mm: vmscan: take page buffers dirty and locked state into account

Page reclaim keeps track of dirty and under writeback pages and uses it
to determine if wait_iff_congested() should stall or if kswapd should
begin writing back pages.  This fails to account for buffer pages that
can be under writeback but not PageWriteback which is the case for
filesystems like ext3 ordered mode.  Furthermore, PageDirty buffer pages
can have all the buffers clean and writepage does no IO so it should not
be accounted as congested.

This patch adds an address_space operation that filesystems may
optionally use to check if a page is really dirty or really under
writeback.  An implementation is provided for for buffer_heads is added
and used for block operations and ext3 in ordered mode.  By default the
page flags are obeyed.

Credit goes to Jan Kara for identifying that the page flags alone are
not sufficient for ext3 and sanity checking a number of ideas on how the
problem could be addressed.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Zlatko Calusic <zcalusic@bitsync.net>
Cc: dormando <dormando@rydia.net>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 50 insertions, 0 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 431b6a0..bb43ce0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1562,6 +1562,7 @@ static const struct address_space_operations def_blk_aops = {
 	.writepages	= generic_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
+	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
 const struct file_operations def_blk_fops = {
diff --git a/fs/buffer.c b/fs/buffer.c
index f93392e..4d74335 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -83,6 +83,40 @@ void unlock_buffer(struct buffer_head *bh)
 EXPORT_SYMBOL(unlock_buffer);
 
 /*
+ * Returns if the page has dirty or writeback buffers. If all the buffers
+ * are unlocked and clean then the PageDirty information is stale. If
+ * any of the pages are locked, it is assumed they are locked for IO.
+ */
+void buffer_check_dirty_writeback(struct page *page,
+				     bool *dirty, bool *writeback)
+{
+	struct buffer_head *head, *bh;
+	*dirty = false;
+	*writeback = false;
+
+	BUG_ON(!PageLocked(page));
+
+	if (!page_has_buffers(page))
+		return;
+
+	if (PageWriteback(page))
+		*writeback = true;
+
+	head = page_buffers(page);
+	bh = head;
+	do {
+		if (buffer_locked(bh))
+			*writeback = true;
+
+		if (buffer_dirty(bh))
+			*dirty = true;
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+}
+EXPORT_SYMBOL(buffer_check_dirty_writeback);
+
+/*
  * Block until a buffer comes unlocked.  This doesn't stop it
  * from becoming locked again - you have to lock it yourself
  * if you want to preserve its state.
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index f67668f..2bd8548 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1985,6 +1985,7 @@ static const struct address_space_operations ext3_ordered_aops = {
 	.direct_IO		= ext3_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.is_dirty_writeback	= buffer_check_dirty_writeback,
 	.error_remove_page	= generic_error_remove_page,
 };
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index f5a3b83..91fa9a9 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -139,6 +139,9 @@ BUFFER_FNS(Prio, prio)
 	})
 #define page_has_buffers(page)	PagePrivate(page)
 
+void buffer_check_dirty_writeback(struct page *page,
+				     bool *dirty, bool *writeback);
+
 /*
  * Declarations
  */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2b82c80..99be011 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -380,6 +380,7 @@ struct address_space_operations {
 	int (*launder_page) (struct page *);
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
+	void (*is_dirty_writeback) (struct page *, bool *, bool *);
 	int (*error_remove_page)(struct address_space *, struct page *);
 
 	/* swapfile support */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bf47784..c857943 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -673,6 +673,8 @@ static enum page_references page_check_references(struct page *page,
 static void page_check_dirty_writeback(struct page *page,
 				       bool *dirty, bool *writeback)
 {
+	struct address_space *mapping;
+
 	/*
 	 * Anonymous pages are not handled by flushers and must be written
 	 * from reclaim context. Do not stall reclaim based on them
@@ -686,6 +688,14 @@ static void page_check_dirty_writeback(struct page *page,
 	/* By default assume that the page flags are accurate */
 	*dirty = PageDirty(page);
 	*writeback = PageWriteback(page);
+
+	/* Verify dirty/writeback state if the filesystem supports it */
+	if (!page_has_private(page))
+		return;
+
+	mapping = page_mapping(page);
+	if (mapping && mapping->a_ops->is_dirty_writeback)
+		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
 /*