mm: add replace_page_cache_page() function

This function basically does:

     remove_from_page_cache(old);
     page_cache_release(old);
     add_to_page_cache_locked(new);

Except it does this atomically, so there's no possibility for the "add" to
fail because of a race.

If memory cgroups are enabled, then the memory cgroup charge is also moved
from the old page to the new.

This function is currently used by fuse to move pages into the page cache
on read, instead of copying the page contents.

[minchan.kim@gmail.com: add freepage() hook to replace_page_cache_page()]
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 73 insertions, 3 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 312b6eb..c1459f2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -387,6 +387,76 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 EXPORT_SYMBOL(filemap_write_and_wait_range);
 
 /**
+ * replace_page_cache_page - replace a pagecache page with a new one
+ * @old:	page to be replaced
+ * @new:	page to replace with
+ * @gfp_mask:	allocation mode
+ *
+ * This function replaces a page in the pagecache with a new one.  On
+ * success it acquires the pagecache reference for the new page and
+ * drops it for the old page.  Both the old and new pages must be
+ * locked.  This function does not add the new page to the LRU, the
+ * caller must do that.
+ *
+ * The remove + add is atomic.  The only way this function can fail is
+ * memory allocation failure.
+ */
+int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
+{
+	int error;
+	struct mem_cgroup *memcg = NULL;
+
+	VM_BUG_ON(!PageLocked(old));
+	VM_BUG_ON(!PageLocked(new));
+	VM_BUG_ON(new->mapping);
+
+	/*
+	 * This is not page migration, but prepare_migration and
+	 * end_migration does enough work for charge replacement.
+	 *
+	 * In the longer term we probably want a specialized function
+	 * for moving the charge from old to new in a more efficient
+	 * manner.
+	 */
+	error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask);
+	if (error)
+		return error;
+
+	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+	if (!error) {
+		struct address_space *mapping = old->mapping;
+		void (*freepage)(struct page *);
+
+		pgoff_t offset = old->index;
+		freepage = mapping->a_ops->freepage;
+
+		page_cache_get(new);
+		new->mapping = mapping;
+		new->index = offset;
+
+		spin_lock_irq(&mapping->tree_lock);
+		__remove_from_page_cache(old);
+		error = radix_tree_insert(&mapping->page_tree, offset, new);
+		BUG_ON(error);
+		mapping->nrpages++;
+		__inc_zone_page_state(new, NR_FILE_PAGES);
+		if (PageSwapBacked(new))
+			__inc_zone_page_state(new, NR_SHMEM);
+		spin_unlock_irq(&mapping->tree_lock);
+		radix_tree_preload_end();
+		if (freepage)
+			freepage(old);
+		page_cache_release(old);
+		mem_cgroup_end_migration(memcg, old, new, true);
+	} else {
+		mem_cgroup_end_migration(memcg, old, new, false);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(replace_page_cache_page);
+
+/**
  * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:	page to add
  * @mapping:	the page's address_space
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index da53a25..6ef5c53 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2883,7 +2883,7 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
  * page belongs to.
  */
 int mem_cgroup_prepare_migration(struct page *page,
-	struct page *newpage, struct mem_cgroup **ptr)
+	struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup *mem = NULL;
@@ -2940,7 +2940,7 @@ int mem_cgroup_prepare_migration(struct page *page,
 		return 0;
 
 	*ptr = mem;
-	ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false, PAGE_SIZE);
+	ret = __mem_cgroup_try_charge(NULL, gfp_mask, ptr, false, PAGE_SIZE);
 	css_put(&mem->css);/* drop extra refcnt */
 	if (ret || *ptr == NULL) {
 		if (PageAnon(page)) {
diff --git a/mm/migrate.c b/mm/migrate.c
index 352de555..8aacce3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -678,7 +678,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	}
 
 	/* 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;