Merge tag 'for-4.20/dm-fixes' of...

Merge tag 'for-4.20/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix DM cache metadata to verify that a cache has block before trying
   to continue with operation that requires them.

 - Fix bio-based DM core's dm_make_request() to properly impose device
   limits on individual bios by making use of blk_queue_split().

 - Fix long-standing race with how DM thinp notified userspace of
   thin-pool mode state changes before they were actually made.

 - Fix the zoned target's bio completion handling; this is a fairly
   invassive fix at this stage but it is localized to the zoned target.
   Any zoned target users will benefit from this fix.

* tag 'for-4.20/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm thin: bump target version
  dm thin: send event about thin-pool state change _after_ making it
  dm zoned: Fix target BIO completion handling
  dm: call blk_queue_split() to impose device limits on bios
  dm cache metadata: verify cache has blocks in blocks_are_clean_separate_dirty()

drivers/md/dm-cache-metadata.c

@@ -930,6 +930,10 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd,
 	bool dirty_flag;
 	*result = true;
 
+	if (from_cblock(cmd->cache_blocks) == 0)
+		/* Nothing to do */
+		return 0;
+
 	r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
 				   from_cblock(cmd->cache_blocks), &cmd->dirty_cursor);
 	if (r) {

drivers/md/dm-thin.c

@@ -195,7 +195,7 @@ static void throttle_unlock(struct throttle *t)
 struct dm_thin_new_mapping;
 
 /*
- * The pool runs in 4 modes.  Ordered in degraded order for comparisons.
+ * The pool runs in various modes.  Ordered in degraded order for comparisons.
  */
 enum pool_mode {
 	PM_WRITE,		/* metadata may be changed */
@@ -282,9 +282,38 @@ struct pool {
 	mempool_t mapping_pool;
 };
 
-static enum pool_mode get_pool_mode(struct pool *pool);
 static void metadata_operation_failed(struct pool *pool, const char *op, int r);
 
+static enum pool_mode get_pool_mode(struct pool *pool)
+{
+	return pool->pf.mode;
+}
+
+static void notify_of_pool_mode_change(struct pool *pool)
+{
+	const char *descs[] = {
+		"write",
+		"out-of-data-space",
+		"read-only",
+		"read-only",
+		"fail"
+	};
+	const char *extra_desc = NULL;
+	enum pool_mode mode = get_pool_mode(pool);
+
+	if (mode == PM_OUT_OF_DATA_SPACE) {
+		if (!pool->pf.error_if_no_space)
+			extra_desc = " (queue IO)";
+		else
+			extra_desc = " (error IO)";
+	}
+
+	dm_table_event(pool->ti->table);
+	DMINFO("%s: switching pool to %s%s mode",
+	       dm_device_name(pool->pool_md),
+	       descs[(int)mode], extra_desc ? : "");
+}
+
 /*
  * Target context for a pool.
  */
@@ -2351,8 +2380,6 @@ static void do_waker(struct work_struct *ws)
 	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
 }
 
-static void notify_of_pool_mode_change_to_oods(struct pool *pool);
-
 /*
  * We're holding onto IO to allow userland time to react.  After the
  * timeout either the pool will have been resized (and thus back in
@@ -2365,7 +2392,7 @@ static void do_no_space_timeout(struct work_struct *ws)
 
 	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
 		pool->pf.error_if_no_space = true;
-		notify_of_pool_mode_change_to_oods(pool);
+		notify_of_pool_mode_change(pool);
 		error_retry_list_with_code(pool, BLK_STS_NOSPC);
 	}
 }
@@ -2433,26 +2460,6 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
 
 /*----------------------------------------------------------------*/
 
-static enum pool_mode get_pool_mode(struct pool *pool)
-{
-	return pool->pf.mode;
-}
-
-static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
-{
-	dm_table_event(pool->ti->table);
-	DMINFO("%s: switching pool to %s mode",
-	       dm_device_name(pool->pool_md), new_mode);
-}
-
-static void notify_of_pool_mode_change_to_oods(struct pool *pool)
-{
-	if (!pool->pf.error_if_no_space)
-		notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)");
-	else
-		notify_of_pool_mode_change(pool, "out-of-data-space (error IO)");
-}
-
 static bool passdown_enabled(struct pool_c *pt)
 {
 	return pt->adjusted_pf.discard_passdown;
@@ -2501,8 +2508,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 
 	switch (new_mode) {
 	case PM_FAIL:
-		if (old_mode != new_mode)
-			notify_of_pool_mode_change(pool, "failure");
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_fail;
 		pool->process_discard = process_bio_fail;
@@ -2516,8 +2521,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 
 	case PM_OUT_OF_METADATA_SPACE:
 	case PM_READ_ONLY:
-		if (!is_read_only_pool_mode(old_mode))
-			notify_of_pool_mode_change(pool, "read-only");
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_bio_success;
@@ -2538,8 +2541,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		 * alarming rate.  Adjust your low water mark if you're
 		 * frequently seeing this mode.
 		 */
-		if (old_mode != new_mode)
-			notify_of_pool_mode_change_to_oods(pool);
 		pool->out_of_data_space = true;
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard_bio;
@@ -2552,8 +2553,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		break;
 
 	case PM_WRITE:
-		if (old_mode != new_mode)
-			notify_of_pool_mode_change(pool, "write");
 		if (old_mode == PM_OUT_OF_DATA_SPACE)
 			cancel_delayed_work_sync(&pool->no_space_timeout);
 		pool->out_of_data_space = false;
@@ -2573,6 +2572,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 	 * doesn't cause an unexpected mode transition on resume.
 	 */
 	pt->adjusted_pf.mode = new_mode;
+
+	if (old_mode != new_mode)
+		notify_of_pool_mode_change(pool);
 }
 
 static void abort_transaction(struct pool *pool)
@@ -4023,7 +4025,7 @@ static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 20, 0},
+	.version = {1, 21, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4397,7 +4399,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 20, 0},
+	.version = {1, 21, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,

drivers/md/dm-zoned-target.c

@@ -20,7 +20,6 @@ struct dmz_bioctx {
 	struct dm_zone		*zone;
 	struct bio		*bio;
 	refcount_t		ref;
-	blk_status_t		status;
 };
 
 /*
@@ -78,65 +77,66 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
 {
 	struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
 
-	if (bioctx->status == BLK_STS_OK && status != BLK_STS_OK)
-		bioctx->status = status;
+	if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
+		bio->bi_status = status;
+
+	if (refcount_dec_and_test(&bioctx->ref)) {
+		struct dm_zone *zone = bioctx->zone;
+
+		if (zone) {
+			if (bio->bi_status != BLK_STS_OK &&
+			    bio_op(bio) == REQ_OP_WRITE &&
+			    dmz_is_seq(zone))
+				set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
+			dmz_deactivate_zone(zone);
+		}
 		bio_endio(bio);
+	}
 }
 
 /*
- * Partial clone read BIO completion callback. This terminates the
+ * Completion callback for an internally cloned target BIO. This terminates the
  * target BIO when there are no more references to its context.
  */
-static void dmz_read_bio_end_io(struct bio *bio)
+static void dmz_clone_endio(struct bio *clone)
 {
-	struct dmz_bioctx *bioctx = bio->bi_private;
-	blk_status_t status = bio->bi_status;
+	struct dmz_bioctx *bioctx = clone->bi_private;
+	blk_status_t status = clone->bi_status;
 
-	bio_put(bio);
+	bio_put(clone);
 	dmz_bio_endio(bioctx->bio, status);
 }
 
 /*
- * Issue a BIO to a zone. The BIO may only partially process the
+ * Issue a clone of a target BIO. The clone may only partially process the
  * original target BIO.
  */
-static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone,
+static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,
 			  struct bio *bio, sector_t chunk_block,
 			  unsigned int nr_blocks)
 {
 	struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
-	sector_t sector;
 	struct bio *clone;
 
-	/* BIO remap sector */
-	sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
-
-	/* If the read is not partial, there is no need to clone the BIO */
-	if (nr_blocks == dmz_bio_blocks(bio)) {
-		/* Setup and submit the BIO */
-		bio->bi_iter.bi_sector = sector;
-		refcount_inc(&bioctx->ref);
-		generic_make_request(bio);
-		return 0;
-	}
-
-	/* Partial BIO: we need to clone the BIO */
 	clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
 	if (!clone)
 		return -ENOMEM;
 
-	/* Setup the clone */
-	clone->bi_iter.bi_sector = sector;
+	bio_set_dev(clone, dmz->dev->bdev);
+	clone->bi_iter.bi_sector =
+		dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
 	clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT;
-	clone->bi_end_io = dmz_read_bio_end_io;
+	clone->bi_end_io = dmz_clone_endio;
 	clone->bi_private = bioctx;
 
 	bio_advance(bio, clone->bi_iter.bi_size);
 
-	/* Submit the clone */
 	refcount_inc(&bioctx->ref);
 	generic_make_request(clone);
 
+	if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
+		zone->wp_block += nr_blocks;
+
 	return 0;
 }
 
@@ -214,7 +214,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone,
 		if (nr_blocks) {
 			/* Valid blocks found: read them */
 			nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block);
-			ret = dmz_submit_read_bio(dmz, rzone, bio, chunk_block, nr_blocks);
+			ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks);
 			if (ret)
 				return ret;
 			chunk_block += nr_blocks;
@@ -228,25 +228,6 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone,
 	return 0;
 }
 
-/*
- * Issue a write BIO to a zone.
- */
-static void dmz_submit_write_bio(struct dmz_target *dmz, struct dm_zone *zone,
-				 struct bio *bio, sector_t chunk_block,
-				 unsigned int nr_blocks)
-{
-	struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
-
-	/* Setup and submit the BIO */
-	bio_set_dev(bio, dmz->dev->bdev);
-	bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
-	refcount_inc(&bioctx->ref);
-	generic_make_request(bio);
-
-	if (dmz_is_seq(zone))
-		zone->wp_block += nr_blocks;
-}
-
 /*
  * Write blocks directly in a data zone, at the write pointer.
  * If a buffer zone is assigned, invalidate the blocks written
@@ -265,7 +246,9 @@ static int dmz_handle_direct_write(struct dmz_target *dmz,
 		return -EROFS;
 
 	/* Submit write */
-	dmz_submit_write_bio(dmz, zone, bio, chunk_block, nr_blocks);
+	ret = dmz_submit_bio(dmz, zone, bio, chunk_block, nr_blocks);
+	if (ret)
+		return ret;
 
 	/*
 	 * Validate the blocks in the data zone and invalidate
@@ -301,7 +284,9 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz,
 		return -EROFS;
 
 	/* Submit write */
-	dmz_submit_write_bio(dmz, bzone, bio, chunk_block, nr_blocks);
+	ret = dmz_submit_bio(dmz, bzone, bio, chunk_block, nr_blocks);
+	if (ret)
+		return ret;
 
 	/*
 	 * Validate the blocks in the buffer zone
@@ -600,7 +585,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
 	bioctx->zone = NULL;
 	bioctx->bio = bio;
 	refcount_set(&bioctx->ref, 1);
-	bioctx->status = BLK_STS_OK;
 
 	/* Set the BIO pending in the flush list */
 	if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) {
@@ -623,35 +607,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_SUBMITTED;
 }
 
-/*
- * Completed target BIO processing.
- */
-static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error)
-{
-	struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
-
-	if (bioctx->status == BLK_STS_OK && *error)
-		bioctx->status = *error;
-
-	if (!refcount_dec_and_test(&bioctx->ref))
-		return DM_ENDIO_INCOMPLETE;
-
-	/* Done */
-	bio->bi_status = bioctx->status;
-
-	if (bioctx->zone) {
-		struct dm_zone *zone = bioctx->zone;
-
-		if (*error && bio_op(bio) == REQ_OP_WRITE) {
-			if (dmz_is_seq(zone))
-				set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
-		}
-		dmz_deactivate_zone(zone);
-	}
-
-	return DM_ENDIO_DONE;
-}
-
 /*
  * Get zoned device information.
  */
@@ -946,7 +901,6 @@ static struct target_type dmz_type = {
 	.ctr		 = dmz_ctr,
 	.dtr		 = dmz_dtr,
 	.map		 = dmz_map,
-	.end_io		 = dmz_end_io,
 	.io_hints	 = dmz_io_hints,
 	.prepare_ioctl	 = dmz_prepare_ioctl,
 	.postsuspend	 = dmz_suspend,

drivers/md/dm.c

@@ -1593,6 +1593,8 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		return ret;
 	}
 
+	blk_queue_split(md->queue, &bio);
+
 	init_clone_info(&ci, md, map, bio);
 
 	if (bio->bi_opf & REQ_PREFLUSH) {