ext4: implement writeback livelock avoidance using page tagging

This is analogous to Jan Kara's commit,
f446daaea9d4a420d16c606f755f3689dcb2d0ce
mm: implement writeback livelock avoidance using page tagging

but since we forked write_cache_pages, we need to reimplement
it there (and in ext4_da_writepages, since range_cyclic handling
was moved to there)

If you start a large buffered IO to a file, and then set
fsync after it, you'll find that fsync does not complete
until the other IO stops.

If you continue re-dirtying the file (say, putting dd
with conv=notrunc in a loop), when fsync finally completes
(after all IO is done), it reports via tracing that
it has written many more pages than the file contains;
in other words it has synced and re-synced pages in
the file multiple times.

This then leads to problems with our writeback_index
update, since it advances it by pages written, and
essentially sets writeback_index off the end of the
file...

With the following patch, we only sync as much as was
dirty at the time of the sync.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

2 files changed, 17 insertions, 3 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6671fcbb529..c9ea95ba5fd 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2809,16 +2809,21 @@ static int write_cache_pages_da(struct address_space *mapping,
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
 	long nr_to_write = wbc->nr_to_write;
+	int tag;
 
 	pagevec_init(&pvec, 0);
 	index = wbc->range_start >> PAGE_CACHE_SHIFT;
 	end = wbc->range_end >> PAGE_CACHE_SHIFT;
 
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		tag = PAGECACHE_TAG_TOWRITE;
+	else
+		tag = PAGECACHE_TAG_DIRTY;
+
 	while (!done && (index <= end)) {
 		int i;
 
-		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-			      PAGECACHE_TAG_DIRTY,
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
 			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
 		if (nr_pages == 0)
 			break;
@@ -2923,6 +2928,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	long desired_nr_to_write, nr_to_writebump = 0;
 	loff_t range_start = wbc->range_start;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+	pgoff_t end;
 
 	trace_ext4_da_writepages(inode, wbc);
 
@@ -2958,8 +2964,11 @@ static int ext4_da_writepages(struct address_space *mapping,
 		wbc->range_start = index << PAGE_CACHE_SHIFT;
 		wbc->range_end  = LLONG_MAX;
 		wbc->range_cyclic = 0;
-	} else
+		end = -1;
+	} else {
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+	}
 
 	/*
 	 * This works around two forms of stupidity.  The first is in
@@ -3000,6 +3009,9 @@ static int ext4_da_writepages(struct address_space *mapping,
 	pages_skipped = wbc->pages_skipped;
 
 retry:
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		tag_pages_for_writeback(mapping, index, end);
+
 	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 72a5d647a5f..3d132bfb4f3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -143,6 +143,8 @@ typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc);
+void tag_pages_for_writeback(struct address_space *mapping,
+			     pgoff_t start, pgoff_t end);
 int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);