Blame view
mm/mmap.c
70.6 KB
1da177e4c
|
1 2 3 4 5 |
/* * mm/mmap.c * * Written by obz. * |
046c68842
|
6 |
* Address space accounting code <alan@lxorguk.ukuu.org.uk> |
1da177e4c
|
7 8 9 |
*/ #include <linux/slab.h> |
4af3c9cc4
|
10 |
#include <linux/backing-dev.h> |
1da177e4c
|
11 12 13 14 15 16 |
#include <linux/mm.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> |
c59ede7b7
|
17 |
#include <linux/capability.h> |
1da177e4c
|
18 19 20 21 22 23 24 |
#include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/profile.h> |
b95f1b31b
|
25 |
#include <linux/export.h> |
1da177e4c
|
26 27 28 |
#include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> |
cddb8a5c1
|
29 |
#include <linux/mmu_notifier.h> |
cdd6c482c
|
30 |
#include <linux/perf_event.h> |
120a795da
|
31 |
#include <linux/audit.h> |
b15d00b6a
|
32 |
#include <linux/khugepaged.h> |
2b1444983
|
33 |
#include <linux/uprobes.h> |
1da177e4c
|
34 35 36 37 |
#include <asm/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> |
d6dd61c83
|
38 |
#include <asm/mmu_context.h> |
1da177e4c
|
39 |
|
42b777281
|
40 |
#include "internal.h" |
3a4597568
|
41 42 43 |
#ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif |
08e7d9b55
|
44 45 46 |
#ifndef arch_rebalance_pgtables #define arch_rebalance_pgtables(addr, len) (addr) #endif |
e0da382c9
|
47 48 49 |
static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); |
1da177e4c
|
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 |
/* * WARNING: the debugging will use recursive algorithms so never enable this * unless you know what you are doing. */ #undef DEBUG_MM_RB /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * */ pgprot_t protection_map[16] = { __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 }; |
804af2cf6
|
75 76 |
pgprot_t vm_get_page_prot(unsigned long vm_flags) { |
b845f313d
|
77 78 79 |
return __pgprot(pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | pgprot_val(arch_vm_get_page_prot(vm_flags))); |
804af2cf6
|
80 81 |
} EXPORT_SYMBOL(vm_get_page_prot); |
34679d7ea
|
82 83 |
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */ |
c3d8c1414
|
84 |
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; |
34679d7ea
|
85 86 87 88 89 |
/* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; |
1da177e4c
|
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
/* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ |
34b4e4aa3
|
107 |
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) |
1da177e4c
|
108 109 110 111 112 113 114 115 116 117 118 119 |
{ unsigned long free, allowed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { |
c15bef309
|
120 121 122 123 124 125 126 127 128 129 |
free = global_page_state(NR_FREE_PAGES); free += global_page_state(NR_FILE_PAGES); /* * shmem pages shouldn't be counted as free in this * case, they can't be purged, only swapped out, and * that won't affect the overall amount of available * memory in the system. */ free -= global_page_state(NR_SHMEM); |
1da177e4c
|
130 |
|
1da177e4c
|
131 132 133 134 135 136 137 138 |
free += nr_swap_pages; /* * Any slabs which are created with the * SLAB_RECLAIM_ACCOUNT flag claim to have contents * which are reclaimable, under pressure. The dentry * cache and most inode caches should fall into this */ |
972d1a7b1
|
139 |
free += global_page_state(NR_SLAB_RECLAIMABLE); |
1da177e4c
|
140 141 |
/* |
6d9f78396
|
142 143 |
* Leave reserved pages. The pages are not for anonymous pages. */ |
c15bef309
|
144 |
if (free <= totalreserve_pages) |
6d9f78396
|
145 146 |
goto error; else |
c15bef309
|
147 |
free -= totalreserve_pages; |
6d9f78396
|
148 149 150 151 |
/* * Leave the last 3% for root */ |
1da177e4c
|
152 |
if (!cap_sys_admin) |
c15bef309
|
153 |
free -= free / 32; |
1da177e4c
|
154 155 156 |
if (free > pages) return 0; |
6d9f78396
|
157 158 |
goto error; |
1da177e4c
|
159 160 161 162 163 164 165 166 167 168 169 170 171 |
} allowed = (totalram_pages - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100; /* * Leave the last 3% for root */ if (!cap_sys_admin) allowed -= allowed / 32; allowed += total_swap_pages; /* Don't let a single process grow too big: leave 3% of the size of this process for other processes */ |
731572d39
|
172 173 |
if (mm) allowed -= mm->total_vm / 32; |
1da177e4c
|
174 |
|
00a62ce91
|
175 |
if (percpu_counter_read_positive(&vm_committed_as) < allowed) |
1da177e4c
|
176 |
return 0; |
6d9f78396
|
177 |
error: |
1da177e4c
|
178 179 180 181 |
vm_unacct_memory(pages); return -ENOMEM; } |
1da177e4c
|
182 |
/* |
3d48ae45e
|
183 |
* Requires inode->i_mapping->i_mmap_mutex |
1da177e4c
|
184 185 186 187 188 |
*/ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { if (vma->vm_flags & VM_DENYWRITE) |
d3ac7f892
|
189 |
atomic_inc(&file->f_path.dentry->d_inode->i_writecount); |
1da177e4c
|
190 191 192 193 194 195 196 197 198 199 200 201 |
if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable--; flush_dcache_mmap_lock(mapping); if (unlikely(vma->vm_flags & VM_NONLINEAR)) list_del_init(&vma->shared.vm_set.list); else vma_prio_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* |
a8fb5618d
|
202 203 |
* Unlink a file-based vm structure from its prio_tree, to hide * vma from rmap and vmtruncate before freeing its page tables. |
1da177e4c
|
204 |
*/ |
a8fb5618d
|
205 |
void unlink_file_vma(struct vm_area_struct *vma) |
1da177e4c
|
206 207 |
{ struct file *file = vma->vm_file; |
1da177e4c
|
208 209 |
if (file) { struct address_space *mapping = file->f_mapping; |
3d48ae45e
|
210 |
mutex_lock(&mapping->i_mmap_mutex); |
1da177e4c
|
211 |
__remove_shared_vm_struct(vma, file, mapping); |
3d48ae45e
|
212 |
mutex_unlock(&mapping->i_mmap_mutex); |
1da177e4c
|
213 |
} |
a8fb5618d
|
214 215 216 217 218 219 220 221 |
} /* * Close a vm structure and free it, returning the next. */ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) { struct vm_area_struct *next = vma->vm_next; |
a8fb5618d
|
222 |
might_sleep(); |
1da177e4c
|
223 224 |
if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); |
925d1c401
|
225 |
if (vma->vm_file) { |
a8fb5618d
|
226 |
fput(vma->vm_file); |
925d1c401
|
227 228 229 |
if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(vma->vm_mm); } |
f0be3d32b
|
230 |
mpol_put(vma_policy(vma)); |
1da177e4c
|
231 |
kmem_cache_free(vm_area_cachep, vma); |
a8fb5618d
|
232 |
return next; |
1da177e4c
|
233 |
} |
e4eb1ff61
|
234 |
static unsigned long do_brk(unsigned long addr, unsigned long len); |
6a6160a7b
|
235 |
SYSCALL_DEFINE1(brk, unsigned long, brk) |
1da177e4c
|
236 237 238 239 |
{ unsigned long rlim, retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; |
a5b4592cf
|
240 |
unsigned long min_brk; |
1da177e4c
|
241 242 |
down_write(&mm->mmap_sem); |
a5b4592cf
|
243 |
#ifdef CONFIG_COMPAT_BRK |
5520e8948
|
244 245 246 247 248 |
/* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ |
4471a675d
|
249 |
if (current->brk_randomized) |
5520e8948
|
250 251 252 |
min_brk = mm->start_brk; else min_brk = mm->end_data; |
a5b4592cf
|
253 254 255 256 |
#else min_brk = mm->start_brk; #endif if (brk < min_brk) |
1da177e4c
|
257 |
goto out; |
1e624196f
|
258 259 260 261 262 263 264 |
/* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ |
59e99e5b9
|
265 |
rlim = rlimit(RLIMIT_DATA); |
c1d171a00
|
266 267 |
if (rlim < RLIM_INFINITY && (brk - mm->start_brk) + (mm->end_data - mm->start_data) > rlim) |
1e624196f
|
268 |
goto out; |
1da177e4c
|
269 270 271 272 273 274 275 276 277 278 279 |
newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) goto set_brk; /* Always allow shrinking brk. */ if (brk <= mm->brk) { if (!do_munmap(mm, newbrk, oldbrk-newbrk)) goto set_brk; goto out; } |
1da177e4c
|
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 |
/* Check against existing mmap mappings. */ if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE)) goto out; /* Ok, looks good - let it rip. */ if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk) goto out; set_brk: mm->brk = brk; out: retval = mm->brk; up_write(&mm->mmap_sem); return retval; } #ifdef DEBUG_MM_RB static int browse_rb(struct rb_root *root) { int i = 0, j; struct rb_node *nd, *pn = NULL; unsigned long prev = 0, pend = 0; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); if (vma->vm_start < prev) printk("vm_start %lx prev %lx ", vma->vm_start, prev), i = -1; if (vma->vm_start < pend) printk("vm_start %lx pend %lx ", vma->vm_start, pend); if (vma->vm_start > vma->vm_end) printk("vm_end %lx < vm_start %lx ", vma->vm_end, vma->vm_start); i++; pn = nd; |
d1af65d13
|
316 317 |
prev = vma->vm_start; pend = vma->vm_end; |
1da177e4c
|
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 |
} j = 0; for (nd = pn; nd; nd = rb_prev(nd)) { j++; } if (i != j) printk("backwards %d, forwards %d ", j, i), i = 0; return i; } void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *tmp = mm->mmap; while (tmp) { tmp = tmp->vm_next; i++; } if (i != mm->map_count) printk("map_count %d vm_next %d ", mm->map_count, i), bug = 1; i = browse_rb(&mm->mm_rb); if (i != mm->map_count) printk("map_count %d rb %d ", mm->map_count, i), bug = 1; |
46a350ef9
|
345 |
BUG_ON(bug); |
1da177e4c
|
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 |
} #else #define validate_mm(mm) do { } while (0) #endif static struct vm_area_struct * find_vma_prepare(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev, struct rb_node ***rb_link, struct rb_node ** rb_parent) { struct vm_area_struct * vma; struct rb_node ** __rb_link, * __rb_parent, * rb_prev; __rb_link = &mm->mm_rb.rb_node; rb_prev = __rb_parent = NULL; vma = NULL; while (*__rb_link) { struct vm_area_struct *vma_tmp; __rb_parent = *__rb_link; vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb); if (vma_tmp->vm_end > addr) { vma = vma_tmp; if (vma_tmp->vm_start <= addr) |
dfe195fb7
|
372 |
break; |
1da177e4c
|
373 374 375 376 377 378 379 380 381 382 383 384 385 386 |
__rb_link = &__rb_parent->rb_left; } else { rb_prev = __rb_parent; __rb_link = &__rb_parent->rb_right; } } *pprev = NULL; if (rb_prev) *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); *rb_link = __rb_link; *rb_parent = __rb_parent; return vma; } |
1da177e4c
|
387 388 389 390 391 392 |
void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { rb_link_node(&vma->vm_rb, rb_parent, rb_link); rb_insert_color(&vma->vm_rb, &mm->mm_rb); } |
cb8f488c3
|
393 |
static void __vma_link_file(struct vm_area_struct *vma) |
1da177e4c
|
394 |
{ |
48aae4255
|
395 |
struct file *file; |
1da177e4c
|
396 397 398 399 400 401 |
file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) |
d3ac7f892
|
402 |
atomic_dec(&file->f_path.dentry->d_inode->i_writecount); |
1da177e4c
|
403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 |
if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable++; flush_dcache_mmap_lock(mapping); if (unlikely(vma->vm_flags & VM_NONLINEAR)) vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); else vma_prio_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } static void __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { __vma_link_list(mm, vma, prev, rb_parent); __vma_link_rb(mm, vma, rb_link, rb_parent); |
1da177e4c
|
422 423 424 425 426 427 428 429 430 431 |
} static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { struct address_space *mapping = NULL; if (vma->vm_file) mapping = vma->vm_file->f_mapping; |
97a894136
|
432 |
if (mapping) |
3d48ae45e
|
433 |
mutex_lock(&mapping->i_mmap_mutex); |
1da177e4c
|
434 435 436 |
__vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); |
1da177e4c
|
437 |
if (mapping) |
3d48ae45e
|
438 |
mutex_unlock(&mapping->i_mmap_mutex); |
1da177e4c
|
439 440 441 442 443 444 |
mm->map_count++; validate_mm(mm); } /* |
88f6b4c32
|
445 446 |
* Helper for vma_adjust() in the split_vma insert case: insert a vma into the * mm's list and rbtree. It has already been inserted into the prio_tree. |
1da177e4c
|
447 |
*/ |
48aae4255
|
448 |
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) |
1da177e4c
|
449 |
{ |
48aae4255
|
450 451 |
struct vm_area_struct *__vma, *prev; struct rb_node **rb_link, *rb_parent; |
1da177e4c
|
452 453 |
__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent); |
46a350ef9
|
454 |
BUG_ON(__vma && __vma->vm_start < vma->vm_end); |
1da177e4c
|
455 456 457 458 459 460 461 462 |
__vma_link(mm, vma, prev, rb_link, rb_parent); mm->map_count++; } static inline void __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev) { |
297c5eee3
|
463 464 465 466 467 |
struct vm_area_struct *next = vma->vm_next; prev->vm_next = next; if (next) next->vm_prev = prev; |
1da177e4c
|
468 469 470 471 472 473 474 475 476 477 478 479 |
rb_erase(&vma->vm_rb, &mm->mm_rb); if (mm->mmap_cache == vma) mm->mmap_cache = prev; } /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. * The following helper function should be used when such adjustments * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ |
5beb49305
|
480 |
int vma_adjust(struct vm_area_struct *vma, unsigned long start, |
1da177e4c
|
481 482 483 484 485 486 487 |
unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next; struct vm_area_struct *importer = NULL; struct address_space *mapping = NULL; struct prio_tree_root *root = NULL; |
012f18004
|
488 |
struct anon_vma *anon_vma = NULL; |
1da177e4c
|
489 |
struct file *file = vma->vm_file; |
1da177e4c
|
490 491 492 493 |
long adjust_next = 0; int remove_next = 0; if (next && !insert) { |
287d97ac0
|
494 |
struct vm_area_struct *exporter = NULL; |
1da177e4c
|
495 496 497 498 499 500 501 |
if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). */ again: remove_next = 1 + (end > next->vm_end); end = next->vm_end; |
287d97ac0
|
502 |
exporter = next; |
1da177e4c
|
503 504 505 506 507 508 509 |
importer = vma; } else if (end > next->vm_start) { /* * vma expands, overlapping part of the next: * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start) >> PAGE_SHIFT; |
287d97ac0
|
510 |
exporter = next; |
1da177e4c
|
511 512 513 514 515 516 517 518 |
importer = vma; } else if (end < vma->vm_end) { /* * vma shrinks, and !insert tells it's not * split_vma inserting another: so it must be * mprotect case 4 shifting the boundary down. */ adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT); |
287d97ac0
|
519 |
exporter = vma; |
1da177e4c
|
520 521 |
importer = next; } |
1da177e4c
|
522 |
|
5beb49305
|
523 524 525 526 527 |
/* * Easily overlooked: when mprotect shifts the boundary, * make sure the expanding vma has anon_vma set if the * shrinking vma had, to cover any anon pages imported. */ |
287d97ac0
|
528 529 |
if (exporter && exporter->anon_vma && !importer->anon_vma) { if (anon_vma_clone(importer, exporter)) |
5beb49305
|
530 |
return -ENOMEM; |
287d97ac0
|
531 |
importer->anon_vma = exporter->anon_vma; |
5beb49305
|
532 533 |
} } |
1da177e4c
|
534 535 |
if (file) { mapping = file->f_mapping; |
682968e0c
|
536 |
if (!(vma->vm_flags & VM_NONLINEAR)) { |
1da177e4c
|
537 |
root = &mapping->i_mmap; |
cbc91f71b
|
538 |
uprobe_munmap(vma, vma->vm_start, vma->vm_end); |
682968e0c
|
539 540 |
if (adjust_next) |
cbc91f71b
|
541 542 |
uprobe_munmap(next, next->vm_start, next->vm_end); |
682968e0c
|
543 |
} |
3d48ae45e
|
544 |
mutex_lock(&mapping->i_mmap_mutex); |
1da177e4c
|
545 |
if (insert) { |
1da177e4c
|
546 547 548 549 550 551 552 553 554 |
/* * Put into prio_tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(insert); } } |
94fcc585f
|
555 |
vma_adjust_trans_huge(vma, start, end, adjust_next); |
012f18004
|
556 557 558 559 560 561 |
/* * When changing only vma->vm_end, we don't really need anon_vma * lock. This is a fairly rare case by itself, but the anon_vma * lock may be shared between many sibling processes. Skipping * the lock for brk adjustments makes a difference sometimes. */ |
5f70b962c
|
562 |
if (vma->anon_vma && (importer || start != vma->vm_start)) { |
012f18004
|
563 564 565 |
anon_vma = vma->anon_vma; anon_vma_lock(anon_vma); } |
1da177e4c
|
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 |
if (root) { flush_dcache_mmap_lock(mapping); vma_prio_tree_remove(vma, root); if (adjust_next) vma_prio_tree_remove(next, root); } vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next << PAGE_SHIFT; next->vm_pgoff += adjust_next; } if (root) { if (adjust_next) vma_prio_tree_insert(next, root); vma_prio_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } if (remove_next) { /* * vma_merge has merged next into vma, and needs * us to remove next before dropping the locks. */ __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); |
1da177e4c
|
596 597 598 599 600 601 602 603 |
} else if (insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ __insert_vm_struct(mm, insert); } |
012f18004
|
604 605 |
if (anon_vma) anon_vma_unlock(anon_vma); |
1da177e4c
|
606 |
if (mapping) |
3d48ae45e
|
607 |
mutex_unlock(&mapping->i_mmap_mutex); |
1da177e4c
|
608 |
|
2b1444983
|
609 |
if (root) { |
7b2d81d48
|
610 |
uprobe_mmap(vma); |
2b1444983
|
611 612 |
if (adjust_next) |
7b2d81d48
|
613 |
uprobe_mmap(next); |
2b1444983
|
614 |
} |
1da177e4c
|
615 |
if (remove_next) { |
925d1c401
|
616 |
if (file) { |
cbc91f71b
|
617 |
uprobe_munmap(next, next->vm_start, next->vm_end); |
1da177e4c
|
618 |
fput(file); |
925d1c401
|
619 620 621 |
if (next->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); } |
5beb49305
|
622 623 |
if (next->anon_vma) anon_vma_merge(vma, next); |
1da177e4c
|
624 |
mm->map_count--; |
f0be3d32b
|
625 |
mpol_put(vma_policy(next)); |
1da177e4c
|
626 627 628 629 630 631 632 633 634 635 636 |
kmem_cache_free(vm_area_cachep, next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter * up the code too much to do both in one go. */ if (remove_next == 2) { next = vma->vm_next; goto again; } } |
2b1444983
|
637 |
if (insert && file) |
7b2d81d48
|
638 |
uprobe_mmap(insert); |
1da177e4c
|
639 640 |
validate_mm(mm); |
5beb49305
|
641 642 |
return 0; |
1da177e4c
|
643 644 645 646 647 648 |
} /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those. */ |
1da177e4c
|
649 650 651 |
static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { |
8314c4f24
|
652 653 |
/* VM_CAN_NONLINEAR may get set later by f_op->mmap() */ if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR) |
1da177e4c
|
654 655 656 657 658 659 660 661 662 |
return 0; if (vma->vm_file != file) return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; return 1; } static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, |
965f55dea
|
663 664 |
struct anon_vma *anon_vma2, struct vm_area_struct *vma) |
1da177e4c
|
665 |
{ |
965f55dea
|
666 667 668 669 670 671 672 673 |
/* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return 1; return anon_vma1 == anon_vma2; |
1da177e4c
|
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 |
} /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap_pgoff() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. */ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff) { if (is_mergeable_vma(vma, file, vm_flags) && |
965f55dea
|
692 |
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { |
1da177e4c
|
693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 |
if (vma->vm_pgoff == vm_pgoff) return 1; } return 0; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. */ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff) { if (is_mergeable_vma(vma, file, vm_flags) && |
965f55dea
|
711 |
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { |
1da177e4c
|
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 |
pgoff_t vm_pglen; vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; if (vma->vm_pgoff + vm_pglen == vm_pgoff) return 1; } return 0; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out * whether that can be merged with its predecessor or its successor. * Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when * called for mprotect, it is certain to be already mapped (either at * an offset within prev, or at the start of next), and the flags of * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * * The following mprotect cases have to be considered, where AAAA is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: * * AAAA AAAA AAAA AAAA * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN PPPPNNNNXXXX * cannot merge might become might become might become * PPNNNNNNNNNN PPPPPPPPPPNN PPPPPPPPPPPP 6 or * mmap, brk or case 4 below case 5 below PPPPPPPPXXXX 7 or * mremap move: PPPPNNNNNNNN 8 * AAAA * PPPP NNNN PPPPPPPPPPPP PPPPPPPPNNNN PPPPNNNNNNNN * might become case 1 below case 2 below case 3 below * * Odd one out? Case 8, because it extends NNNN but needs flags of XXXX: * mprotect_fixup updates vm_flags & vm_page_prot on successful return. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; |
5beb49305
|
757 |
int err; |
1da177e4c
|
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 |
/* * We later require that vma->vm_flags == vm_flags, * so this tests vma->vm_flags & VM_SPECIAL, too. */ if (vm_flags & VM_SPECIAL) return NULL; if (prev) next = prev->vm_next; else next = mm->mmap; area = next; if (next && next->vm_end == end) /* cases 6, 7, 8 */ next = next->vm_next; /* * Can it merge with the predecessor? */ if (prev && prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff)) { /* * OK, it can. Can we now merge in the successor as well? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen) && is_mergeable_anon_vma(prev->anon_vma, |
965f55dea
|
789 |
next->anon_vma, NULL)) { |
1da177e4c
|
790 |
/* cases 1, 6 */ |
5beb49305
|
791 |
err = vma_adjust(prev, prev->vm_start, |
1da177e4c
|
792 793 |
next->vm_end, prev->vm_pgoff, NULL); } else /* cases 2, 5, 7 */ |
5beb49305
|
794 |
err = vma_adjust(prev, prev->vm_start, |
1da177e4c
|
795 |
end, prev->vm_pgoff, NULL); |
5beb49305
|
796 797 |
if (err) return NULL; |
b15d00b6a
|
798 |
khugepaged_enter_vma_merge(prev); |
1da177e4c
|
799 800 801 802 803 804 805 806 807 808 809 |
return prev; } /* * Can this new request be merged in front of next? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen)) { if (prev && addr < prev->vm_end) /* case 4 */ |
5beb49305
|
810 |
err = vma_adjust(prev, prev->vm_start, |
1da177e4c
|
811 812 |
addr, prev->vm_pgoff, NULL); else /* cases 3, 8 */ |
5beb49305
|
813 |
err = vma_adjust(area, addr, next->vm_end, |
1da177e4c
|
814 |
next->vm_pgoff - pglen, NULL); |
5beb49305
|
815 816 |
if (err) return NULL; |
b15d00b6a
|
817 |
khugepaged_enter_vma_merge(area); |
1da177e4c
|
818 819 820 821 822 823 824 |
return area; } return NULL; } /* |
d0e9fe175
|
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 |
* Rough compatbility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mm_sem held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that ACCESS_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mm_sem. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* |
1da177e4c
|
880 881 882 883 884 885 886 887 888 |
* find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { |
d0e9fe175
|
889 |
struct anon_vma *anon_vma; |
1da177e4c
|
890 |
struct vm_area_struct *near; |
1da177e4c
|
891 892 893 894 |
near = vma->vm_next; if (!near) goto try_prev; |
d0e9fe175
|
895 896 897 |
anon_vma = reusable_anon_vma(near, vma, near); if (anon_vma) return anon_vma; |
1da177e4c
|
898 |
try_prev: |
9be34c9d5
|
899 |
near = vma->vm_prev; |
1da177e4c
|
900 901 |
if (!near) goto none; |
d0e9fe175
|
902 903 904 |
anon_vma = reusable_anon_vma(near, near, vma); if (anon_vma) return anon_vma; |
1da177e4c
|
905 906 907 908 909 910 911 912 913 914 915 916 917 |
none: /* * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return NULL; } #ifdef CONFIG_PROC_FS |
ab50b8ed8
|
918 |
void vm_stat_account(struct mm_struct *mm, unsigned long flags, |
1da177e4c
|
919 920 921 922 |
struct file *file, long pages) { const unsigned long stack_flags = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); |
44de9d0ca
|
923 |
mm->total_vm += pages; |
1da177e4c
|
924 925 926 927 928 929 930 931 932 933 934 935 |
if (file) { mm->shared_vm += pages; if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC) mm->exec_vm += pages; } else if (flags & stack_flags) mm->stack_vm += pages; if (flags & (VM_RESERVED|VM_IO)) mm->reserved_vm += pages; } #endif /* CONFIG_PROC_FS */ /* |
404015308
|
936 937 938 939 940 941 942 943 944 945 946 947 948 |
* If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } /* |
27f5de796
|
949 |
* The caller must hold down_write(¤t->mm->mmap_sem). |
1da177e4c
|
950 |
*/ |
e3fc629d7
|
951 |
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, |
1da177e4c
|
952 953 954 955 |
unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff) { struct mm_struct * mm = current->mm; |
1da177e4c
|
956 |
struct inode *inode; |
ca16d140a
|
957 |
vm_flags_t vm_flags; |
1da177e4c
|
958 |
|
1da177e4c
|
959 960 961 962 963 964 965 |
/* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we dont add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) |
d3ac7f892
|
966 |
if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC))) |
1da177e4c
|
967 968 969 970 |
prot |= PROT_EXEC; if (!len) return -EINVAL; |
7cd94146c
|
971 972 |
if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); |
1da177e4c
|
973 974 |
/* Careful about overflows.. */ len = PAGE_ALIGN(len); |
9206de95b
|
975 |
if (!len) |
1da177e4c
|
976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 |
return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = get_unmapped_area(file, addr, len, pgoff, flags); if (addr & ~PAGE_MASK) return addr; /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; |
cdf7b3418
|
999 |
if (flags & MAP_LOCKED) |
1da177e4c
|
1000 1001 |
if (!can_do_mlock()) return -EPERM; |
ba470de43
|
1002 |
|
1da177e4c
|
1003 1004 1005 |
/* mlock MCL_FUTURE? */ if (vm_flags & VM_LOCKED) { unsigned long locked, lock_limit; |
93ea1d0a1
|
1006 1007 |
locked = len >> PAGE_SHIFT; locked += mm->locked_vm; |
59e99e5b9
|
1008 |
lock_limit = rlimit(RLIMIT_MEMLOCK); |
93ea1d0a1
|
1009 |
lock_limit >>= PAGE_SHIFT; |
1da177e4c
|
1010 1011 1012 |
if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } |
d3ac7f892
|
1013 |
inode = file ? file->f_path.dentry->d_inode : NULL; |
1da177e4c
|
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 |
if (file) { switch (flags & MAP_TYPE) { case MAP_SHARED: if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE)) return -EACCES; /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; /* * Make sure there are no mandatory locks on the file. */ if (locks_verify_locked(inode)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); /* fall through */ case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; |
d3ac7f892
|
1042 |
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) { |
80c5606c3
|
1043 1044 1045 1046 |
if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } |
80c5606c3
|
1047 1048 1049 |
if (!file->f_op || !file->f_op->mmap) return -ENODEV; |
1da177e4c
|
1050 1051 1052 1053 1054 1055 1056 1057 |
break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: |
ce3639426
|
1058 1059 1060 1061 |
/* * Ignore pgoff. */ pgoff = 0; |
1da177e4c
|
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 |
vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } |
5a6fe1259
|
1074 |
return mmap_region(file, addr, len, flags, vm_flags, pgoff); |
0165ab443
|
1075 |
} |
6be5ceb02
|
1076 |
|
66f0dc481
|
1077 1078 1079 1080 1081 1082 1083 1084 |
SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { struct file *file = NULL; unsigned long retval = -EBADF; if (!(flags & MAP_ANONYMOUS)) { |
120a795da
|
1085 |
audit_mmap_fd(fd, flags); |
66f0dc481
|
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 |
if (unlikely(flags & MAP_HUGETLB)) return -EINVAL; file = fget(fd); if (!file) goto out; } else if (flags & MAP_HUGETLB) { struct user_struct *user = NULL; /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called * A dummy user value is used because we are not locking * memory so no accounting is necessary */ |
40716e292
|
1099 1100 1101 |
file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE); |
66f0dc481
|
1102 1103 1104 1105 1106 |
if (IS_ERR(file)) return PTR_ERR(file); } flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); |
eb36c5873
|
1107 |
retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); |
66f0dc481
|
1108 1109 1110 1111 1112 |
if (file) fput(file); out: return retval; } |
a4679373c
|
1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 |
#ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (a.offset & ~PAGE_MASK) return -EINVAL; return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ |
4e950f6f0
|
1136 1137 1138 1139 1140 1141 1142 1143 |
/* * Some shared mappigns will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ int vma_wants_writenotify(struct vm_area_struct *vma) { |
ca16d140a
|
1144 |
vm_flags_t vm_flags = vma->vm_flags; |
4e950f6f0
|
1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 |
/* If it was private or non-writable, the write bit is already clear */ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) return 0; /* The backer wishes to know when pages are first written to? */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) return 1; /* The open routine did something to the protections already? */ if (pgprot_val(vma->vm_page_prot) != |
3ed75eb8f
|
1156 |
pgprot_val(vm_get_page_prot(vm_flags))) |
4e950f6f0
|
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 |
return 0; /* Specialty mapping? */ if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) return 0; /* Can the mapping track the dirty pages? */ return vma->vm_file && vma->vm_file->f_mapping && mapping_cap_account_dirty(vma->vm_file->f_mapping); } |
fc8744adc
|
1167 1168 |
/* * We account for memory if it's a private writeable mapping, |
5a6fe1259
|
1169 |
* not hugepages and VM_NORESERVE wasn't set. |
fc8744adc
|
1170 |
*/ |
ca16d140a
|
1171 |
static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) |
fc8744adc
|
1172 |
{ |
5a6fe1259
|
1173 1174 1175 1176 1177 1178 |
/* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return 0; |
fc8744adc
|
1179 1180 |
return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } |
0165ab443
|
1181 1182 |
unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, |
ca16d140a
|
1183 |
vm_flags_t vm_flags, unsigned long pgoff) |
0165ab443
|
1184 1185 1186 1187 1188 1189 1190 1191 |
{ struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; int correct_wcount = 0; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; struct inode *inode = file ? file->f_path.dentry->d_inode : NULL; |
1da177e4c
|
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 |
/* Clear old maps */ error = -ENOMEM; munmap_back: vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); if (vma && vma->vm_start < addr + len) { if (do_munmap(mm, addr, len)) return -ENOMEM; goto munmap_back; } /* Check against address space limit. */ |
119f657c7
|
1203 |
if (!may_expand_vm(mm, len >> PAGE_SHIFT)) |
1da177e4c
|
1204 |
return -ENOMEM; |
fc8744adc
|
1205 1206 |
/* * Set 'VM_NORESERVE' if we should not account for the |
5a6fe1259
|
1207 |
* memory use of this mapping. |
fc8744adc
|
1208 |
*/ |
5a6fe1259
|
1209 1210 1211 1212 1213 1214 1215 1216 1217 |
if ((flags & MAP_NORESERVE)) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } |
cdfd4325c
|
1218 |
|
fc8744adc
|
1219 1220 1221 |
/* * Private writable mapping: check memory availability */ |
5a6fe1259
|
1222 |
if (accountable_mapping(file, vm_flags)) { |
fc8744adc
|
1223 |
charged = len >> PAGE_SHIFT; |
191c54244
|
1224 |
if (security_vm_enough_memory_mm(mm, charged)) |
fc8744adc
|
1225 1226 |
return -ENOMEM; vm_flags |= VM_ACCOUNT; |
1da177e4c
|
1227 1228 1229 |
} /* |
de33c8db5
|
1230 |
* Can we just expand an old mapping? |
1da177e4c
|
1231 |
*/ |
de33c8db5
|
1232 1233 1234 |
vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); if (vma) goto out; |
1da177e4c
|
1235 1236 1237 1238 1239 1240 |
/* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ |
c5e3b83e9
|
1241 |
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c
|
1242 1243 1244 1245 |
if (!vma) { error = -ENOMEM; goto unacct_error; } |
1da177e4c
|
1246 1247 1248 1249 1250 |
vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; |
3ed75eb8f
|
1251 |
vma->vm_page_prot = vm_get_page_prot(vm_flags); |
1da177e4c
|
1252 |
vma->vm_pgoff = pgoff; |
5beb49305
|
1253 |
INIT_LIST_HEAD(&vma->anon_vma_chain); |
1da177e4c
|
1254 |
|
ce8fea7aa
|
1255 |
error = -EINVAL; /* when rejecting VM_GROWSDOWN|VM_GROWSUP */ |
1da177e4c
|
1256 |
if (file) { |
1da177e4c
|
1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 |
if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) goto free_vma; if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; correct_wcount = 1; } vma->vm_file = file; get_file(file); error = file->f_op->mmap(file, vma); if (error) goto unmap_and_free_vma; |
925d1c401
|
1270 1271 |
if (vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); |
f8dbf0a7a
|
1272 1273 1274 1275 1276 1277 1278 1279 1280 |
/* Can addr have changed?? * * Answer: Yes, several device drivers can do it in their * f_op->mmap method. -DaveM */ addr = vma->vm_start; pgoff = vma->vm_pgoff; vm_flags = vma->vm_flags; |
1da177e4c
|
1281 |
} else if (vm_flags & VM_SHARED) { |
835ee7978
|
1282 1283 |
if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP))) goto free_vma; |
1da177e4c
|
1284 1285 1286 1287 |
error = shmem_zero_setup(vma); if (error) goto free_vma; } |
c9d0bf241
|
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 |
if (vma_wants_writenotify(vma)) { pgprot_t pprot = vma->vm_page_prot; /* Can vma->vm_page_prot have changed?? * * Answer: Yes, drivers may have changed it in their * f_op->mmap method. * * Ensures that vmas marked as uncached stay that way. */ |
1ddd439ef
|
1298 |
vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED); |
c9d0bf241
|
1299 1300 1301 |
if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot))) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); } |
d08b3851d
|
1302 |
|
de33c8db5
|
1303 1304 |
vma_link(mm, vma, prev, rb_link, rb_parent); file = vma->vm_file; |
4d3d5b41a
|
1305 1306 1307 1308 1309 |
/* Once vma denies write, undo our temporary denial count */ if (correct_wcount) atomic_inc(&inode->i_writecount); out: |
cdd6c482c
|
1310 |
perf_event_mmap(vma); |
0a4a93919
|
1311 |
|
ab50b8ed8
|
1312 |
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); |
1da177e4c
|
1313 |
if (vm_flags & VM_LOCKED) { |
06f9d8c2b
|
1314 1315 |
if (!mlock_vma_pages_range(vma, addr, addr + len)) mm->locked_vm += (len >> PAGE_SHIFT); |
ba470de43
|
1316 |
} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) |
54cb8821d
|
1317 |
make_pages_present(addr, addr + len); |
2b1444983
|
1318 |
|
7b2d81d48
|
1319 |
if (file && uprobe_mmap(vma)) |
2b1444983
|
1320 1321 |
/* matching probes but cannot insert */ goto unmap_and_free_vma; |
1da177e4c
|
1322 1323 1324 1325 1326 1327 1328 1329 1330 |
return addr; unmap_and_free_vma: if (correct_wcount) atomic_inc(&inode->i_writecount); vma->vm_file = NULL; fput(file); /* Undo any partial mapping done by a device driver. */ |
e0da382c9
|
1331 1332 |
unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); charged = 0; |
1da177e4c
|
1333 1334 1335 1336 1337 1338 1339 |
free_vma: kmem_cache_free(vm_area_cachep, vma); unacct_error: if (charged) vm_unacct_memory(charged); return error; } |
1da177e4c
|
1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 |
/* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; if (len > TASK_SIZE) return -ENOMEM; |
06abdfb47
|
1362 1363 |
if (flags & MAP_FIXED) return addr; |
1da177e4c
|
1364 1365 1366 1367 1368 1369 1370 |
if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) return addr; } |
1363c3cd8
|
1371 1372 1373 1374 1375 1376 |
if (len > mm->cached_hole_size) { start_addr = addr = mm->free_area_cache; } else { start_addr = addr = TASK_UNMAPPED_BASE; mm->cached_hole_size = 0; } |
1da177e4c
|
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 |
full_search: for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ if (TASK_SIZE - len < addr) { /* * Start a new search - just in case we missed * some holes. */ if (start_addr != TASK_UNMAPPED_BASE) { |
1363c3cd8
|
1387 1388 1389 |
addr = TASK_UNMAPPED_BASE; start_addr = addr; mm->cached_hole_size = 0; |
1da177e4c
|
1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 |
goto full_search; } return -ENOMEM; } if (!vma || addr + len <= vma->vm_start) { /* * Remember the place where we stopped the search: */ mm->free_area_cache = addr + len; return addr; } |
1363c3cd8
|
1401 1402 |
if (addr + mm->cached_hole_size < vma->vm_start) mm->cached_hole_size = vma->vm_start - addr; |
1da177e4c
|
1403 1404 1405 1406 |
addr = vma->vm_end; } } #endif |
1363c3cd8
|
1407 |
void arch_unmap_area(struct mm_struct *mm, unsigned long addr) |
1da177e4c
|
1408 1409 1410 1411 |
{ /* * Is this a new hole at the lowest possible address? */ |
f44d21985
|
1412 |
if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) |
1363c3cd8
|
1413 |
mm->free_area_cache = addr; |
1da177e4c
|
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 |
} /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; |
b716ad953
|
1428 |
unsigned long addr = addr0, start_addr; |
1da177e4c
|
1429 1430 1431 1432 |
/* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; |
06abdfb47
|
1433 1434 |
if (flags & MAP_FIXED) return addr; |
1da177e4c
|
1435 1436 1437 1438 1439 1440 1441 1442 |
/* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) return addr; } |
1363c3cd8
|
1443 1444 1445 1446 1447 |
/* check if free_area_cache is useful for us */ if (len <= mm->cached_hole_size) { mm->cached_hole_size = 0; mm->free_area_cache = mm->mmap_base; } |
b716ad953
|
1448 |
try_again: |
1da177e4c
|
1449 |
/* either no address requested or can't fit in requested address hole */ |
b716ad953
|
1450 |
start_addr = addr = mm->free_area_cache; |
73219d178
|
1451 |
|
b716ad953
|
1452 1453 |
if (addr < len) goto fail; |
1da177e4c
|
1454 |
|
b716ad953
|
1455 |
addr -= len; |
1da177e4c
|
1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 |
do { /* * Lookup failure means no vma is above this address, * else if new region fits below vma->vm_start, * return with success: */ vma = find_vma(mm, addr); if (!vma || addr+len <= vma->vm_start) /* remember the address as a hint for next time */ return (mm->free_area_cache = addr); |
1363c3cd8
|
1466 1467 1468 |
/* remember the largest hole we saw so far */ if (addr + mm->cached_hole_size < vma->vm_start) mm->cached_hole_size = vma->vm_start - addr; |
1da177e4c
|
1469 1470 |
/* try just below the current vma->vm_start */ addr = vma->vm_start-len; |
49a43876b
|
1471 |
} while (len < vma->vm_start); |
1da177e4c
|
1472 |
|
b716ad953
|
1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 |
fail: /* * if hint left us with no space for the requested * mapping then try again: * * Note: this is different with the case of bottomup * which does the fully line-search, but we use find_vma * here that causes some holes skipped. */ if (start_addr != mm->mmap_base) { mm->free_area_cache = mm->mmap_base; mm->cached_hole_size = 0; goto try_again; } |
1da177e4c
|
1487 1488 1489 1490 1491 1492 |
/* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ |
1363c3cd8
|
1493 1494 |
mm->cached_hole_size = ~0UL; mm->free_area_cache = TASK_UNMAPPED_BASE; |
1da177e4c
|
1495 1496 1497 1498 1499 |
addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); /* * Restore the topdown base: */ mm->free_area_cache = mm->mmap_base; |
1363c3cd8
|
1500 |
mm->cached_hole_size = ~0UL; |
1da177e4c
|
1501 1502 1503 1504 |
return addr; } #endif |
1363c3cd8
|
1505 |
void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) |
1da177e4c
|
1506 1507 1508 1509 |
{ /* * Is this a new hole at the highest possible address? */ |
1363c3cd8
|
1510 1511 |
if (addr > mm->free_area_cache) mm->free_area_cache = addr; |
1da177e4c
|
1512 1513 |
/* dont allow allocations above current base */ |
1363c3cd8
|
1514 1515 |
if (mm->free_area_cache > mm->mmap_base) mm->free_area_cache = mm->mmap_base; |
1da177e4c
|
1516 1517 1518 1519 1520 1521 |
} unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { |
06abdfb47
|
1522 1523 |
unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); |
9206de95b
|
1524 1525 1526 1527 1528 1529 1530 |
unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; |
06abdfb47
|
1531 1532 1533 1534 1535 1536 |
get_area = current->mm->get_unmapped_area; if (file && file->f_op && file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; |
1da177e4c
|
1537 |
|
07ab67c8d
|
1538 1539 1540 1541 |
if (addr > TASK_SIZE - len) return -ENOMEM; if (addr & ~PAGE_MASK) return -EINVAL; |
06abdfb47
|
1542 |
|
9ac4ed4bd
|
1543 1544 1545 |
addr = arch_rebalance_pgtables(addr, len); error = security_mmap_addr(addr); return error ? error : addr; |
1da177e4c
|
1546 1547 1548 1549 1550 |
} EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ |
48aae4255
|
1551 |
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) |
1da177e4c
|
1552 1553 |
{ struct vm_area_struct *vma = NULL; |
841e31e5c
|
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 |
if (WARN_ON_ONCE(!mm)) /* Remove this in linux-3.6 */ return NULL; /* Check the cache first. */ /* (Cache hit rate is typically around 35%.) */ vma = mm->mmap_cache; if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { struct rb_node *rb_node; rb_node = mm->mm_rb.rb_node; vma = NULL; while (rb_node) { struct vm_area_struct *vma_tmp; vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); if (vma_tmp->vm_end > addr) { vma = vma_tmp; if (vma_tmp->vm_start <= addr) break; rb_node = rb_node->rb_left; } else rb_node = rb_node->rb_right; |
1da177e4c
|
1579 |
} |
841e31e5c
|
1580 1581 |
if (vma) mm->mmap_cache = vma; |
1da177e4c
|
1582 1583 1584 1585 1586 |
} return vma; } EXPORT_SYMBOL(find_vma); |
6bd4837de
|
1587 1588 |
/* * Same as find_vma, but also return a pointer to the previous VMA in *pprev. |
6bd4837de
|
1589 |
*/ |
1da177e4c
|
1590 1591 1592 1593 |
struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { |
6bd4837de
|
1594 |
struct vm_area_struct *vma; |
1da177e4c
|
1595 |
|
6bd4837de
|
1596 |
vma = find_vma(mm, addr); |
83cd904d2
|
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 |
if (vma) { *pprev = vma->vm_prev; } else { struct rb_node *rb_node = mm->mm_rb.rb_node; *pprev = NULL; while (rb_node) { *pprev = rb_entry(rb_node, struct vm_area_struct, vm_rb); rb_node = rb_node->rb_right; } } |
6bd4837de
|
1607 |
return vma; |
1da177e4c
|
1608 1609 1610 1611 1612 1613 1614 |
} /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ |
48aae4255
|
1615 |
static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) |
1da177e4c
|
1616 1617 1618 |
{ struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; |
0d59a01bc
|
1619 |
unsigned long new_start; |
1da177e4c
|
1620 1621 |
/* address space limit tests */ |
119f657c7
|
1622 |
if (!may_expand_vm(mm, grow)) |
1da177e4c
|
1623 1624 1625 |
return -ENOMEM; /* Stack limit test */ |
59e99e5b9
|
1626 |
if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) |
1da177e4c
|
1627 1628 1629 1630 1631 1632 1633 |
return -ENOMEM; /* mlock limit tests */ if (vma->vm_flags & VM_LOCKED) { unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; |
59e99e5b9
|
1634 1635 |
limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); limit >>= PAGE_SHIFT; |
1da177e4c
|
1636 1637 1638 |
if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; } |
0d59a01bc
|
1639 1640 1641 1642 1643 |
/* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; |
1da177e4c
|
1644 1645 1646 1647 |
/* * Overcommit.. This must be the final test, as it will * update security statistics. */ |
05fa199d4
|
1648 |
if (security_vm_enough_memory_mm(mm, grow)) |
1da177e4c
|
1649 1650 1651 |
return -ENOMEM; /* Ok, everything looks good - let it rip */ |
1da177e4c
|
1652 1653 |
if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; |
ab50b8ed8
|
1654 |
vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); |
1da177e4c
|
1655 1656 |
return 0; } |
46dea3d09
|
1657 |
#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) |
1da177e4c
|
1658 |
/* |
46dea3d09
|
1659 1660 |
* PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. |
1da177e4c
|
1661 |
*/ |
46dea3d09
|
1662 |
int expand_upwards(struct vm_area_struct *vma, unsigned long address) |
1da177e4c
|
1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 |
{ int error; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* * We must make sure the anon_vma is allocated * so that the anon_vma locking is not a noop. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; |
bb4a340e0
|
1675 |
vma_lock_anon_vma(vma); |
1da177e4c
|
1676 1677 1678 1679 1680 |
/* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. |
06b32f3ab
|
1681 |
* Also guard against wrapping around to address 0. |
1da177e4c
|
1682 |
*/ |
06b32f3ab
|
1683 1684 1685 |
if (address < PAGE_ALIGN(address+4)) address = PAGE_ALIGN(address+4); else { |
bb4a340e0
|
1686 |
vma_unlock_anon_vma(vma); |
06b32f3ab
|
1687 1688 |
return -ENOMEM; } |
1da177e4c
|
1689 1690 1691 1692 1693 1694 1695 1696 |
error = 0; /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; |
42c36f63a
|
1697 1698 1699 1700 1701 1702 1703 |
error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { vma->vm_end = address; perf_event_mmap(vma); } |
3af9e8592
|
1704 |
} |
1da177e4c
|
1705 |
} |
bb4a340e0
|
1706 |
vma_unlock_anon_vma(vma); |
b15d00b6a
|
1707 |
khugepaged_enter_vma_merge(vma); |
1da177e4c
|
1708 1709 |
return error; } |
46dea3d09
|
1710 |
#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ |
1da177e4c
|
1711 1712 1713 |
/* * vma is the first one with address < vma->vm_start. Have to extend vma. */ |
d05f3169c
|
1714 |
int expand_downwards(struct vm_area_struct *vma, |
b6a2fea39
|
1715 |
unsigned long address) |
1da177e4c
|
1716 1717 1718 1719 1720 1721 1722 1723 1724 |
{ int error; /* * We must make sure the anon_vma is allocated * so that the anon_vma locking is not a noop. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; |
8869477a4
|
1725 1726 |
address &= PAGE_MASK; |
e5467859f
|
1727 |
error = security_mmap_addr(address); |
8869477a4
|
1728 1729 |
if (error) return error; |
bb4a340e0
|
1730 |
vma_lock_anon_vma(vma); |
1da177e4c
|
1731 1732 1733 1734 1735 1736 |
/* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ |
1da177e4c
|
1737 1738 1739 1740 1741 1742 1743 |
/* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; |
a626ca6a6
|
1744 1745 1746 1747 1748 1749 1750 1751 |
error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { vma->vm_start = address; vma->vm_pgoff -= grow; perf_event_mmap(vma); } |
1da177e4c
|
1752 1753 |
} } |
bb4a340e0
|
1754 |
vma_unlock_anon_vma(vma); |
b15d00b6a
|
1755 |
khugepaged_enter_vma_merge(vma); |
1da177e4c
|
1756 1757 |
return error; } |
b6a2fea39
|
1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 |
#ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct * find_extend_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; |
1c1271850
|
1773 |
if (!prev || expand_stack(prev, addr)) |
b6a2fea39
|
1774 |
return NULL; |
ba470de43
|
1775 |
if (prev->vm_flags & VM_LOCKED) { |
c58267c32
|
1776 |
mlock_vma_pages_range(prev, addr, prev->vm_end); |
ba470de43
|
1777 |
} |
b6a2fea39
|
1778 1779 1780 1781 1782 1783 1784 |
return prev; } #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } |
1da177e4c
|
1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 |
struct vm_area_struct * find_extend_vma(struct mm_struct * mm, unsigned long addr) { struct vm_area_struct * vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm,addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; |
ba470de43
|
1802 |
if (vma->vm_flags & VM_LOCKED) { |
c58267c32
|
1803 |
mlock_vma_pages_range(vma, addr, start); |
ba470de43
|
1804 |
} |
1da177e4c
|
1805 1806 1807 |
return vma; } #endif |
1da177e4c
|
1808 |
/* |
2c0b38146
|
1809 |
* Ok - we have the memory areas we should free on the vma list, |
1da177e4c
|
1810 |
* so release them, and do the vma updates. |
2c0b38146
|
1811 1812 |
* * Called with the mm semaphore held. |
1da177e4c
|
1813 |
*/ |
2c0b38146
|
1814 |
static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) |
1da177e4c
|
1815 |
{ |
4f74d2c8e
|
1816 |
unsigned long nr_accounted = 0; |
365e9c87a
|
1817 1818 |
/* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); |
1da177e4c
|
1819 |
do { |
2c0b38146
|
1820 |
long nrpages = vma_pages(vma); |
4f74d2c8e
|
1821 1822 |
if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; |
2c0b38146
|
1823 |
vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); |
a8fb5618d
|
1824 |
vma = remove_vma(vma); |
146425a31
|
1825 |
} while (vma); |
4f74d2c8e
|
1826 |
vm_unacct_memory(nr_accounted); |
1da177e4c
|
1827 1828 1829 1830 1831 1832 |
validate_mm(mm); } /* * Get rid of page table information in the indicated region. * |
f10df6860
|
1833 |
* Called with the mm semaphore held. |
1da177e4c
|
1834 1835 |
*/ static void unmap_region(struct mm_struct *mm, |
e0da382c9
|
1836 1837 |
struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end) |
1da177e4c
|
1838 |
{ |
e0da382c9
|
1839 |
struct vm_area_struct *next = prev? prev->vm_next: mm->mmap; |
d16dfc550
|
1840 |
struct mmu_gather tlb; |
1da177e4c
|
1841 1842 |
lru_add_drain(); |
d16dfc550
|
1843 |
tlb_gather_mmu(&tlb, mm, 0); |
365e9c87a
|
1844 |
update_hiwater_rss(mm); |
4f74d2c8e
|
1845 |
unmap_vmas(&tlb, vma, start, end); |
d16dfc550
|
1846 1847 1848 |
free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : 0); tlb_finish_mmu(&tlb, start, end); |
1da177e4c
|
1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 |
} /* * Create a list of vma's touched by the unmap, removing them from the mm's * vma list as we go.. */ static void detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long end) { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; |
1363c3cd8
|
1861 |
unsigned long addr; |
1da177e4c
|
1862 1863 |
insertion_point = (prev ? &prev->vm_next : &mm->mmap); |
297c5eee3
|
1864 |
vma->vm_prev = NULL; |
1da177e4c
|
1865 1866 1867 1868 1869 1870 1871 |
do { rb_erase(&vma->vm_rb, &mm->mm_rb); mm->map_count--; tail_vma = vma; vma = vma->vm_next; } while (vma && vma->vm_start < end); *insertion_point = vma; |
297c5eee3
|
1872 1873 |
if (vma) vma->vm_prev = prev; |
1da177e4c
|
1874 |
tail_vma->vm_next = NULL; |
1363c3cd8
|
1875 1876 1877 1878 1879 |
if (mm->unmap_area == arch_unmap_area) addr = prev ? prev->vm_end : mm->mmap_base; else addr = vma ? vma->vm_start : mm->mmap_base; mm->unmap_area(mm, addr); |
1da177e4c
|
1880 1881 1882 1883 |
mm->mmap_cache = NULL; /* Kill the cache. */ } /* |
659ace584
|
1884 1885 |
* __split_vma() bypasses sysctl_max_map_count checking. We use this on the * munmap path where it doesn't make sense to fail. |
1da177e4c
|
1886 |
*/ |
659ace584
|
1887 |
static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, |
1da177e4c
|
1888 1889 1890 1891 |
unsigned long addr, int new_below) { struct mempolicy *pol; struct vm_area_struct *new; |
5beb49305
|
1892 |
int err = -ENOMEM; |
1da177e4c
|
1893 |
|
a55164389
|
1894 1895 |
if (is_vm_hugetlb_page(vma) && (addr & ~(huge_page_mask(hstate_vma(vma))))) |
1da177e4c
|
1896 |
return -EINVAL; |
e94b17660
|
1897 |
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c
|
1898 |
if (!new) |
5beb49305
|
1899 |
goto out_err; |
1da177e4c
|
1900 1901 1902 |
/* most fields are the same, copy all, and then fixup */ *new = *vma; |
5beb49305
|
1903 |
INIT_LIST_HEAD(&new->anon_vma_chain); |
1da177e4c
|
1904 1905 1906 1907 1908 1909 |
if (new_below) new->vm_end = addr; else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } |
846a16bf0
|
1910 |
pol = mpol_dup(vma_policy(vma)); |
1da177e4c
|
1911 |
if (IS_ERR(pol)) { |
5beb49305
|
1912 1913 |
err = PTR_ERR(pol); goto out_free_vma; |
1da177e4c
|
1914 1915 |
} vma_set_policy(new, pol); |
5beb49305
|
1916 1917 |
if (anon_vma_clone(new, vma)) goto out_free_mpol; |
925d1c401
|
1918 |
if (new->vm_file) { |
1da177e4c
|
1919 |
get_file(new->vm_file); |
925d1c401
|
1920 1921 1922 |
if (vma->vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); } |
1da177e4c
|
1923 1924 1925 1926 1927 |
if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); if (new_below) |
5beb49305
|
1928 |
err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + |
1da177e4c
|
1929 1930 |
((addr - new->vm_start) >> PAGE_SHIFT), new); else |
5beb49305
|
1931 |
err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); |
1da177e4c
|
1932 |
|
5beb49305
|
1933 1934 1935 1936 1937 |
/* Success. */ if (!err) return 0; /* Clean everything up if vma_adjust failed. */ |
589275338
|
1938 1939 |
if (new->vm_ops && new->vm_ops->close) new->vm_ops->close(new); |
5beb49305
|
1940 1941 1942 1943 1944 |
if (new->vm_file) { if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); fput(new->vm_file); } |
2aeadc30d
|
1945 |
unlink_anon_vmas(new); |
5beb49305
|
1946 1947 1948 1949 1950 1951 |
out_free_mpol: mpol_put(pol); out_free_vma: kmem_cache_free(vm_area_cachep, new); out_err: return err; |
1da177e4c
|
1952 |
} |
659ace584
|
1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 |
/* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(mm, vma, addr, new_below); } |
1da177e4c
|
1965 1966 1967 1968 1969 1970 1971 1972 |
/* Munmap is split into 2 main parts -- this part which finds * what needs doing, and the areas themselves, which do the * work. This now handles partial unmappings. * Jeremy Fitzhardinge <jeremy@goop.org> */ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) { unsigned long end; |
146425a31
|
1973 |
struct vm_area_struct *vma, *prev, *last; |
1da177e4c
|
1974 1975 1976 1977 1978 1979 1980 1981 |
if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; if ((len = PAGE_ALIGN(len)) == 0) return -EINVAL; /* Find the first overlapping VMA */ |
9be34c9d5
|
1982 |
vma = find_vma(mm, start); |
146425a31
|
1983 |
if (!vma) |
1da177e4c
|
1984 |
return 0; |
9be34c9d5
|
1985 |
prev = vma->vm_prev; |
146425a31
|
1986 |
/* we have start < vma->vm_end */ |
1da177e4c
|
1987 1988 1989 |
/* if it doesn't overlap, we have nothing.. */ end = start + len; |
146425a31
|
1990 |
if (vma->vm_start >= end) |
1da177e4c
|
1991 1992 1993 1994 1995 1996 1997 1998 1999 |
return 0; /* * If we need to split any vma, do it now to save pain later. * * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially * unmapped vm_area_struct will remain in use: so lower split_vma * places tmp vma above, and higher split_vma places tmp vma below. */ |
146425a31
|
2000 |
if (start > vma->vm_start) { |
659ace584
|
2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 |
int error; /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) return -ENOMEM; error = __split_vma(mm, vma, start, 0); |
1da177e4c
|
2012 2013 |
if (error) return error; |
146425a31
|
2014 |
prev = vma; |
1da177e4c
|
2015 2016 2017 2018 2019 |
} /* Does it split the last one? */ last = find_vma(mm, end); if (last && end > last->vm_start) { |
659ace584
|
2020 |
int error = __split_vma(mm, last, end, 1); |
1da177e4c
|
2021 2022 2023 |
if (error) return error; } |
146425a31
|
2024 |
vma = prev? prev->vm_next: mm->mmap; |
1da177e4c
|
2025 2026 |
/* |
ba470de43
|
2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 |
* unlock any mlock()ed ranges before detaching vmas */ if (mm->locked_vm) { struct vm_area_struct *tmp = vma; while (tmp && tmp->vm_start < end) { if (tmp->vm_flags & VM_LOCKED) { mm->locked_vm -= vma_pages(tmp); munlock_vma_pages_all(tmp); } tmp = tmp->vm_next; } } /* |
1da177e4c
|
2041 2042 |
* Remove the vma's, and unmap the actual pages */ |
146425a31
|
2043 2044 |
detach_vmas_to_be_unmapped(mm, vma, prev, end); unmap_region(mm, vma, prev, start, end); |
1da177e4c
|
2045 2046 |
/* Fix up all other VM information */ |
2c0b38146
|
2047 |
remove_vma_list(mm, vma); |
1da177e4c
|
2048 2049 2050 |
return 0; } |
1da177e4c
|
2051 |
|
bfce281c2
|
2052 |
int vm_munmap(unsigned long start, size_t len) |
1da177e4c
|
2053 2054 |
{ int ret; |
bfce281c2
|
2055 |
struct mm_struct *mm = current->mm; |
1da177e4c
|
2056 2057 |
down_write(&mm->mmap_sem); |
a46ef99d8
|
2058 |
ret = do_munmap(mm, start, len); |
1da177e4c
|
2059 2060 2061 |
up_write(&mm->mmap_sem); return ret; } |
a46ef99d8
|
2062 2063 2064 2065 2066 |
EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { profile_munmap(addr); |
bfce281c2
|
2067 |
return vm_munmap(addr, len); |
a46ef99d8
|
2068 |
} |
1da177e4c
|
2069 2070 2071 |
static inline void verify_mm_writelocked(struct mm_struct *mm) { |
a241ec65a
|
2072 |
#ifdef CONFIG_DEBUG_VM |
1da177e4c
|
2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 |
if (unlikely(down_read_trylock(&mm->mmap_sem))) { WARN_ON(1); up_read(&mm->mmap_sem); } #endif } /* * this is really a simplified "do_mmap". it only handles * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ |
e4eb1ff61
|
2085 |
static unsigned long do_brk(unsigned long addr, unsigned long len) |
1da177e4c
|
2086 2087 2088 2089 2090 2091 |
{ struct mm_struct * mm = current->mm; struct vm_area_struct * vma, * prev; unsigned long flags; struct rb_node ** rb_link, * rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; |
3a4597568
|
2092 |
int error; |
1da177e4c
|
2093 2094 2095 2096 |
len = PAGE_ALIGN(len); if (!len) return addr; |
3a4597568
|
2097 |
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; |
2c6a10161
|
2098 2099 |
error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (error & ~PAGE_MASK) |
3a4597568
|
2100 |
return error; |
1da177e4c
|
2101 2102 2103 2104 2105 |
/* * mlock MCL_FUTURE? */ if (mm->def_flags & VM_LOCKED) { unsigned long locked, lock_limit; |
93ea1d0a1
|
2106 2107 |
locked = len >> PAGE_SHIFT; locked += mm->locked_vm; |
59e99e5b9
|
2108 |
lock_limit = rlimit(RLIMIT_MEMLOCK); |
93ea1d0a1
|
2109 |
lock_limit >>= PAGE_SHIFT; |
1da177e4c
|
2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 |
if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } /* * mm->mmap_sem is required to protect against another thread * changing the mappings in case we sleep. */ verify_mm_writelocked(mm); /* * Clear old maps. this also does some error checking for us */ munmap_back: vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); if (vma && vma->vm_start < addr + len) { if (do_munmap(mm, addr, len)) return -ENOMEM; goto munmap_back; } /* Check against address space limits *after* clearing old maps... */ |
119f657c7
|
2132 |
if (!may_expand_vm(mm, len >> PAGE_SHIFT)) |
1da177e4c
|
2133 2134 2135 2136 |
return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; |
191c54244
|
2137 |
if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) |
1da177e4c
|
2138 |
return -ENOMEM; |
1da177e4c
|
2139 |
/* Can we just expand an old private anonymous mapping? */ |
ba470de43
|
2140 2141 2142 |
vma = vma_merge(mm, prev, addr, addr + len, flags, NULL, NULL, pgoff, NULL); if (vma) |
1da177e4c
|
2143 2144 2145 2146 2147 |
goto out; /* * create a vma struct for an anonymous mapping */ |
c5e3b83e9
|
2148 |
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c
|
2149 2150 2151 2152 |
if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } |
1da177e4c
|
2153 |
|
5beb49305
|
2154 |
INIT_LIST_HEAD(&vma->anon_vma_chain); |
1da177e4c
|
2155 2156 2157 2158 2159 |
vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; vma->vm_flags = flags; |
3ed75eb8f
|
2160 |
vma->vm_page_prot = vm_get_page_prot(flags); |
1da177e4c
|
2161 2162 |
vma_link(mm, vma, prev, rb_link, rb_parent); out: |
3af9e8592
|
2163 |
perf_event_mmap(vma); |
1da177e4c
|
2164 2165 |
mm->total_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) { |
ba470de43
|
2166 2167 |
if (!mlock_vma_pages_range(vma, addr, addr + len)) mm->locked_vm += (len >> PAGE_SHIFT); |
1da177e4c
|
2168 2169 2170 |
} return addr; } |
e4eb1ff61
|
2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 |
unsigned long vm_brk(unsigned long addr, unsigned long len) { struct mm_struct *mm = current->mm; unsigned long ret; down_write(&mm->mmap_sem); ret = do_brk(addr, len); up_write(&mm->mmap_sem); return ret; } EXPORT_SYMBOL(vm_brk); |
1da177e4c
|
2182 2183 2184 2185 |
/* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { |
d16dfc550
|
2186 |
struct mmu_gather tlb; |
ba470de43
|
2187 |
struct vm_area_struct *vma; |
1da177e4c
|
2188 |
unsigned long nr_accounted = 0; |
d6dd61c83
|
2189 |
/* mm's last user has gone, and its about to be pulled down */ |
cddb8a5c1
|
2190 |
mmu_notifier_release(mm); |
d6dd61c83
|
2191 |
|
ba470de43
|
2192 2193 2194 2195 2196 2197 2198 2199 |
if (mm->locked_vm) { vma = mm->mmap; while (vma) { if (vma->vm_flags & VM_LOCKED) munlock_vma_pages_all(vma); vma = vma->vm_next; } } |
9480c53e9
|
2200 2201 |
arch_exit_mmap(mm); |
ba470de43
|
2202 |
vma = mm->mmap; |
9480c53e9
|
2203 2204 |
if (!vma) /* Can happen if dup_mmap() received an OOM */ return; |
1da177e4c
|
2205 |
lru_add_drain(); |
1da177e4c
|
2206 |
flush_cache_mm(mm); |
d16dfc550
|
2207 |
tlb_gather_mmu(&tlb, mm, 1); |
901608d90
|
2208 |
/* update_hiwater_rss(mm) here? but nobody should be looking */ |
e0da382c9
|
2209 |
/* Use -1 here to ensure all VMAs in the mm are unmapped */ |
4f74d2c8e
|
2210 |
unmap_vmas(&tlb, vma, 0, -1); |
9ba692948
|
2211 |
|
d16dfc550
|
2212 |
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); |
853f5e264
|
2213 |
tlb_finish_mmu(&tlb, 0, -1); |
1da177e4c
|
2214 |
|
1da177e4c
|
2215 |
/* |
8f4f8c164
|
2216 2217 |
* Walk the list again, actually closing and freeing it, * with preemption enabled, without holding any MM locks. |
1da177e4c
|
2218 |
*/ |
4f74d2c8e
|
2219 2220 2221 |
while (vma) { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); |
a8fb5618d
|
2222 |
vma = remove_vma(vma); |
4f74d2c8e
|
2223 2224 |
} vm_unacct_memory(nr_accounted); |
e0da382c9
|
2225 |
|
f9aed62a2
|
2226 |
WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); |
1da177e4c
|
2227 2228 2229 2230 |
} /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL |
3d48ae45e
|
2231 |
* then i_mmap_mutex is taken here. |
1da177e4c
|
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 |
*/ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) { struct vm_area_struct * __vma, * prev; struct rb_node ** rb_link, * rb_parent; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap_pgoff and in do_brk. */ if (!vma->vm_file) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } __vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent); if (__vma && __vma->vm_start < vma->vm_end) return -ENOMEM; |
2fd4ef85e
|
2257 |
if ((vma->vm_flags & VM_ACCOUNT) && |
34b4e4aa3
|
2258 |
security_vm_enough_memory_mm(mm, vma_pages(vma))) |
2fd4ef85e
|
2259 |
return -ENOMEM; |
2b1444983
|
2260 |
|
1da177e4c
|
2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 |
vma_link(mm, vma, prev, rb_link, rb_parent); return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; struct mempolicy *pol; |
948f017b0
|
2278 |
bool faulted_in_anon_vma = true; |
1da177e4c
|
2279 2280 2281 2282 2283 |
/* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ |
948f017b0
|
2284 |
if (unlikely(!vma->vm_file && !vma->anon_vma)) { |
1da177e4c
|
2285 |
pgoff = addr >> PAGE_SHIFT; |
948f017b0
|
2286 2287 |
faulted_in_anon_vma = false; } |
1da177e4c
|
2288 2289 2290 2291 2292 2293 2294 2295 |
find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma */ |
948f017b0
|
2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 |
if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON(faulted_in_anon_vma); |
1da177e4c
|
2311 |
*vmap = new_vma; |
948f017b0
|
2312 2313 |
} else anon_vma_moveto_tail(new_vma); |
1da177e4c
|
2314 |
} else { |
e94b17660
|
2315 |
new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c
|
2316 2317 |
if (new_vma) { *new_vma = *vma; |
846a16bf0
|
2318 |
pol = mpol_dup(vma_policy(vma)); |
5beb49305
|
2319 2320 2321 2322 2323 |
if (IS_ERR(pol)) goto out_free_vma; INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; |
1da177e4c
|
2324 2325 2326 2327 |
vma_set_policy(new_vma, pol); new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; |
925d1c401
|
2328 |
if (new_vma->vm_file) { |
1da177e4c
|
2329 |
get_file(new_vma->vm_file); |
2b1444983
|
2330 |
|
925d1c401
|
2331 2332 2333 |
if (vma->vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); } |
1da177e4c
|
2334 2335 2336 2337 2338 2339 |
if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); } } return new_vma; |
5beb49305
|
2340 2341 2342 2343 2344 2345 |
out_free_mempol: mpol_put(pol); out_free_vma: kmem_cache_free(vm_area_cachep, new_vma); return NULL; |
1da177e4c
|
2346 |
} |
119f657c7
|
2347 2348 2349 2350 2351 2352 2353 2354 2355 |
/* * Return true if the calling process may expand its vm space by the passed * number of pages */ int may_expand_vm(struct mm_struct *mm, unsigned long npages) { unsigned long cur = mm->total_vm; /* pages */ unsigned long lim; |
59e99e5b9
|
2356 |
lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT; |
119f657c7
|
2357 2358 2359 2360 2361 |
if (cur + npages > lim) return 0; return 1; } |
fa5dc22f8
|
2362 |
|
b1d0e4f53
|
2363 2364 |
static int special_mapping_fault(struct vm_area_struct *vma, struct vm_fault *vmf) |
fa5dc22f8
|
2365 |
{ |
b1d0e4f53
|
2366 |
pgoff_t pgoff; |
fa5dc22f8
|
2367 |
struct page **pages; |
b1d0e4f53
|
2368 2369 2370 2371 2372 2373 2374 |
/* * special mappings have no vm_file, and in that case, the mm * uses vm_pgoff internally. So we have to subtract it from here. * We are allowed to do this because we are the mm; do not copy * this code into drivers! */ pgoff = vmf->pgoff - vma->vm_pgoff; |
fa5dc22f8
|
2375 |
|
b1d0e4f53
|
2376 2377 |
for (pages = vma->vm_private_data; pgoff && *pages; ++pages) pgoff--; |
fa5dc22f8
|
2378 2379 2380 2381 |
if (*pages) { struct page *page = *pages; get_page(page); |
b1d0e4f53
|
2382 2383 |
vmf->page = page; return 0; |
fa5dc22f8
|
2384 |
} |
b1d0e4f53
|
2385 |
return VM_FAULT_SIGBUS; |
fa5dc22f8
|
2386 2387 2388 2389 2390 2391 2392 2393 |
} /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } |
f0f37e2f7
|
2394 |
static const struct vm_operations_struct special_mapping_vmops = { |
fa5dc22f8
|
2395 |
.close = special_mapping_close, |
b1d0e4f53
|
2396 |
.fault = special_mapping_fault, |
fa5dc22f8
|
2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 |
}; /* * Called with mm->mmap_sem held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { |
462e635e5
|
2412 |
int ret; |
fa5dc22f8
|
2413 2414 2415 2416 2417 |
struct vm_area_struct *vma; vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (unlikely(vma == NULL)) return -ENOMEM; |
5beb49305
|
2418 |
INIT_LIST_HEAD(&vma->anon_vma_chain); |
fa5dc22f8
|
2419 2420 2421 |
vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; |
2f98735c9
|
2422 |
vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND; |
3ed75eb8f
|
2423 |
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); |
fa5dc22f8
|
2424 2425 2426 |
vma->vm_ops = &special_mapping_vmops; vma->vm_private_data = pages; |
462e635e5
|
2427 2428 2429 |
ret = insert_vm_struct(mm, vma); if (ret) goto out; |
fa5dc22f8
|
2430 2431 |
mm->total_vm += len >> PAGE_SHIFT; |
cdd6c482c
|
2432 |
perf_event_mmap(vma); |
089dd79db
|
2433 |
|
fa5dc22f8
|
2434 |
return 0; |
462e635e5
|
2435 2436 2437 2438 |
out: kmem_cache_free(vm_area_cachep, vma); return ret; |
fa5dc22f8
|
2439 |
} |
7906d00cd
|
2440 2441 |
static DEFINE_MUTEX(mm_all_locks_mutex); |
454ed842d
|
2442 |
static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) |
7906d00cd
|
2443 |
{ |
012f18004
|
2444 |
if (!test_bit(0, (unsigned long *) &anon_vma->root->head.next)) { |
7906d00cd
|
2445 2446 2447 2448 |
/* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ |
2b575eb64
|
2449 |
mutex_lock_nest_lock(&anon_vma->root->mutex, &mm->mmap_sem); |
7906d00cd
|
2450 2451 |
/* * We can safely modify head.next after taking the |
2b575eb64
|
2452 |
* anon_vma->root->mutex. If some other vma in this mm shares |
7906d00cd
|
2453 2454 2455 2456 |
* the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the |
2b575eb64
|
2457 |
* anon_vma->root->mutex. |
7906d00cd
|
2458 2459 |
*/ if (__test_and_set_bit(0, (unsigned long *) |
012f18004
|
2460 |
&anon_vma->root->head.next)) |
7906d00cd
|
2461 2462 2463 |
BUG(); } } |
454ed842d
|
2464 |
static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) |
7906d00cd
|
2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 |
{ if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); |
3d48ae45e
|
2478 |
mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem); |
7906d00cd
|
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 |
} } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_sem in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_sem until mm_drop_all_locks() returns. * * mmap_sem in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout (for example populate_range() with * nonlinear vmas). It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->head.next and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We can take all the locks in random order because the VM code |
2b575eb64
|
2505 |
* taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never |
7906d00cd
|
2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 |
* takes more than one of them in a row. Secondly we're protected * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; |
5beb49305
|
2517 |
struct anon_vma_chain *avc; |
7906d00cd
|
2518 2519 2520 2521 2522 2523 2524 2525 |
BUG_ON(down_read_trylock(&mm->mmap_sem)); mutex_lock(&mm_all_locks_mutex); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; |
7906d00cd
|
2526 |
if (vma->vm_file && vma->vm_file->f_mapping) |
454ed842d
|
2527 |
vm_lock_mapping(mm, vma->vm_file->f_mapping); |
7906d00cd
|
2528 |
} |
7cd5a02f5
|
2529 2530 2531 2532 2533 |
for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) |
5beb49305
|
2534 2535 |
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); |
7906d00cd
|
2536 |
} |
7cd5a02f5
|
2537 |
|
584cff54e
|
2538 |
return 0; |
7906d00cd
|
2539 2540 |
out_unlock: |
584cff54e
|
2541 2542 |
mm_drop_all_locks(mm); return -EINTR; |
7906d00cd
|
2543 2544 2545 2546 |
} static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { |
012f18004
|
2547 |
if (test_bit(0, (unsigned long *) &anon_vma->root->head.next)) { |
7906d00cd
|
2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 |
/* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->head will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the |
2b575eb64
|
2558 |
* anon_vma->root->mutex. |
7906d00cd
|
2559 2560 |
*/ if (!__test_and_clear_bit(0, (unsigned long *) |
012f18004
|
2561 |
&anon_vma->root->head.next)) |
7906d00cd
|
2562 |
BUG(); |
cba48b98f
|
2563 |
anon_vma_unlock(anon_vma); |
7906d00cd
|
2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 |
} } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ |
3d48ae45e
|
2574 |
mutex_unlock(&mapping->i_mmap_mutex); |
7906d00cd
|
2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 |
if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_sem cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; |
5beb49305
|
2588 |
struct anon_vma_chain *avc; |
7906d00cd
|
2589 2590 2591 2592 2593 2594 |
BUG_ON(down_read_trylock(&mm->mmap_sem)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) |
5beb49305
|
2595 2596 |
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); |
7906d00cd
|
2597 2598 2599 2600 2601 2602 |
if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } |
8feae1311
|
2603 2604 2605 2606 2607 2608 |
/* * initialise the VMA slab */ void __init mmap_init(void) { |
00a62ce91
|
2609 2610 2611 2612 |
int ret; ret = percpu_counter_init(&vm_committed_as, 0); VM_BUG_ON(ret); |
8feae1311
|
2613 |
} |