Merge tag 'for-5.19/dm-fixes-4' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix DM era to commit metadata during suspend using drain_workqueue
   instead of flush_workqueue.

 - Fix DM core's dm_io_complete to not return early if io error is
   BLK_STS_AGAIN but bio polling is not in use.

 - Fix DM core's dm_io_complete BLK_STS_DM_REQUEUE handling when dm_io
   represents a split bio.

 - Fix recent DM mirror log regression by clearing bits up to
   BITS_PER_LONG boundary.

* tag 'for-5.19/dm-fixes-4' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm mirror log: clear log bits up to BITS_PER_LONG boundary
  dm: fix BLK_STS_DM_REQUEUE handling when dm_io represents split bio
  dm: do not return early from dm_io_complete if BLK_STS_AGAIN without polling
  dm era: commit metadata in postsuspend after worker stops

Author: torvalds

drivers/md/dm-core.h

@@ -272,6 +272,7 @@ struct dm_io {
 	atomic_t io_count;
 	struct mapped_device *md;
 
+	struct bio *split_bio;
 	/* The three fields represent mapped part of original bio */
 	struct bio *orig_bio;
 	unsigned int sector_offset; /* offset to end of orig_bio */

drivers/md/dm-era-target.c

@@ -1400,7 +1400,7 @@ static void start_worker(struct era *era)
 static void stop_worker(struct era *era)
 {
 	atomic_set(&era->suspended, 1);
-	flush_workqueue(era->wq);
+	drain_workqueue(era->wq);
 }
 
 /*----------------------------------------------------------------
@@ -1570,6 +1570,12 @@ static void era_postsuspend(struct dm_target *ti)
 	}
 
 	stop_worker(era);
+
+	r = metadata_commit(era->md);
+	if (r) {
+		DMERR("%s: metadata_commit failed", __func__);
+		/* FIXME: fail mode */
+	}
 }
 
 static int era_preresume(struct dm_target *ti)

drivers/md/dm-log.c

@@ -615,7 +615,7 @@ static int disk_resume(struct dm_dirty_log *log)
 			log_clear_bit(lc, lc->clean_bits, i);
 
 	/* clear any old bits -- device has shrunk */
-	for (i = lc->region_count; i % (sizeof(*lc->clean_bits) << BYTE_SHIFT); i++)
+	for (i = lc->region_count; i % BITS_PER_LONG; i++)
 		log_clear_bit(lc, lc->clean_bits, i);
 
 	/* copy clean across to sync */

drivers/md/dm.c

@@ -594,6 +594,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
 	atomic_set(&io->io_count, 2);
 	this_cpu_inc(*md->pending_io);
 	io->orig_bio = bio;
+	io->split_bio = NULL;
 	io->md = md;
 	spin_lock_init(&io->lock);
 	io->start_time = jiffies;
@@ -887,7 +888,7 @@ static void dm_io_complete(struct dm_io *io)
 {
 	blk_status_t io_error;
 	struct mapped_device *md = io->md;
-	struct bio *bio = io->orig_bio;
+	struct bio *bio = io->split_bio ? io->split_bio : io->orig_bio;
 
 	if (io->status == BLK_STS_DM_REQUEUE) {
 		unsigned long flags;
@@ -939,9 +940,11 @@ static void dm_io_complete(struct dm_io *io)
 			if (io_error == BLK_STS_AGAIN) {
 				/* io_uring doesn't handle BLK_STS_AGAIN (yet) */
 				queue_io(md, bio);
+				return;
 			}
 		}
-		return;
+		if (io_error == BLK_STS_DM_REQUEUE)
+			return;
 	}
 
 	if (bio_is_flush_with_data(bio)) {
@@ -1691,9 +1694,11 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 	 * Remainder must be passed to submit_bio_noacct() so it gets handled
 	 * *after* bios already submitted have been completely processed.
 	 */
-	bio_trim(bio, io->sectors, ci.sector_count);
-	trace_block_split(bio, bio->bi_iter.bi_sector);
-	bio_inc_remaining(bio);
+	WARN_ON_ONCE(!dm_io_flagged(io, DM_IO_WAS_SPLIT));
+	io->split_bio = bio_split(bio, io->sectors, GFP_NOIO,
+				  &md->queue->bio_split);
+	bio_chain(io->split_bio, bio);
+	trace_block_split(io->split_bio, bio->bi_iter.bi_sector);
 	submit_bio_noacct(bio);
 out:
 	/*