migrate.c

最新最稳定的Linux内存管理模块源代码

/*
 * 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 <[e-mail]>
 * Hirokazu Takahashi <[e-mail]>
 * Dave Hansen <[e-mail]>
 * Christoph Lameter
 */

#include <linux/migrate.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/mm_inline.h>
#include <linux/nsproxy.h>
#include <linux/pagevec.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/writeback.h>
#include <linux/mempolicy.h>
#include <linux/vmalloc.h>
#include <linux/security.h>
#include <linux/memcontrol.h>
#include <linux/syscalls.h>

#include "internal.h"

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

/*
 * migrate_prep() needs to be called before we start compiling a list of pages
 * to be migrated using isolate_lru_page().
 */
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;
}

/*
 * Add isolated pages on the list back to the LRU under page lock
 * to avoid leaking evictable pages back onto unevictable list.
 *
 * 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) {
		list_del(&page->lru);
		putback_lru_page(page);
		count++;
	}
	return count;
}

/*
 * Restore a potential migration pte to a working pte entry
 */
static void remove_migration_pte(struct vm_area_struct *vma,
		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;
	unsigned long addr = page_address_in_vma(new, vma);

	if (addr == -EFAULT)
		return;

 	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);
	flush_cache_page(vma, addr, pte_pfn(pte));
	set_pte_at(mm, addr, ptep, pte);

	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);

out:
	pte_unmap_unlock(ptep, ptl);
}

/*
 * 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);
}

/*
 * Must hold mmap_sem lock on at least one of the vmas containing
 * the page so that the anon_vma cannot vanish.
 */
static void remove_anon_migration_ptes(struct page *old, struct page *new)
{
	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)
		remove_migration_pte(vma, old, new);

	spin_unlock(&anon_vma->lock);
}

/*
 * 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);
}

/*
 * 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);

	/*
	 * 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;
	pte_unmap_unlock(ptep, ptl);
	wait_on_page_locked(page);
	put_page(page);
	return;
out:
	pte_unmap_unlock(ptep, ptl);
}

/*
 * Replace the page in the mapping.
 *
 * 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.
 */
static int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page)
{
	int expected_count;
	void **pslot;

	if (!mapping) {
		/* Anonymous page without mapping */
		if (page_count(page) != 1)
			return -EAGAIN;
		return 0;
	}

	spin_lock_irq(&mapping->tree_lock);

	pslot = radix_tree_lookup_slot(&mapping->page_tree,
 					page_index(page));

	expected_count = 2 + !!PagePrivate(page);
	if (page_count(page) != expected_count ||
			(struct page *)radix_tree_deref_slot(pslot) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	if (!page_freeze_refs(page, expected_count)) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	/*
	 * Now we know that no one else is looking at the page.
	 */
	get_page(newpage);	/* add cache reference */
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}

	radix_tree_replace_slot(pslot, newpage);

	page_unfreeze_refs(page, expected_count);
	/*
	 * Drop cache reference from old page.
	 * We know this isn't the last reference.
	 */
	__put_page(page);

	/*
	 * 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);

	spin_unlock_irq(&mapping->tree_lock);

	return 0;
}

/*
 * Copy the page to its new location
 */
static void migrate_page_copy(struct page *newpage, struct page *page)
{
	int anon;

	copy_highpage(newpage, page);

	if (PageError(page))
		SetPageError(newpage);
	if (PageReferenced(page))
		SetPageReferenced(newpage);
	if (PageUptodate(page))
		SetPageUptodate(newpage);
	if (TestClearPageActive(page)) {
		VM_BUG_ON(PageUnevictable(page));
		SetPageActive(newpage);
	} else
		unevictable_migrate_page(newpage, page);
	if (PageChecked(page))
		SetPageChecked(newpage);
	if (PageMappedToDisk(page))
		SetPageMappedToDisk(newpage);

	if (PageDirty(page)) {
		clear_page_dirty_for_io(page);
		/*
		 * 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);
 	}

	mlock_migrate_page(newpage, page);

	ClearPageSwapCache(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);
	/* page->mapping contains a flag for PageAnon() */
	anon = PageAnon(page);
	page->mapping = NULL;

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

/************************************************************
 *                    Migration functions
 ***********************************************************/

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

/*
 * 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 address_space *mapping,
		struct page *newpage, struct page *page)
{
	int rc;

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

	rc = migrate_page_move_mapping(mapping, newpage, page);

	if (rc)
		return rc;

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

#ifdef CONFIG_BLOCK
/*
 * 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 address_space *mapping,
		struct page *newpage, struct page *page)
{
	struct buffer_head *bh, *head;
	int rc;

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

	head = page_buffers(page);

	rc = migrate_page_move_mapping(mapping, newpage, page);

	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);
#endif

/*
 * Writeback a page to clean the dirty state
 */
static int writeout(struct address_space *mapping, struct page *page)
{
	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;

	/*
	 * 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.
	 */
	remove_migration_ptes(page, page);

	rc = mapping->a_ops->writepage(page, &wbc);

	if (rc != AOP_WRITEPAGE_ACTIVATE)
		/* unlocked. Relock */
		lock_page(page);

	return (rc < 0) ? -EIO : -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);

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

	return migrate_page(mapping, newpage, page);
}

/*
 * 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.
 *
 * Return value:
 *   < 0 - error code
 *  == 0 - success
 */
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 (!trylock_page(newpage))
		BUG();

	/* Prepare mapping for the new page.*/
	newpage->index = page->index;
	newpage->mapping = page->mapping;
	if (PageSwapBacked(page))
		SetPageSwapBacked(newpage);

	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.