1 files changed, 47 insertions, 28 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 19230404d8c2..c5dcd632404c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1541,14 +1541,18 @@ static void __send_empty_flush(struct clone_info *ci)
 {
 	struct dm_table *t = ci->map;
 	struct bio flush_bio;
+	blk_opf_t opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+
+	if ((ci->io->orig_bio->bi_opf & (REQ_IDLE | REQ_SYNC)) ==
+	    (REQ_IDLE | REQ_SYNC))
+		opf |= REQ_IDLE;
 
 	/*
 	 * Use an on-stack bio for this, it's safe since we don't
 	 * need to reference it after submit. It's just used as
 	 * the basis for the clone(s).
 	 */
-	bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0,
-		 REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC);
+	bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, opf);
 
 	ci->bio = &flush_bio;
 	ci->sector_count = 0;
@@ -1784,19 +1788,35 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
-					   struct bio *bio)
+static inline bool dm_zone_bio_needs_split(struct bio *bio)
 {
 	/*
-	 * For mapped device that need zone append emulation, we must
-	 * split any large BIO that straddles zone boundaries.
+	 * Special case the zone operations that cannot or should not be split.
 	 */
-	return dm_emulate_zone_append(md) && bio_straddles_zones(bio) &&
-		!bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+	switch (bio_op(bio)) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return false;
+	default:
+		break;
+	}
+
+	/*
+	 * When mapped devices use the block layer zone write plugging, we must
+	 * split any large BIO to the mapped device limits to not submit BIOs
+	 * that span zone boundaries and to avoid potential deadlocks with
+	 * queue freeze operations.
+	 */
+	return bio_needs_zone_write_plugging(bio) || bio_straddles_zones(bio);
 }
+
 static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
 {
-	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+	if (!bio_needs_zone_write_plugging(bio))
+		return false;
+	return blk_zone_plug_bio(bio, 0);
 }
 
 static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
@@ -1912,8 +1932,7 @@ static blk_status_t __send_zone_reset_all(struct clone_info *ci)
 }
 
 #else
-static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
-					   struct bio *bio)
+static inline bool dm_zone_bio_needs_split(struct bio *bio)
 {
 	return false;
 }
@@ -1940,9 +1959,7 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 
 	is_abnormal = is_abnormal_io(bio);
 	if (static_branch_unlikely(&zoned_enabled)) {
-		/* Special case REQ_OP_ZONE_RESET_ALL as it cannot be split. */
-		need_split = (bio_op(bio) != REQ_OP_ZONE_RESET_ALL) &&
-			(is_abnormal || dm_zone_bio_needs_split(md, bio));
+		need_split = is_abnormal || dm_zone_bio_needs_split(bio);
 	} else {
 		need_split = is_abnormal;
 	}
@@ -2406,21 +2423,29 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 			       struct queue_limits *limits)
 {
 	struct dm_table *old_map;
-	sector_t size;
+	sector_t size, old_size;
 	int ret;
 
 	lockdep_assert_held(&md->suspend_lock);
 
 	size = dm_table_get_size(t);
 
+	old_size = dm_get_size(md);
+	set_capacity(md->disk, size);
+
+	ret = dm_table_set_restrictions(t, md->queue, limits);
+	if (ret) {
+		set_capacity(md->disk, old_size);
+		old_map = ERR_PTR(ret);
+		goto out;
+	}
+
 	/*
 	 * Wipe any geometry if the size of the table changed.
 	 */
-	if (size != dm_get_size(md))
+	if (size != old_size)
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	set_capacity(md->disk, size);
-
 	dm_table_event_callback(t, event_callback, md);
 
 	if (dm_table_request_based(t)) {
@@ -2438,10 +2463,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 * requests in the queue may refer to bio from the old bioset,
 		 * so you must walk through the queue to unprep.
 		 */
-		if (!md->mempools) {
+		if (!md->mempools)
 			md->mempools = t->mempools;
-			t->mempools = NULL;
-		}
+		else
+			dm_free_md_mempools(t->mempools);
 	} else {
 		/*
 		 * The md may already have mempools that need changing.
@@ -2450,14 +2475,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 */
 		dm_free_md_mempools(md->mempools);
 		md->mempools = t->mempools;
-		t->mempools = NULL;
-	}
-
-	ret = dm_table_set_restrictions(t, md->queue, limits);
-	if (ret) {
-		old_map = ERR_PTR(ret);
-		goto out;
 	}
+	t->mempools = NULL;
 
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, (void *)t);