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;
 

drivers/md/dm-rq.c

@@ -328,13 +328,15 @@ static void dm_softirq_done(struct request *rq)
 	int rw;
 
 	if (!clone) {
-		rq_end_stats(tio->md, rq);
+		struct mapped_device *md = tio->md;
+
+		rq_end_stats(md, rq);
 		rw = rq_data_dir(rq);
 		if (!rq->q->mq_ops)
 			blk_end_request_all(rq, tio->error);
 		else
 			blk_mq_end_request(rq, tio->error);
-		rq_completed(tio->md, rw, false);
+		rq_completed(md, rw, false);
 		return;
 	}
 

drivers/nvme/host/fabrics.c

@@ -480,11 +480,16 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
  * being implemented to the common NVMe fabrics library. Part of
  * the overall init sequence of starting up a fabrics driver.
  */
-void nvmf_register_transport(struct nvmf_transport_ops *ops)
+int nvmf_register_transport(struct nvmf_transport_ops *ops)
 {
+	if (!ops->create_ctrl)
+		return -EINVAL;
+
 	mutex_lock(&nvmf_transports_mutex);
 	list_add_tail(&ops->entry, &nvmf_transports);
 	mutex_unlock(&nvmf_transports_mutex);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nvmf_register_transport);
 

drivers/nvme/host/fabrics.h

@@ -128,7 +128,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
 int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
 int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
-void nvmf_register_transport(struct nvmf_transport_ops *ops);
+int nvmf_register_transport(struct nvmf_transport_ops *ops);
 void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);

drivers/nvme/host/fc.c

@@ -2353,18 +2353,6 @@ __nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	/* sanity checks */
 
-	/* FC-NVME supports 64-byte SQE only */
-	if (ctrl->ctrl.ioccsz != 4) {
-		dev_err(ctrl->ctrl.device, "ioccsz %d is not supported!\n",
-				ctrl->ctrl.ioccsz);
-		goto out_remove_admin_queue;
-	}
-	/* FC-NVME supports 16-byte CQE only */
-	if (ctrl->ctrl.iorcsz != 1) {
-		dev_err(ctrl->ctrl.device, "iorcsz %d is not supported!\n",
-				ctrl->ctrl.iorcsz);
-		goto out_remove_admin_queue;
-	}
 	/* FC-NVME does not have other data in the capsule */
 	if (ctrl->ctrl.icdoff) {
 		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
@@ -2562,8 +2550,7 @@ static int __init nvme_fc_init_module(void)
 	if (!nvme_fc_wq)
 		return -ENOMEM;
 
-	nvmf_register_transport(&nvme_fc_transport);
-	return 0;
+	return nvmf_register_transport(&nvme_fc_transport);
 }
 
 static void __exit nvme_fc_exit_module(void)

drivers/nvme/host/nvme.h

@@ -78,6 +78,11 @@ enum nvme_quirks {
 	 * readiness, which is done by reading the NVME_CSTS_RDY bit.
 	 */
 	NVME_QUIRK_DELAY_BEFORE_CHK_RDY		= (1 << 3),
+
+	/*
+	 * APST should not be used.
+	 */
+	NVME_QUIRK_NO_APST			= (1 << 4),
 };
 
 /*
@@ -112,6 +117,7 @@ enum nvme_ctrl_state {
 
 struct nvme_ctrl {
 	enum nvme_ctrl_state state;
+	bool identified;
 	spinlock_t lock;
 	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
@@ -147,13 +153,19 @@ struct nvme_ctrl {
 	u32 vs;
 	u32 sgls;
 	u16 kas;
+	u8 npss;
+	u8 apsta;
 	unsigned int kato;
 	bool subsystem;
 	unsigned long quirks;
+	struct nvme_id_power_state psd[32];
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
 
+	/* Power saving configuration */
+	u64 ps_max_latency_us;
+
 	/* Fabrics only */
 	u16 sqsize;
 	u32 ioccsz;

drivers/nvme/host/pci.c

@@ -613,10 +613,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	spin_lock_irq(&nvmeq->q_lock);
 	if (unlikely(nvmeq->cq_vector < 0)) {
-		if (ns && !test_bit(NVME_NS_DEAD, &ns->flags))
-			ret = BLK_MQ_RQ_QUEUE_BUSY;
-		else
-			ret = BLK_MQ_RQ_QUEUE_ERROR;
+		ret = BLK_MQ_RQ_QUEUE_ERROR;
 		spin_unlock_irq(&nvmeq->q_lock);
 		goto out_cleanup_iod;
 	}
@@ -1739,7 +1736,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
-	kfree(dev->ctrl.opal_dev);
+	free_opal_dev(dev->ctrl.opal_dev);
 	kfree(dev);
 }
 
@@ -1789,14 +1786,17 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
-	if ((dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) && !dev->ctrl.opal_dev) {
-		dev->ctrl.opal_dev =
-			init_opal_dev(&dev->ctrl, &nvme_sec_submit);
+	if (dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) {
+		if (!dev->ctrl.opal_dev)
+			dev->ctrl.opal_dev =
+				init_opal_dev(&dev->ctrl, &nvme_sec_submit);
+		else if (was_suspend)
+			opal_unlock_from_suspend(dev->ctrl.opal_dev);
+	} else {
+		free_opal_dev(dev->ctrl.opal_dev);
+		dev->ctrl.opal_dev = NULL;
 	}
 
-	if (was_suspend)
-		opal_unlock_from_suspend(dev->ctrl.opal_dev);
-
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out;
@@ -2001,8 +2001,10 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	pci_set_drvdata(pdev, NULL);
 
-	if (!pci_device_is_present(pdev))
+	if (!pci_device_is_present(pdev)) {
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
+		nvme_dev_disable(dev, false);
+	}
 
 	flush_work(&dev->reset_work);
 	nvme_uninit_ctrl(&dev->ctrl);
@@ -2121,6 +2123,7 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, nvme_id_table);

drivers/nvme/host/rdma.c

@@ -42,28 +42,6 @@
 
 #define NVME_RDMA_MAX_INLINE_SEGMENTS	1
 
-static const char *const nvme_rdma_cm_status_strs[] = {
-	[NVME_RDMA_CM_INVALID_LEN]	= "invalid length",
-	[NVME_RDMA_CM_INVALID_RECFMT]	= "invalid record format",
-	[NVME_RDMA_CM_INVALID_QID]	= "invalid queue ID",
-	[NVME_RDMA_CM_INVALID_HSQSIZE]	= "invalid host SQ size",
-	[NVME_RDMA_CM_INVALID_HRQSIZE]	= "invalid host RQ size",
-	[NVME_RDMA_CM_NO_RSC]		= "resource not found",
-	[NVME_RDMA_CM_INVALID_IRD]	= "invalid IRD",
-	[NVME_RDMA_CM_INVALID_ORD]	= "Invalid ORD",
-};
-
-static const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
-{
-	size_t index = status;
-
-	if (index < ARRAY_SIZE(nvme_rdma_cm_status_strs) &&
-	    nvme_rdma_cm_status_strs[index])
-		return nvme_rdma_cm_status_strs[index];
-	else
-		return "unrecognized reason";
-};
-
 /*
  * We handle AEN commands ourselves and don't even let the
  * block layer know about them.
@@ -155,6 +133,10 @@ struct nvme_rdma_ctrl {
 		struct sockaddr addr;
 		struct sockaddr_in addr_in;
 	};
+	union {
+		struct sockaddr src_addr;
+		struct sockaddr_in src_addr_in;
+	};
 
 	struct nvme_ctrl	ctrl;
 };
@@ -567,6 +549,7 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
 		int idx, size_t queue_size)
 {
 	struct nvme_rdma_queue *queue;
+	struct sockaddr *src_addr = NULL;
 	int ret;
 
 	queue = &ctrl->queues[idx];
@@ -589,7 +572,10 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
 	}
 
 	queue->cm_error = -ETIMEDOUT;
-	ret = rdma_resolve_addr(queue->cm_id, NULL, &ctrl->addr,
+	if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
+		src_addr = &ctrl->src_addr;
+
+	ret = rdma_resolve_addr(queue->cm_id, src_addr, &ctrl->addr,
 			NVME_RDMA_CONNECT_TIMEOUT_MS);
 	if (ret) {
 		dev_info(ctrl->ctrl.device,
@@ -1905,6 +1891,16 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		goto out_free_ctrl;
 	}
 
+	if (opts->mask & NVMF_OPT_HOST_TRADDR) {
+		ret = nvme_rdma_parse_ipaddr(&ctrl->src_addr_in,
+				opts->host_traddr);
+		if (ret) {
+			pr_err("malformed src IP address passed: %s\n",
+			       opts->host_traddr);
+			goto out_free_ctrl;
+		}
+	}
+
 	if (opts->mask & NVMF_OPT_TRSVCID) {
 		u16 port;
 
@@ -2016,7 +2012,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 static struct nvmf_transport_ops nvme_rdma_transport = {
 	.name		= "rdma",
 	.required_opts	= NVMF_OPT_TRADDR,
-	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY,
+	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
+			  NVMF_OPT_HOST_TRADDR,
 	.create_ctrl	= nvme_rdma_create_ctrl,
 };
 
@@ -2063,8 +2060,7 @@ static int __init nvme_rdma_init_module(void)
 		return ret;
 	}
 
-	nvmf_register_transport(&nvme_rdma_transport);
-	return 0;
+	return nvmf_register_transport(&nvme_rdma_transport);
 }
 
 static void __exit nvme_rdma_cleanup_module(void)

drivers/nvme/target/admin-cmd.c

@@ -41,7 +41,7 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->get_log_page.nsid);
 	if (!ns) {
 		status = NVME_SC_INVALID_NS;
-		pr_err("nvmet : Counld not find namespace id : %d\n",
+		pr_err("nvmet : Could not find namespace id : %d\n",
 				le32_to_cpu(req->cmd->get_log_page.nsid));
 		goto out;
 	}
@@ -509,7 +509,7 @@ int nvmet_parse_admin_cmd(struct nvmet_req *req)
 		break;
 	case nvme_admin_identify:
 		req->data_len = 4096;
-		switch (le32_to_cpu(cmd->identify.cns)) {
+		switch (cmd->identify.cns) {
 		case NVME_ID_CNS_NS:
 			req->execute = nvmet_execute_identify_ns;
 			return 0;

drivers/nvme/target/core.c

@@ -17,6 +17,7 @@
 #include "nvmet.h"
 
 static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
+static DEFINE_IDA(cntlid_ida);
 
 /*
  * This read/write semaphore is used to synchronize access to configuration
@@ -749,7 +750,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	if (!ctrl->sqs)
 		goto out_free_cqs;
 
-	ret = ida_simple_get(&subsys->cntlid_ida,
+	ret = ida_simple_get(&cntlid_ida,
 			     NVME_CNTLID_MIN, NVME_CNTLID_MAX,
 			     GFP_KERNEL);
 	if (ret < 0) {
@@ -819,7 +820,7 @@ static void nvmet_ctrl_free(struct kref *ref)
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fatal_err_work);
 
-	ida_simple_remove(&subsys->cntlid_ida, ctrl->cntlid);
+	ida_simple_remove(&cntlid_ida, ctrl->cntlid);
 	nvmet_subsys_put(subsys);
 
 	kfree(ctrl->sqs);
@@ -918,9 +919,6 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 	mutex_init(&subsys->lock);
 	INIT_LIST_HEAD(&subsys->namespaces);
 	INIT_LIST_HEAD(&subsys->ctrls);
-
-	ida_init(&subsys->cntlid_ida);
-
 	INIT_LIST_HEAD(&subsys->hosts);
 
 	return subsys;
@@ -933,7 +931,6 @@ static void nvmet_subsys_free(struct kref *ref)
 
 	WARN_ON_ONCE(!list_empty(&subsys->namespaces));
 
-	ida_destroy(&subsys->cntlid_ida);
 	kfree(subsys->subsysnqn);
 	kfree(subsys);
 }
@@ -976,6 +973,7 @@ static void __exit nvmet_exit(void)
 {
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
+	ida_destroy(&cntlid_ida);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);

drivers/nvme/target/discovery.c

@@ -186,14 +186,14 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
 		}
 	case nvme_admin_identify:
 		req->data_len = 4096;
-		switch (le32_to_cpu(cmd->identify.cns)) {
+		switch (cmd->identify.cns) {
 		case NVME_ID_CNS_CTRL:
 			req->execute =
 				nvmet_execute_identify_disc_ctrl;
 			return 0;
 		default:
 			pr_err("nvmet: unsupported identify cns %d\n",
-				le32_to_cpu(cmd->identify.cns));
+				cmd->identify.cns);
 			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	default:

drivers/nvme/target/fabrics-cmd.c

@@ -153,8 +153,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 		goto out;
 	}
 
-	pr_info("creating controller %d for NQN %s.\n",
-			ctrl->cntlid, ctrl->hostnqn);
+	pr_info("creating controller %d for subsystem %s for NQN %s.\n",
+		ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn);
 	req->rsp->result.u16 = cpu_to_le16(ctrl->cntlid);
 
 out:
@@ -220,7 +220,7 @@ int nvmet_parse_connect_cmd(struct nvmet_req *req)
 
 	req->ns = NULL;
 
-	if (req->cmd->common.opcode != nvme_fabrics_command) {
+	if (cmd->common.opcode != nvme_fabrics_command) {
 		pr_err("invalid command 0x%x on unconnected queue.\n",
 			cmd->fabrics.opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;

drivers/nvme/target/fc.c

@@ -1817,16 +1817,14 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 		/* data no longer needed */
 		nvmet_fc_free_tgt_pgs(fod);
 
-		if (fcpreq->fcp_error || abort)
-			nvmet_req_complete(&fod->req, fcpreq->fcp_error);
-
+		nvmet_req_complete(&fod->req, fcpreq->fcp_error);
 		return;
 	}
 
 	switch (fcpreq->op) {
 
 	case NVMET_FCOP_WRITEDATA:
-		if (abort || fcpreq->fcp_error ||
+		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
 			nvmet_req_complete(&fod->req,
 					NVME_SC_FC_TRANSPORT_ERROR);
@@ -1849,7 +1847,7 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 
 	case NVMET_FCOP_READDATA:
 	case NVMET_FCOP_READDATA_RSP:
-		if (abort || fcpreq->fcp_error ||
+		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
 			/* data no longer needed */
 			nvmet_fc_free_tgt_pgs(fod);

drivers/nvme/target/loop.c

@@ -724,8 +724,7 @@ static int __init nvme_loop_init_module(void)
 	ret = nvmet_register_transport(&nvme_loop_ops);
 	if (ret)
 		return ret;
-	nvmf_register_transport(&nvme_loop_transport);
-	return 0;
+	return nvmf_register_transport(&nvme_loop_transport);
 }
 
 static void __exit nvme_loop_cleanup_module(void)

drivers/nvme/target/nvmet.h

@@ -142,7 +142,6 @@ struct nvmet_subsys {
 	unsigned int		max_nsid;
 
 	struct list_head	ctrls;
-	struct ida		cntlid_ida;
 
 	struct list_head	hosts;
 	bool			allow_any_host;

drivers/nvme/target/rdma.c

@@ -1041,6 +1041,9 @@ static int nvmet_rdma_cm_reject(struct rdma_cm_id *cm_id,
 {
 	struct nvme_rdma_cm_rej rej;
 
+	pr_debug("rejecting connect request: status %d (%s)\n",
+		 status, nvme_rdma_cm_msg(status));
+
 	rej.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
 	rej.sts = cpu_to_le16(status);
 
@@ -1091,7 +1094,7 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 	queue->idx = ida_simple_get(&nvmet_rdma_queue_ida, 0, 0, GFP_KERNEL);
 	if (queue->idx < 0) {
 		ret = NVME_RDMA_CM_NO_RSC;
-		goto out_free_queue;
+		goto out_destroy_sq;
 	}
 
 	ret = nvmet_rdma_alloc_rsps(queue);
@@ -1135,7 +1138,6 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 out_free_queue:
 	kfree(queue);
 out_reject:
-	pr_debug("rejecting connect request with status code %d\n", ret);
 	nvmet_rdma_cm_reject(cm_id, ret);
 	return NULL;
 }
@@ -1188,7 +1190,6 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 
 	ndev = nvmet_rdma_find_get_device(cm_id);
 	if (!ndev) {
-		pr_err("no client data!\n");
 		nvmet_rdma_cm_reject(cm_id, NVME_RDMA_CM_NO_RSC);
 		return -ECONNREFUSED;
 	}

drivers/scsi/scsi_lib.c

@@ -1167,7 +1167,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
 
 	/* zero out the cmd, except for the embedded scsi_request */
 	memset((char *)cmd + sizeof(cmd->req), 0,
-		sizeof(*cmd) - sizeof(cmd->req));
+		sizeof(*cmd) - sizeof(cmd->req) + dev->host->hostt->cmd_size);
 
 	cmd->device = dev;
 	cmd->sense_buffer = buf;

drivers/scsi/scsi_transport_sas.c

@@ -227,27 +227,31 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 		return 0;
 	}
 
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+	q->cmd_size = sizeof(struct scsi_request);
+
 	if (rphy) {
-		q = blk_init_queue(sas_non_host_smp_request, NULL);
+		q->request_fn = sas_non_host_smp_request;
 		dev = &rphy->dev;
 		name = dev_name(dev);
 		release = NULL;
 	} else {
-		q = blk_init_queue(sas_host_smp_request, NULL);
+		q->request_fn = sas_host_smp_request;
 		dev = &shost->shost_gendev;
 		snprintf(namebuf, sizeof(namebuf),
 			 "sas_host%d", shost->host_no);
 		name = namebuf;
 		release = sas_host_release;
 	}
-	if (!q)
-		return -ENOMEM;
+	error = blk_init_allocated_queue(q);
+	if (error)
+		goto out_cleanup_queue;
 
 	error = bsg_register_queue(q, dev, name, release);
-	if (error) {
-		blk_cleanup_queue(q);
-		return -ENOMEM;
-	}
+	if (error)
+		goto out_cleanup_queue;
 
 	if (rphy)
 		rphy->q = q;
@@ -261,6 +265,10 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 
 	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
 	return 0;
+
+out_cleanup_queue:
+	blk_cleanup_queue(q);
+	return error;
 }
 
 static void sas_bsg_remove(struct Scsi_Host *shost, struct sas_rphy *rphy)

fs/block_dev.c

@@ -1043,13 +1043,22 @@ static struct block_device *bd_acquire(struct inode *inode)
 
 	spin_lock(&bdev_lock);
 	bdev = inode->i_bdev;
-	if (bdev) {
+	if (bdev && !inode_unhashed(bdev->bd_inode)) {
 		bdgrab(bdev);
 		spin_unlock(&bdev_lock);
 		return bdev;
 	}
 	spin_unlock(&bdev_lock);
 
+	/*
+	 * i_bdev references block device inode that was already shut down
+	 * (corresponding device got removed).  Remove the reference and look
+	 * up block device inode again just in case new device got
+	 * reestablished under the same device number.
+	 */
+	if (bdev)
+		bd_forget(inode);
+
 	bdev = bdget(inode->i_rdev);
 	if (bdev) {
 		spin_lock(&bdev_lock);

include/linux/blk-mq.h

@@ -33,6 +33,7 @@ struct blk_mq_hw_ctx {
 	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
 
+	wait_queue_t		dispatch_wait;
 	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
@@ -160,6 +161,7 @@ enum {
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 	BLK_MQ_S_SCHED_RESTART	= 2,
+	BLK_MQ_S_TAG_WAITING	= 3,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 

include/linux/nvme-rdma.h

@@ -29,6 +29,30 @@ enum nvme_rdma_cm_status {
 	NVME_RDMA_CM_INVALID_ORD	= 0x08,
 };
 
+static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
+{
+	switch (status) {
+	case NVME_RDMA_CM_INVALID_LEN:
+		return "invalid length";
+	case NVME_RDMA_CM_INVALID_RECFMT:
+		return "invalid record format";
+	case NVME_RDMA_CM_INVALID_QID:
+		return "invalid queue ID";
+	case NVME_RDMA_CM_INVALID_HSQSIZE:
+		return "invalid host SQ size";
+	case NVME_RDMA_CM_INVALID_HRQSIZE:
+		return "invalid host RQ size";
+	case NVME_RDMA_CM_NO_RSC:
+		return "resource not found";
+	case NVME_RDMA_CM_INVALID_IRD:
+		return "invalid IRD";
+	case NVME_RDMA_CM_INVALID_ORD:
+		return "Invalid ORD";
+	default:
+		return "unrecognized reason";
+	}
+}
+
 /**
  * struct nvme_rdma_cm_req - rdma connect request
  *

include/linux/nvme.h

@@ -579,6 +579,12 @@ struct nvme_write_zeroes_cmd {
 	__le16			appmask;
 };
 
+/* Features */
+
+struct nvme_feat_auto_pst {
+	__le64 entries[32];
+};
+
 /* Admin commands */
 
 enum nvme_admin_opcode {
@@ -644,7 +650,9 @@ struct nvme_identify {
 	__le32			nsid;
 	__u64			rsvd2[2];
 	union nvme_data_ptr	dptr;
-	__le32			cns;
+	__u8			cns;
+	__u8			rsvd3;
+	__le16			ctrlid;
 	__u32			rsvd11[5];
 };
 

include/linux/sed-opal.h

@@ -27,6 +27,7 @@ typedef int (sec_send_recv)(void *data, u16 spsp, u8 secp, void *buffer,
 		size_t len, bool send);
 
 #ifdef CONFIG_BLK_SED_OPAL
+void free_opal_dev(struct opal_dev *dev);
 bool opal_unlock_from_suspend(struct opal_dev *dev);
 struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv);
 int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *ioctl_ptr);
@@ -51,6 +52,10 @@ static inline bool is_sed_ioctl(unsigned int cmd)
 	return false;
 }
 #else
+static inline void free_opal_dev(struct opal_dev *dev)
+{
+}
+
 static inline bool is_sed_ioctl(unsigned int cmd)
 {
 	return false;