Quite a few fixes for DM's blk-mq support thanks to extra DM multipath

testing from Junichi Nomura and Bart Van Assche.
 
 Also fix a casting bug in dm_merge_bvec() that could cause only a single
 page to be added to a bio (Joe identified this while testing dm-cache
 writeback).
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJVaLGPAAoJEMUj8QotnQNa1pcH/3TumkM0rvl1DK7DfWvjgfpp
 +h+whWn79lOUzan/AszRvRU4Pwr7symndnJzJ/tqQ76fm8x84obvKa0jFfB9rmlM
 sgw45alqB+AKcKAvocsuDIdzy2/K8FHBihccPWhe87AtJRlj57nTOJWO06gzExOp
 /AJ/0Vgv3pxUCL2M4XucpQOV8eUg+gpwjDMxuMEsPVzBVYJfuRvNKoERtd9LSCSV
 Y5iqdHCJiW0SWesZNrfthAAlReFzqb1c3mq55G0q0C+Z77Jf3TIPBhVfouM4NOKt
 wjQoPavzyAEiKfLFy6QFCjhSOXKCI3klqO7zcyzyygVue5UTHICYRJKn7TFtbfU=
 =xGAV
 -----END PGP SIGNATURE-----

Merge tag 'dm-4.1-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device-mapper fixes from Mike Snitzer:
 "Quite a few fixes for DM's blk-mq support thanks to extra DM multipath
  testing from Junichi Nomura and Bart Van Assche.

  Also fix a casting bug in dm_merge_bvec() that could cause only a
  single page to be added to a bio (Joe identified this while testing
  dm-cache writeback)"

* tag 'dm-4.1-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: fix casting bug in dm_merge_bvec()
  dm: fix reload failure of 0 path multipath mapping on blk-mq devices
  dm: fix false warning in free_rq_clone() for unmapped requests
  dm: requeue from blk-mq dm_mq_queue_rq() using BLK_MQ_RQ_QUEUE_BUSY
  dm mpath: fix leak of dm_mpath_io structure in blk-mq .queue_rq error path
  dm: fix NULL pointer when clone_and_map_rq returns !DM_MAPIO_REMAPPED
  dm: run queue on re-queue

drivers/md/dm-mpath.c

@@ -429,9 +429,11 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		/* blk-mq request-based interface */
 		*__clone = blk_get_request(bdev_get_queue(bdev),
 					   rq_data_dir(rq), GFP_ATOMIC);
-		if (IS_ERR(*__clone))
+		if (IS_ERR(*__clone)) {
 			/* ENOMEM, requeue */
+			clear_mapinfo(m, map_context);
 			return r;
+		}
 		(*__clone)->bio = (*__clone)->biotail = NULL;
 		(*__clone)->rq_disk = bdev->bd_disk;
 		(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;

drivers/md/dm-table.c

@@ -820,6 +820,12 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
 }
 EXPORT_SYMBOL(dm_consume_args);
 
+static bool __table_type_request_based(unsigned table_type)
+{
+	return (table_type == DM_TYPE_REQUEST_BASED ||
+		table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
 static int dm_table_set_type(struct dm_table *t)
 {
 	unsigned i;
@@ -852,8 +858,7 @@ static int dm_table_set_type(struct dm_table *t)
 		 * Determine the type from the live device.
 		 * Default to bio-based if device is new.
 		 */
-		if (live_md_type == DM_TYPE_REQUEST_BASED ||
-		    live_md_type == DM_TYPE_MQ_REQUEST_BASED)
+		if (__table_type_request_based(live_md_type))
 			request_based = 1;
 		else
 			bio_based = 1;
@@ -903,7 +908,7 @@ static int dm_table_set_type(struct dm_table *t)
 			}
 		t->type = DM_TYPE_MQ_REQUEST_BASED;
 
-	} else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+	} else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
 		/* inherit live MD type */
 		t->type = live_md_type;
 
@@ -925,10 +930,7 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 
 bool dm_table_request_based(struct dm_table *t)
 {
-	unsigned table_type = dm_table_get_type(t);
-
-	return (table_type == DM_TYPE_REQUEST_BASED ||
-		table_type == DM_TYPE_MQ_REQUEST_BASED);
+	return __table_type_request_based(dm_table_get_type(t));
 }
 
 bool dm_table_mq_request_based(struct dm_table *t)

drivers/md/dm.c

@@ -1082,13 +1082,11 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	dm_put(md);
 }
 
-static void free_rq_clone(struct request *clone, bool must_be_mapped)
+static void free_rq_clone(struct request *clone)
 {
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct mapped_device *md = tio->md;
 
-	WARN_ON_ONCE(must_be_mapped && !clone->q);
-
 	blk_rq_unprep_clone(clone);
 
 	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
@@ -1132,7 +1130,7 @@ static void dm_end_request(struct request *clone, int error)
 			rq->sense_len = clone->sense_len;
 	}
 
-	free_rq_clone(clone, true);
+	free_rq_clone(clone);
 	if (!rq->q->mq_ops)
 		blk_end_request_all(rq, error);
 	else
@@ -1151,7 +1149,7 @@ static void dm_unprep_request(struct request *rq)
 	}
 
 	if (clone)
-		free_rq_clone(clone, false);
+		free_rq_clone(clone);
 }
 
 /*
@@ -1164,6 +1162,7 @@ static void old_requeue_request(struct request *rq)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 	blk_requeue_request(q, rq);
+	blk_run_queue_async(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -1724,8 +1723,7 @@ static int dm_merge_bvec(struct request_queue *q,
 	struct mapped_device *md = q->queuedata;
 	struct dm_table *map = dm_get_live_table_fast(md);
 	struct dm_target *ti;
-	sector_t max_sectors;
-	int max_size = 0;
+	sector_t max_sectors, max_size = 0;
 
 	if (unlikely(!map))
 		goto out;
@@ -1740,8 +1738,16 @@ static int dm_merge_bvec(struct request_queue *q,
 	max_sectors = min(max_io_len(bvm->bi_sector, ti),
 			  (sector_t) queue_max_sectors(q));
 	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-	if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */
-		max_size = 0;
+
+	/*
+	 * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
+	 * to the targets' merge function since it holds sectors not bytes).
+	 * Just doing this as an interim fix for stable@ because the more
+	 * comprehensive cleanup of switching to sector_t will impact every
+	 * DM target that implements a ->merge hook.
+	 */
+	if (max_size > INT_MAX)
+		max_size = INT_MAX;
 
 	/*
 	 * merge_bvec_fn() returns number of bytes
@@ -1749,7 +1755,7 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * max is precomputed maximal io size
 	 */
 	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, max_size);
+		max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
 	/*
 	 * If the target doesn't support merge method and some of the devices
 	 * provided their merge_bvec method (we know this by looking for the
@@ -1971,8 +1977,8 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 			dm_kill_unmapped_request(rq, r);
 			return r;
 		}
-		if (IS_ERR(clone))
-			return DM_MAPIO_REQUEUE;
+		if (r != DM_MAPIO_REMAPPED)
+			return r;
 		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
 			/* -ENOMEM */
 			ti->type->release_clone_rq(clone);
@@ -2753,13 +2759,15 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
 		/* clone request is allocated at the end of the pdu */
 		tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
-		if (!clone_rq(rq, md, tio, GFP_ATOMIC))
-			return BLK_MQ_RQ_QUEUE_BUSY;
+		(void) clone_rq(rq, md, tio, GFP_ATOMIC);
 		queue_kthread_work(&md->kworker, &tio->work);
 	} else {
 		/* Direct call is fine since .queue_rq allows allocations */
-		if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-			dm_requeue_unmapped_original_request(md, rq);
+		if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+			/* Undo dm_start_request() before requeuing */
+			rq_completed(md, rq_data_dir(rq), false);
+			return BLK_MQ_RQ_QUEUE_BUSY;
+		}
 	}
 
 	return BLK_MQ_RQ_QUEUE_OK;