Merge branch 'nvme-5.4' of git://git.infradead.org/nvme into for-5.4/…

…block

Pull NVMe changes from Sagi:

"The nvme updates include:
 - ana log parse fix from Anton
 - nvme quirks support for Apple devices from Ben
 - fix missing bio completion tracing for multipath stack devices from
   Hannes and Mikhail
 - IP TOS settings for nvme rdma and tcp transports from Israel
 - rq_dma_dir cleanups from Israel
 - tracing for Get LBA Status command from Minwoo
 - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
 - Some consolidation between the fabrics transports for handling the CAP
   register
 - reset race with ns scanning fix for fabrics (move fabrics commands to
   a dedicated request queue with a different lifetime from the admin
   request queue)."

* 'nvme-5.4' of git://git.infradead.org/nvme: (30 commits)
  nvme-rdma: Use rq_dma_dir macro
  nvme-fc: Use rq_dma_dir macro
  nvme-pci: Tidy up nvme_unmap_data
  nvme: make fabrics command run on a separate request queue
  nvme-pci: Support shared tags across queues for Apple 2018 controllers
  nvme-pci: Add support for Apple 2018+ models
  nvme-pci: Add support for variable IO SQ element size
  nvme-pci: Pass the queue to SQ_SIZE/CQ_SIZE macros
  nvme: trace bio completion
  nvme-multipath: fix ana log nsid lookup when nsid is not found
  nvmet-tcp: Add TOS for tcp transport
  nvme-tcp: Add TOS for tcp transport
  nvme-tcp: Use struct nvme_ctrl directly
  nvme-rdma: Add TOS for rdma transport
  nvme-fabrics: Add type of service (TOS) configuration
  nvmet-tcp: fix possible memory leak
  nvmet-tcp: fix possible NULL deref
  nvmet: trace: parse Get LBA Status command in detail
  nvme: trace: parse Get LBA Status command in detail
  nvme: trace: support for Get LBA Status opcode parsed
  ...

drivers/nvme/host/Kconfig

@@ -64,6 +64,7 @@ config NVME_TCP
 	depends on INET
 	depends on BLK_DEV_NVME
 	select NVME_FABRICS
+	select CRYPTO_CRC32C
 	help
 	  This provides support for the NVMe over Fabrics protocol using
 	  the TCP transport.  This allows you to use remote block devices

drivers/nvme/host/core.c

@@ -22,12 +22,12 @@
 #include <linux/pm_qos.h>
 #include <asm/unaligned.h>
 
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
 #include "nvme.h"
 #include "fabrics.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 #define NVME_MINORS		(1U << MINORBITS)
 
 unsigned int admin_timeout = 60;
@@ -279,6 +279,8 @@ void nvme_complete_rq(struct request *req)
 			return;
 		}
 	}
+
+	nvme_trace_bio_complete(req, status);
 	blk_mq_end_request(req, status);
 }
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
@@ -1950,7 +1952,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
  * bits', but doing so may cause the device to complete commands to the
  * admin queue ... and we don't know what memory that might be pointing at!
  */
-int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
+int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
@@ -1964,20 +1966,27 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
 	if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
 		msleep(NVME_QUIRK_DELAY_AMOUNT);
 
-	return nvme_wait_ready(ctrl, cap, false);
+	return nvme_wait_ready(ctrl, ctrl->cap, false);
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
 
-int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
+int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 {
 	/*
 	 * Default to a 4K page size, with the intention to update this
 	 * path in the future to accomodate architectures with differing
 	 * kernel and IO page sizes.
 	 */
-	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12, page_shift = 12;
+	unsigned dev_page_min, page_shift = 12;
 	int ret;
 
+	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (ret) {
+		dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
+		return ret;
+	}
+	dev_page_min = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+
 	if (page_shift < dev_page_min) {
 		dev_err(ctrl->device,
 			"Minimum device page size %u too large for host (%u)\n",
@@ -1996,7 +2005,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
-	return nvme_wait_ready(ctrl, cap, true);
+	return nvme_wait_ready(ctrl, ctrl->cap, true);
 }
 EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
@@ -2562,7 +2571,6 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 int nvme_init_identify(struct nvme_ctrl *ctrl)
 {
 	struct nvme_id_ctrl *id;
-	u64 cap;
 	int ret, page_shift;
 	u32 max_hw_sectors;
 	bool prev_apst_enabled;
@@ -2572,16 +2580,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_err(ctrl->device, "Reading VS failed (%d)\n", ret);
 		return ret;
 	}
-
-	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap);
-	if (ret) {
-		dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
-		return ret;
-	}
-	page_shift = NVME_CAP_MPSMIN(cap) + 12;
+	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+	ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
 
 	if (ctrl->vs >= NVME_VS(1, 1, 0))
-		ctrl->subsystem = NVME_CAP_NSSRC(cap);
+		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
 
 	ret = nvme_identify_ctrl(ctrl, &id);
 	if (ret) {

drivers/nvme/host/fabrics.c

@@ -150,7 +150,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
 	cmd.prop_get.offset = cpu_to_le32(off);
 
-	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res, NULL, 0, 0,
+	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0, false);
 
 	if (ret >= 0)
@@ -197,7 +197,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.attrib = 1;
 	cmd.prop_get.offset = cpu_to_le32(off);
 
-	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res, NULL, 0, 0,
+	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0, false);
 
 	if (ret >= 0)
@@ -243,7 +243,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.offset = cpu_to_le32(off);
 	cmd.prop_set.value = cpu_to_le64(val);
 
-	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, NULL, 0, 0,
+	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0, false);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
@@ -396,7 +396,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
 	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
 
-	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res,
+	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
 			data, sizeof(*data), 0, NVME_QID_ANY, 1,
 			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, false);
 	if (ret) {
@@ -611,6 +611,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_DATA_DIGEST,		"data_digest"		},
 	{ NVMF_OPT_NR_WRITE_QUEUES,	"nr_write_queues=%d"	},
 	{ NVMF_OPT_NR_POLL_QUEUES,	"nr_poll_queues=%d"	},
+	{ NVMF_OPT_TOS,			"tos=%d"		},
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -632,6 +633,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	opts->duplicate_connect = false;
 	opts->hdr_digest = false;
 	opts->data_digest = false;
+	opts->tos = -1; /* < 0 == use transport default */
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -856,6 +858,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			}
 			opts->nr_poll_queues = token;
 			break;
+		case NVMF_OPT_TOS:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token < 0) {
+				pr_err("Invalid type of service %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token > 255) {
+				pr_warn("Clamping type of service to 255\n");
+				token = 255;
+			}
+			opts->tos = token;
+			break;
 		default:
 			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
 				p);

drivers/nvme/host/fabrics.h

@@ -55,6 +55,7 @@ enum {
 	NVMF_OPT_DATA_DIGEST	= 1 << 16,
 	NVMF_OPT_NR_WRITE_QUEUES = 1 << 17,
 	NVMF_OPT_NR_POLL_QUEUES = 1 << 18,
+	NVMF_OPT_TOS		= 1 << 19,
 };
 
 /**
@@ -87,6 +88,7 @@ enum {
  * @data_digest: generate/verify data digest (TCP)
  * @nr_write_queues: number of queues for write I/O
  * @nr_poll_queues: number of queues for polling I/O
+ * @tos: type of service
  */
 struct nvmf_ctrl_options {
 	unsigned		mask;
@@ -108,6 +110,7 @@ struct nvmf_ctrl_options {
 	bool			data_digest;
 	unsigned int		nr_write_queues;
 	unsigned int		nr_poll_queues;
+	int			tos;
 };
 
 /*

drivers/nvme/host/fc.c

@@ -2006,6 +2006,7 @@ nvme_fc_ctrl_free(struct kref *ref)
 
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 
 	kfree(ctrl->queues);
@@ -2107,7 +2108,6 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 		struct nvme_fc_fcp_op *op)
 {
 	struct nvmefc_fcp_req *freq = &op->fcp_req;
-	enum dma_data_direction dir;
 	int ret;
 
 	freq->sg_cnt = 0;
@@ -2124,9 +2124,8 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 
 	op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl);
 	WARN_ON(op->nents > blk_rq_nr_phys_segments(rq));
-	dir = (rq_data_dir(rq) == WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
-				op->nents, dir);
+				op->nents, rq_dma_dir(rq));
 	if (unlikely(freq->sg_cnt <= 0)) {
 		sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
 		freq->sg_cnt = 0;
@@ -2149,8 +2148,7 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 		return;
 
 	fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents,
-				((rq_data_dir(rq) == WRITE) ?
-					DMA_TO_DEVICE : DMA_FROM_DEVICE));
+			rq_dma_dir(rq));
 
 	nvme_cleanup_cmd(rq);
 
@@ -2633,8 +2631,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_delete_hw_queue;
 
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-
 	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
 	if (ret)
 		goto out_disconnect_admin_queue;
@@ -2648,23 +2644,15 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	 * prior connection values
 	 */
 
-	ret = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
-	if (ret) {
-		dev_err(ctrl->ctrl.device,
-			"prop_get NVME_REG_CAP failed\n");
-		goto out_disconnect_admin_queue;
-	}
-
-	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
-
-	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+	ret = nvme_enable_ctrl(&ctrl->ctrl);
 	if (ret)
 		goto out_disconnect_admin_queue;
 
 	ctrl->ctrl.max_hw_sectors =
 		(ctrl->lport->ops->max_sgl_segments - 1) << (PAGE_SHIFT - 9);
 
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+
 	ret = nvme_init_identify(&ctrl->ctrl);
 	if (ret)
 		goto out_disconnect_admin_queue;
@@ -3111,10 +3099,16 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		goto out_free_queues;
 	ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set;
 
+	ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.fabrics_q)) {
+		ret = PTR_ERR(ctrl->ctrl.fabrics_q);
+		goto out_free_admin_tag_set;
+	}
+
 	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
 	if (IS_ERR(ctrl->ctrl.admin_q)) {
 		ret = PTR_ERR(ctrl->ctrl.admin_q);
-		goto out_free_admin_tag_set;
+		goto out_cleanup_fabrics_q;
 	}
 
 	/*
@@ -3186,6 +3180,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 out_cleanup_admin_q:
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_cleanup_fabrics_q:
+	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
 out_free_admin_tag_set:
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 out_free_queues:

drivers/nvme/host/multipath.c

@@ -444,14 +444,16 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+		unsigned nsid = le32_to_cpu(desc->nsids[n]);
+
+		if (ns->head->ns_id < nsid)
 			continue;
-		nvme_update_ns_ana_state(desc, ns);
+		if (ns->head->ns_id == nsid)
+			nvme_update_ns_ana_state(desc, ns);
 		if (++n == nr_nsids)
 			break;
 	}
 	up_write(&ctrl->namespaces_rwsem);
-	WARN_ON_ONCE(n < nr_nsids);
 	return 0;
 }