dm: Forbid requeue of writes to zones

A target map method requesting the requeue of a bio with
DM_MAPIO_REQUEUE or completing it with DM_ENDIO_REQUEUE can cause
unaligned write errors if the bio is a write operation targeting a
sequential zone. If a zoned target request such a requeue, warn about
it and kill the IO.

The function dm_is_zone_write() is introduced to detect write operations
to zoned targets.

This change does not affect the target drivers supporting zoned devices
and exposing a zoned device, namely dm-crypt, dm-linear and dm-flakey as
none of these targets ever request a requeue.

Signed-off-by: Damien Le Moal <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Reviewed-by: Himanshu Madhani <[email protected]>
Signed-off-by: Mike Snitzer <[email protected]>

drivers/md/dm-zone.c

@@ -104,6 +104,23 @@ int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(dm_report_zones);
 
+bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
+{
+	struct request_queue *q = md->queue;
+
+	if (!blk_queue_is_zoned(q))
+		return false;
+
+	switch (bio_op(bio)) {
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_WRITE:
+		return !op_is_flush(bio->bi_opf) && bio_sectors(bio);
+	default:
+		return false;
+	}
+}
+
 void dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 {
 	if (!blk_queue_is_zoned(q))

drivers/md/dm.c

@@ -841,22 +841,27 @@ static void dec_pending(struct dm_io *io, blk_status_t error)
 	}
 
 	if (atomic_dec_and_test(&io->io_count)) {
+		bio = io->orig_bio;
 		if (io->status == BLK_STS_DM_REQUEUE) {
 			/*
 			 * Target requested pushing back the I/O.
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
-			if (__noflush_suspending(md))
+			if (__noflush_suspending(md) &&
+			    !WARN_ON_ONCE(dm_is_zone_write(md, bio))) {
 				/* NOTE early return due to BLK_STS_DM_REQUEUE below */
-				bio_list_add_head(&md->deferred, io->orig_bio);
-			else
-				/* noflush suspend was interrupted. */
+				bio_list_add_head(&md->deferred, bio);
+			} else {
+				/*
+				 * noflush suspend was interrupted or this is
+				 * a write to a zoned target.
+				 */
 				io->status = BLK_STS_IOERR;
+			}
 			spin_unlock_irqrestore(&md->deferred_lock, flags);
 		}
 
 		io_error = io->status;
-		bio = io->orig_bio;
 		end_io_acct(io);
 		free_io(md, io);
 
@@ -947,7 +952,15 @@ static void clone_endio(struct bio *bio)
 		int r = endio(tio->ti, bio, &error);
 		switch (r) {
 		case DM_ENDIO_REQUEUE:
-			error = BLK_STS_DM_REQUEUE;
+			/*
+			 * Requeuing writes to a sequential zone of a zoned
+			 * target will break the sequential write pattern:
+			 * fail such IO.
+			 */
+			if (WARN_ON_ONCE(dm_is_zone_write(md, bio)))
+				error = BLK_STS_IOERR;
+			else
+				error = BLK_STS_DM_REQUEUE;
 			fallthrough;
 		case DM_ENDIO_DONE:
 			break;

drivers/md/dm.h

@@ -107,8 +107,13 @@ void dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q);
 #ifdef CONFIG_BLK_DEV_ZONED
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
+bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 #else
 #define dm_blk_report_zones	NULL
+static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
+{
+	return false;
+}
 #endif
 
 /*-----------------------------------------------------------------