*/
#include <linux/migrate.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
ptep = pte_offset_map(pmd, addr);
- if (!is_swap_pte(*ptep)) {
- pte_unmap(ptep);
- goto out;
- }
+ /*
+ * 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);
}
*/
__dec_zone_page_state(page, NR_FILE_PAGES);
__inc_zone_page_state(newpage, NR_FILE_PAGES);
- if (PageSwapBacked(page)) {
+ if (!PageSwapCache(page) && PageSwapBacked(page)) {
__dec_zone_page_state(page, NR_SHMEM);
__inc_zone_page_state(newpage, NR_SHMEM);
}
* 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.
+ * Whereas only part of our page may be dirty.
*/
__set_page_dirty_nobuffers(newpage);
}
* == 0 - success
*/
static int move_to_new_page(struct page *newpage, struct page *page,
- int remap_swapcache)
+ int remap_swapcache, bool sync)
{
struct address_space *mapping;
int rc;
mapping = page_mapping(page);
if (!mapping)
rc = migrate_page(mapping, newpage, page);
- else if (mapping->a_ops->migratepage)
+ else {
/*
- * 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.
+ * Do not writeback pages if !sync and migratepage is
+ * not pointing to migrate_page() which is nonblocking
+ * (swapcache/tmpfs uses migratepage = migrate_page).
*/
- rc = mapping->a_ops->migratepage(mapping,
- newpage, page);
- else
- rc = fallback_migrate_page(mapping, newpage, page);
+ if (PageDirty(page) && !sync &&
+ mapping->a_ops->migratepage != migrate_page)
+ rc = -EBUSY;
+ 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.
+ */
+ rc = mapping->a_ops->migratepage(mapping,
+ newpage, page);
+ else
+ rc = fallback_migrate_page(mapping, newpage, page);
+ }
if (rc) {
newpage->mapping = NULL;
return rc;
}
-/*
- * Obtain the lock on page, remove all ptes and migrate the page
- * to the newly allocated page in newpage.
- */
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
- struct page *page, int force, bool offlining, bool sync)
+static int __unmap_and_move(struct page *page, struct page *newpage,
+ int force, bool offlining, bool sync)
{
- int rc = 0;
- int *result = NULL;
- struct page *newpage = get_new_page(page, private, &result);
+ int rc = -EAGAIN;
int remap_swapcache = 1;
int charge = 0;
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *mem;
struct anon_vma *anon_vma = NULL;
- if (!newpage)
- return -ENOMEM;
-
- if (page_count(page) == 1) {
- /* page was freed from under us. So we are done. */
- goto move_newpage;
- }
- if (unlikely(PageTransHuge(page)))
- if (unlikely(split_huge_page(page)))
- goto move_newpage;
-
- /* prepare cgroup just returns 0 or -ENOMEM */
- rc = -EAGAIN;
-
if (!trylock_page(page)) {
- if (!force)
- goto move_newpage;
+ if (!force || !sync)
+ goto out;
/*
* It's not safe for direct compaction to call lock_page.
* altogether.
*/
if (current->flags & PF_MEMALLOC)
- goto move_newpage;
+ goto out;
lock_page(page);
}
}
/* charge against new page */
- charge = mem_cgroup_prepare_migration(page, newpage, &mem);
+ charge = mem_cgroup_prepare_migration(page, newpage, &mem, GFP_KERNEL);
if (charge == -ENOMEM) {
rc = -ENOMEM;
goto unlock;
BUG_ON(charge);
if (PageWriteback(page)) {
- if (!force || !sync)
+ /*
+ * For !sync, there is no point retrying as the retry loop
+ * is expected to be too short for PageWriteback to be cleared
+ */
+ if (!sync) {
+ rc = -EBUSY;
+ goto uncharge;
+ }
+ if (!force)
goto uncharge;
wait_on_page_writeback(page);
}
* Only page_lock_anon_vma() understands the subtleties of
* getting a hold on an anon_vma from outside one of its mms.
*/
- anon_vma = page_lock_anon_vma(page);
+ anon_vma = page_get_anon_vma(page);
if (anon_vma) {
/*
- * Take a reference count on the anon_vma if the
- * page is mapped so that it is guaranteed to
- * exist when the page is remapped later
+ * Anon page
*/
- get_anon_vma(anon_vma);
- page_unlock_anon_vma(anon_vma);
} else if (PageSwapCache(page)) {
/*
* We cannot be sure that the anon_vma of an unmapped
skip_unmap:
if (!page_mapped(page))
- rc = move_to_new_page(newpage, page, remap_swapcache);
+ rc = move_to_new_page(newpage, page, remap_swapcache, sync);
if (rc && remap_swapcache)
remove_migration_ptes(page, page);
/* Drop an anon_vma reference if we took one */
if (anon_vma)
- drop_anon_vma(anon_vma);
+ put_anon_vma(anon_vma);
uncharge:
if (!charge)
- mem_cgroup_end_migration(mem, page, newpage);
+ mem_cgroup_end_migration(mem, page, newpage, rc == 0);
unlock:
unlock_page(page);
+out:
+ return rc;
+}
+
+/*
+ * Obtain the lock on page, remove all ptes and migrate the page
+ * to the newly allocated page in newpage.
+ */
+static int unmap_and_move(new_page_t get_new_page, unsigned long private,
+ struct page *page, int force, bool offlining, bool sync)
+{
+ int rc = 0;
+ int *result = NULL;
+ struct page *newpage = get_new_page(page, private, &result);
+
+ if (!newpage)
+ return -ENOMEM;
+
+ if (page_count(page) == 1) {
+ /* page was freed from under us. So we are done. */
+ goto out;
+ }
+
+ if (unlikely(PageTransHuge(page)))
+ if (unlikely(split_huge_page(page)))
+ goto out;
+ rc = __unmap_and_move(page, newpage, force, offlining, sync);
+out:
if (rc != -EAGAIN) {
- /*
- * A page that has been migrated has all references
- * removed and will be freed. A page that has not been
- * migrated will have kepts its references and be
- * restored.
- */
- list_del(&page->lru);
+ /*
+ * A page that has been migrated has all references
+ * removed and will be freed. A page that has not been
+ * migrated will have kepts its references and be
+ * restored.
+ */
+ list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
putback_lru_page(page);
}
-
-move_newpage:
-
/*
* Move the new page to the LRU. If migration was not successful
* then this will free the page.
*/
putback_lru_page(newpage);
-
if (result) {
if (rc)
*result = rc;
lock_page(hpage);
}
- if (PageAnon(hpage)) {
- anon_vma = page_lock_anon_vma(hpage);
- if (anon_vma) {
- get_anon_vma(anon_vma);
- page_unlock_anon_vma(anon_vma);
- }
- }
+ if (PageAnon(hpage))
+ anon_vma = page_get_anon_vma(hpage);
try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
if (!page_mapped(hpage))
- rc = move_to_new_page(new_hpage, hpage, 1);
+ rc = move_to_new_page(new_hpage, hpage, 1, sync);
if (rc)
remove_migration_ptes(hpage, hpage);
if (anon_vma)
- drop_anon_vma(anon_vma);
-out:
+ put_anon_vma(anon_vma);
unlock_page(hpage);
+out:
if (rc != -EAGAIN) {
list_del(&hpage->lru);
put_page(hpage);
* are movable anymore because to has become empty
* or no retryable pages exist anymore.
* Caller should call putback_lru_pages to return pages to the LRU
- * or free list.
+ * or free list only if ret != 0.
*
* Return: Number of pages not migrated or error code.
*/
}
rc = 0;
out:
-
- list_for_each_entry_safe(page, page2, from, lru)
- put_page(page);
-
if (rc)
return rc;
return -EPERM;
/* Find the mm_struct */
- read_lock(&tasklist_lock);
+ rcu_read_lock();
task = pid ? find_task_by_vpid(pid) : current;
if (!task) {
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return -ESRCH;
}
mm = get_task_mm(task);
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
if (!mm)
return -EINVAL;