* IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
* Hirokazu Takahashi <taka@valinux.co.jp>
* Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter <clameter@sgi.com>
+ * Christoph Lameter
*/
#include <linux/migrate.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))
-/*
- * 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) && get_page_unless_zero(page)) {
- 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;
-}
-
/*
* migrate_prep() needs to be called before we start compiling a list of pages
* to be migrated using isolate_lru_page().
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.
+ * 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.
*/
list_for_each_entry_safe(page, page2, l, lru) {
list_del(&page->lru);
- move_to_lru(page);
+ putback_lru_page(page);
count++;
}
return count;
}
-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
*/
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))
page = migration_entry_to_page(entry);
- get_page(page);
+ /*
+ * 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);
static int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page)
{
+ int expected_count;
void **pslot;
if (!mapping) {
return 0;
}
- write_lock_irq(&mapping->tree_lock);
+ spin_lock_irq(&mapping->tree_lock);
pslot = radix_tree_lookup_slot(&mapping->page_tree,
page_index(page));
- if (page_count(page) != 2 + !!PagePrivate(page) ||
+ expected_count = 2 + !!PagePrivate(page);
+ if (page_count(page) != expected_count ||
(struct page *)radix_tree_deref_slot(pslot) != page) {
- write_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
+ return -EAGAIN;
+ }
+
+ if (!page_freeze_refs(page, expected_count)) {
+ spin_unlock_irq(&mapping->tree_lock);
return -EAGAIN;
}
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.
__dec_zone_page_state(page, NR_FILE_PAGES);
__inc_zone_page_state(newpage, NR_FILE_PAGES);
- write_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
+ if (!PageSwapCache(newpage))
+ mem_cgroup_uncharge_cache_page(page);
return 0;
}
SetPageReferenced(newpage);
if (PageUptodate(page))
SetPageUptodate(newpage);
- if (PageActive(page))
+ if (TestClearPageActive(page)) {
+ VM_BUG_ON(PageUnevictable(page));
SetPageActive(newpage);
+ } else
+ unevictable_migrate_page(newpage, page);
if (PageChecked(page))
SetPageChecked(newpage);
if (PageMappedToDisk(page))
if (PageDirty(page)) {
clear_page_dirty_for_io(page);
- set_page_dirty(newpage);
+ /*
+ * 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);
}
#ifdef CONFIG_SWAP
ClearPageSwapCache(page);
#endif
- ClearPageActive(page);
ClearPagePrivate(page);
set_page_private(page, 0);
page->mapping = NULL;
*
* 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)
{
* establishing additional references. We are the only one
* holding a reference to the new page at this point.
*/
- if (TestSetPageLocked(newpage))
+ 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)
else
rc = fallback_migrate_page(mapping, newpage, page);
- if (!rc)
+ if (!rc) {
remove_migration_ptes(page, newpage);
- else
+ } else
newpage->mapping = NULL;
unlock_page(newpage);
int *result = NULL;
struct page *newpage = get_new_page(page, private, &result);
int rcu_locked = 0;
+ int charge = 0;
if (!newpage)
return -ENOMEM;
- if (page_count(page) == 1)
+ if (page_count(page) == 1) {
/* page was freed from under us. So we are done. */
goto move_newpage;
+ }
+
+ charge = mem_cgroup_prepare_migration(page, newpage);
+ if (charge == -ENOMEM) {
+ rc = -ENOMEM;
+ goto move_newpage;
+ }
+ /* prepare cgroup just returns 0 or -ENOMEM */
+ BUG_ON(charge);
rc = -EAGAIN;
- if (TestSetPageLocked(page)) {
+ if (!trylock_page(page)) {
if (!force)
goto move_newpage;
lock_page(page);
rcu_read_lock();
rcu_locked = 1;
}
+
/*
- * 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.
+ * Corner case handling:
+ * 1. When a new swap-cache page is read into, it is added to the LRU
+ * and treated as swapcache but it has no rmap yet.
+ * Calling try_to_unmap() against a page->mapping==NULL page will
+ * trigger a BUG. So handle it here.
+ * 2. An orphaned page (see truncate_complete_page) might have
+ * fs-private metadata. The page can be picked up due to memory
+ * offlining. Everywhere else except page reclaim, the page is
+ * invisible to the vm, so the page can not be migrated. So try to
+ * free the metadata, so the page can be freed.
*/
- if (!page->mapping)
+ if (!page->mapping) {
+ if (!PageAnon(page) && PagePrivate(page)) {
+ /*
+ * Go direct to try_to_free_buffers() here because
+ * a) that's what try_to_release_page() would do anyway
+ * b) we may be under rcu_read_lock() here, so we can't
+ * use GFP_KERNEL which is what try_to_release_page()
+ * needs to be effective.
+ */
+ try_to_free_buffers(page);
+ }
goto rcu_unlock;
+ }
+
/* Establish migration ptes or remove ptes */
try_to_unmap(page, 1);
rcu_read_unlock();
unlock:
-
unlock_page(page);
if (rc != -EAGAIN) {
* restored.
*/
list_del(&page->lru);
- move_to_lru(page);
+ putback_lru_page(page);
}
move_newpage:
+ if (!charge)
+ mem_cgroup_end_migration(newpage);
+
/*
* Move the new page to the LRU. If migration was not successful
* then this will free the page.
*/
- move_to_lru(newpage);
+ putback_lru_page(newpage);
+
if (result) {
if (rc)
*result = rc;
goto set_status;
page = follow_page(vma, pp->addr, FOLL_GET);
+
+ err = PTR_ERR(page);
+ if (IS_ERR(page))
+ goto set_status;
+
err = -ENOENT;
if (!page)
goto set_status;
!migrate_all)
goto put_and_set;
- err = isolate_lru_page(page, &pagelist);
+ err = isolate_lru_page(page);
+ if (!err)
+ list_add_tail(&page->lru, &pagelist);
put_and_set:
/*
* Either remove the duplicate refcount from
goto set_status;
page = follow_page(vma, pm->addr, 0);
+
+ err = PTR_ERR(page);
+ if (IS_ERR(page))
+ goto set_status;
+
err = -ENOENT;
/* Use PageReserved to check for zero page */
if (!page || PageReserved(page))
mmput(mm);
return err;
}
-#endif
/*
* Call migration functions in the vma_ops that may prepare
}
return err;
}
+#endif