1 files changed, 66 insertions, 25 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6963ad148408..c2d1ba204b04 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -31,6 +31,7 @@ static unsigned int _major = 0;
 
 static DEFINE_SPINLOCK(_minor_lock);
 /*
+ * For bio-based dm.
  * One of these is allocated per bio.
  */
 struct dm_io {
@@ -42,6 +43,7 @@ struct dm_io {
 };
 
 /*
+ * For bio-based dm.
  * One of these is allocated per target within a bio.  Hopefully
  * this will be simplified out one day.
  */
@@ -51,6 +53,27 @@ struct dm_target_io {
 	union map_info info;
 };
 
+/*
+ * For request-based dm.
+ * One of these is allocated per request.
+ */
+struct dm_rq_target_io {
+	struct mapped_device *md;
+	struct dm_target *ti;
+	struct request *orig, clone;
+	int error;
+	union map_info info;
+};
+
+/*
+ * For request-based dm.
+ * One of these is allocated per bio.
+ */
+struct dm_rq_clone_bio_info {
+	struct bio *orig;
+	struct request *rq;
+};
+
 union map_info *dm_get_mapinfo(struct bio *bio)
 {
 	if (bio && bio->bi_private)
@@ -146,6 +169,8 @@ struct mapped_device {
 #define MIN_IOS 256
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_tio_cache;
+static struct kmem_cache *_rq_tio_cache;
+static struct kmem_cache *_rq_bio_info_cache;
 
 static int __init local_init(void)
 {
@@ -161,9 +186,17 @@ static int __init local_init(void)
 	if (!_tio_cache)
 		goto out_free_io_cache;
 
+	_rq_tio_cache = KMEM_CACHE(dm_rq_target_io, 0);
+	if (!_rq_tio_cache)
+		goto out_free_tio_cache;
+
+	_rq_bio_info_cache = KMEM_CACHE(dm_rq_clone_bio_info, 0);
+	if (!_rq_bio_info_cache)
+		goto out_free_rq_tio_cache;
+
 	r = dm_uevent_init();
 	if (r)
-		goto out_free_tio_cache;
+		goto out_free_rq_bio_info_cache;
 
 	_major = major;
 	r = register_blkdev(_major, _name);
@@ -177,6 +210,10 @@ static int __init local_init(void)
 
 out_uevent_exit:
 	dm_uevent_exit();
+out_free_rq_bio_info_cache:
+	kmem_cache_destroy(_rq_bio_info_cache);
+out_free_rq_tio_cache:
+	kmem_cache_destroy(_rq_tio_cache);
 out_free_tio_cache:
 	kmem_cache_destroy(_tio_cache);
 out_free_io_cache:
@@ -187,6 +224,8 @@ out_free_io_cache:
 
 static void local_exit(void)
 {
+	kmem_cache_destroy(_rq_bio_info_cache);
+	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
@@ -375,7 +414,7 @@ static void start_io_acct(struct dm_io *io)
 	dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending);
 }
 
-static int end_io_acct(struct dm_io *io)
+static void end_io_acct(struct dm_io *io)
 {
 	struct mapped_device *md = io->md;
 	struct bio *bio = io->bio;
@@ -391,7 +430,9 @@ static int end_io_acct(struct dm_io *io)
 	dm_disk(md)->part0.in_flight = pending =
 		atomic_dec_return(&md->pending);
 
-	return !pending;
+	/* nudge anyone waiting on suspend queue */
+	if (!pending)
+		wake_up(&md->wait);
 }
 
 /*
@@ -499,9 +540,7 @@ static void dec_pending(struct dm_io *io, int error)
 			spin_unlock_irqrestore(&io->md->pushback_lock, flags);
 		}
 
-		if (end_io_acct(io))
-			/* nudge anyone waiting on suspend queue */
-			wake_up(&io->md->wait);
+		end_io_acct(io);
 
 		if (io->error != DM_ENDIO_REQUEUE) {
 			blk_add_trace_bio(io->md->queue, io->bio,
@@ -794,7 +833,10 @@ static int __split_bio(struct mapped_device *md, struct bio *bio)
 	ci.map = dm_get_table(md);
 	if (unlikely(!ci.map))
 		return -EIO;
-
+	if (unlikely(bio_barrier(bio) && !dm_table_barrier_ok(ci.map))) {
+		bio_endio(bio, -EOPNOTSUPP);
+		return 0;
+	}
 	ci.md = md;
 	ci.bio = bio;
 	ci.io = alloc_io(md);
@@ -878,15 +920,6 @@ static int dm_request(struct request_queue *q, struct bio *bio)
 	struct mapped_device *md = q->queuedata;
 	int cpu;
 
-	/*
-	 * There is no use in forwarding any barrier request since we can't
-	 * guarantee it is (or can be) handled by the targets correctly.
-	 */
-	if (unlikely(bio_barrier(bio))) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
-
 	down_read(&md->io_lock);
 
 	cpu = part_stat_lock();
@@ -937,16 +970,24 @@ static void dm_unplug_all(struct request_queue *q)
 
 static int dm_any_congested(void *congested_data, int bdi_bits)
 {
-	int r;
-	struct mapped_device *md = (struct mapped_device *) congested_data;
-	struct dm_table *map = dm_get_table(md);
+	int r = bdi_bits;
+	struct mapped_device *md = congested_data;
+	struct dm_table *map;
 
-	if (!map || test_bit(DMF_BLOCK_IO, &md->flags))
-		r = bdi_bits;
-	else
-		r = dm_table_any_congested(map, bdi_bits);
+	atomic_inc(&md->pending);
+
+	if (!test_bit(DMF_BLOCK_IO, &md->flags)) {
+		map = dm_get_table(md);
+		if (map) {
+			r = dm_table_any_congested(map, bdi_bits);
+			dm_table_put(map);
+		}
+	}
+
+	if (!atomic_dec_return(&md->pending))
+		/* nudge anyone waiting on suspend queue */
+		wake_up(&md->wait);
 
-	dm_table_put(map);
 	return r;
 }
 
@@ -1320,8 +1361,8 @@ void dm_put(struct mapped_device *md)
 			dm_table_presuspend_targets(map);
 			dm_table_postsuspend_targets(map);
 		}
-		__unbind(md);
 		dm_table_put(map);
+		__unbind(md);
 		free_dev(md);
 	}
 }