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, 16 insertions, 11 deletions

diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3c882cbc7541..20b7c7a02f1c 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -56,7 +56,7 @@
  * Once while executing DATA and again after the whole sequence is
  * complete.  The first completion updates the contained bio but doesn't
  * finish it so that the bio submitter is notified only after the whole
- * sequence is complete.  This is implemented by testing REQ_FLUSH_SEQ in
+ * sequence is complete.  This is implemented by testing RQF_FLUSH_SEQ in
  * req_bio_endio().
  *
  * The above peculiarity requires that each FLUSH/FUA request has only one
@@ -127,17 +127,14 @@ static void blk_flush_restore_request(struct request *rq)
 	rq->bio = rq->biotail;
 
 	/* make @rq a normal request */
-	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
+	rq->rq_flags &= ~RQF_FLUSH_SEQ;
 	rq->end_io = rq->flush.saved_end_io;
 }
 
 static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
 	if (rq->q->mq_ops) {
-		struct request_queue *q = rq->q;
-
-		blk_mq_add_to_requeue_list(rq, add_front);
-		blk_mq_kick_requeue_list(q);
+		blk_mq_add_to_requeue_list(rq, add_front, true);
 		return false;
 	} else {
 		if (add_front)
@@ -330,7 +327,8 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
-	req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
+	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
+	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 
@@ -368,7 +366,7 @@ static void flush_data_end_io(struct request *rq, int error)
 	elv_completed_request(q, rq);
 
 	/* for avoiding double accounting */
-	rq->cmd_flags &= ~REQ_STARTED;
+	rq->rq_flags &= ~RQF_STARTED;
 
 	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read
@@ -426,6 +424,13 @@ void blk_insert_flush(struct request *rq)
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*
+	 * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any
+	 * of those flags, we have to set REQ_SYNC to avoid skewing
+	 * the request accounting.
+	 */
+	rq->cmd_flags |= REQ_SYNC;
+
+	/*
 	 * An empty flush handed down from a stacking driver may
 	 * translate into nothing if the underlying device does not
 	 * advertise a write-back cache.  In this case, simply
@@ -449,7 +454,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_insert_request(rq, false, false, true);
+			blk_mq_insert_request(rq, false, true, false);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
@@ -461,7 +466,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	memset(&rq->flush, 0, sizeof(rq->flush));
 	INIT_LIST_HEAD(&rq->flush.list);
-	rq->cmd_flags |= REQ_FLUSH_SEQ;
+	rq->rq_flags |= RQF_FLUSH_SEQ;
 	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
 	if (q->mq_ops) {
 		rq->end_io = mq_flush_data_end_io;
@@ -513,7 +518,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 
 	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_bdev = bdev;
-	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
 	ret = submit_bio_wait(bio);