */ if ((rsv_blocks > journal->j_max_transaction_buffers / 2) || (rsv_blocks + blocks > journal->j_max_transaction_buffers)) { printk(KERN_ERR "JBD2: %s wants too many credits " "credits:%d rsv_credits:%d max:%d\n", current->comm, blocks, rsv_blocks, journal->j_max_transaction_buffers); WARN_ON(1); return -ENOSPC; } alloc_transaction: /* * This check is racy but it is just an optimization of allocating new * transaction early if there are high chances we'll need it. If we * guess wrong, we'll retry or free unused transaction. */ if (!data_race(journal->j_running_transaction)) { /* * If __GFP_FS is not present, then we may be being called from * inside the fs writeback layer, so we MUST NOT fail. */ if ((gfp_mask & __GFP_FS) == 0) gfp_mask |= __GFP_NOFAIL; new_transaction = kmem_cache_zalloc(transaction_cache, gfp_mask); if (!new_transaction) return -ENOMEM; } jbd_debug(3, "New handle %p going live.\n", handle); /* * We need to hold j_state_lock until t_updates has been incremented, * for proper journal barrier handling */ repeat: read_lock(&journal->j_state_lock); BUG_ON(journal->j_flags & JBD2_UNMOUNT); if (is_journal_aborted(journal) || (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) { read_unlock(&journal->j_state_lock); jbd2_journal_free_transaction(new_transaction); return -EROFS; } /* * Wait on the journal's transaction barrier if necessary. Specifically * we allow reserved handles to proceed because otherwise commit could * deadlock on page writeback not being able to complete. */ if (!handle->h_reserved && journal->j_barrier_count) { read_unlock(&journal->j_state_lock); wait_event(journal->j_wait_transaction_locked, journal->j_barrier_count == 0); goto repeat; } if (!journal->j_running_transaction) { read_unlock(&journal->j_state_lock); if (!new_transaction) goto alloc_transaction; write_lock(&journal->j_state_lock); if (!journal->j_running_transaction && (handle->h_reserved || !journal->j_barrier_count)) { jbd2_get_transaction(journal, new_transaction); new_transaction = NULL; } write_unlock(&journal->j_state_lock); goto repeat; } transaction = journal->j_running_transaction; if (!handle->h_reserved) { /* We may have dropped j_state_lock - restart in that case */ if (add_transaction_credits(journal, blocks, rsv_blocks)) goto repeat; } else { /* * We have handle reserved so we are allowed to join T_LOCKED * transaction and we don't have to check for transaction size * and journal space. But we still have to wait while running * transaction is being switched to a committing one as it * won't wait for any handles anymore. */ if (transaction->t_state == T_SWITCH) { wait_transaction_switching(journal); goto repeat; } sub_reserved_credits(journal, blocks); handle->h_reserved = 0; } /* OK, account for the buffers that this operation expects to * use and add the handle to the running transaction. */ update_t_max_wait(transaction, ts); handle->h_transaction = transaction; handle->h_requested_credits = blocks; handle->h_revoke_credits_requested = handle->h_revoke_credits; handle->h_start_jiffies = jiffies; atomic_inc(&transaction->t_updates); atomic_inc(&transaction->t_handle_count); jbd_debug(4, "Handle %p given %d credits (total %d, free %lu)\n", handle, blocks, atomic_read(&transaction->t_outstanding_credits), jbd2_log_space_left(journal)); read_unlock(&journal->j_state_lock); current->journal_info = handle; rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_); jbd2_journal_free_transaction(new_transaction); /* * Ensure that no allocations done while the transaction is open are * going to recurse back to the fs layer. */ handle->saved_alloc_context = memalloc_nofs_save(); return 0; } /* Allocate a new handle. This should probably be in a slab... */ static handle_t *new_handle(int nblocks) { handle_t *handle = jbd2_alloc_handle(GFP_NOFS); if (!handle) return NULL; handle->h_total_credits = nblocks; handle->h_ref = 1; return handle; } handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no) { handle_t *handle = journal_current_handle(); int err; if (!journal) return ERR_PTR(-EROFS); if (handle) { J_ASSERT(handle->h_transaction->t_journal == journal); handle->h_ref++; return handle; } nblocks += DIV_ROUND_UP(revoke_records, journal->j_revoke_records_per_block); handle = new_handle(nblocks); if (!handle) return ERR_PTR(-ENOMEM); if (rsv_blocks) { handle_t *rsv_handle; rsv_handle = new_handle(rsv_blocks); if (!rsv_handle) { jbd2_free_handle(handle); return ERR_PTR(-ENOMEM); } rsv_handle->h_reserved = 1; rsv_handle->h_journal = journal; handle->h_rsv_handle = rsv_handle; } handle->h_revoke_credits = revoke_records; err = start_this_handle(journal, handle, gfp_mask); if (err < 0) { if (handle->h_rsv_handle) jbd2_free_handle(handle->h_rsv_handle); jbd2_free_handle(handle); return ERR_PTR(err); } handle->h_type = type; handle->h_line_no = line_no; trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, handle->h_transaction->t_tid, type, line_no, nblocks); return handle; } EXPORT_SYMBOL(jbd2__journal_start); /** * jbd2_journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * * We make sure that the transaction can guarantee at least nblocks of * modified buffers in the log. We block until the log can guarantee * that much space. Additionally, if rsv_blocks > 0, we also create another * handle with rsv_blocks reserved blocks in the journal. This handle is * stored in h_rsv_handle. It is not attached to any particular transaction * and thus doesn't block transaction commit. If the caller uses this reserved * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() * on the parent handle will dispose the reserved one. Reserved handle has to * be converted to a normal handle using jbd2_journal_start_reserved() before * it can be used. * * Return a pointer to a newly allocated handle, or an ERR_PTR() value * on failure. */ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) { return jbd2__journal_start(journal, nblocks, 0, 0, GFP_NOFS, 0, 0); } EXPORT_SYMBOL(jbd2_journal_start); static void __jbd2_journal_unreserve_handle(handle_t *handle, transaction_t *t) { journal_t *journal = handle->h_journal; WARN_ON(!handle->h_reserved); sub_reserved_credits(journal, handle->h_total_credits); if (t) atomic_sub(handle->h_total_credits, &t->t_outstanding_credits); } void jbd2_journal_free_reserved(handle_t *handle) { journal_t *journal = handle->h_journal; /* Get j_state_lock to pin running transaction if it exists */ read_lock(&journal->j_state_lock); __jbd2_journal_unreserve_handle(handle, journal->j_running_transaction); read_unlock(&journal->j_state_lock); jbd2_free_handle(handle); } EXPORT_SYMBOL(jbd2_journal_free_reserved); /** * jbd2_journal_start_reserved() - start reserved handle * @handle: handle to start * @type: for handle statistics * @line_no: for handle statistics * * Start handle that has been previously reserved with jbd2_journal_reserve(). * This attaches @handle to the running transaction (or creates one if there's * not transaction running). Unlike jbd2_journal_start() this function cannot * block on journal commit, checkpointing, or similar stuff. It can block on * memory allocation or frozen journal though. * * Return 0 on success, non-zero on error - handle is freed in that case. */ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no) { journal_t *journal = handle->h_journal; int ret = -EIO; if (WARN_ON(!handle->h_reserved)) { /* Someone passed in normal handle? Just stop it. */ jbd2_journal_stop(handle); return ret; } /* * Usefulness of mixing of reserved and unreserved handles is * questionable. So far nobody seems to need it so just error out. */ if (WARN_ON(current->journal_info)) { jbd2_journal_free_reserved(handle); return ret; } handle->h_journal = NULL; /* * GFP_NOFS is here because callers are likely from writeback or * similarly constrained call sites */ ret = start_this_handle(journal, handle, GFP_NOFS); if (ret < 0) { handle->h_journal = journal; jbd2_journal_free_reserved(handle); return ret; } handle->h_type = type; handle->h_line_no = line_no; trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, handle->h_transaction->t_tid, type, line_no, handle->h_total_credits); return 0; } EXPORT_SYMBOL(jbd2_journal_start_reserved); /** * jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. * @revoke_records: number of revoke records to try to extend by. * * Some transactions, such as large extends and truncates, can be done * atomically all at once or in several stages. The operation requests * a credit for a number of buffer modifications in advance, but can * extend its credit if it needs more. * * jbd2_journal_extend tries to give the running handle more buffer credits. * It does not guarantee that allocation - this is a best-effort only. * The calling process MUST be able to deal cleanly with a failure to * extend here. * * Return 0 on success, non-zero on failure. * * return code < 0 implies an error * return code > 0 implies normal transaction-full status. */ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) { transaction_t *transaction = handle->h_transaction; journal_t *journal; int result; int wanted; if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; result = 1; read_lock(&journal->j_state_lock); /* Don't extend a locked-down transaction! */ if (transaction->t_state != T_RUNNING) { jbd_debug(3, "denied handle %p %d blocks: " "transaction not running\n", handle, nblocks); goto error_out; } nblocks += DIV_ROUND_UP( handle->h_revoke_credits_requested + revoke_records, journal->j_revoke_records_per_block) - DIV_ROUND_UP( handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); spin_lock(&transaction->t_handle_lock); wanted = atomic_add_return(nblocks, &transaction->t_outstanding_credits); if (wanted > journal->j_max_transaction_buffers) { jbd_debug(3, "denied handle %p %d blocks: " "transaction too large\n", handle, nblocks); atomic_sub(nblocks, &transaction->t_outstanding_credits); goto unlock; } trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev, transaction->t_tid, handle->h_type, handle->h_line_no, handle->h_total_credits, nblocks); handle->h_total_credits += nblocks; handle->h_requested_credits += nblocks; handle->h_revoke_credits += revoke_records; handle->h_revoke_credits_requested += revoke_records; result = 0; jbd_debug(3, "extended handle %p by %d\n", handle, nblocks); unlock: spin_unlock(&transaction->t_handle_lock); error_out: read_unlock(&journal->j_state_lock); return result; } static void stop_this_handle(handle_t *handle) { transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; int revokes; J_ASSERT(journal_current_handle() == handle); J_ASSERT(atomic_read(&transaction->t_updates) > 0); current->journal_info = NULL; /* * Subtract necessary revoke descriptor blocks from handle credits. We * take care to account only for revoke descriptor blocks the * transaction will really need as large sequences of transactions with * small numbers of revokes are relatively common. */ revokes = handle->h_revoke_credits_requested - handle->h_revoke_credits; if (revokes) { int t_revokes, revoke_descriptors; int rr_per_blk = journal->j_revoke_records_per_block; WARN_ON_ONCE(DIV_ROUND_UP(revokes, rr_per_blk) > handle->h_total_credits); t_revokes = atomic_add_return(revokes, &transaction->t_outstanding_revokes); revoke_descriptors = DIV_ROUND_UP(t_revokes, rr_per_blk) - DIV_ROUND_UP(t_revokes - revokes, rr_per_blk); handle->h_total_credits -= revoke_descriptors; } atomic_sub(handle->h_total_credits, &transaction->t_outstanding_credits); if (handle->h_rsv_handle) __jbd2_journal_unreserve_handle(handle->h_rsv_handle, transaction); if (atomic_dec_and_test(&transaction->t_updates)) wake_up(&journal->j_wait_updates); rwsem_release(&journal->j_trans_commit_map, _THIS_IP_); /* * Scope of the GFP_NOFS context is over here and so we can restore the * original alloc context. */ memalloc_nofs_restore(handle->saved_alloc_context); } /** * jbd2__journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested * @revoke_records: number of revoke record credits requested * @gfp_mask: memory allocation flags (for start_this_handle) * * Restart a handle for a multi-transaction filesystem * operation. * * If the jbd2_journal_extend() call above fails to grant new buffer credits * to a running handle, a call to jbd2_journal_restart will commit the * handle's transaction so far and reattach the handle to a new * transaction capable of guaranteeing the requested number of * credits. We preserve reserved handle if there's any attached to the * passed in handle. */ int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records, gfp_t gfp_mask) { transaction_t *transaction = handle->h_transaction; journal_t *journal; tid_t tid; int need_to_start; int ret; /* If we've had an abort of any type, don't even think about * actually doing the restart! */ if (is_handle_aborted(handle)) return 0; journal = transaction->t_journal; tid = transaction->t_tid; /* * First unlink the handle from its current transaction, and start the * commit on that. */ jbd_debug(2, "restarting handle %p\n", handle); stop_this_handle(handle); handle->h_transaction = NULL; /* * TODO: If we use READ_ONCE / WRITE_ONCE for j_commit_request we can * get rid of pointless j_state_lock traffic like this. */ read_lock(&journal->j_state_lock); need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); handle->h_total_credits = nblocks + DIV_ROUND_UP(revoke_records, journal->j_revoke_records_per_block); handle->h_revoke_credits = revoke_records; ret = start_this_handle(journal, handle, gfp_mask); trace_jbd2_handle_restart(journal->j_fs_dev->bd_dev, ret ? 0 : handle->h_transaction->t_tid, handle->h_type, handle->h_line_no, handle->h_total_credits); return ret; } EXPORT_SYMBOL(jbd2__journal_restart); int jbd2_journal_restart(handle_t *handle, int nblocks) { return jbd2__journal_restart(handle, nblocks, 0, GFP_NOFS); } EXPORT_SYMBOL(jbd2_journal_restart); /** * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. * * This locks out any further updates from being started, and blocks * until all existing updates have completed, returning only once the * journal is in a quiescent state with no updates running. * * The journal lock should not be held on entry. */ void jbd2_journal_lock_updates(journal_t *journal) { DEFINE_WAIT(wait); jbd2_might_wait_for_commit(journal); write_lock(&journal->j_state_lock); ++journal->j_barrier_count; /* Wait until there are no reserved handles */ if (atomic_read(&journal->j_reserved_credits)) { write_unlock(&journal->j_state_lock); wait_event(journal->j_wait_reserved, atomic_read(&journal->j_reserved_credits) == 0); write_lock(&journal->j_state_lock); } /* Wait until there are no running updates */ while (1) { transaction_t *transaction = journal->j_running_transaction; if (!transaction) break; spin_lock(&transaction->t_handle_lock); prepare_to_wait(&journal->j_wait_updates, &wait, TASK_UNINTERRUPTIBLE); if (!atomic_read(&transaction->t_updates)) { spin_unlock(&transaction->t_handle_lock); finish_wait(&journal->j_wait_updates, &wait); break; } spin_unlock(&transaction->t_handle_lock); write_unlock(&journal->j_state_lock); schedule(); finish_wait(&journal->j_wait_updates, &wait); write_lock(&journal->j_state_lock); } write_unlock(&journal->j_state_lock); /* * We have now established a barrier against other normal updates, but * we also need to barrier against other jbd2_journal_lock_updates() calls * to make sure that we serialise special journal-locked operations * too. */ mutex_lock(&journal->j_barrier); } /** * jbd2_journal_unlock_updates () - release barrier * @journal: Journal to release the barrier on. * * Release a transaction barrier obtained with jbd2_journal_lock_updates(). * * Should be called without the journal lock held. */ void jbd2_journal_unlock_updates (journal_t *journal) { J_ASSERT(journal->j_barrier_count != 0); mutex_unlock(&journal->j_barrier); write_lock(&journal->j_state_lock); --journal->j_barrier_count; write_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_transaction_locked); } static void warn_dirty_buffer(struct buffer_head *bh) { printk(KERN_WARNING "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). " "There's a risk of filesystem corruption in case of system " "crash.\n", bh->b_bdev, (unsigned long long)bh->b_blocknr); } /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */ static void jbd2_freeze_jh_data(struct journal_head *jh) { struct page *page; int offset; char *source; struct buffer_head *bh = jh2bh(jh); J_EXPECT_JH(jh, buffer_uptodate(bh), "Possible IO failure.\n"); page = bh->b_page; offset = offset_in_page(bh->b_data); source = kmap_atomic(page); /* Fire data frozen trigger just before we copy the data */ jbd2_buffer_frozen_trigger(jh, source + offset, jh->b_triggers); memcpy(jh->b_frozen_data, source + offset, bh->b_size); kunmap_atomic(source); /* * Now that the frozen data is saved off, we need to store any matching * triggers. */ jh->b_frozen_triggers = jh->b_triggers; } /* * If the buffer is already part of the current transaction, then there * is nothing we need to do. If it is already part of a prior * transaction which we are still committing to disk, then we need to * make sure that we do not overwrite the old copy: we do copy-out to * preserve the copy going to disk. We also account the buffer against * the handle's metadata buffer credits (unless the buffer is already * part of the transaction, that is). * */ static int do_get_write_access(handle_t *handle, struct journal_head *jh, int force_copy) { struct buffer_head *bh; transaction_t *transaction = handle->h_transaction; journal_t *journal; int error; char *frozen_buffer = NULL; unsigned long start_lock, time_lock; journal = transaction->t_journal; jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); JBUFFER_TRACE(jh, "entry"); repeat: bh = jh2bh(jh); /* @@@ Need to check for errors here at some point. */ start_lock = jiffies; lock_buffer(bh); spin_lock(&jh->b_state_lock); /* If it takes too long to lock the buffer, trace it */ time_lock = jbd2_time_diff(start_lock, jiffies); if (time_lock > HZ/10) trace_jbd2_lock_buffer_stall(bh->b_bdev->bd_dev, jiffies_to_msecs(time_lock)); /* We now hold the buffer lock so it is safe to query the buffer * state. Is the buffer dirty? * * If so, there are two possibilities. The buffer may be * non-journaled, and undergoing a quite legitimate writeback. * Otherwise, it is journaled, and we don't expect dirty buffers * in that state (the buffers should be marked JBD_Dirty * instead.) So either the IO is being done under our own * control and this is a bug, or it's a third party IO such as * dump(8) (which may leave the buffer scheduled for read --- * ie. locked but not dirty) or tune2fs (which may actually have * the buffer dirtied, ugh.) */ if (buffer_dirty(bh)) { /* * First question: is this buffer already part of the current * transaction or the existing committing transaction? */ if (jh->b_transaction) { J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_transaction == journal->j_committing_transaction); if (jh->b_next_transaction) J_ASSERT_JH(jh, jh->b_next_transaction == transaction); warn_dirty_buffer(bh); } /* * In any case we need to clean the dirty flag and we must * do it under the buffer lock to be sure we don't race * with running write-out. */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); clear_buffer_dirty(bh); set_buffer_jbddirty(bh); } unlock_buffer(bh); error = -EROFS; if (is_handle_aborted(handle)) { spin_unlock(&jh->b_state_lock); goto out; } error = 0; /* * The buffer is already part of this transaction if b_transaction or * b_next_transaction points to it */ if (jh->b_transaction == transaction || jh->b_next_transaction == transaction) goto done; /* * this is the first time this transaction is touching this buffer, * reset the modified flag */ jh->b_modified = 0; /* * If the buffer is not journaled right now, we need to make sure it * doesn't get written to disk before the caller actually commits the * new data */ if (!jh->b_transaction) { JBUFFER_TRACE(jh, "no transaction"); J_ASSERT_JH(jh, !jh->b_next_transaction); JBUFFER_TRACE(jh, "file as BJ_Reserved"); /* * Make sure all stores to jh (b_modified, b_frozen_data) are * visible before attaching it to the running transaction. * Paired with barrier in jbd2_write_access_granted() */ smp_wmb(); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); goto done; } /* * If there is already a copy-out version of this buffer, then we don't * need to make another one */ if (jh->b_frozen_data) { JBUFFER_TRACE(jh, "has frozen data"); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); goto attach_next; } JBUFFER_TRACE(jh, "owned by older transaction"); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, jh->b_transaction == journal->j_committing_transaction); /* * There is one case we have to be very careful about. If the * committing transaction is currently writing this buffer out to disk * and has NOT made a copy-out, then we cannot modify the buffer * contents at all right now. The essence of copy-out is that it is * the extra copy, not the primary copy, which gets journaled. If the * primary copy is already going to disk then we cannot do copy-out * here. */ if (buffer_shadow(bh)) { JBUFFER_TRACE(jh, "on shadow: sleep"); spin_unlock(&jh->b_state_lock); wait_on_bit_io(&bh->b_state, BH_Shadow, TASK_UNINTERRUPTIBLE); goto repeat; } /* * Only do the copy if the currently-owning transaction still needs it. * If buffer isn't on BJ_Metadata list, the committing transaction is * past that stage (here we use the fact that BH_Shadow is set under * bh_state lock together with refiling to BJ_Shadow list and at this * point we know the buffer doesn't have BH_Shadow set). * * Subtle point, though: if this is a get_undo_access, then we will be * relying on the frozen_data to contain the new value of the * committed_data record after the transaction, so we HAVE to force the * frozen_data copy in that case. */ if (jh->b_jlist == BJ_Metadata || force_copy) { JBUFFER_TRACE(jh, "generate frozen data"); if (!frozen_buffer) { JBUFFER_TRACE(jh, "allocate memory for buffer"); spin_unlock(&jh->b_state_lock); frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS | __GFP_NOFAIL); goto repeat; } jh->b_frozen_data = frozen_buffer; frozen_buffer = NULL; jbd2_freeze_jh_data(jh); } attach_next: /* * Make sure all stores to jh (b_modified, b_frozen_data) are visible * before attaching it to the running transaction. Paired with barrier * in jbd2_write_access_granted() */ smp_wmb(); jh->b_next_transaction = transaction; done: spin_unlock(&jh->b_state_lock); /* * If we are about to journal a buffer, then any revoke pending on it is * no longer valid */ jbd2_journal_cancel_revoke(handle, jh); out: if (unlikely(frozen_buffer)) /* It's usually NULL */ jbd2_free(frozen_buffer, bh->b_size); JBUFFER_TRACE(jh, "exit"); return error; } /* Fast check whether buffer is already attached to the required transaction */ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, bool undo) { struct journal_head *jh; bool ret = false; /* Dirty buffers require special handling... */ if (buffer_dirty(bh)) return false; /* * RCU protects us from dereferencing freed pages. So the checks we do * are guaranteed not to oops. However the jh slab object can get freed * & reallocated while we work with it. So we have to be careful. When * we see jh attached to the running transaction, we know it must stay * so until the transaction is committed. Thus jh won't be freed and * will be attached to the same bh while we run. However it can * happen jh gets freed, reallocated, and attached to the transaction * just after we get pointer to it from bh. So we have to be careful * and recheck jh still belongs to our bh before we return success. */ rcu_read_lock(); if (!buffer_jbd(bh)) goto out; /* This should be bh2jh() but that doesn't work with inline functions */ jh = READ_ONCE(bh->b_private); if (!jh) goto out; /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; if (READ_ONCE(jh->b_transaction) != handle->h_transaction && READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: * 1) Make sure to fetch b_bh after we did previous checks so that we * detect when jh went through free, realloc, attach to transaction * while we were checking. Paired with implicit barrier in that path. * 2) So that access to bh done after jbd2_write_access_granted() * doesn't get reordered and see inconsistent state of concurrent * do_get_write_access(). */ smp_mb(); if (unlikely(jh->b_bh != bh)) goto out; ret = true; out: rcu_read_unlock(); return ret; } /** * jbd2_journal_get_write_access() - notify intent to modify a buffer * for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * * Returns: error code or 0 on success. * * In full data journalling mode the buffer may be of type BJ_AsyncData, * because we're ``write()ing`` a buffer which is also part of a shared mapping. */ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) { struct journal_head *jh; int rc; if (is_handle_aborted(handle)) return -EROFS; if (jbd2_write_access_granted(handle, bh, false)) return 0; jh = jbd2_journal_add_journal_head(bh); /* We do not want to get caught playing with fields which the * log thread also manipulates. Make sure that the buffer * completes any outstanding IO before proceeding. */ rc = do_get_write_access(handle, jh, 0); jbd2_journal_put_journal_head(jh); return rc; } /* * When the user wants to journal a newly created buffer_head * (ie. getblk() returned a new buffer and we are going to populate it * manually rather than reading off disk), then we need to keep the * buffer_head locked until it has been completely filled with new * data. In this case, we should be able to make the assertion that * the bh is not already part of an existing transaction. * * The buffer should already be locked by the caller by this point. * There is no lock ranking violation: it was a newly created, * unlocked buffer beforehand. */ /** * jbd2_journal_get_create_access () - notify intent to use newly created bh * @handle: transaction to new buffer to * @bh: new buffer. * * Call this if you create a new bh. */ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal; struct journal_head *jh = jbd2_journal_add_journal_head(bh); int err; jbd_debug(5, "journal_head %p\n", jh); err = -EROFS; if (is_handle_aborted(handle)) goto out; journal = transaction->t_journal; err = 0; JBUFFER_TRACE(jh, "entry"); /* * The buffer may already belong to this transaction due to pre-zeroing * in the filesystem's new_block code. It may also be on the previous, * committing transaction's lists, but it HAS to be in Forget state in * that case: the transaction must have deleted the buffer for it to be * reused here. */ spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, (jh->b_transaction == transaction || jh->b_transaction == NULL || (jh->b_transaction == journal->j_committing_transaction && jh->b_jlist == BJ_Forget))); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, buffer_locked(jh2bh(jh))); if (jh->b_transaction == NULL) { /* * Previous jbd2_journal_forget() could have left the buffer * with jbddirty bit set because it was being committed. When * the commit finished, we've filed the buffer for * checkpointing and marked it dirty. Now we are reallocating * the buffer so the transaction freeing it must have * committed and so it's safe to clear the dirty bit. */ clear_buffer_dirty(jh2bh(jh)); /* first access by this transaction */ jh->b_modified = 0; JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction == journal->j_committing_transaction) { /* first access by this transaction */ jh->b_modified = 0; JBUFFER_TRACE(jh, "set next transaction"); spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); } spin_unlock(&jh->b_state_lock); /* * akpm: I added this. ext3_alloc_branch can pick up new indirect * blocks which contain freed but then revoked metadata. We need * to cancel the revoke in case we end up freeing it yet again * and the reallocating as data - this would cause a second revoke, * which hits an assertion error. */ JBUFFER_TRACE(jh, "cancelling revoke"); jbd2_journal_cancel_revoke(handle, jh); out: jbd2_journal_put_journal_head(jh); return err; } /** * jbd2_journal_get_undo_access() - Notify intent to modify metadata with * non-rewindable consequences * @handle: transaction * @bh: buffer to undo * * Sometimes there is a need to distinguish between metadata which has * been committed to disk and that which has not. The ext3fs code uses * this for freeing and allocating space, we have to make sure that we * do not reuse freed space until the deallocation has been committed, * since if we overwrote that space we would make the delete * un-rewindable in case of a crash. * * To deal with that, jbd2_journal_get_undo_access requests write access to a * buffer for parts of non-rewindable operations such as delete * operations on the bitmaps. The journaling code must keep a copy of * the buffer's contents prior to the undo_access call until such time * as we know that the buffer has definitely been committed to disk. * * We never need to know which transaction the committed data is part * of, buffers touched here are guaranteed to be dirtied later and so * will be committed to a new transaction in due course, at which point * we can discard the old committed data pointer. * * Returns error number or 0 on success. */ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) { int err; struct journal_head *jh; char *committed_data = NULL; if (is_handle_aborted(handle)) return -EROFS; if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); JBUFFER_TRACE(jh, "entry"); /* * Do this first --- it can drop the journal lock, so we want to * make sure that obtaining the committed_data is done * atomically wrt. completion of any outstanding commits. */ err = do_get_write_access(handle, jh, 1); if (err) goto out; repeat: if (!jh->b_committed_data) committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS|__GFP_NOFAIL); spin_lock(&jh->b_state_lock); if (!jh->b_committed_data) { /* Copy out the current buffer contents into the * preserved, committed copy. */ JBUFFER_TRACE(jh, "generate b_committed data"); if (!committed_data) { spin_unlock(&jh->b_state_lock); goto repeat; } jh->b_committed_data = committed_data; committed_data = NULL; memcpy(jh->b_committed_data, bh->b_data, bh->b_size); } spin_unlock(&jh->b_state_lock); out: jbd2_journal_put_journal_head(jh); if (unlikely(committed_data)) jbd2_free(committed_data, bh->b_size); return err; } /** * jbd2_journal_set_triggers() - Add triggers for commit writeout * @bh: buffer to trigger on * @type: struct jbd2_buffer_trigger_type containing the trigger(s). * * Set any triggers on this journal_head. This is always safe, because * triggers for a committing buffer will be saved off, and triggers for * a running transaction will match the buffer in that transaction. * * Call with NULL to clear the triggers. */ void jbd2_journal_set_triggers(struct buffer_head *bh, struct jbd2_buffer_trigger_type *type) { struct journal_head *jh = jbd2_journal_grab_journal_head(bh); if (WARN_ON(!jh)) return; jh->b_triggers = type; jbd2_journal_put_journal_head(jh); } void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers) { struct buffer_head *bh = jh2bh(jh); if (!triggers || !triggers->t_frozen) return; triggers->t_frozen(triggers, bh, mapped_data, bh->b_size); } void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers) { if (!triggers || !triggers->t_abort) return; triggers->t_abort(triggers, jh2bh(jh)); } /** * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. * @bh: buffer to mark * * mark dirty metadata which needs to be journaled as part of the current * transaction. * * The buffer must have previously had jbd2_journal_get_write_access() * called so that it has a valid journal_head attached to the buffer * head. * * The buffer is placed on the transaction's metadata list and is marked * as belonging to the transaction. * * Returns error number or 0 on success. * * Special care needs to be taken if the buffer already belongs to the * current committing transaction (in which case we should have frozen * data present for that commit). In that case, we don't relink the * buffer: that only gets done when the old transaction finally * completes its commit. */ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal; struct journal_head *jh; int ret = 0; if (is_handle_aborted(handle)) return -EROFS; if (!buffer_jbd(bh)) return -EUCLEAN; /* * We don't grab jh reference here since the buffer must be part * of the running transaction. */ jh = bh2jh(bh); jbd_debug(5, "journal_head %p\n", jh); JBUFFER_TRACE(jh, "entry"); /* * This and the following assertions are unreliable since we may see jh * in inconsistent state unless we grab bh_state lock. But this is * crucial to catch bugs so let's do a reliable check until the * lockless handling is fully proven. */ if (data_race(jh->b_transaction != transaction && jh->b_next_transaction != transaction)) { spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_next_transaction == transaction); spin_unlock(&jh->b_state_lock); } if (jh->b_modified == 1) { /* If it's in our transaction it must be in BJ_Metadata list. */ if (data_race(jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata)) { spin_lock(&jh->b_state_lock); if (jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata) pr_err("JBD2: assertion failure: h_type=%u " "h_line_no=%u block_no=%llu jlist=%u\n", handle->h_type, handle->h_line_no, (unsigned long long) bh->b_blocknr, jh->b_jlist); J_ASSERT_JH(jh, jh->b_transaction != transaction || jh->b_jlist == BJ_Metadata); spin_unlock(&jh->b_state_lock); } goto out; } journal = transaction->t_journal; spin_lock(&jh->b_state_lock); if (jh->b_modified == 0) { /* * This buffer's got modified and becoming part * of the transaction. This needs to be done * once a transaction -bzzz */ if (WARN_ON_ONCE(jbd2_handle_buffer_credits(handle) <= 0)) { ret = -ENOSPC; goto out_unlock_bh; } jh->b_modified = 1; handle->h_total_credits--; } /* * fastpath, to avoid expensive locking. If this buffer is already * on the running transaction's metadata list there is nothing to do. * Nobody can take it off again because there is a handle open. * I _think_ we're OK here with SMP barriers - a mistaken decision will * result in this test being false, so we go in and take the locks. */ if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) { JBUFFER_TRACE(jh, "fastpath"); if (unlikely(jh->b_transaction != journal->j_running_transaction)) { printk(KERN_ERR "JBD2: %s: " "jh->b_transaction (%llu, %p, %u) != " "journal->j_running_transaction (%p, %u)\n", journal->j_devname, (unsigned long long) bh->b_blocknr, jh->b_transaction, jh->b_transaction ? jh->b_transaction->t_tid : 0, journal->j_running_transaction, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); ret = -EINVAL; } goto out_unlock_bh; } set_buffer_jbddirty(bh); /* * Metadata already on the current transaction list doesn't * need to be filed. Metadata on another transaction's list must * be committing, and will be refiled once the commit completes: * leave it alone for now. */ if (jh->b_transaction != transaction) { JBUFFER_TRACE(jh, "already on other transaction"); if (unlikely(((jh->b_transaction != journal->j_committing_transaction)) || (jh->b_next_transaction != transaction))) { printk(KERN_ERR "jbd2_journal_dirty_metadata: %s: " "bad jh for block %llu: " "transaction (%p, %u), " "jh->b_transaction (%p, %u), " "jh->b_next_transaction (%p, %u), jlist %u\n", journal->j_devname, (unsigned long long) bh->b_blocknr, transaction, transaction->t_tid, jh->b_transaction, jh->b_transaction ? jh->b_transaction->t_tid : 0, jh->b_next_transaction, jh->b_next_transaction ? jh->b_next_transaction->t_tid : 0, jh->b_jlist); WARN_ON(1); ret = -EINVAL; } /* And this case is illegal: we can't reuse another * transaction's data buffer, ever. */ goto out_unlock_bh; } /* That test should have eliminated the following case: */ J_ASSERT_JH(jh, jh->b_frozen_data == NULL); JBUFFER_TRACE(jh, "file as BJ_Metadata"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Metadata); spin_unlock(&journal->j_list_lock); out_unlock_bh: spin_unlock(&jh->b_state_lock); out: JBUFFER_TRACE(jh, "exit"); return ret; } /** * jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * * We can only do the bforget if there are no commits pending against the * buffer. If the buffer is dirty in the current running transaction we * can safely unlink it. * * bh may not be a journalled buffer at all - it may be a non-JBD * buffer which came off the hashtable. Check for this. * * Decrements bh->b_count by one. * * Allow this call even if the handle has aborted --- it may be part of * the caller's cleanup after an abort. */ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal; struct journal_head *jh; int drop_reserve = 0; int err = 0; int was_modified = 0; if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; BUFFER_TRACE(bh, "entry"); jh = jbd2_journal_grab_journal_head(bh); if (!jh) { __bforget(bh); return 0; } spin_lock(&jh->b_state_lock); /* Critical error: attempting to delete a bitmap buffer, maybe? * Don't do any jbd operations, and return an error. */ if (!J_EXPECT_JH(jh, !jh->b_committed_data, "inconsistent data on disk")) { err = -EIO; goto drop; } /* keep track of whether or not this transaction modified us */ was_modified = jh->b_modified; /* * The buffer's going from the transaction, we must drop * all references -bzzz */ jh->b_modified = 0; if (jh->b_transaction == transaction) { J_ASSERT_JH(jh, !jh->b_frozen_data); /* If we are forgetting a buffer which is already part * of this transaction, then we can just drop it from * the transaction immediately. */ clear_buffer_dirty(bh); clear_buffer_jbddirty(bh); JBUFFER_TRACE(jh, "belongs to current transaction: unfile"); /* * we only want to drop a reference if this transaction * modified the buffer */ if (was_modified) drop_reserve = 1; /* * We are no longer going to journal this buffer. * However, the commit of this transaction is still * important to the buffer: the delete that we are now * processing might obsolete an old log entry, so by * committing, we can satisfy the buffer's checkpoint. * * So, if we have a checkpoint on the buffer, we should * now refile the buffer on our BJ_Forget list so that * we know to remove the checkpoint after we commit. */ spin_lock(&journal->j_list_lock); if (jh->b_cp_transaction) { __jbd2_journal_temp_unlink_buffer(jh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); jbd2_journal_put_journal_head(jh); } spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction) { J_ASSERT_JH(jh, (jh->b_transaction == journal->j_committing_transaction)); /* However, if the buffer is still owned by a prior * (committing) transaction, we can't drop it yet... */ JBUFFER_TRACE(jh, "belongs to older transaction"); /* ... but we CAN drop it from the new transaction through * marking the buffer as freed and set j_next_transaction to * the new transaction, so that not only the commit code * knows it should clear dirty bits when it is done with the * buffer, but also the buffer can be checkpointed only * after the new transaction commits. */ set_buffer_freed(bh); if (!jh->b_next_transaction) { spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); } else { J_ASSERT(jh->b_next_transaction == transaction); /* * only drop a reference if this transaction modified * the buffer */ if (was_modified) drop_reserve = 1; } } else { /* * Finally, if the buffer is not belongs to any * transaction, we can just drop it now if it has no * checkpoint. */ spin_lock(&journal->j_list_lock); if (!jh->b_cp_transaction) { JBUFFER_TRACE(jh, "belongs to none transaction"); spin_unlock(&journal->j_list_lock); goto drop; } /* * Otherwise, if the buffer has been written to disk, * it is safe to remove the checkpoint and drop it. */ if (!buffer_dirty(bh)) { __jbd2_journal_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); goto drop; } /* * The buffer is still not written to disk, we should * attach this buffer to current transaction so that the * buffer can be checkpointed only after the current * transaction commits. */ clear_buffer_dirty(bh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); spin_unlock(&journal->j_list_lock); } drop: __brelse(bh); spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); if (drop_reserve) { /* no need to reserve log space for this block -bzzz */ handle->h_total_credits++; } return err; } /** * jbd2_journal_stop() - complete a transaction * @handle: transaction to complete. * * All done for a particular handle. * * There is not much action needed here. We just return any remaining * buffer credits to the transaction and remove the handle. The only * complication is that we need to start a commit operation if the * filesystem is marked for synchronous update. * * jbd2_journal_stop itself will not usually return an error, but it may * do so in unusual circumstances. In particular, expect it to * return -EIO if a jbd2_journal_abort has been executed since the * transaction began. */ int jbd2_journal_stop(handle_t *handle) { transaction_t *transaction = handle->h_transaction; journal_t *journal; int err = 0, wait_for_commit = 0; tid_t tid; pid_t pid; if (--handle->h_ref > 0) { jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, handle->h_ref); if (is_handle_aborted(handle)) return -EIO; return 0; } if (!transaction) { /* * Handle is already detached from the transaction so there is * nothing to do other than free the handle. */ memalloc_nofs_restore(handle->saved_alloc_context); goto free_and_exit; } journal = transaction->t_journal; tid = transaction->t_tid; if (is_handle_aborted(handle)) err = -EIO; jbd_debug(4, "Handle %p going down\n", handle); trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev, tid, handle->h_type, handle->h_line_no, jiffies - handle->h_start_jiffies, handle->h_sync, handle->h_requested_credits, (handle->h_requested_credits - handle->h_total_credits)); /* * Implement synchronous transaction batching. If the handle * was synchronous, don't force a commit immediately. Let's * yield and let another thread piggyback onto this * transaction. Keep doing that while new threads continue to * arrive. It doesn't cost much - we're about to run a commit * and sleep on IO anyway. Speeds up many-threaded, many-dir * operations by 30x or more... * * We try and optimize the sleep time against what the * underlying disk can do, instead of having a static sleep * time. This is useful for the case where our storage is so * fast that it is more optimal to go ahead and force a flush * and wait for the transaction to be committed than it is to * wait for an arbitrary amount of time for new writers to * join the transaction. We achieve this by measuring how * long it takes to commit a transaction, and compare it with * how long this transaction has been running, and if run time * < commit time then we sleep for the delta and commit. This * greatly helps super fast disks that would see slowdowns as * more threads started doing fsyncs. * * But don't do this if this process was the most recent one * to perform a synchronous write. We do this to detect the * case where a single process is doing a stream of sync * writes. No point in waiting for joiners in that case. * * Setting max_batch_time to 0 disables this completely. */ pid = current->pid; if (handle->h_sync && journal->j_last_sync_writer != pid && journal->j_max_batch_time) { u64 commit_time, trans_time; journal->j_last_sync_writer = pid; read_lock(&journal->j_state_lock); commit_time = journal->j_average_commit_time; read_unlock(&journal->j_state_lock); trans_time = ktime_to_ns(ktime_sub(ktime_get(), transaction->t_start_time)); commit_time = max_t(u64, commit_time, 1000*journal->j_min_batch_time); commit_time = min_t(u64, commit_time, 1000*journal->j_max_batch_time); if (trans_time < commit_time) { ktime_t expires = ktime_add_ns(ktime_get(), commit_time); set_current_state(TASK_UNINTERRUPTIBLE); schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); } } if (handle->h_sync) transaction->t_synchronous_commit = 1; /* * If the handle is marked SYNC, we need to set another commit * going! We also want to force a commit if the transaction is too * old now. */ if (handle->h_sync || time_after_eq(jiffies, transaction->t_expires)) { /* Do this even for aborted journals: an abort still * completes the commit thread, it just doesn't write * anything to disk. */ jbd_debug(2, "transaction too old, requesting commit for " "handle %p\n", handle); /* This is non-blocking */ jbd2_log_start_commit(journal, tid); /* * Special case: JBD2_SYNC synchronous updates require us * to wait for the commit to complete. */ if (handle->h_sync && !(current->flags & PF_MEMALLOC)) wait_for_commit = 1; } /* * Once stop_this_handle() drops t_updates, the transaction could start * committing on us and eventually disappear. So we must not * dereference transaction pointer again after calling * stop_this_handle(). */ stop_this_handle(handle); if (wait_for_commit) err = jbd2_log_wait_commit(journal, tid); free_and_exit: if (handle->h_rsv_handle) jbd2_free_handle(handle->h_rsv_handle); jbd2_free_handle(handle); return err; } /* * * List management code snippets: various functions for manipulating the * transaction buffer lists. * */ /* * Append a buffer to a transaction list, given the transaction's list head * pointer. * * j_list_lock is held. * * jh->b_state_lock is held. */ static inline void __blist_add_buffer(struct journal_head **list, struct journal_head *jh) { if (!*list) { jh->b_tnext = jh->b_tprev = jh; *list = jh; } else { /* Insert at the tail of the list to preserve order */ struct journal_head *first = *list, *last = first->b_tprev; jh->b_tprev = last; jh->b_tnext = first; last->b_tnext = first->b_tprev = jh; } } /* * Remove a buffer from a transaction list, given the transaction's list * head pointer. * * Called with j_list_lock held, and the journal may not be locked. * * jh->b_state_lock is held. */ static inline void __blist_del_buffer(struct journal_head **list, struct journal_head *jh) { if (*list == jh) { *list = jh->b_tnext; if (*list == jh) *list = NULL; } jh->b_tprev->b_tnext = jh->b_tnext; jh->b_tnext->b_tprev = jh->b_tprev; } /* * Remove a buffer from the appropriate transaction list. * * Note that this function can *change* the value of * bh->b_transaction->t_buffers, t_forget, t_shadow_list, t_log_list or * t_reserved_list. If the caller is holding onto a copy of one of these * pointers, it could go bad. Generally the caller needs to re-read the * pointer from the transaction_t. * * Called under j_list_lock. */ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) { struct journal_head **list = NULL; transaction_t *transaction; struct buffer_head *bh = jh2bh(jh); lockdep_assert_held(&jh->b_state_lock); transaction = jh->b_transaction; if (transaction) assert_spin_locked(&transaction->t_journal->j_list_lock); J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); if (jh->b_jlist != BJ_None) J_ASSERT_JH(jh, transaction != NULL); switch (jh->b_jlist) { case BJ_None: return; case BJ_Metadata: transaction->t_nr_buffers--; J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0); list = &transaction->t_buffers; break; case BJ_Forget: list = &transaction->t_forget; break; case BJ_Shadow: list = &transaction->t_shadow_list; break; case BJ_Reserved: list = &transaction->t_reserved_list; break; } __blist_del_buffer(list, jh); jh->b_jlist = BJ_None; if (transaction && is_journal_aborted(transaction->t_journal)) clear_buffer_jbddirty(bh); else if (test_clear_buffer_jbddirty(bh)) mark_buffer_dirty(bh); /* Expose it to the VM */ } /* * Remove buffer from all transactions. The caller is responsible for dropping * the jh reference that belonged to the transaction. * * Called with bh_state lock and j_list_lock */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { J_ASSERT_JH(jh, jh->b_transaction != NULL); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; } void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); /* Get reference so that buffer cannot be freed before we unlock it */ get_bh(bh); spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); __jbd2_journal_unfile_buffer(jh); spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); __brelse(bh); } /* * Called from jbd2_journal_try_to_free_buffers(). * * Called under jh->b_state_lock */ static void __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) { struct journal_head *jh; jh = bh2jh(bh); if (buffer_locked(bh) || buffer_dirty(bh)) goto out; if (jh->b_next_transaction != NULL || jh->b_transaction != NULL) goto out; spin_lock(&journal->j_list_lock); if (jh->b_cp_transaction != NULL) { /* written-back checkpointed metadata buffer */ JBUFFER_TRACE(jh, "remove from checkpoint list"); __jbd2_journal_remove_checkpoint(jh); } spin_unlock(&journal->j_list_lock); out: return; } /** * jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free * * For all the buffers on this page, * if they are fully written out ordered data, move them onto BUF_CLEAN * so try_to_free_buffers() can reap them. * * This function returns non-zero if we wish try_to_free_buffers() * to be called. We do this if the page is releasable by try_to_free_buffers(). * We also do it if the page has locked or dirty buffers and the caller wants * us to perform sync or async writeout. * * This complicates JBD locking somewhat. We aren't protected by the * BKL here. We wish to remove the buffer from its committing or * running transaction's ->t_datalist via __jbd2_journal_unfile_buffer. * * This may *change* the value of transaction_t->t_datalist, so anyone * who looks at t_datalist needs to lock against this function. * * Even worse, someone may be doing a jbd2_journal_dirty_data on this * buffer. So we need to lock against that. jbd2_journal_dirty_data() * will come out of the lock with the buffer dirty, which makes it * ineligible for release here. * * Who else is affected by this? hmm... Really the only contender * is do_get_write_access() - it could be looking at the buffer while * journal_try_to_free_buffer() is changing its state. But that * cannot happen because we never reallocate freed data as metadata * while the data is part of a transaction. Yes? * * Return 0 on failure, 1 on success */ int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) { struct buffer_head *head; struct buffer_head *bh; bool has_write_io_error = false; int ret = 0; J_ASSERT(PageLocked(page)); head = page_buffers(page); bh = head; do { struct journal_head *jh; /* * We take our own ref against the journal_head here to avoid * having to add tons of locking around each instance of * jbd2_journal_put_journal_head(). */ jh = jbd2_journal_grab_journal_head(bh); if (!jh) continue; spin_lock(&jh->b_state_lock); __journal_try_to_free_buffer(journal, bh); spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); if (buffer_jbd(bh)) goto busy; /* * If we free a metadata buffer which has been failed to * write out, the jbd2 checkpoint procedure will not detect * this failure and may lead to filesystem inconsistency * after cleanup journal tail. */ if (buffer_write_io_error(bh)) { pr_err("JBD2: Error while async write back metadata bh %llu.", (unsigned long long)bh->b_blocknr); has_write_io_error = true; } } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(page); busy: if (has_write_io_error) jbd2_journal_abort(journal, -EIO); return ret; } /* * This buffer is no longer needed. If it is on an older transaction's * checkpoint list we need to record it on this transaction's forget list * to pin this buffer (and hence its checkpointing transaction) down until * this transaction commits. If the buffer isn't on a checkpoint list, we * release it. * Returns non-zero if JBD no longer has an interest in the buffer. * * Called under j_list_lock. * * Called under jh->b_state_lock. */ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) { int may_free = 1; struct buffer_head *bh = jh2bh(jh); if (jh->b_cp_transaction) { JBUFFER_TRACE(jh, "on running+cp transaction"); __jbd2_journal_temp_unlink_buffer(jh); /* * We don't want to write the buffer anymore, clear the * bit so that we don't confuse checks in * __journal_file_buffer */ clear_buffer_dirty(bh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); may_free = 0; } else { JBUFFER_TRACE(jh, "on running transaction"); __jbd2_journal_unfile_buffer(jh); jbd2_journal_put_journal_head(jh); } return may_free; } /* * jbd2_journal_invalidatepage * * This code is tricky. It has a number of cases to deal with. * * There are two invariants which this code relies on: * * i_size must be updated on disk before we start calling invalidatepage on the * data. * * This is done in ext3 by defining an ext3_setattr method which * updates i_size before truncate gets going. By maintaining this * invariant, we can be sure that it is safe to throw away any buffers * attached to the current transaction: once the transaction commits, * we know that the data will not be needed. * * Note however that we can *not* throw away data belonging to the * previous, committing transaction! * * Any disk blocks which *are* part of the previous, committing * transaction (and which therefore cannot be discarded immediately) are * not going to be reused in the new running transaction * * The bitmap committed_data images guarantee this: any block which is * allocated in one transaction and removed in the next will be marked * as in-use in the committed_data bitmap, so cannot be reused until * the next transaction to delete the block commits. This means that * leaving committing buffers dirty is quite safe: the disk blocks * cannot be reallocated to a different file and so buffer aliasing is * not possible. * * * The above applies mainly to ordered data mode. In writeback mode we * don't make guarantees about the order in which data hits disk --- in * particular we don't guarantee that new dirty data is flushed before * transaction commit --- so it is always safe just to discard data * immediately in that mode. --sct */ /* * The journal_unmap_buffer helper function returns zero if the buffer * concerned remains pinned as an anonymous buffer belonging to an older * transaction. * * We're outside-transaction here. Either or both of j_running_transaction * and j_committing_transaction may be NULL. */ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, int partial_page) { transaction_t *transaction; struct journal_head *jh; int may_free = 1; BUFFER_TRACE(bh, "entry"); /* * It is safe to proceed here without the j_list_lock because the * buffers cannot be stolen by try_to_free_buffers as long as we are * holding the page lock. --sct */ jh = jbd2_journal_grab_journal_head(bh); if (!jh) goto zap_buffer_unlocked; /* OK, we have data buffer in journaled mode */ write_lock(&journal->j_state_lock); spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); /* * We cannot remove the buffer from checkpoint lists until the * transaction adding inode to orphan list (let's call it T) * is committed. Otherwise if the transaction changing the * buffer would be cleaned from the journal before T is * committed, a crash will cause that the correct contents of * the buffer will be lost. On the other hand we have to * clear the buffer dirty bit at latest at the moment when the * transaction marking the buffer as freed in the filesystem * structures is committed because from that moment on the * block can be reallocated and used by a different page. * Since the block hasn't been freed yet but the inode has * already been added to orphan list, it is safe for us to add * the buffer to BJ_Forget list of the newest transaction. * * Also we have to clear buffer_mapped flag of a truncated buffer * because the buffer_head may be attached to the page straddling * i_size (can happen only when blocksize < pagesize) and thus the * buffer_head can be reused when the file is extended again. So we end * up keeping around invalidated buffers attached to transactions' * BJ_Forget list just to stop checkpointing code from cleaning up * the transaction this buffer was modified in. */ transaction = jh->b_transaction; if (transaction == NULL) { /* First case: not on any transaction. If it * has no checkpoint link, then we can zap it: * it's a writeback-mode buffer so we don't care * if it hits disk safely. */ if (!jh->b_cp_transaction) { JBUFFER_TRACE(jh, "not on any transaction: zap"); goto zap_buffer; } if (!buffer_dirty(bh)) { /* bdflush has written it. We can drop it now */ __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } /* OK, it must be in the journal but still not * written fully to disk: it's metadata or * journaled data... */ if (journal->j_running_transaction) { /* ... and once the current transaction has * committed, the buffer won't be needed any * longer. */ JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget"); may_free = __dispose_buffer(jh, journal->j_running_transaction); goto zap_buffer; } else { /* There is no currently-running transaction. So the * orphan record which we wrote for this file must have * passed into commit. We must attach this buffer to * the committing transaction, if it exists. */ if (journal->j_committing_transaction) { JBUFFER_TRACE(jh, "give to committing trans"); may_free = __dispose_buffer(jh, journal->j_committing_transaction); goto zap_buffer; } else { /* The orphan record's transaction has * committed. We can cleanse this buffer */ clear_buffer_jbddirty(bh); __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } } } else if (transaction == journal->j_committing_transaction) { JBUFFER_TRACE(jh, "on committing transaction"); /* * The buffer is committing, we simply cannot touch * it. If the page is straddling i_size we have to wait * for commit and try again. */ if (partial_page) { spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); return -EBUSY; } /* * OK, buffer won't be reachable after truncate. We just clear * b_modified to not confuse transaction credit accounting, and * set j_next_transaction to the running transaction (if there * is one) and mark buffer as freed so that commit code knows * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; jh->b_modified = 0; spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); return 0; } else { /* Good, the buffer belongs to the running transaction. * We are writing our own transaction's data, not any * previous one's, so it is safe to throw it away * (remember that we expect the filesystem to have set * i_size already for this truncate so recovery will not * expose the disk blocks we are discarding here.) */ J_ASSERT_JH(jh, transaction == journal->j_running_transaction); JBUFFER_TRACE(jh, "on running transaction"); may_free = __dispose_buffer(jh, transaction); } zap_buffer: /* * This is tricky. Although the buffer is truncated, it may be reused * if blocksize < pagesize and it is attached to the page straddling * EOF. Since the buffer might have been added to BJ_Forget list of the * running transaction, journal_get_write_access() won't clear * b_modified and credit accounting gets confused. So clear b_modified * here. */ jh->b_modified = 0; spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); zap_buffer_unlocked: clear_buffer_dirty(bh); J_ASSERT_BH(bh, !buffer_jbddirty(bh)); clear_buffer_mapped(bh); clear_buffer_req(bh); clear_buffer_new(bh); clear_buffer_delay(bh); clear_buffer_unwritten(bh); bh->b_bdev = NULL; return may_free; } /** * jbd2_journal_invalidatepage() * @journal: journal to use for flush... * @page: page to flush * @offset: start of the range to invalidate * @length: length of the range to invalidate * * Reap page buffers containing data after in the specified range in page. * Can return -EBUSY if buffers are part of the committing transaction and * the page is straddling i_size. Caller then has to wait for current commit * and try again. */ int jbd2_journal_invalidatepage(journal_t *journal, struct page *page, unsigned int offset, unsigned int length) { struct buffer_head *head, *bh, *next; unsigned int stop = offset + length; unsigned int curr_off = 0; int partial_page = (offset || length < PAGE_SIZE); int may_free = 1; int ret = 0; if (!PageLocked(page)) BUG(); if (!page_has_buffers(page)) return 0; BUG_ON(stop > PAGE_SIZE || stop < length); /* We will potentially be playing with lists other than just the * data lists (especially for journaled data mode), so be * cautious in our locking. */ head = bh = page_buffers(page); do { unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; if (next_off > stop) return 0; if (offset <= curr_off) { /* This block is wholly outside the truncation point */ lock_buffer(bh); ret = journal_unmap_buffer(journal, bh, partial_page); unlock_buffer(bh); if (ret < 0) return ret; may_free &= ret; } curr_off = next_off; bh = next; } while (bh != head); if (!partial_page) { if (may_free && try_to_free_buffers(page)) J_ASSERT(!page_has_buffers(page)); } return 0; } /* * File a buffer on the given transaction list. */ void __jbd2_journal_file_buffer(struct journal_head *jh, transaction_t *transaction, int jlist) { struct journal_head **list = NULL; int was_dirty = 0; struct buffer_head *bh = jh2bh(jh); lockdep_assert_held(&jh->b_state_lock); assert_spin_locked(&transaction->t_journal->j_list_lock); J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_transaction == NULL); if (jh->b_transaction && jh->b_jlist == jlist) return; if (jlist == BJ_Metadata || jlist == BJ_Reserved || jlist == BJ_Shadow || jlist == BJ_Forget) { /* * For metadata buffers, we track dirty bit in buffer_jbddirty * instead of buffer_dirty. We should not see a dirty bit set * here because we clear it in do_get_write_access but e.g. * tune2fs can modify the sb and set the dirty bit at any time * so we try to gracefully handle that. */ if (buffer_dirty(bh)) warn_dirty_buffer(bh); if (test_clear_buffer_dirty(bh) || test_clear_buffer_jbddirty(bh)) was_dirty = 1; } if (jh->b_transaction) __jbd2_journal_temp_unlink_buffer(jh); else jbd2_journal_grab_journal_head(bh); jh->b_transaction = transaction; switch (jlist) { case BJ_None: J_ASSERT_JH(jh, !jh->b_committed_data); J_ASSERT_JH(jh, !jh->b_frozen_data); return; case BJ_Metadata: transaction->t_nr_buffers++; list = &transaction->t_buffers; break; case BJ_Forget: list = &transaction->t_forget; break; case BJ_Shadow: list = &transaction->t_shadow_list; break; case BJ_Reserved: list = &transaction->t_reserved_list; break; } __blist_add_buffer(list, jh); jh->b_jlist = jlist; if (was_dirty) set_buffer_jbddirty(bh); } void jbd2_journal_file_buffer(struct journal_head *jh, transaction_t *transaction, int jlist) { spin_lock(&jh->b_state_lock); spin_lock(&transaction->t_journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, jlist); spin_unlock(&transaction->t_journal->j_list_lock); spin_unlock(&jh->b_state_lock); } /* * Remove a buffer from its current buffer list in preparation for * dropping it from its current transaction entirely. If the buffer has * already started to be used by a subsequent transaction, refile the * buffer on that transaction's metadata list. * * Called under j_list_lock * Called under jh->b_state_lock * * When this function returns true, there's no next transaction to refile to * and the caller has to drop jh reference through * jbd2_journal_put_journal_head(). */ bool __jbd2_journal_refile_buffer(struct journal_head *jh) { int was_dirty, jlist; struct buffer_head *bh = jh2bh(jh); lockdep_assert_held(&jh->b_state_lock); if (jh->b_transaction) assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock); /* If the buffer is now unused, just drop it. */ if (jh->b_next_transaction == NULL) { __jbd2_journal_unfile_buffer(jh); return true; } /* * It has been modified by a later transaction: add it to the new * transaction's metadata list. */ was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); /* * b_transaction must be set, otherwise the new b_transaction won't * be holding jh reference */ J_ASSERT_JH(jh, jh->b_transaction != NULL); /* * We set b_transaction here because b_next_transaction will inherit * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) jlist = BJ_Metadata; else jlist = BJ_Reserved; __jbd2_journal_file_buffer(jh, jh->b_transaction, jlist); J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING); if (was_dirty) set_buffer_jbddirty(bh); return false; } /* * __jbd2_journal_refile_buffer() with necessary locking added. We take our * bh reference so that we can safely unlock bh. * * The jh and bh may be freed by this call. */ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) { bool drop; spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); drop = __jbd2_journal_refile_buffer(jh); spin_unlock(&jh->b_state_lock); spin_unlock(&journal->j_list_lock); if (drop) jbd2_journal_put_journal_head(jh); } /* * File inode in the inode list of the handle's transaction */ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, unsigned long flags, loff_t start_byte, loff_t end_byte) { transaction_t *transaction = handle->h_transaction; journal_t *journal; if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); spin_lock(&journal->j_list_lock); jinode->i_flags |= flags; if (jinode->i_dirty_end) { jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte); jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte); } else { jinode->i_dirty_start = start_byte; jinode->i_dirty_end = end_byte; } /* Is inode already attached where we need it? */ if (jinode->i_transaction == transaction || jinode->i_next_transaction == transaction) goto done; /* * We only ever set this variable to 1 so the test is safe. Since * t_need_data_flush is likely to be set, we do the test to save some * cacheline bouncing */ if (!transaction->t_need_data_flush) transaction->t_need_data_flush = 1; /* On some different transaction's list - should be * the committing one */ if (jinode->i_transaction) { J_ASSERT(jinode->i_next_transaction == NULL); J_ASSERT(jinode->i_transaction == journal->j_committing_transaction); jinode->i_next_transaction = transaction; goto done; } /* Not on any transaction list... */ J_ASSERT(!jinode->i_next_transaction); jinode->i_transaction = transaction; list_add(&jinode->i_list, &transaction->t_inode_list); done: spin_unlock(&journal->j_list_lock); return 0; } int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *jinode, loff_t start_byte, loff_t length) { return jbd2_journal_file_inode(handle, jinode, JI_WRITE_DATA | JI_WAIT_DATA, start_byte, start_byte + length - 1); } int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode, loff_t start_byte, loff_t length) { return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, start_byte, start_byte + length - 1); } /* * File truncate and transaction commit interact with each other in a * non-trivial way. If a transaction writing data block A is * committing, we cannot discard the data by truncate until we have * written them. Otherwise if we crashed after the transaction with * write has committed but before the transaction with truncate has * committed, we could see stale data in block A. This function is a * helper to solve this problem. It starts writeout of the truncated * part in case it is in the committing transaction. * * Filesystem code must call this function when inode is journaled in * ordered mode before truncation happens and after the inode has been * placed on orphan list with the new inode size. The second condition * avoids the race that someone writes new data and we start * committing the transaction after this function has been called but * before a transaction for truncate is started (and furthermore it * allows us to optimize the case where the addition to orphan list * happens in the same transaction as write --- we don't have to write * any data in such case). */ int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *jinode, loff_t new_size) { transaction_t *inode_trans, *commit_trans; int ret = 0; /* This is a quick check to avoid locking if not necessary */ if (!jinode->i_transaction) goto out; /* Locks are here just to force reading of recent values, it is * enough that the transaction was not committing before we started * a transaction adding the inode to orphan list */ read_lock(&journal->j_state_lock); commit_trans = journal->j_committing_transaction; read_unlock(&journal->j_state_lock); spin_lock(&journal->j_list_lock); inode_trans = jinode->i_transaction; spin_unlock(&journal->j_list_lock); if (inode_trans == commit_trans) { ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping, new_size, LLONG_MAX); if (ret) jbd2_journal_abort(journal, ret); } out: return ret; }
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set. */ unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next); /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set in both. */ int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next_and); /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Returns >= nr_cpu_ids if no cpus set. */ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } EXPORT_SYMBOL(cpumask_any_but); /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Returns >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>) * Returns TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(zalloc_cpumask_var_node); /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. */ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } EXPORT_SYMBOL(alloc_cpumask_var); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } EXPORT_SYMBOL(zalloc_cpumask_var); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); if (!*mask) panic("%s: Failed to allocate %u bytes\n", __func__, cpumask_size()); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free_early(__pa(mask), cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number * @node: local numa_node * * This function selects an online CPU according to a numa aware policy; * local cpus are returned first, followed by non-local ones, then it * wraps around. * * It's not very efficient, but useful for setup. */ unsigned int cpumask_local_spread(unsigned int i, int node) { int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; } else { /* NUMA first. */ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) if (i-- == 0) return cpu; for_each_cpu(cpu, cpu_online_mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; if (i-- == 0) return cpu; } } BUG(); } EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** * Returns an arbitrary cpu within srcp1 & srcp2. * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * * Returns >= nr_cpu_ids if the intersection is empty. */ int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = cpumask_next_and(prev, src1p, src2p); if (next >= nr_cpu_ids) next = cpumask_first_and(src1p, src2p); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_and_distribute);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_INTERNAL_H #define _ASM_X86_FPU_INTERNAL_H #include <linux/compat.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <asm/user.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #include <asm/cpufeature.h> #include <asm/trace/fpu.h> /* * High level FPU state handling functions: */ extern void fpu__prepare_read(struct fpu *fpu); extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); extern void fpu__drop(struct fpu *fpu); extern int fpu__copy(struct task_struct *dst, struct task_struct *src); extern void fpu__clear_user_states(struct fpu *fpu); extern void fpu__clear_all(struct fpu *fpu); extern int fpu__exception_code(struct fpu *fpu, int trap_nr); /* * Boot time FPU initialization functions: */ extern void fpu__init_cpu(void); extern void fpu__init_system_xstate(void); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system(struct cpuinfo_x86 *c); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: */ #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ (void)(x); 0; }) #endif /* * FPU related CPU feature flag helper routines: */ static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { return static_cpu_has(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return static_cpu_has(X86_FEATURE_FXSR); } /* * fpstate handling functions: */ extern union fpregs_state init_fpstate; extern void fpstate_init(union fpregs_state *state); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif static inline void fpstate_init_xstate(struct xregs_state *xsave) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; } static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; fx->mxcsr = MXCSR_DEFAULT; } extern void fpstate_sanitize_xstate(struct fpu *fpu); /* Returns 0 or the negated trap number, which results in -EFAULT for #PF */ #define user_insn(insn, output, input...) \ ({ \ int err; \ \ might_fault(); \ \ asm volatile(ASM_STAC "\n" \ "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: negl %%eax\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn_err(insn, output, input...) \ ({ \ int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: movl $-1,%[err]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE(1b, 3b) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); } static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_kernel_to_fregs(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fregs_err(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_fxregs_to_kernel(struct fpu *fpu) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); } static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); } /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" /* * After this @err contains 0 on success or the negated trap number when * the operation raises an exception. For faults this results in -EFAULT. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n\t" \ ".pushsection .fixup,\"ax\"\n\t" \ "3: negl %%eax\n\t" \ "jmp 2b\n\t" \ ".popsection\n\t" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact * format and supervisor states in addition to modified optimization in * XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * We use XSAVE as a fallback. * * The 661 label is defined in the ALTERNATIVE* macros as the address of the * original instruction which gets replaced. We need to use it here as the * address of the instruction where we might get an exception at. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile(ALTERNATIVE_2(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ ".pushsection .fixup,\"ax\"\n" \ "4: movl $-2, %[err]\n" \ "jmp 3b\n" \ ".popsection\n" \ _ASM_EXTABLE(661b, 4b) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) { u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON(system_state != SYSTEM_BOOTING); if (boot_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * Save processor xstate to xsave area. */ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) { u64 mask = xfeatures_mask_all; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. */ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(xstate, lmask, hmask); } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for * backward compatibility for old applications which don't understand * compacted format of xsave area. */ static inline int copy_xregs_to_user(struct xregs_state __user *buf) { u64 mask = xfeatures_mask_user(); u32 lmask = mask; u32 hmask = mask >> 32; int err; /* * Clear the xsave header first, so that reserved fields are * initialized to zero. */ err = __clear_user(&buf->header, sizeof(buf->header)); if (unlikely(err)) return -EFAULT; stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); return err; } /* * Restore xstate from user space xsave area. */ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; int err; if (static_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } extern int copy_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); else copy_kernel_to_fregs(&fpstate->fsave); } } static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) { /* * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is * pending. Clear the x87 state here by setting it to fixed values. * "m" is a random variable that should be in L1. */ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" "fildl %P[addr]" /* set F?P to defined value */ : : [addr] "m" (fpstate)); } __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); /* * FPU context switch related helper methods: */ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Either one of these invalidation functions is enough. Invalidate * a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* * These generally need preemption protection to work, * do try to avoid using these on their own: */ static inline void fpregs_deactivate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* * Internal helper, do not use directly. Use switch_fpu_return() instead. */ static inline void __fpregs_load_activate(void) { struct fpu *fpu = &current->thread.fpu; int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return; if (!fpregs_state_valid(fpu, cpu)) { copy_kernel_to_fpregs(&fpu->state); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } /* * FPU state switching for scheduling. * * This is a two-stage process: * * - switch_fpu_prepare() saves the old state. * This is done within the context of the old process. * * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state * will get loaded on return to userspace, or when the kernel needs it. * * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers * are saved in the current thread's FPU register state. * * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not * hold current()'s FPU registers. It is required to load the * registers before returning to userland or using the content * otherwise. * * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ trace_x86_fpu_regs_deactivated(old_fpu); } } /* * Misc helper functions: */ /* * Load PKRU from the FPU context if available. Delay loading of the * complete FPU state until the return to userland. */ static inline void switch_fpu_finish(struct fpu *new_fpu) { u32 pkru_val = init_pkru_value; struct pkru_state *pk; if (!static_cpu_has(X86_FEATURE_FPU)) return; set_thread_flag(TIF_NEED_FPU_LOAD); if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * PKRU state is switched eagerly because it needs to be valid before we * return to userland e.g. for a copy_to_user() operation. */ if (!(current->flags & PF_KTHREAD)) { /* * If the PKRU bit in xsave.header.xfeatures is not set, * then the PKRU component was in init state, which means * XRSTOR will set PKRU to 0. If the bit is not set then * get_xsave_addr() will return NULL because the PKRU value * in memory is not valid. This means pkru_val has to be * set to 0 and not to init_pkru_value. */ pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU); pkru_val = pk ? pk->pkru : 0; } __write_pkru(pkru_val); } #endif /* _ASM_X86_FPU_INTERNAL_H */
1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_mutex * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->lock_page (access_process_vm) * * ->i_mutex (generic_perform_write) * ->mmap_lock (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_adjust) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->pgdat->lru_lock (follow_page->mark_page_accessed) * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * * ->i_mmap_rwsem * ->tasklist_lock (memory_failure, collect_procs_ao) */ static void page_cache_delete(struct address_space *mapping, struct page *page, void *shadow) { XA_STATE(xas, &mapping->i_pages, page->index); unsigned int nr = 1; mapping_set_update(&xas, mapping); /* hugetlb pages are represented by a single entry in the xarray */ if (!PageHuge(page)) { xas_set_order(&xas, page->index, compound_order(page)); nr = compound_nr(page); } VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(nr != 1 && shadow, page); xas_store(&xas, shadow); xas_init_marks(&xas); page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ if (shadow) { mapping->nrexceptional += nr; /* * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing * with reclaim does not see both counters 0 at the * same time and miss a shadow entry. */ smp_wmb(); } mapping->nrpages -= nr; } static void unaccount_page_cache_page(struct address_space *mapping, struct page *page) { int nr; /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave * stale data around in the cleancache once our page is gone */ if (PageUptodate(page) && PageMappedToDisk(page)) cleancache_put_page(page); else cleancache_invalidate_page(mapping, page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_mapped(page), page); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { int mapcount; pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); dump_page(page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); mapcount = page_mapcount(page); if (mapping_exiting(mapping) && page_count(page) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped, * and we'd prefer not to leak it: if we're wrong, * some other bad page check should catch it later. */ page_mapcount_reset(page); page_ref_sub(page, mapcount); } } /* hugetlb pages do not participate in page cache accounting. */ if (PageHuge(page)) return; nr = thp_nr_pages(page); __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { __dec_node_page_state(page, NR_FILE_THPS); filemap_nr_thps_dec(mapping); } /* * At this point page must be either written or cleaned by * truncate. Dirty page here signals a bug and loss of * unwritten data. * * This fixes dirty accounting after removing the page entirely * but leaves PageDirty set: it has no effect for truncated * page and anyway will be cleared before returning page into * buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; trace_mm_filemap_delete_from_page_cache(page); unaccount_page_cache_page(mapping, page); page_cache_delete(mapping, page, shadow); } static void page_cache_free_page(struct address_space *mapping, struct page *page) { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; if (freepage) freepage(page); if (PageTransHuge(page) && !PageHuge(page)) { page_ref_sub(page, thp_nr_pages(page)); VM_BUG_ON_PAGE(page_count(page) <= 0, page); } else { put_page(page); } } /** * delete_from_page_cache - delete page from page cache * @page: the page which the kernel is trying to remove from page cache * * This must be called only on pages that have been verified to be in the page * cache and locked. It will never put the page into the free list, the caller * has a reference on the page. */ void delete_from_page_cache(struct page *page) { struct address_space *mapping = page_mapping(page); unsigned long flags; BUG_ON(!PageLocked(page)); xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); page_cache_free_page(mapping, page); } EXPORT_SYMBOL(delete_from_page_cache); /* * page_cache_delete_batch - delete several pages from page cache * @mapping: the mapping to which pages belong * @pvec: pagevec with pages to delete * * The function walks over mapping->i_pages and removes pages passed in @pvec * from the mapping. The function expects @pvec to be sorted by page index * and is optimised for it to be dense. * It tolerates holes in @pvec (mapping entries at those indices are not * modified). The function expects only THP head pages to be present in the * @pvec. * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct pagevec *pvec) { XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); int total_pages = 0; int i = 0; struct page *page; mapping_set_update(&xas, mapping); xas_for_each(&xas, page, ULONG_MAX) { if (i >= pagevec_count(pvec)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(page)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (page != pvec->pages[i]) { VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, page); continue; } WARN_ON_ONCE(!PageLocked(page)); if (page->index == xas.xa_index) page->mapping = NULL; /* Leave page->index set: truncation lookup relies on it */ /* * Move to the next page in the vector if this is a regular * page or the index is of the last sub-page of this compound * page. */ if (page->index + compound_nr(page) - 1 == xas.xa_index) i++; xas_store(&xas, NULL); total_pages++; } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec) { int i; unsigned long flags; if (!pagevec_count(pvec)) return; xa_lock_irqsave(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); unaccount_page_cache_page(mapping, pvec->pages[i]); } page_cache_delete_batch(mapping, pvec); xa_unlock_irqrestore(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) page_cache_free_page(mapping, pvec->pages[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); return ret; } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct page *page; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { page = xas_find(&xas, max); if (xas_retry(&xas, page)) continue; /* Shadow entries don't count */ if (xa_is_value(page)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return page != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct pagevec pvec; int nr_pages; if (end_byte < start_byte) return; pagevec_init(&pvec); while (index <= end) { unsigned i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, PAGECACHE_TAG_WRITEBACK); if (!nr_pages) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; wait_on_page_writeback(page); ClearPageError(page); } pagevec_release(&pvec); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { if (dax_mapping(mapping)) return mapping->nrexceptional; return mapping->nrpages; } /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) { int err2 = filemap_fdatawait_range(mapping, lstart, lend); if (!err) err = err2; } else { /* Clear any previously stored errors */ filemap_check_errors(mapping); } } else { err = filemap_check_errors(mapping); } return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_page - replace a pagecache page with a new one * @old: page to be replaced * @new: page to replace with * @gfp_mask: allocation mode * * This function replaces a page in the pagecache with a new one. On * success it acquires the pagecache reference for the new page and * drops it for the old page. Both the old and new pages must be * locked. This function does not add the new page to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. * * Return: %0 */ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); get_page(new); new->mapping = mapping; new->index = offset; mem_cgroup_migrate(old, new); xas_lock_irqsave(&xas, flags); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irqrestore(&xas, flags); if (freepage) freepage(old); put_page(old); return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); int error; bool charged = false; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); mapping_set_update(&xas, mapping); get_page(page); page->mapping = mapping; page->index = offset; if (!huge) { error = mem_cgroup_charge(page, current->mm, gfp); if (error) goto error; charged = true; } gfp &= GFP_RECLAIM_MASK; do { unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; if (order > thp_order(page)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } } if (old) { if (shadowp) *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); if (order > thp_order(page)) { xas_split(&xas, old, order); xas_reset(&xas); } } xas_store(&xas, page); if (xas_error(&xas)) goto unlock; if (old) mapping->nrexceptional--; mapping->nrpages++; /* hugetlb pages do not participate in page cache accounting */ if (!huge) __inc_lruvec_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); if (charged) mem_cgroup_uncharge(page); goto error; } trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ put_page(page); return error; } ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add * @mapping: the page's address_space * @offset: page index * @gfp_mask: page allocation mode * * This function is used to add a page to the pagecache. It must be locked. * This function does not add the page to the LRU. The caller must do that. * * Return: %0 on success, negative error code otherwise. */ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { return __add_to_page_cache_locked(page, mapping, offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { void *shadow = NULL; int ret; __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, gfp_mask, &shadow); if (unlikely(ret)) __ClearPageLocked(page); else { /* * The page might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed page. * The exception is pages getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(PageActive(page)); if (!(gfp_mask & __GFP_WRITE) && shadow) workingset_refault(page, shadow); lru_cache_add(page); } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA struct page *__page_cache_alloc(gfp_t gfp) { int n; struct page *page; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = __alloc_pages_node(n, gfp, 0); } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } return alloc_pages(gfp, 0); } EXPORT_SYMBOL(__page_cache_alloc); #endif /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *page_waitqueue(struct page *page) { return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&page_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->page->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->page->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in wait_on_page_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void wake_up_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; key.page = page; key.bit_nr = bit_nr; key.page_match = 0; bookmark.flags = 0; bookmark.private = NULL; bookmark.func = NULL; INIT_LIST_HEAD(&bookmark.entry); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); while (bookmark.flags & WQ_FLAG_BOOKMARK) { /* * Take a breather from holding the lock, * allow pages that finish wake up asynchronously * to acquire the lock and remove themselves * from wait queue */ spin_unlock_irqrestore(&q->lock, flags); cpu_relax(); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); } /* * It is possible for other pages to have collided on the waitqueue * hash, so in that case check for a page match. That prevents a long- * term waiter * * It is still possible to miss a case here, when we woke page waiters * and removed them from the waitqueue, but there are still other * page waiters. */ if (!waitqueue_active(q) || !key.page_match) { ClearPageWaiters(page); /* * It's possible to miss clearing Waiters here, when we woke * our page waiters, but the hashed waitqueue has waiters for * other pages on it. * * That's okay, it's a rare case. The next waker will clear it. */ } spin_unlock_irqrestore(&q->lock, flags); } static void wake_up_page(struct page *page, int bit) { if (!PageWaiters(page)) return; wake_up_page_bit(page, bit); } /* * A choice of three behaviors for wait_on_page_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __lock_page() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like put_and_wait_on_page_locked() on PG_locked. */ }; /* * Attempt to check (or get) the page bit, and mark us done * if successful. */ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &page->flags)) return false; } else if (test_bit(bit_nr, &page->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, enum behavior behavior) { int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; bool delayacct = false; unsigned long pflags; if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { if (!PageSwapBacked(page)) { delayacct_thrashing_start(); delayacct = true; } psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the SetPageWaiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); SetPageWaiters(page); if (!trylock_page_bit_common(page, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the page. */ if (behavior == DROP) put_page(page); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, &page->flags))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the PageWaiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { if (delayacct) delayacct_thrashing_end(); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } void wait_on_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit); int wait_on_page_bit_killable(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit_killable); static int __wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait, bool set) { struct wait_queue_head *q = page_waitqueue(page); int ret = 0; wait->page = page; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); SetPageWaiters(page); if (set) ret = !trylock_page(page); else ret = PageLocked(page); /* * If we were succesful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } static int wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait) { if (!PageLocked(page)) return 0; return __wait_on_page_locked_async(compound_head(page), wait, false); } /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. * * The caller should hold a reference on @page. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the page to * come unlocked. After this function returns, the caller should not * dereference @page. */ void put_and_wait_on_page_locked(struct page *page) { wait_queue_head_t *q; page = compound_head(page); q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); } /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue * @page: Page defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) { wait_queue_head_t *q = page_waitqueue(page); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); SetPageWaiters(page); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(add_page_wait_queue); #ifndef clear_bit_unlock_is_negative_byte /* * PG_waiters is the high bit in the same byte as PG_lock. * * On x86 (and on many other architectures), we can clear PG_lock and * test the sign bit at the same time. But if the architecture does * not support that special operation, we just do this all by hand * instead. * * The read of PG_waiters has to be after (or concurrently with) PG_locked * being cleared, but a memory barrier should be unnecessary since it is * in the same byte as PG_locked. */ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) { clear_bit_unlock(nr, mem); /* smp_mb__after_atomic(); */ return test_bit(PG_waiters, mem); } #endif /** * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in wait_on_page_locked(). * Also wakes sleepers in wait_on_page_writeback() because the wakeup * mechanism between PageLocked pages and PageWriteback pages is shared. * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. * * Note that this depends on PG_waiters being the sign bit in the byte * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to * clear the PG_locked bit and test PG_waiters at the same time fairly * portably (architectures that do LL/SC can test any bit, while x86 can * test the sign bit). */ void unlock_page(struct page *page) { BUILD_BUG_ON(PG_waiters != 7); page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) wake_up_page_bit(page, PG_locked); } EXPORT_SYMBOL(unlock_page); /** * end_page_writeback - end writeback against a page * @page: the page */ void end_page_writeback(struct page *page) { /* * TestClearPageReclaim could be used here but it is an atomic * operation and overkill in this particular case. Failing to * shuffle a page marked for immediate reclaim is too mild to * justify taking an atomic operation penalty at the end of * ever page writeback. */ if (PageReclaim(page)) { ClearPageReclaim(page); rotate_reclaimable_page(page); } /* * Writeback does not hold a page reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the page is not freed and * reused before the wake_up_page(). */ get_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); put_page(page); } EXPORT_SYMBOL(end_page_writeback); /* * After completing I/O on a page, call this routine to update the page * flags appropriately */ void page_endio(struct page *page, bool is_write, int err) { if (!is_write) { if (!err) { SetPageUptodate(page); } else { ClearPageUptodate(page); SetPageError(page); } unlock_page(page); } else { if (err) { struct address_space *mapping; SetPageError(page); mapping = page_mapping(page); if (mapping) mapping_set_error(mapping, err); } end_page_writeback(page); } } EXPORT_SYMBOL_GPL(page_endio); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @__page: the page to lock */ void __lock_page(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__lock_page); int __lock_page_killable(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__lock_page_killable); int __lock_page_async(struct page *page, struct wait_page_queue *wait) { return __wait_on_page_locked_async(page, wait, true); } /* * Return values: * 1 - page is locked; mmap_lock is still held. * 0 - page is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 * with the page locked and the mmap_lock unperturbed. */ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return 0; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) wait_on_page_locked_killable(page); else wait_on_page_locked(page); return 0; } else { if (flags & FAULT_FLAG_KILLABLE) { int ret; ret = __lock_page_killable(page); if (ret) { mmap_read_unlock(mm); return 0; } } else __lock_page(page); return 1; } } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == 0) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /** * find_get_entry - find and get a page cache entry * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, the head page is returned with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; rcu_read_lock(); repeat: xas_reset(&xas); page = xas_load(&xas); if (xas_retry(&xas, page)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!page || xa_is_value(page)) goto out; if (!page_cache_get_speculative(page)) goto repeat; /* * Has the page moved or been split? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != xas_reload(&xas))) { put_page(page); goto repeat; } out: rcu_read_unlock(); return page; } /** * find_lock_entry - Locate and lock a page cache entry. * @mapping: The address_space to search. * @index: The page cache index. * * Looks up the page at @mapping & @index. If there is a page in the * cache, the head page is returned locked and with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Context: May sleep. * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) { struct page *page; repeat: page = find_get_entry(mapping, index); if (page && !xa_is_value(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } return page; } /** * pagecache_get_page - Find and get a reference to a page. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the page is returned. * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * * * %FGP_ACCESSED - The page will be marked accessed. * * %FGP_LOCK - The page is returned locked. * * %FGP_HEAD - If the page is present and a THP, return the head page * rather than the exact page specified by the index. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. * * %FGP_WRITE - The page will be written * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask * * %FGP_NOWAIT - Don't get blocked by page lock * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * * Return: The found page or %NULL otherwise. */ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp_mask) { struct page *page; repeat: page = find_get_entry(mapping, index); if (xa_is_value(page)) page = NULL; if (!page) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!trylock_page(page)) { put_page(page); return NULL; } } else { lock_page(page); } /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } if (fgp_flags & FGP_ACCESSED) mark_page_accessed(page); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (page_is_idle(page)) clear_page_idle(page); } if (!(fgp_flags & FGP_HEAD)) page = find_subpage(page, index); no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp_mask |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp_mask &= ~__GFP_FS; page = __page_cache_alloc(gfp_mask); if (!page) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); err = add_to_page_cache_lru(page, mapping, index, gfp_mask); if (unlikely(err)) { put_page(page); page = NULL; if (err == -EEXIST) goto repeat; } /* * add_to_page_cache_lru locks the page, and for mmap we expect * an unlocked page. */ if (page && (fgp_flags & FGP_FOR_MMAP)) unlock_page(page); } return page; } EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @nr_entries: The maximum number of entries * @entries: Where the resulting entries are placed * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a group of up to * @nr_entries entries in the mapping. The entries are placed at * @entries. find_get_entries() takes a reference against any actual * pages it returns. * * The search returns a group of mapping-contiguous page cache entries * with ascending indexes. There may be holes in the indices due to * not-present pages. * * Any shadow entries of evicted pages, or swap entries from * shmem/tmpfs, are included in the returned array. * * If it finds a Transparent Huge Page, head or tail, find_get_entries() * stops at that page: the caller is likely to have a better way to handle * the compound page as a whole, and then skip its extent, than repeatedly * calling find_get_entries() to return all its tails. * * Return: the number of pages and shadow entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (xa_is_value(page)) goto export; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; /* * Terminate early on finding a THP, to allow the caller to * handle it all at once; but continue if this is hugetlbfs. */ if (PageTransHuge(page) && !PageHuge(page)) { page = find_subpage(page, xas.xa_index); nr_entries = ret + 1; } export: indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } /** * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_range() will search for and return a group of up to @nr_pages * pages in the mapping starting at index @start and up to index @end * (inclusive). The pages are placed at @pages. find_get_pages_range() takes * a reference against the returned pages. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. * We also update @start to index the next page for the traversal. * * Return: the number of pages which were found. If this number is * smaller than @nr_pages, the end of specified range has been * reached. */ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *start); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each(&xas, page, end) { if (xas_retry(&xas, page)) continue; /* Skip over shadow, swap and DAX entries */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broken anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return ret; } /** * find_get_pages_contig - gang contiguous pagecache lookup * @mapping: The address_space to search * @index: The starting page index * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_contig() works exactly like find_get_pages(), except * that the returned number of pages are guaranteed to be contiguous. * * Return: the number of pages which were found. */ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(page)) break; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_contig); /** * find_get_pages_range_tag - find and return pages in given range matching @tag * @mapping: the address_space to search * @index: the starting page index * @end: The final page index (inclusive) * @tag: the tag index * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * * Like find_get_pages, except we only return pages which are tagged with * @tag. We update @index to index the next page for the traversal. * * Return: the number of pages which were found. */ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *index); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each_marked(&xas, page, end, tag) { if (xas_retry(&xas, page)) continue; /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *index = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when we got to @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the * iteration when there is a page at index -1 but that is already * broken anyway. */ if (end == (pgoff_t)-1) *index = (pgoff_t)-1; else *index = end + 1; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_range_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /** * generic_file_buffered_read - generic file read routine * @iocb: the iocb to read * @iter: data destination * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. * * Return: * * total number of bytes copied, including those the were already @written * * negative error code if nothing was copied */ ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t written) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; loff_t *ppos = &iocb->ki_pos; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error = 0; if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; prev_offset = ra->prev_pos & (PAGE_SIZE-1); last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if (written && (iocb->ki_flags & IOCB_WAITQ)) iocb->ki_flags |= IOCB_NOWAIT; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: if (fatal_signal_pending(current)) { error = -EINTR; goto out; } page = find_get_page(mapping, index); if (!page) { if (iocb->ki_flags & IOCB_NOIO) goto would_block; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { if (iocb->ki_flags & IOCB_NOIO) { put_page(page); goto out; } page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } if (!PageUptodate(page)) { /* * See comment in do_read_cache_page on why * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = wait_on_page_locked_async(page, iocb->ki_waitq); } else { if (iocb->ki_flags & IOCB_NOWAIT) { put_page(page); goto would_block; } error = wait_on_page_locked_killable(page); } if (unlikely(error)) goto readpage_error; if (PageUptodate(page)) goto page_ok; if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; /* Did it get truncated before we got the lock? */ if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } page_ok: /* * i_size must be checked after we know the page is Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ nr = PAGE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { put_page(page); goto out; } } nr = nr - offset; /* If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; prev_offset = offset; put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; if (ret < nr) { error = -EFAULT; goto out; } continue; page_not_up_to_date: /* Get exclusive access to the page ... */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); put_page(page); continue; } /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) { unlock_page(page); put_page(page); goto would_block; } /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. * PG_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page. */ error = mapping->a_ops->readpage(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { put_page(page); error = 0; goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_mapping_pages got it */ unlock_page(page); put_page(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(ra); error = -EIO; goto readpage_error; } unlock_page(page); } goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ put_page(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ page = page_cache_alloc(mapping); if (!page) { error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { put_page(page); if (error == -EEXIST) { error = 0; goto find_page; } goto out; } goto readpage; } would_block: error = -EAGAIN; out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; } EXPORT_SYMBOL_GPL(generic_file_buffered_read); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) goto out; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t size; size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_has_page(mapping, iocb->ki_pos, iocb->ki_pos + count - 1)) return -EAGAIN; } else { retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); if (retval < 0) goto out; } file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || iocb->ki_pos >= size || IS_DAX(inode)) goto out; } retval = generic_file_buffered_read(iocb, iter, retval); out: return retval; } EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @page - the page to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_page_or_retry in that it can drop the mmap_lock. * It differs in that it actually returns the page locked if it returns 1 and 0 * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin * will point to the pinned file and needs to be fput()'ed at a later point. */ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { if (trylock_page(page)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__lock_page_killable(page)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals * if we return VM_FAULT_RETRY, so we need to drop the * mmap_lock here and return 0 if we don't have a fpin. */ if (*fpin == NULL) mmap_read_unlock(vmf->vma->vm_mm); return 0; } } else __lock_page(page); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vmf->vma->vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; do_page_cache_ra(&ractl, ra->size, ra->async_size); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct page *page) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; unsigned int mmap_miss; pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (PageReadahead(page)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); } return fpin; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; pgoff_t max_off; struct page *page; vm_fault_t ret = 0; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { /* * We found the page, so try async readahead before * waiting for the lock. */ fpin = do_async_mmap_readahead(vmf, page); } else if (!page) { /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: page = pagecache_get_page(mapping, offset, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (!page) { if (fpin) goto out_retry; return VM_FAULT_OOM; } } if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(compound_head(page)->mapping != mapping)) { unlock_page(page); put_page(page); goto retry_find; } VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ if (unlikely(!PageUptodate(page))) goto page_not_uptodate; /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { unlock_page(page); goto out_retry; } /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) { unlock_page(page); put_page(page); return VM_FAULT_SIGBUS; } vmf->page = page; return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ ClearPageError(page); fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } if (fpin) goto out_retry; put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; shrink_readahead_size_eio(ra); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (page) put_page(page); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long max_idx; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *head, *page; unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); rcu_read_lock(); xas_for_each(&xas, head, end_pgoff) { if (xas_retry(&xas, head)) continue; if (xa_is_value(head)) goto next; /* * Check for a locked page first, as a speculative * reference may adversely influence page migration. */ if (PageLocked(head)) goto next; if (!page_cache_get_speculative(head)) goto next; /* Has the page moved or been split? */ if (unlikely(head != xas_reload(&xas))) goto skip; page = find_subpage(head, xas.xa_index); if (!PageUptodate(head) || PageReadahead(page) || PageHWPoison(page)) goto skip; if (!trylock_page(head)) goto skip; if (head->mapping != mapping || !PageUptodate(head)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas.xa_index >= max_idx) goto unlock; if (mmap_miss > 0) mmap_miss--; vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; if (alloc_set_pte(vmf, page)) goto unlock; unlock_page(head); goto next; unlock: unlock_page(head); skip: put_page(head); next: /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) break; } rcu_read_unlock(); WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the page dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty page and writeprotect it again. */ set_page_dirty(page); wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *wait_on_page_read(struct page *page) { if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { put_page(page); page = ERR_PTR(-EIO); } } return page; } static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data, gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } filler: if (filler) err = filler(data, page); else err = mapping->a_ops->readpage(data, page); if (err < 0) { put_page(page); return ERR_PTR(err); } page = wait_on_page_read(page); if (IS_ERR(page)) return page; goto out; } if (PageUptodate(page)) goto out; /* * Page is not up to date and may be locked due to one of the following * case a: Page is being filled and the page lock is held * case b: Read/write error clearing the page uptodate status * case c: Truncation in progress (page locked) * case d: Reclaim in progress * * Case a, the page will be up to date when the page is unlocked. * There is no need to serialise on the page lock here as the page * is pinned so the lock gives no additional protection. Even if the * page is truncated, the data is still valid if PageUptodate as * it's a race vs truncate race. * Case b, the page will not be up to date * Case c, the page may be truncated but in itself, the data may still * be valid after IO completes as it's a read vs truncate race. The * operation must restart if the page is not uptodate on unlock but * otherwise serialising on page lock to stabilise the mapping gives * no additional guarantees to the caller as the page lock is * released before return. * Case d, similar to truncation. If reclaim holds the page lock, it * will be a race with remove_mapping that determines if the mapping * is valid on unlock but otherwise the data is valid and there is * no need to serialise with page lock. * * As the page lock gives no additional guarantee, we optimistically * wait on the page to be unlocked and check if it's up to date and * use the page if it is. Otherwise, the page lock is required to * distinguish between the different cases. The motivation is that we * avoid spurious serialisations and wakeups when multiple processes * wait on the same page for IO to complete. */ wait_on_page_locked(page); if (PageUptodate(page)) goto out; /* Distinguish between all the cases under the safety of the lock */ lock_page(page); /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); put_page(page); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (PageUptodate(page)) { unlock_page(page); goto out; } /* * A previous I/O error may have been due to temporary * failures. * Clear page error before actual read, PG_error will be * set again if read page fails. */ ClearPageError(page); goto filler; out: mark_page_accessed(page); return page; } /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); } EXPORT_SYMBOL(pagecache_write_begin); int pagecache_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); /* * Warn about a page cache invalidation failure during a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; struct inode *inode = file_inode(filp); char *path; errseq_set(&inode->i_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written; size_t write_len; pgoff_t end; write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ if (filemap_range_has_page(inode->i_mapping, pos, pos + write_len - 1)) return -EAGAIN; } else { written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) goto out; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ if (written) { if (written == -EBUSY) return 0; goto out; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0 && mapping->nrpages && invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end)) dio_warn_stale_pagecache(file); if (written > 0) { pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; } EXPORT_SYMBOL(generic_file_direct_write); /* * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { struct page *page; int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; if (flags & AOP_FLAG_NOFS) fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; unsigned int flags = 0; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ void *fsdata; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * Not only is this an optimisation, but it is also required * to check that the address is actually valid, when atomic * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) break; copied = status; cond_resched(); iov_iter_advance(i, copied); if (unlikely(copied == 0)) { /* * If we were unable to copy any data at all, we must * fall back to a single segment length write. * * If we didn't fallback here, we could livelock * because not all segments in the iov can be copied at * once without a pagefault. */ bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } pos += copied; written += copied; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); return written ? written : status; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_mutex to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; ssize_t status; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; err = file_update_time(file); if (err) goto out; if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos, endbyte; written = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; status = generic_perform_write(file, from, pos = iocb->ki_pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ if (unlikely(status < 0)) { err = status; goto out; } /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + status - 1; err = filemap_write_and_wait_range(mapping, pos, endbyte); if (err == 0) { iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return * the number of bytes which were direct-written */ } } else { written = generic_perform_write(file, from, iocb->ki_pos); if (likely(written > 0)) iocb->ki_pos += written; } out: current->backing_dev_info = NULL; return written ? written : err; } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page * * @page: the page which the kernel is trying to free * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page * (presumably at page->private). * * This may also be called if PG_fscache is set on a page, indicating that the * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). * * Return: %1 if the release was successful, otherwise return zero. */ int try_to_release_page(struct page *page, gfp_t gfp_mask) { struct address_space * const mapping = page->mapping; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping && mapping->a_ops->releasepage) return mapping->a_ops->releasepage(page, gfp_mask); return try_to_free_buffers(page); } EXPORT_SYMBOL(try_to_release_page);
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0 #ifndef _LINUX_KERNEL_TRACE_H #define _LINUX_KERNEL_TRACE_H #include <linux/fs.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/clocksource.h> #include <linux/ring_buffer.h> #include <linux/mmiotrace.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/trace.h> #include <linux/hw_breakpoint.h> #include <linux/trace_seq.h> #include <linux/trace_events.h> #include <linux/compiler.h> #include <linux/glob.h> #include <linux/irq_work.h> #include <linux/workqueue.h> #include <linux/ctype.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */ #include <asm/syscall.h> /* some archs define it here */ #endif enum trace_type { __TRACE_FIRST_TYPE = 0, TRACE_FN, TRACE_CTX, TRACE_WAKE, TRACE_STACK, TRACE_PRINT, TRACE_BPRINT, TRACE_MMIO_RW, TRACE_MMIO_MAP, TRACE_BRANCH, TRACE_GRAPH_RET, TRACE_GRAPH_ENT, TRACE_USER_STACK, TRACE_BLK, TRACE_BPUTS, TRACE_HWLAT, TRACE_RAW_DATA, __TRACE_LAST_TYPE, }; #undef __field #define __field(type, item) type item; #undef __field_fn #define __field_fn(type, item) type item; #undef __field_struct #define __field_struct(type, item) __field(type, item) #undef __field_desc #define __field_desc(type, container, item) #undef __field_packed #define __field_packed(type, container, item) #undef __array #define __array(type, item, size) type item[size]; #undef __array_desc #define __array_desc(type, container, item, size) #undef __dynamic_array #define __dynamic_array(type, item) type item[]; #undef F_STRUCT #define F_STRUCT(args...) args #undef FTRACE_ENTRY #define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct struct_name { \ struct trace_entry ent; \ tstruct \ } #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) #undef FTRACE_ENTRY_REG #define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED #define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print) \ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed #include "trace_entries.h" /* Use this for memory failure errors */ #define MEM_FAIL(condition, fmt, ...) ({ \ static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(condition); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ __warned = true; \ pr_err("ERROR: " fmt, ##__VA_ARGS__); \ } \ unlikely(__ret_warn_once); \ }) /* * syscalls are special, and need special handling, this is why * they are not included in trace_entries.h */ struct syscall_trace_enter { struct trace_entry ent; int nr; unsigned long args[]; }; struct syscall_trace_exit { struct trace_entry ent; int nr; long ret; }; struct kprobe_trace_entry_head { struct trace_entry ent; unsigned long ip; }; struct kretprobe_trace_entry_head { struct trace_entry ent; unsigned long func; unsigned long ret_ip; }; /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: * IRQS_OFF - interrupts were disabled * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags * NEED_RESCHED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, TRACE_FLAG_IRQS_NOSUPPORT = 0x02, TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, }; #define TRACE_BUF_SIZE 1024 struct trace_array; /* * The CPU trace array - it consists of thousands of trace entries * plus some other descriptor data: (for example which task started * the trace, etc.) */ struct trace_array_cpu { atomic_t disabled; void *buffer_page; /* ring buffer spare */ unsigned long entries; unsigned long saved_latency; unsigned long critical_start; unsigned long critical_end; unsigned long critical_sequence; unsigned long nice; unsigned long policy; unsigned long rt_priority; unsigned long skipped_entries; u64 preempt_timestamp; pid_t pid; kuid_t uid; char comm[TASK_COMM_LEN]; #ifdef CONFIG_FUNCTION_TRACER int ftrace_ignore_pid; #endif bool ignore_pid; }; struct tracer; struct trace_option_dentry; struct array_buffer { struct trace_array *tr; struct trace_buffer *buffer; struct trace_array_cpu __percpu *data; u64 time_start; int cpu; }; #define TRACE_FLAGS_MAX_SIZE 32 struct trace_options { struct tracer *tracer; struct trace_option_dentry *topts; }; struct trace_pid_list { int pid_max; unsigned long *pids; }; enum { TRACE_PIDS = BIT(0), TRACE_NO_PIDS = BIT(1), }; static inline bool pid_type_enabled(int type, struct trace_pid_list *pid_list, struct trace_pid_list *no_pid_list) { /* Return true if the pid list in type has pids */ return ((type & TRACE_PIDS) && pid_list) || ((type & TRACE_NO_PIDS) && no_pid_list); } static inline bool still_need_pid_events(int type, struct trace_pid_list *pid_list, struct trace_pid_list *no_pid_list) { /* * Turning off what is in @type, return true if the "other" * pid list, still has pids in it. */ return (!(type & TRACE_PIDS) && pid_list) || (!(type & TRACE_NO_PIDS) && no_pid_list); } typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data); /** * struct cond_snapshot - conditional snapshot data and callback * * The cond_snapshot structure encapsulates a callback function and * data associated with the snapshot for a given tracing instance. * * When a snapshot is taken conditionally, by invoking * tracing_snapshot_cond(tr, cond_data), the cond_data passed in is * passed in turn to the cond_snapshot.update() function. That data * can be compared by the update() implementation with the cond_data * contained within the struct cond_snapshot instance associated with * the trace_array. Because the tr->max_lock is held throughout the * update() call, the update() function can directly retrieve the * cond_snapshot and cond_data associated with the per-instance * snapshot associated with the trace_array. * * The cond_snapshot.update() implementation can save data to be * associated with the snapshot if it decides to, and returns 'true' * in that case, or it returns 'false' if the conditional snapshot * shouldn't be taken. * * The cond_snapshot instance is created and associated with the * user-defined cond_data by tracing_cond_snapshot_enable(). * Likewise, the cond_snapshot instance is destroyed and is no longer * associated with the trace instance by * tracing_cond_snapshot_disable(). * * The method below is required. * * @update: When a conditional snapshot is invoked, the update() * callback function is invoked with the tr->max_lock held. The * update() implementation signals whether or not to actually * take the snapshot, by returning 'true' if so, 'false' if no * snapshot should be taken. Because the max_lock is held for * the duration of update(), the implementation is safe to * directly retrieved and save any implementation data it needs * to in association with the snapshot. */ struct cond_snapshot { void *cond_data; cond_update_fn_t update; }; /* * The trace array - an array of per-CPU trace arrays. This is the * highest level data structure that individual tracers deal with. * They have on/off state as well: */ struct trace_array { struct list_head list; char *name; struct array_buffer array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE /* * The max_buffer is used to snapshot the trace when a maximum * latency is reached, or when the user initiates a snapshot. * Some tracers will use this to store a maximum trace while * it continues examining live traces. * * The buffers for the max_buffer are set up the same as the array_buffer * When a snapshot is taken, the buffer of the max_buffer is swapped * with the buffer of the array_buffer and the buffers are reset for * the array_buffer so the tracing can continue. */ struct array_buffer max_buffer; bool allocated_snapshot; #endif #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) unsigned long max_latency; #ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; struct work_struct fsnotify_work; struct irq_work fsnotify_irqwork; #endif #endif struct trace_pid_list __rcu *filtered_pids; struct trace_pid_list __rcu *filtered_no_pids; /* * max_lock is used to protect the swapping of buffers * when taking a max snapshot. The buffers themselves are * protected by per_cpu spinlocks. But the action of the swap * needs its own lock. * * This is defined as a arch_spinlock_t in order to help * with performance when lockdep debugging is enabled. * * It is also used in other places outside the update_max_tr * so it needs to be defined outside of the * CONFIG_TRACER_MAX_TRACE. */ arch_spinlock_t max_lock; int buffer_disabled; #ifdef CONFIG_FTRACE_SYSCALLS int sys_refcount_enter; int sys_refcount_exit; struct trace_event_file __rcu *enter_syscall_files[NR_syscalls]; struct trace_event_file __rcu *exit_syscall_files[NR_syscalls]; #endif int stop_count; int clock_id; int nr_topts; bool clear_trace; int buffer_percent; unsigned int n_err_log_entries; struct tracer *current_trace; unsigned int trace_flags; unsigned char trace_flags_index[TRACE_FLAGS_MAX_SIZE]; unsigned int flags; raw_spinlock_t start_lock; struct list_head err_log; struct dentry *dir; struct dentry *options; struct dentry *percpu_dir; struct dentry *event_dir; struct trace_options *topts; struct list_head systems; struct list_head events; struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; int trace_ref; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; struct trace_pid_list __rcu *function_no_pids; #ifdef CONFIG_DYNAMIC_FTRACE /* All of these are protected by the ftrace_lock */ struct list_head func_probes; struct list_head mod_trace; struct list_head mod_notrace; #endif /* function tracing enabled */ int function_enabled; #endif int time_stamp_abs_ref; struct list_head hist_vars; #ifdef CONFIG_TRACER_SNAPSHOT struct cond_snapshot *cond_snapshot; #endif }; enum { TRACE_ARRAY_FL_GLOBAL = (1 << 0) }; extern struct list_head ftrace_trace_arrays; extern struct mutex trace_types_lock; extern int trace_array_get(struct trace_array *tr); extern int tracing_check_open_get_tr(struct trace_array *tr); extern struct trace_array *trace_array_find(const char *instance); extern struct trace_array *trace_array_find_get(const char *instance); extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs); extern int tracing_set_clock(struct trace_array *tr, const char *clockstr); extern bool trace_clock_in_ns(struct trace_array *tr); /* * The global tracer (top) should be the first trace array added, * but we check the flag anyway. */ static inline struct trace_array *top_trace_array(void) { struct trace_array *tr; if (list_empty(&ftrace_trace_arrays)) return NULL; tr = list_entry(ftrace_trace_arrays.prev, typeof(*tr), list); WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL)); return tr; } #define FTRACE_CMP_TYPE(var, type) \ __builtin_types_compatible_p(typeof(var), type *) #undef IF_ASSIGN #define IF_ASSIGN(var, entry, etype, id) \ if (FTRACE_CMP_TYPE(var, etype)) { \ var = (typeof(var))(entry); \ WARN_ON(id != 0 && (entry)->type != id); \ break; \ } /* Will cause compile errors if type is not found. */ extern void __ftrace_bad_type(void); /* * The trace_assign_type is a verifier that the entry type is * the same as the type being assigned. To add new types simply * add a line with the following format: * * IF_ASSIGN(var, ent, type, id); * * Where "type" is the trace type that includes the trace_entry * as the "ent" item. And "id" is the trace identifier that is * used in the trace_type enum. * * If the type can have more than one id, then use zero. */ #define trace_assign_type(var, ent) \ do { \ IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \ IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \ IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \ IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \ IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \ IF_ASSIGN(var, ent, struct hwlat_entry, TRACE_HWLAT); \ IF_ASSIGN(var, ent, struct raw_data_entry, TRACE_RAW_DATA);\ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ TRACE_MMIO_RW); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ TRACE_MMIO_MAP); \ IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \ IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \ TRACE_GRAPH_ENT); \ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ __ftrace_bad_type(); \ } while (0) /* * An option specific to a tracer. This is a boolean value. * The bit is the bit index that sets its value on the * flags value in struct tracer_flags. */ struct tracer_opt { const char *name; /* Will appear on the trace_options file */ u32 bit; /* Mask assigned in val field in tracer_flags */ }; /* * The set of specific options for a tracer. Your tracer * have to set the initial value of the flags val. */ struct tracer_flags { u32 val; struct tracer_opt *opts; struct tracer *trace; }; /* Makes more easy to define a tracer opt */ #define TRACER_OPT(s, b) .name = #s, .bit = b struct trace_option_dentry { struct tracer_opt *opt; struct tracer_flags *flags; struct trace_array *tr; struct dentry *entry; }; /** * struct tracer - a specific tracer and its callbacks to interact with tracefs * @name: the name chosen to select it on the available_tracers file * @init: called when one switches to this tracer (echo name > current_tracer) * @reset: called when one switches to another tracer * @start: called when tracing is unpaused (echo 1 > tracing_on) * @stop: called when tracing is paused (echo 0 > tracing_on) * @update_thresh: called when tracing_thresh is updated * @open: called when the trace file is opened * @pipe_open: called when the trace_pipe file is opened * @close: called when the trace file is released * @pipe_close: called when the trace_pipe file is released * @read: override the default read callback on trace_pipe * @splice_read: override the default splice_read callback on trace_pipe * @selftest: selftest to run on boot (see trace_selftest.c) * @print_headers: override the first lines that describe your columns * @print_line: callback that prints a trace * @set_flag: signals one of your private flags changed (trace_options file) * @flags: your private flags */ struct tracer { const char *name; int (*init)(struct trace_array *tr); void (*reset)(struct trace_array *tr); void (*start)(struct trace_array *tr); void (*stop)(struct trace_array *tr); int (*update_thresh)(struct trace_array *tr); void (*open)(struct trace_iterator *iter); void (*pipe_open)(struct trace_iterator *iter); void (*close)(struct trace_iterator *iter); void (*pipe_close)(struct trace_iterator *iter); ssize_t (*read)(struct trace_iterator *iter, struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t (*splice_read)(struct trace_iterator *iter, struct file *filp, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); #ifdef CONFIG_FTRACE_STARTUP_TEST int (*selftest)(struct tracer *trace, struct trace_array *tr); #endif void (*print_header)(struct seq_file *m); enum print_line_t (*print_line)(struct trace_iterator *iter); /* If you handled the flag setting, return 0 */ int (*set_flag)(struct trace_array *tr, u32 old_flags, u32 bit, int set); /* Return 0 if OK with change, else return non-zero */ int (*flag_changed)(struct trace_array *tr, u32 mask, int set); struct tracer *next; struct tracer_flags *flags; int enabled; bool print_max; bool allow_instances; #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; #endif /* True if tracer cannot be enabled in kernel param */ bool noboot; }; /* Only current can touch trace_recursion */ /* * For function tracing recursion: * The order of these bits are important. * * When function tracing occurs, the following steps are made: * If arch does not support a ftrace feature: * call internal function (uses INTERNAL bits) which calls... * If callback is registered to the "global" list, the list * function is called and recursion checks the GLOBAL bits. * then this function calls... * The function callback, which can use the FTRACE bits to * check for recursion. */ enum { /* Function recursion bits */ TRACE_FTRACE_BIT, TRACE_FTRACE_NMI_BIT, TRACE_FTRACE_IRQ_BIT, TRACE_FTRACE_SIRQ_BIT, TRACE_FTRACE_TRANSITION_BIT, /* Internal use recursion bits */ TRACE_INTERNAL_BIT, TRACE_INTERNAL_NMI_BIT, TRACE_INTERNAL_IRQ_BIT, TRACE_INTERNAL_SIRQ_BIT, TRACE_INTERNAL_TRANSITION_BIT, TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. * As we need a way to maintain state if we are tracing the function * graph in irq because we want to trace a particular function that * was called in irq context but we have irq tracing off. Since this * can only be modified by current, we can reuse trace_recursion. */ TRACE_IRQ_BIT, /* Set if the function is in the set_graph_function file */ TRACE_GRAPH_BIT, /* * In the very unlikely case that an interrupt came in * at a start of graph tracing, and we want to trace * the function in that interrupt, the depth can be greater * than zero, because of the preempted start of a previous * trace. In an even more unlikely case, depth could be 2 * if a softirq interrupted the start of graph tracing, * followed by an interrupt preempting a start of graph * tracing in the softirq, and depth can even be 3 * if an NMI came in at the start of an interrupt function * that preempted a softirq start of a function that * preempted normal context!!!! Luckily, it can't be * greater than 3, so the next two bits are a mask * of what the depth is when we set TRACE_GRAPH_BIT */ TRACE_GRAPH_DEPTH_START_BIT, TRACE_GRAPH_DEPTH_END_BIT, /* * To implement set_graph_notrace, if this bit is set, we ignore * function graph tracing of called functions, until the return * function is called to clear it. */ TRACE_GRAPH_NOTRACE_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) #define trace_recursion_depth() \ (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) #define trace_recursion_set_depth(depth) \ do { \ current->trace_recursion &= \ ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ current->trace_recursion |= \ ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ } while (0) #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT #define TRACE_LIST_START TRACE_INTERNAL_BIT #define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) enum { TRACE_CTX_NMI, TRACE_CTX_IRQ, TRACE_CTX_SOFTIRQ, TRACE_CTX_NORMAL, TRACE_CTX_TRANSITION, }; static __always_inline int trace_get_context_bit(void) { int bit; if (in_interrupt()) { if (in_nmi()) bit = TRACE_CTX_NMI; else if (in_irq()) bit = TRACE_CTX_IRQ; else bit = TRACE_CTX_SOFTIRQ; } else bit = TRACE_CTX_NORMAL; return bit; } static __always_inline int trace_test_and_set_recursion(int start) { unsigned int val = current->trace_recursion; int bit; bit = trace_get_context_bit() + start; if (unlikely(val & (1 << bit))) { /* * It could be that preempt_count has not been updated during * a switch between contexts. Allow for a single recursion. */ bit = start + TRACE_CTX_TRANSITION; if (trace_recursion_test(bit)) return -1; trace_recursion_set(bit); barrier(); return bit; } val |= 1 << bit; current->trace_recursion = val; barrier(); return bit; } static __always_inline void trace_clear_recursion(int bit) { unsigned int val = current->trace_recursion; bit = 1 << bit; val &= ~bit; barrier(); current->trace_recursion = val; } static inline struct ring_buffer_iter * trace_buffer_iter(struct trace_iterator *iter, int cpu) { return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL; } int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void tracing_reset_online_cpus(struct array_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); void tracer_tracing_off(struct trace_array *tr); struct dentry *trace_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); int tracing_init_dentry(void); struct ring_buffer_event; struct ring_buffer_event * trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned long flags, int pc); struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data); struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event); int trace_empty(struct trace_iterator *iter); void *trace_find_next_entry_inc(struct trace_iterator *iter); void trace_init_global_iter(struct trace_iterator *iter); void tracing_iter_reset(struct trace_iterator *iter, int cpu); unsigned long trace_total_entries_cpu(struct trace_array *tr, int cpu); unsigned long trace_total_entries(struct trace_array *tr); void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc); void trace_graph_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc); void trace_latency_header(struct seq_file *m); void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); void trace_graph_return(struct ftrace_graph_ret *trace); int trace_graph_entry(struct ftrace_graph_ent *trace); void set_graph_array(struct trace_array *tr); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); void tracing_start_tgid_record(void); void tracing_stop_tgid_record(void); int register_tracer(struct tracer *type); int is_tracing_stopped(void); loff_t tracing_lseek(struct file *file, loff_t offset, int whence); extern cpumask_var_t __read_mostly tracing_buffer_mask; #define for_each_tracing_cpu(cpu) \ for_each_cpu(cpu, tracing_buffer_mask) extern unsigned long nsecs_to_usecs(unsigned long nsecs); extern unsigned long tracing_thresh; /* PID filtering */ extern int pid_max; bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid); bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct trace_pid_list *filtered_no_pids, struct task_struct *task); void trace_filter_add_remove_task(struct trace_pid_list *pid_list, struct task_struct *self, struct task_struct *task); void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos); void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos); int trace_pid_show(struct seq_file *m, void *v); void trace_free_pid_list(struct trace_pid_list *pid_list); int trace_pid_write(struct trace_pid_list *filtered_pids, struct trace_pid_list **new_pid_list, const char __user *ubuf, size_t cnt); #ifdef CONFIG_TRACER_MAX_TRACE void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, void *cond_data); void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu); #endif /* CONFIG_TRACER_MAX_TRACE */ #if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \ defined(CONFIG_FSNOTIFY) void latency_fsnotify(struct trace_array *tr); #else static inline void latency_fsnotify(struct trace_array *tr) { } #endif #ifdef CONFIG_STACKTRACE void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc); #else static inline void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { } #endif /* CONFIG_STACKTRACE */ extern u64 ftrace_now(int cpu); extern void trace_find_cmdline(int pid, char comm[]); extern int trace_find_tgid(int pid); extern void trace_event_follow_fork(struct trace_array *tr, bool enable); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; extern unsigned long ftrace_number_of_pages; extern unsigned long ftrace_number_of_groups; void ftrace_init_trace_array(struct trace_array *tr); #else static inline void ftrace_init_trace_array(struct trace_array *tr) { } #endif #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); extern bool ring_buffer_expanded; extern bool tracing_selftest_disabled; #ifdef CONFIG_FTRACE_STARTUP_TEST extern void __init disable_tracing_selftest(const char *reason); extern int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_function_graph(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); /* * Tracer data references selftest functions that only occur * on boot up. These can be __init functions. Thus, when selftests * are enabled, then the tracers need to reference __init functions. */ #define __tracer_data __refdata #else static inline void __init disable_tracing_selftest(const char *reason) { } /* Tracers are seldom changed. Optimize when selftests are disabled. */ #define __tracer_data __read_mostly #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); extern unsigned long long ns2usecs(u64 nsec); extern int trace_vbprintk(unsigned long ip, const char *fmt, va_list args); extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args); extern int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args); int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...); void trace_printk_seq(struct trace_seq *s); enum print_line_t print_trace_line(struct trace_iterator *iter); extern char trace_find_mark(unsigned long long duration); struct ftrace_hash; struct ftrace_mod_load { struct list_head list; char *func; char *module; int enable; }; enum { FTRACE_HASH_FL_MOD = (1 << 0), }; struct ftrace_hash { unsigned long size_bits; struct hlist_head *buckets; unsigned long count; unsigned long flags; struct rcu_head rcu; }; struct ftrace_func_entry * ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip); static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash) { return !hash || !(hash->count || (hash->flags & FTRACE_HASH_FL_MOD)); } /* Standard output formatting function used for function return traces */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Flag options */ #define TRACE_GRAPH_PRINT_OVERRUN 0x1 #define TRACE_GRAPH_PRINT_CPU 0x2 #define TRACE_GRAPH_PRINT_OVERHEAD 0x4 #define TRACE_GRAPH_PRINT_PROC 0x8 #define TRACE_GRAPH_PRINT_DURATION 0x10 #define TRACE_GRAPH_PRINT_ABS_TIME 0x20 #define TRACE_GRAPH_PRINT_REL_TIME 0x40 #define TRACE_GRAPH_PRINT_IRQS 0x80 #define TRACE_GRAPH_PRINT_TAIL 0x100 #define TRACE_GRAPH_SLEEP_TIME 0x200 #define TRACE_GRAPH_GRAPH_TIME 0x400 #define TRACE_GRAPH_PRINT_FILL_SHIFT 28 #define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT) extern void ftrace_graph_sleep_time_control(bool enable); #ifdef CONFIG_FUNCTION_PROFILER extern void ftrace_graph_graph_time_control(bool enable); #else static inline void ftrace_graph_graph_time_control(bool enable) { } #endif extern enum print_line_t print_graph_function_flags(struct trace_iterator *iter, u32 flags); extern void print_graph_headers_flags(struct seq_file *s, u32 flags); extern void trace_print_graph_duration(unsigned long long duration, struct trace_seq *s); extern void graph_trace_open(struct trace_iterator *iter); extern void graph_trace_close(struct trace_iterator *iter); extern int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent *trace, unsigned long flags, int pc); extern void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, unsigned long flags, int pc); #ifdef CONFIG_DYNAMIC_FTRACE extern struct ftrace_hash __rcu *ftrace_graph_hash; extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash; static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { unsigned long addr = trace->func; int ret = 0; struct ftrace_hash *hash; preempt_disable_notrace(); /* * Have to open code "rcu_dereference_sched()" because the * function graph tracer can be called when RCU is not * "watching". * Protected with schedule_on_each_cpu(ftrace_sync) */ hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible()); if (ftrace_hash_empty(hash)) { ret = 1; goto out; } if (ftrace_lookup_ip(hash, addr)) { /* * This needs to be cleared on the return functions * when the depth is zero. */ trace_recursion_set(TRACE_GRAPH_BIT); trace_recursion_set_depth(trace->depth); /* * If no irqs are to be traced, but a set_graph_function * is set, and called by an interrupt handler, we still * want to trace it. */ if (in_irq()) trace_recursion_set(TRACE_IRQ_BIT); else trace_recursion_clear(TRACE_IRQ_BIT); ret = 1; } out: preempt_enable_notrace(); return ret; } static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) { if (trace_recursion_test(TRACE_GRAPH_BIT) && trace->depth == trace_recursion_depth()) trace_recursion_clear(TRACE_GRAPH_BIT); } static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; struct ftrace_hash *notrace_hash; preempt_disable_notrace(); /* * Have to open code "rcu_dereference_sched()" because the * function graph tracer can be called when RCU is not * "watching". * Protected with schedule_on_each_cpu(ftrace_sync) */ notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash, !preemptible()); if (ftrace_lookup_ip(notrace_hash, addr)) ret = 1; preempt_enable_notrace(); return ret; } #else static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { return 1; } static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) { } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) { /* trace it when it is-nested-in or is a function enabled. */ return !(trace_recursion_test(TRACE_GRAPH_BIT) || ftrace_graph_addr(trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } #else /* CONFIG_FUNCTION_GRAPH_TRACER */ static inline enum print_line_t print_graph_function_flags(struct trace_iterator *iter, u32 flags) { return TRACE_TYPE_UNHANDLED; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER #define FTRACE_PID_IGNORE -1 #define FTRACE_PID_TRACE -2 struct ftrace_func_command { struct list_head list; char *name; int (*func)(struct trace_array *tr, struct ftrace_hash *hash, char *func, char *cmd, char *params, int enable); }; extern bool ftrace_filter_param __initdata; static inline int ftrace_trace_task(struct trace_array *tr) { return this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid) != FTRACE_PID_IGNORE; } extern int ftrace_is_dead(void); int ftrace_create_function_files(struct trace_array *tr, struct dentry *parent); void ftrace_destroy_function_files(struct trace_array *tr); int ftrace_allocate_ftrace_ops(struct trace_array *tr); void ftrace_free_ftrace_ops(struct trace_array *tr); void ftrace_init_global_array_ops(struct trace_array *tr); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d_tracer); void ftrace_clear_pids(struct trace_array *tr); int init_function_trace(void); void ftrace_pid_follow_fork(struct trace_array *tr, bool enable); #else static inline int ftrace_trace_task(struct trace_array *tr) { return 1; } static inline int ftrace_is_dead(void) { return 0; } static inline int ftrace_create_function_files(struct trace_array *tr, struct dentry *parent) { return 0; } static inline int ftrace_allocate_ftrace_ops(struct trace_array *tr) { return 0; } static inline void ftrace_free_ftrace_ops(struct trace_array *tr) { } static inline void ftrace_destroy_function_files(struct trace_array *tr) { } static inline __init void ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_clear_pids(struct trace_array *tr) { } static inline int init_function_trace(void) { return 0; } static inline void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) struct ftrace_probe_ops { void (*func)(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data); int (*init)(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *init_data, void **data); void (*free)(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *data); int (*print)(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data); }; struct ftrace_func_mapper; typedef int (*ftrace_mapper_func)(void *data); struct ftrace_func_mapper *allocate_ftrace_func_mapper(void); void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper, unsigned long ip); int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, unsigned long ip, void *data); void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper, unsigned long ip); void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper, ftrace_mapper_func free_func); extern int register_ftrace_function_probe(char *glob, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data); extern int unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, struct ftrace_probe_ops *ops); extern void clear_ftrace_function_probes(struct trace_array *tr); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); void ftrace_create_filter_files(struct ftrace_ops *ops, struct dentry *parent); void ftrace_destroy_filter_files(struct ftrace_ops *ops); extern int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); extern int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); #else struct ftrace_func_command; static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; } static inline __init int unregister_ftrace_command(char *cmd_name) { return -EINVAL; } static inline void clear_ftrace_function_probes(struct trace_array *tr) { } /* * The ops parameter passed in is usually undefined. * This must be a macro. */ #define ftrace_create_filter_files(ops, parent) do { } while (0) #define ftrace_destroy_filter_files(ops) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */ bool ftrace_event_is_function(struct trace_event_call *call); /* * struct trace_parser - servers for reading the user input separated by spaces * @cont: set if the input is not complete - no final space char was found * @buffer: holds the parsed user input * @idx: user input length * @size: buffer size */ struct trace_parser { bool cont; char *buffer; unsigned idx; unsigned size; }; static inline bool trace_parser_loaded(struct trace_parser *parser) { return (parser->idx != 0); } static inline bool trace_parser_cont(struct trace_parser *parser) { return parser->cont; } static inline void trace_parser_clear(struct trace_parser *parser) { parser->cont = false; parser->idx = 0; } extern int trace_parser_get_init(struct trace_parser *parser, int size); extern void trace_parser_put(struct trace_parser *parser); extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, size_t cnt, loff_t *ppos); /* * Only create function graph options if function graph is configured. */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER # define FGRAPH_FLAGS \ C(DISPLAY_GRAPH, "display-graph"), #else # define FGRAPH_FLAGS #endif #ifdef CONFIG_BRANCH_TRACER # define BRANCH_FLAGS \ C(BRANCH, "branch"), #else # define BRANCH_FLAGS #endif #ifdef CONFIG_FUNCTION_TRACER # define FUNCTION_FLAGS \ C(FUNCTION, "function-trace"), \ C(FUNC_FORK, "function-fork"), # define FUNCTION_DEFAULT_FLAGS TRACE_ITER_FUNCTION #else # define FUNCTION_FLAGS # define FUNCTION_DEFAULT_FLAGS 0UL # define TRACE_ITER_FUNC_FORK 0UL #endif #ifdef CONFIG_STACKTRACE # define STACK_FLAGS \ C(STACKTRACE, "stacktrace"), #else # define STACK_FLAGS #endif /* * trace_iterator_flags is an enumeration that defines bit * positions into trace_flags that controls the output. * * NOTE: These bits must match the trace_options array in * trace.c (this macro guarantees it). */ #define TRACE_FLAGS \ C(PRINT_PARENT, "print-parent"), \ C(SYM_OFFSET, "sym-offset"), \ C(SYM_ADDR, "sym-addr"), \ C(VERBOSE, "verbose"), \ C(RAW, "raw"), \ C(HEX, "hex"), \ C(BIN, "bin"), \ C(BLOCK, "block"), \ C(PRINTK, "trace_printk"), \ C(ANNOTATE, "annotate"), \ C(USERSTACKTRACE, "userstacktrace"), \ C(SYM_USEROBJ, "sym-userobj"), \ C(PRINTK_MSGONLY, "printk-msg-only"), \ C(CONTEXT_INFO, "context-info"), /* Print pid/cpu/time */ \ C(LATENCY_FMT, "latency-format"), \ C(RECORD_CMD, "record-cmd"), \ C(RECORD_TGID, "record-tgid"), \ C(OVERWRITE, "overwrite"), \ C(STOP_ON_FREE, "disable_on_free"), \ C(IRQ_INFO, "irq-info"), \ C(MARKERS, "markers"), \ C(EVENT_FORK, "event-fork"), \ C(PAUSE_ON_TRACE, "pause-on-trace"), \ FUNCTION_FLAGS \ FGRAPH_FLAGS \ STACK_FLAGS \ BRANCH_FLAGS /* * By defining C, we can make TRACE_FLAGS a list of bit names * that will define the bits for the flag masks. */ #undef C #define C(a, b) TRACE_ITER_##a##_BIT enum trace_iterator_bits { TRACE_FLAGS /* Make sure we don't go more than we have bits for */ TRACE_ITER_LAST_BIT }; /* * By redefining C, we can make TRACE_FLAGS a list of masks that * use the bits as defined above. */ #undef C #define C(a, b) TRACE_ITER_##a = (1 << TRACE_ITER_##a##_BIT) enum trace_iterator_flags { TRACE_FLAGS }; /* * TRACE_ITER_SYM_MASK masks the options in trace_flags that * control the output of kernel symbols. */ #define TRACE_ITER_SYM_MASK \ (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR) extern struct tracer nop_trace; #ifdef CONFIG_BRANCH_TRACER extern int enable_branch_tracing(struct trace_array *tr); extern void disable_branch_tracing(void); static inline int trace_branch_enable(struct trace_array *tr) { if (tr->trace_flags & TRACE_ITER_BRANCH) return enable_branch_tracing(tr); return 0; } static inline void trace_branch_disable(void) { /* due to races, always disable */ disable_branch_tracing(); } #else static inline int trace_branch_enable(struct trace_array *tr) { return 0; } static inline void trace_branch_disable(void) { } #endif /* CONFIG_BRANCH_TRACER */ /* set ring buffers to default size if not already done so */ int tracing_update_buffers(void); struct ftrace_event_field { struct list_head link; const char *name; const char *type; int filter_type; int offset; int size; int is_signed; }; struct prog_entry; struct event_filter { struct prog_entry __rcu *prog; char *filter_string; }; struct event_subsystem { struct list_head list; const char *name; struct event_filter *filter; int ref_count; }; struct trace_subsystem_dir { struct list_head list; struct event_subsystem *subsystem; struct trace_array *tr; struct dentry *entry; int ref_count; int nr_events; }; extern int call_filter_check_discard(struct trace_event_call *call, void *rec, struct trace_buffer *buffer, struct ring_buffer_event *event); void trace_buffer_unlock_commit_regs(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc, struct pt_regs *regs); static inline void trace_buffer_unlock_commit(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { trace_buffer_unlock_commit_regs(tr, buffer, event, flags, pc, NULL); } DECLARE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); DECLARE_PER_CPU(int, trace_buffered_event_cnt); void trace_buffered_event_disable(void); void trace_buffered_event_enable(void); static inline void __trace_event_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { if (this_cpu_read(trace_buffered_event) == event) { /* Simply release the temp buffer */ this_cpu_dec(trace_buffered_event_cnt); return; } ring_buffer_discard_commit(buffer, event); } /* * Helper function for event_trigger_unlock_commit{_regs}(). * If there are event triggers attached to this event that requires * filtering against its fields, then they will be called as the * entry already holds the field information of the current event. * * It also checks if the event should be discarded or not. * It is to be discarded if the event is soft disabled and the * event was only recorded to process triggers, or if the event * filter is active and this event did not match the filters. * * Returns true if the event is discarded, false otherwise. */ static inline bool __event_trigger_test_discard(struct trace_event_file *file, struct trace_buffer *buffer, struct ring_buffer_event *event, void *entry, enum event_trigger_type *tt) { unsigned long eflags = file->flags; if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, entry, event); if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED | EVENT_FILE_FL_PID_FILTER)))) return false; if (file->flags & EVENT_FILE_FL_SOFT_DISABLED) goto discard; if (file->flags & EVENT_FILE_FL_FILTERED && !filter_match_preds(file->filter, entry)) goto discard; if ((file->flags & EVENT_FILE_FL_PID_FILTER) && trace_event_ignore_this_pid(file)) goto discard; return false; discard: __trace_event_discard_commit(buffer, event); return true; } /** * event_trigger_unlock_commit - handle triggers and finish event commit * @file: The file pointer assoctiated to the event * @buffer: The ring buffer that the event is being written to * @event: The event meta data in the ring buffer * @entry: The event itself * @irq_flags: The state of the interrupts at the start of the event * @pc: The state of the preempt count at the start of the event. * * This is a helper function to handle triggers that require data * from the event itself. It also tests the event against filters and * if the event is soft disabled and should be discarded. */ static inline void event_trigger_unlock_commit(struct trace_event_file *file, struct trace_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc) { enum event_trigger_type tt = ETT_NONE; if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) event_triggers_post_call(file, tt); } /** * event_trigger_unlock_commit_regs - handle triggers and finish event commit * @file: The file pointer assoctiated to the event * @buffer: The ring buffer that the event is being written to * @event: The event meta data in the ring buffer * @entry: The event itself * @irq_flags: The state of the interrupts at the start of the event * @pc: The state of the preempt count at the start of the event. * * This is a helper function to handle triggers that require data * from the event itself. It also tests the event against filters and * if the event is soft disabled and should be discarded. * * Same as event_trigger_unlock_commit() but calls * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit(). */ static inline void event_trigger_unlock_commit_regs(struct trace_event_file *file, struct trace_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc, struct pt_regs *regs) { enum event_trigger_type tt = ETT_NONE; if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) trace_buffer_unlock_commit_regs(file->tr, buffer, event, irq_flags, pc, regs); if (tt) event_triggers_post_call(file, tt); } #define FILTER_PRED_INVALID ((unsigned short)-1) #define FILTER_PRED_IS_RIGHT (1 << 15) #define FILTER_PRED_FOLD (1 << 15) /* * The max preds is the size of unsigned short with * two flags at the MSBs. One bit is used for both the IS_RIGHT * and FOLD flags. The other is reserved. * * 2^14 preds is way more than enough. */ #define MAX_FILTER_PRED 16384 struct filter_pred; struct regex; typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event); typedef int (*regex_match_func)(char *str, struct regex *r, int len); enum regex_type { MATCH_FULL = 0, MATCH_FRONT_ONLY, MATCH_MIDDLE_ONLY, MATCH_END_ONLY, MATCH_GLOB, MATCH_INDEX, }; struct regex { char pattern[MAX_FILTER_STR_VAL]; int len; int field_len; regex_match_func match; }; struct filter_pred { filter_pred_fn_t fn; u64 val; struct regex regex; unsigned short *ops; struct ftrace_event_field *field; int offset; int not; int op; }; static inline bool is_string_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_DYN_STRING || field->filter_type == FILTER_STATIC_STRING || field->filter_type == FILTER_PTR_STRING || field->filter_type == FILTER_COMM; } static inline bool is_function_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_TRACE_FN; } extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct trace_event_file *file, struct trace_seq *s); extern int apply_event_filter(struct trace_event_file *file, char *filter_string); extern int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, char *filter_string); extern void print_subsystem_event_filter(struct event_subsystem *system, struct trace_seq *s); extern int filter_assign_type(const char *type); extern int create_event_filter(struct trace_array *tr, struct trace_event_call *call, char *filter_str, bool set_str, struct event_filter **filterp); extern void free_event_filter(struct event_filter *filter); struct ftrace_event_field * trace_find_event_field(struct trace_event_call *call, char *name); extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); extern void __trace_early_add_events(struct trace_array *tr); extern struct trace_event_file *__find_event_file(struct trace_array *tr, const char *system, const char *event); extern struct trace_event_file *find_event_file(struct trace_array *tr, const char *system, const char *event); static inline void *event_file_data(struct file *filp) { return READ_ONCE(file_inode(filp)->i_private); } extern struct mutex event_mutex; extern struct list_head ftrace_events; extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; extern const struct file_operations event_hist_debug_fops; extern const struct file_operations event_inject_fops; #ifdef CONFIG_HIST_TRIGGERS extern int register_trigger_hist_cmd(void); extern int register_trigger_hist_enable_disable_cmds(void); #else static inline int register_trigger_hist_cmd(void) { return 0; } static inline int register_trigger_hist_enable_disable_cmds(void) { return 0; } #endif extern int register_trigger_cmds(void); extern void clear_event_triggers(struct trace_array *tr); struct event_trigger_data { unsigned long count; int ref; struct event_trigger_ops *ops; struct event_command *cmd_ops; struct event_filter __rcu *filter; char *filter_str; void *private_data; bool paused; bool paused_tmp; struct list_head list; char *name; struct list_head named_list; struct event_trigger_data *named_data; }; /* Avoid typos */ #define ENABLE_EVENT_STR "enable_event" #define DISABLE_EVENT_STR "disable_event" #define ENABLE_HIST_STR "enable_hist" #define DISABLE_HIST_STR "disable_hist" struct enable_trigger_data { struct trace_event_file *file; bool enable; bool hist; }; extern int event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, struct event_trigger_data *data); extern void event_enable_trigger_free(struct event_trigger_ops *ops, struct event_trigger_data *data); extern int event_enable_trigger_func(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *param); extern int event_enable_register_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); extern void event_enable_unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test, struct trace_event_file *file); extern void trigger_data_free(struct event_trigger_data *data); extern int event_trigger_init(struct event_trigger_ops *ops, struct event_trigger_data *data); extern int trace_event_trigger_enable_disable(struct trace_event_file *file, int trigger_enable); extern void update_cond_flag(struct trace_event_file *file); extern int set_trigger_filter(char *filter_str, struct event_trigger_data *trigger_data, struct trace_event_file *file); extern struct event_trigger_data *find_named_trigger(const char *name); extern bool is_named_trigger(struct event_trigger_data *test); extern int save_named_trigger(const char *name, struct event_trigger_data *data); extern void del_named_trigger(struct event_trigger_data *data); extern void pause_named_trigger(struct event_trigger_data *data); extern void unpause_named_trigger(struct event_trigger_data *data); extern void set_named_trigger_data(struct event_trigger_data *data, struct event_trigger_data *named_data); extern struct event_trigger_data * get_named_trigger_data(struct event_trigger_data *data); extern int register_event_command(struct event_command *cmd); extern int unregister_event_command(struct event_command *cmd); extern int register_trigger_hist_enable_disable_cmds(void); /** * struct event_trigger_ops - callbacks for trace event triggers * * The methods in this structure provide per-event trigger hooks for * various trigger operations. * * All the methods below, except for @init() and @free(), must be * implemented. * * @func: The trigger 'probe' function called when the triggering * event occurs. The data passed into this callback is the data * that was supplied to the event_command @reg() function that * registered the trigger (see struct event_command) along with * the trace record, rec. * * @init: An optional initialization function called for the trigger * when the trigger is registered (via the event_command reg() * function). This can be used to perform per-trigger * initialization such as incrementing a per-trigger reference * count, for instance. This is usually implemented by the * generic utility function @event_trigger_init() (see * trace_event_triggers.c). * * @free: An optional de-initialization function called for the * trigger when the trigger is unregistered (via the * event_command @reg() function). This can be used to perform * per-trigger de-initialization such as decrementing a * per-trigger reference count and freeing corresponding trigger * data, for instance. This is usually implemented by the * generic utility function @event_trigger_free() (see * trace_event_triggers.c). * * @print: The callback function invoked to have the trigger print * itself. This is usually implemented by a wrapper function * that calls the generic utility function @event_trigger_print() * (see trace_event_triggers.c). */ struct event_trigger_ops { void (*func)(struct event_trigger_data *data, void *rec, struct ring_buffer_event *rbe); int (*init)(struct event_trigger_ops *ops, struct event_trigger_data *data); void (*free)(struct event_trigger_ops *ops, struct event_trigger_data *data); int (*print)(struct seq_file *m, struct event_trigger_ops *ops, struct event_trigger_data *data); }; /** * struct event_command - callbacks and data members for event commands * * Event commands are invoked by users by writing the command name * into the 'trigger' file associated with a trace event. The * parameters associated with a specific invocation of an event * command are used to create an event trigger instance, which is * added to the list of trigger instances associated with that trace * event. When the event is hit, the set of triggers associated with * that event is invoked. * * The data members in this structure provide per-event command data * for various event commands. * * All the data members below, except for @post_trigger, must be set * for each event command. * * @name: The unique name that identifies the event command. This is * the name used when setting triggers via trigger files. * * @trigger_type: A unique id that identifies the event command * 'type'. This value has two purposes, the first to ensure that * only one trigger of the same type can be set at a given time * for a particular event e.g. it doesn't make sense to have both * a traceon and traceoff trigger attached to a single event at * the same time, so traceon and traceoff have the same type * though they have different names. The @trigger_type value is * also used as a bit value for deferring the actual trigger * action until after the current event is finished. Some * commands need to do this if they themselves log to the trace * buffer (see the @post_trigger() member below). @trigger_type * values are defined by adding new values to the trigger_type * enum in include/linux/trace_events.h. * * @flags: See the enum event_command_flags below. * * All the methods below, except for @set_filter() and @unreg_all(), * must be implemented. * * @func: The callback function responsible for parsing and * registering the trigger written to the 'trigger' file by the * user. It allocates the trigger instance and registers it with * the appropriate trace event. It makes use of the other * event_command callback functions to orchestrate this, and is * usually implemented by the generic utility function * @event_trigger_callback() (see trace_event_triggers.c). * * @reg: Adds the trigger to the list of triggers associated with the * event, and enables the event trigger itself, after * initializing it (via the event_trigger_ops @init() function). * This is also where commands can use the @trigger_type value to * make the decision as to whether or not multiple instances of * the trigger should be allowed. This is usually implemented by * the generic utility function @register_trigger() (see * trace_event_triggers.c). * * @unreg: Removes the trigger from the list of triggers associated * with the event, and disables the event trigger itself, after * initializing it (via the event_trigger_ops @free() function). * This is usually implemented by the generic utility function * @unregister_trigger() (see trace_event_triggers.c). * * @unreg_all: An optional function called to remove all the triggers * from the list of triggers associated with the event. Called * when a trigger file is opened in truncate mode. * * @set_filter: An optional function called to parse and set a filter * for the trigger. If no @set_filter() method is set for the * event command, filters set by the user for the command will be * ignored. This is usually implemented by the generic utility * function @set_trigger_filter() (see trace_event_triggers.c). * * @get_trigger_ops: The callback function invoked to retrieve the * event_trigger_ops implementation associated with the command. */ struct event_command { struct list_head list; char *name; enum event_trigger_type trigger_type; int flags; int (*func)(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *params); int (*reg)(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); void (*unreg)(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); void (*unreg_all)(struct trace_event_file *file); int (*set_filter)(char *filter_str, struct event_trigger_data *data, struct trace_event_file *file); struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param); }; /** * enum event_command_flags - flags for struct event_command * * @POST_TRIGGER: A flag that says whether or not this command needs * to have its action delayed until after the current event has * been closed. Some triggers need to avoid being invoked while * an event is currently in the process of being logged, since * the trigger may itself log data into the trace buffer. Thus * we make sure the current event is committed before invoking * those triggers. To do that, the trigger invocation is split * in two - the first part checks the filter using the current * trace record; if a command has the @post_trigger flag set, it * sets a bit for itself in the return value, otherwise it * directly invokes the trigger. Once all commands have been * either invoked or set their return flag, the current record is * either committed or discarded. At that point, if any commands * have deferred their triggers, those commands are finally * invoked following the close of the current event. In other * words, if the event_trigger_ops @func() probe implementation * itself logs to the trace buffer, this flag should be set, * otherwise it can be left unspecified. * * @NEEDS_REC: A flag that says whether or not this command needs * access to the trace record in order to perform its function, * regardless of whether or not it has a filter associated with * it (filters make a trigger require access to the trace record * but are not always present). */ enum event_command_flags { EVENT_CMD_FL_POST_TRIGGER = 1, EVENT_CMD_FL_NEEDS_REC = 2, }; static inline bool event_command_post_trigger(struct event_command *cmd_ops) { return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER; } static inline bool event_command_needs_rec(struct event_command *cmd_ops) { return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC; } extern int trace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable); extern int tracing_alloc_snapshot(void); extern void tracing_snapshot_cond(struct trace_array *tr, void *cond_data); extern int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update); extern int tracing_snapshot_cond_disable(struct trace_array *tr); extern void *tracing_cond_snapshot_data(struct trace_array *tr); extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; extern const char *__start___tracepoint_str[]; extern const char *__stop___tracepoint_str[]; void trace_printk_control(bool enabled); void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); /* Used from boot time tracer */ extern int trace_set_options(struct trace_array *tr, char *option); extern int tracing_set_tracer(struct trace_array *tr, const char *buf); extern ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id); extern int tracing_set_cpumask(struct trace_array *tr, cpumask_var_t tracing_cpumask_new); #define MAX_EVENT_NAME_LEN 64 extern int trace_run_command(const char *buf, int (*createfn)(int, char**)); extern ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, size_t count, loff_t *ppos, int (*createfn)(int, char**)); extern unsigned int err_pos(char *cmd, const char *str); extern void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, const char **errs, u8 type, u8 pos); /* * Normal trace_printk() and friends allocates special buffers * to do the manipulation, as well as saves the print formats * into sections to display. But the trace infrastructure wants * to use these without the added overhead at the price of being * a bit slower (used mainly for warnings, where we don't care * about performance). The internal_trace_puts() is for such * a purpose. */ #define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct trace_event_call \ __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED #define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER) int perf_ftrace_event_register(struct trace_event_call *call, enum trace_reg type, void *data); #else #define perf_ftrace_event_register NULL #endif #ifdef CONFIG_FTRACE_SYSCALLS void init_ftrace_syscalls(void); const char *get_syscall_name(int syscall); #else static inline void init_ftrace_syscalls(void) { } static inline const char *get_syscall_name(int syscall) { return NULL; } #endif #ifdef CONFIG_EVENT_TRACING void trace_event_init(void); void trace_event_eval_update(struct trace_eval_map **map, int len); /* Used from boot time tracer */ extern int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set); extern int trigger_process_regex(struct trace_event_file *file, char *buff); #else static inline void __init trace_event_init(void) { } static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { } #endif #ifdef CONFIG_TRACER_SNAPSHOT void tracing_snapshot_instance(struct trace_array *tr); int tracing_alloc_snapshot_instance(struct trace_array *tr); #else static inline void tracing_snapshot_instance(struct trace_array *tr) { } static inline int tracing_alloc_snapshot_instance(struct trace_array *tr) { return 0; } #endif #ifdef CONFIG_PREEMPT_TRACER void tracer_preempt_on(unsigned long a0, unsigned long a1); void tracer_preempt_off(unsigned long a0, unsigned long a1); #else static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { } static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { } #endif #ifdef CONFIG_IRQSOFF_TRACER void tracer_hardirqs_on(unsigned long a0, unsigned long a1); void tracer_hardirqs_off(unsigned long a0, unsigned long a1); #else static inline void tracer_hardirqs_on(unsigned long a0, unsigned long a1) { } static inline void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { } #endif extern struct trace_iterator *tracepoint_print_iter; /* * Reset the state of the trace_iterator so that it can read consumed data. * Normally, the trace_iterator is used for reading the data when it is not * consumed, and must retain state. */ static __always_inline void trace_iterator_reset(struct trace_iterator *iter) { const size_t offset = offsetof(struct trace_iterator, seq); /* * Keep gcc from complaining about overwriting more than just one * member in the structure. */ memset((char *)iter + offset, 0, sizeof(struct trace_iterator) - offset); iter->pos = -1; } /* Check the name is good for event/group/fields */ static inline bool is_good_name(const char *name) { if (!isalpha(*name) && *name != '_') return false; while (*++name != '\0') { if (!isalpha(*name) && !isdigit(*name) && *name != '_') return false; } return true; } #endif /* _LINUX_KERNEL_TRACE_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name, root->name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, id ) __field( int, level ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); ), TP_printk("root=%d id=%d level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_id ) __field( int, dst_level ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path, path); __entry->pid = task->pid; __assign_str(comm, task->comm); ), TP_printk("dst_root=%d dst_id=%d dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, id ) __field( int, level ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); __entry->val = val; ), TP_printk("root=%d id=%d level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* * Flags to use when allocating a user page table page. */ extern gfp_t __userpte_alloc_gfp; #ifdef CONFIG_PAGE_TABLE_ISOLATION /* * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 * in a pointer to swap between the two 4k halves. */ #define PGD_ALLOCATION_ORDER 1 #else #define PGD_ALLOCATION_ORDER 0 #endif /* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pgtable_t pte_alloc_one(struct mm_struct *); extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, unsigned long address) { ___pte_free_tlb(tlb, pte); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate_kernel_safe(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { unsigned long pfn = page_to_pfn(pte); paravirt_alloc_pte(mm, pfn); set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } #define pmd_pgtable(pmd) pmd_page(pmd) #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { ___pmd_free_tlb(tlb, pmd); } #ifdef CONFIG_X86_PAE extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); #else /* !CONFIG_X86_PAE */ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); } #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { ___pud_free_tlb(tlb, pud); } #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; return (p4d_t *)get_zeroed_page(gfp); } static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); free_page((unsigned long)p4d); } extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { if (pgtable_l5_enabled()) ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_DST_CACHE_H #define _NET_DST_CACHE_H #include <linux/jiffies.h> #include <net/dst.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_fib.h> #endif struct dst_cache { struct dst_cache_pcpu __percpu *cache; unsigned long reset_ts; }; /** * dst_cache_get - perform cache lookup * @dst_cache: the cache * * The caller should use dst_cache_get_ip4() if it need to retrieve the * source address to be used when xmitting to the cached dst. * local BH must be disabled. */ struct dst_entry *dst_cache_get(struct dst_cache *dst_cache); /** * dst_cache_get_ip4 - perform cache lookup and fetch ipv4 source address * @dst_cache: the cache * @saddr: return value for the retrieved source address * * local BH must be disabled. */ struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr); /** * dst_cache_set_ip4 - store the ipv4 dst into the cache * @dst_cache: the cache * @dst: the entry to be cached * @saddr: the source address to be stored inside the cache * * local BH must be disabled. */ void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, __be32 saddr); #if IS_ENABLED(CONFIG_IPV6) /** * dst_cache_set_ip6 - store the ipv6 dst into the cache * @dst_cache: the cache * @dst: the entry to be cached * @saddr: the source address to be stored inside the cache * * local BH must be disabled. */ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, const struct in6_addr *saddr); /** * dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address * @dst_cache: the cache * @saddr: return value for the retrieved source address * * local BH must be disabled. */ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, struct in6_addr *saddr); #endif /** * dst_cache_reset - invalidate the cache contents * @dst_cache: the cache * * This does not free the cached dst to avoid races and contentions. * the dst will be freed on later cache lookup. */ static inline void dst_cache_reset(struct dst_cache *dst_cache) { dst_cache->reset_ts = jiffies; } /** * dst_cache_reset_now - invalidate the cache contents immediately * @dst_cache: the cache * * The caller must be sure there are no concurrent users, as this frees * all dst_cache users immediately, rather than waiting for the next * per-cpu usage like dst_cache_reset does. Most callers should use the * higher speed lazily-freed dst_cache_reset function instead. */ void dst_cache_reset_now(struct dst_cache *dst_cache); /** * dst_cache_init - initialize the cache, allocating the required storage * @dst_cache: the cache * @gfp: allocation flags */ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); /** * dst_cache_destroy - empty the cache and free the allocated storage * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache * is unsed. */ void dst_cache_destroy(struct dst_cache *dst_cache); #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