1 files changed, 76 insertions, 48 deletions

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index c15aa29fa16..ed9252bcdac 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -26,10 +26,9 @@
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_trans_priv.h"
+#include "xfs_trace.h"
 #include "xfs_error.h"
 
-struct workqueue_struct	*xfs_ail_wq;	/* AIL workqueue */
-
 #ifdef DEBUG
 /*
  * Check that the list is sorted as it should be.
@@ -356,28 +355,34 @@ xfs_ail_delete(
 	xfs_trans_ail_cursor_clear(ailp, lip);
 }
 
-/*
- * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself
- * to run at a later time if there is more work to do to complete the push.
- */
-STATIC void
-xfs_ail_worker(
-	struct work_struct	*work)
+static long
+xfsaild_push(
+	struct xfs_ail		*ailp)
 {
-	struct xfs_ail		*ailp = container_of(to_delayed_work(work),
-					struct xfs_ail, xa_work);
 	xfs_mount_t		*mp = ailp->xa_mount;
 	struct xfs_ail_cursor	cur;
 	xfs_log_item_t		*lip;
 	xfs_lsn_t		lsn;
 	xfs_lsn_t		target;
 	long			tout = 10;
-	int			flush_log = 0;
 	int			stuck = 0;
 	int			count = 0;
 	int			push_xfsbufd = 0;
 
+	/*
+	 * If last time we ran we encountered pinned items, force the log first
+	 * and wait for it before pushing again.
+	 */
 	spin_lock(&ailp->xa_lock);
+	if (ailp->xa_last_pushed_lsn == 0 && ailp->xa_log_flush &&
+	    !list_empty(&ailp->xa_ail)) {
+		ailp->xa_log_flush = 0;
+		spin_unlock(&ailp->xa_lock);
+		XFS_STATS_INC(xs_push_ail_flush);
+		xfs_log_force(mp, XFS_LOG_SYNC);
+		spin_lock(&ailp->xa_lock);
+	}
+
 	target = ailp->xa_target;
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
 	if (!lip || XFS_FORCED_SHUTDOWN(mp)) {
@@ -421,26 +426,37 @@ xfs_ail_worker(
 		switch (lock_result) {
 		case XFS_ITEM_SUCCESS:
 			XFS_STATS_INC(xs_push_ail_success);
+			trace_xfs_ail_push(lip);
+
 			IOP_PUSH(lip);
 			ailp->xa_last_pushed_lsn = lsn;
 			break;
 
 		case XFS_ITEM_PUSHBUF:
 			XFS_STATS_INC(xs_push_ail_pushbuf);
-			IOP_PUSHBUF(lip);
-			ailp->xa_last_pushed_lsn = lsn;
+			trace_xfs_ail_pushbuf(lip);
+
+			if (!IOP_PUSHBUF(lip)) {
+				trace_xfs_ail_pushbuf_pinned(lip);
+				stuck++;
+				ailp->xa_log_flush++;
+			} else {
+				ailp->xa_last_pushed_lsn = lsn;
+			}
 			push_xfsbufd = 1;
 			break;
 
 		case XFS_ITEM_PINNED:
 			XFS_STATS_INC(xs_push_ail_pinned);
+			trace_xfs_ail_pinned(lip);
+
 			stuck++;
-			flush_log = 1;
+			ailp->xa_log_flush++;
 			break;
 
 		case XFS_ITEM_LOCKED:
 			XFS_STATS_INC(xs_push_ail_locked);
-			ailp->xa_last_pushed_lsn = lsn;
+			trace_xfs_ail_locked(lip);
 			stuck++;
 			break;
 
@@ -480,16 +496,6 @@ xfs_ail_worker(
 	xfs_trans_ail_cursor_done(ailp, &cur);
 	spin_unlock(&ailp->xa_lock);
 
-	if (flush_log) {
-		/*
-		 * If something we need to push out was pinned, then
-		 * push out the log so it will become unpinned and
-		 * move forward in the AIL.
-		 */
-		XFS_STATS_INC(xs_push_ail_flush);
-		xfs_log_force(mp, 0);
-	}
-
 	if (push_xfsbufd) {
 		/* we've got delayed write buffers to flush */
 		wake_up_process(mp->m_ddev_targp->bt_task);
@@ -500,20 +506,7 @@ out_done:
 	if (!count) {
 		/* We're past our target or empty, so idle */
 		ailp->xa_last_pushed_lsn = 0;
-
-		/*
-		 * We clear the XFS_AIL_PUSHING_BIT first before checking
-		 * whether the target has changed. If the target has changed,
-		 * this pushes the requeue race directly onto the result of the
-		 * atomic test/set bit, so we are guaranteed that either the
-		 * the pusher that changed the target or ourselves will requeue
-		 * the work (but not both).
-		 */
-		clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags);
-		smp_rmb();
-		if (XFS_LSN_CMP(ailp->xa_target, target) == 0 ||
-		    test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
-			return;
+		ailp->xa_log_flush = 0;
 
 		tout = 50;
 	} else if (XFS_LSN_CMP(lsn, target) >= 0) {
@@ -532,14 +525,39 @@ out_done:
 		 * were stuck.
 		 *
 		 * Backoff a bit more to allow some I/O to complete before
-		 * continuing from where we were.
+		 * restarting from the start of the AIL. This prevents us
+		 * from spinning on the same items, and if they are pinned will
+		 * all the restart to issue a log force to unpin the stuck
+		 * items.
 		 */
 		tout = 20;
+		ailp->xa_last_pushed_lsn = 0;
+	}
+
+	return tout;
+}
+
+static int
+xfsaild(
+	void		*data)
+{
+	struct xfs_ail	*ailp = data;
+	long		tout = 0;	/* milliseconds */
+
+	while (!kthread_should_stop()) {
+		if (tout && tout <= 20)
+			__set_current_state(TASK_KILLABLE);
+		else
+			__set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(tout ?
+				 msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
+
+		try_to_freeze();
+
+		tout = xfsaild_push(ailp);
 	}
 
-	/* There is more to do, requeue us.  */
-	queue_delayed_work(xfs_syncd_wq, &ailp->xa_work,
-					msecs_to_jiffies(tout));
+	return 0;
 }
 
 /*
@@ -574,8 +592,9 @@ xfs_ail_push(
 	 */
 	smp_wmb();
 	xfs_trans_ail_copy_lsn(ailp, &ailp->xa_target, &threshold_lsn);
-	if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
-		queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0);
+	smp_wmb();
+
+	wake_up_process(ailp->xa_task);
 }
 
 /*
@@ -813,9 +832,18 @@ xfs_trans_ail_init(
 	INIT_LIST_HEAD(&ailp->xa_ail);
 	INIT_LIST_HEAD(&ailp->xa_cursors);
 	spin_lock_init(&ailp->xa_lock);
-	INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker);
+
+	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
+			ailp->xa_mount->m_fsname);
+	if (IS_ERR(ailp->xa_task))
+		goto out_free_ailp;
+
 	mp->m_ail = ailp;
 	return 0;
+
+out_free_ailp:
+	kmem_free(ailp);
+	return ENOMEM;
 }
 
 void
@@ -824,6 +852,6 @@ xfs_trans_ail_destroy(
 {
 	struct xfs_ail	*ailp = mp->m_ail;
 
-	cancel_delayed_work_sync(&ailp->xa_work);
+	kthread_stop(ailp->xa_task);
 	kmem_free(ailp);
 }