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/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;

	/*
	 * 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);

	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