Blame view
mm/mmap.c
69.3 KB
1da177e4c Linux-2.6.12-rc2 |
1 2 3 4 5 |
/* * mm/mmap.c * * Written by obz. * |
046c68842 mm: update my add... |
6 |
* Address space accounting code <alan@lxorguk.ukuu.org.uk> |
1da177e4c Linux-2.6.12-rc2 |
7 8 9 |
*/ #include <linux/slab.h> |
4af3c9cc4 Drop some headers... |
10 |
#include <linux/backing-dev.h> |
1da177e4c Linux-2.6.12-rc2 |
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 [PATCH] move capa... |
17 |
#include <linux/capability.h> |
1da177e4c Linux-2.6.12-rc2 |
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 mm: Map most file... |
25 |
#include <linux/export.h> |
1da177e4c Linux-2.6.12-rc2 |
26 27 28 |
#include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> |
cddb8a5c1 mmu-notifiers: core |
29 |
#include <linux/mmu_notifier.h> |
cdd6c482c perf: Do the big ... |
30 |
#include <linux/perf_event.h> |
120a795da audit mmap |
31 |
#include <linux/audit.h> |
b15d00b6a thp: khugepaged v... |
32 |
#include <linux/khugepaged.h> |
1da177e4c Linux-2.6.12-rc2 |
33 34 35 36 |
#include <asm/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> |
d6dd61c83 [PATCH] x86: PARA... |
37 |
#include <asm/mmu_context.h> |
1da177e4c Linux-2.6.12-rc2 |
38 |
|
42b777281 mm: remove double... |
39 |
#include "internal.h" |
3a4597568 [PATCH] IA64,spar... |
40 41 42 |
#ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif |
08e7d9b55 arch_rebalance_pg... |
43 44 45 |
#ifndef arch_rebalance_pgtables #define arch_rebalance_pgtables(addr, len) (addr) #endif |
e0da382c9 [PATCH] freepgt: ... |
46 47 48 |
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 Linux-2.6.12-rc2 |
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 |
/* * 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 [AGPGART] remove ... |
74 75 |
pgprot_t vm_get_page_prot(unsigned long vm_flags) { |
b845f313d mm: Allow archite... |
76 77 78 |
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 [AGPGART] remove ... |
79 80 |
} EXPORT_SYMBOL(vm_get_page_prot); |
34679d7ea mmap: add alignme... |
81 82 |
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */ |
c3d8c1414 [PATCH] More __re... |
83 |
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; |
34679d7ea mmap: add alignme... |
84 85 86 87 88 |
/* * 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 Linux-2.6.12-rc2 |
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
/* * 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 fix NULL pointer ... |
106 |
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) |
1da177e4c Linux-2.6.12-rc2 |
107 108 109 110 111 112 113 114 115 116 117 118 |
{ 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 mmap: fix and tid... |
119 120 121 122 123 124 125 126 127 128 |
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 Linux-2.6.12-rc2 |
129 |
|
1da177e4c Linux-2.6.12-rc2 |
130 131 132 133 134 135 136 137 |
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 [PATCH] ZVC: Supp... |
138 |
free += global_page_state(NR_SLAB_RECLAIMABLE); |
1da177e4c Linux-2.6.12-rc2 |
139 140 |
/* |
6d9f78396 [PATCH] overcommi... |
141 142 |
* Leave reserved pages. The pages are not for anonymous pages. */ |
c15bef309 mmap: fix and tid... |
143 |
if (free <= totalreserve_pages) |
6d9f78396 [PATCH] overcommi... |
144 145 |
goto error; else |
c15bef309 mmap: fix and tid... |
146 |
free -= totalreserve_pages; |
6d9f78396 [PATCH] overcommi... |
147 148 149 150 |
/* * Leave the last 3% for root */ |
1da177e4c Linux-2.6.12-rc2 |
151 |
if (!cap_sys_admin) |
c15bef309 mmap: fix and tid... |
152 |
free -= free / 32; |
1da177e4c Linux-2.6.12-rc2 |
153 154 155 |
if (free > pages) return 0; |
6d9f78396 [PATCH] overcommi... |
156 157 |
goto error; |
1da177e4c Linux-2.6.12-rc2 |
158 159 160 161 162 163 164 165 166 167 168 169 170 |
} 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 nfsd: fix vm over... |
171 172 |
if (mm) allowed -= mm->total_vm / 32; |
1da177e4c Linux-2.6.12-rc2 |
173 |
|
00a62ce91 mm: fix Committed... |
174 |
if (percpu_counter_read_positive(&vm_committed_as) < allowed) |
1da177e4c Linux-2.6.12-rc2 |
175 |
return 0; |
6d9f78396 [PATCH] overcommi... |
176 |
error: |
1da177e4c Linux-2.6.12-rc2 |
177 178 179 180 |
vm_unacct_memory(pages); return -ENOMEM; } |
1da177e4c Linux-2.6.12-rc2 |
181 |
/* |
3d48ae45e mm: Convert i_mma... |
182 |
* Requires inode->i_mapping->i_mmap_mutex |
1da177e4c Linux-2.6.12-rc2 |
183 184 185 186 187 |
*/ 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 [PATCH] mm: chang... |
188 |
atomic_inc(&file->f_path.dentry->d_inode->i_writecount); |
1da177e4c Linux-2.6.12-rc2 |
189 190 191 192 193 194 195 196 197 198 199 200 |
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 [PATCH] mm: unlin... |
201 202 |
* Unlink a file-based vm structure from its prio_tree, to hide * vma from rmap and vmtruncate before freeing its page tables. |
1da177e4c Linux-2.6.12-rc2 |
203 |
*/ |
a8fb5618d [PATCH] mm: unlin... |
204 |
void unlink_file_vma(struct vm_area_struct *vma) |
1da177e4c Linux-2.6.12-rc2 |
205 206 |
{ struct file *file = vma->vm_file; |
1da177e4c Linux-2.6.12-rc2 |
207 208 |
if (file) { struct address_space *mapping = file->f_mapping; |
3d48ae45e mm: Convert i_mma... |
209 |
mutex_lock(&mapping->i_mmap_mutex); |
1da177e4c Linux-2.6.12-rc2 |
210 |
__remove_shared_vm_struct(vma, file, mapping); |
3d48ae45e mm: Convert i_mma... |
211 |
mutex_unlock(&mapping->i_mmap_mutex); |
1da177e4c Linux-2.6.12-rc2 |
212 |
} |
a8fb5618d [PATCH] mm: unlin... |
213 214 215 216 217 218 219 220 |
} /* * 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 [PATCH] mm: unlin... |
221 |
might_sleep(); |
1da177e4c Linux-2.6.12-rc2 |
222 223 |
if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); |
925d1c401 procfs task exe s... |
224 |
if (vma->vm_file) { |
a8fb5618d [PATCH] mm: unlin... |
225 |
fput(vma->vm_file); |
925d1c401 procfs task exe s... |
226 227 228 |
if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(vma->vm_mm); } |
f0be3d32b mempolicy: rename... |
229 |
mpol_put(vma_policy(vma)); |
1da177e4c Linux-2.6.12-rc2 |
230 |
kmem_cache_free(vm_area_cachep, vma); |
a8fb5618d [PATCH] mm: unlin... |
231 |
return next; |
1da177e4c Linux-2.6.12-rc2 |
232 |
} |
6a6160a7b [CVE-2009-0029] S... |
233 |
SYSCALL_DEFINE1(brk, unsigned long, brk) |
1da177e4c Linux-2.6.12-rc2 |
234 235 236 237 |
{ unsigned long rlim, retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; |
a5b4592cf brk: make sys_brk... |
238 |
unsigned long min_brk; |
1da177e4c Linux-2.6.12-rc2 |
239 240 |
down_write(&mm->mmap_sem); |
a5b4592cf brk: make sys_brk... |
241 |
#ifdef CONFIG_COMPAT_BRK |
5520e8948 brk: fix min_brk ... |
242 243 244 245 246 |
/* * 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 brk: COMPAT_BRK: ... |
247 |
if (current->brk_randomized) |
5520e8948 brk: fix min_brk ... |
248 249 250 |
min_brk = mm->start_brk; else min_brk = mm->end_data; |
a5b4592cf brk: make sys_brk... |
251 252 253 254 |
#else min_brk = mm->start_brk; #endif if (brk < min_brk) |
1da177e4c Linux-2.6.12-rc2 |
255 |
goto out; |
1e624196f [PATCH] mm: fix b... |
256 257 258 259 260 261 262 |
/* * 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 mm: use rlimit he... |
263 |
rlim = rlimit(RLIMIT_DATA); |
c1d171a00 x86: randomize brk |
264 265 |
if (rlim < RLIM_INFINITY && (brk - mm->start_brk) + (mm->end_data - mm->start_data) > rlim) |
1e624196f [PATCH] mm: fix b... |
266 |
goto out; |
1da177e4c Linux-2.6.12-rc2 |
267 268 269 270 271 272 273 274 275 276 277 |
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 Linux-2.6.12-rc2 |
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 |
/* 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 [PATCH] Bug in MM... |
314 315 |
prev = vma->vm_start; pend = vma->vm_end; |
1da177e4c Linux-2.6.12-rc2 |
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 |
} 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 BUG_ON() Conversi... |
343 |
BUG_ON(bug); |
1da177e4c Linux-2.6.12-rc2 |
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 |
} #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 mm: fix uninitial... |
370 |
break; |
1da177e4c Linux-2.6.12-rc2 |
371 372 373 374 375 376 377 378 379 380 381 382 383 384 |
__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 Linux-2.6.12-rc2 |
385 386 387 388 389 390 |
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 mmap.c: deinline ... |
391 |
static void __vma_link_file(struct vm_area_struct *vma) |
1da177e4c Linux-2.6.12-rc2 |
392 |
{ |
48aae4255 mm/mmap.c: fix co... |
393 |
struct file *file; |
1da177e4c Linux-2.6.12-rc2 |
394 395 396 397 398 399 |
file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) |
d3ac7f892 [PATCH] mm: chang... |
400 |
atomic_dec(&file->f_path.dentry->d_inode->i_writecount); |
1da177e4c Linux-2.6.12-rc2 |
401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 |
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 Linux-2.6.12-rc2 |
420 421 422 423 424 425 426 427 428 429 |
} 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 mm: Remove i_mmap... |
430 |
if (mapping) |
3d48ae45e mm: Convert i_mma... |
431 |
mutex_lock(&mapping->i_mmap_mutex); |
1da177e4c Linux-2.6.12-rc2 |
432 433 434 |
__vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); |
1da177e4c Linux-2.6.12-rc2 |
435 |
if (mapping) |
3d48ae45e mm: Convert i_mma... |
436 |
mutex_unlock(&mapping->i_mmap_mutex); |
1da177e4c Linux-2.6.12-rc2 |
437 438 439 440 441 442 443 444 445 446 |
mm->map_count++; validate_mm(mm); } /* * Helper for vma_adjust in the split_vma insert case: * insert vm structure into list and rbtree and anon_vma, * but it has already been inserted into prio_tree earlier. */ |
48aae4255 mm/mmap.c: fix co... |
447 |
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) |
1da177e4c Linux-2.6.12-rc2 |
448 |
{ |
48aae4255 mm/mmap.c: fix co... |
449 450 |
struct vm_area_struct *__vma, *prev; struct rb_node **rb_link, *rb_parent; |
1da177e4c Linux-2.6.12-rc2 |
451 452 |
__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent); |
46a350ef9 BUG_ON() Conversi... |
453 |
BUG_ON(__vma && __vma->vm_start < vma->vm_end); |
1da177e4c Linux-2.6.12-rc2 |
454 455 456 457 458 459 460 461 |
__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 mm: make the vma ... |
462 463 464 465 466 |
struct vm_area_struct *next = vma->vm_next; prev->vm_next = next; if (next) next->vm_prev = prev; |
1da177e4c Linux-2.6.12-rc2 |
467 468 469 470 471 472 473 474 475 476 477 478 |
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 mm: change anon_v... |
479 |
int vma_adjust(struct vm_area_struct *vma, unsigned long start, |
1da177e4c Linux-2.6.12-rc2 |
480 481 482 483 484 485 486 |
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 mm: always lock t... |
487 |
struct anon_vma *anon_vma = NULL; |
1da177e4c Linux-2.6.12-rc2 |
488 |
struct file *file = vma->vm_file; |
1da177e4c Linux-2.6.12-rc2 |
489 490 491 492 |
long adjust_next = 0; int remove_next = 0; if (next && !insert) { |
287d97ac0 vma_adjust: fix t... |
493 |
struct vm_area_struct *exporter = NULL; |
1da177e4c Linux-2.6.12-rc2 |
494 495 496 497 498 499 500 |
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 vma_adjust: fix t... |
501 |
exporter = next; |
1da177e4c Linux-2.6.12-rc2 |
502 503 504 505 506 507 508 |
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 vma_adjust: fix t... |
509 |
exporter = next; |
1da177e4c Linux-2.6.12-rc2 |
510 511 512 513 514 515 516 517 |
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 vma_adjust: fix t... |
518 |
exporter = vma; |
1da177e4c Linux-2.6.12-rc2 |
519 520 |
importer = next; } |
1da177e4c Linux-2.6.12-rc2 |
521 |
|
5beb49305 mm: change anon_v... |
522 523 524 525 526 |
/* * 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 vma_adjust: fix t... |
527 528 |
if (exporter && exporter->anon_vma && !importer->anon_vma) { if (anon_vma_clone(importer, exporter)) |
5beb49305 mm: change anon_v... |
529 |
return -ENOMEM; |
287d97ac0 vma_adjust: fix t... |
530 |
importer->anon_vma = exporter->anon_vma; |
5beb49305 mm: change anon_v... |
531 532 |
} } |
1da177e4c Linux-2.6.12-rc2 |
533 534 535 536 |
if (file) { mapping = file->f_mapping; if (!(vma->vm_flags & VM_NONLINEAR)) root = &mapping->i_mmap; |
3d48ae45e mm: Convert i_mma... |
537 |
mutex_lock(&mapping->i_mmap_mutex); |
1da177e4c Linux-2.6.12-rc2 |
538 |
if (insert) { |
1da177e4c Linux-2.6.12-rc2 |
539 540 541 542 543 544 545 546 547 |
/* * 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 thp: avoid breaki... |
548 |
vma_adjust_trans_huge(vma, start, end, adjust_next); |
012f18004 mm: always lock t... |
549 550 551 552 553 554 |
/* * 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 mmap: avoid unnec... |
555 |
if (vma->anon_vma && (importer || start != vma->vm_start)) { |
012f18004 mm: always lock t... |
556 557 558 |
anon_vma = vma->anon_vma; anon_vma_lock(anon_vma); } |
1da177e4c Linux-2.6.12-rc2 |
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 |
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 Linux-2.6.12-rc2 |
589 590 591 592 593 594 595 596 |
} 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 mm: always lock t... |
597 598 |
if (anon_vma) anon_vma_unlock(anon_vma); |
1da177e4c Linux-2.6.12-rc2 |
599 |
if (mapping) |
3d48ae45e mm: Convert i_mma... |
600 |
mutex_unlock(&mapping->i_mmap_mutex); |
1da177e4c Linux-2.6.12-rc2 |
601 602 |
if (remove_next) { |
925d1c401 procfs task exe s... |
603 |
if (file) { |
1da177e4c Linux-2.6.12-rc2 |
604 |
fput(file); |
925d1c401 procfs task exe s... |
605 606 607 |
if (next->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); } |
5beb49305 mm: change anon_v... |
608 609 |
if (next->anon_vma) anon_vma_merge(vma, next); |
1da177e4c Linux-2.6.12-rc2 |
610 |
mm->map_count--; |
f0be3d32b mempolicy: rename... |
611 |
mpol_put(vma_policy(next)); |
1da177e4c Linux-2.6.12-rc2 |
612 613 614 615 616 617 618 619 620 621 622 623 624 |
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; } } validate_mm(mm); |
5beb49305 mm: change anon_v... |
625 626 |
return 0; |
1da177e4c Linux-2.6.12-rc2 |
627 628 629 630 631 632 |
} /* * 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 Linux-2.6.12-rc2 |
633 634 635 |
static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { |
8314c4f24 ksm: remove VM_ME... |
636 637 |
/* VM_CAN_NONLINEAR may get set later by f_op->mmap() */ if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR) |
1da177e4c Linux-2.6.12-rc2 |
638 639 640 641 642 643 644 645 646 |
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 mmap: avoid mergi... |
647 648 |
struct anon_vma *anon_vma2, struct vm_area_struct *vma) |
1da177e4c Linux-2.6.12-rc2 |
649 |
{ |
965f55dea mmap: avoid mergi... |
650 651 652 653 654 655 656 657 |
/* * 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 Linux-2.6.12-rc2 |
658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 |
} /* * 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 mmap: avoid mergi... |
676 |
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { |
1da177e4c Linux-2.6.12-rc2 |
677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 |
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 mmap: avoid mergi... |
695 |
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { |
1da177e4c Linux-2.6.12-rc2 |
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 |
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 mm: change anon_v... |
741 |
int err; |
1da177e4c Linux-2.6.12-rc2 |
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 |
/* * 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 mmap: avoid mergi... |
773 |
next->anon_vma, NULL)) { |
1da177e4c Linux-2.6.12-rc2 |
774 |
/* cases 1, 6 */ |
5beb49305 mm: change anon_v... |
775 |
err = vma_adjust(prev, prev->vm_start, |
1da177e4c Linux-2.6.12-rc2 |
776 777 |
next->vm_end, prev->vm_pgoff, NULL); } else /* cases 2, 5, 7 */ |
5beb49305 mm: change anon_v... |
778 |
err = vma_adjust(prev, prev->vm_start, |
1da177e4c Linux-2.6.12-rc2 |
779 |
end, prev->vm_pgoff, NULL); |
5beb49305 mm: change anon_v... |
780 781 |
if (err) return NULL; |
b15d00b6a thp: khugepaged v... |
782 |
khugepaged_enter_vma_merge(prev); |
1da177e4c Linux-2.6.12-rc2 |
783 784 785 786 787 788 789 790 791 792 793 |
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 mm: change anon_v... |
794 |
err = vma_adjust(prev, prev->vm_start, |
1da177e4c Linux-2.6.12-rc2 |
795 796 |
addr, prev->vm_pgoff, NULL); else /* cases 3, 8 */ |
5beb49305 mm: change anon_v... |
797 |
err = vma_adjust(area, addr, next->vm_end, |
1da177e4c Linux-2.6.12-rc2 |
798 |
next->vm_pgoff - pglen, NULL); |
5beb49305 mm: change anon_v... |
799 800 |
if (err) return NULL; |
b15d00b6a thp: khugepaged v... |
801 |
khugepaged_enter_vma_merge(area); |
1da177e4c Linux-2.6.12-rc2 |
802 803 804 805 806 807 808 |
return area; } return NULL; } /* |
d0e9fe175 Simplify and comm... |
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 |
* 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 Linux-2.6.12-rc2 |
864 865 866 867 868 869 870 871 872 |
* 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 Simplify and comm... |
873 |
struct anon_vma *anon_vma; |
1da177e4c Linux-2.6.12-rc2 |
874 |
struct vm_area_struct *near; |
1da177e4c Linux-2.6.12-rc2 |
875 876 877 878 |
near = vma->vm_next; if (!near) goto try_prev; |
d0e9fe175 Simplify and comm... |
879 880 881 |
anon_vma = reusable_anon_vma(near, vma, near); if (anon_vma) return anon_vma; |
1da177e4c Linux-2.6.12-rc2 |
882 |
try_prev: |
9be34c9d5 mm: get rid of th... |
883 |
near = vma->vm_prev; |
1da177e4c Linux-2.6.12-rc2 |
884 885 |
if (!near) goto none; |
d0e9fe175 Simplify and comm... |
886 887 888 |
anon_vma = reusable_anon_vma(near, near, vma); if (anon_vma) return anon_vma; |
1da177e4c Linux-2.6.12-rc2 |
889 890 891 892 893 894 895 896 897 898 899 900 901 |
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 [PATCH] mm: vm_st... |
902 |
void vm_stat_account(struct mm_struct *mm, unsigned long flags, |
1da177e4c Linux-2.6.12-rc2 |
903 904 905 906 |
struct file *file, long pages) { const unsigned long stack_flags = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); |
1da177e4c Linux-2.6.12-rc2 |
907 908 909 910 911 912 913 914 915 916 917 918 |
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 */ /* |
27f5de796 mm: Fix problem o... |
919 |
* The caller must hold down_write(¤t->mm->mmap_sem). |
1da177e4c Linux-2.6.12-rc2 |
920 |
*/ |
48aae4255 mm/mmap.c: fix co... |
921 |
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, |
1da177e4c Linux-2.6.12-rc2 |
922 923 924 925 |
unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff) { struct mm_struct * mm = current->mm; |
1da177e4c Linux-2.6.12-rc2 |
926 |
struct inode *inode; |
ca16d140a mm: don't access ... |
927 |
vm_flags_t vm_flags; |
1da177e4c Linux-2.6.12-rc2 |
928 |
int error; |
0165ab443 split mmap |
929 |
unsigned long reqprot = prot; |
1da177e4c Linux-2.6.12-rc2 |
930 |
|
1da177e4c Linux-2.6.12-rc2 |
931 932 933 934 935 936 937 |
/* * 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 [PATCH] mm: chang... |
938 |
if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC))) |
1da177e4c Linux-2.6.12-rc2 |
939 940 941 942 |
prot |= PROT_EXEC; if (!len) return -EINVAL; |
7cd94146c Security: round m... |
943 944 |
if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); |
1da177e4c Linux-2.6.12-rc2 |
945 946 |
/* Careful about overflows.. */ len = PAGE_ALIGN(len); |
9206de95b Take arch_mmap_ch... |
947 |
if (!len) |
1da177e4c Linux-2.6.12-rc2 |
948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 |
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 mmap: remove unne... |
971 |
if (flags & MAP_LOCKED) |
1da177e4c Linux-2.6.12-rc2 |
972 973 |
if (!can_do_mlock()) return -EPERM; |
ba470de43 mmap: handle mloc... |
974 |
|
1da177e4c Linux-2.6.12-rc2 |
975 976 977 |
/* mlock MCL_FUTURE? */ if (vm_flags & VM_LOCKED) { unsigned long locked, lock_limit; |
93ea1d0a1 [PATCH] RLIMIT_ME... |
978 979 |
locked = len >> PAGE_SHIFT; locked += mm->locked_vm; |
59e99e5b9 mm: use rlimit he... |
980 |
lock_limit = rlimit(RLIMIT_MEMLOCK); |
93ea1d0a1 [PATCH] RLIMIT_ME... |
981 |
lock_limit >>= PAGE_SHIFT; |
1da177e4c Linux-2.6.12-rc2 |
982 983 984 |
if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } |
d3ac7f892 [PATCH] mm: chang... |
985 |
inode = file ? file->f_path.dentry->d_inode : NULL; |
1da177e4c Linux-2.6.12-rc2 |
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 |
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 [PATCH] mm: chang... |
1014 |
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) { |
80c5606c3 Fix VM_MAYEXEC ca... |
1015 1016 1017 1018 |
if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } |
80c5606c3 Fix VM_MAYEXEC ca... |
1019 1020 1021 |
if (!file->f_op || !file->f_op->mmap) return -ENODEV; |
1da177e4c Linux-2.6.12-rc2 |
1022 1023 1024 1025 1026 1027 1028 1029 |
break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: |
ce3639426 mmap: fix petty b... |
1030 1031 1032 1033 |
/* * Ignore pgoff. */ pgoff = 0; |
1da177e4c Linux-2.6.12-rc2 |
1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 |
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; } } |
ed0321895 security: Protect... |
1046 |
error = security_file_mmap(file, reqprot, prot, flags, addr, 0); |
1da177e4c Linux-2.6.12-rc2 |
1047 1048 |
if (error) return error; |
ed0321895 security: Protect... |
1049 |
|
5a6fe1259 Do not account fo... |
1050 |
return mmap_region(file, addr, len, flags, vm_flags, pgoff); |
0165ab443 split mmap |
1051 1052 |
} EXPORT_SYMBOL(do_mmap_pgoff); |
66f0dc481 mm: move sys_mmap... |
1053 1054 1055 1056 1057 1058 1059 1060 |
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 audit mmap |
1061 |
audit_mmap_fd(fd, flags); |
66f0dc481 mm: move sys_mmap... |
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 |
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 */ len = ALIGN(len, huge_page_size(&default_hstate)); file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE); if (IS_ERR(file)) return PTR_ERR(file); } flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); down_write(¤t->mm->mmap_sem); retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); up_write(¤t->mm->mmap_sem); if (file) fput(file); out: return retval; } |
a4679373c Add generic sys_o... |
1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 |
#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 Remove fs.h from ... |
1116 1117 1118 1119 1120 1121 1122 1123 |
/* * 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 mm: don't access ... |
1124 |
vm_flags_t vm_flags = vma->vm_flags; |
4e950f6f0 Remove fs.h from ... |
1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 |
/* 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 setup vma->vm_pag... |
1136 |
pgprot_val(vm_get_page_prot(vm_flags))) |
4e950f6f0 Remove fs.h from ... |
1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 |
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 Stop playing sill... |
1147 1148 |
/* * We account for memory if it's a private writeable mapping, |
5a6fe1259 Do not account fo... |
1149 |
* not hugepages and VM_NORESERVE wasn't set. |
fc8744adc Stop playing sill... |
1150 |
*/ |
ca16d140a mm: don't access ... |
1151 |
static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) |
fc8744adc Stop playing sill... |
1152 |
{ |
5a6fe1259 Do not account fo... |
1153 1154 1155 1156 1157 1158 |
/* * 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 Stop playing sill... |
1159 1160 |
return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } |
0165ab443 split mmap |
1161 1162 |
unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, |
ca16d140a mm: don't access ... |
1163 |
vm_flags_t vm_flags, unsigned long pgoff) |
0165ab443 split mmap |
1164 1165 1166 1167 1168 1169 1170 1171 |
{ 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 Linux-2.6.12-rc2 |
1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 |
/* 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 [PATCH] RLIMIT_AS... |
1183 |
if (!may_expand_vm(mm, len >> PAGE_SHIFT)) |
1da177e4c Linux-2.6.12-rc2 |
1184 |
return -ENOMEM; |
fc8744adc Stop playing sill... |
1185 1186 |
/* * Set 'VM_NORESERVE' if we should not account for the |
5a6fe1259 Do not account fo... |
1187 |
* memory use of this mapping. |
fc8744adc Stop playing sill... |
1188 |
*/ |
5a6fe1259 Do not account fo... |
1189 1190 1191 1192 1193 1194 1195 1196 1197 |
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 mm: record MAP_NO... |
1198 |
|
fc8744adc Stop playing sill... |
1199 1200 1201 |
/* * Private writable mapping: check memory availability */ |
5a6fe1259 Do not account fo... |
1202 |
if (accountable_mapping(file, vm_flags)) { |
fc8744adc Stop playing sill... |
1203 1204 1205 1206 |
charged = len >> PAGE_SHIFT; if (security_vm_enough_memory(charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; |
1da177e4c Linux-2.6.12-rc2 |
1207 1208 1209 |
} /* |
de33c8db5 Fix OOPS in mmap_... |
1210 |
* Can we just expand an old mapping? |
1da177e4c Linux-2.6.12-rc2 |
1211 |
*/ |
de33c8db5 Fix OOPS in mmap_... |
1212 1213 1214 |
vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); if (vma) goto out; |
1da177e4c Linux-2.6.12-rc2 |
1215 1216 1217 1218 1219 1220 |
/* * 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 [PATCH] mm: use k... |
1221 |
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c Linux-2.6.12-rc2 |
1222 1223 1224 1225 |
if (!vma) { error = -ENOMEM; goto unacct_error; } |
1da177e4c Linux-2.6.12-rc2 |
1226 1227 1228 1229 1230 |
vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; |
3ed75eb8f setup vma->vm_pag... |
1231 |
vma->vm_page_prot = vm_get_page_prot(vm_flags); |
1da177e4c Linux-2.6.12-rc2 |
1232 |
vma->vm_pgoff = pgoff; |
5beb49305 mm: change anon_v... |
1233 |
INIT_LIST_HEAD(&vma->anon_vma_chain); |
1da177e4c Linux-2.6.12-rc2 |
1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 |
if (file) { error = -EINVAL; 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 procfs task exe s... |
1250 1251 |
if (vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); |
f8dbf0a7a mmap: save some c... |
1252 1253 1254 1255 1256 1257 1258 1259 1260 |
/* 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 Linux-2.6.12-rc2 |
1261 1262 1263 1264 1265 |
} else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } |
c9d0bf241 mm: uncached vma ... |
1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 |
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 fix mprotect vma_... |
1276 |
vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED); |
c9d0bf241 mm: uncached vma ... |
1277 1278 1279 |
if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot))) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); } |
d08b3851d [PATCH] mm: track... |
1280 |
|
de33c8db5 Fix OOPS in mmap_... |
1281 1282 |
vma_link(mm, vma, prev, rb_link, rb_parent); file = vma->vm_file; |
4d3d5b41a mmap_region: clea... |
1283 1284 1285 1286 1287 |
/* Once vma denies write, undo our temporary denial count */ if (correct_wcount) atomic_inc(&inode->i_writecount); out: |
cdd6c482c perf: Do the big ... |
1288 |
perf_event_mmap(vma); |
0a4a93919 perf_counter: exe... |
1289 |
|
1da177e4c Linux-2.6.12-rc2 |
1290 |
mm->total_vm += len >> PAGE_SHIFT; |
ab50b8ed8 [PATCH] mm: vm_st... |
1291 |
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); |
1da177e4c Linux-2.6.12-rc2 |
1292 |
if (vm_flags & VM_LOCKED) { |
06f9d8c2b mm: mlock_vma_pag... |
1293 1294 |
if (!mlock_vma_pages_range(vma, addr, addr + len)) mm->locked_vm += (len >> PAGE_SHIFT); |
ba470de43 mmap: handle mloc... |
1295 |
} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) |
54cb8821d mm: merge populat... |
1296 |
make_pages_present(addr, addr + len); |
1da177e4c Linux-2.6.12-rc2 |
1297 1298 1299 1300 1301 1302 1303 1304 1305 |
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 [PATCH] freepgt: ... |
1306 1307 |
unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); charged = 0; |
1da177e4c Linux-2.6.12-rc2 |
1308 1309 1310 1311 1312 1313 1314 |
free_vma: kmem_cache_free(vm_area_cachep, vma); unacct_error: if (charged) vm_unacct_memory(charged); return error; } |
1da177e4c Linux-2.6.12-rc2 |
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 |
/* 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 get_unmapped_area... |
1337 1338 |
if (flags & MAP_FIXED) return addr; |
1da177e4c Linux-2.6.12-rc2 |
1339 1340 1341 1342 1343 1344 1345 |
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 [PATCH] Avoiding ... |
1346 1347 1348 1349 1350 1351 |
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 Linux-2.6.12-rc2 |
1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 |
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 [PATCH] Avoiding ... |
1362 1363 1364 |
addr = TASK_UNMAPPED_BASE; start_addr = addr; mm->cached_hole_size = 0; |
1da177e4c Linux-2.6.12-rc2 |
1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 |
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 [PATCH] Avoiding ... |
1376 1377 |
if (addr + mm->cached_hole_size < vma->vm_start) mm->cached_hole_size = vma->vm_start - addr; |
1da177e4c Linux-2.6.12-rc2 |
1378 1379 1380 1381 |
addr = vma->vm_end; } } #endif |
1363c3cd8 [PATCH] Avoiding ... |
1382 |
void arch_unmap_area(struct mm_struct *mm, unsigned long addr) |
1da177e4c Linux-2.6.12-rc2 |
1383 1384 1385 1386 |
{ /* * Is this a new hole at the lowest possible address? */ |
1363c3cd8 [PATCH] Avoiding ... |
1387 1388 1389 1390 |
if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) { mm->free_area_cache = addr; mm->cached_hole_size = ~0UL; } |
1da177e4c Linux-2.6.12-rc2 |
1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 |
} /* * 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; unsigned long addr = addr0; /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; |
06abdfb47 get_unmapped_area... |
1410 1411 |
if (flags & MAP_FIXED) return addr; |
1da177e4c Linux-2.6.12-rc2 |
1412 1413 1414 1415 1416 1417 1418 1419 |
/* 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 [PATCH] Avoiding ... |
1420 1421 1422 1423 1424 |
/* 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; } |
1da177e4c Linux-2.6.12-rc2 |
1425 1426 1427 1428 |
/* either no address requested or can't fit in requested address hole */ addr = mm->free_area_cache; /* make sure it can fit in the remaining address space */ |
49a43876b [PATCH] prevent N... |
1429 |
if (addr > len) { |
1da177e4c Linux-2.6.12-rc2 |
1430 1431 1432 1433 1434 |
vma = find_vma(mm, addr-len); if (!vma || addr <= vma->vm_start) /* remember the address as a hint for next time */ return (mm->free_area_cache = addr-len); } |
73219d178 [PATCH] mmap topd... |
1435 1436 |
if (mm->mmap_base < len) goto bottomup; |
1da177e4c Linux-2.6.12-rc2 |
1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 |
addr = mm->mmap_base-len; 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 [PATCH] Avoiding ... |
1449 1450 1451 |
/* 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 Linux-2.6.12-rc2 |
1452 1453 |
/* try just below the current vma->vm_start */ addr = vma->vm_start-len; |
49a43876b [PATCH] prevent N... |
1454 |
} while (len < vma->vm_start); |
1da177e4c Linux-2.6.12-rc2 |
1455 |
|
73219d178 [PATCH] mmap topd... |
1456 |
bottomup: |
1da177e4c Linux-2.6.12-rc2 |
1457 1458 1459 1460 1461 1462 |
/* * 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 [PATCH] Avoiding ... |
1463 1464 |
mm->cached_hole_size = ~0UL; mm->free_area_cache = TASK_UNMAPPED_BASE; |
1da177e4c Linux-2.6.12-rc2 |
1465 1466 1467 1468 1469 |
addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); /* * Restore the topdown base: */ mm->free_area_cache = mm->mmap_base; |
1363c3cd8 [PATCH] Avoiding ... |
1470 |
mm->cached_hole_size = ~0UL; |
1da177e4c Linux-2.6.12-rc2 |
1471 1472 1473 1474 |
return addr; } #endif |
1363c3cd8 [PATCH] Avoiding ... |
1475 |
void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) |
1da177e4c Linux-2.6.12-rc2 |
1476 1477 1478 1479 |
{ /* * Is this a new hole at the highest possible address? */ |
1363c3cd8 [PATCH] Avoiding ... |
1480 1481 |
if (addr > mm->free_area_cache) mm->free_area_cache = addr; |
1da177e4c Linux-2.6.12-rc2 |
1482 1483 |
/* dont allow allocations above current base */ |
1363c3cd8 [PATCH] Avoiding ... |
1484 1485 |
if (mm->free_area_cache > mm->mmap_base) mm->free_area_cache = mm->mmap_base; |
1da177e4c Linux-2.6.12-rc2 |
1486 1487 1488 1489 1490 1491 |
} unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { |
06abdfb47 get_unmapped_area... |
1492 1493 |
unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); |
9206de95b Take arch_mmap_ch... |
1494 1495 1496 1497 1498 1499 1500 |
unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; |
06abdfb47 get_unmapped_area... |
1501 1502 1503 1504 1505 1506 |
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 Linux-2.6.12-rc2 |
1507 |
|
07ab67c8d Fix get_unmapped_... |
1508 1509 1510 1511 |
if (addr > TASK_SIZE - len) return -ENOMEM; if (addr & ~PAGE_MASK) return -EINVAL; |
06abdfb47 get_unmapped_area... |
1512 |
|
08e7d9b55 arch_rebalance_pg... |
1513 |
return arch_rebalance_pgtables(addr, len); |
1da177e4c Linux-2.6.12-rc2 |
1514 1515 1516 1517 1518 |
} EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ |
48aae4255 mm/mmap.c: fix co... |
1519 |
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) |
1da177e4c Linux-2.6.12-rc2 |
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 |
{ struct vm_area_struct *vma = NULL; if (mm) { /* 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; } if (vma) mm->mmap_cache = vma; } } return vma; } EXPORT_SYMBOL(find_vma); /* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma = NULL, *prev = NULL; |
48aae4255 mm/mmap.c: fix co... |
1562 |
struct rb_node *rb_node; |
1da177e4c Linux-2.6.12-rc2 |
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 |
if (!mm) goto out; /* Guard against addr being lower than the first VMA */ vma = mm->mmap; /* Go through the RB tree quickly. */ rb_node = mm->mm_rb.rb_node; while (rb_node) { struct vm_area_struct *vma_tmp; vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); if (addr < vma_tmp->vm_end) { rb_node = rb_node->rb_left; } else { prev = vma_tmp; if (!prev->vm_next || (addr < prev->vm_next->vm_end)) break; rb_node = rb_node->rb_right; } } out: *pprev = prev; return prev ? prev->vm_next : vma; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ |
48aae4255 mm/mmap.c: fix co... |
1596 |
static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) |
1da177e4c Linux-2.6.12-rc2 |
1597 1598 1599 |
{ struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; |
0d59a01bc [PATCH] Don't all... |
1600 |
unsigned long new_start; |
1da177e4c Linux-2.6.12-rc2 |
1601 1602 |
/* address space limit tests */ |
119f657c7 [PATCH] RLIMIT_AS... |
1603 |
if (!may_expand_vm(mm, grow)) |
1da177e4c Linux-2.6.12-rc2 |
1604 1605 1606 |
return -ENOMEM; /* Stack limit test */ |
59e99e5b9 mm: use rlimit he... |
1607 |
if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) |
1da177e4c Linux-2.6.12-rc2 |
1608 1609 1610 1611 1612 1613 1614 |
return -ENOMEM; /* mlock limit tests */ if (vma->vm_flags & VM_LOCKED) { unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; |
59e99e5b9 mm: use rlimit he... |
1615 1616 |
limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); limit >>= PAGE_SHIFT; |
1da177e4c Linux-2.6.12-rc2 |
1617 1618 1619 |
if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; } |
0d59a01bc [PATCH] Don't all... |
1620 1621 1622 1623 1624 |
/* 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 Linux-2.6.12-rc2 |
1625 1626 1627 1628 |
/* * Overcommit.. This must be the final test, as it will * update security statistics. */ |
05fa199d4 mm: pass correct ... |
1629 |
if (security_vm_enough_memory_mm(mm, grow)) |
1da177e4c Linux-2.6.12-rc2 |
1630 1631 1632 1633 1634 1635 |
return -ENOMEM; /* Ok, everything looks good - let it rip */ mm->total_vm += grow; if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; |
ab50b8ed8 [PATCH] mm: vm_st... |
1636 |
vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); |
1da177e4c Linux-2.6.12-rc2 |
1637 1638 |
return 0; } |
46dea3d09 [PATCH] mm: ia64 ... |
1639 |
#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) |
1da177e4c Linux-2.6.12-rc2 |
1640 |
/* |
46dea3d09 [PATCH] mm: ia64 ... |
1641 1642 |
* 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 Linux-2.6.12-rc2 |
1643 |
*/ |
46dea3d09 [PATCH] mm: ia64 ... |
1644 |
int expand_upwards(struct vm_area_struct *vma, unsigned long address) |
1da177e4c Linux-2.6.12-rc2 |
1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 |
{ 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 mm: rename anon_v... |
1657 |
vma_lock_anon_vma(vma); |
1da177e4c Linux-2.6.12-rc2 |
1658 1659 1660 1661 1662 |
/* * 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 [PARISC] Handle w... |
1663 |
* Also guard against wrapping around to address 0. |
1da177e4c Linux-2.6.12-rc2 |
1664 |
*/ |
06b32f3ab [PARISC] Handle w... |
1665 1666 1667 |
if (address < PAGE_ALIGN(address+4)) address = PAGE_ALIGN(address+4); else { |
bb4a340e0 mm: rename anon_v... |
1668 |
vma_unlock_anon_vma(vma); |
06b32f3ab [PARISC] Handle w... |
1669 1670 |
return -ENOMEM; } |
1da177e4c Linux-2.6.12-rc2 |
1671 1672 1673 1674 1675 1676 1677 1678 |
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 vm: fix vm_pgoff ... |
1679 1680 1681 1682 1683 1684 1685 |
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 perf: Add non-exe... |
1686 |
} |
1da177e4c Linux-2.6.12-rc2 |
1687 |
} |
bb4a340e0 mm: rename anon_v... |
1688 |
vma_unlock_anon_vma(vma); |
b15d00b6a thp: khugepaged v... |
1689 |
khugepaged_enter_vma_merge(vma); |
1da177e4c Linux-2.6.12-rc2 |
1690 1691 |
return error; } |
46dea3d09 [PATCH] mm: ia64 ... |
1692 |
#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ |
1da177e4c Linux-2.6.12-rc2 |
1693 1694 1695 |
/* * vma is the first one with address < vma->vm_start. Have to extend vma. */ |
d05f3169c mm: make expand_d... |
1696 |
int expand_downwards(struct vm_area_struct *vma, |
b6a2fea39 mm: variable leng... |
1697 |
unsigned long address) |
1da177e4c Linux-2.6.12-rc2 |
1698 1699 1700 1701 1702 1703 1704 1705 1706 |
{ 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 security: protect... |
1707 1708 |
address &= PAGE_MASK; |
88c3f7a8f Security: remove ... |
1709 |
error = security_file_mmap(NULL, 0, 0, 0, address, 1); |
8869477a4 security: protect... |
1710 1711 |
if (error) return error; |
bb4a340e0 mm: rename anon_v... |
1712 |
vma_lock_anon_vma(vma); |
1da177e4c Linux-2.6.12-rc2 |
1713 1714 1715 1716 1717 1718 |
/* * 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 Linux-2.6.12-rc2 |
1719 1720 1721 1722 1723 1724 1725 |
/* 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 vm: fix vm_pgoff ... |
1726 1727 1728 1729 1730 1731 1732 1733 |
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 Linux-2.6.12-rc2 |
1734 1735 |
} } |
bb4a340e0 mm: rename anon_v... |
1736 |
vma_unlock_anon_vma(vma); |
b15d00b6a thp: khugepaged v... |
1737 |
khugepaged_enter_vma_merge(vma); |
1da177e4c Linux-2.6.12-rc2 |
1738 1739 |
return error; } |
b6a2fea39 mm: variable leng... |
1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 |
#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 parisc: fix find_... |
1755 |
if (!prev || expand_stack(prev, addr)) |
b6a2fea39 mm: variable leng... |
1756 |
return NULL; |
ba470de43 mmap: handle mloc... |
1757 |
if (prev->vm_flags & VM_LOCKED) { |
c58267c32 mm: mlock_vma_pag... |
1758 |
mlock_vma_pages_range(prev, addr, prev->vm_end); |
ba470de43 mmap: handle mloc... |
1759 |
} |
b6a2fea39 mm: variable leng... |
1760 1761 1762 1763 1764 1765 1766 |
return prev; } #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } |
1da177e4c Linux-2.6.12-rc2 |
1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 |
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 mmap: handle mloc... |
1784 |
if (vma->vm_flags & VM_LOCKED) { |
c58267c32 mm: mlock_vma_pag... |
1785 |
mlock_vma_pages_range(vma, addr, start); |
ba470de43 mmap: handle mloc... |
1786 |
} |
1da177e4c Linux-2.6.12-rc2 |
1787 1788 1789 |
return vma; } #endif |
1da177e4c Linux-2.6.12-rc2 |
1790 |
/* |
2c0b38146 [PATCH] mm: remov... |
1791 |
* Ok - we have the memory areas we should free on the vma list, |
1da177e4c Linux-2.6.12-rc2 |
1792 |
* so release them, and do the vma updates. |
2c0b38146 [PATCH] mm: remov... |
1793 1794 |
* * Called with the mm semaphore held. |
1da177e4c Linux-2.6.12-rc2 |
1795 |
*/ |
2c0b38146 [PATCH] mm: remov... |
1796 |
static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) |
1da177e4c Linux-2.6.12-rc2 |
1797 |
{ |
365e9c87a [PATCH] mm: updat... |
1798 1799 |
/* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); |
1da177e4c Linux-2.6.12-rc2 |
1800 |
do { |
2c0b38146 [PATCH] mm: remov... |
1801 1802 1803 |
long nrpages = vma_pages(vma); mm->total_vm -= nrpages; |
2c0b38146 [PATCH] mm: remov... |
1804 |
vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); |
a8fb5618d [PATCH] mm: unlin... |
1805 |
vma = remove_vma(vma); |
146425a31 [PATCH] freepgt: ... |
1806 |
} while (vma); |
1da177e4c Linux-2.6.12-rc2 |
1807 1808 1809 1810 1811 1812 |
validate_mm(mm); } /* * Get rid of page table information in the indicated region. * |
f10df6860 [PATCH] fix locki... |
1813 |
* Called with the mm semaphore held. |
1da177e4c Linux-2.6.12-rc2 |
1814 1815 |
*/ static void unmap_region(struct mm_struct *mm, |
e0da382c9 [PATCH] freepgt: ... |
1816 1817 |
struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end) |
1da177e4c Linux-2.6.12-rc2 |
1818 |
{ |
e0da382c9 [PATCH] freepgt: ... |
1819 |
struct vm_area_struct *next = prev? prev->vm_next: mm->mmap; |
d16dfc550 mm: mmu_gather re... |
1820 |
struct mmu_gather tlb; |
1da177e4c Linux-2.6.12-rc2 |
1821 1822 1823 |
unsigned long nr_accounted = 0; lru_add_drain(); |
d16dfc550 mm: mmu_gather re... |
1824 |
tlb_gather_mmu(&tlb, mm, 0); |
365e9c87a [PATCH] mm: updat... |
1825 |
update_hiwater_rss(mm); |
508034a32 [PATCH] mm: unmap... |
1826 |
unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL); |
1da177e4c Linux-2.6.12-rc2 |
1827 |
vm_unacct_memory(nr_accounted); |
d16dfc550 mm: mmu_gather re... |
1828 1829 1830 |
free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : 0); tlb_finish_mmu(&tlb, start, end); |
1da177e4c Linux-2.6.12-rc2 |
1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 |
} /* * 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 [PATCH] Avoiding ... |
1843 |
unsigned long addr; |
1da177e4c Linux-2.6.12-rc2 |
1844 1845 |
insertion_point = (prev ? &prev->vm_next : &mm->mmap); |
297c5eee3 mm: make the vma ... |
1846 |
vma->vm_prev = NULL; |
1da177e4c Linux-2.6.12-rc2 |
1847 1848 1849 1850 1851 1852 1853 |
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 mm: make the vma ... |
1854 1855 |
if (vma) vma->vm_prev = prev; |
1da177e4c Linux-2.6.12-rc2 |
1856 |
tail_vma->vm_next = NULL; |
1363c3cd8 [PATCH] Avoiding ... |
1857 1858 1859 1860 1861 |
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 Linux-2.6.12-rc2 |
1862 1863 1864 1865 |
mm->mmap_cache = NULL; /* Kill the cache. */ } /* |
659ace584 mmap: don't retur... |
1866 1867 |
* __split_vma() bypasses sysctl_max_map_count checking. We use this on the * munmap path where it doesn't make sense to fail. |
1da177e4c Linux-2.6.12-rc2 |
1868 |
*/ |
659ace584 mmap: don't retur... |
1869 |
static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, |
1da177e4c Linux-2.6.12-rc2 |
1870 1871 1872 1873 |
unsigned long addr, int new_below) { struct mempolicy *pol; struct vm_area_struct *new; |
5beb49305 mm: change anon_v... |
1874 |
int err = -ENOMEM; |
1da177e4c Linux-2.6.12-rc2 |
1875 |
|
a55164389 hugetlb: modular ... |
1876 1877 |
if (is_vm_hugetlb_page(vma) && (addr & ~(huge_page_mask(hstate_vma(vma))))) |
1da177e4c Linux-2.6.12-rc2 |
1878 |
return -EINVAL; |
e94b17660 [PATCH] slab: rem... |
1879 |
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c Linux-2.6.12-rc2 |
1880 |
if (!new) |
5beb49305 mm: change anon_v... |
1881 |
goto out_err; |
1da177e4c Linux-2.6.12-rc2 |
1882 1883 1884 |
/* most fields are the same, copy all, and then fixup */ *new = *vma; |
5beb49305 mm: change anon_v... |
1885 |
INIT_LIST_HEAD(&new->anon_vma_chain); |
1da177e4c Linux-2.6.12-rc2 |
1886 1887 1888 1889 1890 1891 |
if (new_below) new->vm_end = addr; else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } |
846a16bf0 mempolicy: rename... |
1892 |
pol = mpol_dup(vma_policy(vma)); |
1da177e4c Linux-2.6.12-rc2 |
1893 |
if (IS_ERR(pol)) { |
5beb49305 mm: change anon_v... |
1894 1895 |
err = PTR_ERR(pol); goto out_free_vma; |
1da177e4c Linux-2.6.12-rc2 |
1896 1897 |
} vma_set_policy(new, pol); |
5beb49305 mm: change anon_v... |
1898 1899 |
if (anon_vma_clone(new, vma)) goto out_free_mpol; |
925d1c401 procfs task exe s... |
1900 |
if (new->vm_file) { |
1da177e4c Linux-2.6.12-rc2 |
1901 |
get_file(new->vm_file); |
925d1c401 procfs task exe s... |
1902 1903 1904 |
if (vma->vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); } |
1da177e4c Linux-2.6.12-rc2 |
1905 1906 1907 1908 1909 |
if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); if (new_below) |
5beb49305 mm: change anon_v... |
1910 |
err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + |
1da177e4c Linux-2.6.12-rc2 |
1911 1912 |
((addr - new->vm_start) >> PAGE_SHIFT), new); else |
5beb49305 mm: change anon_v... |
1913 |
err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); |
1da177e4c Linux-2.6.12-rc2 |
1914 |
|
5beb49305 mm: change anon_v... |
1915 1916 1917 1918 1919 |
/* Success. */ if (!err) return 0; /* Clean everything up if vma_adjust failed. */ |
589275338 mmap: check ->vm_... |
1920 1921 |
if (new->vm_ops && new->vm_ops->close) new->vm_ops->close(new); |
5beb49305 mm: change anon_v... |
1922 1923 1924 1925 1926 |
if (new->vm_file) { if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); fput(new->vm_file); } |
2aeadc30d mmap: call unlink... |
1927 |
unlink_anon_vmas(new); |
5beb49305 mm: change anon_v... |
1928 1929 1930 1931 1932 1933 |
out_free_mpol: mpol_put(pol); out_free_vma: kmem_cache_free(vm_area_cachep, new); out_err: return err; |
1da177e4c Linux-2.6.12-rc2 |
1934 |
} |
659ace584 mmap: don't retur... |
1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 |
/* * 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 Linux-2.6.12-rc2 |
1947 1948 1949 1950 1951 1952 1953 1954 |
/* 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 [PATCH] freepgt: ... |
1955 |
struct vm_area_struct *vma, *prev, *last; |
1da177e4c Linux-2.6.12-rc2 |
1956 1957 1958 1959 1960 1961 1962 1963 |
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 mm: get rid of th... |
1964 |
vma = find_vma(mm, start); |
146425a31 [PATCH] freepgt: ... |
1965 |
if (!vma) |
1da177e4c Linux-2.6.12-rc2 |
1966 |
return 0; |
9be34c9d5 mm: get rid of th... |
1967 |
prev = vma->vm_prev; |
146425a31 [PATCH] freepgt: ... |
1968 |
/* we have start < vma->vm_end */ |
1da177e4c Linux-2.6.12-rc2 |
1969 1970 1971 |
/* if it doesn't overlap, we have nothing.. */ end = start + len; |
146425a31 [PATCH] freepgt: ... |
1972 |
if (vma->vm_start >= end) |
1da177e4c Linux-2.6.12-rc2 |
1973 1974 1975 1976 1977 1978 1979 1980 1981 |
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 [PATCH] freepgt: ... |
1982 |
if (start > vma->vm_start) { |
659ace584 mmap: don't retur... |
1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 |
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 Linux-2.6.12-rc2 |
1994 1995 |
if (error) return error; |
146425a31 [PATCH] freepgt: ... |
1996 |
prev = vma; |
1da177e4c Linux-2.6.12-rc2 |
1997 1998 1999 2000 2001 |
} /* Does it split the last one? */ last = find_vma(mm, end); if (last && end > last->vm_start) { |
659ace584 mmap: don't retur... |
2002 |
int error = __split_vma(mm, last, end, 1); |
1da177e4c Linux-2.6.12-rc2 |
2003 2004 2005 |
if (error) return error; } |
146425a31 [PATCH] freepgt: ... |
2006 |
vma = prev? prev->vm_next: mm->mmap; |
1da177e4c Linux-2.6.12-rc2 |
2007 2008 |
/* |
ba470de43 mmap: handle mloc... |
2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 |
* 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 Linux-2.6.12-rc2 |
2023 2024 |
* Remove the vma's, and unmap the actual pages */ |
146425a31 [PATCH] freepgt: ... |
2025 2026 |
detach_vmas_to_be_unmapped(mm, vma, prev, end); unmap_region(mm, vma, prev, start, end); |
1da177e4c Linux-2.6.12-rc2 |
2027 2028 |
/* Fix up all other VM information */ |
2c0b38146 [PATCH] mm: remov... |
2029 |
remove_vma_list(mm, vma); |
1da177e4c Linux-2.6.12-rc2 |
2030 2031 2032 2033 2034 |
return 0; } EXPORT_SYMBOL(do_munmap); |
6a6160a7b [CVE-2009-0029] S... |
2035 |
SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) |
1da177e4c Linux-2.6.12-rc2 |
2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 |
{ int ret; struct mm_struct *mm = current->mm; profile_munmap(addr); down_write(&mm->mmap_sem); ret = do_munmap(mm, addr, len); up_write(&mm->mmap_sem); return ret; } static inline void verify_mm_writelocked(struct mm_struct *mm) { |
a241ec65a [PATCH] RCU tortu... |
2050 |
#ifdef CONFIG_DEBUG_VM |
1da177e4c Linux-2.6.12-rc2 |
2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 |
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. */ unsigned long do_brk(unsigned long addr, unsigned long len) { 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 [PATCH] IA64,spar... |
2070 |
int error; |
1da177e4c Linux-2.6.12-rc2 |
2071 2072 2073 2074 |
len = PAGE_ALIGN(len); if (!len) return addr; |
88c3f7a8f Security: remove ... |
2075 |
error = security_file_mmap(NULL, 0, 0, 0, addr, 1); |
5a211a5de VM/Security: add ... |
2076 2077 |
if (error) return error; |
3a4597568 [PATCH] IA64,spar... |
2078 |
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; |
2c6a10161 switch do_brk() t... |
2079 2080 |
error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (error & ~PAGE_MASK) |
3a4597568 [PATCH] IA64,spar... |
2081 |
return error; |
1da177e4c Linux-2.6.12-rc2 |
2082 2083 2084 2085 2086 |
/* * mlock MCL_FUTURE? */ if (mm->def_flags & VM_LOCKED) { unsigned long locked, lock_limit; |
93ea1d0a1 [PATCH] RLIMIT_ME... |
2087 2088 |
locked = len >> PAGE_SHIFT; locked += mm->locked_vm; |
59e99e5b9 mm: use rlimit he... |
2089 |
lock_limit = rlimit(RLIMIT_MEMLOCK); |
93ea1d0a1 [PATCH] RLIMIT_ME... |
2090 |
lock_limit >>= PAGE_SHIFT; |
1da177e4c Linux-2.6.12-rc2 |
2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 |
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 [PATCH] RLIMIT_AS... |
2113 |
if (!may_expand_vm(mm, len >> PAGE_SHIFT)) |
1da177e4c Linux-2.6.12-rc2 |
2114 2115 2116 2117 2118 2119 2120 |
return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory(len >> PAGE_SHIFT)) return -ENOMEM; |
1da177e4c Linux-2.6.12-rc2 |
2121 |
/* Can we just expand an old private anonymous mapping? */ |
ba470de43 mmap: handle mloc... |
2122 2123 2124 |
vma = vma_merge(mm, prev, addr, addr + len, flags, NULL, NULL, pgoff, NULL); if (vma) |
1da177e4c Linux-2.6.12-rc2 |
2125 2126 2127 2128 2129 |
goto out; /* * create a vma struct for an anonymous mapping */ |
c5e3b83e9 [PATCH] mm: use k... |
2130 |
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c Linux-2.6.12-rc2 |
2131 2132 2133 2134 |
if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } |
1da177e4c Linux-2.6.12-rc2 |
2135 |
|
5beb49305 mm: change anon_v... |
2136 |
INIT_LIST_HEAD(&vma->anon_vma_chain); |
1da177e4c Linux-2.6.12-rc2 |
2137 2138 2139 2140 2141 |
vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; vma->vm_flags = flags; |
3ed75eb8f setup vma->vm_pag... |
2142 |
vma->vm_page_prot = vm_get_page_prot(flags); |
1da177e4c Linux-2.6.12-rc2 |
2143 2144 |
vma_link(mm, vma, prev, rb_link, rb_parent); out: |
3af9e8592 perf: Add non-exe... |
2145 |
perf_event_mmap(vma); |
1da177e4c Linux-2.6.12-rc2 |
2146 2147 |
mm->total_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) { |
ba470de43 mmap: handle mloc... |
2148 2149 |
if (!mlock_vma_pages_range(vma, addr, addr + len)) mm->locked_vm += (len >> PAGE_SHIFT); |
1da177e4c Linux-2.6.12-rc2 |
2150 2151 2152 2153 2154 2155 2156 2157 2158 |
} return addr; } EXPORT_SYMBOL(do_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { |
d16dfc550 mm: mmu_gather re... |
2159 |
struct mmu_gather tlb; |
ba470de43 mmap: handle mloc... |
2160 |
struct vm_area_struct *vma; |
1da177e4c Linux-2.6.12-rc2 |
2161 |
unsigned long nr_accounted = 0; |
ee39b37b2 [PATCH] freepgt: ... |
2162 |
unsigned long end; |
1da177e4c Linux-2.6.12-rc2 |
2163 |
|
d6dd61c83 [PATCH] x86: PARA... |
2164 |
/* mm's last user has gone, and its about to be pulled down */ |
cddb8a5c1 mmu-notifiers: core |
2165 |
mmu_notifier_release(mm); |
d6dd61c83 [PATCH] x86: PARA... |
2166 |
|
ba470de43 mmap: handle mloc... |
2167 2168 2169 2170 2171 2172 2173 2174 |
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 mm: rearrange exi... |
2175 2176 |
arch_exit_mmap(mm); |
ba470de43 mmap: handle mloc... |
2177 |
vma = mm->mmap; |
9480c53e9 mm: rearrange exi... |
2178 2179 |
if (!vma) /* Can happen if dup_mmap() received an OOM */ return; |
1da177e4c Linux-2.6.12-rc2 |
2180 |
lru_add_drain(); |
1da177e4c Linux-2.6.12-rc2 |
2181 |
flush_cache_mm(mm); |
d16dfc550 mm: mmu_gather re... |
2182 |
tlb_gather_mmu(&tlb, mm, 1); |
901608d90 mm: introduce get... |
2183 |
/* update_hiwater_rss(mm) here? but nobody should be looking */ |
e0da382c9 [PATCH] freepgt: ... |
2184 |
/* Use -1 here to ensure all VMAs in the mm are unmapped */ |
508034a32 [PATCH] mm: unmap... |
2185 |
end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); |
1da177e4c Linux-2.6.12-rc2 |
2186 |
vm_unacct_memory(nr_accounted); |
9ba692948 ksm: fix oom dead... |
2187 |
|
d16dfc550 mm: mmu_gather re... |
2188 2189 |
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); tlb_finish_mmu(&tlb, 0, end); |
1da177e4c Linux-2.6.12-rc2 |
2190 |
|
1da177e4c Linux-2.6.12-rc2 |
2191 |
/* |
8f4f8c164 [PATCH] mm: unlin... |
2192 2193 |
* Walk the list again, actually closing and freeing it, * with preemption enabled, without holding any MM locks. |
1da177e4c Linux-2.6.12-rc2 |
2194 |
*/ |
a8fb5618d [PATCH] mm: unlin... |
2195 2196 |
while (vma) vma = remove_vma(vma); |
e0da382c9 [PATCH] freepgt: ... |
2197 |
|
e2cdef8c8 [PATCH] freepgt: ... |
2198 |
BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); |
1da177e4c Linux-2.6.12-rc2 |
2199 2200 2201 2202 |
} /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL |
3d48ae45e mm: Convert i_mma... |
2203 |
* then i_mmap_mutex is taken here. |
1da177e4c Linux-2.6.12-rc2 |
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 |
*/ 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 [PATCH] error pat... |
2229 |
if ((vma->vm_flags & VM_ACCOUNT) && |
34b4e4aa3 fix NULL pointer ... |
2230 |
security_vm_enough_memory_mm(mm, vma_pages(vma))) |
2fd4ef85e [PATCH] error pat... |
2231 |
return -ENOMEM; |
1da177e4c Linux-2.6.12-rc2 |
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 |
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; /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (!vma->vm_file && !vma->anon_vma) pgoff = addr >> PAGE_SHIFT; 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 */ if (vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end) *vmap = new_vma; } else { |
e94b17660 [PATCH] slab: rem... |
2268 |
new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c Linux-2.6.12-rc2 |
2269 2270 |
if (new_vma) { *new_vma = *vma; |
846a16bf0 mempolicy: rename... |
2271 |
pol = mpol_dup(vma_policy(vma)); |
5beb49305 mm: change anon_v... |
2272 2273 2274 2275 2276 |
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 Linux-2.6.12-rc2 |
2277 2278 2279 2280 |
vma_set_policy(new_vma, pol); new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; |
925d1c401 procfs task exe s... |
2281 |
if (new_vma->vm_file) { |
1da177e4c Linux-2.6.12-rc2 |
2282 |
get_file(new_vma->vm_file); |
925d1c401 procfs task exe s... |
2283 2284 2285 |
if (vma->vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); } |
1da177e4c Linux-2.6.12-rc2 |
2286 2287 2288 2289 2290 2291 |
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 mm: change anon_v... |
2292 2293 2294 2295 2296 2297 |
out_free_mempol: mpol_put(pol); out_free_vma: kmem_cache_free(vm_area_cachep, new_vma); return NULL; |
1da177e4c Linux-2.6.12-rc2 |
2298 |
} |
119f657c7 [PATCH] RLIMIT_AS... |
2299 2300 2301 2302 2303 2304 2305 2306 2307 |
/* * 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 mm: use rlimit he... |
2308 |
lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT; |
119f657c7 [PATCH] RLIMIT_AS... |
2309 2310 2311 2312 2313 |
if (cur + npages > lim) return 0; return 1; } |
fa5dc22f8 [PATCH] Add insta... |
2314 |
|
b1d0e4f53 mm: special mappi... |
2315 2316 |
static int special_mapping_fault(struct vm_area_struct *vma, struct vm_fault *vmf) |
fa5dc22f8 [PATCH] Add insta... |
2317 |
{ |
b1d0e4f53 mm: special mappi... |
2318 |
pgoff_t pgoff; |
fa5dc22f8 [PATCH] Add insta... |
2319 |
struct page **pages; |
b1d0e4f53 mm: special mappi... |
2320 2321 2322 2323 2324 2325 2326 |
/* * 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 [PATCH] Add insta... |
2327 |
|
b1d0e4f53 mm: special mappi... |
2328 2329 |
for (pages = vma->vm_private_data; pgoff && *pages; ++pages) pgoff--; |
fa5dc22f8 [PATCH] Add insta... |
2330 2331 2332 2333 |
if (*pages) { struct page *page = *pages; get_page(page); |
b1d0e4f53 mm: special mappi... |
2334 2335 |
vmf->page = page; return 0; |
fa5dc22f8 [PATCH] Add insta... |
2336 |
} |
b1d0e4f53 mm: special mappi... |
2337 |
return VM_FAULT_SIGBUS; |
fa5dc22f8 [PATCH] Add insta... |
2338 2339 2340 2341 2342 2343 2344 2345 |
} /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } |
f0f37e2f7 const: mark struc... |
2346 |
static const struct vm_operations_struct special_mapping_vmops = { |
fa5dc22f8 [PATCH] Add insta... |
2347 |
.close = special_mapping_close, |
b1d0e4f53 mm: special mappi... |
2348 |
.fault = special_mapping_fault, |
fa5dc22f8 [PATCH] Add insta... |
2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 |
}; /* * 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 install_special_m... |
2364 |
int ret; |
fa5dc22f8 [PATCH] Add insta... |
2365 2366 2367 2368 2369 |
struct vm_area_struct *vma; vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (unlikely(vma == NULL)) return -ENOMEM; |
5beb49305 mm: change anon_v... |
2370 |
INIT_LIST_HEAD(&vma->anon_vma_chain); |
fa5dc22f8 [PATCH] Add insta... |
2371 2372 2373 |
vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; |
2f98735c9 vm audit: add VM_... |
2374 |
vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND; |
3ed75eb8f setup vma->vm_pag... |
2375 |
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); |
fa5dc22f8 [PATCH] Add insta... |
2376 2377 2378 |
vma->vm_ops = &special_mapping_vmops; vma->vm_private_data = pages; |
462e635e5 install_special_m... |
2379 2380 2381 2382 2383 2384 2385 |
ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1); if (ret) goto out; ret = insert_vm_struct(mm, vma); if (ret) goto out; |
fa5dc22f8 [PATCH] Add insta... |
2386 2387 |
mm->total_vm += len >> PAGE_SHIFT; |
cdd6c482c perf: Do the big ... |
2388 |
perf_event_mmap(vma); |
089dd79db perf_counter: Gen... |
2389 |
|
fa5dc22f8 [PATCH] Add insta... |
2390 |
return 0; |
462e635e5 install_special_m... |
2391 2392 2393 2394 |
out: kmem_cache_free(vm_area_cachep, vma); return ret; |
fa5dc22f8 [PATCH] Add insta... |
2395 |
} |
7906d00cd mmu-notifiers: ad... |
2396 2397 |
static DEFINE_MUTEX(mm_all_locks_mutex); |
454ed842d lockdep: annotate... |
2398 |
static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) |
7906d00cd mmu-notifiers: ad... |
2399 |
{ |
012f18004 mm: always lock t... |
2400 |
if (!test_bit(0, (unsigned long *) &anon_vma->root->head.next)) { |
7906d00cd mmu-notifiers: ad... |
2401 2402 2403 2404 |
/* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ |
2b575eb64 mm: convert anon_... |
2405 |
mutex_lock_nest_lock(&anon_vma->root->mutex, &mm->mmap_sem); |
7906d00cd mmu-notifiers: ad... |
2406 2407 |
/* * We can safely modify head.next after taking the |
2b575eb64 mm: convert anon_... |
2408 |
* anon_vma->root->mutex. If some other vma in this mm shares |
7906d00cd mmu-notifiers: ad... |
2409 2410 2411 2412 |
* 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 mm: convert anon_... |
2413 |
* anon_vma->root->mutex. |
7906d00cd mmu-notifiers: ad... |
2414 2415 |
*/ if (__test_and_set_bit(0, (unsigned long *) |
012f18004 mm: always lock t... |
2416 |
&anon_vma->root->head.next)) |
7906d00cd mmu-notifiers: ad... |
2417 2418 2419 |
BUG(); } } |
454ed842d lockdep: annotate... |
2420 |
static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) |
7906d00cd mmu-notifiers: ad... |
2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 |
{ 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 mm: Convert i_mma... |
2434 |
mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem); |
7906d00cd mmu-notifiers: ad... |
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 |
} } /* * 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 mm: convert anon_... |
2461 |
* taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never |
7906d00cd mmu-notifiers: ad... |
2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 |
* 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 mm: change anon_v... |
2473 |
struct anon_vma_chain *avc; |
7906d00cd mmu-notifiers: ad... |
2474 2475 2476 2477 2478 2479 2480 2481 |
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 mmu-notifiers: ad... |
2482 |
if (vma->vm_file && vma->vm_file->f_mapping) |
454ed842d lockdep: annotate... |
2483 |
vm_lock_mapping(mm, vma->vm_file->f_mapping); |
7906d00cd mmu-notifiers: ad... |
2484 |
} |
7cd5a02f5 mm: fix mm_take_a... |
2485 2486 2487 2488 2489 |
for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) |
5beb49305 mm: change anon_v... |
2490 2491 |
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); |
7906d00cd mmu-notifiers: ad... |
2492 |
} |
7cd5a02f5 mm: fix mm_take_a... |
2493 |
|
584cff54e mm/mmap.c: elimin... |
2494 |
return 0; |
7906d00cd mmu-notifiers: ad... |
2495 2496 |
out_unlock: |
584cff54e mm/mmap.c: elimin... |
2497 2498 |
mm_drop_all_locks(mm); return -EINTR; |
7906d00cd mmu-notifiers: ad... |
2499 2500 2501 2502 |
} static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { |
012f18004 mm: always lock t... |
2503 |
if (test_bit(0, (unsigned long *) &anon_vma->root->head.next)) { |
7906d00cd mmu-notifiers: ad... |
2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 |
/* * 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 mm: convert anon_... |
2514 |
* anon_vma->root->mutex. |
7906d00cd mmu-notifiers: ad... |
2515 2516 |
*/ if (!__test_and_clear_bit(0, (unsigned long *) |
012f18004 mm: always lock t... |
2517 |
&anon_vma->root->head.next)) |
7906d00cd mmu-notifiers: ad... |
2518 |
BUG(); |
cba48b98f mm: change direct... |
2519 |
anon_vma_unlock(anon_vma); |
7906d00cd mmu-notifiers: ad... |
2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 |
} } 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 mm: Convert i_mma... |
2530 |
mutex_unlock(&mapping->i_mmap_mutex); |
7906d00cd mmu-notifiers: ad... |
2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 |
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 mm: change anon_v... |
2544 |
struct anon_vma_chain *avc; |
7906d00cd mmu-notifiers: ad... |
2545 2546 2547 2548 2549 2550 |
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 mm: change anon_v... |
2551 2552 |
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); |
7906d00cd mmu-notifiers: ad... |
2553 2554 2555 2556 2557 2558 |
if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } |
8feae1311 NOMMU: Make VMAs ... |
2559 2560 2561 2562 2563 2564 |
/* * initialise the VMA slab */ void __init mmap_init(void) { |
00a62ce91 mm: fix Committed... |
2565 2566 2567 2568 |
int ret; ret = percpu_counter_init(&vm_committed_as, 0); VM_BUG_ON(ret); |
8feae1311 NOMMU: Make VMAs ... |
2569 |
} |