vmalloc.c 21.2 KB
Newer Older
L
Linus Torvalds 已提交
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
C
Christoph Lameter 已提交
8
 *  Numa awareness, Christoph Lameter, SGI, June 2005
L
Linus Torvalds 已提交
9 10 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>
17
#include <linux/seq_file.h>
L
Linus Torvalds 已提交
18 19 20 21 22 23 24 25 26
#include <linux/vmalloc.h>

#include <asm/uaccess.h>
#include <asm/tlbflush.h>


DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;

A
Adrian Bunk 已提交
27 28 29
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
			    int node);

L
Linus Torvalds 已提交
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70
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);
}

static inline void vunmap_pmd_range(pud_t *pud, unsigned long addr,
						unsigned long end)
{
	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);
}

static inline void vunmap_pud_range(pgd_t *pgd, unsigned long addr,
						unsigned long end)
{
	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);
}

71
void unmap_kernel_range(unsigned long addr, unsigned long size)
L
Linus Torvalds 已提交
72 73 74
{
	pgd_t *pgd;
	unsigned long next;
75 76
	unsigned long start = addr;
	unsigned long end = addr + size;
L
Linus Torvalds 已提交
77 78 79 80 81 82 83 84 85 86

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	flush_cache_vunmap(addr, end);
	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);
87 88 89 90 91 92
	flush_tlb_kernel_range(start, end);
}

static void unmap_vm_area(struct vm_struct *area)
{
	unmap_kernel_range((unsigned long)area->addr, area->size);
L
Linus Torvalds 已提交
93 94 95 96 97 98 99
}

static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
			unsigned long end, pgprot_t prot, struct page ***pages)
{
	pte_t *pte;

H
Hugh Dickins 已提交
100
	pte = pte_alloc_kernel(pmd, addr);
L
Linus Torvalds 已提交
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166
	if (!pte)
		return -ENOMEM;
	do {
		struct page *page = **pages;
		WARN_ON(!pte_none(*pte));
		if (!page)
			return -ENOMEM;
		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
		(*pages)++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	return 0;
}

static inline int vmap_pmd_range(pud_t *pud, unsigned long addr,
			unsigned long end, pgprot_t prot, struct page ***pages)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_alloc(&init_mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (vmap_pte_range(pmd, addr, next, prot, pages))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int vmap_pud_range(pgd_t *pgd, unsigned long addr,
			unsigned long end, pgprot_t prot, struct page ***pages)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_alloc(&init_mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (vmap_pmd_range(pud, addr, next, prot, pages))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long addr = (unsigned long) area->addr;
	unsigned long end = addr + area->size - PAGE_SIZE;
	int err;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = vmap_pud_range(pgd, addr, next, prot, pages);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);
	flush_cache_vmap((unsigned long) area->addr, end);
	return err;
}
167
EXPORT_SYMBOL_GPL(map_vm_area);
L
Linus Torvalds 已提交
168

169 170 171
/*
 * Map a vmalloc()-space virtual address to the physical page.
 */
172
struct page *vmalloc_to_page(const void *vmalloc_addr)
173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
{
	unsigned long addr = (unsigned long) vmalloc_addr;
	struct page *page = NULL;
	pgd_t *pgd = pgd_offset_k(addr);
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;

	if (!pgd_none(*pgd)) {
		pud = pud_offset(pgd, addr);
		if (!pud_none(*pud)) {
			pmd = pmd_offset(pud, addr);
			if (!pmd_none(*pmd)) {
				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.
 */
201
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
202 203 204 205 206
{
	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);

207 208 209
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)
L
Linus Torvalds 已提交
210 211 212 213 214
{
	struct vm_struct **p, *tmp, *area;
	unsigned long align = 1;
	unsigned long addr;

215
	BUG_ON(in_interrupt());
L
Linus Torvalds 已提交
216 217 218 219 220 221 222 223 224 225 226 227
	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;
	}
	addr = ALIGN(start, align);
	size = PAGE_ALIGN(size);
228 229
	if (unlikely(!size))
		return NULL;
L
Linus Torvalds 已提交
230

C
Christoph Lameter 已提交
231 232
	area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);

L
Linus Torvalds 已提交
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
	if (unlikely(!area))
		return NULL;

	/*
	 * We always allocate a guard page.
	 */
	size += PAGE_SIZE;

	write_lock(&vmlist_lock);
	for (p = &vmlist; (tmp = *p) != NULL ;p = &tmp->next) {
		if ((unsigned long)tmp->addr < addr) {
			if((unsigned long)tmp->addr + tmp->size >= addr)
				addr = ALIGN(tmp->size + 
					     (unsigned long)tmp->addr, align);
			continue;
		}
		if ((size + addr) < addr)
			goto out;
		if (size + addr <= (unsigned long)tmp->addr)
			goto found;
		addr = ALIGN(tmp->size + (unsigned long)tmp->addr, align);
		if (addr > end - size)
			goto out;
	}
257 258 259 260
	if ((size + addr) < addr)
		goto out;
	if (addr > end - size)
		goto out;
L
Linus Torvalds 已提交
261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283

found:
	area->next = *p;
	*p = area;

	area->flags = flags;
	area->addr = (void *)addr;
	area->size = size;
	area->pages = NULL;
	area->nr_pages = 0;
	area->phys_addr = 0;
	write_unlock(&vmlist_lock);

	return area;

out:
	write_unlock(&vmlist_lock);
	kfree(area);
	if (printk_ratelimit())
		printk(KERN_WARNING "allocation failed: out of vmalloc space - use vmalloc=<size> to increase size.\n");
	return NULL;
}

C
Christoph Lameter 已提交
284 285 286
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
				unsigned long start, unsigned long end)
{
287
	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL);
C
Christoph Lameter 已提交
288
}
289
EXPORT_SYMBOL_GPL(__get_vm_area);
C
Christoph Lameter 已提交
290

L
Linus Torvalds 已提交
291
/**
S
Simon Arlott 已提交
292
 *	get_vm_area  -  reserve a contiguous kernel virtual area
L
Linus Torvalds 已提交
293 294 295 296 297 298 299 300 301 302 303 304
 *	@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)
{
	return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END);
}

305 306
struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
				   int node, gfp_t gfp_mask)
C
Christoph Lameter 已提交
307
{
308 309
	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
				  gfp_mask);
C
Christoph Lameter 已提交
310 311
}

312
/* Caller must hold vmlist_lock */
313
static struct vm_struct *__find_vm_area(const void *addr)
314 315 316 317 318 319 320 321 322 323 324
{
	struct vm_struct *tmp;

	for (tmp = vmlist; tmp != NULL; tmp = tmp->next) {
		 if (tmp->addr == addr)
			break;
	}

	return tmp;
}

325
/* Caller must hold vmlist_lock */
326
static struct vm_struct *__remove_vm_area(const void *addr)
L
Linus Torvalds 已提交
327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346
{
	struct vm_struct **p, *tmp;

	for (p = &vmlist ; (tmp = *p) != NULL ;p = &tmp->next) {
		 if (tmp->addr == addr)
			 goto found;
	}
	return NULL;

found:
	unmap_vm_area(tmp);
	*p = tmp->next;

	/*
	 * Remove the guard page.
	 */
	tmp->size -= PAGE_SIZE;
	return tmp;
}

347
/**
S
Simon Arlott 已提交
348
 *	remove_vm_area  -  find and remove a continuous kernel virtual area
349 350 351 352 353 354
 *	@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.
 */
355
struct vm_struct *remove_vm_area(const void *addr)
356 357 358 359 360 361 362 363
{
	struct vm_struct *v;
	write_lock(&vmlist_lock);
	v = __remove_vm_area(addr);
	write_unlock(&vmlist_lock);
	return v;
}

364
static void __vunmap(const void *addr, int deallocate_pages)
L
Linus Torvalds 已提交
365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384
{
	struct vm_struct *area;

	if (!addr)
		return;

	if ((PAGE_SIZE-1) & (unsigned long)addr) {
		printk(KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
		WARN_ON(1);
		return;
	}

	area = remove_vm_area(addr);
	if (unlikely(!area)) {
		printk(KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
				addr);
		WARN_ON(1);
		return;
	}

385 386
	debug_check_no_locks_freed(addr, area->size);

L
Linus Torvalds 已提交
387 388 389 390
	if (deallocate_pages) {
		int i;

		for (i = 0; i < area->nr_pages; i++) {
391 392 393 394
			struct page *page = area->pages[i];

			BUG_ON(!page);
			__free_page(page);
L
Linus Torvalds 已提交
395 396
		}

397
		if (area->flags & VM_VPAGES)
L
Linus Torvalds 已提交
398 399 400 401 402 403 404 405 406 407 408 409 410
			vfree(area->pages);
		else
			kfree(area->pages);
	}

	kfree(area);
	return;
}

/**
 *	vfree  -  release memory allocated by vmalloc()
 *	@addr:		memory base address
 *
S
Simon Arlott 已提交
411
 *	Free the virtually continuous memory area starting at @addr, as
412 413
 *	obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
 *	NULL, no operation is performed.
L
Linus Torvalds 已提交
414
 *
415
 *	Must not be called in interrupt context.
L
Linus Torvalds 已提交
416
 */
417
void vfree(const void *addr)
L
Linus Torvalds 已提交
418 419 420 421 422 423 424 425 426 427 428 429 430
{
	BUG_ON(in_interrupt());
	__vunmap(addr, 1);
}
EXPORT_SYMBOL(vfree);

/**
 *	vunmap  -  release virtual mapping obtained by vmap()
 *	@addr:		memory base address
 *
 *	Free the virtually contiguous memory area starting at @addr,
 *	which was created from the page array passed to vmap().
 *
431
 *	Must not be called in interrupt context.
L
Linus Torvalds 已提交
432
 */
433
void vunmap(const void *addr)
L
Linus Torvalds 已提交
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469
{
	BUG_ON(in_interrupt());
	__vunmap(addr, 0);
}
EXPORT_SYMBOL(vunmap);

/**
 *	vmap  -  map an array of pages into virtually contiguous space
 *	@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;

	if (count > num_physpages)
		return NULL;

	area = get_vm_area((count << PAGE_SHIFT), flags);
	if (!area)
		return NULL;
	if (map_vm_area(area, prot, &pages)) {
		vunmap(area->addr);
		return NULL;
	}

	return area->addr;
}
EXPORT_SYMBOL(vmap);

A
Adrian Bunk 已提交
470 471
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
				 pgprot_t prot, int node)
L
Linus Torvalds 已提交
472 473 474 475 476 477 478 479 480
{
	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. */
481
	if (array_size > PAGE_SIZE) {
482 483
		pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
					PAGE_KERNEL, node);
484
		area->flags |= VM_VPAGES;
485 486
	} else {
		pages = kmalloc_node(array_size,
C
Christoph Lameter 已提交
487
				(gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO,
488 489
				node);
	}
L
Linus Torvalds 已提交
490 491 492 493 494 495 496 497
	area->pages = pages;
	if (!area->pages) {
		remove_vm_area(area->addr);
		kfree(area);
		return NULL;
	}

	for (i = 0; i < area->nr_pages; i++) {
498 499
		struct page *page;

C
Christoph Lameter 已提交
500
		if (node < 0)
501
			page = alloc_page(gfp_mask);
C
Christoph Lameter 已提交
502
		else
503 504 505
			page = alloc_pages_node(node, gfp_mask, 0);

		if (unlikely(!page)) {
L
Linus Torvalds 已提交
506 507 508 509
			/* Successfully allocated i pages, free them in __vunmap() */
			area->nr_pages = i;
			goto fail;
		}
510
		area->pages[i] = page;
L
Linus Torvalds 已提交
511 512 513 514 515 516 517 518 519 520 521
	}

	if (map_vm_area(area, prot, &pages))
		goto fail;
	return area->addr;

fail:
	vfree(area->addr);
	return NULL;
}

C
Christoph Lameter 已提交
522 523 524 525 526
void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
{
	return __vmalloc_area_node(area, gfp_mask, prot, -1);
}

L
Linus Torvalds 已提交
527
/**
C
Christoph Lameter 已提交
528
 *	__vmalloc_node  -  allocate virtually contiguous memory
L
Linus Torvalds 已提交
529 530 531
 *	@size:		allocation size
 *	@gfp_mask:	flags for the page level allocator
 *	@prot:		protection mask for the allocated pages
532
 *	@node:		node to use for allocation or -1
L
Linus Torvalds 已提交
533 534 535 536 537
 *
 *	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.
 */
A
Adrian Bunk 已提交
538 539
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
			    int node)
L
Linus Torvalds 已提交
540 541 542 543 544 545 546
{
	struct vm_struct *area;

	size = PAGE_ALIGN(size);
	if (!size || (size >> PAGE_SHIFT) > num_physpages)
		return NULL;

547
	area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask);
L
Linus Torvalds 已提交
548 549 550
	if (!area)
		return NULL;

C
Christoph Lameter 已提交
551
	return __vmalloc_area_node(area, gfp_mask, prot, node);
L
Linus Torvalds 已提交
552 553
}

C
Christoph Lameter 已提交
554 555 556 557
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
	return __vmalloc_node(size, gfp_mask, prot, -1);
}
L
Linus Torvalds 已提交
558 559 560 561 562 563 564 565
EXPORT_SYMBOL(__vmalloc);

/**
 *	vmalloc  -  allocate virtually contiguous memory
 *	@size:		allocation size
 *	Allocate enough pages to cover @size from the page level
 *	allocator and map them into contiguous kernel virtual space.
 *
566
 *	For tight control over page level allocator and protection flags
L
Linus Torvalds 已提交
567 568 569 570
 *	use __vmalloc() instead.
 */
void *vmalloc(unsigned long size)
{
571
	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
L
Linus Torvalds 已提交
572 573 574
}
EXPORT_SYMBOL(vmalloc);

575
/**
576 577
 * vmalloc_user - allocate zeroed virtually contiguous memory for userspace
 * @size: allocation size
578
 *
579 580
 * The resulting memory area is zeroed so it can be mapped to userspace
 * without leaking data.
581 582 583 584 585 586 587
 */
void *vmalloc_user(unsigned long size)
{
	struct vm_struct *area;
	void *ret;

	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
588 589 590 591 592 593
	if (ret) {
		write_lock(&vmlist_lock);
		area = __find_vm_area(ret);
		area->flags |= VM_USERMAP;
		write_unlock(&vmlist_lock);
	}
594 595 596 597
	return ret;
}
EXPORT_SYMBOL(vmalloc_user);

C
Christoph Lameter 已提交
598 599 600
/**
 *	vmalloc_node  -  allocate memory on a specific node
 *	@size:		allocation size
601
 *	@node:		numa node
C
Christoph Lameter 已提交
602 603 604 605
 *
 *	Allocate enough pages to cover @size from the page level
 *	allocator and map them into contiguous kernel virtual space.
 *
606
 *	For tight control over page level allocator and protection flags
C
Christoph Lameter 已提交
607 608 609 610
 *	use __vmalloc() instead.
 */
void *vmalloc_node(unsigned long size, int node)
{
611
	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node);
C
Christoph Lameter 已提交
612 613 614
}
EXPORT_SYMBOL(vmalloc_node);

615 616 617 618
#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif

L
Linus Torvalds 已提交
619 620 621 622 623 624 625 626
/**
 *	vmalloc_exec  -  allocate virtually contiguous, executable memory
 *	@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.
 *
627
 *	For tight control over page level allocator and protection flags
L
Linus Torvalds 已提交
628 629 630 631 632 633 634 635
 *	use __vmalloc() instead.
 */

void *vmalloc_exec(unsigned long size)
{
	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
}

636
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
637
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
638
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
639
#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL
640 641 642 643
#else
#define GFP_VMALLOC32 GFP_KERNEL
#endif

L
Linus Torvalds 已提交
644 645 646 647 648 649 650 651 652
/**
 *	vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
 *	@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)
{
653
	return __vmalloc(size, GFP_VMALLOC32, PAGE_KERNEL);
L
Linus Torvalds 已提交
654 655 656
}
EXPORT_SYMBOL(vmalloc_32);

657
/**
658
 * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
659
 *	@size:		allocation size
660 661 662
 *
 * The resulting memory area is 32bit addressable and zeroed so it can be
 * mapped to userspace without leaking data.
663 664 665 666 667 668
 */
void *vmalloc_32_user(unsigned long size)
{
	struct vm_struct *area;
	void *ret;

669
	ret = __vmalloc(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL);
670 671 672 673 674 675
	if (ret) {
		write_lock(&vmlist_lock);
		area = __find_vm_area(ret);
		area->flags |= VM_USERMAP;
		write_unlock(&vmlist_lock);
	}
676 677 678 679
	return ret;
}
EXPORT_SYMBOL(vmalloc_32_user);

L
Linus Torvalds 已提交
680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753
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;
}
754 755 756 757 758 759

/**
 *	remap_vmalloc_range  -  map vmalloc pages to userspace
 *	@vma:		vma to cover (map full range of vma)
 *	@addr:		vmalloc memory
 *	@pgoff:		number of pages into addr before first page to map
760 761
 *
 *	Returns:	0 for success, -Exxx on failure
762 763 764 765 766
 *
 *	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.
 *
767
 *	Similar to remap_pfn_range() (see mm/memory.c)
768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814
 */
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;
	int ret;

	if ((PAGE_SIZE-1) & (unsigned long)addr)
		return -EINVAL;

	read_lock(&vmlist_lock);
	area = __find_vm_area(addr);
	if (!area)
		goto out_einval_locked;

	if (!(area->flags & VM_USERMAP))
		goto out_einval_locked;

	if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE)
		goto out_einval_locked;
	read_unlock(&vmlist_lock);

	addr += pgoff << PAGE_SHIFT;
	do {
		struct page *page = vmalloc_to_page(addr);
		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;

	return ret;

out_einval_locked:
	read_unlock(&vmlist_lock);
	return -EINVAL;
}
EXPORT_SYMBOL(remap_vmalloc_range);

815 816 817 818 819 820 821
/*
 * Implement a stub for vmalloc_sync_all() if the architecture chose not to
 * have one.
 */
void  __attribute__((weak)) vmalloc_sync_all(void)
{
}
822 823


824
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
825 826 827 828 829 830 831 832
{
	/* 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
833 834
 *
 *	Returns:	NULL on failure, vm_struct on success
835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875
 *
 *	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;

	area = get_vm_area(size, VM_IOREMAP);
	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);
876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949


#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);
}

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);

	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");

	seq_putc(m, '\n');
	return 0;
}

const struct seq_operations vmalloc_op = {
	.start = s_start,
	.next = s_next,
	.stop = s_stop,
	.show = s_show,
};
#endif