md/raid5: fix a deadlock in the case that reshape is interrupted

If reshape is in progress and io across reshape_position is issued, such
io will wait for reshape to make progress(see details in the case that
make_stripe_request() return STRIPE_SCHEDULE_AND_RETRY).

It has been reported several times that if system reboot while growing
raid5 to raid6, array assemble will hang infinitely([1, 2]). This is
because following deadlock is triggered:

1) a normal io is waiting for reshape to progress, this io can be from
   system-udevd or mdadm.
2) while assemble, mdadm tries to suspend the array, hence
   'reconfig_mutex' is held and mddev_suspend() must wait for normal io
   to be done.
3) daemon thread can't start reshape because 'reconfig_mutex' can't be
   held.

1) and 3) is unbreakable because they're foundation design. In order to
break 2), following is possible solutions that I can think of:

a) Let mddev_suspend() fail is not a good option, because this will
   break many scenarios since mddev_suspend() doesn't fail before.
b) Fail the io that is waiting for reshape to make progress from
   mddev_suspend().
c) Return false for the io that is waiting for reshape to make
   progress from raid5_make_request(), and these io will wait for
   suspend to be done in md_handle_request(), where 'active_io' is
   not grabbed.

c) sounds better than b), however, b) is used because it's easy and
straightforward, and it's verified that mdadm can assemble in this case.
On the other hand, c) breaks the logic that mddev_suspend() will wait
for submitted io to be completely handled.

Fix the problem by checking reshape in mddev_suspend(), if reshape can't
make progress and there are still some io waiting for reshape, fail
those io.

[1] https://lore.kernel.org/all/CAFig2csUV2QiomUhj_t3dPOgV300dbQ6XtM9ygKPdXJFSH__Nw@mail.gmail.com/
[2] https://lore.kernel.org/all/CAO2ABipzbw6QL5eNa44CQHjiVa-LTvS696Mh9QaTw+qsUKFUCw@mail.gmail.com/

Reported-by: Jove <jovetoo@gmail.com>
Reported-by: David Gilmour <dgilmour76@gmail.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230512015610.821290-6-yukuai1@huaweicloud.com

1 files changed, 43 insertions, 1 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5950932323fc..01c55f24ab09 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5966,6 +5966,19 @@ out:
 	return ret;
 }
 
+static bool reshape_inprogress(struct mddev *mddev)
+{
+	return test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	       test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
+	       !test_bit(MD_RECOVERY_DONE, &mddev->recovery) &&
+	       !test_bit(MD_RECOVERY_INTR, &mddev->recovery);
+}
+
+static bool reshape_disabled(struct mddev *mddev)
+{
+	return is_md_suspended(mddev) || !md_is_rdwr(mddev);
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -5997,7 +6010,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 			if (ahead_of_reshape(mddev, logical_sector,
 					     conf->reshape_safe)) {
 				spin_unlock_irq(&conf->device_lock);
-				return STRIPE_SCHEDULE_AND_RETRY;
+				ret = STRIPE_SCHEDULE_AND_RETRY;
+				goto out;
 			}
 		}
 		spin_unlock_irq(&conf->device_lock);
@@ -6076,6 +6090,15 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 
 out_release:
 	raid5_release_stripe(sh);
+out:
+	if (ret == STRIPE_SCHEDULE_AND_RETRY && !reshape_inprogress(mddev) &&
+	    reshape_disabled(mddev)) {
+		bi->bi_status = BLK_STS_IOERR;
+		ret = STRIPE_FAIL;
+		pr_err("md/raid456:%s: io failed across reshape position while reshape can't make progress.\n",
+		       mdname(mddev));
+	}
+
 	return ret;
 }
 
@@ -9044,6 +9067,22 @@ static int raid5_start(struct mddev *mddev)
 	return r5l_start(conf->log);
 }
 
+static void raid5_prepare_suspend(struct mddev *mddev)
+{
+	struct r5conf *conf = mddev->private;
+
+	wait_event(mddev->sb_wait, !reshape_inprogress(mddev) ||
+				    percpu_ref_is_zero(&mddev->active_io));
+	if (percpu_ref_is_zero(&mddev->active_io))
+		return;
+
+	/*
+	 * Reshape is not in progress, and array is suspended, io that is
+	 * waiting for reshpape can never be done.
+	 */
+	wake_up(&conf->wait_for_overlap);
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -9064,6 +9103,7 @@ static struct md_personality raid6_personality =
 	.check_reshape	= raid6_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
+	.prepare_suspend = raid5_prepare_suspend,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
@@ -9088,6 +9128,7 @@ static struct md_personality raid5_personality =
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
+	.prepare_suspend = raid5_prepare_suspend,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
@@ -9113,6 +9154,7 @@ static struct md_personality raid4_personality =
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
+	.prepare_suspend = raid5_prepare_suspend,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,