1 files changed, 34 insertions, 55 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c18fc2548518..b3c3c8b4cb42 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -476,8 +476,10 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 		return -EAGAIN;
 
 	map = dm_get_live_table(md, &srcu_idx);
-	if (!map)
-		return -EIO;
+	if (!map) {
+		ret = -EIO;
+		goto out;
+	}
 
 	do {
 		struct dm_target *tgt;
@@ -507,7 +509,6 @@ out:
 
 static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
 			    struct block_device **bdev)
-	__acquires(md->io_barrier)
 {
 	struct dm_target *tgt;
 	struct dm_table *map;
@@ -541,7 +542,6 @@ retry:
 }
 
 static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx)
-	__releases(md->io_barrier)
 {
 	dm_put_live_table(md, srcu_idx);
 }
@@ -570,7 +570,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 		}
 	}
 
-	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	if (!bdev->bd_disk->fops->ioctl)
+		r = -ENOTTY;
+	else
+		r = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
 out:
 	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
@@ -1037,15 +1040,18 @@ static sector_t max_io_len(struct dm_target *ti, sector_t sector)
 	sector_t max_len;
 
 	/*
-	 * Does the target need to split even further?
-	 * - q->limits.chunk_sectors reflects ti->max_io_len so
-	 *   blk_max_size_offset() provides required splitting.
-	 * - blk_max_size_offset() also respects q->limits.max_sectors
+	 * Does the target need to split IO even further?
+	 * - varied (per target) IO splitting is a tenet of DM; this
+	 *   explains why stacked chunk_sectors based splitting via
+	 *   blk_max_size_offset() isn't possible here. So pass in
+	 *   ti->max_io_len to override stacked chunk_sectors.
 	 */
-	max_len = blk_max_size_offset(ti->table->md->queue,
-				      target_offset);
-	if (len > max_len)
-		len = max_len;
+	if (ti->max_io_len) {
+		max_len = blk_max_size_offset(ti->table->md->queue,
+					      target_offset, ti->max_io_len);
+		if (len > max_len)
+			len = max_len;
+	}
 
 	return len;
 }
@@ -1196,11 +1202,9 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 		 * ->zero_page_range() is mandatory dax operation. If we are
 		 *  here, something is wrong.
 		 */
-		dm_put_live_table(md, srcu_idx);
 		goto out;
 	}
 	ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages);
-
  out:
 	dm_put_live_table(md, srcu_idx);
 
@@ -1273,8 +1277,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		break;
 	case DM_MAPIO_REMAPPED:
 		/* the bio has been remapped so dispatch it */
-		trace_block_bio_remap(clone->bi_disk->queue, clone,
-				      bio_dev(io->orig_bio), sector);
+		trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector);
 		ret = submit_bio_noacct(clone);
 		break;
 	case DM_MAPIO_KILL:
@@ -1419,18 +1422,12 @@ static int __send_empty_flush(struct clone_info *ci)
 	 */
 	bio_init(&flush_bio, NULL, 0);
 	flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+	flush_bio.bi_disk = ci->io->md->disk;
+	bio_associate_blkg(&flush_bio);
+
 	ci->bio = &flush_bio;
 	ci->sector_count = 0;
 
-	/*
-	 * Empty flush uses a statically initialized bio, as the base for
-	 * cloning.  However, blkg association requires that a bdev is
-	 * associated with a gendisk, which doesn't happen until the bdev is
-	 * opened.  So, blkg association is done at issue time of the flush
-	 * rather than when the device is created in alloc_dev().
-	 */
-	bio_set_dev(ci->bio, ci->io->md->bdev);
-
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
@@ -1589,7 +1586,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		ci.sector_count = bio_sectors(bio);
 		while (ci.sector_count && !error) {
 			error = __split_and_process_non_flush(&ci);
-			if (current->bio_list && ci.sector_count && !error) {
+			if (ci.sector_count && !error) {
 				/*
 				 * Remainder must be passed to submit_bio_noacct()
 				 * so that it gets handled *after* bios already submitted
@@ -1610,12 +1607,12 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * (by eliminating DM's splitting and just using bio_split)
 				 */
 				part_stat_lock();
-				__dm_part_stat_sub(&dm_disk(md)->part0,
+				__dm_part_stat_sub(dm_disk(md)->part0,
 						   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
 				part_stat_unlock();
 
 				bio_chain(b, bio);
-				trace_block_split(md->queue, b, bio->bi_iter.bi_sector);
+				trace_block_split(b, bio->bi_iter.bi_sector);
 				ret = submit_bio_noacct(bio);
 				break;
 			}
@@ -1747,11 +1744,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 
 	cleanup_srcu_struct(&md->io_barrier);
 
-	if (md->bdev) {
-		bdput(md->bdev);
-		md->bdev = NULL;
-	}
-
 	mutex_destroy(&md->suspend_lock);
 	mutex_destroy(&md->type_lock);
 	mutex_destroy(&md->table_devices_lock);
@@ -1843,10 +1835,6 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->wq)
 		goto bad;
 
-	md->bdev = bdget_disk(md->disk, 0);
-	if (!md->bdev)
-		goto bad;
-
 	dm_stats_init(&md->stats);
 
 	/* Populate the mapping, nobody knows we exist yet */
@@ -1971,8 +1959,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (size != dm_get_size(md))
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	set_capacity(md->disk, size);
-	bd_set_nr_sectors(md->bdev, size);
+	set_capacity_and_notify(md->disk, size);
 
 	dm_table_event_callback(t, event_callback, md);
 
@@ -2255,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put);
 static bool md_in_flight_bios(struct mapped_device *md)
 {
 	int cpu;
-	struct hd_struct *part = &dm_disk(md)->part0;
+	struct block_device *part = dm_disk(md)->part0;
 	long sum = 0;
 
 	for_each_possible_cpu(cpu) {
@@ -2390,27 +2377,19 @@ static int lock_fs(struct mapped_device *md)
 {
 	int r;
 
-	WARN_ON(md->frozen_sb);
-
-	md->frozen_sb = freeze_bdev(md->bdev);
-	if (IS_ERR(md->frozen_sb)) {
-		r = PTR_ERR(md->frozen_sb);
-		md->frozen_sb = NULL;
-		return r;
-	}
-
-	set_bit(DMF_FROZEN, &md->flags);
+	WARN_ON(test_bit(DMF_FROZEN, &md->flags));
 
-	return 0;
+	r = freeze_bdev(md->disk->part0);
+	if (!r)
+		set_bit(DMF_FROZEN, &md->flags);
+	return r;
 }
 
 static void unlock_fs(struct mapped_device *md)
 {
 	if (!test_bit(DMF_FROZEN, &md->flags))
 		return;
-
-	thaw_bdev(md->bdev, md->frozen_sb);
-	md->frozen_sb = NULL;
+	thaw_bdev(md->disk->part0);
 	clear_bit(DMF_FROZEN, &md->flags);
 }