Merge tag 'dm-4.9-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - various fixes and cleanups for request-based DM core

 - add support for delaying the requeue of requests; used by DM
   multipath when all paths have failed and 'queue_if_no_path' is
   enabled

 - DM cache improvements to speedup the loading metadata and the writing
   of the hint array

 - fix potential for a dm-crypt crash on device teardown

 - remove dm_bufio_cond_resched() and just using cond_resched()

 - change DM multipath to return a reservation conflict error
   immediately; rather than failing the path and retrying (potentially
   indefinitely)

* tag 'dm-4.9-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (24 commits)
  dm mpath: always return reservation conflict without failing over
  dm bufio: remove dm_bufio_cond_resched()
  dm crypt: fix crash on exit
  dm cache metadata: switch to using the new cursor api for loading metadata
  dm array: introduce cursor api
  dm btree: introduce cursor api
  dm cache policy smq: distribute entries to random levels when switching to smq
  dm cache: speed up writing of the hint array
  dm array: add dm_array_new()
  dm mpath: delay the requeue of blk-mq requests while all paths down
  dm mpath: use dm_mq_kick_requeue_list()
  dm rq: introduce dm_mq_kick_requeue_list()
  dm rq: reduce arguments passed to map_request() and dm_requeue_original_request()
  dm rq: add DM_MAPIO_DELAY_REQUEUE to delay requeue of blk-mq requests
  dm: convert wait loops to use autoremove_wake_function()
  dm: use signal_pending_state() in dm_wait_for_completion()
  dm: rename task state function arguments
  dm: add two lockdep_assert_held() statements
  dm rq: simplify dm_old_stop_queue()
  dm mpath: check if path's request_queue is dying in activate_path()
  ...

1 files changed, 67 insertions, 37 deletions

diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index ee48230a2952..182b67947dad 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -73,15 +73,24 @@ static void dm_old_start_queue(struct request_queue *q)
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
+static void dm_mq_start_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	blk_mq_start_stopped_hw_queues(q, true);
+	blk_mq_kick_requeue_list(q);
+}
+
 void dm_start_queue(struct request_queue *q)
 {
 	if (!q->mq_ops)
 		dm_old_start_queue(q);
-	else {
-		queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, q);
-		blk_mq_start_stopped_hw_queues(q, true);
-		blk_mq_kick_requeue_list(q);
-	}
+	else
+		dm_mq_start_queue(q);
 }
 
 static void dm_old_stop_queue(struct request_queue *q)
@@ -89,27 +98,35 @@ static void dm_old_stop_queue(struct request_queue *q)
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
+	if (!blk_queue_stopped(q))
+		blk_stop_queue(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_mq_stop_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
 	if (blk_queue_stopped(q)) {
 		spin_unlock_irqrestore(q->queue_lock, flags);
 		return;
 	}
 
-	blk_stop_queue(q);
+	queue_flag_set(QUEUE_FLAG_STOPPED, q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	/* Avoid that requeuing could restart the queue. */
+	blk_mq_cancel_requeue_work(q);
+	blk_mq_stop_hw_queues(q);
 }
 
 void dm_stop_queue(struct request_queue *q)
 {
 	if (!q->mq_ops)
 		dm_old_stop_queue(q);
-	else {
-		spin_lock_irq(q->queue_lock);
-		queue_flag_set(QUEUE_FLAG_STOPPED, q);
-		spin_unlock_irq(q->queue_lock);
-
-		blk_mq_cancel_requeue_work(q);
-		blk_mq_stop_hw_queues(q);
-	}
+	else
+		dm_mq_stop_queue(q);
 }
 
 static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
@@ -319,21 +336,32 @@ static void dm_old_requeue_request(struct request *rq)
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static void dm_mq_requeue_request(struct request *rq)
+static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs)
 {
-	struct request_queue *q = rq->q;
 	unsigned long flags;
 
-	blk_mq_requeue_request(rq);
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (!blk_queue_stopped(q))
-		blk_mq_kick_requeue_list(q);
+		blk_mq_delay_kick_requeue_list(q, msecs);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static void dm_requeue_original_request(struct mapped_device *md,
-					struct request *rq)
+void dm_mq_kick_requeue_list(struct mapped_device *md)
+{
+	__dm_mq_kick_requeue_list(dm_get_md_queue(md), 0);
+}
+EXPORT_SYMBOL(dm_mq_kick_requeue_list);
+
+static void dm_mq_delay_requeue_request(struct request *rq, unsigned long msecs)
+{
+	blk_mq_requeue_request(rq);
+	__dm_mq_kick_requeue_list(rq->q, msecs);
+}
+
+static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_requeue)
 {
+	struct mapped_device *md = tio->md;
+	struct request *rq = tio->orig;
 	int rw = rq_data_dir(rq);
 
 	rq_end_stats(md, rq);
@@ -342,7 +370,7 @@ static void dm_requeue_original_request(struct mapped_device *md,
 	if (!rq->q->mq_ops)
 		dm_old_requeue_request(rq);
 	else
-		dm_mq_requeue_request(rq);
+		dm_mq_delay_requeue_request(rq, delay_requeue ? 5000 : 0);
 
 	rq_completed(md, rw, false);
 }
@@ -372,7 +400,7 @@ static void dm_done(struct request *clone, int error, bool mapped)
 		return;
 	else if (r == DM_ENDIO_REQUEUE)
 		/* The target wants to requeue the I/O */
-		dm_requeue_original_request(tio->md, tio->orig);
+		dm_requeue_original_request(tio, false);
 	else {
 		DMWARN("unimplemented target endio return value: %d", r);
 		BUG();
@@ -612,20 +640,23 @@ static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
 
 /*
  * Returns:
- * 0                : the request has been processed
- * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * DM_MAPIO_*       : the request has been processed as indicated
+ * DM_MAPIO_REQUEUE : the original request needs to be immediately requeued
  * < 0              : the request was completed due to failure
  */
-static int map_request(struct dm_rq_target_io *tio, struct request *rq,
-		       struct mapped_device *md)
+static int map_request(struct dm_rq_target_io *tio)
 {
 	int r;
 	struct dm_target *ti = tio->ti;
+	struct mapped_device *md = tio->md;
+	struct request *rq = tio->orig;
 	struct request *clone = NULL;
 
 	if (tio->clone) {
 		clone = tio->clone;
 		r = ti->type->map_rq(ti, clone, &tio->info);
+		if (r == DM_MAPIO_DELAY_REQUEUE)
+			return DM_MAPIO_REQUEUE; /* .request_fn requeue is always immediate */
 	} else {
 		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
 		if (r < 0) {
@@ -633,9 +664,8 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 			dm_kill_unmapped_request(rq, r);
 			return r;
 		}
-		if (r != DM_MAPIO_REMAPPED)
-			return r;
-		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+		if (r == DM_MAPIO_REMAPPED &&
+		    setup_clone(clone, rq, tio, GFP_ATOMIC)) {
 			/* -ENOMEM */
 			ti->type->release_clone_rq(clone);
 			return DM_MAPIO_REQUEUE;
@@ -654,7 +684,10 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 		break;
 	case DM_MAPIO_REQUEUE:
 		/* The target wants to requeue the I/O */
-		dm_requeue_original_request(md, tio->orig);
+		break;
+	case DM_MAPIO_DELAY_REQUEUE:
+		/* The target wants to requeue the I/O after a delay */
+		dm_requeue_original_request(tio, true);
 		break;
 	default:
 		if (r > 0) {
@@ -664,10 +697,9 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 
 		/* The target wants to complete the I/O */
 		dm_kill_unmapped_request(rq, r);
-		return r;
 	}
 
-	return 0;
+	return r;
 }
 
 static void dm_start_request(struct mapped_device *md, struct request *orig)
@@ -706,11 +738,9 @@ static void dm_start_request(struct mapped_device *md, struct request *orig)
 static void map_tio_request(struct kthread_work *work)
 {
 	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
-	struct request *rq = tio->orig;
-	struct mapped_device *md = tio->md;
 
-	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-		dm_requeue_original_request(md, rq);
+	if (map_request(tio) == DM_MAPIO_REQUEUE)
+		dm_requeue_original_request(tio, false);
 }
 
 ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
@@ -896,7 +926,7 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 	tio->ti = ti;
 
 	/* Direct call is fine since .queue_rq allows allocations */
-	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+	if (map_request(tio) == DM_MAPIO_REQUEUE) {
 		/* Undo dm_start_request() before requeuing */
 		rq_end_stats(md, rq);
 		rq_completed(md, rq_data_dir(rq), false);