Blame view
mm/vmalloc.c
46.4 KB
1da177e4c
|
1 2 3 4 5 6 7 |
/* * linux/mm/vmalloc.c * * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 |
930fc45a4
|
8 |
* Numa awareness, Christoph Lameter, SGI, June 2005 |
1da177e4c
|
9 |
*/ |
db64fe022
|
10 |
#include <linux/vmalloc.h> |
1da177e4c
|
11 12 13 14 15 16 |
#include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> |
5f6a6a9c4
|
17 |
#include <linux/proc_fs.h> |
a10aa5798
|
18 |
#include <linux/seq_file.h> |
3ac7fe5a4
|
19 |
#include <linux/debugobjects.h> |
230169693
|
20 |
#include <linux/kallsyms.h> |
db64fe022
|
21 22 23 24 |
#include <linux/list.h> #include <linux/rbtree.h> #include <linux/radix-tree.h> #include <linux/rcupdate.h> |
f0aa66179
|
25 |
#include <linux/pfn.h> |
89219d37a
|
26 |
#include <linux/kmemleak.h> |
1da177e4c
|
27 |
|
db64fe022
|
28 |
#include <asm/atomic.h> |
1da177e4c
|
29 30 |
#include <asm/uaccess.h> #include <asm/tlbflush.h> |
db64fe022
|
31 |
/*** Page table manipulation functions ***/ |
b221385bc
|
32 |
|
1da177e4c
|
33 34 35 36 37 38 39 40 41 42 |
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) { pte_t *pte; pte = pte_offset_kernel(pmd, addr); do { pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); } |
db64fe022
|
43 |
static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) |
1da177e4c
|
44 45 46 47 48 49 50 51 52 53 54 55 |
{ pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next); } while (pmd++, addr = next, addr != end); } |
db64fe022
|
56 |
static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) |
1da177e4c
|
57 58 59 60 61 62 63 64 65 66 67 68 |
{ pud_t *pud; unsigned long next; pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next); } while (pud++, addr = next, addr != end); } |
db64fe022
|
69 |
static void vunmap_page_range(unsigned long addr, unsigned long end) |
1da177e4c
|
70 71 72 |
{ pgd_t *pgd; unsigned long next; |
1da177e4c
|
73 74 75 |
BUG_ON(addr >= end); pgd = pgd_offset_k(addr); |
1da177e4c
|
76 77 78 79 80 81 |
do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; vunmap_pud_range(pgd, addr, next); } while (pgd++, addr = next, addr != end); |
1da177e4c
|
82 83 84 |
} static int vmap_pte_range(pmd_t *pmd, unsigned long addr, |
db64fe022
|
85 |
unsigned long end, pgprot_t prot, struct page **pages, int *nr) |
1da177e4c
|
86 87 |
{ pte_t *pte; |
db64fe022
|
88 89 90 91 |
/* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ |
872fec16d
|
92 |
pte = pte_alloc_kernel(pmd, addr); |
1da177e4c
|
93 94 95 |
if (!pte) return -ENOMEM; do { |
db64fe022
|
96 97 98 99 100 |
struct page *page = pages[*nr]; if (WARN_ON(!pte_none(*pte))) return -EBUSY; if (WARN_ON(!page)) |
1da177e4c
|
101 102 |
return -ENOMEM; set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); |
db64fe022
|
103 |
(*nr)++; |
1da177e4c
|
104 105 106 |
} while (pte++, addr += PAGE_SIZE, addr != end); return 0; } |
db64fe022
|
107 108 |
static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) |
1da177e4c
|
109 110 111 112 113 114 115 116 117 |
{ pmd_t *pmd; unsigned long next; pmd = pmd_alloc(&init_mm, pud, addr); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); |
db64fe022
|
118 |
if (vmap_pte_range(pmd, addr, next, prot, pages, nr)) |
1da177e4c
|
119 120 121 122 |
return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } |
db64fe022
|
123 124 |
static int vmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) |
1da177e4c
|
125 126 127 128 129 130 131 132 133 |
{ pud_t *pud; unsigned long next; pud = pud_alloc(&init_mm, pgd, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); |
db64fe022
|
134 |
if (vmap_pmd_range(pud, addr, next, prot, pages, nr)) |
1da177e4c
|
135 136 137 138 |
return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } |
db64fe022
|
139 140 141 142 143 144 |
/* * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and * will have pfns corresponding to the "pages" array. * * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] */ |
8fc489850
|
145 146 |
static int vmap_page_range_noflush(unsigned long start, unsigned long end, pgprot_t prot, struct page **pages) |
1da177e4c
|
147 148 149 |
{ pgd_t *pgd; unsigned long next; |
2e4e27c7d
|
150 |
unsigned long addr = start; |
db64fe022
|
151 152 |
int err = 0; int nr = 0; |
1da177e4c
|
153 154 155 |
BUG_ON(addr >= end); pgd = pgd_offset_k(addr); |
1da177e4c
|
156 157 |
do { next = pgd_addr_end(addr, end); |
db64fe022
|
158 |
err = vmap_pud_range(pgd, addr, next, prot, pages, &nr); |
1da177e4c
|
159 160 161 |
if (err) break; } while (pgd++, addr = next, addr != end); |
db64fe022
|
162 163 164 165 |
if (unlikely(err)) return err; return nr; |
1da177e4c
|
166 |
} |
8fc489850
|
167 168 169 170 171 172 173 174 175 |
static int vmap_page_range(unsigned long start, unsigned long end, pgprot_t prot, struct page **pages) { int ret; ret = vmap_page_range_noflush(start, end, prot, pages); flush_cache_vmap(start, end); return ret; } |
73bdf0a60
|
176 177 178 |
static inline int is_vmalloc_or_module_addr(const void *x) { /* |
ab4f2ee13
|
179 |
* ARM, x86-64 and sparc64 put modules in a special place, |
73bdf0a60
|
180 181 182 183 184 185 186 187 188 189 |
* and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_MODULES) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)x; if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } |
48667e7a4
|
190 |
/* |
db64fe022
|
191 |
* Walk a vmap address to the struct page it maps. |
48667e7a4
|
192 |
*/ |
b3bdda02a
|
193 |
struct page *vmalloc_to_page(const void *vmalloc_addr) |
48667e7a4
|
194 195 196 197 |
{ unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); |
48667e7a4
|
198 |
|
7aa413def
|
199 200 201 202 |
/* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ |
73bdf0a60
|
203 |
VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); |
59ea74633
|
204 |
|
48667e7a4
|
205 |
if (!pgd_none(*pgd)) { |
db64fe022
|
206 |
pud_t *pud = pud_offset(pgd, addr); |
48667e7a4
|
207 |
if (!pud_none(*pud)) { |
db64fe022
|
208 |
pmd_t *pmd = pmd_offset(pud, addr); |
48667e7a4
|
209 |
if (!pmd_none(*pmd)) { |
db64fe022
|
210 |
pte_t *ptep, pte; |
48667e7a4
|
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 |
ptep = pte_offset_map(pmd, addr); pte = *ptep; if (pte_present(pte)) page = pte_page(pte); pte_unmap(ptep); } } } return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ |
b3bdda02a
|
226 |
unsigned long vmalloc_to_pfn(const void *vmalloc_addr) |
48667e7a4
|
227 228 229 230 |
{ return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); |
db64fe022
|
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 |
/*** Global kva allocator ***/ #define VM_LAZY_FREE 0x01 #define VM_LAZY_FREEING 0x02 #define VM_VM_AREA 0x04 struct vmap_area { unsigned long va_start; unsigned long va_end; unsigned long flags; struct rb_node rb_node; /* address sorted rbtree */ struct list_head list; /* address sorted list */ struct list_head purge_list; /* "lazy purge" list */ void *private; struct rcu_head rcu_head; }; static DEFINE_SPINLOCK(vmap_area_lock); static struct rb_root vmap_area_root = RB_ROOT; static LIST_HEAD(vmap_area_list); static struct vmap_area *__find_vmap_area(unsigned long addr) |
1da177e4c
|
254 |
{ |
db64fe022
|
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 |
struct rb_node *n = vmap_area_root.rb_node; while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr > va->va_start) n = n->rb_right; else return va; } return NULL; } static void __insert_vmap_area(struct vmap_area *va) { struct rb_node **p = &vmap_area_root.rb_node; struct rb_node *parent = NULL; struct rb_node *tmp; while (*p) { struct vmap_area *tmp; parent = *p; tmp = rb_entry(parent, struct vmap_area, rb_node); if (va->va_start < tmp->va_end) p = &(*p)->rb_left; else if (va->va_end > tmp->va_start) p = &(*p)->rb_right; else BUG(); } rb_link_node(&va->rb_node, parent, p); rb_insert_color(&va->rb_node, &vmap_area_root); /* address-sort this list so it is usable like the vmlist */ tmp = rb_prev(&va->rb_node); if (tmp) { struct vmap_area *prev; prev = rb_entry(tmp, struct vmap_area, rb_node); list_add_rcu(&va->list, &prev->list); } else list_add_rcu(&va->list, &vmap_area_list); } static void purge_vmap_area_lazy(void); /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask) { struct vmap_area *va; struct rb_node *n; |
1da177e4c
|
317 |
unsigned long addr; |
db64fe022
|
318 |
int purged = 0; |
7766970cc
|
319 |
BUG_ON(!size); |
db64fe022
|
320 |
BUG_ON(size & ~PAGE_MASK); |
db64fe022
|
321 322 323 324 325 326 |
va = kmalloc_node(sizeof(struct vmap_area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); retry: |
0ae15132a
|
327 |
addr = ALIGN(vstart, align); |
db64fe022
|
328 |
spin_lock(&vmap_area_lock); |
7766970cc
|
329 330 |
if (addr + size - 1 < addr) goto overflow; |
db64fe022
|
331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 |
/* XXX: could have a last_hole cache */ n = vmap_area_root.rb_node; if (n) { struct vmap_area *first = NULL; do { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end >= addr) { if (!first && tmp->va_start < addr + size) first = tmp; n = n->rb_left; } else { first = tmp; n = n->rb_right; } } while (n); if (!first) goto found; if (first->va_end < addr) { n = rb_next(&first->rb_node); if (n) first = rb_entry(n, struct vmap_area, rb_node); else goto found; } |
f011c2dae
|
359 |
while (addr + size > first->va_start && addr + size <= vend) { |
db64fe022
|
360 |
addr = ALIGN(first->va_end + PAGE_SIZE, align); |
7766970cc
|
361 362 |
if (addr + size - 1 < addr) goto overflow; |
db64fe022
|
363 364 365 366 367 368 369 370 371 372 |
n = rb_next(&first->rb_node); if (n) first = rb_entry(n, struct vmap_area, rb_node); else goto found; } } found: if (addr + size > vend) { |
7766970cc
|
373 |
overflow: |
db64fe022
|
374 375 376 377 378 379 380 |
spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); purged = 1; goto retry; } if (printk_ratelimit()) |
c1279c4ef
|
381 382 383 384 |
printk(KERN_WARNING "vmap allocation for size %lu failed: " "use vmalloc=<size> to increase size. ", size); |
2498ce42d
|
385 |
kfree(va); |
db64fe022
|
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 |
return ERR_PTR(-EBUSY); } BUG_ON(addr & (align-1)); va->va_start = addr; va->va_end = addr + size; va->flags = 0; __insert_vmap_area(va); spin_unlock(&vmap_area_lock); return va; } static void rcu_free_va(struct rcu_head *head) { struct vmap_area *va = container_of(head, struct vmap_area, rcu_head); kfree(va); } static void __free_vmap_area(struct vmap_area *va) { BUG_ON(RB_EMPTY_NODE(&va->rb_node)); rb_erase(&va->rb_node, &vmap_area_root); RB_CLEAR_NODE(&va->rb_node); list_del_rcu(&va->list); call_rcu(&va->rcu_head, rcu_free_va); } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { spin_lock(&vmap_area_lock); __free_vmap_area(va); spin_unlock(&vmap_area_lock); } /* * Clear the pagetable entries of a given vmap_area */ static void unmap_vmap_area(struct vmap_area *va) { vunmap_page_range(va->va_start, va->va_end); } |
cd52858c7
|
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 |
static void vmap_debug_free_range(unsigned long start, unsigned long end) { /* * Unmap page tables and force a TLB flush immediately if * CONFIG_DEBUG_PAGEALLOC is set. This catches use after free * bugs similarly to those in linear kernel virtual address * space after a page has been freed. * * All the lazy freeing logic is still retained, in order to * minimise intrusiveness of this debugging feature. * * This is going to be *slow* (linear kernel virtual address * debugging doesn't do a broadcast TLB flush so it is a lot * faster). */ #ifdef CONFIG_DEBUG_PAGEALLOC vunmap_page_range(start, end); flush_tlb_kernel_range(start, end); #endif } |
db64fe022
|
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 |
/* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_t vmap_lazy_nr = ATOMIC_INIT(0); /* * Purges all lazily-freed vmap areas. * * If sync is 0 then don't purge if there is already a purge in progress. * If force_flush is 1, then flush kernel TLBs between *start and *end even * if we found no lazy vmap areas to unmap (callers can use this to optimise * their own TLB flushing). * Returns with *start = min(*start, lowest purged address) * *end = max(*end, highest purged address) */ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, int sync, int force_flush) { |
46666d8ac
|
494 |
static DEFINE_SPINLOCK(purge_lock); |
db64fe022
|
495 496 |
LIST_HEAD(valist); struct vmap_area *va; |
cbb766766
|
497 |
struct vmap_area *n_va; |
db64fe022
|
498 499 500 501 502 503 504 505 |
int nr = 0; /* * If sync is 0 but force_flush is 1, we'll go sync anyway but callers * should not expect such behaviour. This just simplifies locking for * the case that isn't actually used at the moment anyway. */ if (!sync && !force_flush) { |
46666d8ac
|
506 |
if (!spin_trylock(&purge_lock)) |
db64fe022
|
507 508 |
return; } else |
46666d8ac
|
509 |
spin_lock(&purge_lock); |
db64fe022
|
510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 |
rcu_read_lock(); list_for_each_entry_rcu(va, &vmap_area_list, list) { if (va->flags & VM_LAZY_FREE) { if (va->va_start < *start) *start = va->va_start; if (va->va_end > *end) *end = va->va_end; nr += (va->va_end - va->va_start) >> PAGE_SHIFT; unmap_vmap_area(va); list_add_tail(&va->purge_list, &valist); va->flags |= VM_LAZY_FREEING; va->flags &= ~VM_LAZY_FREE; } } rcu_read_unlock(); if (nr) { BUG_ON(nr > atomic_read(&vmap_lazy_nr)); atomic_sub(nr, &vmap_lazy_nr); } if (nr || force_flush) flush_tlb_kernel_range(*start, *end); if (nr) { spin_lock(&vmap_area_lock); |
cbb766766
|
537 |
list_for_each_entry_safe(va, n_va, &valist, purge_list) |
db64fe022
|
538 539 540 |
__free_vmap_area(va); spin_unlock(&vmap_area_lock); } |
46666d8ac
|
541 |
spin_unlock(&purge_lock); |
db64fe022
|
542 543 544 |
} /* |
496850e5f
|
545 546 547 548 549 550 551 552 553 554 555 |
* Kick off a purge of the outstanding lazy areas. Don't bother if somebody * is already purging. */ static void try_purge_vmap_area_lazy(void) { unsigned long start = ULONG_MAX, end = 0; __purge_vmap_area_lazy(&start, &end, 0, 0); } /* |
db64fe022
|
556 557 558 559 560 |
* Kick off a purge of the outstanding lazy areas. */ static void purge_vmap_area_lazy(void) { unsigned long start = ULONG_MAX, end = 0; |
496850e5f
|
561 |
__purge_vmap_area_lazy(&start, &end, 1, 0); |
db64fe022
|
562 563 564 |
} /* |
b29acbdcf
|
565 566 |
* Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been * called for the correct range previously. |
db64fe022
|
567 |
*/ |
b29acbdcf
|
568 |
static void free_unmap_vmap_area_noflush(struct vmap_area *va) |
db64fe022
|
569 570 571 572 |
{ va->flags |= VM_LAZY_FREE; atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages())) |
496850e5f
|
573 |
try_purge_vmap_area_lazy(); |
db64fe022
|
574 |
} |
b29acbdcf
|
575 576 577 578 579 580 581 582 |
/* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); free_unmap_vmap_area_noflush(va); } |
db64fe022
|
583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 |
static struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_area *va; spin_lock(&vmap_area_lock); va = __find_vmap_area(addr); spin_unlock(&vmap_area_lock); return va; } static void free_unmap_vmap_area_addr(unsigned long addr) { struct vmap_area *va; va = find_vmap_area(addr); BUG_ON(!va); free_unmap_vmap_area(va); } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / NR_CPUS / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) |
9b4633340
|
632 |
static bool vmap_initialized __read_mostly = false; |
db64fe022
|
633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 |
struct vmap_block_queue { spinlock_t lock; struct list_head free; struct list_head dirty; unsigned int nr_dirty; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; struct vmap_block_queue *vbq; unsigned long free, dirty; DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS); DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); union { |
d086817dc
|
648 |
struct list_head free_list; |
db64fe022
|
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 |
struct rcu_head rcu_head; }; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block * in the free path. Could get rid of this if we change the API to return a * "cookie" from alloc, to be passed to free. But no big deal yet. */ static DEFINE_SPINLOCK(vmap_block_tree_lock); static RADIX_TREE(vmap_block_tree, GFP_ATOMIC); /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static struct vmap_block *new_vmap_block(gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; int node, err; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask); if (unlikely(IS_ERR(va))) { kfree(vb); return ERR_PTR(PTR_ERR(va)); } err = radix_tree_preload(gfp_mask); if (unlikely(err)) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } spin_lock_init(&vb->lock); vb->va = va; vb->free = VMAP_BBMAP_BITS; vb->dirty = 0; bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS); bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); INIT_LIST_HEAD(&vb->free_list); |
db64fe022
|
715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 |
vb_idx = addr_to_vb_idx(va->va_start); spin_lock(&vmap_block_tree_lock); err = radix_tree_insert(&vmap_block_tree, vb_idx, vb); spin_unlock(&vmap_block_tree_lock); BUG_ON(err); radix_tree_preload_end(); vbq = &get_cpu_var(vmap_block_queue); vb->vbq = vbq; spin_lock(&vbq->lock); list_add(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); put_cpu_var(vmap_cpu_blocks); return vb; } static void rcu_free_vb(struct rcu_head *head) { struct vmap_block *vb = container_of(head, struct vmap_block, rcu_head); kfree(vb); } static void free_vmap_block(struct vmap_block *vb) { struct vmap_block *tmp; unsigned long vb_idx; |
d086817dc
|
744 |
BUG_ON(!list_empty(&vb->free_list)); |
db64fe022
|
745 746 747 748 749 750 |
vb_idx = addr_to_vb_idx(vb->va->va_start); spin_lock(&vmap_block_tree_lock); tmp = radix_tree_delete(&vmap_block_tree, vb_idx); spin_unlock(&vmap_block_tree_lock); BUG_ON(tmp != vb); |
b29acbdcf
|
751 |
free_unmap_vmap_area_noflush(vb->va); |
db64fe022
|
752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 |
call_rcu(&vb->rcu_head, rcu_free_vb); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; unsigned long addr = 0; unsigned int order; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); order = get_order(size); again: rcu_read_lock(); vbq = &get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; spin_lock(&vb->lock); i = bitmap_find_free_region(vb->alloc_map, VMAP_BBMAP_BITS, order); if (i >= 0) { addr = vb->va->va_start + (i << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(vb->va->va_start)); vb->free -= 1UL << order; if (vb->free == 0) { spin_lock(&vbq->lock); list_del_init(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } spin_unlock(&vb->lock); } put_cpu_var(vmap_cpu_blocks); rcu_read_unlock(); if (!addr) { vb = new_vmap_block(gfp_mask); if (IS_ERR(vb)) return vb; goto again; } return (void *)addr; } static void vb_free(const void *addr, unsigned long size) { unsigned long offset; unsigned long vb_idx; unsigned int order; struct vmap_block *vb; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); |
b29acbdcf
|
813 814 |
flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size); |
db64fe022
|
815 816 817 818 819 820 821 822 823 824 825 826 |
order = get_order(size); offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1); vb_idx = addr_to_vb_idx((unsigned long)addr); rcu_read_lock(); vb = radix_tree_lookup(&vmap_block_tree, vb_idx); rcu_read_unlock(); BUG_ON(!vb); spin_lock(&vb->lock); bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order); |
d086817dc
|
827 |
|
db64fe022
|
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 |
vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free || !list_empty(&vb->free_list)); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { unsigned long start = ULONG_MAX, end = 0; int cpu; int flush = 0; |
9b4633340
|
855 856 |
if (unlikely(!vmap_initialized)) return; |
db64fe022
|
857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 |
for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; spin_lock(&vb->lock); i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS); while (i < VMAP_BBMAP_BITS) { unsigned long s, e; int j; j = find_next_zero_bit(vb->dirty_map, VMAP_BBMAP_BITS, i); s = vb->va->va_start + (i << PAGE_SHIFT); e = vb->va->va_start + (j << PAGE_SHIFT); vunmap_page_range(s, e); flush = 1; if (s < start) start = s; if (e > end) end = e; i = j; i = find_next_bit(vb->dirty_map, VMAP_BBMAP_BITS, i); } spin_unlock(&vb->lock); } rcu_read_unlock(); } __purge_vmap_area_lazy(&start, &end, 1, flush); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = count << PAGE_SHIFT; unsigned long addr = (unsigned long)mem; BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(addr & (PAGE_SIZE-1)); debug_check_no_locks_freed(mem, size); |
cd52858c7
|
912 |
vmap_debug_free_range(addr, addr+size); |
db64fe022
|
913 914 915 916 917 918 919 920 921 922 923 924 925 926 |
if (likely(count <= VMAP_MAX_ALLOC)) vb_free(mem, size); else free_unmap_vmap_area_addr(addr); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * @prot: memory protection to use. PAGE_KERNEL for regular RAM |
e99c97ade
|
927 928 |
* * Returns: a pointer to the address that has been mapped, or %NULL on failure |
db64fe022
|
929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 |
*/ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) { unsigned long size = count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } if (vmap_page_range(addr, addr + size, prot, pages) < 0) { vm_unmap_ram(mem, count); return NULL; } return mem; } EXPORT_SYMBOL(vm_map_ram); |
f0aa66179
|
958 959 960 |
/** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register |
c0c0a2937
|
961 |
* @align: requested alignment |
f0aa66179
|
962 963 964 965 966 967 968 969 |
* * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ |
c0c0a2937
|
970 |
void __init vm_area_register_early(struct vm_struct *vm, size_t align) |
f0aa66179
|
971 972 |
{ static size_t vm_init_off __initdata; |
c0c0a2937
|
973 974 975 976 |
unsigned long addr; addr = ALIGN(VMALLOC_START + vm_init_off, align); vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; |
f0aa66179
|
977 |
|
c0c0a2937
|
978 |
vm->addr = (void *)addr; |
f0aa66179
|
979 980 981 982 |
vm->next = vmlist; vmlist = vm; } |
db64fe022
|
983 984 |
void __init vmalloc_init(void) { |
822c18f2e
|
985 986 |
struct vmap_area *va; struct vm_struct *tmp; |
db64fe022
|
987 988 989 990 991 992 993 994 995 996 997 |
int i; for_each_possible_cpu(i) { struct vmap_block_queue *vbq; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); INIT_LIST_HEAD(&vbq->dirty); vbq->nr_dirty = 0; } |
9b4633340
|
998 |
|
822c18f2e
|
999 1000 |
/* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { |
43ebdac42
|
1001 |
va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT); |
822c18f2e
|
1002 1003 1004 1005 1006 |
va->flags = tmp->flags | VM_VM_AREA; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; __insert_vmap_area(va); } |
9b4633340
|
1007 |
vmap_initialized = true; |
db64fe022
|
1008 |
} |
8fc489850
|
1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 |
/** * map_kernel_range_noflush - map kernel VM area with the specified pages * @addr: start of the VM area to map * @size: size of the VM area to map * @prot: page protection flags to use * @pages: pages to map * * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size * specify should have been allocated using get_vm_area() and its * friends. * * NOTE: * This function does NOT do any cache flushing. The caller is * responsible for calling flush_cache_vmap() on to-be-mapped areas * before calling this function. * * RETURNS: * The number of pages mapped on success, -errno on failure. */ int map_kernel_range_noflush(unsigned long addr, unsigned long size, pgprot_t prot, struct page **pages) { return vmap_page_range_noflush(addr, addr + size, prot, pages); } /** * unmap_kernel_range_noflush - unmap kernel VM area * @addr: start of the VM area to unmap * @size: size of the VM area to unmap * * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size * specify should have been allocated using get_vm_area() and its * friends. * * NOTE: * This function does NOT do any cache flushing. The caller is * responsible for calling flush_cache_vunmap() on to-be-mapped areas * before calling this function and flush_tlb_kernel_range() after. */ void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) { vunmap_page_range(addr, addr + size); } /** * unmap_kernel_range - unmap kernel VM area and flush cache and TLB * @addr: start of the VM area to unmap * @size: size of the VM area to unmap * * Similar to unmap_kernel_range_noflush() but flushes vcache before * the unmapping and tlb after. */ |
db64fe022
|
1061 1062 1063 |
void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; |
f6fcba701
|
1064 1065 |
flush_cache_vunmap(addr, end); |
db64fe022
|
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 |
vunmap_page_range(addr, end); flush_tlb_kernel_range(addr, end); } int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) { unsigned long addr = (unsigned long)area->addr; unsigned long end = addr + area->size - PAGE_SIZE; int err; err = vmap_page_range(addr, end, prot, *pages); if (err > 0) { *pages += err; err = 0; } return err; } EXPORT_SYMBOL_GPL(map_vm_area); /*** Old vmalloc interfaces ***/ DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, void *caller) { static struct vmap_area *va; struct vm_struct *area; struct vm_struct *tmp, **p; unsigned long align = 1; |
1da177e4c
|
1098 |
|
52fd24ca1
|
1099 |
BUG_ON(in_interrupt()); |
1da177e4c
|
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 |
if (flags & VM_IOREMAP) { int bit = fls(size); if (bit > IOREMAP_MAX_ORDER) bit = IOREMAP_MAX_ORDER; else if (bit < PAGE_SHIFT) bit = PAGE_SHIFT; align = 1ul << bit; } |
db64fe022
|
1110 |
|
1da177e4c
|
1111 |
size = PAGE_ALIGN(size); |
31be83095
|
1112 1113 |
if (unlikely(!size)) return NULL; |
1da177e4c
|
1114 |
|
6cb062296
|
1115 |
area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); |
1da177e4c
|
1116 1117 |
if (unlikely(!area)) return NULL; |
1da177e4c
|
1118 1119 1120 1121 |
/* * We always allocate a guard page. */ size += PAGE_SIZE; |
db64fe022
|
1122 1123 1124 1125 |
va = alloc_vmap_area(size, align, start, end, node, gfp_mask); if (IS_ERR(va)) { kfree(area); return NULL; |
1da177e4c
|
1126 |
} |
1da177e4c
|
1127 1128 |
area->flags = flags; |
db64fe022
|
1129 |
area->addr = (void *)va->va_start; |
1da177e4c
|
1130 1131 1132 1133 |
area->size = size; area->pages = NULL; area->nr_pages = 0; area->phys_addr = 0; |
230169693
|
1134 |
area->caller = caller; |
db64fe022
|
1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 |
va->private = area; va->flags |= VM_VM_AREA; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= area->addr) break; } area->next = *p; *p = area; |
1da177e4c
|
1145 1146 1147 |
write_unlock(&vmlist_lock); return area; |
1da177e4c
|
1148 |
} |
930fc45a4
|
1149 1150 1151 |
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { |
230169693
|
1152 1153 |
return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, __builtin_return_address(0)); |
930fc45a4
|
1154 |
} |
5992b6dac
|
1155 |
EXPORT_SYMBOL_GPL(__get_vm_area); |
930fc45a4
|
1156 |
|
c29686129
|
1157 1158 1159 1160 1161 1162 1163 |
struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, void *caller) { return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, caller); } |
1da177e4c
|
1164 |
/** |
183ff22bb
|
1165 |
* get_vm_area - reserve a contiguous kernel virtual area |
1da177e4c
|
1166 1167 1168 1169 1170 1171 1172 1173 1174 |
* @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { |
230169693
|
1175 1176 1177 1178 1179 1180 1181 1182 1183 |
return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, void *caller) { return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, caller); |
1da177e4c
|
1184 |
} |
52fd24ca1
|
1185 1186 |
struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node, gfp_t gfp_mask) |
930fc45a4
|
1187 |
{ |
52fd24ca1
|
1188 |
return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node, |
230169693
|
1189 |
gfp_mask, __builtin_return_address(0)); |
930fc45a4
|
1190 |
} |
db64fe022
|
1191 |
static struct vm_struct *find_vm_area(const void *addr) |
833423143
|
1192 |
{ |
db64fe022
|
1193 |
struct vmap_area *va; |
833423143
|
1194 |
|
db64fe022
|
1195 1196 1197 |
va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) return va->private; |
1da177e4c
|
1198 |
|
1da177e4c
|
1199 |
return NULL; |
1da177e4c
|
1200 |
} |
7856dfeb2
|
1201 |
/** |
183ff22bb
|
1202 |
* remove_vm_area - find and remove a continuous kernel virtual area |
7856dfeb2
|
1203 1204 1205 1206 1207 1208 |
* @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. */ |
b3bdda02a
|
1209 |
struct vm_struct *remove_vm_area(const void *addr) |
7856dfeb2
|
1210 |
{ |
db64fe022
|
1211 1212 1213 1214 1215 1216 |
struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->private; struct vm_struct *tmp, **p; |
cd52858c7
|
1217 1218 |
vmap_debug_free_range(va->va_start, va->va_end); |
db64fe022
|
1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 |
free_unmap_vmap_area(va); vm->size -= PAGE_SIZE; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) ; *p = tmp->next; write_unlock(&vmlist_lock); return vm; } return NULL; |
7856dfeb2
|
1231 |
} |
b3bdda02a
|
1232 |
static void __vunmap(const void *addr, int deallocate_pages) |
1da177e4c
|
1233 1234 1235 1236 1237 1238 1239 |
{ struct vm_struct *area; if (!addr) return; if ((PAGE_SIZE-1) & (unsigned long)addr) { |
4c8573e25
|
1240 1241 |
WARN(1, KERN_ERR "Trying to vfree() bad address (%p) ", addr); |
1da177e4c
|
1242 1243 1244 1245 1246 |
return; } area = remove_vm_area(addr); if (unlikely(!area)) { |
4c8573e25
|
1247 1248 |
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p) ", |
1da177e4c
|
1249 |
addr); |
1da177e4c
|
1250 1251 |
return; } |
9a11b49a8
|
1252 |
debug_check_no_locks_freed(addr, area->size); |
3ac7fe5a4
|
1253 |
debug_check_no_obj_freed(addr, area->size); |
9a11b49a8
|
1254 |
|
1da177e4c
|
1255 1256 1257 1258 |
if (deallocate_pages) { int i; for (i = 0; i < area->nr_pages; i++) { |
bf53d6f8f
|
1259 1260 1261 1262 |
struct page *page = area->pages[i]; BUG_ON(!page); __free_page(page); |
1da177e4c
|
1263 |
} |
8757d5fa6
|
1264 |
if (area->flags & VM_VPAGES) |
1da177e4c
|
1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 |
vfree(area->pages); else kfree(area->pages); } kfree(area); return; } /** * vfree - release memory allocated by vmalloc() |
1da177e4c
|
1276 1277 |
* @addr: memory base address * |
183ff22bb
|
1278 |
* Free the virtually continuous memory area starting at @addr, as |
80e93effc
|
1279 1280 |
* obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is * NULL, no operation is performed. |
1da177e4c
|
1281 |
* |
80e93effc
|
1282 |
* Must not be called in interrupt context. |
1da177e4c
|
1283 |
*/ |
b3bdda02a
|
1284 |
void vfree(const void *addr) |
1da177e4c
|
1285 1286 |
{ BUG_ON(in_interrupt()); |
89219d37a
|
1287 1288 |
kmemleak_free(addr); |
1da177e4c
|
1289 1290 |
__vunmap(addr, 1); } |
1da177e4c
|
1291 1292 1293 1294 |
EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() |
1da177e4c
|
1295 1296 1297 1298 1299 |
* @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * |
80e93effc
|
1300 |
* Must not be called in interrupt context. |
1da177e4c
|
1301 |
*/ |
b3bdda02a
|
1302 |
void vunmap(const void *addr) |
1da177e4c
|
1303 1304 |
{ BUG_ON(in_interrupt()); |
34754b69a
|
1305 |
might_sleep(); |
1da177e4c
|
1306 1307 |
__vunmap(addr, 0); } |
1da177e4c
|
1308 1309 1310 1311 |
EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space |
1da177e4c
|
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 |
* @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual * space. */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; |
34754b69a
|
1324 |
might_sleep(); |
1da177e4c
|
1325 1326 |
if (count > num_physpages) return NULL; |
230169693
|
1327 1328 |
area = get_vm_area_caller((count << PAGE_SHIFT), flags, __builtin_return_address(0)); |
1da177e4c
|
1329 1330 |
if (!area) return NULL; |
230169693
|
1331 |
|
1da177e4c
|
1332 1333 1334 1335 1336 1337 1338 |
if (map_vm_area(area, prot, &pages)) { vunmap(area->addr); return NULL; } return area->addr; } |
1da177e4c
|
1339 |
EXPORT_SYMBOL(vmap); |
db64fe022
|
1340 1341 |
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, int node, void *caller); |
e31d9eb5c
|
1342 |
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, |
230169693
|
1343 |
pgprot_t prot, int node, void *caller) |
1da177e4c
|
1344 1345 1346 1347 1348 1349 1350 1351 1352 |
{ struct page **pages; unsigned int nr_pages, array_size, i; nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ |
8757d5fa6
|
1353 |
if (array_size > PAGE_SIZE) { |
94f6030ca
|
1354 |
pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO, |
230169693
|
1355 |
PAGE_KERNEL, node, caller); |
8757d5fa6
|
1356 |
area->flags |= VM_VPAGES; |
286e1ea3a
|
1357 1358 |
} else { pages = kmalloc_node(array_size, |
6cb062296
|
1359 |
(gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO, |
286e1ea3a
|
1360 1361 |
node); } |
1da177e4c
|
1362 |
area->pages = pages; |
230169693
|
1363 |
area->caller = caller; |
1da177e4c
|
1364 1365 1366 1367 1368 |
if (!area->pages) { remove_vm_area(area->addr); kfree(area); return NULL; } |
1da177e4c
|
1369 1370 |
for (i = 0; i < area->nr_pages; i++) { |
bf53d6f8f
|
1371 |
struct page *page; |
930fc45a4
|
1372 |
if (node < 0) |
bf53d6f8f
|
1373 |
page = alloc_page(gfp_mask); |
930fc45a4
|
1374 |
else |
bf53d6f8f
|
1375 1376 1377 |
page = alloc_pages_node(node, gfp_mask, 0); if (unlikely(!page)) { |
1da177e4c
|
1378 1379 1380 1381 |
/* Successfully allocated i pages, free them in __vunmap() */ area->nr_pages = i; goto fail; } |
bf53d6f8f
|
1382 |
area->pages[i] = page; |
1da177e4c
|
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 |
} if (map_vm_area(area, prot, &pages)) goto fail; return area->addr; fail: vfree(area->addr); return NULL; } |
930fc45a4
|
1393 1394 |
void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) { |
89219d37a
|
1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 |
void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1, __builtin_return_address(0)); /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. */ kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask); return addr; |
930fc45a4
|
1406 |
} |
1da177e4c
|
1407 |
/** |
930fc45a4
|
1408 |
* __vmalloc_node - allocate virtually contiguous memory |
1da177e4c
|
1409 1410 1411 |
* @size: allocation size * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages |
d44e0780b
|
1412 |
* @node: node to use for allocation or -1 |
c85d194bf
|
1413 |
* @caller: caller's return address |
1da177e4c
|
1414 1415 1416 1417 1418 |
* * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. */ |
b221385bc
|
1419 |
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, |
230169693
|
1420 |
int node, void *caller) |
1da177e4c
|
1421 1422 |
{ struct vm_struct *area; |
89219d37a
|
1423 1424 |
void *addr; unsigned long real_size = size; |
1da177e4c
|
1425 1426 1427 1428 |
size = PAGE_ALIGN(size); if (!size || (size >> PAGE_SHIFT) > num_physpages) return NULL; |
230169693
|
1429 1430 |
area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END, node, gfp_mask, caller); |
1da177e4c
|
1431 1432 |
if (!area) return NULL; |
89219d37a
|
1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 |
addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. */ kmemleak_alloc(addr, real_size, 3, gfp_mask); return addr; |
1da177e4c
|
1443 |
} |
930fc45a4
|
1444 1445 |
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { |
230169693
|
1446 1447 |
return __vmalloc_node(size, gfp_mask, prot, -1, __builtin_return_address(0)); |
930fc45a4
|
1448 |
} |
1da177e4c
|
1449 1450 1451 1452 |
EXPORT_SYMBOL(__vmalloc); /** * vmalloc - allocate virtually contiguous memory |
1da177e4c
|
1453 |
* @size: allocation size |
1da177e4c
|
1454 1455 1456 |
* Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * |
c1c8897f8
|
1457 |
* For tight control over page level allocator and protection flags |
1da177e4c
|
1458 1459 1460 1461 |
* use __vmalloc() instead. */ void *vmalloc(unsigned long size) { |
230169693
|
1462 1463 |
return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, -1, __builtin_return_address(0)); |
1da177e4c
|
1464 |
} |
1da177e4c
|
1465 |
EXPORT_SYMBOL(vmalloc); |
930fc45a4
|
1466 |
/** |
ead04089b
|
1467 1468 |
* vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size |
833423143
|
1469 |
* |
ead04089b
|
1470 1471 |
* The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. |
833423143
|
1472 1473 1474 1475 1476 |
*/ void *vmalloc_user(unsigned long size) { struct vm_struct *area; void *ret; |
848778483
|
1477 1478 |
ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL, -1, __builtin_return_address(0)); |
2b4ac44e7
|
1479 |
if (ret) { |
db64fe022
|
1480 |
area = find_vm_area(ret); |
2b4ac44e7
|
1481 |
area->flags |= VM_USERMAP; |
2b4ac44e7
|
1482 |
} |
833423143
|
1483 1484 1485 1486 1487 |
return ret; } EXPORT_SYMBOL(vmalloc_user); /** |
930fc45a4
|
1488 |
* vmalloc_node - allocate memory on a specific node |
930fc45a4
|
1489 |
* @size: allocation size |
d44e0780b
|
1490 |
* @node: numa node |
930fc45a4
|
1491 1492 1493 1494 |
* * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * |
c1c8897f8
|
1495 |
* For tight control over page level allocator and protection flags |
930fc45a4
|
1496 1497 1498 1499 |
* use __vmalloc() instead. */ void *vmalloc_node(unsigned long size, int node) { |
230169693
|
1500 1501 |
return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node, __builtin_return_address(0)); |
930fc45a4
|
1502 1503 |
} EXPORT_SYMBOL(vmalloc_node); |
4dc3b16ba
|
1504 1505 1506 |
#ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif |
1da177e4c
|
1507 1508 |
/** * vmalloc_exec - allocate virtually contiguous, executable memory |
1da177e4c
|
1509 1510 1511 1512 1513 1514 |
* @size: allocation size * * Kernel-internal function to allocate enough pages to cover @size * the page level allocator and map them into contiguous and * executable kernel virtual space. * |
c1c8897f8
|
1515 |
* For tight control over page level allocator and protection flags |
1da177e4c
|
1516 1517 |
* use __vmalloc() instead. */ |
1da177e4c
|
1518 1519 |
void *vmalloc_exec(unsigned long size) { |
848778483
|
1520 1521 |
return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, -1, __builtin_return_address(0)); |
1da177e4c
|
1522 |
} |
0d08e0d3a
|
1523 |
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) |
7ac674f52
|
1524 |
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL |
0d08e0d3a
|
1525 |
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) |
7ac674f52
|
1526 |
#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL |
0d08e0d3a
|
1527 1528 1529 |
#else #define GFP_VMALLOC32 GFP_KERNEL #endif |
1da177e4c
|
1530 1531 |
/** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) |
1da177e4c
|
1532 1533 1534 1535 1536 1537 1538 |
* @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. */ void *vmalloc_32(unsigned long size) { |
848778483
|
1539 1540 |
return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL, -1, __builtin_return_address(0)); |
1da177e4c
|
1541 |
} |
1da177e4c
|
1542 |
EXPORT_SYMBOL(vmalloc_32); |
833423143
|
1543 |
/** |
ead04089b
|
1544 |
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory |
833423143
|
1545 |
* @size: allocation size |
ead04089b
|
1546 1547 1548 |
* * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. |
833423143
|
1549 1550 1551 1552 1553 |
*/ void *vmalloc_32_user(unsigned long size) { struct vm_struct *area; void *ret; |
848778483
|
1554 1555 |
ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, -1, __builtin_return_address(0)); |
2b4ac44e7
|
1556 |
if (ret) { |
db64fe022
|
1557 |
area = find_vm_area(ret); |
2b4ac44e7
|
1558 |
area->flags |= VM_USERMAP; |
2b4ac44e7
|
1559 |
} |
833423143
|
1560 1561 1562 |
return ret; } EXPORT_SYMBOL(vmalloc_32_user); |
1da177e4c
|
1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 |
long vread(char *buf, char *addr, unsigned long count) { struct vm_struct *tmp; char *vaddr, *buf_start = buf; unsigned long n; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; read_lock(&vmlist_lock); for (tmp = vmlist; tmp; tmp = tmp->next) { vaddr = (char *) tmp->addr; if (addr >= vaddr + tmp->size - PAGE_SIZE) continue; while (addr < vaddr) { if (count == 0) goto finished; *buf = '\0'; buf++; addr++; count--; } n = vaddr + tmp->size - PAGE_SIZE - addr; do { if (count == 0) goto finished; *buf = *addr; buf++; addr++; count--; } while (--n > 0); } finished: read_unlock(&vmlist_lock); return buf - buf_start; } long vwrite(char *buf, char *addr, unsigned long count) { struct vm_struct *tmp; char *vaddr, *buf_start = buf; unsigned long n; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; read_lock(&vmlist_lock); for (tmp = vmlist; tmp; tmp = tmp->next) { vaddr = (char *) tmp->addr; if (addr >= vaddr + tmp->size - PAGE_SIZE) continue; while (addr < vaddr) { if (count == 0) goto finished; buf++; addr++; count--; } n = vaddr + tmp->size - PAGE_SIZE - addr; do { if (count == 0) goto finished; *addr = *buf; buf++; addr++; count--; } while (--n > 0); } finished: read_unlock(&vmlist_lock); return buf - buf_start; } |
833423143
|
1637 1638 1639 |
/** * remap_vmalloc_range - map vmalloc pages to userspace |
833423143
|
1640 1641 1642 |
* @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map |
7682486b3
|
1643 1644 |
* * Returns: 0 for success, -Exxx on failure |
833423143
|
1645 1646 1647 1648 1649 |
* * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * |
72fd4a35a
|
1650 |
* Similar to remap_pfn_range() (see mm/memory.c) |
833423143
|
1651 1652 1653 1654 1655 1656 1657 |
*/ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { struct vm_struct *area; unsigned long uaddr = vma->vm_start; unsigned long usize = vma->vm_end - vma->vm_start; |
833423143
|
1658 1659 1660 |
if ((PAGE_SIZE-1) & (unsigned long)addr) return -EINVAL; |
db64fe022
|
1661 |
area = find_vm_area(addr); |
833423143
|
1662 |
if (!area) |
db64fe022
|
1663 |
return -EINVAL; |
833423143
|
1664 1665 |
if (!(area->flags & VM_USERMAP)) |
db64fe022
|
1666 |
return -EINVAL; |
833423143
|
1667 1668 |
if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE) |
db64fe022
|
1669 |
return -EINVAL; |
833423143
|
1670 1671 1672 1673 |
addr += pgoff << PAGE_SHIFT; do { struct page *page = vmalloc_to_page(addr); |
db64fe022
|
1674 |
int ret; |
833423143
|
1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 |
ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; addr += PAGE_SIZE; usize -= PAGE_SIZE; } while (usize > 0); /* Prevent "things" like memory migration? VM_flags need a cleanup... */ vma->vm_flags |= VM_RESERVED; |
db64fe022
|
1686 |
return 0; |
833423143
|
1687 1688 |
} EXPORT_SYMBOL(remap_vmalloc_range); |
1eeb66a1b
|
1689 1690 1691 1692 1693 1694 1695 |
/* * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. */ void __attribute__((weak)) vmalloc_sync_all(void) { } |
5f4352fbf
|
1696 |
|
2f569afd9
|
1697 |
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data) |
5f4352fbf
|
1698 1699 1700 1701 1702 1703 1704 1705 |
{ /* apply_to_page_range() does all the hard work. */ return 0; } /** * alloc_vm_area - allocate a range of kernel address space * @size: size of the area |
7682486b3
|
1706 1707 |
* * Returns: NULL on failure, vm_struct on success |
5f4352fbf
|
1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 |
* * This function reserves a range of kernel address space, and * allocates pagetables to map that range. No actual mappings * are created. If the kernel address space is not shared * between processes, it syncs the pagetable across all * processes. */ struct vm_struct *alloc_vm_area(size_t size) { struct vm_struct *area; |
230169693
|
1718 1719 |
area = get_vm_area_caller(size, VM_IOREMAP, __builtin_return_address(0)); |
5f4352fbf
|
1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 |
if (area == NULL) return NULL; /* * This ensures that page tables are constructed for this region * of kernel virtual address space and mapped into init_mm. */ if (apply_to_page_range(&init_mm, (unsigned long)area->addr, area->size, f, NULL)) { free_vm_area(area); return NULL; } /* Make sure the pagetables are constructed in process kernel mappings */ vmalloc_sync_all(); return area; } EXPORT_SYMBOL_GPL(alloc_vm_area); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); |
a10aa5798
|
1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 |
#ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) { loff_t n = *pos; struct vm_struct *v; read_lock(&vmlist_lock); v = vmlist; while (n > 0 && v) { n--; v = v->next; } if (!n) return v; return NULL; } static void *s_next(struct seq_file *m, void *p, loff_t *pos) { struct vm_struct *v = p; ++*pos; return v->next; } static void s_stop(struct seq_file *m, void *p) { read_unlock(&vmlist_lock); } |
a47a126ad
|
1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 |
static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (NUMA_BUILD) { unsigned int nr, *counters = m->private; if (!counters) return; memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr++) counters[page_to_nid(v->pages[nr])]++; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } } |
a10aa5798
|
1800 1801 1802 1803 1804 1805 |
static int s_show(struct seq_file *m, void *p) { struct vm_struct *v = p; seq_printf(m, "0x%p-0x%p %7ld", v->addr, v->addr + v->size, v->size); |
230169693
|
1806 |
if (v->caller) { |
9c2462472
|
1807 |
char buff[KSYM_SYMBOL_LEN]; |
230169693
|
1808 1809 1810 1811 1812 |
seq_putc(m, ' '); sprint_symbol(buff, (unsigned long)v->caller); seq_puts(m, buff); } |
a10aa5798
|
1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 |
if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%lx", v->phys_addr); if (v->flags & VM_IOREMAP) seq_printf(m, " ioremap"); if (v->flags & VM_ALLOC) seq_printf(m, " vmalloc"); if (v->flags & VM_MAP) seq_printf(m, " vmap"); if (v->flags & VM_USERMAP) seq_printf(m, " user"); if (v->flags & VM_VPAGES) seq_printf(m, " vpages"); |
a47a126ad
|
1833 |
show_numa_info(m, v); |
a10aa5798
|
1834 1835 1836 1837 |
seq_putc(m, ' '); return 0; } |
5f6a6a9c4
|
1838 |
static const struct seq_operations vmalloc_op = { |
a10aa5798
|
1839 1840 1841 1842 1843 |
.start = s_start, .next = s_next, .stop = s_stop, .show = s_show, }; |
5f6a6a9c4
|
1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 |
static int vmalloc_open(struct inode *inode, struct file *file) { unsigned int *ptr = NULL; int ret; if (NUMA_BUILD) ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); ret = seq_open(file, &vmalloc_op); if (!ret) { struct seq_file *m = file->private_data; m->private = ptr; } else kfree(ptr); return ret; } static const struct file_operations proc_vmalloc_operations = { .open = vmalloc_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; static int __init proc_vmalloc_init(void) { proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations); return 0; } module_init(proc_vmalloc_init); |
a10aa5798
|
1874 |
#endif |