migrate.c 14.7 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 18
/*
 * 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>
#include <linux/pagemap.h>
19
#include <linux/buffer_head.h>
C
Christoph Lameter 已提交
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
#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>
#include <linux/swapops.h>

#include "internal.h"

/* The maximum number of pages to take off the LRU for migration */
#define MIGRATE_CHUNK_SIZE 256

#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);
		if (PageLRU(page)) {
			ret = 0;
			get_page(page);
			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;
}

/*
 * migrate_prep() needs to be called after we have compiled the list of pages
 * to be migrated using isolate_lru_page() but before we begin a series of calls
 * to migrate_pages().
 */
int migrate_prep(void)
{
	/* Must have swap device for migration */
	if (nr_swap_pages <= 0)
		return -ENODEV;

	/*
	 * 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)
{
	list_del(&page->lru);
	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) {
		move_to_lru(page);
		count++;
	}
	return count;
}

/*
 * swapout a single page
 * page is locked upon entry, unlocked on exit
 */
static int swap_page(struct page *page)
{
	struct address_space *mapping = page_mapping(page);

	if (page_mapped(page) && mapping)
		if (try_to_unmap(page, 1) != SWAP_SUCCESS)
			goto unlock_retry;

	if (PageDirty(page)) {
		/* Page is dirty, try to write it out here */
		switch(pageout(page, mapping)) {
		case PAGE_KEEP:
		case PAGE_ACTIVATE:
			goto unlock_retry;

		case PAGE_SUCCESS:
			goto retry;

		case PAGE_CLEAN:
			; /* try to free the page below */
		}
	}

	if (PagePrivate(page)) {
		if (!try_to_release_page(page, GFP_KERNEL) ||
		    (!mapping && page_count(page) == 1))
			goto unlock_retry;
	}

	if (remove_mapping(mapping, page)) {
		/* Success */
		unlock_page(page);
		return 0;
	}

unlock_retry:
	unlock_page(page);

retry:
	return -EAGAIN;
}

/*
169
 * Replace the page in the mapping.
170 171 172 173 174
 *
 * 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
175
 */
176
static int migrate_page_move_mapping(struct page *newpage,
177
				struct page *page)
C
Christoph Lameter 已提交
178 179 180 181
{
	struct address_space *mapping = page_mapping(page);
	struct page **radix_pointer;

182
	if (!mapping)
C
Christoph Lameter 已提交
183 184 185 186 187 188 189 190
		return -EAGAIN;

	write_lock_irq(&mapping->tree_lock);

	radix_pointer = (struct page **)radix_tree_lookup_slot(
						&mapping->page_tree,
						page_index(page));

191 192
	if (!page_mapping(page) ||
			page_count(page) != 2 + !!PagePrivate(page) ||
C
Christoph Lameter 已提交
193 194
			*radix_pointer != page) {
		write_unlock_irq(&mapping->tree_lock);
195
		return -EAGAIN;
C
Christoph Lameter 已提交
196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
	}

	/*
	 * Now we know that no one else is looking at the page.
	 *
	 * Certain minimal information about a page must be available
	 * in order for other subsystems to properly handle the page if they
	 * find it through the radix tree update before we are finished
	 * copying the page.
	 */
	get_page(newpage);
	newpage->index = page->index;
	newpage->mapping = page->mapping;
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}

	*radix_pointer = newpage;
	__put_page(page);
	write_unlock_irq(&mapping->tree_lock);

	return 0;
}

/*
 * Copy the page to its new location
 */
224
static void migrate_page_copy(struct page *newpage, struct page *page)
C
Christoph Lameter 已提交
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
{
	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);
 	}

	ClearPageSwapCache(page);
	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);
}

260 261 262 263 264 265 266 267 268 269 270
/************************************************************
 *                    Migration functions
 ***********************************************************/

/* Always fail migration. Used for mappings that are not movable */
int fail_migrate_page(struct page *newpage, struct page *page)
{
	return -EIO;
}
EXPORT_SYMBOL(fail_migrate_page);

C
Christoph Lameter 已提交
271 272 273 274 275 276 277 278 279 280 281 282
/*
 * Common logic to directly migrate a single page suitable for
 * pages that do not use PagePrivate.
 *
 * Pages are locked upon entry and exit.
 */
int migrate_page(struct page *newpage, struct page *page)
{
	int rc;

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

283
	rc = migrate_page_move_mapping(newpage, page);
C
Christoph Lameter 已提交
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302

	if (rc)
		return rc;

	migrate_page_copy(newpage, page);

	/*
	 * Remove auxiliary swap entries and replace
	 * them with real ptes.
	 *
	 * Note that a real pte entry will allow processes that are not
	 * waiting on the page lock to use the new page via the page tables
	 * before the new page is unlocked.
	 */
	remove_from_swap(newpage);
	return 0;
}
EXPORT_SYMBOL(migrate_page);

303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
/*
 * Migration function for pages with buffers. This function can only be used
 * if the underlying filesystem guarantees that no other references to "page"
 * exist.
 */
int buffer_migrate_page(struct page *newpage, struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct buffer_head *bh, *head;
	int rc;

	if (!mapping)
		return -EAGAIN;

	if (!page_has_buffers(page))
		return migrate_page(newpage, page);

	head = page_buffers(page);

322
	rc = migrate_page_move_mapping(newpage, page);
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363

	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);

C
Christoph Lameter 已提交
364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
/*
 * migrate_pages
 *
 * Two lists are passed to this function. The first list
 * contains the pages isolated from the LRU to be migrated.
 * The second list contains new pages that the pages isolated
 * can be moved to. If the second list is NULL then all
 * pages are swapped out.
 *
 * The function returns after 10 attempts or if no pages
 * are movable anymore because to has become empty
 * or no retryable pages exist anymore.
 *
 * Return: Number of pages not migrated when "to" ran empty.
 */
int migrate_pages(struct list_head *from, struct list_head *to,
		  struct list_head *moved, struct list_head *failed)
{
	int retry;
	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;

redo:
	retry = 0;

	list_for_each_entry_safe(page, page2, from, lru) {
		struct page *newpage = NULL;
		struct address_space *mapping;

		cond_resched();

		rc = 0;
		if (page_count(page) == 1)
			/* page was freed from under us. So we are done. */
			goto next;

		if (to && list_empty(to))
			break;

		/*
		 * Skip locked pages during the first two passes to give the
		 * functions holding the lock time to release the page. Later we
		 * use lock_page() to have a higher chance of acquiring the
		 * lock.
		 */
		rc = -EAGAIN;
		if (pass > 2)
			lock_page(page);
		else
			if (TestSetPageLocked(page))
				goto next;

		/*
		 * Only wait on writeback if we have already done a pass where
		 * we we may have triggered writeouts for lots of pages.
		 */
		if (pass > 0) {
			wait_on_page_writeback(page);
		} else {
			if (PageWriteback(page))
				goto unlock_page;
		}

		/*
		 * Anonymous pages must have swap cache references otherwise
		 * the information contained in the page maps cannot be
		 * preserved.
		 */
		if (PageAnon(page) && !PageSwapCache(page)) {
			if (!add_to_swap(page, GFP_KERNEL)) {
				rc = -ENOMEM;
				goto unlock_page;
			}
		}

		if (!to) {
			rc = swap_page(page);
			goto next;
		}

		newpage = lru_to_page(to);
		lock_page(newpage);

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
		/*
		 * Establish swap ptes for anonymous pages or destroy pte
		 * maps for files.
		 *
		 * In order to reestablish file backed mappings the fault handlers
		 * will take the radix tree_lock which may then be used to stop
	  	 * processses from accessing this page until the new page is ready.
		 *
		 * A process accessing via a swap pte (an anonymous page) will take a
		 * page_lock on the old page which will block the process until the
		 * migration attempt is complete. At that time the PageSwapCache bit
		 * will be examined. If the page was migrated then the PageSwapCache
		 * bit will be clear and the operation to retrieve the page will be
		 * retried which will find the new page in the radix tree. Then a new
		 * direct mapping may be generated based on the radix tree contents.
		 *
		 * If the page was not migrated then the PageSwapCache bit
		 * is still set and the operation may continue.
		 */
		rc = -EPERM;
		if (try_to_unmap(page, 1) == SWAP_FAIL)
			/* A vma has VM_LOCKED set -> permanent failure */
			goto unlock_both;

		rc = -EAGAIN;
		if (page_mapped(page))
			goto unlock_both;
C
Christoph Lameter 已提交
481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649
		/*
		 * Pages are properly locked and writeback is complete.
		 * Try to migrate the page.
		 */
		mapping = page_mapping(page);
		if (!mapping)
			goto unlock_both;

		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(newpage, page);
			goto unlock_both;
                }

		/*
		 * Default handling if a filesystem does not provide
		 * a migration function. We can only migrate clean
		 * pages so try to write out any dirty pages first.
		 */
		if (PageDirty(page)) {
			switch (pageout(page, mapping)) {
			case PAGE_KEEP:
			case PAGE_ACTIVATE:
				goto unlock_both;

			case PAGE_SUCCESS:
				unlock_page(newpage);
				goto next;

			case PAGE_CLEAN:
				; /* try to migrate the page below */
			}
                }

		/*
		 * Buffers are managed in a filesystem specific way.
		 * We must have no buffers or drop them.
		 */
		if (!page_has_buffers(page) ||
		    try_to_release_page(page, GFP_KERNEL)) {
			rc = migrate_page(newpage, page);
			goto unlock_both;
		}

		/*
		 * On early passes with mapped pages simply
		 * retry. There may be a lock held for some
		 * buffers that may go away. Later
		 * swap them out.
		 */
		if (pass > 4) {
			/*
			 * Persistently unable to drop buffers..... As a
			 * measure of last resort we fall back to
			 * swap_page().
			 */
			unlock_page(newpage);
			newpage = NULL;
			rc = swap_page(page);
			goto next;
		}

unlock_both:
		unlock_page(newpage);

unlock_page:
		unlock_page(page);

next:
		if (rc == -EAGAIN) {
			retry++;
		} else if (rc) {
			/* Permanent failure */
			list_move(&page->lru, failed);
			nr_failed++;
		} else {
			if (newpage) {
				/* Successful migration. Return page to LRU */
				move_to_lru(newpage);
			}
			list_move(&page->lru, moved);
		}
	}
	if (retry && pass++ < 10)
		goto redo;

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

	return nr_failed + retry;
}

/*
 * Migrate the list 'pagelist' of pages to a certain destination.
 *
 * Specify destination with either non-NULL vma or dest_node >= 0
 * Return the number of pages not migrated or error code
 */
int migrate_pages_to(struct list_head *pagelist,
			struct vm_area_struct *vma, int dest)
{
	LIST_HEAD(newlist);
	LIST_HEAD(moved);
	LIST_HEAD(failed);
	int err = 0;
	unsigned long offset = 0;
	int nr_pages;
	struct page *page;
	struct list_head *p;

redo:
	nr_pages = 0;
	list_for_each(p, pagelist) {
		if (vma) {
			/*
			 * The address passed to alloc_page_vma is used to
			 * generate the proper interleave behavior. We fake
			 * the address here by an increasing offset in order
			 * to get the proper distribution of pages.
			 *
			 * No decision has been made as to which page
			 * a certain old page is moved to so we cannot
			 * specify the correct address.
			 */
			page = alloc_page_vma(GFP_HIGHUSER, vma,
					offset + vma->vm_start);
			offset += PAGE_SIZE;
		}
		else
			page = alloc_pages_node(dest, GFP_HIGHUSER, 0);

		if (!page) {
			err = -ENOMEM;
			goto out;
		}
		list_add_tail(&page->lru, &newlist);
		nr_pages++;
		if (nr_pages > MIGRATE_CHUNK_SIZE)
			break;
	}
	err = migrate_pages(pagelist, &newlist, &moved, &failed);

	putback_lru_pages(&moved);	/* Call release pages instead ?? */

	if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist))
		goto redo;
out:
	/* Return leftover allocated pages */
	while (!list_empty(&newlist)) {
		page = list_entry(newlist.next, struct page, lru);
		list_del(&page->lru);
		__free_page(page);
	}
	list_splice(&failed, pagelist);
	if (err < 0)
		return err;

	/* Calculate number of leftover pages */
	nr_pages = 0;
	list_for_each(p, pagelist)
		nr_pages++;
	return nr_pages;
}