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, 41 insertions, 10 deletions

diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 935d9be5af39..2882897aece2 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -402,15 +402,18 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd,
 	sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no;
 	struct bio *bio;
 
+	if (dmz_bdev_is_dying(zmd->dev))
+		return ERR_PTR(-EIO);
+
 	/* Get a new block and a BIO to read it */
 	mblk = dmz_alloc_mblock(zmd, mblk_no);
 	if (!mblk)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio) {
 		dmz_free_mblock(zmd, mblk);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	spin_lock(&zmd->mblk_lock);
@@ -541,8 +544,8 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 	if (!mblk) {
 		/* Cache miss: read the block from disk */
 		mblk = dmz_get_mblock_slow(zmd, mblk_no);
-		if (!mblk)
-			return ERR_PTR(-ENOMEM);
+		if (IS_ERR(mblk))
+			return mblk;
 	}
 
 	/* Wait for on-going read I/O and check for error */
@@ -570,16 +573,19 @@ static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk)
 /*
  * Issue a metadata block write BIO.
  */
-static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
-			     unsigned int set)
+static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
+			    unsigned int set)
 {
 	sector_t block = zmd->sb[set].block + mblk->no;
 	struct bio *bio;
 
+	if (dmz_bdev_is_dying(zmd->dev))
+		return -EIO;
+
 	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio) {
 		set_bit(DMZ_META_ERROR, &mblk->state);
-		return;
+		return -ENOMEM;
 	}
 
 	set_bit(DMZ_META_WRITING, &mblk->state);
@@ -591,6 +597,8 @@ static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
 	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO);
 	bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
 	submit_bio(bio);
+
+	return 0;
 }
 
 /*
@@ -602,6 +610,9 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
 	struct bio *bio;
 	int ret;
 
+	if (dmz_bdev_is_dying(zmd->dev))
+		return -EIO;
+
 	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio)
 		return -ENOMEM;
@@ -659,22 +670,29 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 {
 	struct dmz_mblock *mblk;
 	struct blk_plug plug;
-	int ret = 0;
+	int ret = 0, nr_mblks_submitted = 0;
 
 	/* Issue writes */
 	blk_start_plug(&plug);
-	list_for_each_entry(mblk, write_list, link)
-		dmz_write_mblock(zmd, mblk, set);
+	list_for_each_entry(mblk, write_list, link) {
+		ret = dmz_write_mblock(zmd, mblk, set);
+		if (ret)
+			break;
+		nr_mblks_submitted++;
+	}
 	blk_finish_plug(&plug);
 
 	/* Wait for completion */
 	list_for_each_entry(mblk, write_list, link) {
+		if (!nr_mblks_submitted)
+			break;
 		wait_on_bit_io(&mblk->state, DMZ_META_WRITING,
 			       TASK_UNINTERRUPTIBLE);
 		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 			clear_bit(DMZ_META_ERROR, &mblk->state);
 			ret = -EIO;
 		}
+		nr_mblks_submitted--;
 	}
 
 	/* Flush drive cache (this will also sync data) */
@@ -736,6 +754,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	dmz_lock_flush(zmd);
 
+	if (dmz_bdev_is_dying(zmd->dev)) {
+		ret = -EIO;
+		goto out;
+	}
+
 	/* Get dirty blocks */
 	spin_lock(&zmd->mblk_lock);
 	list_splice_init(&zmd->mblk_dirty_list, &write_list);
@@ -1631,6 +1654,10 @@ again:
 		/* Alloate a random zone */
 		dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
 		if (!dzone) {
+			if (dmz_bdev_is_dying(zmd->dev)) {
+				dzone = ERR_PTR(-EIO);
+				goto out;
+			}
 			dmz_wait_for_free_zones(zmd);
 			goto again;
 		}
@@ -1728,6 +1755,10 @@ again:
 	/* Alloate a random zone */
 	bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
 	if (!bzone) {
+		if (dmz_bdev_is_dying(zmd->dev)) {
+			bzone = ERR_PTR(-EIO);
+			goto out;
+		}
 		dmz_wait_for_free_zones(zmd);
 		goto again;
 	}