Merge tag 'md-6.9-20240305' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.9/block

Pull MD fixes from Song:

"This set fixes two issues:

 1. dmraid regression since 6.7 kernels. This issue was initially
    reported in [1]. This set of fix has been reviewed and tested by
    md and dm folks.

 2. raid5 hang since 6.7 kernel, reported in [2]. We haven't got a
    better fix for this issue yet. This revert is a workaround. It has
    been applied to 6.7 stable kernels [3], and proved to be affective.
    We will look more into this issue for a better fix.

 [1] https://lore.kernel.org/linux-raid/e5e8afe2-e9a8-49a2-5ab0-958d4065c55e@redhat.com/
 [2] https://lore.kernel.org/linux-raid/20240123005700.9302-1-dan@danm.net/
 [3] 87165c64fe1a in linux-6.7.y branch."

* tag 'md-6.9-20240305' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  dm-raid: fix lockdep waring in "pers->hot_add_disk"
  dm-raid456, md/raid456: fix a deadlock for dm-raid456 while io concurrent with reshape
  dm-raid: add a new helper prepare_suspend() in md_personality
  md/dm-raid: don't call md_reap_sync_thread() directly
  dm-raid: really frozen sync_thread during suspend
  md: add a new helper reshape_interrupted()
  md: export helper md_is_rdwr()
  md: export helpers to stop sync_thread
  md: don't clear MD_RECOVERY_FROZEN for new dm-raid until resume
  Revert "Revert "md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d""

1 files changed, 42 insertions, 2 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 48129de21aec..58f8395b56d6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,6 +36,7 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -760,6 +761,7 @@ enum stripe_result {
 	STRIPE_RETRY,
 	STRIPE_SCHEDULE_AND_RETRY,
 	STRIPE_FAIL,
+	STRIPE_WAIT_RESHAPE,
 };
 
 struct stripe_request_ctx {
@@ -5937,7 +5939,8 @@ 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);
@@ -6016,6 +6019,12 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 
 out_release:
 	raid5_release_stripe(sh);
+out:
+	if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) {
+		bi->bi_status = BLK_STS_RESOURCE;
+		ret = STRIPE_WAIT_RESHAPE;
+		pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress");
+	}
 	return ret;
 }
 
@@ -6137,7 +6146,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	while (1) {
 		res = make_stripe_request(mddev, conf, &ctx, logical_sector,
 					  bi);
-		if (res == STRIPE_FAIL)
+		if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE)
 			break;
 
 		if (res == STRIPE_RETRY)
@@ -6175,6 +6184,11 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 
 	if (rw == WRITE)
 		md_write_end(mddev);
+	if (res == STRIPE_WAIT_RESHAPE) {
+		md_free_cloned_bio(bi);
+		return false;
+	}
+
 	bio_endio(bi);
 	return true;
 }
@@ -6764,7 +6778,18 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
+
+			/*
+			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
+			 * seeing md_check_recovery() is needed to clear
+			 * the flag when using mdmon.
+			 */
+			continue;
 		}
+
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -8925,6 +8950,18 @@ static int raid5_start(struct mddev *mddev)
 	return r5l_start(conf->log);
 }
 
+/*
+ * This is only used for dm-raid456, caller already frozen sync_thread, hence
+ * if rehsape is still in progress, io that is waiting for reshape can never be
+ * done now, hence wake up and handle those IO.
+ */
+static void raid5_prepare_suspend(struct mddev *mddev)
+{
+	struct r5conf *conf = mddev->private;
+
+	wake_up(&conf->wait_for_overlap);
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -8948,6 +8985,7 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 static struct md_personality raid5_personality =
 {
@@ -8972,6 +9010,7 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static struct md_personality raid4_personality =
@@ -8997,6 +9036,7 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static int __init raid5_init(void)