xfs: prevent unwritten extent conversion from blocking I/O completion

Unwritten extent conversion can recurse back into the filesystem due
to memory allocation. Memory reclaim requires I/O completions to be
processed to allow the callers to make progress. If the I/O
completion workqueue thread is doing the recursion, then we have a
deadlock situation.

Move unwritten extent completion into it's own workqueue so it
doesn't block I/O completions for normal delayed allocation or
overwrite data.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

3 files changed, 31 insertions, 17 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index c13f67300fe..7ec89fc05b2 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -153,23 +153,6 @@ xfs_find_bdev_for_inode(
 }
 
 /*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
-	xfs_ioend_t	*ioend,
-	int		wait)
-{
-	if (atomic_dec_and_test(&ioend->io_remaining)) {
-		queue_work(xfsdatad_workqueue, &ioend->io_work);
-		if (wait)
-			flush_workqueue(xfsdatad_workqueue);
-	}
-}
-
-/*
  * We're now finished for good with this ioend structure.
  * Update the page state via the associated buffer_heads,
  * release holds on the inode and bio, and finally free
@@ -310,6 +293,27 @@ xfs_end_bio_read(
 }
 
 /*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+	xfs_ioend_t	*ioend,
+	int		wait)
+{
+	if (atomic_dec_and_test(&ioend->io_remaining)) {
+		struct workqueue_struct *wq = xfsdatad_workqueue;
+		if (ioend->io_work.func == xfs_end_bio_unwritten)
+			wq = xfsconvertd_workqueue;
+
+		queue_work(wq, &ioend->io_work);
+		if (wait)
+			flush_workqueue(wq);
+	}
+}
+
+/*
  * Allocate and initialise an IO completion structure.
  * We need to track unwritten extent write completion here initially.
  * We'll need to extend this for updating the ondisk inode size later
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h
index 1dd52884975..221b3e66cee 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/linux-2.6/xfs_aops.h
@@ -19,6 +19,7 @@
 #define __XFS_AOPS_H__
 
 extern struct workqueue_struct *xfsdatad_workqueue;
+extern struct workqueue_struct *xfsconvertd_workqueue;
 extern mempool_t *xfs_ioend_pool;
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index aa1016bb913..e28800a9f2b 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -51,6 +51,7 @@ static struct shrinker xfs_buf_shake = {
 
 static struct workqueue_struct *xfslogd_workqueue;
 struct workqueue_struct *xfsdatad_workqueue;
+struct workqueue_struct *xfsconvertd_workqueue;
 
 #ifdef XFS_BUF_TRACE
 void
@@ -1775,6 +1776,7 @@ xfs_flush_buftarg(
 	xfs_buf_t	*bp, *n;
 	int		pincount = 0;
 
+	xfs_buf_runall_queues(xfsconvertd_workqueue);
 	xfs_buf_runall_queues(xfsdatad_workqueue);
 	xfs_buf_runall_queues(xfslogd_workqueue);
 
@@ -1831,9 +1833,15 @@ xfs_buf_init(void)
 	if (!xfsdatad_workqueue)
 		goto out_destroy_xfslogd_workqueue;
 
+	xfsconvertd_workqueue = create_workqueue("xfsconvertd");
+	if (!xfsconvertd_workqueue)
+		goto out_destroy_xfsdatad_workqueue;
+
 	register_shrinker(&xfs_buf_shake);
 	return 0;
 
+ out_destroy_xfsdatad_workqueue:
+	destroy_workqueue(xfsdatad_workqueue);
  out_destroy_xfslogd_workqueue:
 	destroy_workqueue(xfslogd_workqueue);
  out_free_buf_zone:
@@ -1849,6 +1857,7 @@ void
 xfs_buf_terminate(void)
 {
 	unregister_shrinker(&xfs_buf_shake);
+	destroy_workqueue(xfsconvertd_workqueue);
 	destroy_workqueue(xfsdatad_workqueue);
 	destroy_workqueue(xfslogd_workqueue);
 	kmem_zone_destroy(xfs_buf_zone);