Merge tag 'for-5.5/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Fix DM core to disallow stacking request-based DM on partitions.

 - Fix DM raid target to properly resync raidset even if bitmap needed
   additional pages.

 - Fix DM crypt performance regression due to use of WQ_HIGHPRI for the
   IO and crypt workqueues.

 - Fix DM integrity metadata layout that was aligned on 128K boundary
   rather than the intended 4K boundary (removes 124K of wasted space
   for each metadata block).

 - Improve the DM thin, cache and clone targets to use spin_lock_irq
   rather than spin_lock_irqsave where possible.

 - Fix DM thin single thread performance that was lost due to needless
   workqueue wakeups.

 - Fix DM zoned target performance that was lost due to excessive
   backing device checks.

 - Add ability to trigger write failure with the DM dust test target.

 - Fix whitespace indentation in drivers/md/Kconfig.

 - Various smalls fixes and cleanups (e.g. use struct_size, fix
   uninitialized variable, variable renames, etc).

* tag 'for-5.5/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (22 commits)
  Revert "dm crypt: use WQ_HIGHPRI for the IO and crypt workqueues"
  dm: Fix Kconfig indentation
  dm thin: wakeup worker only when deferred bios exist
  dm integrity: fix excessive alignment of metadata runs
  dm raid: Remove unnecessary negation of a shift in raid10_format_to_md_layout
  dm zoned: reduce overhead of backing device checks
  dm dust: add limited write failure mode
  dm dust: change ret to r in dust_map_read and dust_map
  dm dust: change result vars to r
  dm cache: replace spin_lock_irqsave with spin_lock_irq
  dm bio prison: replace spin_lock_irqsave with spin_lock_irq
  dm thin: replace spin_lock_irqsave with spin_lock_irq
  dm clone: add bucket_lock_irq/bucket_unlock_irq helpers
  dm clone: replace spin_lock_irqsave with spin_lock_irq
  dm writecache: handle REQ_FUA
  dm writecache: fix uninitialized variable warning
  dm stripe: use struct_size() in kmalloc()
  dm raid: streamline rs_get_progress() and its raid_status() caller side
  dm raid: simplify rs_setup_recovery call chain
  dm raid: to ensure resynchronization, perform raid set grow in preresume
  ...

1 files changed, 38 insertions, 16 deletions

diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index d3bcc4197f5d..4574e0dedbd6 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -80,6 +80,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
 
 	if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
 		bio->bi_status = status;
+	if (bio->bi_status != BLK_STS_OK)
+		bioctx->target->dev->flags |= DMZ_CHECK_BDEV;
 
 	if (refcount_dec_and_test(&bioctx->ref)) {
 		struct dm_zone *zone = bioctx->zone;
@@ -565,32 +567,52 @@ out:
 }
 
 /*
- * Check the backing device availability. If it's on the way out,
+ * Check if the backing device is being removed. 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)
+		return true;
 
-	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;
-			}
-		}
+	if (dmz_dev->flags & DMZ_CHECK_BDEV)
+		return !dmz_check_bdev(dmz_dev);
+
+	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;
 	}
 
 	return dmz_dev->flags & DMZ_BDEV_DYING;
 }
 
 /*
+ * Check the backing device availability. This detects such events as
+ * backing device going offline due to errors, media removals, etc.
+ * This check is less efficient than dmz_bdev_is_dying() and should
+ * only be performed as a part of error handling.
+ */
+bool dmz_check_bdev(struct dmz_dev *dmz_dev)
+{
+	struct gendisk *disk;
+
+	dmz_dev->flags &= ~DMZ_CHECK_BDEV;
+
+	if (dmz_bdev_is_dying(dmz_dev))
+		return false;
+
+	disk = dmz_dev->bdev->bd_disk;
+	if (disk->fops->check_events &&
+	    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)
@@ -902,8 +924,8 @@ 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;
+	if (!dmz_check_bdev(dmz->dev))
+		return -EIO;
 
 	*bdev = dmz->dev->bdev;