dm: allocate requests in target when stacking on blk-mq devices

For blk-mq request-based DM the responsibility of allocating a cloned
request is transfered from DM core to the target type.  Doing so
enables the cloned request to be allocated from the appropriate
blk-mq request_queue's pool (only the DM target, e.g. multipath, can
know which block device to send a given cloned request to).

Care was taken to preserve compatibility with old-style block request
completion that requires request-based DM _not_ acquire the clone
request's queue lock in the completion path.  As such, there are now 2
different request-based DM target_type interfaces:
1) the original .map_rq() interface will continue to be used for
   non-blk-mq devices -- the preallocated clone request is passed in
   from DM core.
2) a new .clone_and_map_rq() and .release_clone_rq() will be used for
   blk-mq devices -- blk_get_request() and blk_put_request() are used
   respectively from these hooks.

dm_table_set_type() was updated to detect if the request-based target is
being stacked on blk-mq devices, if so DM_TYPE_MQ_REQUEST_BASED is set.
DM core disallows switching the DM table's type after it is set.  This
means that there is no mixing of non-blk-mq and blk-mq devices within
the same request-based DM table.

[This patch was started by Keith and later heavily modified by Mike]

Tested-by: Bart Van Assche <[email protected]>
Signed-off-by: Keith Busch <[email protected]>
Signed-off-by: Mike Snitzer <[email protected]>

drivers/md/dm-mpath.c

@@ -11,6 +11,7 @@
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
+#include <linux/blkdev.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/mempool.h>
@@ -378,12 +379,13 @@ static int __must_push_back(struct multipath *m)
 /*
  * Map cloned requests
  */
-static int multipath_map(struct dm_target *ti, struct request *clone,
-			 union map_info *map_context)
+static int __multipath_map(struct dm_target *ti, struct request *clone,
+			   union map_info *map_context,
+			   struct request *rq, struct request **__clone)
 {
 	struct multipath *m = (struct multipath *) ti->private;
 	int r = DM_MAPIO_REQUEUE;
-	size_t nr_bytes = blk_rq_bytes(clone);
+	size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
 	struct pgpath *pgpath;
 	struct block_device *bdev;
 	struct dm_mpath_io *mpio;
@@ -416,12 +418,25 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
 
 	bdev = pgpath->path.dev->bdev;
 
-	clone->q = bdev_get_queue(bdev);
-	clone->rq_disk = bdev->bd_disk;
-	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-
 	spin_unlock_irq(&m->lock);
 
+	if (clone) {
+		/* Old request-based interface: allocated clone is passed in */
+		clone->q = bdev_get_queue(bdev);
+		clone->rq_disk = bdev->bd_disk;
+		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	} else {
+		/* blk-mq request-based interface */
+		*__clone = blk_get_request(bdev_get_queue(bdev),
+					   rq_data_dir(rq), GFP_KERNEL);
+		if (IS_ERR(*__clone))
+			/* ENOMEM, requeue */
+			return r;
+		(*__clone)->bio = (*__clone)->biotail = NULL;
+		(*__clone)->rq_disk = bdev->bd_disk;
+		(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	}
+
 	if (pgpath->pg->ps.type->start_io)
 		pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
 					      &pgpath->path,
@@ -434,6 +449,24 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
 	return r;
 }
 
+static int multipath_map(struct dm_target *ti, struct request *clone,
+			 union map_info *map_context)
+{
+	return __multipath_map(ti, clone, map_context, NULL, NULL);
+}
+
+static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
+				   union map_info *map_context,
+				   struct request **clone)
+{
+	return __multipath_map(ti, NULL, map_context, rq, clone);
+}
+
+static void multipath_release_clone(struct request *clone)
+{
+	blk_put_request(clone);
+}
+
 /*
  * If we run out of usable paths, should we queue I/O or error it?
  */
@@ -1670,11 +1703,13 @@ static int multipath_busy(struct dm_target *ti)
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 7, 0},
+	.version = {1, 8, 0},
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
 	.map_rq = multipath_map,
+	.clone_and_map_rq = multipath_clone_and_map,
+	.release_clone_rq = multipath_release_clone,
 	.rq_end_io = multipath_end_io,
 	.presuspend = multipath_presuspend,
 	.postsuspend = multipath_postsuspend,

drivers/md/dm-table.c

@@ -827,6 +827,7 @@ static int dm_table_set_type(struct dm_table *t)
 {
 	unsigned i;
 	unsigned bio_based = 0, request_based = 0, hybrid = 0;
+	bool use_blk_mq = false;
 	struct dm_target *tgt;
 	struct dm_dev_internal *dd;
 	struct list_head *devices;
@@ -872,11 +873,26 @@ static int dm_table_set_type(struct dm_table *t)
 	/* Non-request-stackable devices can't be used for request-based dm */
 	devices = dm_table_get_devices(t);
 	list_for_each_entry(dd, devices, list) {
-		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) {
-			DMWARN("table load rejected: including"
-			       " non-request-stackable devices");
+		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
+
+		if (!blk_queue_stackable(q)) {
+			DMERR("table load rejected: including"
+			      " non-request-stackable devices");
 			return -EINVAL;
 		}
+
+		if (q->mq_ops)
+			use_blk_mq = true;
+	}
+
+	if (use_blk_mq) {
+		/* verify _all_ devices in the table are blk-mq devices */
+		list_for_each_entry(dd, devices, list)
+			if (!bdev_get_queue(dd->dm_dev->bdev)->mq_ops) {
+				DMERR("table load rejected: not all devices"
+				      " are blk-mq request-stackable");
+				return -EINVAL;
+			}
 	}
 
 	/*
@@ -890,7 +906,7 @@ static int dm_table_set_type(struct dm_table *t)
 		return -EINVAL;
 	}
 
-	t->type = DM_TYPE_REQUEST_BASED;
+	t->type = !use_blk_mq ? DM_TYPE_REQUEST_BASED : DM_TYPE_MQ_REQUEST_BASED;
 
 	return 0;
 }
@@ -907,7 +923,15 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 
 bool dm_table_request_based(struct dm_table *t)
 {
-	return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED;
+	unsigned table_type = dm_table_get_type(t);
+
+	return (table_type == DM_TYPE_REQUEST_BASED ||
+		table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
+bool dm_table_mq_request_based(struct dm_table *t)
+{
+	return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED;
 }
 
 static int dm_table_alloc_md_mempools(struct dm_table *t)

drivers/md/dm-target.c

@@ -137,13 +137,26 @@ static int io_err_map_rq(struct dm_target *ti, struct request *clone,
 	return -EIO;
 }
 
+static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
+				   union map_info *map_context,
+				   struct request **clone)
+{
+	return -EIO;
+}
+
+static void io_err_release_clone_rq(struct request *clone)
+{
+}
+
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 2, 0},
+	.version = {1, 3, 0},
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
 	.map_rq = io_err_map_rq,
+	.clone_and_map_rq = io_err_clone_and_map_rq,
+	.release_clone_rq = io_err_release_clone_rq,
 };
 
 int __init dm_target_init(void)