block: Introduce bio_needs_zone_write_plugging()

In preparation for fixing device mapper zone write handling, introduce
the inline helper function bio_needs_zone_write_plugging() to test if a
BIO requires handling through zone write plugging using the function
blk_zone_plug_bio(). This function returns true for any write
(op_is_write(bio) == true) operation directed at a zoned block device
using zone write plugging, that is, a block device with a disk that has
a zone write plug hash table.

This helper allows simplifying the check on entry to blk_zone_plug_bio()
and used in to protect calls to it for blk-mq devices and DM devices.

Fixes: f211268ed1f9 ("dm: Use the block layer zone append emulation")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250625093327.548866-3-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

4 files changed, 63 insertions, 22 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4806b867e37d..0c61492724d2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3169,8 +3169,10 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 		goto queue_exit;
 
-	if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs))
-		goto queue_exit;
+	if (bio_needs_zone_write_plugging(bio)) {
+		if (blk_zone_plug_bio(bio, nr_segs))
+			goto queue_exit;
+	}
 
 new_request:
 	if (rq) {
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 351d659280e1..efe71b1a1da1 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1116,25 +1116,7 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 {
 	struct block_device *bdev = bio->bi_bdev;
 
-	if (!bdev->bd_disk->zone_wplugs_hash)
-		return false;
-
-	/*
-	 * If the BIO already has the plugging flag set, then it was already
-	 * handled through this path and this is a submission from the zone
-	 * plug bio submit work.
-	 */
-	if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
-		return false;
-
-	/*
-	 * We do not need to do anything special for empty flush BIOs, e.g
-	 * BIOs such as issued by blkdev_issue_flush(). The is because it is
-	 * the responsibility of the user to first wait for the completion of
-	 * write operations for flush to have any effect on the persistence of
-	 * the written data.
-	 */
-	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+	if (WARN_ON_ONCE(!bdev->bd_disk->zone_wplugs_hash))
 		return false;
 
 	/*
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1726f0f828cc..6e3de50eae47 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1788,7 +1788,9 @@ static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
 }
 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,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5c626d23cbb2..a51f92b6c340 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -837,6 +837,55 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return disk->nr_zones;
 }
+
+/**
+ * bio_needs_zone_write_plugging - Check if a BIO needs to be handled with zone
+ *				   write plugging
+ * @bio: The BIO being submitted
+ *
+ * Return true whenever @bio execution needs to be handled through zone
+ * write plugging (using blk_zone_plug_bio()). Return false otherwise.
+ */
+static inline bool bio_needs_zone_write_plugging(struct bio *bio)
+{
+	enum req_op op = bio_op(bio);
+
+	/*
+	 * Only zoned block devices have a zone write plug hash table. But not
+	 * all of them have one (e.g. DM devices may not need one).
+	 */
+	if (!bio->bi_bdev->bd_disk->zone_wplugs_hash)
+		return false;
+
+	/* Only write operations need zone write plugging. */
+	if (!op_is_write(op))
+		return false;
+
+	/* Ignore empty flush */
+	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+		return false;
+
+	/* Ignore BIOs that already have been handled by zone write plugging. */
+	if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
+		return false;
+
+	/*
+	 * All zone write operations must be handled through zone write plugging
+	 * using blk_zone_plug_bio().
+	 */
+	switch (op) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return true;
+	default:
+		return false;
+	}
+}
+
 bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
 
 /**
@@ -866,6 +915,12 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
 }
+
+static inline bool bio_needs_zone_write_plugging(struct bio *bio)
+{
+	return false;
+}
+
 static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 {
 	return false;