Merge tag 'for-linus-20180616' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes that should go into -rc1. This contains:

   - bsg_open vs bsg_unregister race fix (Anatoliy)

   - NVMe pull request from Christoph, with fixes for regressions in
     this window, FC connect/reconnect path code unification, and a
     trace point addition.

   - timeout fix (Christoph)

   - remove a few unused functions (Christoph)

   - blk-mq tag_set reinit fix (Roman)"

* tag 'for-linus-20180616' of git://git.kernel.dk/linux-block:
  bsg: fix race of bsg_open and bsg_unregister
  block: remov blk_queue_invalidate_tags
  nvme-fabrics: fix and refine state checks in __nvmf_check_ready
  nvme-fabrics: handle the admin-only case properly in nvmf_check_ready
  nvme-fabrics: refactor queue ready check
  blk-mq: remove blk_mq_tagset_iter
  nvme: remove nvme_reinit_tagset
  nvme-fc: fix nulling of queue data on reconnect
  nvme-fc: remove reinit_request routine
  blk-mq: don't time out requests again that are in the timeout handler
  nvme-fc: change controllers first connect to use reconnect path
  nvme: don't rely on the changed namespace list log
  nvmet: free smart-log buffer after use
  nvme-rdma: fix error flow during mapping request data
  nvme: add bio remapping tracepoint
  nvme: fix NULL pointer dereference in nvme_init_subsystem
  blk-mq: reinit q->tag_set_list entry only after grace period

Documentation/block/biodoc.txt

@@ -752,18 +752,6 @@ completion of the request to the block layer. This means ending tag
 operations before calling end_that_request_last()! For an example of a user
 of these helpers, see the IDE tagged command queueing support.
 
-Certain hardware conditions may dictate a need to invalidate the block tag
-queue. For instance, on IDE any tagged request error needs to clear both
-the hardware and software block queue and enable the driver to sanely restart
-all the outstanding requests. There's a third helper to do that:
-
-	blk_queue_invalidate_tags(struct request_queue *q)
-
-	Clear the internal block tag queue and re-add all the pending requests
-	to the request queue. The driver will receive them again on the
-	next request_fn run, just like it did the first time it encountered
-	them.
-
 3.2.5.2 Tag info
 
 Some block functions exist to query current tag status or to go from a
@@ -805,8 +793,7 @@ Internally, block manages tags in the blk_queue_tag structure:
 Most of the above is simple and straight forward, however busy_list may need
 a bit of explaining. Normally we don't care too much about request ordering,
 but in the event of any barrier requests in the tag queue we need to ensure
-that requests are restarted in the order they were queue. This may happen
-if the driver needs to use blk_queue_invalidate_tags().
+that requests are restarted in the order they were queue.
 
 3.3 I/O Submission
 

block/blk-mq-tag.c

@@ -311,35 +311,6 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
-int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data,
-			 int (fn)(void *, struct request *))
-{
-	int i, j, ret = 0;
-
-	if (WARN_ON_ONCE(!fn))
-		goto out;
-
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		struct blk_mq_tags *tags = set->tags[i];
-
-		if (!tags)
-			continue;
-
-		for (j = 0; j < tags->nr_tags; j++) {
-			if (!tags->static_rqs[j])
-				continue;
-
-			ret = fn(data, tags->static_rqs[j]);
-			if (ret)
-				goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tagset_iter);
-
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {

block/blk-mq.c

@@ -671,6 +671,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+		rq->rq_flags &= ~RQF_TIMED_OUT;
 		if (q->dma_drain_size && blk_rq_bytes(rq))
 			rq->nr_phys_segments--;
 	}
@@ -770,6 +771,7 @@ EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
 static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
+	req->rq_flags |= RQF_TIMED_OUT;
 	if (req->q->mq_ops->timeout) {
 		enum blk_eh_timer_return ret;
 
@@ -779,6 +781,7 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
 	}
 
+	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_add_timer(req);
 }
 
@@ -788,6 +791,8 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 
 	if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
 		return false;
+	if (rq->rq_flags & RQF_TIMED_OUT)
+		return false;
 
 	deadline = blk_rq_deadline(rq);
 	if (time_after_eq(jiffies, deadline))
@@ -2349,7 +2354,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 
 	mutex_lock(&set->tag_list_lock);
 	list_del_rcu(&q->tag_set_list);
-	INIT_LIST_HEAD(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
 		set->flags &= ~BLK_MQ_F_TAG_SHARED;
@@ -2357,8 +2361,8 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-
 	synchronize_rcu();
+	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,

block/blk-tag.c

@@ -188,7 +188,6 @@ int blk_queue_init_tags(struct request_queue *q, int depth,
 	 */
 	q->queue_tags = tags;
 	queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
-	INIT_LIST_HEAD(&q->tag_busy_list);
 	return 0;
 }
 EXPORT_SYMBOL(blk_queue_init_tags);
@@ -374,27 +373,6 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;
 	blk_start_request(rq);
-	list_add(&rq->queuelist, &q->tag_busy_list);
 	return 0;
 }
 EXPORT_SYMBOL(blk_queue_start_tag);
-
-/**
- * blk_queue_invalidate_tags - invalidate all pending tags
- * @q:  the request queue for the device
- *
- *  Description:
- *   Hardware conditions may dictate a need to stop all pending requests.
- *   In this case, we will safely clear the block side of the tag queue and
- *   readd all requests to the request queue in the right order.
- **/
-void blk_queue_invalidate_tags(struct request_queue *q)
-{
-	struct list_head *tmp, *n;
-
-	lockdep_assert_held(q->queue_lock);
-
-	list_for_each_safe(tmp, n, &q->tag_busy_list)
-		blk_requeue_request(q, list_entry_rq(tmp));
-}
-EXPORT_SYMBOL(blk_queue_invalidate_tags);

block/bsg.c

@@ -693,6 +693,8 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	struct bsg_device *bd;
 	unsigned char buf[32];
 
+	lockdep_assert_held(&bsg_mutex);
+
 	if (!blk_get_queue(rq))
 		return ERR_PTR(-ENXIO);
 
@@ -707,14 +709,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	bsg_set_block(bd, file);
 
 	atomic_set(&bd->ref_count, 1);
-	mutex_lock(&bsg_mutex);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
 	strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
 	bsg_dbg(bd, "bound to <%s>, max queue %d\n",
 		format_dev_t(buf, inode->i_rdev), bd->max_queue);
 
-	mutex_unlock(&bsg_mutex);
 	return bd;
 }
 
@@ -722,7 +722,7 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
 {
 	struct bsg_device *bd;
 
-	mutex_lock(&bsg_mutex);
+	lockdep_assert_held(&bsg_mutex);
 
 	hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) {
 		if (bd->queue == q) {
@@ -732,7 +732,6 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
 	}
 	bd = NULL;
 found:
-	mutex_unlock(&bsg_mutex);
 	return bd;
 }
 
@@ -746,17 +745,18 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
 	 */
 	mutex_lock(&bsg_mutex);
 	bcd = idr_find(&bsg_minor_idr, iminor(inode));
-	mutex_unlock(&bsg_mutex);
 
-	if (!bcd)
-		return ERR_PTR(-ENODEV);
+	if (!bcd) {
+		bd = ERR_PTR(-ENODEV);
+		goto out_unlock;
+	}
 
 	bd = __bsg_get_device(iminor(inode), bcd->queue);
-	if (bd)
-		return bd;
-
-	bd = bsg_add_device(inode, bcd->queue, file);
+	if (!bd)
+		bd = bsg_add_device(inode, bcd->queue, file);
 
+out_unlock:
+	mutex_unlock(&bsg_mutex);
 	return bd;
 }
 

drivers/nvme/host/core.c

@@ -2208,7 +2208,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		 * Verify that the subsystem actually supports multiple
 		 * controllers, else bail out.
 		 */
-		if (!ctrl->opts->discovery_nqn &&
+		if (!(ctrl->opts && ctrl->opts->discovery_nqn) &&
 		    nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
 			dev_err(ctrl->device,
 				"ignoring ctrl due to duplicate subnqn (%s).\n",
@@ -3197,40 +3197,28 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 	nvme_remove_invalid_namespaces(ctrl, nn);
 }
 
-static bool nvme_scan_changed_ns_log(struct nvme_ctrl *ctrl)
+static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 {
 	size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
 	__le32 *log;
-	int error, i;
-	bool ret = false;
+	int error;
 
 	log = kzalloc(log_size, GFP_KERNEL);
 	if (!log)
-		return false;
+		return;
 
+	/*
+	 * We need to read the log to clear the AEN, but we don't want to rely
+	 * on it for the changed namespace information as userspace could have
+	 * raced with us in reading the log page, which could cause us to miss
+	 * updates.
+	 */
 	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
-	if (error) {
+	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
-		goto out_free_log;
-	}
-
-	if (log[0] == cpu_to_le32(0xffffffff))
-		goto out_free_log;
-
-	for (i = 0; i < NVME_MAX_CHANGED_NAMESPACES; i++) {
-		u32 nsid = le32_to_cpu(log[i]);
 
-		if (nsid == 0)
-			break;
-		dev_info(ctrl->device, "rescanning namespace %d.\n", nsid);
-		nvme_validate_ns(ctrl, nsid);
-	}
-	ret = true;
-
-out_free_log:
 	kfree(log);
-	return ret;
 }
 
 static void nvme_scan_work(struct work_struct *work)
@@ -3246,9 +3234,8 @@ static void nvme_scan_work(struct work_struct *work)
 	WARN_ON_ONCE(!ctrl->tagset);
 
 	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
-		if (nvme_scan_changed_ns_log(ctrl))
-			goto out_sort_namespaces;
 		dev_info(ctrl->device, "rescanning namespaces.\n");
+		nvme_clear_changed_ns_log(ctrl);
 	}
 
 	if (nvme_identify_ctrl(ctrl, &id))
@@ -3263,7 +3250,6 @@ static void nvme_scan_work(struct work_struct *work)
 	nvme_scan_ns_sequential(ctrl, nn);
 out_free_id:
 	kfree(id);
-out_sort_namespaces:
 	down_write(&ctrl->namespaces_rwsem);
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	up_write(&ctrl->namespaces_rwsem);
@@ -3641,16 +3627,6 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set)
-{
-	if (!ctrl->ops->reinit_request)
-		return 0;
-
-	return blk_mq_tagset_iter(set, set->driver_data,
-			ctrl->ops->reinit_request);
-}
-EXPORT_SYMBOL_GPL(nvme_reinit_tagset);
-
 int __init nvme_core_init(void)
 {
 	int result = -ENOMEM;

drivers/nvme/host/fabrics.c

@@ -536,67 +536,55 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 	return NULL;
 }
 
-blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live, bool is_connected)
+/*
+ * For something we're not in a state to send to the device the default action
+ * is to busy it and retry it after the controller state is recovered.  However,
+ * anything marked for failfast or nvme multipath is immediately failed.
+ *
+ * Note: commands used to initialize the controller will be marked for failfast.
+ * Note: nvme cli/ioctl commands are marked for failfast.
+ */
+blk_status_t nvmf_fail_nonready_command(struct request *rq)
 {
-	struct nvme_command *cmd = nvme_req(rq)->cmd;
+	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+		return BLK_STS_RESOURCE;
+	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
+	return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command);
 
-	if (likely(ctrl->state == NVME_CTRL_LIVE && is_connected))
-		return BLK_STS_OK;
+bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	struct nvme_request *req = nvme_req(rq);
+
+	/*
+	 * If we are in some state of setup or teardown only allow
+	 * internally generated commands.
+	 */
+	if (!blk_rq_is_passthrough(rq) || (req->flags & NVME_REQ_USERCMD))
+		return false;
 
+	/*
+	 * Only allow commands on a live queue, except for the connect command,
+	 * which is require to set the queue live in the appropinquate states.
+	 */
 	switch (ctrl->state) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
-	case NVME_CTRL_DELETING:
-		/*
-		 * This is the case of starting a new or deleting an association
-		 * but connectivity was lost before it was fully created or torn
-		 * down. We need to error the commands used to initialize the
-		 * controller so the reconnect can go into a retry attempt.  The
-		 * commands should all be marked REQ_FAILFAST_DRIVER, which will
-		 * hit the reject path below. Anything else will be queued while
-		 * the state settles.
-		 */
-		if (!is_connected)
-			break;
-
-		/*
-		 * If queue is live, allow only commands that are internally
-		 * generated pass through.  These are commands on the admin
-		 * queue to initialize the controller. This will reject any
-		 * ioctl admin cmds received while initializing.
-		 */
-		if (queue_live && !(nvme_req(rq)->flags & NVME_REQ_USERCMD))
-			return BLK_STS_OK;
-
-		/*
-		 * If the queue is not live, allow only a connect command.  This
-		 * will reject any ioctl admin cmd as well as initialization
-		 * commands if the controller reverted the queue to non-live.
-		 */
-		if (!queue_live && blk_rq_is_passthrough(rq) &&
-		     cmd->common.opcode == nvme_fabrics_command &&
-		     cmd->fabrics.fctype == nvme_fabrics_type_connect)
-			return BLK_STS_OK;
+		if (req->cmd->common.opcode == nvme_fabrics_command &&
+		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
+			return true;
 		break;
 	default:
 		break;
+	case NVME_CTRL_DEAD:
+		return false;
 	}
 
-	/*
-	 * Any other new io is something we're not in a state to send to the
-	 * device.  Default action is to busy it and retry it after the
-	 * controller state is recovered. However, anything marked for failfast
-	 * or nvme multipath is immediately failed.  Note: commands used to
-	 * initialize the controller will be marked for failfast.
-	 * Note: nvme cli/ioctl commands are marked for failfast.
-	 */
-	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
-		return BLK_STS_RESOURCE;
-	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
-	return BLK_STS_IOERR;
+	return queue_live;
 }
-EXPORT_SYMBOL_GPL(nvmf_check_if_ready);
+EXPORT_SYMBOL_GPL(__nvmf_check_ready);
 
 static const match_table_t opt_tokens = {
 	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},

drivers/nvme/host/fabrics.h

@@ -162,7 +162,17 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl,
-	struct request *rq, bool queue_live, bool is_connected);
+blk_status_t nvmf_fail_nonready_command(struct request *rq);
+bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live);
+
+static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	if (likely(ctrl->state == NVME_CTRL_LIVE ||
+		   ctrl->state == NVME_CTRL_ADMIN_ONLY))
+		return true;
+	return __nvmf_check_ready(ctrl, rq, queue_live);
+}
 
 #endif /* _NVME_FABRICS_H */

drivers/nvme/host/fc.c

@@ -142,6 +142,7 @@ struct nvme_fc_ctrl {
 	struct nvme_fc_rport	*rport;
 	u32			cnum;
 
+	bool			ioq_live;
 	bool			assoc_active;
 	u64			association_id;
 
@@ -1470,21 +1471,6 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 
 static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg);
 
-static int
-nvme_fc_reinit_request(void *data, struct request *rq)
-{
-	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
-	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
-
-	memset(cmdiu, 0, sizeof(*cmdiu));
-	cmdiu->scsi_id = NVME_CMD_SCSI_ID;
-	cmdiu->fc_id = NVME_CMD_FC_ID;
-	cmdiu->iu_len = cpu_to_be16(sizeof(*cmdiu) / sizeof(u32));
-	memset(&op->rsp_iu, 0, sizeof(op->rsp_iu));
-
-	return 0;
-}
-
 static void
 __nvme_fc_exit_request(struct nvme_fc_ctrl *ctrl,
 		struct nvme_fc_fcp_op *op)
@@ -1893,6 +1879,7 @@ nvme_fc_free_queue(struct nvme_fc_queue *queue)
 	 */
 
 	queue->connection_id = 0;
+	atomic_set(&queue->csn, 1);
 }
 
 static void
@@ -2279,14 +2266,13 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
 	struct nvme_command *sqe = &cmdiu->sqe;
 	enum nvmefc_fcp_datadir	io_dir;
+	bool queue_ready = test_bit(NVME_FC_Q_LIVE, &queue->flags);
 	u32 data_len;
 	blk_status_t ret;
 
-	ret = nvmf_check_if_ready(&queue->ctrl->ctrl, rq,
-		test_bit(NVME_FC_Q_LIVE, &queue->flags),
-		ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE);
-	if (unlikely(ret))
-		return ret;
+	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
+	    !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+		return nvmf_fail_nonready_command(rq);
 
 	ret = nvme_setup_cmd(ns, rq, sqe);
 	if (ret)
@@ -2463,6 +2449,8 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_delete_hw_queues;
 
+	ctrl->ioq_live = true;
+
 	return 0;
 
 out_delete_hw_queues:
@@ -2480,7 +2468,7 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 }
 
 static int
-nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
+nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl)
 {
 	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 	unsigned int nr_io_queues;
@@ -2500,12 +2488,6 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ctrl->ctrl.queue_count == 1)
 		return 0;
 
-	nvme_fc_init_io_queues(ctrl);
-
-	ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
-	if (ret)
-		goto out_free_io_queues;
-
 	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_free_io_queues;
@@ -2603,8 +2585,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	 * Create the admin queue
 	 */
 
-	nvme_fc_init_queue(ctrl, 0);
-
 	ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
 				NVME_AQ_DEPTH);
 	if (ret)
@@ -2615,8 +2595,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_delete_hw_queue;
 
-	if (ctrl->ctrl.state != NVME_CTRL_NEW)
-		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 
 	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
 	if (ret)
@@ -2689,10 +2668,10 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	 */
 
 	if (ctrl->ctrl.queue_count > 1) {
-		if (ctrl->ctrl.state == NVME_CTRL_NEW)
+		if (!ctrl->ioq_live)
 			ret = nvme_fc_create_io_queues(ctrl);
 		else
-			ret = nvme_fc_reinit_io_queues(ctrl);
+			ret = nvme_fc_recreate_io_queues(ctrl);
 		if (ret)
 			goto out_term_aen_ops;
 	}
@@ -2776,8 +2755,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
 	 * use blk_mq_tagset_busy_itr() and the transport routine to
 	 * terminate the exchanges.
 	 */
-	if (ctrl->ctrl.state != NVME_CTRL_NEW)
-		blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_fc_terminate_exchange, &ctrl->ctrl);
 
@@ -2917,7 +2895,6 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.submit_async_event	= nvme_fc_submit_async_event,
 	.delete_ctrl		= nvme_fc_delete_ctrl,
 	.get_address		= nvmf_get_address,
-	.reinit_request		= nvme_fc_reinit_request,
 };
 
 static void
@@ -2934,7 +2911,7 @@ nvme_fc_connect_ctrl_work(struct work_struct *work)
 		nvme_fc_reconnect_or_delete(ctrl, ret);
 	else
 		dev_info(ctrl->ctrl.device,
-			"NVME-FC{%d}: controller reconnect complete\n",
+			"NVME-FC{%d}: controller connect complete\n",
 			ctrl->cnum);
 }
 
@@ -2982,7 +2959,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 {
 	struct nvme_fc_ctrl *ctrl;
 	unsigned long flags;
-	int ret, idx, retry;
+	int ret, idx;
 
 	if (!(rport->remoteport.port_role &
 	    (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) {
@@ -3009,11 +2986,13 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	}
 
 	ctrl->ctrl.opts = opts;
+	ctrl->ctrl.nr_reconnects = 0;
 	INIT_LIST_HEAD(&ctrl->ctrl_list);
 	ctrl->lport = lport;
 	ctrl->rport = rport;
 	ctrl->dev = lport->dev;
 	ctrl->cnum = idx;
+	ctrl->ioq_live = false;
 	ctrl->assoc_active = false;
 	init_waitqueue_head(&ctrl->ioabort_wait);
 
@@ -3032,6 +3011,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	ctrl->ctrl.sqsize = opts->queue_size - 1;
 	ctrl->ctrl.kato = opts->kato;
+	ctrl->ctrl.cntlid = 0xffff;
 
 	ret = -ENOMEM;
 	ctrl->queues = kcalloc(ctrl->ctrl.queue_count,
@@ -3039,6 +3019,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	if (!ctrl->queues)
 		goto out_free_ida;
 
+	nvme_fc_init_queue(ctrl, 0);
+
 	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
 	ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
 	ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
@@ -3081,62 +3063,24 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
 	spin_unlock_irqrestore(&rport->lock, flags);
 
-	/*
-	 * It's possible that transactions used to create the association
-	 * may fail. Examples: CreateAssociation LS or CreateIOConnection
-	 * LS gets dropped/corrupted/fails; or a frame gets dropped or a
-	 * command times out for one of the actions to init the controller
-	 * (Connect, Get/Set_Property, Set_Features, etc). Many of these
-	 * transport errors (frame drop, LS failure) inherently must kill
-	 * the association. The transport is coded so that any command used
-	 * to create the association (prior to a LIVE state transition
-	 * while NEW or CONNECTING) will fail if it completes in error or
-	 * times out.
-	 *
-	 * As such: as the connect request was mostly likely due to a
-	 * udev event that discovered the remote port, meaning there is
-	 * not an admin or script there to restart if the connect
-	 * request fails, retry the initial connection creation up to
-	 * three times before giving up and declaring failure.
-	 */
-	for (retry = 0; retry < 3; retry++) {
-		ret = nvme_fc_create_association(ctrl);
-		if (!ret)
-			break;
-	}
-
-	if (ret) {
-		nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
-		cancel_work_sync(&ctrl->ctrl.reset_work);
-		cancel_delayed_work_sync(&ctrl->connect_work);
-
-		/* couldn't schedule retry - fail out */
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING) ||
+	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_err(ctrl->ctrl.device,
-			"NVME-FC{%d}: Connect retry failed\n", ctrl->cnum);
-
-		ctrl->ctrl.opts = NULL;
+			"NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum);
+		goto fail_ctrl;
+	}
 
-		/* initiate nvme ctrl ref counting teardown */
-		nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_get_ctrl(&ctrl->ctrl);
 
-		/* Remove core ctrl ref. */
+	if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
 		nvme_put_ctrl(&ctrl->ctrl);
-
-		/* as we're past the point where we transition to the ref
-		 * counting teardown path, if we return a bad pointer here,
-		 * the calling routine, thinking it's prior to the
-		 * transition, will do an rport put. Since the teardown
-		 * path also does a rport put, we do an extra get here to
-		 * so proper order/teardown happens.
-		 */
-		nvme_fc_rport_get(rport);
-
-		if (ret > 0)
-			ret = -EIO;
-		return ERR_PTR(ret);
+		dev_err(ctrl->ctrl.device,
+			"NVME-FC{%d}: failed to schedule initial connect\n",
+			ctrl->cnum);
+		goto fail_ctrl;
 	}
 
-	nvme_get_ctrl(&ctrl->ctrl);
+	flush_delayed_work(&ctrl->connect_work);
 
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
@@ -3144,6 +3088,30 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	return &ctrl->ctrl;
 
+fail_ctrl:
+	nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
+	cancel_work_sync(&ctrl->ctrl.reset_work);
+	cancel_delayed_work_sync(&ctrl->connect_work);
+
+	ctrl->ctrl.opts = NULL;
+
+	/* initiate nvme ctrl ref counting teardown */
+	nvme_uninit_ctrl(&ctrl->ctrl);
+
+	/* Remove core ctrl ref. */
+	nvme_put_ctrl(&ctrl->ctrl);
+
+	/* as we're past the point where we transition to the ref
+	 * counting teardown path, if we return a bad pointer here,
+	 * the calling routine, thinking it's prior to the
+	 * transition, will do an rport put. Since the teardown
+	 * path also does a rport put, we do an extra get here to
+	 * so proper order/teardown happens.
+	 */
+	nvme_fc_rport_get(rport);
+
+	return ERR_PTR(-EIO);
+
 out_cleanup_admin_q:
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
 out_free_admin_tag_set:

drivers/nvme/host/multipath.c

@@ -12,6 +12,7 @@
  */
 
 #include <linux/moduleparam.h>
+#include <trace/events/block.h>
 #include "nvme.h"
 
 static bool multipath = true;
@@ -111,6 +112,9 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 	if (likely(ns)) {
 		bio->bi_disk = ns->disk;
 		bio->bi_opf |= REQ_NVME_MPATH;
+		trace_block_bio_remap(bio->bi_disk->queue, bio,
+				      disk_devt(ns->head->disk),
+				      bio->bi_iter.bi_sector);
 		ret = direct_make_request(bio);
 	} else if (!list_empty_careful(&head->list)) {
 		dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");

drivers/nvme/host/nvme.h

@@ -321,7 +321,6 @@ struct nvme_ctrl_ops {
 	void (*submit_async_event)(struct nvme_ctrl *ctrl);
 	void (*delete_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
-	int (*reinit_request)(void *data, struct request *rq);
 	void (*stop_ctrl)(struct nvme_ctrl *ctrl);
 };
 
@@ -416,7 +415,6 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
-int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set);
 
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,

drivers/nvme/host/rdma.c

@@ -1189,21 +1189,38 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 	count = ib_dma_map_sg(ibdev, req->sg_table.sgl, req->nents,
 		    rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	if (unlikely(count <= 0)) {
-		sg_free_table_chained(&req->sg_table, true);
-		return -EIO;
+		ret = -EIO;
+		goto out_free_table;
 	}
 
 	if (count == 1) {
 		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
 		    blk_rq_payload_bytes(rq) <=
-				nvme_rdma_inline_data_size(queue))
-			return nvme_rdma_map_sg_inline(queue, req, c);
+				nvme_rdma_inline_data_size(queue)) {
+			ret = nvme_rdma_map_sg_inline(queue, req, c);
+			goto out;
+		}
 
-		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)
-			return nvme_rdma_map_sg_single(queue, req, c);
+		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
+			ret = nvme_rdma_map_sg_single(queue, req, c);
+			goto out;
+		}
 	}
 
-	return nvme_rdma_map_sg_fr(queue, req, c, count);
+	ret = nvme_rdma_map_sg_fr(queue, req, c, count);
+out:
+	if (unlikely(ret))
+		goto out_unmap_sg;
+
+	return 0;
+
+out_unmap_sg:
+	ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
+			req->nents, rq_data_dir(rq) ==
+			WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+out_free_table:
+	sg_free_table_chained(&req->sg_table, true);
+	return ret;
 }
 
 static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
@@ -1613,15 +1630,14 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_rdma_qe *sqe = &req->sqe;
 	struct nvme_command *c = sqe->data;
 	struct ib_device *dev;
+	bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 	int err;
 
 	WARN_ON_ONCE(rq->tag < 0);
 
-	ret = nvmf_check_if_ready(&queue->ctrl->ctrl, rq,
-		test_bit(NVME_RDMA_Q_LIVE, &queue->flags), true);
-	if (unlikely(ret))
-		return ret;
+	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+		return nvmf_fail_nonready_command(rq);
 
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,

drivers/nvme/target/admin-cmd.c

@@ -119,9 +119,11 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 	else
 		status = nvmet_get_smart_log_nsid(req, log);
 	if (status)
-		goto out;
+		goto out_free_log;
 
 	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+out_free_log:
+	kfree(log);
 out:
 	nvmet_req_complete(req, status);
 }

drivers/nvme/target/loop.c

@@ -158,12 +158,11 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_loop_queue *queue = hctx->driver_data;
 	struct request *req = bd->rq;
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
+	bool queue_ready = test_bit(NVME_LOOP_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 
-	ret = nvmf_check_if_ready(&queue->ctrl->ctrl, req,
-		test_bit(NVME_LOOP_Q_LIVE, &queue->flags), true);
-	if (unlikely(ret))
-		return ret;
+	if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
+		return nvmf_fail_nonready_command(req);
 
 	ret = nvme_setup_cmd(ns, req, &iod->cmd);
 	if (ret)

include/linux/blk-mq.h

@@ -281,8 +281,6 @@ void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
-int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data,
-		int (reinit_request)(void *, struct request *));
 
 int blk_mq_map_queues(struct blk_mq_tag_set *set);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);

include/linux/blkdev.h

@@ -127,6 +127,8 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
 /* already slept for hybrid poll */
 #define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 20))
+/* ->timeout has been called, don't expire again */
+#define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
@@ -560,7 +562,6 @@ struct request_queue {
 	unsigned int		dma_alignment;
 
 	struct blk_queue_tag	*queue_tags;
-	struct list_head	tag_busy_list;
 
 	unsigned int		nr_sorted;
 	unsigned int		in_flight[2];
@@ -1373,7 +1374,6 @@ extern void blk_queue_end_tag(struct request_queue *, struct request *);
 extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
 extern void blk_queue_free_tags(struct request_queue *);
 extern int blk_queue_resize_tags(struct request_queue *, int);
-extern void blk_queue_invalidate_tags(struct request_queue *);
 extern struct blk_queue_tag *blk_init_tags(int, int);
 extern void blk_free_tags(struct blk_queue_tag *);