Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

1 files changed, 69 insertions, 30 deletions

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index bcc1694cebcd..54de24c785dd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -252,9 +252,9 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	struct scsi_request *rq;
 	int ret = DRIVER_ERROR << 24;
 
-	req = blk_get_request(sdev->request_queue,
+	req = blk_get_request_flags(sdev->request_queue,
 			data_direction == DMA_TO_DEVICE ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT);
 	if (IS_ERR(req))
 		return ret;
 	rq = scsi_req(req);
@@ -268,7 +268,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	rq->retries = retries;
 	req->timeout = timeout;
 	req->cmd_flags |= flags;
-	req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT;
+	req->rq_flags |= rq_flags | RQF_QUIET;
 
 	/*
 	 * head injection *required* here otherwise quiesce won't work
@@ -1301,7 +1301,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 			/*
 			 * If the devices is blocked we defer normal commands.
 			 */
-			if (!(req->rq_flags & RQF_PREEMPT))
+			if (req && !(req->rq_flags & RQF_PREEMPT))
 				ret = BLKPREP_DEFER;
 			break;
 		default:
@@ -1310,7 +1310,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 			 * special commands.  In particular any user initiated
 			 * command is not allowed.
 			 */
-			if (!(req->rq_flags & RQF_PREEMPT))
+			if (req && !(req->rq_flags & RQF_PREEMPT))
 				ret = BLKPREP_KILL;
 			break;
 		}
@@ -1940,6 +1940,33 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)
 	blk_mq_complete_request(cmd->request);
 }
 
+static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+
+	atomic_dec(&sdev->device_busy);
+	put_device(&sdev->sdev_gendev);
+}
+
+static bool scsi_mq_get_budget(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+
+	if (!get_device(&sdev->sdev_gendev))
+		goto out;
+	if (!scsi_dev_queue_ready(q, sdev))
+		goto out_put_device;
+
+	return true;
+
+out_put_device:
+	put_device(&sdev->sdev_gendev);
+out:
+	return false;
+}
+
 static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 			 const struct blk_mq_queue_data *bd)
 {
@@ -1953,16 +1980,11 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	ret = prep_to_mq(scsi_prep_state_check(sdev, req));
 	if (ret != BLK_STS_OK)
-		goto out;
+		goto out_put_budget;
 
 	ret = BLK_STS_RESOURCE;
-	if (!get_device(&sdev->sdev_gendev))
-		goto out;
-
-	if (!scsi_dev_queue_ready(q, sdev))
-		goto out_put_device;
 	if (!scsi_target_queue_ready(shost, sdev))
-		goto out_dec_device_busy;
+		goto out_put_budget;
 	if (!scsi_host_queue_ready(q, shost, sdev))
 		goto out_dec_target_busy;
 
@@ -1993,15 +2015,12 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 
 out_dec_host_busy:
-	atomic_dec(&shost->host_busy);
+       atomic_dec(&shost->host_busy);
 out_dec_target_busy:
 	if (scsi_target(sdev)->can_queue > 0)
 		atomic_dec(&scsi_target(sdev)->target_busy);
-out_dec_device_busy:
-	atomic_dec(&sdev->device_busy);
-out_put_device:
-	put_device(&sdev->sdev_gendev);
-out:
+out_put_budget:
+	scsi_mq_put_budget(hctx);
 	switch (ret) {
 	case BLK_STS_OK:
 		break;
@@ -2205,6 +2224,8 @@ struct request_queue *scsi_old_alloc_queue(struct scsi_device *sdev)
 }
 
 static const struct blk_mq_ops scsi_mq_ops = {
+	.get_budget	= scsi_mq_get_budget,
+	.put_budget	= scsi_mq_put_budget,
 	.queue_rq	= scsi_queue_rq,
 	.complete	= scsi_softirq_done,
 	.timeout	= scsi_timeout,
@@ -2919,21 +2940,37 @@ static void scsi_wait_for_queuecommand(struct scsi_device *sdev)
 int
 scsi_device_quiesce(struct scsi_device *sdev)
 {
+	struct request_queue *q = sdev->request_queue;
 	int err;
 
+	/*
+	 * It is allowed to call scsi_device_quiesce() multiple times from
+	 * the same context but concurrent scsi_device_quiesce() calls are
+	 * not allowed.
+	 */
+	WARN_ON_ONCE(sdev->quiesced_by && sdev->quiesced_by != current);
+
+	blk_set_preempt_only(q);
+
+	blk_mq_freeze_queue(q);
+	/*
+	 * Ensure that the effect of blk_set_preempt_only() will be visible
+	 * for percpu_ref_tryget() callers that occur after the queue
+	 * unfreeze even if the queue was already frozen before this function
+	 * was called. See also https://lwn.net/Articles/573497/.
+	 */
+	synchronize_rcu();
+	blk_mq_unfreeze_queue(q);
+
 	mutex_lock(&sdev->state_mutex);
 	err = scsi_device_set_state(sdev, SDEV_QUIESCE);
+	if (err == 0)
+		sdev->quiesced_by = current;
+	else
+		blk_clear_preempt_only(q);
 	mutex_unlock(&sdev->state_mutex);
 
-	if (err)
-		return err;
-
-	scsi_run_queue(sdev->request_queue);
-	while (atomic_read(&sdev->device_busy)) {
-		msleep_interruptible(200);
-		scsi_run_queue(sdev->request_queue);
-	}
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL(scsi_device_quiesce);
 
@@ -2953,9 +2990,11 @@ void scsi_device_resume(struct scsi_device *sdev)
 	 * device deleted during suspend)
 	 */
 	mutex_lock(&sdev->state_mutex);
-	if (sdev->sdev_state == SDEV_QUIESCE &&
-	    scsi_device_set_state(sdev, SDEV_RUNNING) == 0)
-		scsi_run_queue(sdev->request_queue);
+	WARN_ON_ONCE(!sdev->quiesced_by);
+	sdev->quiesced_by = NULL;
+	blk_clear_preempt_only(sdev->request_queue);
+	if (sdev->sdev_state == SDEV_QUIESCE)
+		scsi_device_set_state(sdev, SDEV_RUNNING);
 	mutex_unlock(&sdev->state_mutex);
 }
 EXPORT_SYMBOL(scsi_device_resume);