[V2,01/12] dm raid: fix deadlock caused by stopped writes

Commit Message

Heinz Mauelshagen Dec. 2, 2017, 12:03 a.m. UTC

md_stop_writes() is called in presuspend causing deadlocks on
bios submitted afterwards which happens on loaded raid sets
with conversion requests.

Fix by moving md_stop_writes to postsuspend.
Hence the raid set is quiesced remove superfluous
readonly setting too.

Adjust target version to be able to recognize the fix.
---
 Documentation/device-mapper/dm-raid.txt |  3 ++-
 drivers/md/dm-raid.c                    | 20 +++++++++-----------
 2 files changed, 11 insertions(+), 12 deletions(-)

Patch

diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index 32df07e29f68..4d260fedcd8b 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -343,5 +343,6 @@  Version History
 1.11.0  Fix table line argument order
 	(wrong raid10_copies/raid10_format sequence)
 1.11.1  Add raid4/5/6 journal write-back support via journal_mode option
-1.12.1  fix for MD deadlock between mddev_suspend() and md_write_start() available
+1.12.1  Fix for MD deadlock between mddev_suspend() and md_write_start() available
 1.13.0  Fix dev_health status at end of "recover" (was 'a', now 'A')
+1.13.1  Fix deadlock caused by early md_stop_writes()
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 6319d846e0ad..536666facbf1 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3613,24 +3613,23 @@  static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size * mddev_data_stripes(rs));
 }
 
-static void raid_presuspend(struct dm_target *ti)
-{
-	struct raid_set *rs = ti->private;
-
-	md_stop_writes(&rs->md);
-}
-
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
 	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
+		/*
+		 * Writes have to be stopped before suspending to avoid deadlocks.
+		 *
+		 * https://bugzilla.redhat.com/show_bug.cgi?id=1514539
+		 */
+		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
+			md_stop_writes(&rs->md);
+
 		mddev_lock_nointr(&rs->md);
 		mddev_suspend(&rs->md);
 		mddev_unlock(&rs->md);
 	}
-
-	rs->md.ro = 1;
 }
 
 static void attempt_restore_of_faulty_devices(struct raid_set *rs)
@@ -3894,7 +3893,7 @@  static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 13, 0},
+	.version = {1, 13, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
@@ -3903,7 +3902,6 @@  static struct target_type raid_target = {
 	.message = raid_message,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
-	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.preresume = raid_preresume,
 	.resume = raid_resume,