Merge branch 'block-5.9' into for-5.10/block

* block-5.9:
  blk-stat: make q->stats->lock irqsafe
  blk-iocost: ioc_pd_free() shouldn't assume irq disabled
  block: fix locking in bdev_del_partition
  block: release disk reference in hd_struct_free_work
  block: ensure bdi->io_pages is always initialized
  nvme-pci: cancel nvme device request before disabling
  nvme: only use power of two io boundaries
  nvme: fix controller instance leak
  nvmet-fc: Fix a missed _irqsave version of spin_lock in 'nvmet_fc_fod_op_done()'
  nvme: Fix NULL dereference for pci nvme controllers
  nvme-rdma: fix reset hang if controller died in the middle of a reset
  nvme-rdma: fix timeout handler
  nvme-rdma: serialize controller teardown sequences
  nvme-tcp: fix reset hang if controller died in the middle of a reset
  nvme-tcp: fix timeout handler
  nvme-tcp: serialize controller teardown sequences
  nvme: have nvme_wait_freeze_timeout return if it timed out
  nvme-fabrics: don't check state NVME_CTRL_NEW for request acceptance
  nvmet-tcp: Fix NULL dereference when a connect data comes in h2cdata pdu

block/blk-core.c

@@ -539,6 +539,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 		goto fail_stats;
 
 	q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES;
+	q->backing_dev_info->io_pages = VM_READAHEAD_PAGES;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 

block/blk-iocost.c

@@ -2092,14 +2092,15 @@ static void ioc_pd_free(struct blkg_policy_data *pd)
 {
 	struct ioc_gq *iocg = pd_to_iocg(pd);
 	struct ioc *ioc = iocg->ioc;
+	unsigned long flags;
 
 	if (ioc) {
-		spin_lock(&ioc->lock);
+		spin_lock_irqsave(&ioc->lock, flags);
 		if (!list_empty(&iocg->active_list)) {
 			propagate_active_weight(iocg, 0, 0);
 			list_del_init(&iocg->active_list);
 		}
-		spin_unlock(&ioc->lock);
+		spin_unlock_irqrestore(&ioc->lock, flags);
 
 		hrtimer_cancel(&iocg->waitq_timer);
 		hrtimer_cancel(&iocg->delay_timer);

block/blk-stat.c

@@ -137,6 +137,7 @@ void blk_stat_add_callback(struct request_queue *q,
 			   struct blk_stat_callback *cb)
 {
 	unsigned int bucket;
+	unsigned long flags;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
@@ -147,20 +148,22 @@ void blk_stat_add_callback(struct request_queue *q,
 			blk_rq_stat_init(&cpu_stat[bucket]);
 	}
 
-	spin_lock(&q->stats->lock);
+	spin_lock_irqsave(&q->stats->lock, flags);
 	list_add_tail_rcu(&cb->list, &q->stats->callbacks);
 	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
 
 void blk_stat_remove_callback(struct request_queue *q,
 			      struct blk_stat_callback *cb)
 {
-	spin_lock(&q->stats->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
 	list_del_rcu(&cb->list);
 	if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
 		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 
 	del_timer_sync(&cb->timer);
 }
@@ -183,10 +186,12 @@ void blk_stat_free_callback(struct blk_stat_callback *cb)
 
 void blk_stat_enable_accounting(struct request_queue *q)
 {
-	spin_lock(&q->stats->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
 	q->stats->enable_accounting = true;
 	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
 EXPORT_SYMBOL_GPL(blk_stat_enable_accounting);
 

block/partitions/core.c

@@ -278,6 +278,15 @@ static void hd_struct_free_work(struct work_struct *work)
 {
 	struct hd_struct *part =
 		container_of(to_rcu_work(work), struct hd_struct, rcu_work);
+	struct gendisk *disk = part_to_disk(part);
+
+	/*
+	 * Release the disk reference acquired in delete_partition here.
+	 * We can't release it in hd_struct_free because the final put_device
+	 * needs process context and thus can't be run directly from a
+	 * percpu_ref ->release handler.
+	 */
+	put_device(disk_to_dev(disk));
 
 	part->start_sect = 0;
 	part->nr_sects = 0;
@@ -293,7 +302,6 @@ static void hd_struct_free(struct percpu_ref *ref)
 		rcu_dereference_protected(disk->part_tbl, 1);
 
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
-	put_device(disk_to_dev(disk));
 
 	INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
 	queue_rcu_work(system_wq, &part->rcu_work);
@@ -524,19 +532,20 @@ int bdev_add_partition(struct block_device *bdev, int partno,
 int bdev_del_partition(struct block_device *bdev, int partno)
 {
 	struct block_device *bdevp;
-	struct hd_struct *part;
+	struct hd_struct *part = NULL;
-	int ret = 0;
+	int ret;
 
-	part = disk_get_part(bdev->bd_disk, partno);
+	bdevp = bdget_disk(bdev->bd_disk, partno);
-	if (!part)
-		return -ENXIO;
-
-	ret = -ENOMEM;
-	bdevp = bdget(part_devt(part));
 	if (!bdevp)
-		goto out_put_part;
+		return -ENOMEM;
 
 	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, 1);
+
+	ret = -ENXIO;
+	part = disk_get_part(bdev->bd_disk, partno);
+	if (!part)
+		goto out_unlock;
 
 	ret = -EBUSY;
 	if (bdevp->bd_openers)
@@ -545,16 +554,14 @@ int bdev_del_partition(struct block_device *bdev, int partno)
 	sync_blockdev(bdevp);
 	invalidate_bdev(bdevp);
 
-	mutex_lock_nested(&bdev->bd_mutex, 1);
 	delete_partition(bdev->bd_disk, part);
-	mutex_unlock(&bdev->bd_mutex);
-
 	ret = 0;
 out_unlock:
+	mutex_unlock(&bdev->bd_mutex);
 	mutex_unlock(&bdevp->bd_mutex);
 	bdput(bdevp);
-out_put_part:
+	if (part)
-	disk_put_part(part);
+		disk_put_part(part);
 	return ret;
 }
 

drivers/nvme/host/core.c

@@ -2026,13 +2026,49 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
+static inline bool nvme_first_scan(struct gendisk *disk)
+{
+	/* nvme_alloc_ns() scans the disk prior to adding it */
+	return !(disk->flags & GENHD_FL_UP);
+}
+
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	u32 iob;
+
+	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
+	    is_power_of_2(ctrl->max_hw_sectors))
+		iob = ctrl->max_hw_sectors;
+	else
+		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
+
+	if (!iob)
+		return;
+
+	if (!is_power_of_2(iob)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring unaligned IO boundary:%u\n",
+				ns->disk->disk_name, iob);
+		return;
+	}
+
+	if (blk_queue_is_zoned(ns->disk->queue)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring zoned namespace IO boundary\n",
+				ns->disk->disk_name);
+		return;
+	}
+
+	blk_queue_chunk_sectors(ns->queue, iob);
+}
+
 static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
-	u32 iob;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
@@ -2060,12 +2096,6 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		return -ENODEV;
 	}
 
-	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
-	    is_power_of_2(ctrl->max_hw_sectors))
-		iob = ctrl->max_hw_sectors;
-	else
-		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
-
 	ns->features = 0;
 	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
@@ -2097,8 +2127,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		}
 	}
 
-	if (iob && !blk_queue_is_zoned(ns->queue))
+	nvme_set_chunk_sectors(ns, id);
-		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
 	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
 	if (ns->head->disk) {
@@ -3676,6 +3705,10 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 		return 0;
 	if (a == &dev_attr_hostid.attr && !ctrl->opts)
 		return 0;
+	if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts)
+		return 0;
+	if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts)
+		return 0;
 
 	return a->mode;
 }
@@ -4390,7 +4423,7 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_subsystem *subsys = ctrl->subsys;
 	struct nvme_cel *cel, *next;
 
-	if (subsys && ctrl->instance != subsys->instance)
+	if (!subsys || ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
 	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
@@ -4534,7 +4567,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
-void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 {
 	struct nvme_ns *ns;
 
@@ -4545,6 +4578,7 @@ void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 			break;
 	}
 	up_read(&ctrl->namespaces_rwsem);
+	return timeout;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
 

drivers/nvme/host/fabrics.c

@@ -576,7 +576,6 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 	 * which is require to set the queue live in the appropinquate states.
 	 */
 	switch (ctrl->state) {
-	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
 		if (nvme_is_fabrics(req->cmd) &&
 		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)

drivers/nvme/host/nvme.h

@@ -605,7 +605,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl);
 void nvme_sync_queues(struct nvme_ctrl *ctrl);
 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);
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
 
 #define NVME_QID_ANY -1

drivers/nvme/host/pci.c

@@ -1249,8 +1249,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, true);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
+		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
 	case NVME_CTRL_RESETTING:
 		return BLK_EH_RESET_TIMER;
@@ -1267,10 +1267,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
+		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, false);
 		nvme_reset_ctrl(&dev->ctrl);
 
-		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
 	}
 

drivers/nvme/host/rdma.c

@@ -122,6 +122,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -975,7 +976,15 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 	if (!new) {
 		nvme_start_queues(&ctrl->ctrl);
-		nvme_wait_freeze(&ctrl->ctrl);
+		if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
 		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
 			ctrl->ctrl.queue_count - 1);
 		nvme_unfreeze(&ctrl->ctrl);
@@ -983,6 +992,9 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(&ctrl->ctrl);
+	nvme_rdma_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
@@ -997,6 +1009,7 @@ out_free_io_queues:
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
@@ -1007,11 +1020,13 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
@@ -1025,6 +1040,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1180,6 +1196,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
@@ -1946,6 +1963,22 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	return 0;
 }
 
+static void nvme_rdma_complete_timed_out(struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = req->queue;
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&ctrl->teardown_lock);
+	nvme_rdma_stop_queue(queue);
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&ctrl->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_rdma_timeout(struct request *rq, bool reserved)
 {
@@ -1956,29 +1989,29 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
+		 * If we are resetting, connecting or deleting we should
-		 * or we are already started error recovery. all outstanding
+		 * complete immediately because we may block controller
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
+		nvme_rdma_complete_timed_out(rq);
-		nvme_rdma_teardown_io_queues(ctrl, false);
-		nvme_rdma_teardown_admin_queue(ctrl, false);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
 	nvme_rdma_error_recovery(ctrl);
-
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2278,6 +2311,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =

drivers/nvme/host/tcp.c

@@ -124,6 +124,7 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
+	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -464,6 +465,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
@@ -1526,7 +1528,6 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 
 	if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return;
-
 	__nvme_tcp_stop_queue(queue);
 }
 
@@ -1781,7 +1782,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 	if (!new) {
 		nvme_start_queues(ctrl);
-		nvme_wait_freeze(ctrl);
+		if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
 		blk_mq_update_nr_hw_queues(ctrl->tagset,
 			ctrl->queue_count - 1);
 		nvme_unfreeze(ctrl);
@@ -1789,6 +1798,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(ctrl);
+	nvme_tcp_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->connect_q);
@@ -1874,6 +1886,7 @@ out_free_queue:
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
@@ -1884,13 +1897,16 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		return;
+		goto out;
+	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
@@ -1902,6 +1918,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
+out:
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2148,40 +2166,55 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	nvme_tcp_queue_request(&ctrl->async_req, true, true);
 }
 
+static void nvme_tcp_complete_timed_out(struct request *rq)
+{
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
+	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_tcp_timeout(struct request *rq, bool reserved)
 {
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
-	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
-	/*
+	dev_warn(ctrl->device,
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
-	dev_warn(ctrl->ctrl.device,
 		"queue %d: timeout request %#x type %d\n",
 		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
 
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+	if (ctrl->state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
+		 * If we are resetting, connecting or deleting we should
-		 * or we are already started error recovery. all outstanding
+		 * complete immediately because we may block controller
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
+		nvme_tcp_complete_timed_out(rq);
-		nvme_tcp_teardown_io_queues(&ctrl->ctrl, false);
-		nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	/*
-	nvme_tcp_error_recovery(&ctrl->ctrl);
+	 * LIVE state should trigger the normal error recovery which will
-
+	 * handle completing this request.
+	 */
+	nvme_tcp_error_recovery(ctrl);
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2422,6 +2455,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =

drivers/nvme/target/fc.c

@@ -2342,9 +2342,9 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 			return;
 		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
-			spin_lock(&fod->flock);
+			spin_lock_irqsave(&fod->flock, flags);
 			fod->abort = true;
-			spin_unlock(&fod->flock);
+			spin_unlock_irqrestore(&fod->flock, flags);
 
 			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return;

drivers/nvme/target/tcp.c

@@ -160,6 +160,11 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd);
 static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue,
 		struct nvmet_tcp_cmd *cmd)
 {
+	if (unlikely(!queue->nr_cmds)) {
+		/* We didn't allocate cmds yet, send 0xffff */
+		return USHRT_MAX;
+	}
+
 	return cmd - queue->cmds;
 }
 
@@ -866,7 +871,10 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
 
-	cmd = &queue->cmds[data->ttag];
+	if (likely(queue->nr_cmds))
+		cmd = &queue->cmds[data->ttag];
+	else
+		cmd = &queue->connect;
 
 	if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) {
 		pr_err("ttag %u unexpected data offset %u (expected %u)\n",