path: root/mm/migrate.c

/*
 * 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
 */

#include <linux/migrate.h>
#include <linux/export.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/ksm.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 <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>

#include <asm/tlbflush.h>

#define CREATE_TRACE_POINTS
#include <trace/events/migrate.h>

#include "internal.h"

/*
 * migrate_prep() needs to be called before we start compiling a list of pages
 * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is
 * undesirable, use migrate_prep_local()
 */
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;
}

/* Do the necessary work of migrate_prep but not if it involves other CPUs */
int migrate_prep_local(void)
{
	lru_add_drain();

	return 0;
}

/*
 * Add isolated pages on the list back to the LRU under page lock
 * to avoid leaking evictable pages back onto unevictable list.
 */
void putback_lru_pages(struct list_head *l)
{
	struct page *page;
	struct page *page2;

	list_for_each_entry_safe(page, page2, l, lru) {
		list_del(&page->lru);
		dec_zone_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		putback_lru_page(page);
	}
}

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

	if (unlikely(PageHuge(new))) {
		ptep = huge_pte_offset(mm, addr);
		if (!ptep)
			goto out;
		ptl = &mm->page_table_lock;
	} else {
		pgd = pgd_offset(mm, addr);
		if (!pgd_present(*pgd))
			goto out;

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

		pmd = pmd_offset(pud, addr);
		if (pmd_trans_huge(*pmd))
			goto out;
		if (!pmd_present(*pmd))
			goto out;

		ptep = pte_offset_map(pmd, addr);

		/*
		 * Peek to check is_swap_pte() before taking ptlock?  No, we
		 * can race mremap's move_ptes(), which skips anon_vma lock.
		 */

		ptl = pte_lockptr(mm, pmd);
	}

 	spin_lock(ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto unlock;

	entry = pte_to_swp_entry(pte);

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

	get_page(new);
	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
	if (is_write_migration_entry(entry))
		pte = pte_mkwrite(pte);
#ifdef CONFIG_HUGETLB_PAGE
	if (PageHuge(new))
		pte = pte_mkhuge(pte);
#endif
	flush_cache_page(vma, addr, pte_pfn(pte));
	set_pte_at(mm, addr, ptep, pte);

	if (PageHuge(new)) {
		if (PageAnon(new))
			hugepage_add_anon_rmap(new, vma, addr);
		else
			page_dup_rmap(new);
	} else 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, ptep);
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return SWAP_AGAIN;
}

/*
 * 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)
{
	rmap_walk(new, remove_migration_pte, old);
}

/*
 * 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.
 */
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);
}

#ifdef CONFIG_BLOCK
/* Returns true if all buffers are successfully locked */
static bool buffer_migrate_lock_buffers(struct buffer_head *head,
							enum migrate_mode mode)
{
	struct buffer_head *bh = head;

	/* Simple case, sync compaction */
	if (mode != MIGRATE_ASYNC) {
		do {
			get_bh(bh);
			lock_buffer(bh);
			bh = bh->b_this_page;

		} while (bh != head);

		return true;
	}

	/* async case, we cannot block on lock_buffer so use trylock_buffer */
	do {
		get_bh(bh);
		if (!trylock_buffer(bh)) {
			/*
			 * We failed to lock the buffer and cannot stall in
			 * async migration. Release the taken locks
			 */
			struct buffer_head *failed_bh = bh;
			put_bh(failed_bh);
			bh = head;
			while (bh != failed_bh) {
				unlock_buffer(bh);
				put_bh(bh);
				bh = bh->b_this_page;
			}
			return false;
		}

		bh = bh->b_this_page;
	} while (bh != head);
	return true;
}
#else
static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
							enum migrate_mode mode)
{
	return true;
}
#endif /* CONFIG_BLOCK */

/*
 * 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/PagePrivate2 set.
 */
static int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page,
		struct buffer_head *head, enum migrate_mode mode)
{
	int expected_count = 0;
	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 + page_has_private(page);
	if (page_count(page) != expected_count ||
		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

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

	/*
	 * In the async migration case of moving a page with buffers, lock the
	 * buffers using trylock before the mapping is moved. If the mapping
	 * was moved, we later failed to lock the buffers and could not move
	 * the mapping back due to an elevated page count, we would have to
	 * block waiting on other references to be dropped.
	 */
	if (mode == MIGRATE_ASYNC && head &&
			!buffer_migrate_lock_buffers(head, mode)) {
		page_unfreeze_refs(page, expected_count);
		spin_unlock_irq(&mapping->tree_lock);
		retur