dm: do not initialise full request queue when bio based

Change bio-based mapped devices no longer to have a fully initialized
request_queue (request_fn, elevator, etc).  This means bio-based DM
devices no longer register elevator sysfs attributes ('iosched/' tree
or 'scheduler' other than "none").

In contrast, a request-based DM device will continue to have a full
request_queue and will register elevator sysfs attributes.  Therefore
a user can determine a DM device's type by checking if elevator sysfs
attributes exist.

First allocate a minimalist request_queue structure for a DM device
(needed for both bio and request-based DM).

Initialization of a full request_queue is deferred until it is known
that the DM device is request-based, at the end of the table load
sequence.

Factor DM device's request_queue initialization:
- common to both request-based and bio-based into dm_init_md_queue().
- specific to request-based into dm_init_request_based_queue().

The md->type_lock mutex is used to protect md->queue, in addition to
md->type, during table_load().

A DM device's first table_load will establish the immutable md->type.
But md->queue initialization, based on md->type, may fail at that time
(because blk_init_allocated_queue cannot allocate memory).  Therefore
any subsequent table_load must (re)try dm_setup_md_queue independently of
establishing md->type.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

3 files changed, 79 insertions, 26 deletions

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 4702f380cb4..ed8585954a3 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1189,7 +1189,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 		goto out;
 	}
 
-	/* Protect md->type against concurrent table loads. */
+	/* Protect md->type and md->queue against concurrent table loads. */
 	dm_lock_md_type(md);
 	if (dm_get_md_type(md) == DM_TYPE_NONE)
 		/* Initial table load: acquire type of table. */
@@ -1201,6 +1201,15 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 		r = -EINVAL;
 		goto out;
 	}
+
+	/* setup md->queue to reflect md's type (may block) */
+	r = dm_setup_md_queue(md);
+	if (r) {
+		DMWARN("unable to set up device queue for new table.");
+		dm_table_destroy(t);
+		dm_unlock_md_type(md);
+		goto out;
+	}
 	dm_unlock_md_type(md);
 
 	/* stage inactive table */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 345e94c10c6..5ae0a05b481 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -126,7 +126,7 @@ struct mapped_device {
 
 	struct request_queue *queue;
 	unsigned type;
-	/* Protect type against concurrent access. */
+	/* Protect queue and type against concurrent access. */
 	struct mutex type_lock;
 
 	struct gendisk *disk;
@@ -1856,6 +1856,28 @@ static const struct block_device_operations dm_blk_dops;
 static void dm_wq_work(struct work_struct *work);
 static void dm_rq_barrier_work(struct work_struct *work);
 
+static void dm_init_md_queue(struct mapped_device *md)
+{
+	/*
+	 * Request-based dm devices cannot be stacked on top of bio-based dm
+	 * devices.  The type of this dm device has not been decided yet.
+	 * The type is decided at the first table loading time.
+	 * To prevent problematic device stacking, clear the queue flag
+	 * for request stacking support until then.
+	 *
+	 * This queue is new, so no concurrency on the queue_flags.
+	 */
+	queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue);
+
+	md->queue->queuedata = md;
+	md->queue->backing_dev_info.congested_fn = dm_any_congested;
+	md->queue->backing_dev_info.congested_data = md;
+	blk_queue_make_request(md->queue, dm_request);
+	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
+	md->queue->unplug_fn = dm_unplug_all;
+	blk_queue_merge_bvec(md->queue, dm_merge_bvec);
+}
+
 /*
  * Allocate and initialise a blank device with a given minor.
  */
@@ -1895,33 +1917,11 @@ static struct mapped_device *alloc_dev(int minor)
 	INIT_LIST_HEAD(&md->uevent_list);
 	spin_lock_init(&md->uevent_lock);
 
-	md->queue = blk_init_queue(dm_request_fn, NULL);
+	md->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!md->queue)
 		goto bad_queue;
 
-	/*
-	 * Request-based dm devices cannot be stacked on top of bio-based dm
-	 * devices.  The type of this dm device has not been decided yet,
-	 * although we initialized the queue using blk_init_queue().
-	 * The type is decided at the first table loading time.
-	 * To prevent problematic device stacking, clear the queue flag
-	 * for request stacking support until then.
-	 *
-	 * This queue is new, so no concurrency on the queue_flags.
-	 */
-	queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue);
-	md->saved_make_request_fn = md->queue->make_request_fn;
-	md->queue->queuedata = md;
-	md->queue->backing_dev_info.congested_fn = dm_any_congested;
-	md->queue->backing_dev_info.congested_data = md;
-	blk_queue_make_request(md->queue, dm_request);
-	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
-	md->queue->unplug_fn = dm_unplug_all;
-	blk_queue_merge_bvec(md->queue, dm_merge_bvec);
-	blk_queue_softirq_done(md->queue, dm_softirq_done);
-	blk_queue_prep_rq(md->queue, dm_prep_fn);
-	blk_queue_lld_busy(md->queue, dm_lld_busy);
-	blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
+	dm_init_md_queue(md);
 
 	md->disk = alloc_disk(1);
 	if (!md->disk)
@@ -2160,6 +2160,48 @@ unsigned dm_get_md_type(struct mapped_device *md)
 	return md->type;
 }
 
+/*
+ * Fully initialize a request-based queue (->elevator, ->request_fn, etc).
+ */
+static int dm_init_request_based_queue(struct mapped_device *md)
+{
+	struct request_queue *q = NULL;
+
+	if (md->queue->elevator)
+		return 1;
+
+	/* Fully initialize the queue */
+	q = blk_init_allocated_queue(md->queue, dm_request_fn, NULL);
+	if (!q)
+		return 0;
+
+	md->queue = q;
+	md->saved_make_request_fn = md->queue->make_request_fn;
+	dm_init_md_queue(md);
+	blk_queue_softirq_done(md->queue, dm_softirq_done);
+	blk_queue_prep_rq(md->queue, dm_prep_fn);
+	blk_queue_lld_busy(md->queue, dm_lld_busy);
+	blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
+
+	elv_register_queue(md->queue);
+
+	return 1;
+}
+
+/*
+ * Setup the DM device's queue based on md's type
+ */
+int dm_setup_md_queue(struct mapped_device *md)
+{
+	if ((dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) &&
+	    !dm_init_request_based_queue(md)) {
+		DMWARN("Cannot initialize queue for request-based mapped device");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct mapped_device *dm_find_md(dev_t dev)
 {
 	struct mapped_device *md;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 1db782530ce..450fbd98c48 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -71,6 +71,8 @@ void dm_unlock_md_type(struct mapped_device *md);
 void dm_set_md_type(struct mapped_device *md, unsigned type);
 unsigned dm_get_md_type(struct mapped_device *md);
 
+int dm_setup_md_queue(struct mapped_device *md);
+
 /*
  * To check the return value from dm_table_find_target().
  */