vmalloc.c 22.8 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
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
Christoph Lameter's avatar
Christoph Lameter committed
8
 *  Numa awareness, Christoph Lameter, SGI, June 2005
Linus Torvalds's avatar
Linus Torvalds committed
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>
18
#include <linux/debugobjects.h>
Linus Torvalds's avatar
Linus Torvalds committed
19
#include <linux/vmalloc.h>
20
#include <linux/kallsyms.h>
Linus Torvalds's avatar
Linus Torvalds committed
21 22 23 24 25 26 27 28

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


DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;

29
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
30
			    int node, void *caller);
31

Linus Torvalds's avatar
Linus Torvalds committed
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
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);
}

73
void unmap_kernel_range(unsigned long addr, unsigned long size)
Linus Torvalds's avatar
Linus Torvalds committed
74 75 76
{
	pgd_t *pgd;
	unsigned long next;
77 78
	unsigned long start = addr;
	unsigned long end = addr + size;
Linus Torvalds's avatar
Linus Torvalds committed
79 80 81 82 83 84 85 86 87 88

	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);
89 90 91 92 93 94
	flush_tlb_kernel_range(start, end);
}

static void unmap_vm_area(struct vm_struct *area)
{
	unmap_kernel_range((unsigned long)area->addr, area->size);
Linus Torvalds's avatar
Linus Torvalds committed
95 96 97 98 99 100 101
}

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

102
	pte = pte_alloc_kernel(pmd, addr);
Linus Torvalds's avatar
Linus Torvalds committed
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
	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;
}
169
EXPORT_SYMBOL_GPL(map_vm_area);
Linus Torvalds's avatar
Linus Torvalds committed
170

171 172 173
/*
 * Map a vmalloc()-space virtual address to the physical page.
 */
174
struct page *vmalloc_to_page(const void *vmalloc_addr)
175 176 177 178 179 180 181 182
{
	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;

183 184 185 186
	/*
	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
	 * architectures that do not vmalloc module space
	 */
Jiri Slaby's avatar
Jiri Slaby committed
187 188 189
	VIRTUAL_BUG_ON(!is_vmalloc_addr(vmalloc_addr) &&
			!is_module_address(addr));

190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
	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.
 */
210
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
211 212 213 214 215
{
	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);

216 217 218
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)
Linus Torvalds's avatar
Linus Torvalds committed
219 220 221 222 223
{
	struct vm_struct **p, *tmp, *area;
	unsigned long align = 1;
	unsigned long addr;

224
	BUG_ON(in_interrupt());
Linus Torvalds's avatar
Linus Torvalds committed
225 226 227 228 229 230 231 232 233 234 235 236
	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);
237 238
	if (unlikely(!size))
		return NULL;
Linus Torvalds's avatar
Linus Torvalds committed
239

Christoph Lameter's avatar
Christoph Lameter committed
240 241
	area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);

Linus Torvalds's avatar
Linus Torvalds committed
242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265
	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;
	}
266 267 268 269
	if ((size + addr) < addr)
		goto out;
	if (addr > end - size)
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
270 271 272 273 274 275 276 277 278 279 280

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;
281
	area->caller = caller;
Linus Torvalds's avatar
Linus Torvalds committed
282 283 284 285 286 287 288 289 290 291 292 293
	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;
}

Christoph Lameter's avatar
Christoph Lameter committed
294 295 296
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
				unsigned long start, unsigned long end)
{
297 298
	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
						__builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
299
}
300
EXPORT_SYMBOL_GPL(__get_vm_area);
Christoph Lameter's avatar
Christoph Lameter committed
301

Linus Torvalds's avatar
Linus Torvalds committed
302
/**
Simon Arlott's avatar
Simon Arlott committed
303
 *	get_vm_area  -  reserve a contiguous kernel virtual area
Linus Torvalds's avatar
Linus Torvalds committed
304 305 306 307 308 309 310 311 312
 *	@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)
{
313 314 315 316 317 318 319 320 321
	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);
Linus Torvalds's avatar
Linus Torvalds committed
322 323
}

324 325
struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
				   int node, gfp_t gfp_mask)
Christoph Lameter's avatar
Christoph Lameter committed
326
{
327
	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
328
				  gfp_mask, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
329 330
}

331
/* Caller must hold vmlist_lock */
332
static struct vm_struct *__find_vm_area(const void *addr)
333 334 335 336 337 338 339 340 341 342 343
{
	struct vm_struct *tmp;

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

	return tmp;
}

344
/* Caller must hold vmlist_lock */
345
static struct vm_struct *__remove_vm_area(const void *addr)
Linus Torvalds's avatar
Linus Torvalds committed
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
{
	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;
}

366
/**
Simon Arlott's avatar
Simon Arlott committed
367
 *	remove_vm_area  -  find and remove a continuous kernel virtual area
368 369 370 371 372 373
 *	@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.
 */
374
struct vm_struct *remove_vm_area(const void *addr)
375 376 377 378 379 380 381 382
{
	struct vm_struct *v;
	write_lock(&vmlist_lock);
	v = __remove_vm_area(addr);
	write_unlock(&vmlist_lock);
	return v;
}

383
static void __vunmap(const void *addr, int deallocate_pages)
Linus Torvalds's avatar
Linus Torvalds committed
384 385 386 387 388 389 390
{
	struct vm_struct *area;

	if (!addr)
		return;

	if ((PAGE_SIZE-1) & (unsigned long)addr) {
Arjan van de Ven's avatar
Arjan van de Ven committed
391
		WARN(1, KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
Linus Torvalds's avatar
Linus Torvalds committed
392 393 394 395 396
		return;
	}

	area = remove_vm_area(addr);
	if (unlikely(!area)) {
Arjan van de Ven's avatar
Arjan van de Ven committed
397
		WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
Linus Torvalds's avatar
Linus Torvalds committed
398 399 400 401
				addr);
		return;
	}

402
	debug_check_no_locks_freed(addr, area->size);
403
	debug_check_no_obj_freed(addr, area->size);
404

Linus Torvalds's avatar
Linus Torvalds committed
405 406 407 408
	if (deallocate_pages) {
		int i;

		for (i = 0; i < area->nr_pages; i++) {
409 410 411 412
			struct page *page = area->pages[i];

			BUG_ON(!page);
			__free_page(page);
Linus Torvalds's avatar
Linus Torvalds committed
413 414
		}

415
		if (area->flags & VM_VPAGES)
Linus Torvalds's avatar
Linus Torvalds committed
416 417 418 419 420 421 422 423 424 425 426 427 428
			vfree(area->pages);
		else
			kfree(area->pages);
	}

	kfree(area);
	return;
}

/**
 *	vfree  -  release memory allocated by vmalloc()
 *	@addr:		memory base address
 *
Simon Arlott's avatar
Simon Arlott committed
429
 *	Free the virtually continuous memory area starting at @addr, as
430 431
 *	obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
 *	NULL, no operation is performed.
Linus Torvalds's avatar
Linus Torvalds committed
432
 *
433
 *	Must not be called in interrupt context.
Linus Torvalds's avatar
Linus Torvalds committed
434
 */
435
void vfree(const void *addr)
Linus Torvalds's avatar
Linus Torvalds committed
436 437 438 439 440 441 442 443 444 445 446 447 448
{
	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().
 *
449
 *	Must not be called in interrupt context.
Linus Torvalds's avatar
Linus Torvalds committed
450
 */
451
void vunmap(const void *addr)
Linus Torvalds's avatar
Linus Torvalds committed
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475
{
	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;

476 477
	area = get_vm_area_caller((count << PAGE_SHIFT), flags,
					__builtin_return_address(0));
Linus Torvalds's avatar
Linus Torvalds committed
478 479
	if (!area)
		return NULL;
480

Linus Torvalds's avatar
Linus Torvalds committed
481 482 483 484 485 486 487 488 489
	if (map_vm_area(area, prot, &pages)) {
		vunmap(area->addr);
		return NULL;
	}

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

490
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
491
				 pgprot_t prot, int node, void *caller)
Linus Torvalds's avatar
Linus Torvalds committed
492 493 494 495 496 497 498 499 500
{
	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. */
501
	if (array_size > PAGE_SIZE) {
502
		pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
503
				PAGE_KERNEL, node, caller);
504
		area->flags |= VM_VPAGES;
505 506
	} else {
		pages = kmalloc_node(array_size,
Christoph Lameter's avatar
Christoph Lameter committed
507
				(gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO,
508 509
				node);
	}
Linus Torvalds's avatar
Linus Torvalds committed
510
	area->pages = pages;
511
	area->caller = caller;
Linus Torvalds's avatar
Linus Torvalds committed
512 513 514 515 516 517 518
	if (!area->pages) {
		remove_vm_area(area->addr);
		kfree(area);
		return NULL;
	}

	for (i = 0; i < area->nr_pages; i++) {
519 520
		struct page *page;

Christoph Lameter's avatar
Christoph Lameter committed
521
		if (node < 0)
522
			page = alloc_page(gfp_mask);
Christoph Lameter's avatar
Christoph Lameter committed
523
		else
524 525 526
			page = alloc_pages_node(node, gfp_mask, 0);

		if (unlikely(!page)) {
Linus Torvalds's avatar
Linus Torvalds committed
527 528 529 530
			/* Successfully allocated i pages, free them in __vunmap() */
			area->nr_pages = i;
			goto fail;
		}
531
		area->pages[i] = page;
Linus Torvalds's avatar
Linus Torvalds committed
532 533 534 535 536 537 538 539 540 541 542
	}

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

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

Christoph Lameter's avatar
Christoph Lameter committed
543 544
void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
{
545 546
	return __vmalloc_area_node(area, gfp_mask, prot, -1,
					__builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
547 548
}

Linus Torvalds's avatar
Linus Torvalds committed
549
/**
Christoph Lameter's avatar
Christoph Lameter committed
550
 *	__vmalloc_node  -  allocate virtually contiguous memory
Linus Torvalds's avatar
Linus Torvalds committed
551 552 553
 *	@size:		allocation size
 *	@gfp_mask:	flags for the page level allocator
 *	@prot:		protection mask for the allocated pages
554
 *	@node:		node to use for allocation or -1
555
 *	@caller:	caller's return address
Linus Torvalds's avatar
Linus Torvalds committed
556 557 558 559 560
 *
 *	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.
 */
561
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
562
						int node, void *caller)
Linus Torvalds's avatar
Linus Torvalds committed
563 564 565 566 567 568 569
{
	struct vm_struct *area;

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

570 571 572
	area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END,
						node, gfp_mask, caller);

Linus Torvalds's avatar
Linus Torvalds committed
573 574 575
	if (!area)
		return NULL;

576
	return __vmalloc_area_node(area, gfp_mask, prot, node, caller);
Linus Torvalds's avatar
Linus Torvalds committed
577 578
}

Christoph Lameter's avatar
Christoph Lameter committed
579 580
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
581 582
	return __vmalloc_node(size, gfp_mask, prot, -1,
				__builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
583
}
Linus Torvalds's avatar
Linus Torvalds committed
584 585 586 587 588 589 590 591
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.
 *
592
 *	For tight control over page level allocator and protection flags
Linus Torvalds's avatar
Linus Torvalds committed
593 594 595 596
 *	use __vmalloc() instead.
 */
void *vmalloc(unsigned long size)
{
597 598
	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
					-1, __builtin_return_address(0));
Linus Torvalds's avatar
Linus Torvalds committed
599 600 601
}
EXPORT_SYMBOL(vmalloc);

602
/**
603 604
 * vmalloc_user - allocate zeroed virtually contiguous memory for userspace
 * @size: allocation size
605
 *
606 607
 * The resulting memory area is zeroed so it can be mapped to userspace
 * without leaking data.
608 609 610 611 612 613 614
 */
void *vmalloc_user(unsigned long size)
{
	struct vm_struct *area;
	void *ret;

	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
615 616 617 618 619 620
	if (ret) {
		write_lock(&vmlist_lock);
		area = __find_vm_area(ret);
		area->flags |= VM_USERMAP;
		write_unlock(&vmlist_lock);
	}
621 622 623 624
	return ret;
}
EXPORT_SYMBOL(vmalloc_user);

Christoph Lameter's avatar
Christoph Lameter committed
625 626 627
/**
 *	vmalloc_node  -  allocate memory on a specific node
 *	@size:		allocation size
628
 *	@node:		numa node
Christoph Lameter's avatar
Christoph Lameter committed
629 630 631 632
 *
 *	Allocate enough pages to cover @size from the page level
 *	allocator and map them into contiguous kernel virtual space.
 *
633
 *	For tight control over page level allocator and protection flags
Christoph Lameter's avatar
Christoph Lameter committed
634 635 636 637
 *	use __vmalloc() instead.
 */
void *vmalloc_node(unsigned long size, int node)
{
638 639
	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
					node, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
640 641 642
}
EXPORT_SYMBOL(vmalloc_node);

643 644 645 646
#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif

Linus Torvalds's avatar
Linus Torvalds committed
647 648 649 650 651 652 653 654
/**
 *	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.
 *
655
 *	For tight control over page level allocator and protection flags
Linus Torvalds's avatar
Linus Torvalds committed
656 657 658 659 660 661 662 663
 *	use __vmalloc() instead.
 */

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

664
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
665
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
666
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
667
#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL
668 669 670 671
#else
#define GFP_VMALLOC32 GFP_KERNEL
#endif

Linus Torvalds's avatar
Linus Torvalds committed
672 673 674 675 676 677 678 679 680
/**
 *	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)
{
681
	return __vmalloc(size, GFP_VMALLOC32, PAGE_KERNEL);
Linus Torvalds's avatar
Linus Torvalds committed
682 683 684
}
EXPORT_SYMBOL(vmalloc_32);

685
/**
686
 * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
687
 *	@size:		allocation size
688 689 690
 *
 * The resulting memory area is 32bit addressable and zeroed so it can be
 * mapped to userspace without leaking data.
691 692 693 694 695 696
 */
void *vmalloc_32_user(unsigned long size)
{
	struct vm_struct *area;
	void *ret;

697
	ret = __vmalloc(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL);
698 699 700 701 702 703
	if (ret) {
		write_lock(&vmlist_lock);
		area = __find_vm_area(ret);
		area->flags |= VM_USERMAP;
		write_unlock(&vmlist_lock);
	}
704 705 706 707
	return ret;
}
EXPORT_SYMBOL(vmalloc_32_user);

Linus Torvalds's avatar
Linus Torvalds committed
708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781
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;
}
782 783 784 785 786 787

/**
 *	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
788 789
 *
 *	Returns:	0 for success, -Exxx on failure
790 791 792 793 794
 *
 *	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.
 *
795
 *	Similar to remap_pfn_range() (see mm/memory.c)
796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842
 */
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);

843 844 845 846 847 848 849
/*
 * Implement a stub for vmalloc_sync_all() if the architecture chose not to
 * have one.
 */
void  __attribute__((weak)) vmalloc_sync_all(void)
{
}
850 851


852
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
853 854 855 856 857 858 859 860
{
	/* 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
861 862
 *
 *	Returns:	NULL on failure, vm_struct on success
863 864 865 866 867 868 869 870 871 872 873
 *
 *	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;

874 875
	area = get_vm_area_caller(size, VM_IOREMAP,
				__builtin_return_address(0));
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
	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);
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


#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);
}

939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957
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]);
	}
}

958 959 960 961 962 963 964
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);

965 966 967 968 969 970 971 972
	if (v->caller) {
		char buff[2 * KSYM_NAME_LEN];

		seq_putc(m, ' ');
		sprint_symbol(buff, (unsigned long)v->caller);
		seq_puts(m, buff);
	}

973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
	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");

994
	show_numa_info(m, v);
995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006
	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