Merge branch 'for-4.10/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main block pull request this series. Contrary to previous
  release, I've kept the core and driver changes in the same branch. We
  always ended up having dependencies between the two for obvious
  reasons, so makes more sense to keep them together. That said, I'll
  probably try and keep more topical branches going forward, especially
  for cycles that end up being as busy as this one.

  The major parts of this pull request is:

   - Improved support for O_DIRECT on block devices, with a small
     private implementation instead of using the pig that is
     fs/direct-io.c. From Christoph.

   - Request completion tracking in a scalable fashion. This is utilized
     by two components in this pull, the new hybrid polling and the
     writeback queue throttling code.

   - Improved support for polling with O_DIRECT, adding a hybrid mode
     that combines pure polling with an initial sleep. From me.

   - Support for automatic throttling of writeback queues on the block
     side. This uses feedback from the device completion latencies to
     scale the queue on the block side up or down. From me.

   - Support from SMR drives in the block layer and for SD. From Hannes
     and Shaun.

   - Multi-connection support for nbd. From Josef.

   - Cleanup of request and bio flags, so we have a clear split between
     which are bio (or rq) private, and which ones are shared. From
     Christoph.

   - A set of patches from Bart, that improve how we handle queue
     stopping and starting in blk-mq.

   - Support for WRITE_ZEROES from Chaitanya.

   - Lightnvm updates from Javier/Matias.

   - Supoort for FC for the nvme-over-fabrics code. From James Smart.

   - A bunch of fixes from a whole slew of people, too many to name
     here"

* 'for-4.10/block' of git://git.kernel.dk/linux-block: (182 commits)
  blk-stat: fix a few cases of missing batch flushing
  blk-flush: run the queue when inserting blk-mq flush
  elevator: make the rqhash helpers exported
  blk-mq: abstract out blk_mq_dispatch_rq_list() helper
  blk-mq: add blk_mq_start_stopped_hw_queue()
  block: improve handling of the magic discard payload
  blk-wbt: don't throttle discard or write zeroes
  nbd: use dev_err_ratelimited in io path
  nbd: reset the setup task for NBD_CLEAR_SOCK
  nvme-fabrics: Add FC LLDD loopback driver to test FC-NVME
  nvme-fabrics: Add target support for FC transport
  nvme-fabrics: Add host support for FC transport
  nvme-fabrics: Add FC transport LLDD api definitions
  nvme-fabrics: Add FC transport FC-NVME definitions
  nvme-fabrics: Add FC transport error codes to nvme.h
  Add type 0x28 NVME type code to scsi fc headers
  nvme-fabrics: patch target code in prep for FC transport support
  nvme-fabrics: set sqe.command_id in core not transports
  parser: add u64 number parser
  nvme-rdma: align to generic ib_event logging helper
  ...

1 files changed, 10 insertions, 42 deletions

diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 1d0d2adc050a..b2a9e2d161e4 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -75,12 +75,6 @@ static void dm_old_start_queue(struct request_queue *q)
 
 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);
 }
@@ -105,20 +99,10 @@ static void dm_old_stop_queue(struct request_queue *q)
 
 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);
+	if (blk_mq_queue_stopped(q))
 		return;
-	}
-
-	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);
+	blk_mq_quiesce_queue(q);
 }
 
 void dm_stop_queue(struct request_queue *q)
@@ -313,7 +297,7 @@ static void dm_unprep_request(struct request *rq)
 
 	if (!rq->q->mq_ops) {
 		rq->special = NULL;
-		rq->cmd_flags &= ~REQ_DONTPREP;
+		rq->rq_flags &= ~RQF_DONTPREP;
 	}
 
 	if (clone)
@@ -338,12 +322,7 @@ static void dm_old_requeue_request(struct request *rq)
 
 static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (!blk_queue_stopped(q))
-		blk_mq_delay_kick_requeue_list(q, msecs);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	blk_mq_delay_kick_requeue_list(q, msecs);
 }
 
 void dm_mq_kick_requeue_list(struct mapped_device *md)
@@ -354,7 +333,7 @@ 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);
+	blk_mq_requeue_request(rq, false);
 	__dm_mq_kick_requeue_list(rq->q, msecs);
 }
 
@@ -431,7 +410,7 @@ static void dm_softirq_done(struct request *rq)
 		return;
 	}
 
-	if (rq->cmd_flags & REQ_FAILED)
+	if (rq->rq_flags & RQF_FAILED)
 		mapped = false;
 
 	dm_done(clone, tio->error, mapped);
@@ -460,7 +439,7 @@ static void dm_complete_request(struct request *rq, int error)
  */
 static void dm_kill_unmapped_request(struct request *rq, int error)
 {
-	rq->cmd_flags |= REQ_FAILED;
+	rq->rq_flags |= RQF_FAILED;
 	dm_complete_request(rq, error);
 }
 
@@ -476,7 +455,7 @@ static void end_clone_request(struct request *clone, int error)
 		 * For just cleaning up the information of the queue in which
 		 * the clone was dispatched.
 		 * The clone is *NOT* freed actually here because it is alloced
-		 * from dm own mempool (REQ_ALLOCED isn't set).
+		 * from dm own mempool (RQF_ALLOCED isn't set).
 		 */
 		__blk_put_request(clone->q, clone);
 	}
@@ -497,7 +476,7 @@ static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
 	int r;
 
 	if (blk_queue_io_stat(clone->q))
-		clone->cmd_flags |= REQ_IO_STAT;
+		clone->rq_flags |= RQF_IO_STAT;
 
 	clone->start_time = jiffies;
 	r = blk_insert_cloned_request(clone->q, clone);
@@ -633,7 +612,7 @@ static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
 		return BLKPREP_DEFER;
 
 	rq->special = tio;
-	rq->cmd_flags |= REQ_DONTPREP;
+	rq->rq_flags |= RQF_DONTPREP;
 
 	return BLKPREP_OK;
 }
@@ -904,17 +883,6 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 		dm_put_live_table(md, srcu_idx);
 	}
 
-	/*
-	 * On suspend dm_stop_queue() handles stopping the blk-mq
-	 * request_queue BUT: even though the hw_queues are marked
-	 * BLK_MQ_S_STOPPED at that point there is still a race that
-	 * is allowing block/blk-mq.c to call ->queue_rq against a
-	 * hctx that it really shouldn't.  The following check guards
-	 * against this rarity (albeit _not_ race-free).
-	 */
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
-		return BLK_MQ_RQ_QUEUE_BUSY;
-
 	if (ti->type->busy && ti->type->busy(ti))
 		return BLK_MQ_RQ_QUEUE_BUSY;