migrate.c 22.5 KB
Newer Older
C
Christoph Lameter 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * 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>
 * Christoph Lameter <clameter@sgi.com>
 */

#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 22 23 24 25 26
#include <linux/mm_inline.h>
#include <linux/pagevec.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
27
#include <linux/writeback.h>
28 29
#include <linux/mempolicy.h>
#include <linux/vmalloc.h>
30
#include <linux/security.h>
C
Christoph Lameter 已提交
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51

#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);
52
		if (PageLRU(page) && get_page_unless_zero(page)) {
C
Christoph Lameter 已提交
53 54 55 56 57 58 59 60 61 62 63 64 65 66
			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;
}

/*
67 68
 * 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
69 70 71 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
 */
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) {
110
		list_del(&page->lru);
C
Christoph Lameter 已提交
111 112 113 114 115 116
		move_to_lru(page);
		count++;
	}
	return count;
}

117 118 119 120 121 122 123 124
static inline int is_swap_pte(pte_t pte)
{
	return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
}

/*
 * Restore a potential migration pte to a working pte entry
 */
125
static void remove_migration_pte(struct vm_area_struct *vma,
126 127 128 129 130 131 132 133 134
		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;
135 136 137 138
	unsigned long addr = page_address_in_vma(new, vma);

	if (addr == -EFAULT)
		return;
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174

 	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;

	get_page(new);
	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
	if (is_write_migration_entry(entry))
		pte = pte_mkwrite(pte);
	set_pte_at(mm, addr, ptep, pte);
175 176 177 178 179 180 181 182 183 184

	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);
	lazy_mmu_prot_update(pte);

185 186 187 188 189
out:
	pte_unmap_unlock(ptep, ptl);
}

/*
190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211
 * 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);
}

/*
212 213 214
 * Must hold mmap_sem lock on at least one of the vmas containing
 * the page so that the anon_vma cannot vanish.
 */
215
static void remove_anon_migration_ptes(struct page *old, struct page *new)
216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232
{
	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)
233
		remove_migration_pte(vma, old, new);
234 235 236 237

	spin_unlock(&anon_vma->lock);
}

238 239 240 241 242 243 244 245 246 247 248 249
/*
 * 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);
}

250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
/*
 * 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);

	get_page(page);
	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
285
/*
286
 * Replace the page in the mapping.
287 288 289 290 291
 *
 * 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
292
 */
293 294
static int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
295
{
296
	void **pslot;
C
Christoph Lameter 已提交
297

298
	if (!mapping) {
299
		/* Anonymous page without mapping */
300 301 302 303 304
		if (page_count(page) != 1)
			return -EAGAIN;
		return 0;
	}

C
Christoph Lameter 已提交
305 306
	write_lock_irq(&mapping->tree_lock);

307 308
	pslot = radix_tree_lookup_slot(&mapping->page_tree,
 					page_index(page));
C
Christoph Lameter 已提交
309

310
	if (page_count(page) != 2 + !!PagePrivate(page) ||
311
			(struct page *)radix_tree_deref_slot(pslot) != page) {
C
Christoph Lameter 已提交
312
		write_unlock_irq(&mapping->tree_lock);
313
		return -EAGAIN;
C
Christoph Lameter 已提交
314 315 316 317 318
	}

	/*
	 * Now we know that no one else is looking at the page.
	 */
319
	get_page(newpage);	/* add cache reference */
320
#ifdef CONFIG_SWAP
C
Christoph Lameter 已提交
321 322 323 324
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}
325
#endif
C
Christoph Lameter 已提交
326

327 328 329 330 331 332
	radix_tree_replace_slot(pslot, newpage);

	/*
	 * Drop cache reference from old page.
	 * We know this isn't the last reference.
	 */
C
Christoph Lameter 已提交
333
	__put_page(page);
334

335 336 337 338 339 340 341 342 343 344 345 346 347
	/*
	 * 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
348 349 350 351 352 353 354 355
	write_unlock_irq(&mapping->tree_lock);

	return 0;
}

/*
 * Copy the page to its new location
 */
356
static void migrate_page_copy(struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377
{
	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);
		set_page_dirty(newpage);
 	}

378
#ifdef CONFIG_SWAP
C
Christoph Lameter 已提交
379
	ClearPageSwapCache(page);
380
#endif
C
Christoph Lameter 已提交
381 382 383 384 385 386 387 388 389 390 391 392 393
	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);
}

394 395 396 397 398
/************************************************************
 *                    Migration functions
 ***********************************************************/

/* Always fail migration. Used for mappings that are not movable */
399 400
int fail_migrate_page(struct address_space *mapping,
			struct page *newpage, struct page *page)
401 402 403 404 405
{
	return -EIO;
}
EXPORT_SYMBOL(fail_migrate_page);

C
Christoph Lameter 已提交
406 407 408 409 410 411
/*
 * Common logic to directly migrate a single page suitable for
 * pages that do not use PagePrivate.
 *
 * Pages are locked upon entry and exit.
 */
412 413
int migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
414 415 416 417 418
{
	int rc;

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

419
	rc = migrate_page_move_mapping(mapping, newpage, page);
C
Christoph Lameter 已提交
420 421 422 423 424 425 426 427 428

	if (rc)
		return rc;

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

429
#ifdef CONFIG_BLOCK
430 431 432 433 434
/*
 * Migration function for pages with buffers. This function can only be used
 * if the underlying filesystem guarantees that no other references to "page"
 * exist.
 */
435 436
int buffer_migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page)
437 438 439 440 441
{
	struct buffer_head *bh, *head;
	int rc;

	if (!page_has_buffers(page))
442
		return migrate_page(mapping, newpage, page);
443 444 445

	head = page_buffers(page);

446
	rc = migrate_page_move_mapping(mapping, newpage, page);
447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486

	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);
487
#endif
488

489 490 491 492
/*
 * Writeback a page to clean the dirty state
 */
static int writeout(struct address_space *mapping, struct page *page)
493
{
494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
	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;

512
	/*
513 514 515 516 517 518
	 * 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.
519
	 */
520
	remove_migration_ptes(page, page);
521

522 523 524 525
	rc = mapping->a_ops->writepage(page, &wbc);
	if (rc < 0)
		/* I/O Error writing */
		return -EIO;
526

527 528 529 530 531 532 533 534 535 536 537 538 539 540 541
	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);
542 543 544 545 546

	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
547
	if (PagePrivate(page) &&
548 549 550 551 552 553
	    !try_to_release_page(page, GFP_KERNEL))
		return -EAGAIN;

	return migrate_page(mapping, newpage, page);
}

554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607
/*
 * 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);

	if (!rc)
		remove_migration_ptes(page, newpage);
	else
		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.
 */
608 609
static int unmap_and_move(new_page_t get_new_page, unsigned long private,
			struct page *page, int force)
610 611
{
	int rc = 0;
612 613
	int *result = NULL;
	struct page *newpage = get_new_page(page, private, &result);
614 615 616

	if (!newpage)
		return -ENOMEM;
617 618 619

	if (page_count(page) == 1)
		/* page was freed from under us. So we are done. */
620
		goto move_newpage;
621 622 623 624

	rc = -EAGAIN;
	if (TestSetPageLocked(page)) {
		if (!force)
625
			goto move_newpage;
626 627 628 629 630 631 632 633 634
		lock_page(page);
	}

	if (PageWriteback(page)) {
		if (!force)
			goto unlock;
		wait_on_page_writeback(page);
	}
	/*
635 636 637 638 639 640 641 642 643 644 645 646
	 * 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()
	 */
	rcu_read_lock();
	/*
	 * This is a corner case handling.
	 * When a new swap-cache is read into, it is linked to LRU
	 * and treated as swapcache but has no rmap yet.
	 * Calling try_to_unmap() against a page->mapping==NULL page is
	 * BUG. So handle it here.
647
	 */
648 649 650
	if (!page->mapping)
		goto rcu_unlock;
	/* Establish migration ptes or remove ptes */
651
	try_to_unmap(page, 1);
652

653 654
	if (!page_mapped(page))
		rc = move_to_new_page(newpage, page);
655 656 657

	if (rc)
		remove_migration_ptes(page, page);
658 659
rcu_unlock:
	rcu_read_unlock();
660

661
unlock:
662

663
	unlock_page(page);
664

665
	if (rc != -EAGAIN) {
666 667 668 669 670 671 672 673
 		/*
 		 * 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);
674
	}
675 676 677 678 679 680 681

move_newpage:
	/*
	 * Move the new page to the LRU. If migration was not successful
	 * then this will free the page.
	 */
	move_to_lru(newpage);
682 683 684 685 686 687
	if (result) {
		if (rc)
			*result = rc;
		else
			*result = page_to_nid(newpage);
	}
688 689 690
	return rc;
}

C
Christoph Lameter 已提交
691 692 693
/*
 * migrate_pages
 *
694 695 696
 * 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
697 698 699
 *
 * The function returns after 10 attempts or if no pages
 * are movable anymore because to has become empty
700 701
 * or no retryable pages exist anymore. All pages will be
 * retruned to the LRU or freed.
C
Christoph Lameter 已提交
702
 *
703
 * Return: Number of pages not migrated or error code.
C
Christoph Lameter 已提交
704
 */
705 706
int migrate_pages(struct list_head *from,
		new_page_t get_new_page, unsigned long private)
C
Christoph Lameter 已提交
707
{
708
	int retry = 1;
C
Christoph Lameter 已提交
709 710 711 712 713 714 715 716 717 718
	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;

719 720
	for(pass = 0; pass < 10 && retry; pass++) {
		retry = 0;
C
Christoph Lameter 已提交
721

722 723
		list_for_each_entry_safe(page, page2, from, lru) {
			cond_resched();
724

725 726
			rc = unmap_and_move(get_new_page, private,
						page, pass > 2);
727

728
			switch(rc) {
729 730
			case -ENOMEM:
				goto out;
731
			case -EAGAIN:
732
				retry++;
733 734 735 736
				break;
			case 0:
				break;
			default:
737 738
				/* Permanent failure */
				nr_failed++;
739
				break;
740
			}
C
Christoph Lameter 已提交
741 742
		}
	}
743 744
	rc = 0;
out:
C
Christoph Lameter 已提交
745 746 747
	if (!swapwrite)
		current->flags &= ~PF_SWAPWRITE;

748
	putback_lru_pages(from);
C
Christoph Lameter 已提交
749

750 751
	if (rc)
		return rc;
C
Christoph Lameter 已提交
752

753
	return nr_failed + retry;
C
Christoph Lameter 已提交
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
#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;

780 781
	return alloc_pages_node(pm->node,
				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
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
}

/*
 * 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);
814
		if (!vma || !vma_migratable(vma))
815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943
			goto set_status;

		page = follow_page(vma, pp->addr, FOLL_GET);
		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);
		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);
	task = pid ? find_task_by_pid(pid) : current;
	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;
	}

944 945 946 947 948
 	err = security_task_movememory(task);
 	if (err)
 		goto out2;


949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989
	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++) {
		const void *p;

		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;
			if (!node_online(node))
				goto out;

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

			pm[i].node = node;
990 991
		} else
			pm[i].node = 0;	/* anything to not match MAX_NUMNODES */
992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014
	}
	/* 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;
}
#endif

1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034
/*
 * 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;
}