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

Pull block updates and fixes from Jens Axboe:

 - NVMe updates and fixes that missed the first pull request. This
   includes bug fixes, and support for autonomous power management.

 - Fix from Christoph for missing clear of the request payload, causing
   a problem with (at least) the storvsc driver.

 - Further fixes for the queue/bdi life time issues from Jan.

 - The Kconfig mq scheduler update from me.

 - Fixing a use-after-free in dm-rq, spotted by Bart, introduced in this
   merge window.

 - Three fixes for nbd from Josef.

 - Bug fix from Omar, fixing a bug in sas transport code that oopses
   when bsg ioctls were used. From Omar.

 - Improvements to the queue restart and tag wait from from Omar.

 - Set of fixes for the sed/opal code from Scott.

 - Three trivial patches to cciss from Tobin

* 'for-linus' of git://git.kernel.dk/linux-block: (41 commits)
  dm-rq: don't dereference request payload after ending request
  blk-mq-sched: separate mark hctx and queue restart operations
  blk-mq: use sbq wait queues instead of restart for driver tags
  block/sed-opal: Propagate original error message to userland.
  nvme/pci: re-check security protocol support after reset
  block/sed-opal: Introduce free_opal_dev to free the structure and clean up state
  nvme: detect NVMe controller in recent MacBooks
  nvme-rdma: add support for host_traddr
  nvmet-rdma: Fix error handling
  nvmet-rdma: use nvme cm status helper
  nvme-rdma: move nvme cm status helper to .h file
  nvme-fc: don't bother to validate ioccsz and iorcsz
  nvme/pci: No special case for queue busy on IO
  nvme/core: Fix race kicking freed request_queue
  nvme/pci: Disable on removal when disconnected
  nvme: Enable autonomous power state transitions
  nvme: Add a quirk mechanism that uses identify_ctrl
  nvme: make nvmf_register_transport require a create_ctrl callback
  nvme: Use CNS as 8-bit field and avoid endianness conversion
  nvme: add semicolon in nvme_command setting
  ...

block/Kconfig.iosched

@@ -69,50 +69,6 @@ config MQ_IOSCHED_DEADLINE
 	---help---
 	  MQ version of the deadline IO scheduler.
 
-config MQ_IOSCHED_NONE
-	bool
-	default y
-
-choice
-	prompt "Default single-queue blk-mq I/O scheduler"
-	default DEFAULT_SQ_NONE
-	help
-	  Select the I/O scheduler which will be used by default for blk-mq
-	  managed block devices with a single queue.
-
-	config DEFAULT_SQ_DEADLINE
-		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
-
-	config DEFAULT_SQ_NONE
-		bool "None"
-
-endchoice
-
-config DEFAULT_SQ_IOSCHED
-	string
-	default "mq-deadline" if DEFAULT_SQ_DEADLINE
-	default "none" if DEFAULT_SQ_NONE
-
-choice
-	prompt "Default multi-queue blk-mq I/O scheduler"
-	default DEFAULT_MQ_NONE
-	help
-	  Select the I/O scheduler which will be used by default for blk-mq
-	  managed block devices with multiple queues.
-
-	config DEFAULT_MQ_DEADLINE
-		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
-
-	config DEFAULT_MQ_NONE
-		bool "None"
-
-endchoice
-
-config DEFAULT_MQ_IOSCHED
-	string
-	default "mq-deadline" if DEFAULT_MQ_DEADLINE
-	default "none" if DEFAULT_MQ_NONE
-
 endmenu
 
 endif

block/blk-mq-sched.c

@@ -205,7 +205,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 * needing a restart in that case.
 	 */
 	if (!list_empty(&rq_list)) {
-		blk_mq_sched_mark_restart(hctx);
+		blk_mq_sched_mark_restart_hctx(hctx);
 		did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
 	} else if (!has_sched_dispatch) {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
@@ -331,20 +331,16 @@ static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 
 void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
 {
+	struct request_queue *q = hctx->queue;
 	unsigned int i;
 
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
+		if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
+			queue_for_each_hw_ctx(q, hctx, i)
+				blk_mq_sched_restart_hctx(hctx);
+		}
+	} else {
 		blk_mq_sched_restart_hctx(hctx);
-	else {
-		struct request_queue *q = hctx->queue;
-
-		if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
-			return;
-
-		clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-
-		queue_for_each_hw_ctx(q, hctx, i)
-			blk_mq_sched_restart_hctx(hctx);
 	}
 }
 
@@ -498,15 +494,6 @@ int blk_mq_sched_init(struct request_queue *q)
 {
 	int ret;
 
-#if defined(CONFIG_DEFAULT_SQ_NONE)
-	if (q->nr_hw_queues == 1)
-		return 0;
-#endif
-#if defined(CONFIG_DEFAULT_MQ_NONE)
-	if (q->nr_hw_queues > 1)
-		return 0;
-#endif
-
 	mutex_lock(&q->sysfs_lock);
 	ret = elevator_init(q, NULL);
 	mutex_unlock(&q->sysfs_lock);

block/blk-mq-sched.h

@@ -122,17 +122,27 @@ static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
 	return false;
 }
 
-static inline void blk_mq_sched_mark_restart(struct blk_mq_hw_ctx *hctx)
+/*
+ * Mark a hardware queue as needing a restart.
+ */
+static inline void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
 {
-	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
+	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
 		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
-		if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-			struct request_queue *q = hctx->queue;
+}
+
+/*
+ * Mark a hardware queue and the request queue it belongs to as needing a
+ * restart.
+ */
+static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
 
-			if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
-				set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-		}
-	}
+	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+	if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
+		set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
 }
 
 static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)

block/blk-mq.c

@@ -904,6 +904,44 @@ static bool reorder_tags_to_front(struct list_head *list)
 	return first != NULL;
 }
 
+static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags,
+				void *key)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
+
+	list_del(&wait->task_list);
+	clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
+	blk_mq_run_hw_queue(hctx, true);
+	return 1;
+}
+
+static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
+{
+	struct sbq_wait_state *ws;
+
+	/*
+	 * The TAG_WAITING bit serves as a lock protecting hctx->dispatch_wait.
+	 * The thread which wins the race to grab this bit adds the hardware
+	 * queue to the wait queue.
+	 */
+	if (test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state) ||
+	    test_and_set_bit_lock(BLK_MQ_S_TAG_WAITING, &hctx->state))
+		return false;
+
+	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
+	ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);
+
+	/*
+	 * As soon as this returns, it's no longer safe to fiddle with
+	 * hctx->dispatch_wait, since a completion can wake up the wait queue
+	 * and unlock the bit.
+	 */
+	add_wait_queue(&ws->wait, &hctx->dispatch_wait);
+	return true;
+}
+
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct request_queue *q = hctx->queue;
@@ -931,15 +969,22 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 				continue;
 
 			/*
-			 * We failed getting a driver tag. Mark the queue(s)
-			 * as needing a restart. Retry getting a tag again,
-			 * in case the needed IO completed right before we
-			 * marked the queue as needing a restart.
+			 * The initial allocation attempt failed, so we need to
+			 * rerun the hardware queue when a tag is freed.
 			 */
-			blk_mq_sched_mark_restart(hctx);
-			if (!blk_mq_get_driver_tag(rq, &hctx, false))
+			if (blk_mq_dispatch_wait_add(hctx)) {
+				/*
+				 * It's possible that a tag was freed in the
+				 * window between the allocation failure and
+				 * adding the hardware queue to the wait queue.
+				 */
+				if (!blk_mq_get_driver_tag(rq, &hctx, false))
+					break;
+			} else {
 				break;
+			}
 		}
+
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -995,10 +1040,11 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 		 *
 		 * blk_mq_run_hw_queue() already checks the STOPPED bit
 		 *
-		 * If RESTART is set, then let completion restart the queue
-		 * instead of potentially looping here.
+		 * If RESTART or TAG_WAITING is set, then let completion restart
+		 * the queue instead of potentially looping here.
 		 */
-		if (!blk_mq_sched_needs_restart(hctx))
+		if (!blk_mq_sched_needs_restart(hctx) &&
+		    !test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))
 			blk_mq_run_hw_queue(hctx, true);
 	}
 

block/elevator.c

@@ -220,17 +220,24 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	if (!e) {
-		if (q->mq_ops && q->nr_hw_queues == 1)
-			e = elevator_get(CONFIG_DEFAULT_SQ_IOSCHED, false);
-		else if (q->mq_ops)
-			e = elevator_get(CONFIG_DEFAULT_MQ_IOSCHED, false);
-		else
+		/*
+		 * For blk-mq devices, we default to using mq-deadline,
+		 * if available, for single queue devices. If deadline
+		 * isn't available OR we have multiple queues, default
+		 * to "none".
+		 */
+		if (q->mq_ops) {
+			if (q->nr_hw_queues == 1)
+				e = elevator_get("mq-deadline", false);
+			if (!e)
+				return 0;
+		} else
 			e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
 
 		if (!e) {
 			printk(KERN_ERR
 				"Default I/O scheduler not found. " \
-				"Using noop/none.\n");
+				"Using noop.\n");
 			e = elevator_get("noop", false);
 		}
 	}

block/genhd.c

@@ -669,14 +669,14 @@ void del_gendisk(struct gendisk *disk)
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
-		bdev_unhash_inode(MKDEV(disk->major,
-					disk->first_minor + part->partno));
 		invalidate_partition(disk, part->partno);
+		bdev_unhash_inode(part_devt(part));
 		delete_partition(disk, part->partno);
 	}
 	disk_part_iter_exit(&piter);
 
 	invalidate_partition(disk, 0);
+	bdev_unhash_inode(disk_devt(disk));
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;