Merge branch 'nvme-5.0' of git://git.infradead.org/nvme into for-linus

Pull NVMe fixes from Christoph.

* 'nvme-5.0' of git://git.infradead.org/nvme:
  nvme: don't initlialize ctrl->cntlid twice
  nvme: introduce NVME_QUIRK_IGNORE_DEV_SUBNQN
  nvme: pad fake subsys NQN vid and ssvid with zeros
  nvme-multipath: zero out ANA log buffer
  nvme-fabrics: unset write/poll queues for discovery controllers
  nvme-tcp: don't ask if controller is fabrics
  nvme-tcp: remove dead code
  nvme-pci: fix out of bounds access in nvme_cqe_pending
  nvme-pci: rerun irq setup on IO queue init errors
  nvme-pci: use the same attributes when freeing host_mem_desc_bufs.
  nvme-pci: fix the wrong setting of nr_maps

6 files changed, 72 insertions, 39 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 08f2c92602f4..150e49723c15 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2173,18 +2173,20 @@ 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 +2502,6 @@ 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
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..df4b3a6db51b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -570,6 +570,7 @@ 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 +578,6 @@ 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..ab961bdeea89 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),
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5a0bf6a24d50..fc9d17c317b8 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];
@@ -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);
@@ -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);
@@ -2132,6 +2145,12 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 	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)
 {
 	struct nvme_queue *adminq = &dev->queues[0];
@@ -2168,6 +2187,7 @@ 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 +2205,34 @@ 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 +2277,7 @@ 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 +2323,6 @@ 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 +2438,6 @@ 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 +2464,11 @@ 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);
@@ -2946,6 +2971,8 @@ 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 */
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index de174912445e..265a0543b381 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);
 	}