[PATCH] don't allow background writes to hide dirty buffers

If pdflush hits a locked-and-clean buffer in __block_write_full_page() it
will just pass over the buffer.  Typically the buffer is an ext3 data=ordered
buffer which is being written by kjournald, but a similar thing can happen
with blockdev buffers and ll_rw_block().

This is bad because the buffer is still under I/O and a subsequent fsync's
fdatawait() needs to know about it.

It is not practical to tag the page for writeback - only the submitter of the
I/O can do that, because the submitter has control of the end_io handler.

So instead, redirty the page so a subsequent fsync's fdatawrite() will wait on
the underway I/O.

There is a risk that pdflush::background_writeout() will lock up, repeatedly
trying and failing to write the same page.  This is prevented by ensuring
that background_writeout() always throttles when it made no progress.

1 files changed, 1 insertions, 0 deletions

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 1424811e1eab..7380d2cefb16 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -39,6 +39,7 @@ struct writeback_control {
 					   older than this */
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
+	long pages_skipped;		/* Pages which were not written */
 	int nonblocking;		/* Don't get stuck on request queues */
 	int encountered_congestion;	/* An output: a queue is full */
 	int for_kupdate;		/* A kupdate writeback */