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""

4 files changed, 208 insertions, 40 deletions

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index eb009d6bb03a..17e9af60bbf7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -213,6 +213,7 @@ struct raid_dev {
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
 #define RT_FLAG_RS_GROW			8
+#define RT_FLAG_RS_FROZEN		9
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -3240,11 +3241,12 @@ size_check:
 	rs->md.ro = 1;
 	rs->md.in_sync = 1;
 
-	/* Keep array frozen until resume. */
-	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
-
 	/* Has to be held on running the array */
 	mddev_suspend_and_lock_nointr(&rs->md);
+
+	/* Keep array frozen until resume. */
+	md_frozen_sync_thread(&rs->md);
+
 	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
 	if (r) {
@@ -3339,7 +3341,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	md_handle_request(mddev, bio);
+	if (unlikely(!md_handle_request(mddev, bio)))
+		return DM_MAPIO_REQUEUE;
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -3718,21 +3721,33 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
+	int ret = 0;
 
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (!strcasecmp(argv[0], "frozen"))
-		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) ||
+	    test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags))
+		return -EBUSY;
 
-	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
-		if (mddev->sync_thread) {
-			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
-		}
-	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
+	if (!strcasecmp(argv[0], "frozen")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_frozen_sync_thread(mddev);
+		mddev_unlock(mddev);
+	} else if (!strcasecmp(argv[0], "idle")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_idle_sync_thread(mddev);
+		mddev_unlock(mddev);
+	}
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;
 	else if (!strcasecmp(argv[0], "resync"))
 		; /* MD_RECOVERY_NEEDED set below */
@@ -3791,15 +3806,46 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
 }
 
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	/*
+	 * From now on, disallow raid_message() to change sync_thread until
+	 * resume, raid_postsuspend() is too late.
+	 */
+	set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+
+	if (!reshape_interrupted(mddev))
+		return;
+
+	/*
+	 * For raid456, if reshape is interrupted, IO across reshape position
+	 * will never make progress, while caller will wait for IO to be done.
+	 * Inform raid456 to handle those IO to prevent deadlock.
+	 */
+	if (mddev->pers && mddev->pers->prepare_suspend)
+		mddev->pers->prepare_suspend(mddev);
+}
+
+static void raid_presuspend_undo(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+}
+
 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. */
-		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
-			md_stop_writes(&rs->md);
-
+		/*
+		 * sync_thread must be stopped during suspend, and writes have
+		 * to be stopped before suspending to avoid deadlocks.
+		 */
+		md_stop_writes(&rs->md);
 		mddev_suspend(&rs->md, false);
 	}
 }
@@ -4012,8 +4058,6 @@ static int raid_preresume(struct dm_target *ti)
 	}
 
 	/* Check for any resize/reshape on @rs and adjust/initiate */
-	/* Be prepared for mddev_resume() in raid_resume() */
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
 		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		mddev->resync_min = mddev->recovery_cp;
@@ -4047,7 +4091,9 @@ static void raid_resume(struct dm_target *ti)
 		 * Take this opportunity to check whether any failed
 		 * devices are reachable again.
 		 */
+		mddev_lock_nointr(mddev);
 		attempt_restore_of_faulty_devices(rs);
+		mddev_unlock(mddev);
 	}
 
 	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
@@ -4055,10 +4101,13 @@ static void raid_resume(struct dm_target *ti)
 		if (mddev->delta_disks < 0)
 			rs_set_capacity(rs);
 
+		WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
+		WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+		clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
 		mddev_lock_nointr(mddev);
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
+		md_unfrozen_sync_thread(mddev);
 		mddev_unlock_and_resume(mddev);
 	}
 }
@@ -4074,6 +4123,8 @@ static struct target_type raid_target = {
 	.message = raid_message,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.presuspend_undo = raid_presuspend_undo,
 	.postsuspend = raid_postsuspend,
 	.preresume = raid_preresume,
 	.resume = raid_resume,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 48ae2b1cb57a..64d544f09295 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -99,18 +99,6 @@ static void mddev_detach(struct mddev *mddev);
 static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
 static void md_wakeup_thread_directly(struct md_thread __rcu *thread);
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -378,7 +366,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 	return true;
 }
 
-void md_handle_request(struct mddev *mddev, struct bio *bio)
+bool md_handle_request(struct mddev *mddev, struct bio *bio)
 {
 check_suspended:
 	if (is_suspended(mddev, bio)) {
@@ -386,7 +374,7 @@ check_suspended:
 		/* Bail out if REQ_NOWAIT is set for the bio */
 		if (bio->bi_opf & REQ_NOWAIT) {
 			bio_wouldblock_error(bio);
-			return;
+			return true;
 		}
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
@@ -402,10 +390,13 @@ check_suspended:
 
 	if (!mddev->pers->make_request(mddev, bio)) {
 		percpu_ref_put(&mddev->active_io);
+		if (!mddev->gendisk && mddev->pers->prepare_suspend)
+			return false;
 		goto check_suspended;
 	}
 
 	percpu_ref_put(&mddev->active_io);
+	return true;
 }
 EXPORT_SYMBOL(md_handle_request);
 
@@ -4942,6 +4933,35 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 		mddev_lock_nointr(mddev);
 }
 
+void md_idle_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, true);
+}
+EXPORT_SYMBOL_GPL(md_idle_sync_thread);
+
+void md_frozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
+}
+EXPORT_SYMBOL_GPL(md_frozen_sync_thread);
+
+void md_unfrozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+}
+EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread);
+
 static void idle_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
@@ -6062,7 +6082,10 @@ int md_run(struct mddev *mddev)
 			pr_warn("True protection against single-disk failure might be compromised.\n");
 	}
 
-	mddev->recovery = 0;
+	/* dm-raid expect sync_thread to be frozen until resume */
+	if (mddev->gendisk)
+		mddev->recovery = 0;
+
 	/* may be over-ridden by personality */
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
@@ -6344,7 +6367,6 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6369,6 +6391,8 @@ static void __md_stop_writes(struct mddev *mddev)
 void md_stop_writes(struct mddev *mddev)
 {
 	mddev_lock_nointr(mddev);
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
 	__md_stop_writes(mddev);
 	mddev_unlock(mddev);
 }
@@ -8712,6 +8736,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio)
 }
 EXPORT_SYMBOL_GPL(md_account_bio);
 
+void md_free_cloned_bio(struct bio *bio)
+{
+	struct md_io_clone *md_io_clone = bio->bi_private;
+	struct bio *orig_bio = md_io_clone->orig_bio;
+	struct mddev *mddev = md_io_clone->mddev;
+
+	if (bio->bi_status && !orig_bio->bi_status)
+		orig_bio->bi_status = bio->bi_status;
+
+	if (md_io_clone->start_time)
+		bio_end_io_acct(orig_bio, md_io_clone->start_time);
+
+	bio_put(bio);
+	percpu_ref_put(&mddev->active_io);
+}
+EXPORT_SYMBOL_GPL(md_free_cloned_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b2076a165c10..556db28a49aa 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -569,6 +569,37 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
+enum md_ro_state {
+	MD_RDWR,
+	MD_RDONLY,
+	MD_AUTO_READ,
+	MD_MAX_STATE
+};
+
+static inline bool md_is_rdwr(struct mddev *mddev)
+{
+	return (mddev->ro == MD_RDWR);
+}
+
+static inline bool reshape_interrupted(struct mddev *mddev)
+{
+	/* reshape never start */
+	if (mddev->reshape_position == MaxSector)
+		return false;
+
+	/* interrupted */
+	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return true;
+
+	/* running reshape will be interrupted soon. */
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+		return true;
+
+	return false;
+}
+
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -628,6 +659,7 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
+	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -761,6 +793,7 @@ extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
 void md_account_bio(struct mddev *mddev, struct bio **bio);
+void md_free_cloned_bio(struct bio *bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
@@ -789,9 +822,12 @@ extern void md_stop_writes(struct mddev *mddev);
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
-extern void md_handle_request(struct mddev *mddev, struct bio *bio);
+extern bool md_handle_request(struct mddev *mddev, struct bio *bio);
 extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
+extern void md_idle_sync_thread(struct mddev *mddev);
+extern void md_frozen_sync_thread(struct mddev *mddev);
+extern void md_unfrozen_sync_thread(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
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)