swapfile.c 42.3 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33
/*
 *  linux/mm/swapfile.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 */

#include <linux/config.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shm.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/syscalls.h>

#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>

34
DEFINE_SPINLOCK(swap_lock);
L
Linus Torvalds 已提交
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
unsigned int nr_swapfiles;
long total_swap_pages;
static int swap_overflow;

static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";

struct swap_list_t swap_list = {-1, -1};

struct swap_info_struct swap_info[MAX_SWAPFILES];

static DECLARE_MUTEX(swapon_sem);

/*
 * We need this because the bdev->unplug_fn can sleep and we cannot
52
 * hold swap_lock while calling the unplug_fn. And swap_lock
L
Linus Torvalds 已提交
53 54 55 56 57 58 59 60 61
 * cannot be turned into a semaphore.
 */
static DECLARE_RWSEM(swap_unplug_sem);

void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
{
	swp_entry_t entry;

	down_read(&swap_unplug_sem);
H
Hugh Dickins 已提交
62
	entry.val = page_private(page);
L
Linus Torvalds 已提交
63 64 65 66 67 68 69
	if (PageSwapCache(page)) {
		struct block_device *bdev = swap_info[swp_type(entry)].bdev;
		struct backing_dev_info *bdi;

		/*
		 * If the page is removed from swapcache from under us (with a
		 * racy try_to_unuse/swapoff) we need an additional reference
H
Hugh Dickins 已提交
70 71
		 * count to avoid reading garbage from page_private(page) above.
		 * If the WARN_ON triggers during a swapoff it maybe the race
L
Linus Torvalds 已提交
72 73 74 75 76 77
		 * condition and it's harmless. However if it triggers without
		 * swapoff it signals a problem.
		 */
		WARN_ON(page_count(page) <= 1);

		bdi = bdev->bd_inode->i_mapping->backing_dev_info;
M
McMullan, Jason 已提交
78
		blk_run_backing_dev(bdi, page);
L
Linus Torvalds 已提交
79 80 81 82
	}
	up_read(&swap_unplug_sem);
}

83 84 85
#define SWAPFILE_CLUSTER	256
#define LATENCY_LIMIT		256

86
static inline unsigned long scan_swap_map(struct swap_info_struct *si)
L
Linus Torvalds 已提交
87
{
88
	unsigned long offset, last_in_cluster;
89
	int latency_ration = LATENCY_LIMIT;
90

L
Linus Torvalds 已提交
91
	/* 
92 93 94 95 96 97 98 99 100
	 * We try to cluster swap pages by allocating them sequentially
	 * in swap.  Once we've allocated SWAPFILE_CLUSTER pages this
	 * way, however, we resort to first-free allocation, starting
	 * a new cluster.  This prevents us from scattering swap pages
	 * all over the entire swap partition, so that we reduce
	 * overall disk seek times between swap pages.  -- sct
	 * But we do now try to find an empty cluster.  -Andrea
	 */

101
	si->flags += SWP_SCANNING;
102 103 104 105
	if (unlikely(!si->cluster_nr)) {
		si->cluster_nr = SWAPFILE_CLUSTER - 1;
		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER)
			goto lowest;
106
		spin_unlock(&swap_lock);
107 108 109 110 111 112

		offset = si->lowest_bit;
		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;

		/* Locate the first empty (unaligned) cluster */
		for (; last_in_cluster <= si->highest_bit; offset++) {
L
Linus Torvalds 已提交
113
			if (si->swap_map[offset])
114 115
				last_in_cluster = offset + SWAPFILE_CLUSTER;
			else if (offset == last_in_cluster) {
116
				spin_lock(&swap_lock);
117 118
				si->cluster_next = offset-SWAPFILE_CLUSTER-1;
				goto cluster;
L
Linus Torvalds 已提交
119
			}
120 121 122 123
			if (unlikely(--latency_ration < 0)) {
				cond_resched();
				latency_ration = LATENCY_LIMIT;
			}
124
		}
125
		spin_lock(&swap_lock);
126
		goto lowest;
L
Linus Torvalds 已提交
127
	}
128 129 130 131 132 133

	si->cluster_nr--;
cluster:
	offset = si->cluster_next;
	if (offset > si->highest_bit)
lowest:		offset = si->lowest_bit;
134 135
checks:	if (!(si->flags & SWP_WRITEOK))
		goto no_page;
136 137 138
	if (!si->highest_bit)
		goto no_page;
	if (!si->swap_map[offset]) {
139
		if (offset == si->lowest_bit)
L
Linus Torvalds 已提交
140 141 142
			si->lowest_bit++;
		if (offset == si->highest_bit)
			si->highest_bit--;
143 144
		si->inuse_pages++;
		if (si->inuse_pages == si->pages) {
L
Linus Torvalds 已提交
145 146 147 148
			si->lowest_bit = si->max;
			si->highest_bit = 0;
		}
		si->swap_map[offset] = 1;
149
		si->cluster_next = offset + 1;
150
		si->flags -= SWP_SCANNING;
L
Linus Torvalds 已提交
151 152
		return offset;
	}
153

154
	spin_unlock(&swap_lock);
155
	while (++offset <= si->highest_bit) {
156
		if (!si->swap_map[offset]) {
157
			spin_lock(&swap_lock);
158 159
			goto checks;
		}
160 161 162 163
		if (unlikely(--latency_ration < 0)) {
			cond_resched();
			latency_ration = LATENCY_LIMIT;
		}
164
	}
165
	spin_lock(&swap_lock);
166 167 168
	goto lowest;

no_page:
169
	si->flags -= SWP_SCANNING;
L
Linus Torvalds 已提交
170 171 172 173 174
	return 0;
}

swp_entry_t get_swap_page(void)
{
175 176 177 178
	struct swap_info_struct *si;
	pgoff_t offset;
	int type, next;
	int wrapped = 0;
L
Linus Torvalds 已提交
179

180
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
181
	if (nr_swap_pages <= 0)
182 183 184 185 186 187 188 189 190 191
		goto noswap;
	nr_swap_pages--;

	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
		si = swap_info + type;
		next = si->next;
		if (next < 0 ||
		    (!wrapped && si->prio != swap_info[next].prio)) {
			next = swap_list.head;
			wrapped++;
L
Linus Torvalds 已提交
192
		}
193 194 195 196 197 198 199 200

		if (!si->highest_bit)
			continue;
		if (!(si->flags & SWP_WRITEOK))
			continue;

		swap_list.next = next;
		offset = scan_swap_map(si);
201 202
		if (offset) {
			spin_unlock(&swap_lock);
203
			return swp_entry(type, offset);
204
		}
205
		next = swap_list.next;
L
Linus Torvalds 已提交
206
	}
207 208 209

	nr_swap_pages++;
noswap:
210
	spin_unlock(&swap_lock);
211
	return (swp_entry_t) {0};
L
Linus Torvalds 已提交
212 213
}

214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
swp_entry_t get_swap_page_of_type(int type)
{
	struct swap_info_struct *si;
	pgoff_t offset;

	spin_lock(&swap_lock);
	si = swap_info + type;
	if (si->flags & SWP_WRITEOK) {
		nr_swap_pages--;
		offset = scan_swap_map(si);
		if (offset) {
			spin_unlock(&swap_lock);
			return swp_entry(type, offset);
		}
		nr_swap_pages++;
	}
	spin_unlock(&swap_lock);
	return (swp_entry_t) {0};
}

L
Linus Torvalds 已提交
234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
static struct swap_info_struct * swap_info_get(swp_entry_t entry)
{
	struct swap_info_struct * p;
	unsigned long offset, type;

	if (!entry.val)
		goto out;
	type = swp_type(entry);
	if (type >= nr_swapfiles)
		goto bad_nofile;
	p = & swap_info[type];
	if (!(p->flags & SWP_USED))
		goto bad_device;
	offset = swp_offset(entry);
	if (offset >= p->max)
		goto bad_offset;
	if (!p->swap_map[offset])
		goto bad_free;
252
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281
	return p;

bad_free:
	printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
	goto out;
bad_offset:
	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
	goto out;
bad_device:
	printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
	goto out;
bad_nofile:
	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
out:
	return NULL;
}	

static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
{
	int count = p->swap_map[offset];

	if (count < SWAP_MAP_MAX) {
		count--;
		p->swap_map[offset] = count;
		if (!count) {
			if (offset < p->lowest_bit)
				p->lowest_bit = offset;
			if (offset > p->highest_bit)
				p->highest_bit = offset;
282 283
			if (p->prio > swap_info[swap_list.next].prio)
				swap_list.next = p - swap_info;
L
Linus Torvalds 已提交
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
			nr_swap_pages++;
			p->inuse_pages--;
		}
	}
	return count;
}

/*
 * Caller has made sure that the swapdevice corresponding to entry
 * is still around or has not been recycled.
 */
void swap_free(swp_entry_t entry)
{
	struct swap_info_struct * p;

	p = swap_info_get(entry);
	if (p) {
		swap_entry_free(p, swp_offset(entry));
302
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
303 304 305 306
	}
}

/*
307
 * How many references to page are currently swapped out?
L
Linus Torvalds 已提交
308
 */
309
static inline int page_swapcount(struct page *page)
L
Linus Torvalds 已提交
310
{
311 312
	int count = 0;
	struct swap_info_struct *p;
L
Linus Torvalds 已提交
313 314
	swp_entry_t entry;

H
Hugh Dickins 已提交
315
	entry.val = page_private(page);
L
Linus Torvalds 已提交
316 317
	p = swap_info_get(entry);
	if (p) {
318 319
		/* Subtract the 1 for the swap cache itself */
		count = p->swap_map[swp_offset(entry)] - 1;
320
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
321
	}
322
	return count;
L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330
}

/*
 * We can use this swap cache entry directly
 * if there are no other references to it.
 */
int can_share_swap_page(struct page *page)
{
331 332 333 334 335 336 337
	int count;

	BUG_ON(!PageLocked(page));
	count = page_mapcount(page);
	if (count <= 1 && PageSwapCache(page))
		count += page_swapcount(page);
	return count == 1;
L
Linus Torvalds 已提交
338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
}

/*
 * Work out if there are any other processes sharing this
 * swap cache page. Free it if you can. Return success.
 */
int remove_exclusive_swap_page(struct page *page)
{
	int retval;
	struct swap_info_struct * p;
	swp_entry_t entry;

	BUG_ON(PagePrivate(page));
	BUG_ON(!PageLocked(page));

	if (!PageSwapCache(page))
		return 0;
	if (PageWriteback(page))
		return 0;
	if (page_count(page) != 2) /* 2: us + cache */
		return 0;

H
Hugh Dickins 已提交
360
	entry.val = page_private(page);
L
Linus Torvalds 已提交
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
	p = swap_info_get(entry);
	if (!p)
		return 0;

	/* Is the only swap cache user the cache itself? */
	retval = 0;
	if (p->swap_map[swp_offset(entry)] == 1) {
		/* Recheck the page count with the swapcache lock held.. */
		write_lock_irq(&swapper_space.tree_lock);
		if ((page_count(page) == 2) && !PageWriteback(page)) {
			__delete_from_swap_cache(page);
			SetPageDirty(page);
			retval = 1;
		}
		write_unlock_irq(&swapper_space.tree_lock);
	}
377
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399

	if (retval) {
		swap_free(entry);
		page_cache_release(page);
	}

	return retval;
}

/*
 * Free the swap entry like above, but also try to
 * free the page cache entry if it is the last user.
 */
void free_swap_and_cache(swp_entry_t entry)
{
	struct swap_info_struct * p;
	struct page *page = NULL;

	p = swap_info_get(entry);
	if (p) {
		if (swap_entry_free(p, swp_offset(entry)) == 1)
			page = find_trylock_page(&swapper_space, entry.val);
400
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418
	}
	if (page) {
		int one_user;

		BUG_ON(PagePrivate(page));
		page_cache_get(page);
		one_user = (page_count(page) == 2);
		/* Only cache user (+us), or swap space full? Free it! */
		if (!PageWriteback(page) && (one_user || vm_swap_full())) {
			delete_from_swap_cache(page);
			SetPageDirty(page);
		}
		unlock_page(page);
		page_cache_release(page);
	}
}

/*
419 420 421
 * No need to decide whether this PTE shares the swap entry with others,
 * just let do_wp_page work it out if a write is requested later - to
 * force COW, vm_page_prot omits write permission from any private vma.
L
Linus Torvalds 已提交
422 423 424 425
 */
static void unuse_pte(struct vm_area_struct *vma, pte_t *pte,
		unsigned long addr, swp_entry_t entry, struct page *page)
{
426
	inc_mm_counter(vma->vm_mm, anon_rss);
L
Linus Torvalds 已提交
427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443
	get_page(page);
	set_pte_at(vma->vm_mm, addr, pte,
		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
	page_add_anon_rmap(page, vma, addr);
	swap_free(entry);
	/*
	 * Move the page to the active list so it is not
	 * immediately swapped out again after swapon.
	 */
	activate_page(page);
}

static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
				unsigned long addr, unsigned long end,
				swp_entry_t entry, struct page *page)
{
	pte_t swp_pte = swp_entry_to_pte(entry);
444 445 446
	pte_t *pte;
	spinlock_t *ptl;
	int found = 0;
L
Linus Torvalds 已提交
447

448
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
L
Linus Torvalds 已提交
449 450 451 452 453 454
	do {
		/*
		 * swapoff spends a _lot_ of time in this loop!
		 * Test inline before going to call unuse_pte.
		 */
		if (unlikely(pte_same(*pte, swp_pte))) {
455 456 457
			unuse_pte(vma, pte++, addr, entry, page);
			found = 1;
			break;
L
Linus Torvalds 已提交
458 459
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);
460 461
	pte_unmap_unlock(pte - 1, ptl);
	return found;
L
Linus Torvalds 已提交
462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
}

static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
				unsigned long addr, unsigned long end,
				swp_entry_t entry, struct page *page)
{
	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;
		if (unuse_pte_range(vma, pmd, addr, next, entry, page))
			return 1;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				swp_entry_t entry, struct page *page)
{
	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;
		if (unuse_pmd_range(vma, pud, addr, next, entry, page))
			return 1;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static int unuse_vma(struct vm_area_struct *vma,
				swp_entry_t entry, struct page *page)
{
	pgd_t *pgd;
	unsigned long addr, end, next;

	if (page->mapping) {
		addr = page_address_in_vma(page, vma);
		if (addr == -EFAULT)
			return 0;
		else
			end = addr + PAGE_SIZE;
	} else {
		addr = vma->vm_start;
		end = vma->vm_end;
	}

	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		if (unuse_pud_range(vma, pgd, addr, next, entry, page))
			return 1;
	} while (pgd++, addr = next, addr != end);
	return 0;
}

static int unuse_mm(struct mm_struct *mm,
				swp_entry_t entry, struct page *page)
{
	struct vm_area_struct *vma;

	if (!down_read_trylock(&mm->mmap_sem)) {
		/*
535 536
		 * Activate page so shrink_cache is unlikely to unmap its
		 * ptes while lock is dropped, so swapoff can make progress.
L
Linus Torvalds 已提交
537
		 */
538
		activate_page(page);
L
Linus Torvalds 已提交
539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
		unlock_page(page);
		down_read(&mm->mmap_sem);
		lock_page(page);
	}
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (vma->anon_vma && unuse_vma(vma, entry, page))
			break;
	}
	up_read(&mm->mmap_sem);
	/*
	 * Currently unuse_mm cannot fail, but leave error handling
	 * at call sites for now, since we change it from time to time.
	 */
	return 0;
}

/*
 * Scan swap_map from current position to next entry still in use.
 * Recycle to start on reaching the end, returning 0 when empty.
 */
559 560
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
					unsigned int prev)
L
Linus Torvalds 已提交
561
{
562 563
	unsigned int max = si->max;
	unsigned int i = prev;
L
Linus Torvalds 已提交
564 565 566
	int count;

	/*
567
	 * No need for swap_lock here: we're just looking
L
Linus Torvalds 已提交
568 569
	 * for whether an entry is in use, not modifying it; false
	 * hits are okay, and sys_swapoff() has already prevented new
570
	 * allocations from this area (while holding swap_lock).
L
Linus Torvalds 已提交
571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
	 */
	for (;;) {
		if (++i >= max) {
			if (!prev) {
				i = 0;
				break;
			}
			/*
			 * No entries in use at top of swap_map,
			 * loop back to start and recheck there.
			 */
			max = prev + 1;
			prev = 0;
			i = 1;
		}
		count = si->swap_map[i];
		if (count && count != SWAP_MAP_BAD)
			break;
	}
	return i;
}

/*
 * We completely avoid races by reading each swap page in advance,
 * and then search for the process using it.  All the necessary
 * page table adjustments can then be made atomically.
 */
static int try_to_unuse(unsigned int type)
{
	struct swap_info_struct * si = &swap_info[type];
	struct mm_struct *start_mm;
	unsigned short *swap_map;
	unsigned short swcount;
	struct page *page;
	swp_entry_t entry;
606
	unsigned int i = 0;
L
Linus Torvalds 已提交
607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759
	int retval = 0;
	int reset_overflow = 0;
	int shmem;

	/*
	 * When searching mms for an entry, a good strategy is to
	 * start at the first mm we freed the previous entry from
	 * (though actually we don't notice whether we or coincidence
	 * freed the entry).  Initialize this start_mm with a hold.
	 *
	 * A simpler strategy would be to start at the last mm we
	 * freed the previous entry from; but that would take less
	 * advantage of mmlist ordering, which clusters forked mms
	 * together, child after parent.  If we race with dup_mmap(), we
	 * prefer to resolve parent before child, lest we miss entries
	 * duplicated after we scanned child: using last mm would invert
	 * that.  Though it's only a serious concern when an overflowed
	 * swap count is reset from SWAP_MAP_MAX, preventing a rescan.
	 */
	start_mm = &init_mm;
	atomic_inc(&init_mm.mm_users);

	/*
	 * Keep on scanning until all entries have gone.  Usually,
	 * one pass through swap_map is enough, but not necessarily:
	 * there are races when an instance of an entry might be missed.
	 */
	while ((i = find_next_to_unuse(si, i)) != 0) {
		if (signal_pending(current)) {
			retval = -EINTR;
			break;
		}

		/* 
		 * Get a page for the entry, using the existing swap
		 * cache page if there is one.  Otherwise, get a clean
		 * page and read the swap into it. 
		 */
		swap_map = &si->swap_map[i];
		entry = swp_entry(type, i);
		page = read_swap_cache_async(entry, NULL, 0);
		if (!page) {
			/*
			 * Either swap_duplicate() failed because entry
			 * has been freed independently, and will not be
			 * reused since sys_swapoff() already disabled
			 * allocation from here, or alloc_page() failed.
			 */
			if (!*swap_map)
				continue;
			retval = -ENOMEM;
			break;
		}

		/*
		 * Don't hold on to start_mm if it looks like exiting.
		 */
		if (atomic_read(&start_mm->mm_users) == 1) {
			mmput(start_mm);
			start_mm = &init_mm;
			atomic_inc(&init_mm.mm_users);
		}

		/*
		 * Wait for and lock page.  When do_swap_page races with
		 * try_to_unuse, do_swap_page can handle the fault much
		 * faster than try_to_unuse can locate the entry.  This
		 * apparently redundant "wait_on_page_locked" lets try_to_unuse
		 * defer to do_swap_page in such a case - in some tests,
		 * do_swap_page and try_to_unuse repeatedly compete.
		 */
		wait_on_page_locked(page);
		wait_on_page_writeback(page);
		lock_page(page);
		wait_on_page_writeback(page);

		/*
		 * Remove all references to entry.
		 * Whenever we reach init_mm, there's no address space
		 * to search, but use it as a reminder to search shmem.
		 */
		shmem = 0;
		swcount = *swap_map;
		if (swcount > 1) {
			if (start_mm == &init_mm)
				shmem = shmem_unuse(entry, page);
			else
				retval = unuse_mm(start_mm, entry, page);
		}
		if (*swap_map > 1) {
			int set_start_mm = (*swap_map >= swcount);
			struct list_head *p = &start_mm->mmlist;
			struct mm_struct *new_start_mm = start_mm;
			struct mm_struct *prev_mm = start_mm;
			struct mm_struct *mm;

			atomic_inc(&new_start_mm->mm_users);
			atomic_inc(&prev_mm->mm_users);
			spin_lock(&mmlist_lock);
			while (*swap_map > 1 && !retval &&
					(p = p->next) != &start_mm->mmlist) {
				mm = list_entry(p, struct mm_struct, mmlist);
				if (atomic_inc_return(&mm->mm_users) == 1) {
					atomic_dec(&mm->mm_users);
					continue;
				}
				spin_unlock(&mmlist_lock);
				mmput(prev_mm);
				prev_mm = mm;

				cond_resched();

				swcount = *swap_map;
				if (swcount <= 1)
					;
				else if (mm == &init_mm) {
					set_start_mm = 1;
					shmem = shmem_unuse(entry, page);
				} else
					retval = unuse_mm(mm, entry, page);
				if (set_start_mm && *swap_map < swcount) {
					mmput(new_start_mm);
					atomic_inc(&mm->mm_users);
					new_start_mm = mm;
					set_start_mm = 0;
				}
				spin_lock(&mmlist_lock);
			}
			spin_unlock(&mmlist_lock);
			mmput(prev_mm);
			mmput(start_mm);
			start_mm = new_start_mm;
		}
		if (retval) {
			unlock_page(page);
			page_cache_release(page);
			break;
		}

		/*
		 * How could swap count reach 0x7fff when the maximum
		 * pid is 0x7fff, and there's no way to repeat a swap
		 * page within an mm (except in shmem, where it's the
		 * shared object which takes the reference count)?
		 * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
		 *
		 * If that's wrong, then we should worry more about
		 * exit_mmap() and do_munmap() cases described above:
		 * we might be resetting SWAP_MAP_MAX too early here.
		 * We know "Undead"s can happen, they're okay, so don't
		 * report them; but do report if we reset SWAP_MAP_MAX.
		 */
		if (*swap_map == SWAP_MAP_MAX) {
760
			spin_lock(&swap_lock);
L
Linus Torvalds 已提交
761
			*swap_map = 1;
762
			spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825
			reset_overflow = 1;
		}

		/*
		 * If a reference remains (rare), we would like to leave
		 * the page in the swap cache; but try_to_unmap could
		 * then re-duplicate the entry once we drop page lock,
		 * so we might loop indefinitely; also, that page could
		 * not be swapped out to other storage meanwhile.  So:
		 * delete from cache even if there's another reference,
		 * after ensuring that the data has been saved to disk -
		 * since if the reference remains (rarer), it will be
		 * read from disk into another page.  Splitting into two
		 * pages would be incorrect if swap supported "shared
		 * private" pages, but they are handled by tmpfs files.
		 *
		 * Note shmem_unuse already deleted a swappage from
		 * the swap cache, unless the move to filepage failed:
		 * in which case it left swappage in cache, lowered its
		 * swap count to pass quickly through the loops above,
		 * and now we must reincrement count to try again later.
		 */
		if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
			struct writeback_control wbc = {
				.sync_mode = WB_SYNC_NONE,
			};

			swap_writepage(page, &wbc);
			lock_page(page);
			wait_on_page_writeback(page);
		}
		if (PageSwapCache(page)) {
			if (shmem)
				swap_duplicate(entry);
			else
				delete_from_swap_cache(page);
		}

		/*
		 * So we could skip searching mms once swap count went
		 * to 1, we did not mark any present ptes as dirty: must
		 * mark page dirty so shrink_list will preserve it.
		 */
		SetPageDirty(page);
		unlock_page(page);
		page_cache_release(page);

		/*
		 * Make sure that we aren't completely killing
		 * interactive performance.
		 */
		cond_resched();
	}

	mmput(start_mm);
	if (reset_overflow) {
		printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
		swap_overflow = 0;
	}
	return retval;
}

/*
826 827 828
 * After a successful try_to_unuse, if no swap is now in use, we know
 * we can empty the mmlist.  swap_lock must be held on entry and exit.
 * Note that mmlist_lock nests inside swap_lock, and an mm must be
L
Linus Torvalds 已提交
829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860
 * added to the mmlist just after page_duplicate - before would be racy.
 */
static void drain_mmlist(void)
{
	struct list_head *p, *next;
	unsigned int i;

	for (i = 0; i < nr_swapfiles; i++)
		if (swap_info[i].inuse_pages)
			return;
	spin_lock(&mmlist_lock);
	list_for_each_safe(p, next, &init_mm.mmlist)
		list_del_init(p);
	spin_unlock(&mmlist_lock);
}

/*
 * Use this swapdev's extent info to locate the (PAGE_SIZE) block which
 * corresponds to page offset `offset'.
 */
sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset)
{
	struct swap_extent *se = sis->curr_swap_extent;
	struct swap_extent *start_se = se;

	for ( ; ; ) {
		struct list_head *lh;

		if (se->start_page <= offset &&
				offset < (se->start_page + se->nr_pages)) {
			return se->start_block + (offset - se->start_page);
		}
861
		lh = se->list.next;
L
Linus Torvalds 已提交
862
		if (lh == &sis->extent_list)
863
			lh = lh->next;
L
Linus Torvalds 已提交
864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
		se = list_entry(lh, struct swap_extent, list);
		sis->curr_swap_extent = se;
		BUG_ON(se == start_se);		/* It *must* be present */
	}
}

/*
 * Free all of a swapdev's extent information
 */
static void destroy_swap_extents(struct swap_info_struct *sis)
{
	while (!list_empty(&sis->extent_list)) {
		struct swap_extent *se;

		se = list_entry(sis->extent_list.next,
				struct swap_extent, list);
		list_del(&se->list);
		kfree(se);
	}
}

/*
 * Add a block range (and the corresponding page range) into this swapdev's
887
 * extent list.  The extent list is kept sorted in page order.
L
Linus Torvalds 已提交
888
 *
889
 * This function rather assumes that it is called in ascending page order.
L
Linus Torvalds 已提交
890 891 892 893 894 895 896 897 898
 */
static int
add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
		unsigned long nr_pages, sector_t start_block)
{
	struct swap_extent *se;
	struct swap_extent *new_se;
	struct list_head *lh;

899 900
	lh = sis->extent_list.prev;	/* The highest page extent */
	if (lh != &sis->extent_list) {
L
Linus Torvalds 已提交
901
		se = list_entry(lh, struct swap_extent, list);
902 903
		BUG_ON(se->start_page + se->nr_pages != start_page);
		if (se->start_block + se->nr_pages == start_block) {
L
Linus Torvalds 已提交
904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919
			/* Merge it */
			se->nr_pages += nr_pages;
			return 0;
		}
	}

	/*
	 * No merge.  Insert a new extent, preserving ordering.
	 */
	new_se = kmalloc(sizeof(*se), GFP_KERNEL);
	if (new_se == NULL)
		return -ENOMEM;
	new_se->start_page = start_page;
	new_se->nr_pages = nr_pages;
	new_se->start_block = start_block;

920
	list_add_tail(&new_se->list, &sis->extent_list);
921
	return 1;
L
Linus Torvalds 已提交
922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943
}

/*
 * A `swap extent' is a simple thing which maps a contiguous range of pages
 * onto a contiguous range of disk blocks.  An ordered list of swap extents
 * is built at swapon time and is then used at swap_writepage/swap_readpage
 * time for locating where on disk a page belongs.
 *
 * If the swapfile is an S_ISBLK block device, a single extent is installed.
 * This is done so that the main operating code can treat S_ISBLK and S_ISREG
 * swap files identically.
 *
 * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap
 * extent list operates in PAGE_SIZE disk blocks.  Both S_ISREG and S_ISBLK
 * swapfiles are handled *identically* after swapon time.
 *
 * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks
 * and will parse them into an ordered extent list, in PAGE_SIZE chunks.  If
 * some stray blocks are found which do not fall within the PAGE_SIZE alignment
 * requirements, they are simply tossed out - we will never use those blocks
 * for swapping.
 *
944
 * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon.  This
L
Linus Torvalds 已提交
945 946 947 948 949 950 951 952 953 954
 * prevents root from shooting her foot off by ftruncating an in-use swapfile,
 * which will scribble on the fs.
 *
 * The amount of disk space which a single swap extent represents varies.
 * Typically it is in the 1-4 megabyte range.  So we can have hundreds of
 * extents in the list.  To avoid much list walking, we cache the previous
 * search location in `curr_swap_extent', and start new searches from there.
 * This is extremely effective.  The average number of iterations in
 * map_swap_page() has been measured at about 0.3 per page.  - akpm.
 */
955
static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
L
Linus Torvalds 已提交
956 957 958 959 960 961 962
{
	struct inode *inode;
	unsigned blocks_per_page;
	unsigned long page_no;
	unsigned blkbits;
	sector_t probe_block;
	sector_t last_block;
963 964 965
	sector_t lowest_block = -1;
	sector_t highest_block = 0;
	int nr_extents = 0;
L
Linus Torvalds 已提交
966 967 968 969 970
	int ret;

	inode = sis->swap_file->f_mapping->host;
	if (S_ISBLK(inode->i_mode)) {
		ret = add_swap_extent(sis, 0, sis->max, 0);
971
		*span = sis->pages;
L
Linus Torvalds 已提交
972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
		goto done;
	}

	blkbits = inode->i_blkbits;
	blocks_per_page = PAGE_SIZE >> blkbits;

	/*
	 * Map all the blocks into the extent list.  This code doesn't try
	 * to be very smart.
	 */
	probe_block = 0;
	page_no = 0;
	last_block = i_size_read(inode) >> blkbits;
	while ((probe_block + blocks_per_page) <= last_block &&
			page_no < sis->max) {
		unsigned block_in_page;
		sector_t first_block;

		first_block = bmap(inode, probe_block);
		if (first_block == 0)
			goto bad_bmap;

		/*
		 * It must be PAGE_SIZE aligned on-disk
		 */
		if (first_block & (blocks_per_page - 1)) {
			probe_block++;
			goto reprobe;
		}

		for (block_in_page = 1; block_in_page < blocks_per_page;
					block_in_page++) {
			sector_t block;

			block = bmap(inode, probe_block + block_in_page);
			if (block == 0)
				goto bad_bmap;
			if (block != first_block + block_in_page) {
				/* Discontiguity */
				probe_block++;
				goto reprobe;
			}
		}

1016 1017 1018 1019 1020 1021 1022 1023
		first_block >>= (PAGE_SHIFT - blkbits);
		if (page_no) {	/* exclude the header page */
			if (first_block < lowest_block)
				lowest_block = first_block;
			if (first_block > highest_block)
				highest_block = first_block;
		}

L
Linus Torvalds 已提交
1024 1025 1026
		/*
		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
		 */
1027 1028
		ret = add_swap_extent(sis, page_no, 1, first_block);
		if (ret < 0)
L
Linus Torvalds 已提交
1029
			goto out;
1030
		nr_extents += ret;
L
Linus Torvalds 已提交
1031 1032 1033 1034 1035
		page_no++;
		probe_block += blocks_per_page;
reprobe:
		continue;
	}
1036 1037
	ret = nr_extents;
	*span = 1 + highest_block - lowest_block;
L
Linus Torvalds 已提交
1038
	if (page_no == 0)
1039
		page_no = 1;	/* force Empty message */
L
Linus Torvalds 已提交
1040
	sis->max = page_no;
1041
	sis->pages = page_no - 1;
L
Linus Torvalds 已提交
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062
	sis->highest_bit = page_no - 1;
done:
	sis->curr_swap_extent = list_entry(sis->extent_list.prev,
					struct swap_extent, list);
	goto out;
bad_bmap:
	printk(KERN_ERR "swapon: swapfile has holes\n");
	ret = -EINVAL;
out:
	return ret;
}

#if 0	/* We don't need this yet */
#include <linux/backing-dev.h>
int page_queue_congested(struct page *page)
{
	struct backing_dev_info *bdi;

	BUG_ON(!PageLocked(page));	/* It pins the swap_info_struct */

	if (PageSwapCache(page)) {
H
Hugh Dickins 已提交
1063
		swp_entry_t entry = { .val = page_private(page) };
L
Linus Torvalds 已提交
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
		struct swap_info_struct *sis;

		sis = get_swap_info_struct(swp_type(entry));
		bdi = sis->bdev->bd_inode->i_mapping->backing_dev_info;
	} else
		bdi = page->mapping->backing_dev_info;
	return bdi_write_congested(bdi);
}
#endif

asmlinkage long sys_swapoff(const char __user * specialfile)
{
	struct swap_info_struct * p = NULL;
	unsigned short *swap_map;
	struct file *swap_file, *victim;
	struct address_space *mapping;
	struct inode *inode;
	char * pathname;
	int i, type, prev;
	int err;
	
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	pathname = getname(specialfile);
	err = PTR_ERR(pathname);
	if (IS_ERR(pathname))
		goto out;

	victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0);
	putname(pathname);
	err = PTR_ERR(victim);
	if (IS_ERR(victim))
		goto out;

	mapping = victim->f_mapping;
	prev = -1;
1101
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1102 1103 1104 1105 1106 1107 1108 1109 1110 1111
	for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
		p = swap_info + type;
		if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) {
			if (p->swap_file->f_mapping == mapping)
				break;
		}
		prev = type;
	}
	if (type < 0) {
		err = -EINVAL;
1112
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1113 1114 1115 1116 1117 1118
		goto out_dput;
	}
	if (!security_vm_enough_memory(p->pages))
		vm_unacct_memory(p->pages);
	else {
		err = -ENOMEM;
1119
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
		goto out_dput;
	}
	if (prev < 0) {
		swap_list.head = p->next;
	} else {
		swap_info[prev].next = p->next;
	}
	if (type == swap_list.next) {
		/* just pick something that's safe... */
		swap_list.next = swap_list.head;
	}
	nr_swap_pages -= p->pages;
	total_swap_pages -= p->pages;
	p->flags &= ~SWP_WRITEOK;
1134
	spin_unlock(&swap_lock);
1135

L
Linus Torvalds 已提交
1136 1137 1138 1139 1140 1141
	current->flags |= PF_SWAPOFF;
	err = try_to_unuse(type);
	current->flags &= ~PF_SWAPOFF;

	if (err) {
		/* re-insert swap space back into swap_list */
1142
		spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
		for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
			if (p->prio >= swap_info[i].prio)
				break;
		p->next = i;
		if (prev < 0)
			swap_list.head = swap_list.next = p - swap_info;
		else
			swap_info[prev].next = p - swap_info;
		nr_swap_pages += p->pages;
		total_swap_pages += p->pages;
		p->flags |= SWP_WRITEOK;
1154
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1155 1156
		goto out_dput;
	}
1157 1158 1159 1160 1161

	/* wait for any unplug function to finish */
	down_write(&swap_unplug_sem);
	up_write(&swap_unplug_sem);

1162 1163 1164 1165 1166
	destroy_swap_extents(p);
	down(&swapon_sem);
	spin_lock(&swap_lock);
	drain_mmlist();

1167 1168 1169
	/* wait for anyone still in scan_swap_map */
	p->highest_bit = 0;		/* cuts scans short */
	while (p->flags >= SWP_SCANNING) {
1170
		spin_unlock(&swap_lock);
1171
		schedule_timeout_uninterruptible(1);
1172
		spin_lock(&swap_lock);
1173 1174
	}

L
Linus Torvalds 已提交
1175 1176 1177 1178 1179 1180
	swap_file = p->swap_file;
	p->swap_file = NULL;
	p->max = 0;
	swap_map = p->swap_map;
	p->swap_map = NULL;
	p->flags = 0;
1181
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1182 1183 1184 1185 1186 1187 1188 1189
	up(&swapon_sem);
	vfree(swap_map);
	inode = mapping->host;
	if (S_ISBLK(inode->i_mode)) {
		struct block_device *bdev = I_BDEV(inode);
		set_blocksize(bdev, p->old_block_size);
		bd_release(bdev);
	} else {
1190
		mutex_lock(&inode->i_mutex);
L
Linus Torvalds 已提交
1191
		inode->i_flags &= ~S_SWAPFILE;
1192
		mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253
	}
	filp_close(swap_file, NULL);
	err = 0;

out_dput:
	filp_close(victim, NULL);
out:
	return err;
}

#ifdef CONFIG_PROC_FS
/* iterator */
static void *swap_start(struct seq_file *swap, loff_t *pos)
{
	struct swap_info_struct *ptr = swap_info;
	int i;
	loff_t l = *pos;

	down(&swapon_sem);

	for (i = 0; i < nr_swapfiles; i++, ptr++) {
		if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
			continue;
		if (!l--)
			return ptr;
	}

	return NULL;
}

static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
{
	struct swap_info_struct *ptr = v;
	struct swap_info_struct *endptr = swap_info + nr_swapfiles;

	for (++ptr; ptr < endptr; ptr++) {
		if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
			continue;
		++*pos;
		return ptr;
	}

	return NULL;
}

static void swap_stop(struct seq_file *swap, void *v)
{
	up(&swapon_sem);
}

static int swap_show(struct seq_file *swap, void *v)
{
	struct swap_info_struct *ptr = v;
	struct file *file;
	int len;

	if (v == swap_info)
		seq_puts(swap, "Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n");

	file = ptr->swap_file;
	len = seq_path(swap, file->f_vfsmnt, file->f_dentry, " \t\n\\");
1254
	seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
L
Linus Torvalds 已提交
1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312
		       len < 40 ? 40 - len : 1, " ",
		       S_ISBLK(file->f_dentry->d_inode->i_mode) ?
				"partition" : "file\t",
		       ptr->pages << (PAGE_SHIFT - 10),
		       ptr->inuse_pages << (PAGE_SHIFT - 10),
		       ptr->prio);
	return 0;
}

static struct seq_operations swaps_op = {
	.start =	swap_start,
	.next =		swap_next,
	.stop =		swap_stop,
	.show =		swap_show
};

static int swaps_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &swaps_op);
}

static struct file_operations proc_swaps_operations = {
	.open		= swaps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int __init procswaps_init(void)
{
	struct proc_dir_entry *entry;

	entry = create_proc_entry("swaps", 0, NULL);
	if (entry)
		entry->proc_fops = &proc_swaps_operations;
	return 0;
}
__initcall(procswaps_init);
#endif /* CONFIG_PROC_FS */

/*
 * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
 *
 * The swapon system call
 */
asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
{
	struct swap_info_struct * p;
	char *name = NULL;
	struct block_device *bdev = NULL;
	struct file *swap_file = NULL;
	struct address_space *mapping;
	unsigned int type;
	int i, prev;
	int error;
	static int least_priority;
	union swap_header *swap_header = NULL;
	int swap_header_version;
1313 1314
	unsigned int nr_good_pages = 0;
	int nr_extents = 0;
1315
	sector_t span;
L
Linus Torvalds 已提交
1316 1317 1318 1319 1320 1321 1322 1323 1324
	unsigned long maxpages = 1;
	int swapfilesize;
	unsigned short *swap_map;
	struct page *page = NULL;
	struct inode *inode = NULL;
	int did_down = 0;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
1325
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
	p = swap_info;
	for (type = 0 ; type < nr_swapfiles ; type++,p++)
		if (!(p->flags & SWP_USED))
			break;
	error = -EPERM;
	/*
	 * Test if adding another swap device is possible. There are
	 * two limiting factors: 1) the number of bits for the swap
	 * type swp_entry_t definition and 2) the number of bits for
	 * the swap type in the swap ptes as defined by the different
	 * architectures. To honor both limitations a swap entry
	 * with swap offset 0 and swap type ~0UL is created, encoded
	 * to a swap pte, decoded to a swp_entry_t again and finally
	 * the swap type part is extracted. This will mask all bits
	 * from the initial ~0UL that can't be encoded in either the
	 * swp_entry_t or the architecture definition of a swap pte.
	 */
	if (type > swp_type(pte_to_swp_entry(swp_entry_to_pte(swp_entry(~0UL,0))))) {
1344
		spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364
		goto out;
	}
	if (type >= nr_swapfiles)
		nr_swapfiles = type+1;
	INIT_LIST_HEAD(&p->extent_list);
	p->flags = SWP_USED;
	p->swap_file = NULL;
	p->old_block_size = 0;
	p->swap_map = NULL;
	p->lowest_bit = 0;
	p->highest_bit = 0;
	p->cluster_nr = 0;
	p->inuse_pages = 0;
	p->next = -1;
	if (swap_flags & SWAP_FLAG_PREFER) {
		p->prio =
		  (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
	} else {
		p->prio = --least_priority;
	}
1365
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398
	name = getname(specialfile);
	error = PTR_ERR(name);
	if (IS_ERR(name)) {
		name = NULL;
		goto bad_swap_2;
	}
	swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0);
	error = PTR_ERR(swap_file);
	if (IS_ERR(swap_file)) {
		swap_file = NULL;
		goto bad_swap_2;
	}

	p->swap_file = swap_file;
	mapping = swap_file->f_mapping;
	inode = mapping->host;

	error = -EBUSY;
	for (i = 0; i < nr_swapfiles; i++) {
		struct swap_info_struct *q = &swap_info[i];

		if (i == type || !q->swap_file)
			continue;
		if (mapping == q->swap_file->f_mapping)
			goto bad_swap;
	}

	error = -EINVAL;
	if (S_ISBLK(inode->i_mode)) {
		bdev = I_BDEV(inode);
		error = bd_claim(bdev, sys_swapon);
		if (error < 0) {
			bdev = NULL;
R
Rob Landley 已提交
1399
			error = -EINVAL;
L
Linus Torvalds 已提交
1400 1401 1402 1403 1404 1405 1406 1407 1408
			goto bad_swap;
		}
		p->old_block_size = block_size(bdev);
		error = set_blocksize(bdev, PAGE_SIZE);
		if (error < 0)
			goto bad_swap;
		p->bdev = bdev;
	} else if (S_ISREG(inode->i_mode)) {
		p->bdev = inode->i_sb->s_bdev;
1409
		mutex_lock(&inode->i_mutex);
L
Linus Torvalds 已提交
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467
		did_down = 1;
		if (IS_SWAPFILE(inode)) {
			error = -EBUSY;
			goto bad_swap;
		}
	} else {
		goto bad_swap;
	}

	swapfilesize = i_size_read(inode) >> PAGE_SHIFT;

	/*
	 * Read the swap header.
	 */
	if (!mapping->a_ops->readpage) {
		error = -EINVAL;
		goto bad_swap;
	}
	page = read_cache_page(mapping, 0,
			(filler_t *)mapping->a_ops->readpage, swap_file);
	if (IS_ERR(page)) {
		error = PTR_ERR(page);
		goto bad_swap;
	}
	wait_on_page_locked(page);
	if (!PageUptodate(page))
		goto bad_swap;
	kmap(page);
	swap_header = page_address(page);

	if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
		swap_header_version = 1;
	else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
		swap_header_version = 2;
	else {
		printk("Unable to find swap-space signature\n");
		error = -EINVAL;
		goto bad_swap;
	}
	
	switch (swap_header_version) {
	case 1:
		printk(KERN_ERR "version 0 swap is no longer supported. "
			"Use mkswap -v1 %s\n", name);
		error = -EINVAL;
		goto bad_swap;
	case 2:
		/* Check the swap header's sub-version and the size of
                   the swap file and bad block lists */
		if (swap_header->info.version != 1) {
			printk(KERN_WARNING
			       "Unable to handle swap header version %d\n",
			       swap_header->info.version);
			error = -EINVAL;
			goto bad_swap;
		}

		p->lowest_bit  = 1;
1468 1469
		p->cluster_next = 1;

L
Linus Torvalds 已提交
1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489
		/*
		 * Find out how many pages are allowed for a single swap
		 * device. There are two limiting factors: 1) the number of
		 * bits for the swap offset in the swp_entry_t type and
		 * 2) the number of bits in the a swap pte as defined by
		 * the different architectures. In order to find the
		 * largest possible bit mask a swap entry with swap type 0
		 * and swap offset ~0UL is created, encoded to a swap pte,
		 * decoded to a swp_entry_t again and finally the swap
		 * offset is extracted. This will mask all the bits from
		 * the initial ~0UL mask that can't be encoded in either
		 * the swp_entry_t or the architecture definition of a
		 * swap pte.
		 */
		maxpages = swp_offset(pte_to_swp_entry(swp_entry_to_pte(swp_entry(0,~0UL)))) - 1;
		if (maxpages > swap_header->info.last_page)
			maxpages = swap_header->info.last_page;
		p->highest_bit = maxpages - 1;

		error = -EINVAL;
1490 1491 1492 1493
		if (!maxpages)
			goto bad_swap;
		if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
			goto bad_swap;
L
Linus Torvalds 已提交
1494 1495
		if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
			goto bad_swap;
1496

L
Linus Torvalds 已提交
1497 1498 1499 1500 1501 1502 1503 1504
		/* OK, set up the swap map and apply the bad block list */
		if (!(p->swap_map = vmalloc(maxpages * sizeof(short)))) {
			error = -ENOMEM;
			goto bad_swap;
		}

		error = 0;
		memset(p->swap_map, 0, maxpages * sizeof(short));
1505 1506 1507
		for (i = 0; i < swap_header->info.nr_badpages; i++) {
			int page_nr = swap_header->info.badpages[i];
			if (page_nr <= 0 || page_nr >= swap_header->info.last_page)
L
Linus Torvalds 已提交
1508 1509
				error = -EINVAL;
			else
1510
				p->swap_map[page_nr] = SWAP_MAP_BAD;
L
Linus Torvalds 已提交
1511 1512 1513 1514
		}
		nr_good_pages = swap_header->info.last_page -
				swap_header->info.nr_badpages -
				1 /* header page */;
1515
		if (error)
L
Linus Torvalds 已提交
1516 1517
			goto bad_swap;
	}
1518

L
Linus Torvalds 已提交
1519 1520 1521 1522 1523 1524
	if (swapfilesize && maxpages > swapfilesize) {
		printk(KERN_WARNING
		       "Swap area shorter than signature indicates\n");
		error = -EINVAL;
		goto bad_swap;
	}
1525 1526 1527 1528
	if (nr_good_pages) {
		p->swap_map[0] = SWAP_MAP_BAD;
		p->max = maxpages;
		p->pages = nr_good_pages;
1529 1530 1531
		nr_extents = setup_swap_extents(p, &span);
		if (nr_extents < 0) {
			error = nr_extents;
1532
			goto bad_swap;
1533
		}
1534 1535
		nr_good_pages = p->pages;
	}
L
Linus Torvalds 已提交
1536 1537 1538 1539 1540 1541 1542
	if (!nr_good_pages) {
		printk(KERN_WARNING "Empty swap-file\n");
		error = -EINVAL;
		goto bad_swap;
	}

	down(&swapon_sem);
1543
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1544 1545 1546
	p->flags = SWP_ACTIVE;
	nr_swap_pages += nr_good_pages;
	total_swap_pages += nr_good_pages;
1547

1548
	printk(KERN_INFO "Adding %uk swap on %s.  "
1549 1550 1551
			"Priority:%d extents:%d across:%lluk\n",
		nr_good_pages<<(PAGE_SHIFT-10), name, p->prio,
		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10));
L
Linus Torvalds 已提交
1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566

	/* insert swap space into swap_list: */
	prev = -1;
	for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
		if (p->prio >= swap_info[i].prio) {
			break;
		}
		prev = i;
	}
	p->next = i;
	if (prev < 0) {
		swap_list.head = swap_list.next = p - swap_info;
	} else {
		swap_info[prev].next = p - swap_info;
	}
1567
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1568 1569 1570 1571 1572 1573 1574 1575
	up(&swapon_sem);
	error = 0;
	goto out;
bad_swap:
	if (bdev) {
		set_blocksize(bdev, p->old_block_size);
		bd_release(bdev);
	}
1576
	destroy_swap_extents(p);
L
Linus Torvalds 已提交
1577
bad_swap_2:
1578
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1579 1580 1581 1582 1583 1584
	swap_map = p->swap_map;
	p->swap_file = NULL;
	p->swap_map = NULL;
	p->flags = 0;
	if (!(swap_flags & SWAP_FLAG_PREFER))
		++least_priority;
1585
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598
	vfree(swap_map);
	if (swap_file)
		filp_close(swap_file, NULL);
out:
	if (page && !IS_ERR(page)) {
		kunmap(page);
		page_cache_release(page);
	}
	if (name)
		putname(name);
	if (did_down) {
		if (!error)
			inode->i_flags |= S_SWAPFILE;
1599
		mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
1600 1601 1602 1603 1604 1605 1606 1607 1608
	}
	return error;
}

void si_swapinfo(struct sysinfo *val)
{
	unsigned int i;
	unsigned long nr_to_be_unused = 0;

1609
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1610 1611 1612 1613 1614 1615 1616 1617
	for (i = 0; i < nr_swapfiles; i++) {
		if (!(swap_info[i].flags & SWP_USED) ||
		     (swap_info[i].flags & SWP_WRITEOK))
			continue;
		nr_to_be_unused += swap_info[i].inuse_pages;
	}
	val->freeswap = nr_swap_pages + nr_to_be_unused;
	val->totalswap = total_swap_pages + nr_to_be_unused;
1618
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638
}

/*
 * Verify that a swap entry is valid and increment its swap map count.
 *
 * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
 * "permanent", but will be reclaimed by the next swapoff.
 */
int swap_duplicate(swp_entry_t entry)
{
	struct swap_info_struct * p;
	unsigned long offset, type;
	int result = 0;

	type = swp_type(entry);
	if (type >= nr_swapfiles)
		goto bad_file;
	p = type + swap_info;
	offset = swp_offset(entry);

1639
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650
	if (offset < p->max && p->swap_map[offset]) {
		if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
			p->swap_map[offset]++;
			result = 1;
		} else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
			if (swap_overflow++ < 5)
				printk(KERN_WARNING "swap_dup: swap entry overflow\n");
			p->swap_map[offset] = SWAP_MAP_MAX;
			result = 1;
		}
	}
1651
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666
out:
	return result;

bad_file:
	printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
	goto out;
}

struct swap_info_struct *
get_swap_info_struct(unsigned type)
{
	return &swap_info[type];
}

/*
1667
 * swap_lock prevents swap_map being freed. Don't grab an extra
L
Linus Torvalds 已提交
1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682
 * reference on the swaphandle, it doesn't matter if it becomes unused.
 */
int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
{
	int ret = 0, i = 1 << page_cluster;
	unsigned long toff;
	struct swap_info_struct *swapdev = swp_type(entry) + swap_info;

	if (!page_cluster)	/* no readahead */
		return 0;
	toff = (swp_offset(entry) >> page_cluster) << page_cluster;
	if (!toff)		/* first page is swap header */
		toff++, i--;
	*offset = toff;

1683
	spin_lock(&swap_lock);
L
Linus Torvalds 已提交
1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695
	do {
		/* Don't read-ahead past the end of the swap area */
		if (toff >= swapdev->max)
			break;
		/* Don't read in free or bad pages */
		if (!swapdev->swap_map[toff])
			break;
		if (swapdev->swap_map[toff] == SWAP_MAP_BAD)
			break;
		toff++;
		ret++;
	} while (--i);
1696
	spin_unlock(&swap_lock);
L
Linus Torvalds 已提交
1697 1698
	return ret;
}