dm zoned: properly handle backing device failure

dm-zoned is observed to lock up or livelock in case of hardware
failure or some misconfiguration of the backing zoned device.

This patch adds a new dm-zoned target function that checks the status of
the backing device. If the request queue of the backing device is found
to be in dying state or the SCSI backing device enters offline state,
the health check code sets a dm-zoned target flag prompting all further
incoming I/O to be rejected. In order to detect backing device failures
timely, this new function is called in the request mapping path, at the
beginning of every reclaim run and before performing any metadata I/O.

The proper way out of this situation is to do

dmsetup remove <dm-zoned target>

and recreate the target when the problem with the backing device
is resolved.

Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

1 files changed, 43 insertions, 2 deletions

diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 944db71ed3d7..ff3fd011796e 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -133,6 +133,8 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,
 
 	refcount_inc(&bioctx->ref);
 	generic_make_request(clone);
+	if (clone->bi_status == BLK_STS_IOERR)
+		return -EIO;
 
 	if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
 		zone->wp_block += nr_blocks;
@@ -277,8 +279,8 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz,
 
 	/* Get the buffer zone. One will be allocated if needed */
 	bzone = dmz_get_chunk_buffer(zmd, zone);
-	if (!bzone)
-		return -ENOSPC;
+	if (IS_ERR(bzone))
+		return PTR_ERR(bzone);
 
 	if (dmz_is_readonly(bzone))
 		return -EROFS;
@@ -389,6 +391,11 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,
 
 	dmz_lock_metadata(zmd);
 
+	if (dmz->dev->flags & DMZ_BDEV_DYING) {
+		ret = -EIO;
+		goto out;
+	}
+
 	/*
 	 * Get the data zone mapping the chunk. There may be no
 	 * mapping for read and discard. If a mapping is obtained,
@@ -493,6 +500,8 @@ static void dmz_flush_work(struct work_struct *work)
 
 	/* Flush dirty metadata blocks */
 	ret = dmz_flush_metadata(dmz->metadata);
+	if (ret)
+		dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret);
 
 	/* Process queued flush requests */
 	while (1) {
@@ -557,6 +566,32 @@ out:
 }
 
 /*
+ * Check the backing device availability. If it's on the way out,
+ * start failing I/O. Reclaim and metadata components also call this
+ * function to cleanly abort operation in the event of such failure.
+ */
+bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev)
+{
+	struct gendisk *disk;
+
+	if (!(dmz_dev->flags & DMZ_BDEV_DYING)) {
+		disk = dmz_dev->bdev->bd_disk;
+		if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
+			dmz_dev_warn(dmz_dev, "Backing device queue dying");
+			dmz_dev->flags |= DMZ_BDEV_DYING;
+		} else if (disk->fops->check_events) {
+			if (disk->fops->check_events(disk, 0) &
+					DISK_EVENT_MEDIA_CHANGE) {
+				dmz_dev_warn(dmz_dev, "Backing device offline");
+				dmz_dev->flags |= DMZ_BDEV_DYING;
+			}
+		}
+	}
+
+	return dmz_dev->flags & DMZ_BDEV_DYING;
+}
+
+/*
  * Process a new BIO.
  */
 static int dmz_map(struct dm_target *ti, struct bio *bio)
@@ -569,6 +604,9 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
 	sector_t chunk_sector;
 	int ret;
 
+	if (dmz_bdev_is_dying(dmz->dev))
+		return DM_MAPIO_KILL;
+
 	dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks",
 		      bio_op(bio), (unsigned long long)sector, nr_sectors,
 		      (unsigned long long)dmz_bio_chunk(dmz->dev, bio),
@@ -865,6 +903,9 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct dmz_target *dmz = ti->private;
 
+	if (dmz_bdev_is_dying(dmz->dev))
+		return -ENODEV;
+
 	*bdev = dmz->dev->bdev;
 
 	return 0;