migrate.c 25.4 KB
Newer Older
C
Christoph Lameter 已提交
1 2 3 4 5 6 7 8 9 10 11
/*
 * Memory Migration functionality - linux/mm/migration.c
 *
 * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
 *
 * Page migration was first developed in the context of the memory hotplug
 * project. The main authors of the migration code are:
 *
 * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
 * Hirokazu Takahashi <taka@valinux.co.jp>
 * Dave Hansen <haveblue@us.ibm.com>
C
Christoph Lameter 已提交
12
 * Christoph Lameter
C
Christoph Lameter 已提交
13 14 15 16 17
 */

#include <linux/migrate.h>
#include <linux/module.h>
#include <linux/swap.h>
18
#include <linux/swapops.h>
C
Christoph Lameter 已提交
19
#include <linux/pagemap.h>
20
#include <linux/buffer_head.h>
C
Christoph Lameter 已提交
21
#include <linux/mm_inline.h>
22
#include <linux/nsproxy.h>
C
Christoph Lameter 已提交
23 24 25 26 27
#include <linux/pagevec.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
28
#include <linux/writeback.h>
29 30
#include <linux/mempolicy.h>
#include <linux/vmalloc.h>
31
#include <linux/security.h>
32
#include <linux/memcontrol.h>
33
#include <linux/syscalls.h>
C
Christoph Lameter 已提交
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54

#include "internal.h"

#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))

/*
 * Isolate one page from the LRU lists. If successful put it onto
 * the indicated list with elevated page count.
 *
 * Result:
 *  -EBUSY: page not on LRU list
 *  0: page removed from LRU list and added to the specified list.
 */
int isolate_lru_page(struct page *page, struct list_head *pagelist)
{
	int ret = -EBUSY;

	if (PageLRU(page)) {
		struct zone *zone = page_zone(page);

		spin_lock_irq(&zone->lru_lock);
55
		if (PageLRU(page) && get_page_unless_zero(page)) {
C
Christoph Lameter 已提交
56 57 58 59 60 61 62 63 64 65 66 67 68 69
			ret = 0;
			ClearPageLRU(page);
			if (PageActive(page))
				del_page_from_active_list(zone, page);
			else
				del_page_from_inactive_list(zone, page);
			list_add_tail(&page->lru, pagelist);
		}
		spin_unlock_irq(&zone->lru_lock);
	}
	return ret;
}

/*
70 71
 * migrate_prep() needs to be called before we start compiling a list of pages
 * to be migrated using isolate_lru_page().
C
Christoph Lameter 已提交
72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
 */
int migrate_prep(void)
{
	/*
	 * Clear the LRU lists so pages can be isolated.
	 * Note that pages may be moved off the LRU after we have
	 * drained them. Those pages will fail to migrate like other
	 * pages that may be busy.
	 */
	lru_add_drain_all();

	return 0;
}

static inline void move_to_lru(struct page *page)
{
	if (PageActive(page)) {
		/*
		 * lru_cache_add_active checks that
		 * the PG_active bit is off.
		 */
		ClearPageActive(page);
		lru_cache_add_active(page);
	} else {
		lru_cache_add(page);
	}
	put_page(page);
}

/*
 * Add isolated pages on the list back to the LRU.
 *
 * returns the number of pages put back.
 */
int putback_lru_pages(struct list_head *l)
{
	struct page *page;
	struct page *page2;
	int count = 0;

	list_for_each_entry_safe(page, page2, l, lru) {
113
		list_del(&page->lru);
C
Christoph Lameter 已提交
114 115 116 117 118 119
		move_to_lru(page);
		count++;
	}
	return count;
}

120 121 122
/*
 * Restore a potential migration pte to a working pte entry
 */
123
static void remove_migration_pte(struct vm_area_struct *vma,
124 125 126 127 128 129 130 131 132
		struct page *old, struct page *new)
{
	struct mm_struct *mm = vma->vm_mm;
	swp_entry_t entry;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
	pte_t *ptep, pte;
 	spinlock_t *ptl;
133 134 135 136
	unsigned long addr = page_address_in_vma(new, vma);

	if (addr == -EFAULT)
		return;
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

 	pgd = pgd_offset(mm, addr);
	if (!pgd_present(*pgd))
                return;

	pud = pud_offset(pgd, addr);
	if (!pud_present(*pud))
                return;

	pmd = pmd_offset(pud, addr);
	if (!pmd_present(*pmd))
		return;

	ptep = pte_offset_map(pmd, addr);

	if (!is_swap_pte(*ptep)) {
		pte_unmap(ptep);
 		return;
 	}

 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto out;

	entry = pte_to_swp_entry(pte);

	if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
		goto out;

168 169 170 171 172 173 174 175 176 177 178 179 180 181
	/*
	 * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge.
	 * Failure is not an option here: we're now expected to remove every
	 * migration pte, and will cause crashes otherwise.  Normally this
	 * is not an issue: mem_cgroup_prepare_migration bumped up the old
	 * page_cgroup count for safety, that's now attached to the new page,
	 * so this charge should just be another incrementation of the count,
	 * to keep in balance with rmap.c's mem_cgroup_uncharging.  But if
	 * there's been a force_empty, those reference counts may no longer
	 * be reliable, and this charge can actually fail: oh well, we don't
	 * make the situation any worse by proceeding as if it had succeeded.
	 */
	mem_cgroup_charge(new, mm, GFP_ATOMIC);

182 183 184 185
	get_page(new);
	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
	if (is_write_migration_entry(entry))
		pte = pte_mkwrite(pte);
186
	flush_cache_page(vma, addr, pte_pfn(pte));
187
	set_pte_at(mm, addr, ptep, pte);
188 189 190 191 192 193 194 195 196

	if (PageAnon(new))
		page_add_anon_rmap(new, vma, addr);
	else
		page_add_file_rmap(new);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, addr, pte);

197 198 199 200 201
out:
	pte_unmap_unlock(ptep, ptl);
}

/*
202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
 * Note that remove_file_migration_ptes will only work on regular mappings,
 * Nonlinear mappings do not use migration entries.
 */
static void remove_file_migration_ptes(struct page *old, struct page *new)
{
	struct vm_area_struct *vma;
	struct address_space *mapping = page_mapping(new);
	struct prio_tree_iter iter;
	pgoff_t pgoff = new->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);

	if (!mapping)
		return;

	spin_lock(&mapping->i_mmap_lock);

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff)
		remove_migration_pte(vma, old, new);

	spin_unlock(&mapping->i_mmap_lock);
}

/*
224 225 226
 * Must hold mmap_sem lock on at least one of the vmas containing
 * the page so that the anon_vma cannot vanish.
 */
227
static void remove_anon_migration_ptes(struct page *old, struct page *new)
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
{
	struct anon_vma *anon_vma;
	struct vm_area_struct *vma;
	unsigned long mapping;

	mapping = (unsigned long)new->mapping;

	if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0)
		return;

	/*
	 * We hold the mmap_sem lock. So no need to call page_lock_anon_vma.
	 */
	anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON);
	spin_lock(&anon_vma->lock);

	list_for_each_entry(vma, &anon_vma->head, anon_vma_node)
245
		remove_migration_pte(vma, old, new);
246 247 248 249

	spin_unlock(&anon_vma->lock);
}

250 251 252 253 254 255 256 257 258 259 260 261
/*
 * Get rid of all migration entries and replace them by
 * references to the indicated page.
 */
static void remove_migration_ptes(struct page *old, struct page *new)
{
	if (PageAnon(new))
		remove_anon_migration_ptes(old, new);
	else
		remove_file_migration_ptes(old, new);
}

262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
/*
 * Something used the pte of a page under migration. We need to
 * get to the page and wait until migration is finished.
 * When we return from this function the fault will be retried.
 *
 * This function is called from do_swap_page().
 */
void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
				unsigned long address)
{
	pte_t *ptep, pte;
	spinlock_t *ptl;
	swp_entry_t entry;
	struct page *page;

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto out;

	entry = pte_to_swp_entry(pte);
	if (!is_migration_entry(entry))
		goto out;

	page = migration_entry_to_page(entry);

N
Nick Piggin 已提交
288 289 290 291 292 293 294 295 296
	/*
	 * Once radix-tree replacement of page migration started, page_count
	 * *must* be zero. And, we don't want to call wait_on_page_locked()
	 * against a page without get_page().
	 * So, we use get_page_unless_zero(), here. Even failed, page fault
	 * will occur again.
	 */
	if (!get_page_unless_zero(page))
		goto out;
297 298 299 300 301 302 303 304
	pte_unmap_unlock(ptep, ptl);
	wait_on_page_locked(page);
	put_page(page);
	return;
out:
	pte_unmap_unlock(ptep, ptl);
}

C
Christoph Lameter 已提交
305
/*
306
 * Replace the page in the mapping.
307 308 309 310 311
 *
 * The number of remaining references must be:
 * 1 for anonymous pages without a mapping
 * 2 for pages with a mapping
 * 3 for pages with a mapping and PagePrivate set.
C
Christoph Lameter 已提交
312
 */
313 314
static int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
315
{
N
Nick Piggin 已提交
316
	int expected_count;
317
	void **pslot;
C
Christoph Lameter 已提交
318

319
	if (!mapping) {
320
		/* Anonymous page without mapping */
321 322 323 324 325
		if (page_count(page) != 1)
			return -EAGAIN;
		return 0;
	}

C
Christoph Lameter 已提交
326 327
	write_lock_irq(&mapping->tree_lock);

328 329
	pslot = radix_tree_lookup_slot(&mapping->page_tree,
 					page_index(page));
C
Christoph Lameter 已提交
330

N
Nick Piggin 已提交
331 332
	expected_count = 2 + !!PagePrivate(page);
	if (page_count(page) != expected_count ||
333
			(struct page *)radix_tree_deref_slot(pslot) != page) {
C
Christoph Lameter 已提交
334
		write_unlock_irq(&mapping->tree_lock);
335
		return -EAGAIN;
C
Christoph Lameter 已提交
336 337
	}

N
Nick Piggin 已提交
338 339 340 341 342
	if (!page_freeze_refs(page, expected_count)) {
		write_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

C
Christoph Lameter 已提交
343 344 345
	/*
	 * Now we know that no one else is looking at the page.
	 */
346
	get_page(newpage);	/* add cache reference */
347
#ifdef CONFIG_SWAP
C
Christoph Lameter 已提交
348 349 350 351
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}
352
#endif
C
Christoph Lameter 已提交
353

354 355
	radix_tree_replace_slot(pslot, newpage);

N
Nick Piggin 已提交
356
	page_unfreeze_refs(page, expected_count);
357 358 359 360
	/*
	 * Drop cache reference from old page.
	 * We know this isn't the last reference.
	 */
C
Christoph Lameter 已提交
361
	__put_page(page);
362

363 364 365 366 367 368 369 370 371 372 373 374 375
	/*
	 * If moved to a different zone then also account
	 * the page for that zone. Other VM counters will be
	 * taken care of when we establish references to the
	 * new page and drop references to the old page.
	 *
	 * Note that anonymous pages are accounted for
	 * via NR_FILE_PAGES and NR_ANON_PAGES if they
	 * are mapped to swap space.
	 */
	__dec_zone_page_state(page, NR_FILE_PAGES);
	__inc_zone_page_state(newpage, NR_FILE_PAGES);

C
Christoph Lameter 已提交
376
	write_unlock_irq(&mapping->tree_lock);
377
	if (!PageSwapCache(newpage)) {
378
		mem_cgroup_uncharge_cache_page(page);
379
	}
C
Christoph Lameter 已提交
380 381 382 383 384 385 386

	return 0;
}

/*
 * Copy the page to its new location
 */
387
static void migrate_page_copy(struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
{
	copy_highpage(newpage, page);

	if (PageError(page))
		SetPageError(newpage);
	if (PageReferenced(page))
		SetPageReferenced(newpage);
	if (PageUptodate(page))
		SetPageUptodate(newpage);
	if (PageActive(page))
		SetPageActive(newpage);
	if (PageChecked(page))
		SetPageChecked(newpage);
	if (PageMappedToDisk(page))
		SetPageMappedToDisk(newpage);

	if (PageDirty(page)) {
		clear_page_dirty_for_io(page);
N
Nick Piggin 已提交
406 407 408 409 410 411 412 413
		/*
		 * Want to mark the page and the radix tree as dirty, and
		 * redo the accounting that clear_page_dirty_for_io undid,
		 * but we can't use set_page_dirty because that function
		 * is actually a signal that all of the page has become dirty.
		 * Wheras only part of our page may be dirty.
		 */
		__set_page_dirty_nobuffers(newpage);
C
Christoph Lameter 已提交
414 415
 	}

416
#ifdef CONFIG_SWAP
C
Christoph Lameter 已提交
417
	ClearPageSwapCache(page);
418
#endif
C
Christoph Lameter 已提交
419 420 421 422 423 424 425 426 427 428 429 430 431
	ClearPageActive(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);
	page->mapping = NULL;

	/*
	 * If any waiters have accumulated on the new page then
	 * wake them up.
	 */
	if (PageWriteback(newpage))
		end_page_writeback(newpage);
}

432 433 434 435 436
/************************************************************
 *                    Migration functions
 ***********************************************************/

/* Always fail migration. Used for mappings that are not movable */
437 438
int fail_migrate_page(struct address_space *mapping,
			struct page *newpage, struct page *page)
439 440 441 442 443
{
	return -EIO;
}
EXPORT_SYMBOL(fail_migrate_page);

C
Christoph Lameter 已提交
444 445 446 447 448 449
/*
 * Common logic to directly migrate a single page suitable for
 * pages that do not use PagePrivate.
 *
 * Pages are locked upon entry and exit.
 */
450 451
int migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
452 453 454 455 456
{
	int rc;

	BUG_ON(PageWriteback(page));	/* Writeback must be complete */

457
	rc = migrate_page_move_mapping(mapping, newpage, page);
C
Christoph Lameter 已提交
458 459 460 461 462 463 464 465 466

	if (rc)
		return rc;

	migrate_page_copy(newpage, page);
	return 0;
}
EXPORT_SYMBOL(migrate_page);

467
#ifdef CONFIG_BLOCK
468 469 470 471 472
/*
 * Migration function for pages with buffers. This function can only be used
 * if the underlying filesystem guarantees that no other references to "page"
 * exist.
 */
473 474
int buffer_migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page)
475 476 477 478 479
{
	struct buffer_head *bh, *head;
	int rc;

	if (!page_has_buffers(page))
480
		return migrate_page(mapping, newpage, page);
481 482 483

	head = page_buffers(page);

484
	rc = migrate_page_move_mapping(mapping, newpage, page);
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

	if (rc)
		return rc;

	bh = head;
	do {
		get_bh(bh);
		lock_buffer(bh);
		bh = bh->b_this_page;

	} while (bh != head);

	ClearPagePrivate(page);
	set_page_private(newpage, page_private(page));
	set_page_private(page, 0);
	put_page(page);
	get_page(newpage);

	bh = head;
	do {
		set_bh_page(bh, newpage, bh_offset(bh));
		bh = bh->b_this_page;

	} while (bh != head);

	SetPagePrivate(newpage);

	migrate_page_copy(newpage, page);

	bh = head;
	do {
		unlock_buffer(bh);
 		put_bh(bh);
		bh = bh->b_this_page;

	} while (bh != head);

	return 0;
}
EXPORT_SYMBOL(buffer_migrate_page);
525
#endif
526

527 528 529 530
/*
 * Writeback a page to clean the dirty state
 */
static int writeout(struct address_space *mapping, struct page *page)
531
{
532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_NONE,
		.nr_to_write = 1,
		.range_start = 0,
		.range_end = LLONG_MAX,
		.nonblocking = 1,
		.for_reclaim = 1
	};
	int rc;

	if (!mapping->a_ops->writepage)
		/* No write method for the address space */
		return -EINVAL;

	if (!clear_page_dirty_for_io(page))
		/* Someone else already triggered a write */
		return -EAGAIN;

550
	/*
551 552 553 554 555 556
	 * A dirty page may imply that the underlying filesystem has
	 * the page on some queue. So the page must be clean for
	 * migration. Writeout may mean we loose the lock and the
	 * page state is no longer what we checked for earlier.
	 * At this point we know that the migration attempt cannot
	 * be successful.
557
	 */
558
	remove_migration_ptes(page, page);
559

560 561 562 563
	rc = mapping->a_ops->writepage(page, &wbc);
	if (rc < 0)
		/* I/O Error writing */
		return -EIO;
564

565 566 567 568 569 570 571 572 573 574 575 576 577 578 579
	if (rc != AOP_WRITEPAGE_ACTIVATE)
		/* unlocked. Relock */
		lock_page(page);

	return -EAGAIN;
}

/*
 * Default handling if a filesystem does not provide a migration function.
 */
static int fallback_migrate_page(struct address_space *mapping,
	struct page *newpage, struct page *page)
{
	if (PageDirty(page))
		return writeout(mapping, page);
580 581 582 583 584

	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
585
	if (PagePrivate(page) &&
586 587 588 589 590 591
	    !try_to_release_page(page, GFP_KERNEL))
		return -EAGAIN;

	return migrate_page(mapping, newpage, page);
}

592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631
/*
 * Move a page to a newly allocated page
 * The page is locked and all ptes have been successfully removed.
 *
 * The new page will have replaced the old page if this function
 * is successful.
 */
static int move_to_new_page(struct page *newpage, struct page *page)
{
	struct address_space *mapping;
	int rc;

	/*
	 * Block others from accessing the page when we get around to
	 * establishing additional references. We are the only one
	 * holding a reference to the new page at this point.
	 */
	if (TestSetPageLocked(newpage))
		BUG();

	/* Prepare mapping for the new page.*/
	newpage->index = page->index;
	newpage->mapping = page->mapping;

	mapping = page_mapping(page);
	if (!mapping)
		rc = migrate_page(mapping, newpage, page);
	else if (mapping->a_ops->migratepage)
		/*
		 * Most pages have a mapping and most filesystems
		 * should provide a migration function. Anonymous
		 * pages are part of swap space which also has its
		 * own migration function. This is the most common
		 * path for page migration.
		 */
		rc = mapping->a_ops->migratepage(mapping,
						newpage, page);
	else
		rc = fallback_migrate_page(mapping, newpage, page);

632
	if (!rc) {
633
		remove_migration_ptes(page, newpage);
634
	} else
635 636 637 638 639 640 641 642 643 644 645
		newpage->mapping = NULL;

	unlock_page(newpage);

	return rc;
}

/*
 * Obtain the lock on page, remove all ptes and migrate the page
 * to the newly allocated page in newpage.
 */
646 647
static int unmap_and_move(new_page_t get_new_page, unsigned long private,
			struct page *page, int force)
648 649
{
	int rc = 0;
650 651
	int *result = NULL;
	struct page *newpage = get_new_page(page, private, &result);
652
	int rcu_locked = 0;
653
	int charge = 0;
654 655 656

	if (!newpage)
		return -ENOMEM;
657 658 659

	if (page_count(page) == 1)
		/* page was freed from under us. So we are done. */
660
		goto move_newpage;
661

662 663 664 665 666 667 668 669
	charge = mem_cgroup_prepare_migration(page, newpage);
	if (charge == -ENOMEM) {
		rc = -ENOMEM;
		goto move_newpage;
	}
	/* prepare cgroup just returns 0 or -ENOMEM */
	BUG_ON(charge);

670 671 672
	rc = -EAGAIN;
	if (TestSetPageLocked(page)) {
		if (!force)
673
			goto move_newpage;
674 675 676 677 678 679 680 681 682
		lock_page(page);
	}

	if (PageWriteback(page)) {
		if (!force)
			goto unlock;
		wait_on_page_writeback(page);
	}
	/*
683 684 685 686
	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
	 * we cannot notice that anon_vma is freed while we migrates a page.
	 * This rcu_read_lock() delays freeing anon_vma pointer until the end
	 * of migration. File cache pages are no problem because of page_lock()
687 688
	 * File Caches may use write_page() or lock_page() in migration, then,
	 * just care Anon page here.
689
	 */
690 691 692 693
	if (PageAnon(page)) {
		rcu_read_lock();
		rcu_locked = 1;
	}
694

695
	/*
696 697 698 699 700 701 702 703 704 705
	 * Corner case handling:
	 * 1. When a new swap-cache page is read into, it is added to the LRU
	 * and treated as swapcache but it has no rmap yet.
	 * Calling try_to_unmap() against a page->mapping==NULL page will
	 * trigger a BUG.  So handle it here.
	 * 2. An orphaned page (see truncate_complete_page) might have
	 * fs-private metadata. The page can be picked up due to memory
	 * offlining.  Everywhere else except page reclaim, the page is
	 * invisible to the vm, so the page can not be migrated.  So try to
	 * free the metadata, so the page can be freed.
706
	 */
707 708 709 710 711 712 713 714 715 716 717
	if (!page->mapping) {
		if (!PageAnon(page) && PagePrivate(page)) {
			/*
			 * Go direct to try_to_free_buffers() here because
			 * a) that's what try_to_release_page() would do anyway
			 * b) we may be under rcu_read_lock() here, so we can't
			 *    use GFP_KERNEL which is what try_to_release_page()
			 *    needs to be effective.
			 */
			try_to_free_buffers(page);
		}
718
		goto rcu_unlock;
719 720
	}

721
	/* Establish migration ptes or remove ptes */
722
	try_to_unmap(page, 1);
723

724 725
	if (!page_mapped(page))
		rc = move_to_new_page(newpage, page);
726

727
	if (rc)
728
		remove_migration_ptes(page, page);
729
rcu_unlock:
730 731
	if (rcu_locked)
		rcu_read_unlock();
732

733
unlock:
734

735
	unlock_page(page);
736

737
	if (rc != -EAGAIN) {
738 739 740 741 742 743 744 745
 		/*
 		 * A page that has been migrated has all references
 		 * removed and will be freed. A page that has not been
 		 * migrated will have kepts its references and be
 		 * restored.
 		 */
 		list_del(&page->lru);
 		move_to_lru(page);
746
	}
747 748

move_newpage:
749 750
	if (!charge)
		mem_cgroup_end_migration(newpage);
751 752 753 754 755
	/*
	 * Move the new page to the LRU. If migration was not successful
	 * then this will free the page.
	 */
	move_to_lru(newpage);
756 757 758 759 760 761
	if (result) {
		if (rc)
			*result = rc;
		else
			*result = page_to_nid(newpage);
	}
762 763 764
	return rc;
}

C
Christoph Lameter 已提交
765 766 767
/*
 * migrate_pages
 *
768 769 770
 * The function takes one list of pages to migrate and a function
 * that determines from the page to be migrated and the private data
 * the target of the move and allocates the page.
C
Christoph Lameter 已提交
771 772 773
 *
 * The function returns after 10 attempts or if no pages
 * are movable anymore because to has become empty
774
 * or no retryable pages exist anymore. All pages will be
G
Gabriel Craciunescu 已提交
775
 * returned to the LRU or freed.
C
Christoph Lameter 已提交
776
 *
777
 * Return: Number of pages not migrated or error code.
C
Christoph Lameter 已提交
778
 */
779 780
int migrate_pages(struct list_head *from,
		new_page_t get_new_page, unsigned long private)
C
Christoph Lameter 已提交
781
{
782
	int retry = 1;
C
Christoph Lameter 已提交
783 784 785 786 787 788 789 790 791 792
	int nr_failed = 0;
	int pass = 0;
	struct page *page;
	struct page *page2;
	int swapwrite = current->flags & PF_SWAPWRITE;
	int rc;

	if (!swapwrite)
		current->flags |= PF_SWAPWRITE;

793 794
	for(pass = 0; pass < 10 && retry; pass++) {
		retry = 0;
C
Christoph Lameter 已提交
795

796 797
		list_for_each_entry_safe(page, page2, from, lru) {
			cond_resched();
798

799 800
			rc = unmap_and_move(get_new_page, private,
						page, pass > 2);
801

802
			switch(rc) {
803 804
			case -ENOMEM:
				goto out;
805
			case -EAGAIN:
806
				retry++;
807 808 809 810
				break;
			case 0:
				break;
			default:
811 812
				/* Permanent failure */
				nr_failed++;
813
				break;
814
			}
C
Christoph Lameter 已提交
815 816
		}
	}
817 818
	rc = 0;
out:
C
Christoph Lameter 已提交
819 820 821
	if (!swapwrite)
		current->flags &= ~PF_SWAPWRITE;

822
	putback_lru_pages(from);
C
Christoph Lameter 已提交
823

824 825
	if (rc)
		return rc;
C
Christoph Lameter 已提交
826

827
	return nr_failed + retry;
C
Christoph Lameter 已提交
828
}
829

830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853
#ifdef CONFIG_NUMA
/*
 * Move a list of individual pages
 */
struct page_to_node {
	unsigned long addr;
	struct page *page;
	int node;
	int status;
};

static struct page *new_page_node(struct page *p, unsigned long private,
		int **result)
{
	struct page_to_node *pm = (struct page_to_node *)private;

	while (pm->node != MAX_NUMNODES && pm->page != p)
		pm++;

	if (pm->node == MAX_NUMNODES)
		return NULL;

	*result = &pm->status;

854 855
	return alloc_pages_node(pm->node,
				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887
}

/*
 * Move a set of pages as indicated in the pm array. The addr
 * field must be set to the virtual address of the page to be moved
 * and the node number must contain a valid target node.
 */
static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm,
				int migrate_all)
{
	int err;
	struct page_to_node *pp;
	LIST_HEAD(pagelist);

	down_read(&mm->mmap_sem);

	/*
	 * Build a list of pages to migrate
	 */
	migrate_prep();
	for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
		struct vm_area_struct *vma;
		struct page *page;

		/*
		 * A valid page pointer that will not match any of the
		 * pages that will be moved.
		 */
		pp->page = ZERO_PAGE(0);

		err = -EFAULT;
		vma = find_vma(mm, pp->addr);
888
		if (!vma || !vma_migratable(vma))
889 890 891
			goto set_status;

		page = follow_page(vma, pp->addr, FOLL_GET);
892 893 894 895 896

		err = PTR_ERR(page);
		if (IS_ERR(page))
			goto set_status;

897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
		err = -ENOENT;
		if (!page)
			goto set_status;

		if (PageReserved(page))		/* Check for zero page */
			goto put_and_set;

		pp->page = page;
		err = page_to_nid(page);

		if (err == pp->node)
			/*
			 * Node already in the right place
			 */
			goto put_and_set;

		err = -EACCES;
		if (page_mapcount(page) > 1 &&
				!migrate_all)
			goto put_and_set;

		err = isolate_lru_page(page, &pagelist);
put_and_set:
		/*
		 * Either remove the duplicate refcount from
		 * isolate_lru_page() or drop the page ref if it was
		 * not isolated.
		 */
		put_page(page);
set_status:
		pp->status = err;
	}

	if (!list_empty(&pagelist))
		err = migrate_pages(&pagelist, new_page_node,
				(unsigned long)pm);
	else
		err = -ENOENT;

	up_read(&mm->mmap_sem);
	return err;
}

/*
 * Determine the nodes of a list of pages. The addr in the pm array
 * must have been set to the virtual address of which we want to determine
 * the node number.
 */
static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm)
{
	down_read(&mm->mmap_sem);

	for ( ; pm->node != MAX_NUMNODES; pm++) {
		struct vm_area_struct *vma;
		struct page *page;
		int err;

		err = -EFAULT;
		vma = find_vma(mm, pm->addr);
		if (!vma)
			goto set_status;

		page = follow_page(vma, pm->addr, 0);
960 961 962 963 964

		err = PTR_ERR(page);
		if (IS_ERR(page))
			goto set_status;

965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003
		err = -ENOENT;
		/* Use PageReserved to check for zero page */
		if (!page || PageReserved(page))
			goto set_status;

		err = page_to_nid(page);
set_status:
		pm->status = err;
	}

	up_read(&mm->mmap_sem);
	return 0;
}

/*
 * Move a list of pages in the address space of the currently executing
 * process.
 */
asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
			const void __user * __user *pages,
			const int __user *nodes,
			int __user *status, int flags)
{
	int err = 0;
	int i;
	struct task_struct *task;
	nodemask_t task_nodes;
	struct mm_struct *mm;
	struct page_to_node *pm = NULL;

	/* Check flags */
	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
		return -EINVAL;

	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
		return -EPERM;

	/* Find the mm_struct */
	read_lock(&tasklist_lock);
1004
	task = pid ? find_task_by_vpid(pid) : current;
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
	if (!task) {
		read_unlock(&tasklist_lock);
		return -ESRCH;
	}
	mm = get_task_mm(task);
	read_unlock(&tasklist_lock);

	if (!mm)
		return -EINVAL;

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser privileges or the same
	 * userid as the target process.
	 */
	if ((current->euid != task->suid) && (current->euid != task->uid) &&
	    (current->uid != task->suid) && (current->uid != task->uid) &&
	    !capable(CAP_SYS_NICE)) {
		err = -EPERM;
		goto out2;
	}

1028 1029 1030 1031 1032
 	err = security_task_movememory(task);
 	if (err)
 		goto out2;


1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	task_nodes = cpuset_mems_allowed(task);

	/* Limit nr_pages so that the multiplication may not overflow */
	if (nr_pages >= ULONG_MAX / sizeof(struct page_to_node) - 1) {
		err = -E2BIG;
		goto out2;
	}

	pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node));
	if (!pm) {
		err = -ENOMEM;
		goto out2;
	}

	/*
	 * Get parameters from user space and initialize the pm
	 * array. Return various errors if the user did something wrong.
	 */
	for (i = 0; i < nr_pages; i++) {
A
Al Viro 已提交
1052
		const void __user *p;
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065

		err = -EFAULT;
		if (get_user(p, pages + i))
			goto out;

		pm[i].addr = (unsigned long)p;
		if (nodes) {
			int node;

			if (get_user(node, nodes + i))
				goto out;

			err = -ENODEV;
1066
			if (!node_state(node, N_HIGH_MEMORY))
1067 1068 1069 1070 1071 1072 1073
				goto out;

			err = -EACCES;
			if (!node_isset(node, task_nodes))
				goto out;

			pm[i].node = node;
1074 1075
		} else
			pm[i].node = 0;	/* anything to not match MAX_NUMNODES */
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
	}
	/* End marker */
	pm[nr_pages].node = MAX_NUMNODES;

	if (nodes)
		err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL);
	else
		err = do_pages_stat(mm, pm);

	if (err >= 0)
		/* Return status information */
		for (i = 0; i < nr_pages; i++)
			if (put_user(pm[i].status, status + i))
				err = -EFAULT;

out:
	vfree(pm);
out2:
	mmput(mm);
	return err;
}

1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
/*
 * Call migration functions in the vma_ops that may prepare
 * memory in a vm for migration. migration functions may perform
 * the migration for vmas that do not have an underlying page struct.
 */
int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
	const nodemask_t *from, unsigned long flags)
{
 	struct vm_area_struct *vma;
 	int err = 0;

 	for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
 		if (vma->vm_ops && vma->vm_ops->migrate) {
 			err = vma->vm_ops->migrate(vma, to, from, flags);
 			if (err)
 				break;
 		}
 	}
 	return err;
}
1118
#endif