7 files changed, 195 insertions, 161 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 08f2c92602f4..6a9dd68c0f4f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1253,6 +1253,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	 * effects say only one namespace is affected.
 	 */
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
+		mutex_lock(&ctrl->scan_lock);
 		nvme_start_freeze(ctrl);
 		nvme_wait_freeze(ctrl);
 	}
@@ -1281,8 +1282,10 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 	 */
 	if (effects & NVME_CMD_EFFECTS_LBCC)
 		nvme_update_formats(ctrl);
-	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK))
+	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
 		nvme_unfreeze(ctrl);
+		mutex_unlock(&ctrl->scan_lock);
+	}
 	if (effects & NVME_CMD_EFFECTS_CCC)
 		nvme_init_identify(ctrl);
 	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC))
@@ -2173,18 +2176,20 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct
 	size_t nqnlen;
 	int off;
 
-	nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
-	if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
-		strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
-		return;
-	}
+	if(!(ctrl->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) {
+		nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
+		if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
+			strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
+			return;
+		}
 
-	if (ctrl->vs >= NVME_VS(1, 2, 1))
-		dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n");
+		if (ctrl->vs >= NVME_VS(1, 2, 1))
+			dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n");
+	}
 
 	/* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */
 	off = snprintf(subsys->subnqn, NVMF_NQN_SIZE,
-			"nqn.2014.08.org.nvmexpress:%4x%4x",
+			"nqn.2014.08.org.nvmexpress:%04x%04x",
 			le16_to_cpu(id->vid), le16_to_cpu(id->ssvid));
 	memcpy(subsys->subnqn + off, id->sn, sizeof(id->sn));
 	off += sizeof(id->sn);
@@ -2500,7 +2505,6 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->oaes = le32_to_cpu(id->oaes);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
-	ctrl->cntlid = le16_to_cpup(&id->cntlid);
 	if (id->mdts)
 		max_hw_sectors = 1 << (id->mdts + page_shift - 9);
 	else
@@ -3400,6 +3404,7 @@ static void nvme_scan_work(struct work_struct *work)
 	if (nvme_identify_ctrl(ctrl, &id))
 		return;
 
+	mutex_lock(&ctrl->scan_lock);
 	nn = le32_to_cpu(id->nn);
 	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
 	    !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
@@ -3408,6 +3413,7 @@ static void nvme_scan_work(struct work_struct *work)
 	}
 	nvme_scan_ns_sequential(ctrl, nn);
 out_free_id:
+	mutex_unlock(&ctrl->scan_lock);
 	kfree(id);
 	down_write(&ctrl->namespaces_rwsem);
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
@@ -3651,6 +3657,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 
 	ctrl->state = NVME_CTRL_NEW;
 	spin_lock_init(&ctrl->lock);
+	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index b2ab213f43de..3eb908c50e1a 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -874,6 +874,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	if (opts->discovery_nqn) {
 		opts->kato = 0;
 		opts->nr_io_queues = 0;
+		opts->nr_write_queues = 0;
+		opts->nr_poll_queues = 0;
 		opts->duplicate_connect = true;
 	}
 	if (ctrl_loss_tmo < 0)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 183ec17ba067..b9fff3b8ed1b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -545,8 +545,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
 	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
 		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
-	if (!(ctrl->anacap & (1 << 6)))
-		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
+	ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
 
 	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
 		dev_err(ctrl->device,
@@ -570,6 +569,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	return 0;
 out_free_ana_log_buf:
 	kfree(ctrl->ana_log_buf);
+	ctrl->ana_log_buf = NULL;
 out:
 	return error;
 }
@@ -577,5 +577,6 @@ out:
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
 	kfree(ctrl->ana_log_buf);
+	ctrl->ana_log_buf = NULL;
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2b36ac922596..c4a1bb41abf0 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -90,6 +90,11 @@ enum nvme_quirks {
 	 * Set MEDIUM priority on SQ creation
 	 */
 	NVME_QUIRK_MEDIUM_PRIO_SQ		= (1 << 7),
+
+	/*
+	 * Ignore device provided subnqn.
+	 */
+	NVME_QUIRK_IGNORE_DEV_SUBNQN		= (1 << 8),
 };
 
 /*
@@ -149,6 +154,7 @@ struct nvme_ctrl {
 	enum nvme_ctrl_state state;
 	bool identified;
 	spinlock_t lock;
+	struct mutex scan_lock;
 	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
 	struct request_queue *connect_q;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5a0bf6a24d50..e905861186e3 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -95,6 +95,7 @@ struct nvme_dev;
 struct nvme_queue;
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
+static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode);
 
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
@@ -1019,9 +1020,11 @@ static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
 
 static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
 {
-	if (++nvmeq->cq_head == nvmeq->q_depth) {
+	if (nvmeq->cq_head == nvmeq->q_depth - 1) {
 		nvmeq->cq_head = 0;
 		nvmeq->cq_phase = !nvmeq->cq_phase;
+	} else {
+		nvmeq->cq_head++;
 	}
 }
 
@@ -1420,6 +1423,14 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 	return 0;
 }
 
+static void nvme_suspend_io_queues(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--)
+		nvme_suspend_queue(&dev->queues[i]);
+}
+
 static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 {
 	struct nvme_queue *nvmeq = &dev->queues[0];
@@ -1485,8 +1496,8 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
 	if (dev->ctrl.queue_count > qid)
 		return 0;
 
-	nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
-					  &nvmeq->cq_dma_addr, GFP_KERNEL);
+	nvmeq->cqes = dma_alloc_coherent(dev->dev, CQ_SIZE(depth),
+					 &nvmeq->cq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->cqes)
 		goto free_nvmeq;
 
@@ -1885,8 +1896,9 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
 		struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i];
 		size_t size = le32_to_cpu(desc->size) * dev->ctrl.page_size;
 
-		dma_free_coherent(dev->dev, size, dev->host_mem_desc_bufs[i],
-				le64_to_cpu(desc->addr));
+		dma_free_attrs(dev->dev, size, dev->host_mem_desc_bufs[i],
+			       le64_to_cpu(desc->addr),
+			       DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
 	}
 
 	kfree(dev->host_mem_desc_bufs);
@@ -1915,8 +1927,8 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 	if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
 		max_entries = dev->ctrl.hmmaxd;
 
-	descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs),
-			&descs_dma, GFP_KERNEL);
+	descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs),
+				   &descs_dma, GFP_KERNEL);
 	if (!descs)
 		goto out;
 
@@ -1952,8 +1964,9 @@ out_free_bufs:
 	while (--i >= 0) {
 		size_t size = le32_to_cpu(descs[i].size) * dev->ctrl.page_size;
 
-		dma_free_coherent(dev->dev, size, bufs[i],
-				le64_to_cpu(descs[i].addr));
+		dma_free_attrs(dev->dev, size, bufs[i],
+			       le64_to_cpu(descs[i].addr),
+			       DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
 	}
 
 	kfree(bufs);
@@ -2028,49 +2041,52 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
 	return ret;
 }
 
-static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues)
+/*
+ * nirqs is the number of interrupts available for write and read
+ * queues. The core already reserved an interrupt for the admin queue.
+ */
+static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs)
 {
-	unsigned int this_w_queues = write_queues;
-
-	/*
-	 * Setup read/write queue split
-	 */
-	if (irq_queues == 1) {
-		dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
-		dev->io_queues[HCTX_TYPE_READ] = 0;
-		return;
-	}
-
-	/*
-	 * If 'write_queues' is set, ensure it leaves room for at least
-	 * one read queue
-	 */
-	if (this_w_queues >= irq_queues)
-		this_w_queues = irq_queues - 1;
+	struct nvme_dev *dev = affd->priv;
+	unsigned int nr_read_queues;
 
 	/*
-	 * If 'write_queues' is set to zero, reads and writes will share
-	 * a queue set.
+	 * If there is no interupt available for queues, ensure that
+	 * the default queue is set to 1. The affinity set size is
+	 * also set to one, but the irq core ignores it for this case.
+	 *
+	 * If only one interrupt is available or 'write_queue' == 0, combine
+	 * write and read queues.
+	 *
+	 * If 'write_queues' > 0, ensure it leaves room for at least one read
+	 * queue.
 	 */
-	if (!this_w_queues) {
-		dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues;
-		dev->io_queues[HCTX_TYPE_READ] = 0;
+	if (!nrirqs) {
+		nrirqs = 1;
+		nr_read_queues = 0;
+	} else if (nrirqs == 1 || !write_queues) {
+		nr_read_queues = 0;
+	} else if (write_queues >= nrirqs) {
+		nr_read_queues = 1;
 	} else {
-		dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues;
-		dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues;
+		nr_read_queues = nrirqs - write_queues;
 	}
+
+	dev->io_queues[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;
+	affd->set_size[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;
+	dev->io_queues[HCTX_TYPE_READ] = nr_read_queues;
+	affd->set_size[HCTX_TYPE_READ] = nr_read_queues;
+	affd->nr_sets = nr_read_queues ? 2 : 1;
 }
 
 static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	int irq_sets[2];
 	struct irq_affinity affd = {
-		.pre_vectors = 1,
-		.nr_sets = ARRAY_SIZE(irq_sets),
-		.sets = irq_sets,
+		.pre_vectors	= 1,
+		.calc_sets	= nvme_calc_irq_sets,
+		.priv		= dev,
 	};
-	int result = 0;
 	unsigned int irq_queues, this_p_queues;
 
 	/*
@@ -2082,54 +2098,22 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		this_p_queues = nr_io_queues - 1;
 		irq_queues = 1;
 	} else {
-		irq_queues = nr_io_queues - this_p_queues;
+		irq_queues = nr_io_queues - this_p_queues + 1;
 	}
 	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
 
-	/*
-	 * For irq sets, we have to ask for minvec == maxvec. This passes
-	 * any reduction back to us, so we can adjust our queue counts and
-	 * IRQ vector needs.
-	 */
-	do {
-		nvme_calc_io_queues(dev, irq_queues);
-		irq_sets[0] = dev->io_queues[HCTX_TYPE_DEFAULT];
-		irq_sets[1] = dev->io_queues[HCTX_TYPE_READ];
-		if (!irq_sets[1])
-			affd.nr_sets = 1;
-
-		/*
-		 * If we got a failure and we're down to asking for just
-		 * 1 + 1 queues, just ask for a single vector. We'll share
-		 * that between the single IO queue and the admin queue.
-		 */
-		if (result >= 0 && irq_queues > 1)
-			irq_queues = irq_sets[0] + irq_sets[1] + 1;
-
-		result = pci_alloc_irq_vectors_affinity(pdev, irq_queues,
-				irq_queues,
-				PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+	/* Initialize for the single interrupt case */
+	dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
+	dev->io_queues[HCTX_TYPE_READ] = 0;
 
-		/*
-		 * Need to reduce our vec counts. If we get ENOSPC, the
-		 * platform should support mulitple vecs, we just need
-		 * to decrease our ask. If we get EINVAL, the platform
-		 * likely does not. Back down to ask for just one vector.
-		 */
-		if (result == -ENOSPC) {
-			irq_queues--;
-			if (!irq_queues)
-				return result;
-			continue;
-		} else if (result == -EINVAL) {
-			irq_queues = 1;
-			continue;
-		} else if (result <= 0)
-			return -EIO;
-		break;
-	} while (1);
+	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
+			      PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+}
 
-	return result;
+static void nvme_disable_io_queues(struct nvme_dev *dev)
+{
+	if (__nvme_disable_io_queues(dev, nvme_admin_delete_sq))
+		__nvme_disable_io_queues(dev, nvme_admin_delete_cq);
 }
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
@@ -2168,6 +2152,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	} while (1);
 	adminq->q_db = dev->dbs;
 
+ retry:
 	/* Deregister the admin queue's interrupt */
 	pci_free_irq(pdev, 0, adminq);
 
@@ -2185,25 +2170,34 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	result = max(result - 1, 1);
 	dev->max_qid = result + dev->io_queues[HCTX_TYPE_POLL];
 
-	dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
-					dev->io_queues[HCTX_TYPE_DEFAULT],
-					dev->io_queues[HCTX_TYPE_READ],
-					dev->io_queues[HCTX_TYPE_POLL]);
-
 	/*
 	 * Should investigate if there's a performance win from allocating
 	 * more queues than interrupt vectors; it might allow the submission
 	 * path to scale better, even if the receive path is limited by the
 	 * number of interrupts.
 	 */
-
 	result = queue_request_irq(adminq);
 	if (result) {
 		adminq->cq_vector = -1;
 		return result;
 	}
 	set_bit(NVMEQ_ENABLED, &adminq->flags);
-	return nvme_create_io_queues(dev);
+
+	result = nvme_create_io_queues(dev);
+	if (result || dev->online_queues < 2)
+		return result;
+
+	if (dev->online_queues - 1 < dev->max_qid) {
+		nr_io_queues = dev->online_queues - 1;
+		nvme_disable_io_queues(dev);
+		nvme_suspend_io_queues(dev);
+		goto retry;
+	}
+	dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
+					dev->io_queues[HCTX_TYPE_DEFAULT],
+					dev->io_queues[HCTX_TYPE_READ],
+					dev->io_queues[HCTX_TYPE_POLL]);
+	return 0;
 }
 
 static void nvme_del_queue_end(struct request *req, blk_status_t error)
@@ -2248,7 +2242,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	return 0;
 }
 
-static bool nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
+static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
 {
 	int nr_queues = dev->online_queues - 1, sent = 0;
 	unsigned long timeout;
@@ -2294,7 +2288,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		dev->tagset.nr_maps = 2; /* default + read */
 		if (dev->io_queues[HCTX_TYPE_POLL])
 			dev->tagset.nr_maps++;
-		dev->tagset.nr_maps = HCTX_MAX_TYPES;
 		dev->tagset.timeout = NVME_IO_TIMEOUT;
 		dev->tagset.numa_node = dev_to_node(dev->dev);
 		dev->tagset.queue_depth =
@@ -2410,7 +2403,6 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
-	int i;
 	bool dead = true;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
@@ -2437,13 +2429,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	nvme_stop_queues(&dev->ctrl);
 
 	if (!dead && dev->ctrl.queue_count > 0) {
-		if (nvme_disable_io_queues(dev, nvme_admin_delete_sq))
-			nvme_disable_io_queues(dev, nvme_admin_delete_cq);
+		nvme_disable_io_queues(dev);
 		nvme_disable_admin_queue(dev, shutdown);
 	}
-	for (i = dev->ctrl.queue_count - 1; i >= 0; i--)
-		nvme_suspend_queue(&dev->queues[i]);
-
+	nvme_suspend_io_queues(dev);
+	nvme_suspend_queue(&dev->queues[0]);
 	nvme_pci_disable(dev);
 
 	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
@@ -2527,27 +2517,18 @@ static void nvme_reset_work(struct work_struct *work)
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
 
-	/*
-	 * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
-	 * initializing procedure here.
-	 */
-	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
-		dev_warn(dev->ctrl.device,
-			"failed to mark controller CONNECTING\n");
-		goto out;
-	}
-
+	mutex_lock(&dev->shutdown_lock);
 	result = nvme_pci_enable(dev);
 	if (result)
-		goto out;
+		goto out_unlock;
 
 	result = nvme_pci_configure_admin_queue(dev);
 	if (result)
-		goto out;
+		goto out_unlock;
 
 	result = nvme_alloc_admin_tags(dev);
 	if (result)
-		goto out;
+		goto out_unlock;
 
 	/*
 	 * Limit the max command size to prevent iod->sg allocations going
@@ -2555,6 +2536,17 @@ static void nvme_reset_work(struct work_struct *work)
 	 */
 	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
 	dev->ctrl.max_segments = NVME_MAX_SEGS;
+	mutex_unlock(&dev->shutdown_lock);
+
+	/*
+	 * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
+	 * initializing procedure here.
+	 */
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
+		dev_warn(dev->ctrl.device,
+			"failed to mark controller CONNECTING\n");
+		goto out;
+	}
 
 	result = nvme_init_identify(&dev->ctrl);
 	if (result)
@@ -2619,6 +2611,8 @@ static void nvme_reset_work(struct work_struct *work)
 	nvme_start_ctrl(&dev->ctrl);
 	return;
 
+ out_unlock:
+	mutex_unlock(&dev->shutdown_lock);
  out:
 	nvme_remove_dead_ctrl(dev, result);
 }
@@ -2946,6 +2940,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_MEDIUM_PRIO_SQ },
+	{ PCI_VDEVICE(INTEL, 0xf1a6),	/* Intel 760p/Pro 7600p */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
 	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
@@ -2988,6 +2984,7 @@ static struct pci_driver nvme_driver = {
 
 static int __init nvme_init(void)
 {
+	BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2);
 	return pci_register_driver(&nvme_driver);
 }
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 0a2fd2949ad7..52abc3a6de12 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -119,6 +119,7 @@ struct nvme_rdma_ctrl {
 
 	struct nvme_ctrl	ctrl;
 	bool			use_inline_data;
+	u32			io_queues[HCTX_MAX_TYPES];
 };
 
 static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -165,8 +166,8 @@ static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue)
 static bool nvme_rdma_poll_queue(struct nvme_rdma_queue *queue)
 {
 	return nvme_rdma_queue_idx(queue) >
-		queue->ctrl->ctrl.opts->nr_io_queues +
-		queue->ctrl->ctrl.opts->nr_write_queues;
+		queue->ctrl->io_queues[HCTX_TYPE_DEFAULT] +
+		queue->ctrl->io_queues[HCTX_TYPE_READ];
 }
 
 static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue)
@@ -661,8 +662,21 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	nr_io_queues = min_t(unsigned int, nr_io_queues,
 				ibdev->num_comp_vectors);
 
-	nr_io_queues += min(opts->nr_write_queues, num_online_cpus());
-	nr_io_queues += min(opts->nr_poll_queues, num_online_cpus());
+	if (opts->nr_write_queues) {
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
+				min(opts->nr_write_queues, nr_io_queues);
+		nr_io_queues += ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] = nr_io_queues;
+	}
+
+	ctrl->io_queues[HCTX_TYPE_READ] = nr_io_queues;
+
+	if (opts->nr_poll_queues) {
+		ctrl->io_queues[HCTX_TYPE_POLL] =
+			min(opts->nr_poll_queues, num_online_cpus());
+		nr_io_queues += ctrl->io_queues[HCTX_TYPE_POLL];
+	}
 
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
@@ -1689,18 +1703,28 @@ static enum blk_eh_timer_return
 nvme_rdma_timeout(struct request *rq, bool reserved)
 {
 	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;
 
-	dev_warn(req->queue->ctrl->ctrl.device,
-		 "I/O %d QID %d timeout, reset controller\n",
-		 rq->tag, nvme_rdma_queue_idx(req->queue));
+	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
+		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	/* queue error recovery */
-	nvme_rdma_error_recovery(req->queue->ctrl);
+	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+		/*
+		 * Teardown immediately if controller times out while starting
+		 * or we are already started error recovery. all outstanding
+		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 */
+		flush_work(&ctrl->err_work);
+		nvme_rdma_teardown_io_queues(ctrl, false);
+		nvme_rdma_teardown_admin_queue(ctrl, false);
+		return BLK_EH_DONE;
+	}
 
-	/* fail with DNR on cmd timeout */
-	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	nvme_rdma_error_recovery(ctrl);
 
-	return BLK_EH_DONE;
+	return BLK_EH_RESET_TIMER;
 }
 
 static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -1779,17 +1803,15 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 	struct nvme_rdma_ctrl *ctrl = set->driver_data;
 
 	set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-	set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues;
+	set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	set->map[HCTX_TYPE_READ].nr_queues = ctrl->io_queues[HCTX_TYPE_READ];
 	if (ctrl->ctrl.opts->nr_write_queues) {
 		/* separate read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-				ctrl->ctrl.opts->nr_write_queues;
 		set->map[HCTX_TYPE_READ].queue_offset =
-				ctrl->ctrl.opts->nr_write_queues;
+				ctrl->io_queues[HCTX_TYPE_DEFAULT];
 	} else {
 		/* mixed read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-				ctrl->ctrl.opts->nr_io_queues;
 		set->map[HCTX_TYPE_READ].queue_offset = 0;
 	}
 	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT],
@@ -1799,12 +1821,12 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 
 	if (ctrl->ctrl.opts->nr_poll_queues) {
 		set->map[HCTX_TYPE_POLL].nr_queues =
-				ctrl->ctrl.opts->nr_poll_queues;
+				ctrl->io_queues[HCTX_TYPE_POLL];
 		set->map[HCTX_TYPE_POLL].queue_offset =
-				ctrl->ctrl.opts->nr_io_queues;
+				ctrl->io_queues[HCTX_TYPE_DEFAULT];
 		if (ctrl->ctrl.opts->nr_write_queues)
 			set->map[HCTX_TYPE_POLL].queue_offset +=
-				ctrl->ctrl.opts->nr_write_queues;
+				ctrl->io_queues[HCTX_TYPE_READ];
 		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
 	}
 	return 0;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index de174912445e..5f0a00425242 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1565,8 +1565,7 @@ static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove)
 {
 	nvme_tcp_stop_io_queues(ctrl);
 	if (remove) {
-		if (ctrl->ops->flags & NVME_F_FABRICS)
-			blk_cleanup_queue(ctrl->connect_q);
+		blk_cleanup_queue(ctrl->connect_q);
 		blk_mq_free_tag_set(ctrl->tagset);
 	}
 	nvme_tcp_free_io_queues(ctrl);
@@ -1587,12 +1586,10 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			goto out_free_io_queues;
 		}
 
-		if (ctrl->ops->flags & NVME_F_FABRICS) {
-			ctrl->connect_q = blk_mq_init_queue(ctrl->tagset);
-			if (IS_ERR(ctrl->connect_q)) {
-				ret = PTR_ERR(ctrl->connect_q);
-				goto out_free_tag_set;
-			}
+		ctrl->connect_q = blk_mq_init_queue(ctrl->tagset);
+		if (IS_ERR(ctrl->connect_q)) {
+			ret = PTR_ERR(ctrl->connect_q);
+			goto out_free_tag_set;
 		}
 	} else {
 		blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1606,7 +1603,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 	return 0;
 
 out_cleanup_connect_q:
-	if (new && (ctrl->ops->flags & NVME_F_FABRICS))
+	if (new)
 		blk_cleanup_queue(ctrl->connect_q);
 out_free_tag_set:
 	if (new)
@@ -1620,7 +1617,6 @@ static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove)
 {
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (remove) {
-		free_opal_dev(ctrl->opal_dev);
 		blk_cleanup_queue(ctrl->admin_q);
 		blk_mq_free_tag_set(ctrl->admin_tagset);
 	}
@@ -1952,20 +1948,23 @@ nvme_tcp_timeout(struct request *rq, bool reserved)
 	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
-	dev_dbg(ctrl->ctrl.device,
+	dev_warn(ctrl->ctrl.device,
 		"queue %d: timeout request %#x type %d\n",
-		nvme_tcp_queue_id(req->queue), rq->tag,
-		pdu->hdr.type);
+		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
 
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
-		union nvme_result res = {};
-
-		nvme_req(rq)->flags |= NVME_REQ_CANCELLED;
-		nvme_end_request(rq, cpu_to_le16(NVME_SC_ABORT_REQ), res);
+		/*
+		 * Teardown immediately if controller times out while starting
+		 * or we are already started error recovery. all outstanding
+		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 */
+		flush_work(&ctrl->err_work);
+		nvme_tcp_teardown_io_queues(&ctrl->ctrl, false);
+		nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false);
 		return BLK_EH_DONE;
 	}
 
-	/* queue error recovery */
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
 	nvme_tcp_error_recovery(&ctrl->ctrl);
 
 	return BLK_EH_RESET_TIMER;