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, 50 insertions, 42 deletions

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2cca9cffc63fd..9a8ccff1121fb 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -86,10 +86,8 @@ scsi_set_blocked(struct scsi_cmnd *cmd, int reason)
 static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdev = cmd->device;
-	struct request_queue *q = cmd->request->q;
 
-	blk_mq_requeue_request(cmd->request);
-	blk_mq_kick_requeue_list(q);
+	blk_mq_requeue_request(cmd->request, true);
 	put_device(&sdev->sdev_gendev);
 }
 
@@ -163,26 +161,11 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 {
 	__scsi_queue_insert(cmd, reason, 1);
 }
-/**
- * scsi_execute - insert request and wait for the result
- * @sdev:	scsi device
- * @cmd:	scsi command
- * @data_direction: data direction
- * @buffer:	data buffer
- * @bufflen:	len of buffer
- * @sense:	optional sense buffer
- * @timeout:	request timeout in seconds
- * @retries:	number of times to retry request
- * @flags:	or into request flags;
- * @resid:	optional residual length
- *
- * returns the req->errors value which is the scsi_cmnd result
- * field.
- */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+
+static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, int timeout, int retries, u64 flags,
-		 int *resid)
+		 req_flags_t rq_flags, int *resid)
 {
 	struct request *req;
 	int write = (data_direction == DMA_TO_DEVICE);
@@ -203,7 +186,8 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	req->sense_len = 0;
 	req->retries = retries;
 	req->timeout = timeout;
-	req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT;
+	req->cmd_flags |= flags;
+	req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT;
 
 	/*
 	 * head injection *required* here otherwise quiesce won't work
@@ -227,12 +211,37 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
+
+/**
+ * scsi_execute - insert request and wait for the result
+ * @sdev:	scsi device
+ * @cmd:	scsi command
+ * @data_direction: data direction
+ * @buffer:	data buffer
+ * @bufflen:	len of buffer
+ * @sense:	optional sense buffer
+ * @timeout:	request timeout in seconds
+ * @retries:	number of times to retry request
+ * @flags:	or into request flags;
+ * @resid:	optional residual length
+ *
+ * returns the req->errors value which is the scsi_cmnd result
+ * field.
+ */
+int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+		 int data_direction, void *buffer, unsigned bufflen,
+		 unsigned char *sense, int timeout, int retries, u64 flags,
+		 int *resid)
+{
+	return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,
+			timeout, retries, flags, 0, resid);
+}
 EXPORT_SYMBOL(scsi_execute);
 
 int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		     int data_direction, void *buffer, unsigned bufflen,
 		     struct scsi_sense_hdr *sshdr, int timeout, int retries,
-		     int *resid, u64 flags)
+		     int *resid, u64 flags, req_flags_t rq_flags)
 {
 	char *sense = NULL;
 	int result;
@@ -242,8 +251,8 @@ int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		if (!sense)
 			return DRIVER_ERROR << 24;
 	}
-	result = scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
-			      sense, timeout, retries, flags, resid);
+	result = __scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
+			      sense, timeout, retries, flags, rq_flags, resid);
 	if (sshdr)
 		scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, sshdr);
 
@@ -813,7 +822,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 */
 		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
 			;
-		else if (!(req->cmd_flags & REQ_QUIET))
+		else if (!(req->rq_flags & RQF_QUIET))
 			scsi_print_sense(cmd);
 		result = 0;
 		/* BLOCK_PC may have set error */
@@ -943,7 +952,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	switch (action) {
 	case ACTION_FAIL:
 		/* Give up and fail the remainder of the request */
-		if (!(req->cmd_flags & REQ_QUIET)) {
+		if (!(req->rq_flags & RQF_QUIET)) {
 			static DEFINE_RATELIMIT_STATE(_rs,
 					DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
@@ -972,7 +981,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 * A new command will be prepared and issued.
 		 */
 		if (q->mq_ops) {
-			cmd->request->cmd_flags &= ~REQ_DONTPREP;
+			cmd->request->rq_flags &= ~RQF_DONTPREP;
 			scsi_mq_uninit_cmd(cmd);
 			scsi_mq_requeue_cmd(cmd);
 		} else {
@@ -998,8 +1007,8 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
 	/*
 	 * If sg table allocation fails, requeue request later.
 	 */
-	if (unlikely(sg_alloc_table_chained(&sdb->table, req->nr_phys_segments,
-					sdb->table.sgl)))
+	if (unlikely(sg_alloc_table_chained(&sdb->table,
+			blk_rq_nr_phys_segments(req), sdb->table.sgl)))
 		return BLKPREP_DEFER;
 
 	/* 
@@ -1031,7 +1040,7 @@ int scsi_init_io(struct scsi_cmnd *cmd)
 	bool is_mq = (rq->mq_ctx != NULL);
 	int error;
 
-	BUG_ON(!rq->nr_phys_segments);
+	BUG_ON(!blk_rq_nr_phys_segments(rq));
 
 	error = scsi_init_sgtable(rq, &cmd->sdb);
 	if (error)
@@ -1234,7 +1243,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 			/*
 			 * If the devices is blocked we defer normal commands.
 			 */
-			if (!(req->cmd_flags & REQ_PREEMPT))
+			if (!(req->rq_flags & RQF_PREEMPT))
 				ret = BLKPREP_DEFER;
 			break;
 		default:
@@ -1243,7 +1252,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 			 * special commands.  In particular any user initiated
 			 * command is not allowed.
 			 */
-			if (!(req->cmd_flags & REQ_PREEMPT))
+			if (!(req->rq_flags & RQF_PREEMPT))
 				ret = BLKPREP_KILL;
 			break;
 		}
@@ -1279,7 +1288,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 			blk_delay_queue(q, SCSI_QUEUE_DELAY);
 		break;
 	default:
-		req->cmd_flags |= REQ_DONTPREP;
+		req->rq_flags |= RQF_DONTPREP;
 	}
 
 	return ret;
@@ -1736,7 +1745,7 @@ static void scsi_request_fn(struct request_queue *q)
 		 * we add the dev to the starved list so it eventually gets
 		 * a run when a tag is freed.
 		 */
-		if (blk_queue_tagged(q) && !(req->cmd_flags & REQ_QUEUED)) {
+		if (blk_queue_tagged(q) && !(req->rq_flags & RQF_QUEUED)) {
 			spin_lock_irq(shost->host_lock);
 			if (list_empty(&sdev->starved_entry))
 				list_add_tail(&sdev->starved_entry,
@@ -1801,7 +1810,7 @@ static inline int prep_to_mq(int ret)
 {
 	switch (ret) {
 	case BLKPREP_OK:
-		return 0;
+		return BLK_MQ_RQ_QUEUE_OK;
 	case BLKPREP_DEFER:
 		return BLK_MQ_RQ_QUEUE_BUSY;
 	default:
@@ -1888,7 +1897,7 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int reason;
 
 	ret = prep_to_mq(scsi_prep_state_check(sdev, req));
-	if (ret)
+	if (ret != BLK_MQ_RQ_QUEUE_OK)
 		goto out;
 
 	ret = BLK_MQ_RQ_QUEUE_BUSY;
@@ -1903,11 +1912,11 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 		goto out_dec_target_busy;
 
 
-	if (!(req->cmd_flags & REQ_DONTPREP)) {
+	if (!(req->rq_flags & RQF_DONTPREP)) {
 		ret = prep_to_mq(scsi_mq_prep_fn(req));
-		if (ret)
+		if (ret != BLK_MQ_RQ_QUEUE_OK)
 			goto out_dec_host_busy;
-		req->cmd_flags |= REQ_DONTPREP;
+		req->rq_flags |= RQF_DONTPREP;
 	} else {
 		blk_mq_start_request(req);
 	}
@@ -1941,7 +1950,6 @@ out_put_device:
 out:
 	switch (ret) {
 	case BLK_MQ_RQ_QUEUE_BUSY:
-		blk_mq_stop_hw_queue(hctx);
 		if (atomic_read(&sdev->device_busy) == 0 &&
 		    !scsi_device_blocked(sdev))
 			blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);
@@ -1952,7 +1960,7 @@ out:
 		 * we hit an error, as we will never see this command
 		 * again.
 		 */
-		if (req->cmd_flags & REQ_DONTPREP)
+		if (req->rq_flags & RQF_DONTPREP)
 			scsi_mq_uninit_cmd(cmd);
 		break;
 	default: