1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the extensible bitmap type. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support to import/export the NetLabel category bitmap * * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 */ /* * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * Applied standard bit operations to improve bitmap scanning. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jhash.h> #include <net/netlabel.h> #include "ebitmap.h" #include "policydb.h" #define BITS_PER_U64 (sizeof(u64) * 8) static struct kmem_cache *ebitmap_node_cachep; int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2) { struct ebitmap_node *n1, *n2; if (e1->highbit != e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit == n2->startbit) && !memcmp(n1->maps, n2->maps, EBITMAP_SIZE / 8)) { n1 = n1->next; n2 = n2->next; } if (n1 || n2) return 0; return 1; } int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src) { struct ebitmap_node *n, *new, *prev; ebitmap_init(dst); n = src->node; prev = NULL; while (n) { new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) { ebitmap_destroy(dst); return -ENOMEM; } new->startbit = n->startbit; memcpy(new->maps, n->maps, EBITMAP_SIZE / 8); new->next = NULL; if (prev) prev->next = new; else dst->node = new; prev = new; n = n->next; } dst->highbit = src->highbit; return 0; } int ebitmap_and(struct ebitmap *dst, struct ebitmap *e1, struct ebitmap *e2) { struct ebitmap_node *n; int bit, rc; ebitmap_init(dst); ebitmap_for_each_positive_bit(e1, n, bit) { if (ebitmap_get_bit(e2, bit)) { rc = ebitmap_set_bit(dst, bit, 1); if (rc < 0) return rc; } } return 0; } #ifdef CONFIG_NETLABEL /** * ebitmap_netlbl_export - Export an ebitmap into a NetLabel category bitmap * @ebmap: the ebitmap to export * @catmap: the NetLabel category bitmap * * Description: * Export a SELinux extensibile bitmap into a NetLabel category bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { struct ebitmap_node *e_iter = ebmap->node; unsigned long e_map; u32 offset; unsigned int iter; int rc; if (e_iter == NULL) { *catmap = NULL; return 0; } if (*catmap != NULL) netlbl_catmap_free(*catmap); *catmap = NULL; while (e_iter) { offset = e_iter->startbit; for (iter = 0; iter < EBITMAP_UNIT_NUMS; iter++) { e_map = e_iter->maps[iter]; if (e_map != 0) { rc = netlbl_catmap_setlong(catmap, offset, e_map, GFP_ATOMIC); if (rc != 0) goto netlbl_export_failure; } offset += EBITMAP_UNIT_SIZE; } e_iter = e_iter->next; } return 0; netlbl_export_failure: netlbl_catmap_free(*catmap); return -ENOMEM; } /** * ebitmap_netlbl_import - Import a NetLabel category bitmap into an ebitmap * @ebmap: the ebitmap to import * @catmap: the NetLabel category bitmap * * Description: * Import a NetLabel category bitmap into a SELinux extensibile bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { int rc; struct ebitmap_node *e_iter = NULL; struct ebitmap_node *e_prev = NULL; u32 offset = 0, idx; unsigned long bitmap; for (;;) { rc = netlbl_catmap_getlong(catmap, &offset, &bitmap); if (rc < 0) goto netlbl_import_failure; if (offset == (u32)-1) return 0; /* don't waste ebitmap space if the netlabel bitmap is empty */ if (bitmap == 0) { offset += EBITMAP_UNIT_SIZE; continue; } if (e_iter == NULL || offset >= e_iter->startbit + EBITMAP_SIZE) { e_prev = e_iter; e_iter = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (e_iter == NULL) goto netlbl_import_failure; e_iter->startbit = offset - (offset % EBITMAP_SIZE); if (e_prev == NULL) ebmap->node = e_iter; else e_prev->next = e_iter; ebmap->highbit = e_iter->startbit + EBITMAP_SIZE; } /* offset will always be aligned to an unsigned long */ idx = EBITMAP_NODE_INDEX(e_iter, offset); e_iter->maps[idx] = bitmap; /* next */ offset += EBITMAP_UNIT_SIZE; } /* NOTE: we should never reach this return */ return 0; netlbl_import_failure: ebitmap_destroy(ebmap); return -ENOMEM; } #endif /* CONFIG_NETLABEL */ /* * Check to see if all the bits set in e2 are also set in e1. Optionally, * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed * last_e2bit. */ int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit) { struct ebitmap_node *n1, *n2; int i; if (e1->highbit < e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit <= n2->startbit)) { if (n1->startbit < n2->startbit) { n1 = n1->next; continue; } for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i]; ) i--; /* Skip trailing NULL map entries */ if (last_e2bit && (i >= 0)) { u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE + __fls(n2->maps[i]); if (lastsetbit > last_e2bit) return 0; } while (i >= 0) { if ((n1->maps[i] & n2->maps[i]) != n2->maps[i]) return 0; i--; } n1 = n1->next; n2 = n2->next; } if (n2) return 0; return 1; } int ebitmap_get_bit(struct ebitmap *e, unsigned long bit) { struct ebitmap_node *n; if (e->highbit < bit) return 0; n = e->node; while (n && (n->startbit <= bit)) { if ((n->startbit + EBITMAP_SIZE) > bit) return ebitmap_node_get_bit(n, bit); n = n->next; } return 0; } int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value) { struct ebitmap_node *n, *prev, *new; prev = NULL; n = e->node; while (n && n->startbit <= bit) { if ((n->startbit + EBITMAP_SIZE) > bit) { if (value) { ebitmap_node_set_bit(n, bit); } else { unsigned int s; ebitmap_node_clr_bit(n, bit); s = find_first_bit(n->maps, EBITMAP_SIZE); if (s < EBITMAP_SIZE) return 0; /* drop this node from the bitmap */ if (!n->next) { /* * this was the highest map * within the bitmap */ if (prev) e->highbit = prev->startbit + EBITMAP_SIZE; else e->highbit = 0; } if (prev) prev->next = n->next; else e->node = n->next; kmem_cache_free(ebitmap_node_cachep, n); } return 0; } prev = n; n = n->next; } if (!value) return 0; new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) return -ENOMEM; new->startbit = bit - (bit % EBITMAP_SIZE); ebitmap_node_set_bit(new, bit); if (!n) /* this node will be the highest map within the bitmap */ e->highbit = new->startbit + EBITMAP_SIZE; if (prev) { new->next = prev->next; prev->next = new; } else { new->next = e->node; e->node = new; } return 0; } void ebitmap_destroy(struct ebitmap *e) { struct ebitmap_node *n, *temp; if (!e) return; n = e->node; while (n) { temp = n; n = n->next; kmem_cache_free(ebitmap_node_cachep, temp); } e->highbit = 0; e->node = NULL; return; } int ebitmap_read(struct ebitmap *e, void *fp) { struct ebitmap_node *n = NULL; u32 mapunit, count, startbit, index; __le32 ebitmap_start; u64 map; __le64 mapbits; __le32 buf[3]; int rc, i; ebitmap_init(e); rc = next_entry(buf, fp, sizeof buf); if (rc < 0) goto out; mapunit = le32_to_cpu(buf[0]); e->highbit = le32_to_cpu(buf[1]); count = le32_to_cpu(buf[2]); if (mapunit != BITS_PER_U64) { pr_err("SELinux: ebitmap: map size %u does not " "match my size %zd (high bit was %d)\n", mapunit, BITS_PER_U64, e->highbit); goto bad; } /* round up e->highbit */ e->highbit += EBITMAP_SIZE - 1; e->highbit -= (e->highbit % EBITMAP_SIZE); if (!e->highbit) { e->node = NULL; goto ok; } if (e->highbit && !count) goto bad; for (i = 0; i < count; i++) { rc = next_entry(&ebitmap_start, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } startbit = le32_to_cpu(ebitmap_start); if (startbit & (mapunit - 1)) { pr_err("SELinux: ebitmap start bit (%d) is " "not a multiple of the map unit size (%u)\n", startbit, mapunit); goto bad; } if (startbit > e->highbit - mapunit) { pr_err("SELinux: ebitmap start bit (%d) is " "beyond the end of the bitmap (%u)\n", startbit, (e->highbit - mapunit)); goto bad; } if (!n || startbit >= n->startbit + EBITMAP_SIZE) { struct ebitmap_node *tmp; tmp = kmem_cache_zalloc(ebitmap_node_cachep, GFP_KERNEL); if (!tmp) { pr_err("SELinux: ebitmap: out of memory\n"); rc = -ENOMEM; goto bad; } /* round down */ tmp->startbit = startbit - (startbit % EBITMAP_SIZE); if (n) n->next = tmp; else e->node = tmp; n = tmp; } else if (startbit <= n->startbit) { pr_err("SELinux: ebitmap: start bit %d" " comes after start bit %d\n", startbit, n->startbit); goto bad; } rc = next_entry(&mapbits, fp, sizeof(u64)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } map = le64_to_cpu(mapbits); index = (startbit - n->startbit) / EBITMAP_UNIT_SIZE; while (map) { n->maps[index++] = map & (-1UL); map = EBITMAP_SHIFT_UNIT_SIZE(map); } } ok: rc = 0; out: return rc; bad: if (!rc) rc = -EINVAL; ebitmap_destroy(e); goto out; } int ebitmap_write(struct ebitmap *e, void *fp) { struct ebitmap_node *n; u32 count; __le32 buf[3]; u64 map; int bit, last_bit, last_startbit, rc; buf[0] = cpu_to_le32(BITS_PER_U64); count = 0; last_bit = 0; last_startbit = -1; ebitmap_for_each_positive_bit(e, n, bit) { if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) { count++; last_startbit = rounddown(bit, BITS_PER_U64); } last_bit = roundup(bit + 1, BITS_PER_U64); } buf[1] = cpu_to_le32(last_bit); buf[2] = cpu_to_le32(count); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; map = 0; last_startbit = INT_MIN; ebitmap_for_each_positive_bit(e, n, bit) { if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) { __le64 buf64[1]; /* this is the very first bit */ if (!map) { last_startbit = rounddown(bit, BITS_PER_U64); map = (u64)1 << (bit - last_startbit); continue; } /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; /* set up for the next node */ map = 0; last_startbit = rounddown(bit, BITS_PER_U64); } map |= (u64)1 << (bit - last_startbit); } /* write the last node */ if (map) { __le64 buf64[1]; /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; } return 0; } u32 ebitmap_hash(const struct ebitmap *e, u32 hash) { struct ebitmap_node *node; /* need to change hash even if ebitmap is empty */ hash = jhash_1word(e->highbit, hash); for (node = e->node; node; node = node->next) { hash = jhash_1word(node->startbit, hash); hash = jhash(node->maps, sizeof(node->maps), hash); } return hash; } void __init ebitmap_cache_init(void) { ebitmap_node_cachep = kmem_cache_create("ebitmap_node", sizeof(struct ebitmap_node), 0, SLAB_PANIC, NULL); }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H #include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); /** * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @pgprot: page protection to use * @write: whether it's a write fault * * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) { return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); } vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); /** * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @pgprot: page protection to use * @write: whether it's a write fault * * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) { return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); } enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_NEVER_DAX, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif }; struct kobject; struct kobj_attribute; ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) #define HPAGE_PUD_SHIFT PUD_SHIFT #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) extern unsigned long transparent_hugepage_flags; static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR)) return false; } if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, unsigned long vm_flags) { /* Explicitly disabled through madvise. */ if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; return true; } /* * to be used on vmas which are known to support THP. * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { /* * If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (vma_is_temporary_stack(vma)) return false; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; if (vma_is_dax(vma)) return true; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) return !!(vma->vm_flags & VM_HUGEPAGE); return false; } bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ } while (0) void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ if (pud_trans_huge(*____pud) \ || pud_devmap(*____pud)) \ __split_huge_pud(__vma, __pud, __address); \ } while (0) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { return !pmd_none(pmd) && !pmd_present(pmd); } /* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } /** * thp_head - Head page of a transparent huge page. * @page: Any page (tail, head or regular) found in the page cache. */ static inline struct page *thp_head(struct page *page) { return compound_head(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_ORDER; return 0; } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline int thp_nr_pages(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_NR; return 1; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_page(struct page *page) { return READ_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); } static inline bool is_huge_zero_pud(pud_t pud) { return false; } struct page *mm_get_huge_zero_page(struct mm_struct *mm); void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } static inline struct list_head *page_deferred_list(struct page *page) { /* * Global or memcg deferred list in the second tail pages is * occupied by compound_head. */ return &page[2].deferred_list; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) static inline struct page *thp_head(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return page; } static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 0; } static inline int thp_nr_pages(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 1; } static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; } static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { return false; } static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, unsigned long vm_flags) { return false; } static inline void prep_transhuge_page(struct page *page) {} static inline bool is_transparent_hugepage(struct page *page) { return false; } #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool can_split_huge_page(struct page *page, int *pextra_pins) { BUILD_BUG(); return false; } static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { return 0; } static inline int split_huge_page(struct page *page) { return 0; } static inline void deferred_split_huge_page(struct page *page) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { BUG(); return 0; } static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { } static inline int is_swap_pmd(pmd_t pmd) { return 0; } static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { return NULL; } static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd) { return 0; } static inline bool is_huge_zero_page(struct page *page) { return false; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return false; } static inline bool is_huge_zero_pud(pud_t pud) { return false; } static inline void mm_put_huge_zero_page(struct mm_struct *mm) { return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline bool thp_migration_supported(void) { return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #endif /* _LINUX_HUGE_MM_H */
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> #ifdef CONFIG_SET_FS /* * Force the uaccess routines to be wired up for actual userspace access, * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone * using force_uaccess_end below. */ static inline mm_segment_t force_uaccess_begin(void) { mm_segment_t fs = get_fs(); set_fs(USER_DS); return fs; } static inline void force_uaccess_end(mm_segment_t oldfs) { set_fs(oldfs); } #else /* CONFIG_SET_FS */ typedef struct { /* empty dummy */ } mm_segment_t; #ifndef TASK_SIZE_MAX #define TASK_SIZE_MAX TASK_SIZE #endif #define uaccess_kernel() (false) #define user_addr_max() (TASK_SIZE_MAX) static inline mm_segment_t force_uaccess_begin(void) { return (mm_segment_t) { }; } static inline void force_uaccess_end(mm_segment_t oldfs) { } #endif /* CONFIG_SET_FS */ /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } #ifdef INLINE_COPY_FROM_USER static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } #else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (likely(check_copy_size(to, n, false))) n = _copy_from_user(to, from, n); return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (likely(check_copy_size(from, n, true))) n = _copy_to_user(to, from, n); return n; } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(to, n) && access_ok(from, n)) n = raw_copy_in_user(to, from, n); return n; } #endif #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 // SPDX-License-Identifier: GPL-2.0-or-later /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/minmax.h> #if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ !defined(find_next_and_bit) /* * This is a common helper function for find_next_bit, find_next_zero_bit, and * find_next_and_bit. The differences are: * - The "invert" argument, which is XORed with each fetched word before * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ static unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { unsigned long tmp, mask; if (unlikely(start >= nbits)) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; /* Handle 1st word. */ mask = BITMAP_FIRST_WORD_MASK(start); if (le) mask = swab(mask); tmp &= mask; start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; } if (le) tmp = swab(tmp); return min(start + __ffs(tmp), nbits); } #endif #ifndef find_next_bit /* * Find the next set bit in a memory region. */ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_bit); #endif #ifndef find_next_zero_bit unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } EXPORT_SYMBOL(find_next_zero_bit); #endif #if !defined(find_next_and_bit) unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_and_bit); #endif #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx]) return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx] != ~0UL) return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_zero_bit); #endif #ifndef find_last_bit unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(find_last_bit); #endif #ifdef __BIG_ENDIAN #ifndef find_next_zero_bit_le unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif #ifndef find_next_bit_le unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 1); } EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { offset = find_next_bit(addr, size, offset); if (offset == size) return size; offset = round_down(offset, 8); *clump = bitmap_get_value8(addr, offset); return offset; } EXPORT_SYMBOL(find_next_clump8);
1 1 1 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 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/dir.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linus Torvalds * * ext4 directory handling functions * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * * Hash Tree Directory indexing (c) 2001 Daniel Phillips * */ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/iversion.h> #include <linux/unicode.h> #include "ext4.h" #include "xattr.h" static int ext4_dx_readdir(struct file *, struct dir_context *); /** * is_dx_dir() - check if a directory is using htree indexing * @inode: directory inode * * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which could potentially get converted to use htree * indexing). * * Return 1 if it is a dx dir, 0 if not */ static int is_dx_dir(struct inode *inode) { struct super_block *sb = inode->i_sb; if (ext4_has_feature_dir_index(inode->i_sb) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || ((inode->i_size >> sb->s_blocksize_bits) == 1) || ext4_has_inline_data(inode))) return 1; return 0; } /* * Return 0 if the directory entry is OK, and 1 if there is a problem * * Note: this is the opposite of what ext2 and ext3 historically returned... * * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. */ int __ext4_check_dir_entry(const char *function, unsigned int line, struct inode *dir, struct file *filp, struct ext4_dir_entry_2 *de, struct buffer_head *bh, char *buf, int size, unsigned int offset) { const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); const int next_offset = ((char *) de - buf) + rlen; if (unlikely(rlen < EXT4_DIR_REC_LEN(1))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; else if (unlikely(next_offset > size - EXT4_DIR_REC_LEN(1) && next_offset != size)) error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; else return 0; if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, name_len=%d, size=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, de->name_len, size); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, name_len=%d, size=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, de->name_len, size); return 1; } static int ext4_readdir(struct file *file, struct dir_context *ctx) { unsigned int offset; int i; struct ext4_dir_entry_2 *de; int err; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); if (IS_ENCRYPTED(inode)) { err = fscrypt_get_encryption_info(inode); if (err) return err; } if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) { return err; } /* Can we just clear INDEX flag to ignore htree information? */ if (!ext4_has_metadata_csum(sb)) { /* * We don't set the inode dirty flag since it's not * critical that it gets flushed back to the disk. */ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } } if (ext4_has_inline_data(inode)) { int has_inline_data = 1; err = ext4_read_inline_dir(file, ctx, &has_inline_data); if (has_inline_data) return err; } if (IS_ENCRYPTED(inode)) { err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr); if (err < 0) return err; } while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto errout; } cond_resched(); offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); if (err == 0) { /* m_len should never be zero but let's avoid * an infinite loop if it somehow is */ if (map.m_len == 0) map.m_len = 1; ctx->pos += map.m_len * sb->s_blocksize; continue; } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); if (!ra_has_index(&file->f_ra, index)) page_cache_sync_readahead( sb->s_bdev->bd_inode->i_mapping, &file->f_ra, file, index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; goto errout; } } if (!bh) { /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; ctx->pos += sb->s_blocksize - offset; continue; } /* Check the checksum */ if (!buffer_verified(bh) && !ext4_dirblock_csum_verify(inode, bh)) { EXT4_ERROR_FILE(file, 0, "directory fails checksum " "at offset %llu", (unsigned long long)ctx->pos); ctx->pos += sb->s_blocksize - offset; brelse(bh); bh = NULL; continue; } set_buffer_verified(bh); /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ if (!inode_eq_iversion(inode, file->f_version)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ext4_dir_entry_2 *) (bh->b_data + i); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) < EXT4_DIR_REC_LEN(1)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } offset = i; ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) | offset; file->f_version = inode_query_iversion(inode); } while (ctx->pos < inode->i_size && offset < sb->s_blocksize) { de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); if (ext4_check_dir_entry(inode, file, de, bh, bh->b_data, bh->b_size, offset)) { /* * On error, skip to the next block */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; break; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); if (le32_to_cpu(de->inode)) { if (!IS_ENCRYPTED(inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } else { int save_len = fstr.len; struct fscrypt_str de_name = FSTR_INIT(de->name, de->name_len); /* Directory is encrypted */ err = fscrypt_fname_disk_to_usr(inode, 0, 0, &de_name, &fstr); de_name = fstr; fstr.len = save_len; if (err) goto errout; if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } } ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode)) goto done; brelse(bh); bh = NULL; offset = 0; } done: err = 0; errout: fscrypt_fname_free_buffer(&fstr); brelse(bh); return err; } static inline int is_32bit_api(void) { #ifdef CONFIG_COMPAT return in_compat_syscall(); #else return (BITS_PER_LONG == 32); #endif } /* * These functions convert from the major/minor hash to an f_pos * value for dx directories * * Upper layer (for example NFS) should specify FMODE_32BITHASH or * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted * directly on both 32-bit and 64-bit nodes, under such case, neither * FMODE_32BITHASH nor FMODE_64BITHASH is specified. */ static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return major >> 1; else return ((__u64)(major >> 1) << 32) | (__u64)minor; } static inline __u32 pos2maj_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return (pos << 1) & 0xffffffff; else return ((pos >> 32) << 1) & 0xffffffff; } static inline __u32 pos2min_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return 0; else return pos & 0xffffffff; } /* * Return 32- or 64-bit end-of-file for dx directories */ static inline loff_t ext4_get_htree_eof(struct file *filp) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return EXT4_HTREE_EOF_32BIT; else return EXT4_HTREE_EOF_64BIT; } /* * ext4_dir_llseek() calls generic_file_llseek_size to handle htree * directories, where the "offset" is in terms of the filename hash * value instead of the byte offset. * * Because we may return a 64-bit hash that is well beyond offset limits, * we need to pass the max hash as the maximum allowable offset in * the htree directory case. * * For non-htree, ext4_llseek already chooses the proper max offset. */ static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; int dx_dir = is_dx_dir(inode); loff_t ret, htree_max = ext4_get_htree_eof(file); if (likely(dx_dir)) ret = generic_file_llseek_size(file, offset, whence, htree_max, htree_max); else ret = ext4_llseek(file, offset, whence); file->f_version = inode_peek_iversion(inode) - 1; return ret; } /* * This structure holds the nodes of the red-black tree used to store * the directory entry in hash order. */ struct fname { __u32 hash; __u32 minor_hash; struct rb_node rb_hash; struct fname *next; __u32 inode; __u8 name_len; __u8 file_type; char name[]; }; /* * This functoin implements a non-recursive way of freeing all of the * nodes in the red-black tree. */ static void free_rb_tree_fname(struct rb_root *root) { struct fname *fname, *next; rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash) while (fname) { struct fname *old = fname; fname = fname->next; kfree(old); } *root = RB_ROOT; } static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp, loff_t pos) { struct dir_private_info *p; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return NULL; p->curr_hash = pos2maj_hash(filp, pos); p->curr_minor_hash = pos2min_hash(filp, pos); return p; } void ext4_htree_free_dir_info(struct dir_private_info *p) { free_rb_tree_fname(&p->root); kfree(p); } /* * Given a directory entry, enter it into the fname rb tree. * * When filename encryption is enabled, the dirent will hold the * encrypted filename, while the htree will hold decrypted filename. * The decrypted filename is passed in via ent_name. parameter. */ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name) { struct rb_node **p, *parent = NULL; struct fname *fname, *new_fn; struct dir_private_info *info; int len; info = dir_file->private_data; p = &info->root.rb_node; /* Create and allocate the fname structure */ len = sizeof(struct fname) + ent_name->len + 1; new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; memcpy(new_fn->name, ent_name->name, ent_name->len); while (*p) { parent = *p; fname = rb_entry(parent, struct fname, rb_hash); /* * If the hash and minor hash match up, then we put * them on a linked list. This rarely happens... */ if ((new_fn->hash == fname->hash) && (new_fn->minor_hash == fname->minor_hash)) { new_fn->next = fname->next; fname->next = new_fn; return 0; } if (new_fn->hash < fname->hash) p = &(*p)->rb_left; else if (new_fn->hash > fname->hash) p = &(*p)->rb_right; else if (new_fn->minor_hash < fname->minor_hash) p = &(*p)->rb_left; else /* if (new_fn->minor_hash > fname->minor_hash) */ p = &(*p)->rb_right; } rb_link_node(&new_fn->rb_hash, parent, p); rb_insert_color(&new_fn->rb_hash, &info->root); return 0; } /* * This is a helper function for ext4_dx_readdir. It calls filldir * for all entres on the fname linked list. (Normally there is only * one entry on the linked list, unless there are 62 bit hash collisions.) */ static int call_filldir(struct file *file, struct dir_context *ctx, struct fname *fname) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; if (!fname) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: " "called with null fname?!?", __func__, __LINE__, inode->i_ino, current->comm); return 0; } ctx->pos = hash2pos(file, fname->hash, fname->minor_hash); while (fname) { if (!dir_emit(ctx, fname->name, fname->name_len, fname->inode, get_dtype(sb, fname->file_type))) { info->extra_fname = fname; return 1; } fname = fname->next; } return 0; } static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); if (!info) return -ENOMEM; file->private_data = info; } if (ctx->pos == ext4_get_htree_eof(file)) return 0; /* EOF */ /* Some one has messed with f_pos; reset the world */ if (info->last_pos != ctx->pos) { free_rb_tree_fname(&info->root); info->curr_node = NULL; info->extra_fname = NULL; info->curr_hash = pos2maj_hash(file, ctx->pos); info->curr_minor_hash = pos2min_hash(file, ctx->pos); } /* * If there are any leftover names on the hash collision * chain, return them first. */ if (info->extra_fname) { if (call_filldir(file, ctx, info->extra_fname)) goto finished; info->extra_fname = NULL; goto next_node; } else if (!info->curr_node) info->curr_node = rb_first(&info->root); while (1) { /* * Fill the rbtree if we have no more entries, * or the inode has changed since we last read in the * cached entries. */ if ((!info->curr_node) || !inode_eq_iversion(inode, file->f_version)) { info->curr_node = NULL; free_rb_tree_fname(&info->root); file->f_version = inode_query_iversion(inode); ret = ext4_htree_fill_tree(file, info->curr_hash, info->curr_minor_hash, &info->next_hash); if (ret < 0) goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_node = rb_first(&info->root); } fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; if (call_filldir(file, ctx, fname)) break; next_node: info->curr_node = rb_next(info->curr_node); if (info->curr_node) { fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; } else { if (info->next_hash == ~0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_hash = info->next_hash; info->curr_minor_hash = 0; } } finished: info->last_pos = ctx->pos; return ret < 0 ? ret : 0; } static int ext4_dir_open(struct inode * inode, struct file * filp) { if (IS_ENCRYPTED(inode)) return fscrypt_get_encryption_info(inode) ? -EACCES : 0; return 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) { if (filp->private_data) ext4_htree_free_dir_info(filp->private_data); return 0; } int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size) { struct ext4_dir_entry_2 *de; int rlen; unsigned int offset = 0; char *top; de = (struct ext4_dir_entry_2 *)buf; top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) return -EFSCORRUPTED; rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } if ((char *) de > top) return -EFSCORRUPTED; return 0; } const struct file_operations ext4_dir_operations = { .llseek = ext4_dir_llseek, .read = generic_read_dir, .iterate_shared = ext4_readdir, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, #endif .fsync = ext4_sync_file, .open = ext4_dir_open, .release = ext4_release_dir, }; #ifdef CONFIG_UNICODE const struct dentry_operations ext4_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, }; #endif
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 // SPDX-License-Identifier: GPL-2.0 /* * blk-mq scheduling framework * * Copyright (C) 2016 Jens Axboe */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blk-mq.h> #include <linux/list_sort.h> #include <trace/events/block.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" #include "blk-mq-tag.h" #include "blk-wbt.h" void blk_mq_sched_assign_ioc(struct request *rq) { struct request_queue *q = rq->q; struct io_context *ioc; struct io_cq *icq; /* * May not have an IO context if it's a passthrough request */ ioc = current->io_context; if (!ioc) return; spin_lock_irq(&q->queue_lock); icq = ioc_lookup_icq(ioc, q); spin_unlock_irq(&q->queue_lock); if (!icq) { icq = ioc_create_icq(ioc, q, GFP_ATOMIC); if (!icq) return; } get_io_context(icq->ioc); rq->elv.icq = icq; } /* * Mark a hardware queue as needing a restart. For shared queues, maintain * a count of how many hardware queues are marked for restart. */ void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) { if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) return; set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } EXPORT_SYMBOL_GPL(blk_mq_sched_mark_restart_hctx); void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) { if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) return; clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); /* * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch) * in blk_mq_run_hw_queue(). Its pair is the barrier in * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART, * meantime new request added to hctx->dispatch is missed to check in * blk_mq_run_hw_queue(). */ smp_mb(); blk_mq_run_hw_queue(hctx, true); } static int sched_rq_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); return rqa->mq_hctx > rqb->mq_hctx; } static bool blk_mq_dispatch_hctx_list(struct list_head *rq_list) { struct blk_mq_hw_ctx *hctx = list_first_entry(rq_list, struct request, queuelist)->mq_hctx; struct request *rq; LIST_HEAD(hctx_list); unsigned int count = 0; list_for_each_entry(rq, rq_list, queuelist) { if (rq->mq_hctx != hctx) { list_cut_before(&hctx_list, rq_list, &rq->queuelist); goto dispatch; } count++; } list_splice_tail_init(rq_list, &hctx_list); dispatch: return blk_mq_dispatch_rq_list(hctx, &hctx_list, count); } #define BLK_MQ_BUDGET_DELAY 3 /* ms units */ /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. */ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; bool multi_hctxs = false, run_queue = false; bool dispatched = false, busy = false; unsigned int max_dispatch; LIST_HEAD(rq_list); int count = 0; if (hctx->dispatch_busy) max_dispatch = 1; else max_dispatch = hctx->queue->nr_requests; do { struct request *rq; if (e->type->ops.has_work && !e->type->ops.has_work(hctx)) break; if (!list_empty_careful(&hctx->dispatch)) { busy = true; break; } if (!blk_mq_get_dispatch_budget(q)) break; rq = e->type->ops.dispatch_request(hctx); if (!rq) { blk_mq_put_dispatch_budget(q); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the * same queue and if we didn't dispatch then there's * no guarantee anyone will kick the queue. Kick it * ourselves. */ run_queue = true; break; } /* * Now this rq owns the budget which has to be released * if this rq won't be queued to driver via .queue_rq() * in blk_mq_dispatch_rq_list(). */ list_add_tail(&rq->queuelist, &rq_list); if (rq->mq_hctx != hctx) multi_hctxs = true; } while (++count < max_dispatch); if (!count) { if (run_queue) blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); } else if (multi_hctxs) { /* * Requests from different hctx may be dequeued from some * schedulers, such as bfq and deadline. * * Sort the requests in the list according to their hctx, * dispatch batching requests from same hctx at a time. */ list_sort(NULL, &rq_list, sched_rq_cmp); do { dispatched |= blk_mq_dispatch_hctx_list(&rq_list); } while (!list_empty(&rq_list)); } else { dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, count); } if (busy) return -EAGAIN; return !!dispatched; } static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { int ret; do { ret = __blk_mq_do_dispatch_sched(hctx); } while (ret == 1); return ret; } static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { unsigned short idx = ctx->index_hw[hctx->type]; if (++idx == hctx->nr_ctx) idx = 0; return hctx->ctxs[idx]; } /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. */ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; LIST_HEAD(rq_list); struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from); int ret = 0; struct request *rq; do { if (!list_empty_careful(&hctx->dispatch)) { ret = -EAGAIN; break; } if (!sbitmap_any_bit_set(&hctx->ctx_map)) break; if (!blk_mq_get_dispatch_budget(q)) break; rq = blk_mq_dequeue_from_ctx(hctx, ctx); if (!rq) { blk_mq_put_dispatch_budget(q); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the * same queue and if we didn't dispatch then there's * no guarantee anyone will kick the queue. Kick it * ourselves. */ blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); break; } /* * Now this rq owns the budget which has to be released * if this rq won't be queued to driver via .queue_rq() * in blk_mq_dispatch_rq_list(). */ list_add(&rq->queuelist, &rq_list); /* round robin for fair dispatch */ ctx = blk_mq_next_ctx(hctx, rq->mq_ctx); } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, 1)); WRITE_ONCE(hctx->dispatch_from, ctx); return ret; } static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; const bool has_sched_dispatch = e && e->type->ops.dispatch_request; int ret = 0; LIST_HEAD(rq_list); /* * If we have previous entries on our dispatch list, grab them first for * more fair dispatch. */ if (!list_empty_careful(&hctx->dispatch)) { spin_lock(&hctx->lock); if (!list_empty(&hctx->dispatch)) list_splice_init(&hctx->dispatch, &rq_list); spin_unlock(&hctx->lock); } /* * Only ask the scheduler for requests, if we didn't have residual * requests from the dispatch list. This is to avoid the case where * we only ever dispatch a fraction of the requests available because * of low device queue depth. Once we pull requests out of the IO * scheduler, we can no longer merge or sort them. So it's best to * leave them there for as long as we can. Mark the hw queue as * needing a restart in that case. * * We want to dispatch from the scheduler if there was nothing * on the dispatch list or we were able to dispatch from the * dispatch list. */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); if (blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) { if (has_sched_dispatch) ret = blk_mq_do_dispatch_sched(hctx); else ret = blk_mq_do_dispatch_ctx(hctx); } } else if (has_sched_dispatch) { ret = blk_mq_do_dispatch_sched(hctx); } else if (hctx->dispatch_busy) { /* dequeue request one by one from sw queue if queue is busy */ ret = blk_mq_do_dispatch_ctx(hctx); } else { blk_mq_flush_busy_ctxs(hctx, &rq_list); blk_mq_dispatch_rq_list(hctx, &rq_list, 0); } return ret; } void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; /* RCU or SRCU read lock is needed before checking quiesced flag */ if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) return; hctx->run++; /* * A return of -EAGAIN is an indication that hctx->dispatch is not * empty and we must run again in order to avoid starving flushes. */ if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) { if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) blk_mq_run_hw_queue(hctx, true); } } bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; bool ret = false; enum hctx_type type; if (e && e->type->ops.bio_merge) return e->type->ops.bio_merge(q, bio, nr_segs); ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); type = hctx->type; if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) || list_empty_careful(&ctx->rq_lists[type])) return false; /* default per sw-queue merge */ spin_lock(&ctx->lock); /* * Reverse check our software queue for entries that we could * potentially merge with. Currently includes a hand-wavy stop * count of 8, to not spend too much time checking for merges. */ if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) { ctx->rq_merged++; ret = true; } spin_unlock(&ctx->lock); return ret; } bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq) { return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq); } EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge); void blk_mq_sched_request_inserted(struct request *rq) { trace_block_rq_insert(rq->q, rq); } EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted); static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, bool has_sched, struct request *rq) { /* * dispatch flush and passthrough rq directly * * passthrough request has to be added to hctx->dispatch directly. * For some reason, device may be in one situation which can't * handle FS request, so STS_RESOURCE is always returned and the * FS request will be added to hctx->dispatch. However passthrough * request may be required at that time for fixing the problem. If * passthrough request is added to scheduler queue, there isn't any * chance to dispatch it given we prioritize requests in hctx->dispatch. */ if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq)) return true; if (has_sched) rq->rq_flags |= RQF_SORTED; return false; } void blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue, bool async) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; WARN_ON(e && (rq->tag != BLK_MQ_NO_TAG)); if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) { /* * Firstly normal IO request is inserted to scheduler queue or * sw queue, meantime we add flush request to dispatch queue( * hctx->dispatch) directly and there is at most one in-flight * flush request for each hw queue, so it doesn't matter to add * flush request to tail or front of the dispatch queue. * * Secondly in case of NCQ, flush request belongs to non-NCQ * command, and queueing it will fail when there is any * in-flight normal IO request(NCQ command). When adding flush * rq to the front of hctx->dispatch, it is easier to introduce * extra time to flush rq's latency because of S_SCHED_RESTART * compared with adding to the tail of dispatch queue, then * chance of flush merge is increased, and less flush requests * will be issued to controller. It is observed that ~10% time * is saved in blktests block/004 on disk attached to AHCI/NCQ * drive when adding flush rq to the front of hctx->dispatch. * * Simply queue flush rq to the front of hctx->dispatch so that * intensive flush workloads can benefit in case of NCQ HW. */ at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head; blk_mq_request_bypass_insert(rq, at_head, false); goto run; } if (e && e->type->ops.insert_requests) { LIST_HEAD(list); list_add(&rq->queuelist, &list); e->type->ops.insert_requests(hctx, &list, at_head); } else { spin_lock(&ctx->lock); __blk_mq_insert_request(hctx, rq, at_head); spin_unlock(&ctx->lock); } run: if (run_queue) blk_mq_run_hw_queue(hctx, async); } void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list, bool run_queue_async) { struct elevator_queue *e; struct request_queue *q = hctx->queue; /* * blk_mq_sched_insert_requests() is called from flush plug * context only, and hold one usage counter to prevent queue * from being released. */ percpu_ref_get(&q->q_usage_counter); e = hctx->queue->elevator; if (e && e->type->ops.insert_requests) e->type->ops.insert_requests(hctx, list, false); else { /* * try to issue requests directly if the hw queue isn't * busy in case of 'none' scheduler, and this way may save * us one extra enqueue & dequeue to sw queue. */ if (!hctx->dispatch_busy && !e && !run_queue_async) { blk_mq_try_issue_list_directly(hctx, list); if (list_empty(list)) goto out; } blk_mq_insert_requests(hctx, ctx, list); } blk_mq_run_hw_queue(hctx, run_queue_async); out: percpu_ref_put(&q->q_usage_counter); } static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; if (hctx->sched_tags) { blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); blk_mq_free_rq_map(hctx->sched_tags, flags); hctx->sched_tags = NULL; } } static int blk_mq_sched_alloc_tags(struct request_queue *q, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { struct blk_mq_tag_set *set = q->tag_set; /* Clear HCTX_SHARED so tags are init'ed */ unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; int ret; hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, set->reserved_tags, flags); if (!hctx->sched_tags) return -ENOMEM; ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests); if (ret) blk_mq_sched_free_tags(set, hctx, hctx_idx); return ret; } /* called in queue's release handler, tagset has gone away */ static void blk_mq_sched_tags_teardown(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { /* Clear HCTX_SHARED so tags are freed */ unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; if (hctx->sched_tags) { blk_mq_free_rq_map(hctx->sched_tags, flags); hctx->sched_tags = NULL; } } } int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) { struct blk_mq_hw_ctx *hctx; struct elevator_queue *eq; unsigned int i; int ret; if (!e) { q->elevator = NULL; q->nr_requests = q->tag_set->queue_depth; return 0; } /* * Default to double of smaller one between hw queue_depth and 128, * since we don't split into sync/async like the old code did. * Additionally, this is a per-hw queue depth. */ q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth, BLKDEV_MAX_RQ); queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_sched_alloc_tags(q, hctx, i); if (ret) goto err; } ret = e->ops.init_sched(q, e); if (ret) goto err; blk_mq_debugfs_register_sched(q); queue_for_each_hw_ctx(q, hctx, i) { if (e->ops.init_hctx) { ret = e->ops.init_hctx(hctx, i); if (ret) { eq = q->elevator; blk_mq_sched_free_requests(q); blk_mq_exit_sched(q, eq); kobject_put(&eq->kobj); return ret; } } blk_mq_debugfs_register_sched_hctx(q, hctx); } return 0; err: blk_mq_sched_free_requests(q); blk_mq_sched_tags_teardown(q); q->elevator = NULL; return ret; } /* * called in either blk_queue_cleanup or elevator_switch, tagset * is required for freeing requests */ void blk_mq_sched_free_requests(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (hctx->sched_tags) blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i); } } void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) { blk_mq_debugfs_unregister_sched_hctx(hctx); if (e->type->ops.exit_hctx && hctx->sched_data) { e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; } } blk_mq_debugfs_unregister_sched(q); if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q); q->elevator = NULL; }
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BH_H #define _LINUX_BH_H #include <linux/preempt.h> #ifdef CONFIG_TRACE_IRQFLAGS extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { preempt_count_add(cnt); barrier(); } #endif static inline void local_bh_disable(void) { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } extern void _local_bh_enable(void); extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); static inline void local_bh_enable_ip(unsigned long ip) { __local_bh_enable_ip(ip, SOFTIRQ_DISABLE_OFFSET); } static inline void local_bh_enable(void) { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } #endif /* _LINUX_BH_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 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 // SPDX-License-Identifier: GPL-2.0 /* * kobject.h - generic kernel object infrastructure. * * Copyright (c) 2002-2003 Patrick Mochel * Copyright (c) 2002-2003 Open Source Development Labs * Copyright (c) 2006-2008 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2008 Novell Inc. * * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ #ifndef _KOBJECT_H_ #define _KOBJECT_H_ #include <linux/types.h> #include <linux/list.h> #include <linux/sysfs.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> #include <linux/uidgid.h> #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 64 /* number of env pointers */ #define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */ #ifdef CONFIG_UEVENT_HELPER /* path to the userspace helper executed on an event */ extern char uevent_helper[]; #endif /* counter to tag the uevent, read only except for the kobject core */ extern u64 uevent_seqnum; /* * The actions here must match the index to the string array * in lib/kobject_uevent.c * * Do not add new actions here without checking with the driver-core * maintainers. Action strings are not meant to express subsystem * or device specific properties. In most cases you want to send a * kobject_uevent_env(kobj, KOBJ_CHANGE, env) with additional event * specific variables added to the event environment. */ enum kobject_action { KOBJ_ADD, KOBJ_REMOVE, KOBJ_CHANGE, KOBJ_MOVE, KOBJ_ONLINE, KOBJ_OFFLINE, KOBJ_BIND, KOBJ_UNBIND, }; struct kobject { const char *name; struct list_head entry; struct kobject *parent; struct kset *kset; struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; #endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; unsigned int uevent_suppress:1; }; extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); extern __printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); extern struct kobject *kobject_get(struct kobject *kobj); extern struct kobject * __must_check kobject_get_unless_zero( struct kobject *kobj); extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); /** * kobject_has_children - Returns whether a kobject has children. * @kobj: the object to test * * This will return whether a kobject has other kobjects as children. * * It does NOT account for the presence of attribute files, only sub * directories. It also assumes there is no concurrent addition or * removal of such children, and thus relies on external locking. */ static inline bool kobject_has_children(struct kobject *kobj) { WARN_ON_ONCE(kref_read(&kobj->kref) == 0); return kobj->sd && kobj->sd->dir.subdirs; } struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid); }; struct kobj_uevent_env { char *argv[3]; char *envp[UEVENT_NUM_ENVP]; int envp_idx; char buf[UEVENT_BUFFER_SIZE]; int buflen; }; struct kset_uevent_ops { int (* const filter)(struct kset *kset, struct kobject *kobj); const char *(* const name)(struct kset *kset, struct kobject *kobj); int (* const uevent)(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, char *buf); ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count); }; extern const struct sysfs_ops kobj_sysfs_ops; struct sock; /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * * A kset defines a group of kobjects. They can be individually * different "types" but overall these kobjects all want to be grouped * together and operated on in the same manner. ksets are used to * define the attribute callbacks and other common events that happen to * a kobject. * * @list: the list of all kobjects for this kset * @list_lock: a lock for iterating over the kobjects * @kobj: the embedded kobject for this kset (recursion, isn't it fun...) * @uevent_ops: the set of uevent operations for this kset. These are * called whenever a kobject has something happen to it so that the kset * can add new environment variables, or filter out the uevents if so * desired. */ struct kset { struct list_head list; spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; } __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); extern void kset_unregister(struct kset *kset); extern struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { return kobj ? container_of(kobj, struct kset, kobj) : NULL; } static inline struct kset *kset_get(struct kset *k) { return k ? to_kset(kobject_get(&k->kobj)) : NULL; } static inline void kset_put(struct kset *k) { kobject_put(&k->kobj); } static inline struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } extern struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; /* The global /sys/kernel/mm/ kobject for people to chain off of */ extern struct kobject *mm_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kobject for people to chain off of */ extern struct kobject *power_kobj; /* The global /sys/firmware/ kobject for people to chain off of */ extern struct kobject *firmware_kobj; int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count); __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); #endif /* _KOBJECT_H_ */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H #include <linux/cgroup.h> #include <linux/kernfs.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/fs_parser.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; extern bool cgroup_debug; extern void __init enable_debug_cgroup(void); /* * cgroup_path() takes a spin lock. It is good practice not to take * spin locks within trace point handlers, as they are mostly hidden * from normal view. As cgroup_path() can take the kernfs_rename_lock * spin lock, it is best to not call that function from the trace event * handler. * * Note: trace_cgroup_##type##_enabled() is a static branch that will only * be set when the trace event is enabled. */ #define TRACE_CGROUP_PATH(type, cgrp, ...) \ do { \ if (trace_cgroup_##type##_enabled()) { \ unsigned long flags; \ spin_lock_irqsave(&trace_cgroup_path_lock, \ flags); \ cgroup_path(cgrp, trace_cgroup_path, \ TRACE_CGROUP_PATH_LEN); \ trace_cgroup_##type(cgrp, trace_cgroup_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_cgroup_path_lock, \ flags); \ } \ } while (0) /* * The cgroup filesystem superblock creation/mount context. */ struct cgroup_fs_context { struct kernfs_fs_context kfc; struct cgroup_root *root; struct cgroup_namespace *ns; unsigned int flags; /* CGRP_ROOT_* flags */ /* cgroup1 bits */ bool cpuset_clone_children; bool none; /* User explicitly requested empty subsystem */ bool all_ss; /* Seen 'all' option */ u16 subsys_mask; /* Selected subsystems */ char *name; /* Hierarchy name */ char *release_agent; /* Path for release notifications */ }; static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; return container_of(kfc, struct cgroup_fs_context, kfc); } /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* used to track tasks and csets during migration */ struct cgroup_taskset { /* the src and dst cset list running through cset->mg_node */ struct list_head src_csets; struct list_head dst_csets; /* the number of tasks in the set */ int nr_tasks; /* the subsys currently being processed */ int ssid; /* * Fields for cgroup_taskset_*() iteration. * * Before migration is committed, the target migration tasks are on * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of * the csets on ->dst_csets. ->csets point to either ->src_csets * or ->dst_csets depending on whether migration is committed. * * ->cur_csets and ->cur_task point to the current task position * during iteration. */ struct list_head *csets; struct css_set *cur_cset; struct task_struct *cur_task; }; /* migration context also tracks preloading */ struct cgroup_mgctx { /* * Preloaded source and destination csets. Used to guarantee * atomic success or failure on actual migration. */ struct list_head preloaded_src_csets; struct list_head preloaded_dst_csets; /* tasks and csets to migrate */ struct cgroup_taskset tset; /* subsystems affected by migration */ u16 ss_mask; }; #define CGROUP_TASKSET_INIT(tset) \ { \ .src_csets = LIST_HEAD_INIT(tset.src_csets), \ .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ .csets = &tset.src_csets, \ } #define CGROUP_MGCTX_INIT(name) \ { \ LIST_HEAD_INIT(name.preloaded_src_csets), \ LIST_HEAD_INIT(name.preloaded_dst_csets), \ CGROUP_TASKSET_INIT(name.tset), \ } #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry((root), &cgroup_roots, root_list) /** * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end */ #define for_each_subsys(ss, ssid) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return !(cgrp->self.flags & CSS_ONLINE); } static inline bool notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } void put_css_set_locked(struct css_set *cset); static inline void put_css_set(struct css_set *cset) { unsigned long flags; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (refcount_dec_not_one(&cset->refcount)) return; spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); spin_unlock_irqrestore(&css_set_lock, flags); } /* * refcounted get/put for css_set objects */ static inline void get_css_set(struct css_set *cset) { refcount_inc(&cset->refcount); } bool cgroup_ssid_enabled(int ssid); bool cgroup_on_dfl(const struct cgroup *cgrp); bool cgroup_is_thread_root(struct cgroup *cgrp); bool cgroup_is_threaded(struct cgroup *cgrp); struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root); struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); void cgroup_kn_unlock(struct kernfs_node *kn); int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); void cgroup_free_root(struct cgroup_root *root); void init_cgroup_root(struct cgroup_fs_context *ctx); int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); int cgroup_do_get_tree(struct fs_context *fc); int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx); int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx); int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *locked) __acquires(&cgroup_threadgroup_rwsem); void cgroup_procs_write_finish(struct task_struct *task, bool locked) __releases(&cgroup_threadgroup_rwsem); void cgroup_lock_and_drain_offline(struct cgroup *cgrp); int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); int cgroup_rmdir(struct kernfs_node *kn); int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root); int __cgroup_task_count(const struct cgroup *cgrp); int cgroup_task_count(const struct cgroup *cgrp); /* * rstat.c */ int cgroup_rstat_init(struct cgroup *cgrp); void cgroup_rstat_exit(struct cgroup *cgrp); void cgroup_rstat_boot(void); void cgroup_base_stat_cputime_show(struct seq_file *seq); /* * namespace.c */ extern const struct proc_ns_operations cgroupns_operations; /* * cgroup-v1.c */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; extern const struct fs_parameter_spec cgroup1_fs_parameters[]; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); void cgroup1_check_for_release(struct cgroup *cgrp); int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); int cgroup1_get_tree(struct fs_context *fc); int cgroup1_reconfigure(struct fs_context *ctx); #endif /* __CGROUP_INTERNAL_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __IPC_NAMESPACE_H__ #define __IPC_NAMESPACE_H__ #include <linux/err.h> #include <linux/idr.h> #include <linux/rwsem.h> #include <linux/notifier.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/refcount.h> #include <linux/rhashtable-types.h> struct user_namespace; struct ipc_ids { int in_use; unsigned short seq; struct rw_semaphore rwsem; struct idr ipcs_idr; int max_idx; int last_idx; /* For wrap around detection */ #ifdef CONFIG_CHECKPOINT_RESTORE int next_id; #endif struct rhashtable key_ht; }; struct ipc_namespace { refcount_t count; struct ipc_ids ids[3]; int sem_ctls[4]; int used_sems; unsigned int msg_ctlmax; unsigned int msg_ctlmnb; unsigned int msg_ctlmni; atomic_t msg_bytes; atomic_t msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; unsigned long shm_tot; int shm_ctlmni; /* * Defines whether IPC_RMID is forced for _all_ shm segments regardless * of shmctl() */ int shm_rmid_forced; struct notifier_block ipcns_nb; /* The kern_mount of the mqueuefs sb. We take a ref on it */ struct vfsmount *mq_mnt; /* # queues in this ns, protected by mq_lock */ unsigned int mq_queues_count; /* next fields are set through sysctl */ unsigned int mq_queues_max; /* initialized to DFLT_QUEUESMAX */ unsigned int mq_msg_max; /* initialized to DFLT_MSGMAX */ unsigned int mq_msgsize_max; /* initialized to DFLT_MSGSIZEMAX */ unsigned int mq_msg_default; unsigned int mq_msgsize_default; /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; struct ucounts *ucounts; struct llist_node mnt_llist; struct ns_common ns; } __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; #ifdef CONFIG_SYSVIPC extern void shm_destroy_orphaned(struct ipc_namespace *ns); #else /* CONFIG_SYSVIPC */ static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {} #endif /* CONFIG_SYSVIPC */ #ifdef CONFIG_POSIX_MQUEUE extern int mq_init_ns(struct ipc_namespace *ns); /* * POSIX Message Queue default values: * * MIN_*: Lowest value an admin can set the maximum unprivileged limit to * DFLT_*MAX: Default values for the maximum unprivileged limits * DFLT_{MSG,MSGSIZE}: Default values used when the user doesn't supply * an attribute to the open call and the queue must be created * HARD_*: Highest value the maximums can be set to. These are enforced * on CAP_SYS_RESOURCE apps as well making them inviolate (so make them * suitably high) * * POSIX Requirements: * Per app minimum openable message queues - 8. This does not map well * to the fact that we limit the number of queues on a per namespace * basis instead of a per app basis. So, make the default high enough * that no given app should have a hard time opening 8 queues. * Minimum maximum for HARD_MSGMAX - 32767. I bumped this to 65536. * Minimum maximum for HARD_MSGSIZEMAX - POSIX is silent on this. However, * we have run into a situation where running applications in the wild * require this to be at least 5MB, and preferably 10MB, so I set the * value to 16MB in hopes that this user is the worst of the bunch and * the new maximum will handle anyone else. I may have to revisit this * in the future. */ #define DFLT_QUEUESMAX 256 #define MIN_MSGMAX 1 #define DFLT_MSG 10U #define DFLT_MSGMAX 10 #define HARD_MSGMAX 65536 #define MIN_MSGSIZEMAX 128 #define DFLT_MSGSIZE 8192U #define DFLT_MSGSIZEMAX 8192 #define HARD_MSGSIZEMAX (16*1024*1024) #else static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #endif #if defined(CONFIG_IPC_NS) extern struct ipc_namespace *copy_ipcs(unsigned long flags, struct user_namespace *user_ns, struct ipc_namespace *ns); static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) refcount_inc(&ns->count); return ns; } static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) { if (ns) { if (refcount_inc_not_zero(&ns->count)) return ns; } return NULL; } extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, struct user_namespace *user_ns, struct ipc_namespace *ns) { if (flags & CLONE_NEWIPC) return ERR_PTR(-EINVAL); return ns; } static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { return ns; } static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) { return ns; } static inline void put_ipc_ns(struct ipc_namespace *ns) { } #endif #ifdef CONFIG_POSIX_MQUEUE_SYSCTL struct ctl_table_header; extern struct ctl_table_header *mq_register_sysctl_table(void); #else /* CONFIG_POSIX_MQUEUE_SYSCTL */ static inline struct ctl_table_header *mq_register_sysctl_table(void) { return NULL; } #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions for diskquota-operations. When diskquota is configured these * macros expand to the right source-code. * * Author: Marco van Wieringen <mvw@planets.elm.net> */ #ifndef _LINUX_QUOTAOPS_ #define _LINUX_QUOTAOPS_ #include <linux/fs.h> #define DQUOT_SPACE_WARN 0x1 #define DQUOT_SPACE_RESERVE 0x2 #define DQUOT_SPACE_NOFAIL 0x4 static inline struct quota_info *sb_dqopt(struct super_block *sb) { return &sb->s_dquot; } /* i_mutex must being held */ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) { return (ia->ia_valid & ATTR_SIZE) || (ia->ia_valid & ATTR_UID && !uid_eq(ia->ia_uid, inode->i_uid)) || (ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid)); } #if defined(CONFIG_QUOTA) #define quota_error(sb, fmt, args...) \ __quota_error((sb), __func__, fmt , ## args) extern __printf(3, 4) void __quota_error(struct super_block *sb, const char *func, const char *fmt, ...); /* * declaration of quota_function calls in kernel. */ int dquot_initialize(struct inode *inode); bool dquot_initialize_needed(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); static inline struct dquot *dqgrab(struct dquot *dquot) { /* Make sure someone else has active reference to dquot */ WARN_ON_ONCE(!atomic_read(&dquot->dq_count)); WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); atomic_inc(&dquot->dq_count); return dquot; } static inline bool dquot_is_busy(struct dquot *dquot) { if (test_bit(DQ_MOD_B, &dquot->dq_flags)) return true; if (atomic_read(&dquot->dq_count) > 1) return true; return false; } void dqput(struct dquot *dquot); int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), unsigned long priv); struct dquot *dquot_alloc(struct super_block *sb, int type); void dquot_destroy(struct dquot *dquot); int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags); void __dquot_free_space(struct inode *inode, qsize_t number, int flags); int dquot_alloc_inode(struct inode *inode); int dquot_claim_space_nodirty(struct inode *inode, qsize_t number); void dquot_free_inode(struct inode *inode); void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number); int dquot_disable(struct super_block *sb, int type, unsigned int flags); /* Suspend quotas on remount RO */ static inline int dquot_suspend(struct super_block *sb, int type) { return dquot_disable(sb, type, DQUOT_SUSPENDED); } int dquot_resume(struct super_block *sb, int type); int dquot_commit(struct dquot *dquot); int dquot_acquire(struct dquot *dquot); int dquot_release(struct dquot *dquot); int dquot_commit_info(struct super_block *sb, int type); int dquot_get_next_id(struct super_block *sb, struct kqid *qid); int dquot_mark_dquot_dirty(struct dquot *dquot); int dquot_file_open(struct inode *inode, struct file *file); int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags); int dquot_load_quota_inode(struct inode *inode, int type, int format_id, unsigned int flags); int dquot_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); int dquot_quota_off(struct super_block *sb, int type); int dquot_writeback_dquots(struct super_block *sb, int type); int dquot_quota_sync(struct super_block *sb, int type); int dquot_get_state(struct super_block *sb, struct qc_state *state); int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii); int dquot_get_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int dquot_get_next_dqblk(struct super_block *sb, struct kqid *id, struct qc_dqblk *di); int dquot_set_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); int dquot_transfer(struct inode *inode, struct iattr *iattr); static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) { return sb_dqopt(sb)->info + type; } /* * Functions for checking status of quota */ static inline bool sb_has_quota_usage_enabled(struct super_block *sb, int type) { return sb_dqopt(sb)->flags & dquot_state_flag(DQUOT_USAGE_ENABLED, type); } static inline bool sb_has_quota_limits_enabled(struct super_block *sb, int type) { return sb_dqopt(sb)->flags & dquot_state_flag(DQUOT_LIMITS_ENABLED, type); } static inline bool sb_has_quota_suspended(struct super_block *sb, int type) { return sb_dqopt(sb)->flags & dquot_state_flag(DQUOT_SUSPENDED, type); } static inline unsigned sb_any_quota_suspended(struct super_block *sb) { return dquot_state_types(sb_dqopt(sb)->flags, DQUOT_SUSPENDED); } /* Does kernel know about any quota information for given sb + type? */ static inline bool sb_has_quota_loaded(struct super_block *sb, int type) { /* Currently if anything is on, then quota usage is on as well */ return sb_has_quota_usage_enabled(sb, type); } static inline unsigned sb_any_quota_loaded(struct super_block *sb) { return dquot_state_types(sb_dqopt(sb)->flags, DQUOT_USAGE_ENABLED); } static inline bool sb_has_quota_active(struct super_block *sb, int type) { return sb_has_quota_loaded(sb, type) && !sb_has_quota_suspended(sb, type); } /* * Operations supported for diskquotas. */ extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else static inline int sb_has_quota_usage_enabled(struct super_block *sb, int type) { return 0; } static inline int sb_has_quota_limits_enabled(struct super_block *sb, int type) { return 0; } static inline int sb_has_quota_suspended(struct super_block *sb, int type) { return 0; } static inline int sb_any_quota_suspended(struct super_block *sb) { return 0; } /* Does kernel know about any quota information for given sb + type? */ static inline int sb_has_quota_loaded(struct super_block *sb, int type) { return 0; } static inline int sb_any_quota_loaded(struct super_block *sb) { return 0; } static inline int sb_has_quota_active(struct super_block *sb, int type) { return 0; } static inline int dquot_initialize(struct inode *inode) { return 0; } static inline bool dquot_initialize_needed(struct inode *inode) { return false; } static inline void dquot_drop(struct inode *inode) { } static inline int dquot_alloc_inode(struct inode *inode) { return 0; } static inline void dquot_free_inode(struct inode *inode) { } static inline int dquot_transfer(struct inode *inode, struct iattr *iattr) { return 0; } static inline int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) { if (!(flags & DQUOT_SPACE_RESERVE)) inode_add_bytes(inode, number); return 0; } static inline void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { if (!(flags & DQUOT_SPACE_RESERVE)) inode_sub_bytes(inode, number); } static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { inode_add_bytes(inode, number); return 0; } static inline int dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { inode_sub_bytes(inode, number); return 0; } static inline int dquot_disable(struct super_block *sb, int type, unsigned int flags) { return 0; } static inline int dquot_suspend(struct super_block *sb, int type) { return 0; } static inline int dquot_resume(struct super_block *sb, int type) { return 0; } #define dquot_file_open generic_file_open static inline int dquot_writeback_dquots(struct super_block *sb, int type) { return 0; } #endif /* CONFIG_QUOTA */ static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr) { return __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN); } static inline void dquot_alloc_space_nofail(struct inode *inode, qsize_t nr) { __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN|DQUOT_SPACE_NOFAIL); mark_inode_dirty_sync(inode); } static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) { int ret; ret = dquot_alloc_space_nodirty(inode, nr); if (!ret) { /* * Mark inode fully dirty. Since we are allocating blocks, inode * would become fully dirty soon anyway and it reportedly * reduces lock contention. */ mark_inode_dirty(inode); } return ret; } static inline int dquot_alloc_block_nodirty(struct inode *inode, qsize_t nr) { return dquot_alloc_space_nodirty(inode, nr << inode->i_blkbits); } static inline void dquot_alloc_block_nofail(struct inode *inode, qsize_t nr) { dquot_alloc_space_nofail(inode, nr << inode->i_blkbits); } static inline int dquot_alloc_block(struct inode *inode, qsize_t nr) { return dquot_alloc_space(inode, nr << inode->i_blkbits); } static inline int dquot_prealloc_block_nodirty(struct inode *inode, qsize_t nr) { return __dquot_alloc_space(inode, nr << inode->i_blkbits, 0); } static inline int dquot_prealloc_block(struct inode *inode, qsize_t nr) { int ret; ret = dquot_prealloc_block_nodirty(inode, nr); if (!ret) mark_inode_dirty_sync(inode); return ret; } static inline int dquot_reserve_block(struct inode *inode, qsize_t nr) { return __dquot_alloc_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE); } static inline int dquot_claim_block(struct inode *inode, qsize_t nr) { int ret; ret = dquot_claim_space_nodirty(inode, nr << inode->i_blkbits); if (!ret) mark_inode_dirty_sync(inode); return ret; } static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr) { dquot_reclaim_space_nodirty(inode, nr << inode->i_blkbits); mark_inode_dirty_sync(inode); } static inline void dquot_free_space_nodirty(struct inode *inode, qsize_t nr) { __dquot_free_space(inode, nr, 0); } static inline void dquot_free_space(struct inode *inode, qsize_t nr) { dquot_free_space_nodirty(inode, nr); mark_inode_dirty_sync(inode); } static inline void dquot_free_block_nodirty(struct inode *inode, qsize_t nr) { dquot_free_space_nodirty(inode, nr << inode->i_blkbits); } static inline void dquot_free_block(struct inode *inode, qsize_t nr) { dquot_free_space(inode, nr << inode->i_blkbits); } static inline void dquot_release_reservation_block(struct inode *inode, qsize_t nr) { __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } unsigned int qtype_enforce_flag(int type); #endif /* _LINUX_QUOTAOPS_ */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/xattr.h Extended attributes handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <uapi/linux/xattr.h> struct inode; struct dentry; /* * struct xattr_handler: When @name is set, match attributes with exactly that * name. When @prefix is set instead, match attributes with that prefix and * with a non-empty suffix. */ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { const char *name; void *value; size_t value_len; }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct dentry *, const char *); int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); int vfs_removexattr(struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supported_namespace(struct inode *inode, const char *prefix); static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; } struct simple_xattrs { struct list_head head; spinlock_t lock; }; struct simple_xattr { struct list_head list; char *name; size_t size; char value[]; }; /* * initialize the simple_xattrs structure */ static inline void simple_xattrs_init(struct simple_xattrs *xattrs) { INIT_LIST_HEAD(&xattrs->head); spin_lock_init(&xattrs->lock); } /* * free all the xattrs */ static inline void simple_xattrs_free(struct simple_xattrs *xattrs) { struct simple_xattr *xattr, *node; list_for_each_entry_safe(xattr, node, &xattrs->head, list) { kfree(xattr->name); kvfree(xattr); } } struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); #endif /* _LINUX_XATTR_H */
1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /** * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses * this_cpu_add which is irq-safe by definition. Hence there is no need muck * with irq state before calling this one */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; preempt_disable(); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock_irqrestore(&fbc->lock, flags); } else { this_cpu_add(*fbc->counters, amount); } preempt_enable(); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { unsigned long flags __maybe_unused; raw_spin_lock_init(&fbc->lock); lockdep_set_class(&fbc->lock, key); fbc->count = amount; fbc->counters = alloc_percpu_gfp(s32, gfp); if (!fbc->counters) return -ENOMEM; debug_percpu_counter_activate(fbc); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc->list); spin_lock_irqsave(&percpu_counters_lock, flags); list_add(&fbc->list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init); void percpu_counter_destroy(struct percpu_counter *fbc) { unsigned long flags __maybe_unused; if (!fbc->counters) return; debug_percpu_counter_deactivate(fbc); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); list_del(&fbc->list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc->counters); fbc->counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup);
1 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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _INET_ECN_H_ #define _INET_ECN_H_ #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #include <net/inet_sock.h> #include <net/dsfield.h> enum { INET_ECN_NOT_ECT = 0, INET_ECN_ECT_1 = 1, INET_ECN_ECT_0 = 2, INET_ECN_CE = 3, INET_ECN_MASK = 3, }; extern int sysctl_tunnel_ecn_log; static inline int INET_ECN_is_ce(__u8 dsfield) { return (dsfield & INET_ECN_MASK) == INET_ECN_CE; } static inline int INET_ECN_is_not_ect(__u8 dsfield) { return (dsfield & INET_ECN_MASK) == INET_ECN_NOT_ECT; } static inline int INET_ECN_is_capable(__u8 dsfield) { return dsfield & INET_ECN_ECT_0; } /* * RFC 3168 9.1.1 * The full-functionality option for ECN encapsulation is to copy the * ECN codepoint of the inside header to the outside header on * encapsulation if the inside header is not-ECT or ECT, and to set the * ECN codepoint of the outside header to ECT(0) if the ECN codepoint of * the inside header is CE. */ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) { outer &= ~INET_ECN_MASK; outer |= !INET_ECN_is_ce(inner) ? (inner & INET_ECN_MASK) : INET_ECN_ECT_0; return outer; } static inline void INET_ECN_xmit(struct sock *sk) { inet_sk(sk)->tos |= INET_ECN_ECT_0; if (inet6_sk(sk) != NULL) inet6_sk(sk)->tclass |= INET_ECN_ECT_0; } static inline void INET_ECN_dontxmit(struct sock *sk) { inet_sk(sk)->tos &= ~INET_ECN_MASK; if (inet6_sk(sk) != NULL) inet6_sk(sk)->tclass &= ~INET_ECN_MASK; } #define IP6_ECN_flow_init(label) do { \ (label) &= ~htonl(INET_ECN_MASK << 20); \ } while (0) #define IP6_ECN_flow_xmit(sk, label) do { \ if (INET_ECN_is_capable(inet6_sk(sk)->tclass)) \ (label) |= htonl(INET_ECN_ECT_0 << 20); \ } while (0) static inline int IP_ECN_set_ce(struct iphdr *iph) { u32 check = (__force u32)iph->check; u32 ecn = (iph->tos + 1) & INET_ECN_MASK; /* * After the last operation we have (in binary): * INET_ECN_NOT_ECT => 01 * INET_ECN_ECT_1 => 10 * INET_ECN_ECT_0 => 11 * INET_ECN_CE => 00 */ if (!(ecn & 2)) return !ecn; /* * The following gives us: * INET_ECN_ECT_1 => check += htons(0xFFFD) * INET_ECN_ECT_0 => check += htons(0xFFFE) */ check += (__force u16)htons(0xFFFB) + (__force u16)htons(ecn); iph->check = (__force __sum16)(check + (check>=0xFFFF)); iph->tos |= INET_ECN_CE; return 1; } static inline int IP_ECN_set_ect1(struct iphdr *iph) { u32 check = (__force u32)iph->check; if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; check += (__force u16)htons(0x1); iph->check = (__force __sum16)(check + (check>=0xFFFF)); iph->tos ^= INET_ECN_MASK; return 1; } static inline void IP_ECN_clear(struct iphdr *iph) { iph->tos &= ~INET_ECN_MASK; } static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner) { dscp &= ~INET_ECN_MASK; ipv4_change_dsfield(inner, INET_ECN_MASK, dscp); } struct ipv6hdr; /* Note: * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE, * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE * In IPv6 case, no checksum compensates the change in IPv6 header, * so we have to update skb->csum. */ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) { __be32 from, to; if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph))) return 0; from = *(__be32 *)iph; to = from | htonl(INET_ECN_CE << 20); *(__be32 *)iph = to; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), (__force __wsum)to); return 1; } static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) { __be32 from, to; if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; from = *(__be32 *)iph; to = from ^ htonl(INET_ECN_MASK << 20); *(__be32 *)iph = to; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), (__force __wsum)to); return 1; } static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; ipv6_change_dsfield(inner, INET_ECN_MASK, dscp); } static inline int INET_ECN_set_ce(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) return IP_ECN_set_ce(ip_hdr(skb)); break; case cpu_to_be16(ETH_P_IPV6): if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= skb_tail_pointer(skb)) return IP6_ECN_set_ce(skb, ipv6_hdr(skb)); break; } return 0; } static inline int INET_ECN_set_ect1(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) return IP_ECN_set_ect1(ip_hdr(skb)); break; case cpu_to_be16(ETH_P_IPV6): if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= skb_tail_pointer(skb)) return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); break; } return 0; } /* * RFC 6040 4.2 * To decapsulate the inner header at the tunnel egress, a compliant * tunnel egress MUST set the outgoing ECN field to the codepoint at the * intersection of the appropriate arriving inner header (row) and outer * header (column) in Figure 4 * * +---------+------------------------------------------------+ * |Arriving | Arriving Outer Header | * | Inner +---------+------------+------------+------------+ * | Header | Not-ECT | ECT(0) | ECT(1) | CE | * +---------+---------+------------+------------+------------+ * | Not-ECT | Not-ECT |Not-ECT(!!!)|Not-ECT(!!!)| <drop>(!!!)| * | ECT(0) | ECT(0) | ECT(0) | ECT(1) | CE | * | ECT(1) | ECT(1) | ECT(1) (!) | ECT(1) | CE | * | CE | CE | CE | CE(!!!)| CE | * +---------+---------+------------+------------+------------+ * * Figure 4: New IP in IP Decapsulation Behaviour * * returns 0 on success * 1 if something is broken and should be logged (!!! above) * 2 if packet should be dropped */ static inline int __INET_ECN_decapsulate(__u8 outer, __u8 inner, bool *set_ce) { if (INET_ECN_is_not_ect(inner)) { switch (outer & INET_ECN_MASK) { case INET_ECN_NOT_ECT: return 0; case INET_ECN_ECT_0: case INET_ECN_ECT_1: return 1; case INET_ECN_CE: return 2; } } *set_ce = INET_ECN_is_ce(outer); return 0; } static inline int INET_ECN_decapsulate(struct sk_buff *skb, __u8 outer, __u8 inner) { bool set_ce = false; int rc; rc = __INET_ECN_decapsulate(outer, inner, &set_ce); if (!rc) { if (set_ce) INET_ECN_set_ce(skb); else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) INET_ECN_set_ect1(skb); } return rc; } static inline int IP_ECN_decapsulate(const struct iphdr *oiph, struct sk_buff *skb) { __u8 inner; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; break; case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); break; default: return 0; } return INET_ECN_decapsulate(skb, oiph->tos, inner); } static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, struct sk_buff *skb) { __u8 inner; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; break; case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); break; default: return 0; } return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); } #endif
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Supervisor Mode Access Prevention support * * Copyright (C) 2012 Intel Corporation * Author: H. Peter Anvin <hpa@linux.intel.com> */ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H #include <asm/nops.h> #include <asm/cpufeatures.h> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" #define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ #include <asm/alternative-asm.h> #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #else /* __ASSEMBLY__ */ #include <asm/alternative.h> #ifdef CONFIG_X86_SMAP static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_CLAC, X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_STAC, X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) { unsigned long flags; asm volatile ("# smap_save\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "pushf; pop %0; " __ASM_CLAC "\n\t" "1:" : "=rm" (flags) : : "memory", "cc"); return flags; } static __always_inline void smap_restore(unsigned long flags) { asm volatile ("# smap_restore\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "push %0; popf\n\t" "1:" : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ static inline void clac(void) { } static inline void stac(void) { } static inline unsigned long smap_save(void) { return 0; } static inline void smap_restore(unsigned long flags) { } #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */
1 2 3 4 5 6 7 8 9 10 11 12 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MSDOS_FS_H #define _LINUX_MSDOS_FS_H #include <uapi/linux/msdos_fs.h> /* media of boot sector */ static inline int fat_valid_media(u8 media) { return 0xf8 <= media || media == 0xf0; } #endif /* !_LINUX_MSDOS_FS_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) { unsigned long start = 0UL, end = TLB_FLUSH_ALL; unsigned int stride_shift = tlb_get_unmap_shift(tlb); if (!tlb->fullmm && !tlb->need_flush_all) { start = tlb->start; end = tlb->end; } flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); } /* * While x86 architecture in general requires an IPI to perform TLB * shootdown, enablement code for several hypervisors overrides * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing * a hypercall. To keep software pagetable walkers safe in this case we * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h * for more details. */ static inline void __tlb_remove_table(void *table) { free_page_and_swap_cache(table); } #endif /* _ASM_X86_TLB_H */
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { /* * Those arches which don't have hw access flag feature need to * implement their own helper. By default, "true" means pagefault * will be hit on old pte. */ return true; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { if (current->rss_stat.count[i]) { add_mm_counter(mm, i, current->rss_stat.count[i]); current->rss_stat.count[i] = 0; } } current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { struct task_struct *task = current; if (likely(task->mm == mm)) task->rss_stat.count[member] += val; else add_mm_counter(mm, member, val); } #define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) #define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) /* sync counter once per 64 page faults */ #define TASK_RSS_EVENTS_THRESH (64) static void check_sync_rss_stat(struct task_struct *task) { if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) static void check_sync_rss_stat(struct task_struct *task) { } #endif /* SPLIT_RSS_COUNTING */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); pmd_populate(mm, pmd, new); new = NULL; } spin_unlock(ptl); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; if (current->mm == mm) sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The disadvantage is that pages are refcounted * (which can be slower and simply not an option for some PFNMAP users). The * advantage is that we don't have to follow the strict linearity rule of * PFNMAP mappings in order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* * There is no pmd_special() but there may be special pmds, e.g. * in a direct-access (dax) mapping, so let's just replicate the * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #endif /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return entry.val; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = device_private_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ get_page(page); rss[mm_counter(page)]++; page_dup_rmap(page, false); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_write_device_private_entry(entry) && is_cow_mapping(vm_flags)) { make_device_private_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page if necessary. * * NOTE! The usual case is that this doesn't need to do * anything, and can just return a positive value. That * will let the caller know that it can just increase * the page refcount and re-use the pte the traditional * way. * * But _if_ we need to copy it because it needs to be * pinned in the parent (and the child should get its own * copy rather than just a reference to the same page), * we'll do that here and return zero to let the caller * know we're done. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; if (!is_cow_mapping(src_vma->vm_flags)) return 1; /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy * the page immediately so that we'll always guarantee * the pinned page won't be randomly replaced in the * future. * * The page pinning checks are just "has this mm ever * seen pinning", along with the (inexact) check of * the page count. That might give false positives for * for pinning, but it will work correctly. */ if (likely(!atomic_read(&src_mm->has_pinned))) return 1; if (likely(!page_maybe_dma_pinned(page))) return 1; new_page = *prealloc; if (!new_page) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); page_add_new_anon_rmap(new_page, dst_vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, *src_pte)) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } /* * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page * is required to copy this pte. */ static inline int copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc) { struct mm_struct *src_mm = src_vma->vm_mm; unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, pte, page); if (retval <= 0) return retval; get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; } /* * If it's a COW mapping, write protect it both * in the parent and the child */ if (is_cow_mapping(vm_flags) && pte_write(pte)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } /* * If it's a shared mapping, mark it clean in * the child */ if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static inline struct page * page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr) { struct page *new_page; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); if (!new_page) return NULL; if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } cgroup_throttle_swaprate(new_page, GFP_KERNEL); return new_page; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct page *prealloc = NULL; again: progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } if (unlikely(!pte_present(*src_pte))) { entry.val = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (entry.val) break; progress += 8; continue; } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. */ if (unlikely(ret == -EAGAIN)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ put_page(prealloc); prealloc = NULL; } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (entry.val) { if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret) { WARN_ON_ONCE(ret != -EAGAIN); prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; /* We've captured and resolved the error. Reset, try again. */ ret = 0; } if (addr != end) goto again; out: if (unlikely(prealloc)) put_page(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; /* * Don't copy ptes where a page fault will fill them correctly. * Fork becomes much lighter when there are big shared or private * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && !src_vma->anon_vma) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ mmap_assert_write_locked(src_mm); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { struct page *page; page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping && details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; addr += PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry)) { struct page *page = device_private_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping != page_rmapping(page)) continue; } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; page_remove_rmap(page, false); put_page(page); continue; } /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; if (!non_swap_entry(entry)) rss[MM_SWAPENTS]--; else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; tlb_flush_mmu(tlb); } if (addr != end) { cond_resched(); goto again; } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } else if (details && details->single_page && PageTransCompound(details->single_page) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is * none or trans huge it can change under us. This is * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); next: cond_resched(); } while (pmd++, addr = next, addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) unmap_single_vma(&tlb, vma, start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, start, range.end); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, address, range.end); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static int validate_page_before_insert(struct page *page) { if (PageAnon(page) || PageSlab(page) || page_has_type(page)) return -EINVAL; flush_dcache_page(page); return 0; } static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); return 0; } /* * This is the old fallback for page remapping. * * For historical reasons, it only allows reserved pages. Only * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); if (err) return err; return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. Arch *must* define pte_index. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } #endif /* ifdef pte_index */ /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { #ifdef pte_index const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); if (err) break; } *num = pgcount - idx; return err; #endif /* ifdef pte_index */ } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } entry = pte_mkyoung(*pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * See vmf_insert_mixed_prot() for a discussion of the implication of using * a value of @pgprot different from that of @vma->vm_page_prot. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot, bool mkwrite) { int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } /** * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and * encryption bits different than those of @vma->vm_page_prot, because * the caching- or encryption mode may not be known at mmap() time. * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot) { return __vm_insert_mixed(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_mixed_prot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; unsigned long remap_pfn = pfn; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; } while (pgd++, addr = next, addr != end); if (err) untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte; int err = 0; spinlock_t *ptl; if (create) { pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(*pte)) { err = fn(pte++, addr, data); if (err) break; } } while (addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_huge(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (create || !pmd_none_or_clear_bad(pmd)) { err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (create || !pud_none_or_clear_bad(pud)) { err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (create || !p4d_none_or_clear_bad(p4d)) { err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (!create && pgd_none_or_clear_bad(pgd)) continue; err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spinlock_t *ptl = pte_lockptr(mm, pmd); spin_lock(ptl); same = pte_same(*page_table, orig_pte); spin_unlock(ptl); } #endif pte_unmap(page_table); return same; } static inline bool cow_user_page(struct page *dst, struct page *src, struct vm_fault *vmf) { bool ret; void *kaddr; void __user *uaddr; bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { copy_user_highpage(dst, src, addr, vma); return true; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_atomic(dst); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache(vma, addr, vmf->pte); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (locked) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = true; pte_unlock: if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) { vm_fault_t ret; struct page *page = vmf->page; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { lock_page(page); if (!page->mapping) { unlock_page(page); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_PAGE(!PageLocked(page), page); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = set_page_dirty(page); VM_BUG_ON_PAGE(PageAnon(page), page); /* * Take a local copy of the address_space - page.mapping may be zeroed * by truncate after unlock_page(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = page_rmapping(page); unlock_page(page); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_RETRY; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * Handle the case of a page which we actually need to copy to a new page. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) goto oom; if (!cow_user_page(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. */ put_page(new_page); if (old_page) put_page(old_page); return 0; } } if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry. This will avoid a race condition * seen in the presence of one thread doing SMC and another * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * page_remove_rmap with the ptp_clear_flush above. * Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in page_remove_rmap. * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) put_page(new_page); pte_unmap_unlock(vmf->pte, vmf->ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above ptep_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); unlock_page(old_page); } put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); return VM_FAULT_OOM; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); return VM_FAULT_WRITE; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } tmp = finish_mkwrite_fault(vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { unlock_page(vmf->page); put_page(vmf->page); return tmp; } } else { wp_page_reuse(vmf); lock_page(vmf->page); } ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); return ret; } /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary * COW. * * We also mark the page dirty at this point even though the page will * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } /* * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ if (PageAnon(vmf->page)) { struct page *page = vmf->page; /* PageKsm() doesn't necessarily raise the page refcount */ if (PageKsm(page) || page_count(page) != 1) goto copy; if (!trylock_page(page)) goto copy; if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { unlock_page(page); goto copy; } /* * Ok, we've got the only map reference, and the only * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ unlock_page(page); wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } copy: /* * Ok, we need to copy. Oh, well.. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = details->first_index; if (zba < vba) zba = vba; zea = details->last_index; if (zea > vea) zea = vea; unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_page() - Unmap single page from processes. * @page: The locked page to be unmapped. * * Unmap this page from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a page, it may find that * the page has been remapped again: and then uses unmap_mapping_page() * to unmap it finally. */ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); details.check_mapping = mapping; details.first_index = page->index; details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; details.check_mapping = even_cows ? NULL : mapping; details.first_index = start; details.last_index = start + nr - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = holebegin >> PAGE_SHIFT; pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_private_entry(entry)) { vmf->page = device_private_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { struct swap_info_struct *si = swp_swap_info(entry); if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (page) { int err; __SetPageLocked(page); __SetPageSwapBacked(page); set_page_private(page, entry.val); /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); if (err) { ret = VM_FAULT_OOM; goto out_page; } shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(page, shadow); lru_cache_add(page); swap_readpage(page, true); } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = page; } if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not * release the swapcache from under us. The page pin, and pte_same * test below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not changed. */ if (unlikely((!PageSwapCache(page) || page_private(page) != entry.val)) && swapcache) goto out_page; page = ksm_might_need_to_copy(page, vma, vmf->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* * The page isn't present yet, go ahead with the fault. * * Be careful about the sequence of operations here. * To get its accounting right, reuse_swap_page() must be called * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. */ inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) { pte = pte_mkuffd_wp(pte); pte = pte_wrprotect(pte); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); vmf->orig_pte = pte; /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); } swap_free(entry); if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ unlock_page(swapcache); put_page(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); out_release: put_page(page); if (page != swapcache && swapcache) { unlock_page(swapcache); put_page(swapcache); } return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* See the comment in pte_alloc_one_map() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!page) goto oom; if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_cache(vma, vmf->address, vmf->pte); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: put_page(page); goto unlock; oom_free_page: put_page(page); oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; if (unlikely(PageHWPoison(vmf->page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf->page); put_page(vmf->page); vmf->page = NULL; return VM_FAULT_HWPOISON; } if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf->page); else VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); return ret; } /* * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. * If we check pmd_trans_unstable() first we will trip the bad_pmd() check * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. */ static int pmd_devmap_trans_unstable(pmd_t *pmd) { return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); } static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (!pmd_none(*vmf->pmd)) goto map_pte; if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { spin_unlock(vmf->ptl); goto map_pte; } mm_inc_nr_ptes(vma->vm_mm); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); spin_unlock(vmf->ptl); vmf->prealloc_pte = NULL; } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; } map_pte: /* * If a huge pmd materialized under us just retry later. Use * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge * under us and then back to pmd_none, as a result of MADV_DONTNEED * running immediately after a huge pmd fault in a different thread of * this mm, in turn leading to a misleading pmd_trans_huge() retval. * All we have to ensure is that it is a regular pmd that we can walk * with pte_offset_map() and we can do that through an atomic read in * C, which is what pmd_trans_unstable() provides. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; /* * At this point we know that our vmf->pmd points to a page of ptes * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() * for the duration of the fault. If a racing MADV_DONTNEED runs and * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still * be valid and we will re-check to make sure the vmf->pte isn't * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); return 0; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) return ret; page = compound_head(page); if (compound_order(page) != HPAGE_PMD_ORDER) return ret; /* * Archs like ppc64 need additonal space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); page_add_file_rmap(page, true); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { BUILD_BUG(); return 0; } #endif /** * alloc_set_pte - setup new PTE entry for given page and add reverse page * mapping. If needed, the function allocates page table or use pre-allocated. * * @vmf: fault environment * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on * return. * * Target users are page handler itself and implementations of * vm_ops->map_pages. * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; pte_t entry; vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (!vmf->pte) { ret = pte_alloc_one_map(vmf); if (ret) return ret; } /* Re-check under ptl */ if (unlikely(!pte_none(*vmf->pte))) { update_mmu_tlb(vma, vmf->address, vmf->pte); return VM_FAULT_NOPAGE; } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, vmf->address, vmf->pte); return 0; } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct page *page; vm_fault_t ret = 0; /* Did we COW the page? */