Merge tag 'nvme-6.5-2023-06-16' of git://git.infradead.org/nvme into for-6.5/block

Pull NVMe updates from Keith:

"nvme updates for Linux 6.5

 - Various cleanups all around (Irvin, Chaitanya, Christophe)
 - Better struct packing (Christophe JAILLET)
 - Reduce controller error logs for optional commands (Keith)
 - Support for >=64KiB block sizes (Daniel Gomez)
 - Fabrics fixes and code organization (Max, Chaitanya, Daniel Wagner)"

* tag 'nvme-6.5-2023-06-16' of git://git.infradead.org/nvme: (27 commits)
  nvme: forward port sysfs delete fix
  nvme: skip optional id ctrl csi if it failed
  nvme-core: use nvme_ns_head_multipath instead of ns->head->disk
  nvmet-fcloop: Do not wait on completion when unregister fails
  nvme-fabrics: open code __nvmf_host_find()
  nvme-fabrics: error out to unlock the mutex
  nvme: Increase block size variable size to 32-bit
  nvme-fcloop: no need to return from void function
  nvmet-auth: remove unnecessary break after goto
  nvmet-auth: remove some dead code
  nvme-core: remove redundant check from nvme_init_ns_head
  nvme: move sysfs code to a dedicated sysfs.c file
  nvme-fabrics: prevent overriding of existing host
  nvme-fabrics: check hostid using uuid_equal
  nvme-fabrics: unify common code in admin and io queue connect
  nvmet: reorder fields in 'struct nvmefc_fcp_req'
  nvmet: reorder fields in 'struct nvme_dhchap_queue_context'
  nvmet: reorder fields in 'struct nvmf_ctrl_options'
  nvme: reorder fields in 'struct nvme_ctrl'
  nvmet: reorder fields in 'struct nvmet_sq'
  ...

drivers/nvme/host/Makefile

@@ -10,7 +10,7 @@ obj-$(CONFIG_NVME_FC)			+= nvme-fc.o
 obj-$(CONFIG_NVME_TCP)			+= nvme-tcp.o
 obj-$(CONFIG_NVME_APPLE)		+= nvme-apple.o
 
-nvme-core-y				+= core.o ioctl.o
+nvme-core-y				+= core.o ioctl.o sysfs.o
 nvme-core-$(CONFIG_NVME_VERBOSE_ERRORS)	+= constants.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o

drivers/nvme/host/auth.c

@@ -30,18 +30,18 @@ struct nvme_dhchap_queue_context {
 	u32 s2;
 	u16 transaction;
 	u8 status;
+	u8 dhgroup_id;
 	u8 hash_id;
 	size_t hash_len;
-	u8 dhgroup_id;
 	u8 c1[64];
 	u8 c2[64];
 	u8 response[64];
 	u8 *host_response;
 	u8 *ctrl_key;
-	int ctrl_key_len;
 	u8 *host_key;
-	int host_key_len;
 	u8 *sess_key;
+	int ctrl_key_len;
+	int host_key_len;
 	int sess_key_len;
 };
 

drivers/nvme/host/fabrics.c

@@ -21,35 +21,60 @@ static DEFINE_MUTEX(nvmf_hosts_mutex);
 
 static struct nvmf_host *nvmf_default_host;
 
-static struct nvmf_host *__nvmf_host_find(const char *hostnqn)
+static struct nvmf_host *nvmf_host_alloc(const char *hostnqn, uuid_t *id)
 {
 	struct nvmf_host *host;
 
-	list_for_each_entry(host, &nvmf_hosts, list) {
-		if (!strcmp(host->nqn, hostnqn))
-			return host;
-	}
-
+	host = kmalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
 		return NULL;
+
+	kref_init(&host->ref);
+	uuid_copy(&host->id, id);
+	strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
+
+	return host;
 }
 
-static struct nvmf_host *nvmf_host_add(const char *hostnqn)
+static struct nvmf_host *nvmf_host_add(const char *hostnqn, uuid_t *id)
 {
 	struct nvmf_host *host;
 
 	mutex_lock(&nvmf_hosts_mutex);
-	host = __nvmf_host_find(hostnqn);
-	if (host) {
+
+	/*
+	 * We have defined a host as how it is perceived by the target.
+	 * Therefore, we don't allow different Host NQNs with the same Host ID.
+	 * Similarly, we do not allow the usage of the same Host NQN with
+	 * different Host IDs. This'll maintain unambiguous host identification.
+	 */
+	list_for_each_entry(host, &nvmf_hosts, list) {
+		bool same_hostnqn = !strcmp(host->nqn, hostnqn);
+		bool same_hostid = uuid_equal(&host->id, id);
+
+		if (same_hostnqn && same_hostid) {
 			kref_get(&host->ref);
 			goto out_unlock;
 		}
-
-	host = kmalloc(sizeof(*host), GFP_KERNEL);
-	if (!host)
+		if (same_hostnqn) {
+			pr_err("found same hostnqn %s but different hostid %pUb\n",
+			       hostnqn, id);
+			host = ERR_PTR(-EINVAL);
+			goto out_unlock;
+		}
+		if (same_hostid) {
+			pr_err("found same hostid %pUb but different hostnqn %s\n",
+			       id, hostnqn);
+			host = ERR_PTR(-EINVAL);
 			goto out_unlock;
+		}
+	}
 
-	kref_init(&host->ref);
-	strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
+	host = nvmf_host_alloc(hostnqn, id);
+	if (!host) {
+		host = ERR_PTR(-ENOMEM);
+		goto out_unlock;
+	}
 
 	list_add_tail(&host->list, &nvmf_hosts);
 out_unlock:
@@ -60,16 +85,17 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn)
 static struct nvmf_host *nvmf_host_default(void)
 {
 	struct nvmf_host *host;
+	char nqn[NVMF_NQN_SIZE];
+	uuid_t id;
 
-	host = kmalloc(sizeof(*host), GFP_KERNEL);
+	uuid_gen(&id);
+	snprintf(nqn, NVMF_NQN_SIZE,
+		"nqn.2014-08.org.nvmexpress:uuid:%pUb", &id);
+
+	host = nvmf_host_alloc(nqn, &id);
 	if (!host)
 		return NULL;
 
-	kref_init(&host->ref);
-	uuid_gen(&host->id);
-	snprintf(host->nqn, NVMF_NQN_SIZE,
-		"nqn.2014-08.org.nvmexpress:uuid:%pUb", &host->id);
-
 	mutex_lock(&nvmf_hosts_mutex);
 	list_add_tail(&host->list, &nvmf_hosts);
 	mutex_unlock(&nvmf_hosts_mutex);
@@ -349,6 +375,45 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 	}
 }
 
+static struct nvmf_connect_data *nvmf_connect_data_prep(struct nvme_ctrl *ctrl,
+		u16 cntlid)
+{
+	struct nvmf_connect_data *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	uuid_copy(&data->hostid, &ctrl->opts->host->id);
+	data->cntlid = cpu_to_le16(cntlid);
+	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+
+	return data;
+}
+
+static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid,
+		struct nvme_command *cmd)
+{
+	cmd->connect.opcode = nvme_fabrics_command;
+	cmd->connect.fctype = nvme_fabrics_type_connect;
+	cmd->connect.qid = cpu_to_le16(qid);
+
+	if (qid) {
+		cmd->connect.sqsize = cpu_to_le16(ctrl->sqsize);
+	} else {
+		cmd->connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1);
+
+		/*
+		 * set keep-alive timeout in seconds granularity (ms * 1000)
+		 */
+		cmd->connect.kato = cpu_to_le32(ctrl->kato * 1000);
+	}
+
+	if (ctrl->opts->disable_sqflow)
+		cmd->connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;
+}
+
 /**
  * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect"
  *				API function.
@@ -377,28 +442,12 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 	int ret;
 	u32 result;
 
-	cmd.connect.opcode = nvme_fabrics_command;
-	cmd.connect.fctype = nvme_fabrics_type_connect;
-	cmd.connect.qid = 0;
-	cmd.connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1);
-
-	/*
-	 * Set keep-alive timeout in seconds granularity (ms * 1000)
-	 */
-	cmd.connect.kato = cpu_to_le32(ctrl->kato * 1000);
-
-	if (ctrl->opts->disable_sqflow)
-		cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;
+	nvmf_connect_cmd_prep(ctrl, 0, &cmd);
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = nvmf_connect_data_prep(ctrl, 0xffff);
 	if (!data)
 		return -ENOMEM;
 
-	uuid_copy(&data->hostid, &ctrl->opts->host->id);
-	data->cntlid = cpu_to_le16(0xffff);
-	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->fabrics_q, &cmd, &res,
 			data, sizeof(*data), NVME_QID_ANY, 1,
 			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
@@ -468,23 +517,12 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 	int ret;
 	u32 result;
 
-	cmd.connect.opcode = nvme_fabrics_command;
-	cmd.connect.fctype = nvme_fabrics_type_connect;
-	cmd.connect.qid = cpu_to_le16(qid);
-	cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);
-
-	if (ctrl->opts->disable_sqflow)
-		cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;
+	nvmf_connect_cmd_prep(ctrl, qid, &cmd);
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = nvmf_connect_data_prep(ctrl, ctrl->cntlid);
 	if (!data)
 		return -ENOMEM;
 
-	uuid_copy(&data->hostid, &ctrl->opts->host->id);
-	data->cntlid = cpu_to_le16(ctrl->cntlid);
-	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->connect_q, &cmd, &res,
 			data, sizeof(*data), qid, 1,
 			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
@@ -621,6 +659,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	size_t nqnlen  = 0;
 	int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
 	uuid_t hostid;
+	char hostnqn[NVMF_NQN_SIZE];
 
 	/* Set defaults */
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
@@ -637,7 +676,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	if (!options)
 		return -ENOMEM;
 
-	uuid_gen(&hostid);
+	/* use default host if not given by user space */
+	uuid_copy(&hostid, &nvmf_default_host->id);
+	strscpy(hostnqn, nvmf_default_host->nqn, NVMF_NQN_SIZE);
 
 	while ((p = strsep(&o, ",\n")) != NULL) {
 		if (!*p)
@@ -783,12 +824,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -EINVAL;
 				goto out;
 			}
-			opts->host = nvmf_host_add(p);
+			strscpy(hostnqn, p, NVMF_NQN_SIZE);
 			kfree(p);
-			if (!opts->host) {
-				ret = -ENOMEM;
-				goto out;
-			}
 			break;
 		case NVMF_OPT_RECONNECT_DELAY:
 			if (match_int(args, &token)) {
@@ -945,18 +982,94 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				opts->fast_io_fail_tmo, ctrl_loss_tmo);
 	}
 
-	if (!opts->host) {
-		kref_get(&nvmf_default_host->ref);
-		opts->host = nvmf_default_host;
+	opts->host = nvmf_host_add(hostnqn, &hostid);
+	if (IS_ERR(opts->host)) {
+		ret = PTR_ERR(opts->host);
+		opts->host = NULL;
+		goto out;
 	}
 
-	uuid_copy(&opts->host->id, &hostid);
-
 out:
 	kfree(options);
 	return ret;
 }
 
+void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues,
+			u32 io_queues[HCTX_MAX_TYPES])
+{
+	if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) {
+		/*
+		 * separate read/write queues
+		 * hand out dedicated default queues only after we have
+		 * sufficient read queues.
+		 */
+		io_queues[HCTX_TYPE_READ] = opts->nr_io_queues;
+		nr_io_queues -= io_queues[HCTX_TYPE_READ];
+		io_queues[HCTX_TYPE_DEFAULT] =
+			min(opts->nr_write_queues, nr_io_queues);
+		nr_io_queues -= io_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		/*
+		 * shared read/write queues
+		 * either no write queues were requested, or we don't have
+		 * sufficient queue count to have dedicated default queues.
+		 */
+		io_queues[HCTX_TYPE_DEFAULT] =
+			min(opts->nr_io_queues, nr_io_queues);
+		nr_io_queues -= io_queues[HCTX_TYPE_DEFAULT];
+	}
+
+	if (opts->nr_poll_queues && nr_io_queues) {
+		/* map dedicated poll queues only if we have queues left */
+		io_queues[HCTX_TYPE_POLL] =
+			min(opts->nr_poll_queues, nr_io_queues);
+	}
+}
+EXPORT_SYMBOL_GPL(nvmf_set_io_queues);
+
+void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl,
+		     u32 io_queues[HCTX_MAX_TYPES])
+{
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+
+	if (opts->nr_write_queues && io_queues[HCTX_TYPE_READ]) {
+		/* separate read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			io_queues[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			io_queues[HCTX_TYPE_READ];
+		set->map[HCTX_TYPE_READ].queue_offset =
+			io_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		/* shared read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			io_queues[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			io_queues[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_READ].queue_offset = 0;
+	}
+
+	blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
+	blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
+	if (opts->nr_poll_queues && io_queues[HCTX_TYPE_POLL]) {
+		/* map dedicated poll queues only if we have queues left */
+		set->map[HCTX_TYPE_POLL].nr_queues = io_queues[HCTX_TYPE_POLL];
+		set->map[HCTX_TYPE_POLL].queue_offset =
+			io_queues[HCTX_TYPE_DEFAULT] +
+			io_queues[HCTX_TYPE_READ];
+		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
+	}
+
+	dev_info(ctrl->device,
+		"mapped %d/%d/%d default/read/poll queues.\n",
+		io_queues[HCTX_TYPE_DEFAULT],
+		io_queues[HCTX_TYPE_READ],
+		io_queues[HCTX_TYPE_POLL]);
+}
+EXPORT_SYMBOL_GPL(nvmf_map_queues);
+
 static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts,
 		unsigned int required_opts)
 {

drivers/nvme/host/fabrics.h

@@ -77,6 +77,9 @@ enum {
  *			      with the parsing opts enum.
  * @mask:	Used by the fabrics library to parse through sysfs options
  *		on adding a NVMe controller.
+ * @max_reconnects: maximum number of allowed reconnect attempts before removing
+ *		the controller, (-1) means reconnect forever, zero means remove
+ *		immediately;
  * @transport:	Holds the fabric transport "technology name" (for a lack of
  *		better description) that will be used by an NVMe controller
  *		being added.
@@ -96,9 +99,6 @@ enum {
  * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN.
  * @kato:	Keep-alive timeout.
  * @host:	Virtual NVMe host, contains the NQN and Host ID.
- * @max_reconnects: maximum number of allowed reconnect attempts before removing
- *              the controller, (-1) means reconnect forever, zero means remove
- *              immediately;
  * @dhchap_secret: DH-HMAC-CHAP secret
  * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional
  *              authentication
@@ -112,6 +112,7 @@ enum {
  */
 struct nvmf_ctrl_options {
 	unsigned		mask;
+	int			max_reconnects;
 	char			*transport;
 	char			*subsysnqn;
 	char			*traddr;
@@ -125,7 +126,6 @@ struct nvmf_ctrl_options {
 	bool			duplicate_connect;
 	unsigned int		kato;
 	struct nvmf_host	*host;
-	int			max_reconnects;
 	char			*dhchap_secret;
 	char			*dhchap_ctrl_secret;
 	bool			disable_sqflow;
@@ -181,7 +181,7 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 	    ctrl->state == NVME_CTRL_DEAD ||
 	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
-	    memcmp(&opts->host->id, &ctrl->opts->host->id, sizeof(uuid_t)))
+	    !uuid_equal(&opts->host->id, &ctrl->opts->host->id))
 		return false;
 
 	return true;
@@ -203,6 +203,13 @@ static inline void nvmf_complete_timed_out_request(struct request *rq)
 	}
 }
 
+static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts)
+{
+	return min(opts->nr_io_queues, num_online_cpus()) +
+		min(opts->nr_write_queues, num_online_cpus()) +
+		min(opts->nr_poll_queues, num_online_cpus());
+}
+
 int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
@@ -215,5 +222,9 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
 bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
 		struct nvmf_ctrl_options *opts);
+void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues,
+			u32 io_queues[HCTX_MAX_TYPES]);
+void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl,
+		     u32 io_queues[HCTX_MAX_TYPES]);
 
 #endif /* _NVME_FABRICS_H */

drivers/nvme/host/nvme.h

@@ -242,12 +242,13 @@ enum nvme_ctrl_flags {
 	NVME_CTRL_ADMIN_Q_STOPPED	= 1,
 	NVME_CTRL_STARTED_ONCE		= 2,
 	NVME_CTRL_STOPPED		= 3,
+	NVME_CTRL_SKIP_ID_CNS_CS	= 4,
 };
 
 struct nvme_ctrl {
 	bool comp_seen;
-	enum nvme_ctrl_state state;
 	bool identified;
+	enum nvme_ctrl_state state;
 	spinlock_t lock;
 	struct mutex scan_lock;
 	const struct nvme_ctrl_ops *ops;
@@ -279,8 +280,8 @@ struct nvme_ctrl {
 	char name[12];
 	u16 cntlid;
 
-	u32 ctrl_config;
 	u16 mtfa;
+	u32 ctrl_config;
 	u32 queue_count;
 
 	u64 cap;
@@ -353,10 +354,10 @@ struct nvme_ctrl {
 	bool apst_enabled;
 
 	/* PCIe only: */
+	u16 hmmaxd;
 	u32 hmpre;
 	u32 hmmin;
 	u32 hmminds;
-	u16 hmmaxd;
 
 	/* Fabrics only */
 	u32 ioccsz;
@@ -860,7 +861,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[];
 extern const struct pr_ops nvme_pr_ops;
 extern const struct block_device_operations nvme_ns_head_ops;
 extern const struct attribute_group nvme_dev_attrs_group;
+extern const struct attribute_group *nvme_subsys_attrs_groups[];
+extern const struct attribute_group *nvme_dev_attr_groups[];
+extern const struct block_device_operations nvme_bdev_ops;
 
+void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 #ifdef CONFIG_NVME_MULTIPATH
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)

drivers/nvme/host/pci.c

@@ -420,10 +420,9 @@ static int nvme_pci_init_request(struct blk_mq_tag_set *set,
 		struct request *req, unsigned int hctx_idx,
 		unsigned int numa_node)
 {
-	struct nvme_dev *dev = to_nvme_dev(set->driver_data);
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
-	nvme_req(req)->ctrl = &dev->ctrl;
+	nvme_req(req)->ctrl = set->driver_data;
 	nvme_req(req)->cmd = &iod->cmd;
 	return 0;
 }

drivers/nvme/host/rdma.c

@@ -501,7 +501,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	}
 	ibdev = queue->device->dev;
 
-	/* +1 for ib_stop_cq */
+	/* +1 for ib_drain_qp */
 	queue->cq_size = cq_factor * queue->queue_size + 1;
 
 	ret = nvme_rdma_create_cq(ibdev, queue);
@@ -713,18 +713,10 @@ static int nvme_rdma_start_io_queues(struct nvme_rdma_ctrl *ctrl,
 static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 {
 	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
-	struct ib_device *ibdev = ctrl->device->dev;
-	unsigned int nr_io_queues, nr_default_queues;
-	unsigned int nr_read_queues, nr_poll_queues;
+	unsigned int nr_io_queues;
 	int i, ret;
 
-	nr_read_queues = min_t(unsigned int, ibdev->num_comp_vectors,
-				min(opts->nr_io_queues, num_online_cpus()));
-	nr_default_queues =  min_t(unsigned int, ibdev->num_comp_vectors,
-				min(opts->nr_write_queues, num_online_cpus()));
-	nr_poll_queues = min(opts->nr_poll_queues, num_online_cpus());
-	nr_io_queues = nr_read_queues + nr_default_queues + nr_poll_queues;
-
+	nr_io_queues = nvmf_nr_io_queues(opts);
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
 		return ret;
@@ -739,34 +731,7 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	dev_info(ctrl->ctrl.device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
-	if (opts->nr_write_queues && nr_read_queues < nr_io_queues) {
-		/*
-		 * separate read/write queues
-		 * hand out dedicated default queues only after we have
-		 * sufficient read queues.
-		 */
-		ctrl->io_queues[HCTX_TYPE_READ] = nr_read_queues;
-		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ];
-		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
-			min(nr_default_queues, nr_io_queues);
-		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	} else {
-		/*
-		 * shared read/write queues
-		 * either no write queues were requested, or we don't have
-		 * sufficient queue count to have dedicated default queues.
-		 */
-		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
-			min(nr_read_queues, nr_io_queues);
-		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	}
-
-	if (opts->nr_poll_queues && nr_io_queues) {
-		/* map dedicated poll queues only if we have queues left */
-		ctrl->io_queues[HCTX_TYPE_POLL] =
-			min(nr_poll_queues, nr_io_queues);
-	}
-
+	nvmf_set_io_queues(opts, nr_io_queues, ctrl->io_queues);
 	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
 		ret = nvme_rdma_alloc_queue(ctrl, i,
 				ctrl->ctrl.sqsize + 1);
@@ -2138,44 +2103,8 @@ static void nvme_rdma_complete_rq(struct request *rq)
 static void nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(set->driver_data);
-	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 
-	if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) {
-		/* separate read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-		set->map[HCTX_TYPE_READ].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_READ];
-		set->map[HCTX_TYPE_READ].queue_offset =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	} else {
-		/* shared read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-		set->map[HCTX_TYPE_READ].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		set->map[HCTX_TYPE_READ].queue_offset = 0;
-	}
-	blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
-	blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
-
-	if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) {
-		/* map dedicated poll queues only if we have queues left */
-		set->map[HCTX_TYPE_POLL].nr_queues =
-				ctrl->io_queues[HCTX_TYPE_POLL];
-		set->map[HCTX_TYPE_POLL].queue_offset =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT] +
-			ctrl->io_queues[HCTX_TYPE_READ];
-		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
-	}
-
-	dev_info(ctrl->ctrl.device,
-		"mapped %d/%d/%d default/read/poll queues.\n",
-		ctrl->io_queues[HCTX_TYPE_DEFAULT],
-		ctrl->io_queues[HCTX_TYPE_READ],
-		ctrl->io_queues[HCTX_TYPE_POLL]);
+	nvmf_map_queues(set, &ctrl->ctrl, ctrl->io_queues);
 }
 
 static const struct blk_mq_ops nvme_rdma_mq_ops = {

drivers/nvme/host/tcp.c

@@ -1802,58 +1802,12 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	return ret;
 }
 
-static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl)
-{
-	unsigned int nr_io_queues;
-
-	nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus());
-	nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus());
-	nr_io_queues += min(ctrl->opts->nr_poll_queues, num_online_cpus());
-
-	return nr_io_queues;
-}
-
-static void nvme_tcp_set_io_queues(struct nvme_ctrl *nctrl,
-		unsigned int nr_io_queues)
-{
-	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
-	struct nvmf_ctrl_options *opts = nctrl->opts;
-
-	if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) {
-		/*
-		 * separate read/write queues
-		 * hand out dedicated default queues only after we have
-		 * sufficient read queues.
-		 */
-		ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues;
-		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ];
-		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
-			min(opts->nr_write_queues, nr_io_queues);
-		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	} else {
-		/*
-		 * shared read/write queues
-		 * either no write queues were requested, or we don't have
-		 * sufficient queue count to have dedicated default queues.
-		 */
-		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
-			min(opts->nr_io_queues, nr_io_queues);
-		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	}
-
-	if (opts->nr_poll_queues && nr_io_queues) {
-		/* map dedicated poll queues only if we have queues left */
-		ctrl->io_queues[HCTX_TYPE_POLL] =
-			min(opts->nr_poll_queues, nr_io_queues);
-	}
-}
-
 static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 {
 	unsigned int nr_io_queues;
 	int ret;
 
-	nr_io_queues = nvme_tcp_nr_io_queues(ctrl);
+	nr_io_queues = nvmf_nr_io_queues(ctrl->opts);
 	ret = nvme_set_queue_count(ctrl, &nr_io_queues);
 	if (ret)
 		return ret;
@@ -1868,8 +1822,8 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	dev_info(ctrl->device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
-	nvme_tcp_set_io_queues(ctrl, nr_io_queues);
-
+	nvmf_set_io_queues(ctrl->opts, nr_io_queues,
+			   to_tcp_ctrl(ctrl)->io_queues);
 	return __nvme_tcp_alloc_io_queues(ctrl);
 }
 
@@ -2449,44 +2403,8 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 static void nvme_tcp_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data);
-	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
-
-	if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) {
-		/* separate read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-		set->map[HCTX_TYPE_READ].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_READ];
-		set->map[HCTX_TYPE_READ].queue_offset =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	} else {
-		/* shared read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-		set->map[HCTX_TYPE_READ].nr_queues =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		set->map[HCTX_TYPE_READ].queue_offset = 0;
-	}
-	blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
-	blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
-
-	if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) {
-		/* map dedicated poll queues only if we have queues left */
-		set->map[HCTX_TYPE_POLL].nr_queues =
-				ctrl->io_queues[HCTX_TYPE_POLL];
-		set->map[HCTX_TYPE_POLL].queue_offset =
-			ctrl->io_queues[HCTX_TYPE_DEFAULT] +
-			ctrl->io_queues[HCTX_TYPE_READ];
-		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
-	}
 
-	dev_info(ctrl->ctrl.device,
-		"mapped %d/%d/%d default/read/poll queues.\n",
-		ctrl->io_queues[HCTX_TYPE_DEFAULT],
-		ctrl->io_queues[HCTX_TYPE_READ],
-		ctrl->io_queues[HCTX_TYPE_POLL]);
+	nvmf_map_queues(set, &ctrl->ctrl, ctrl->io_queues);
 }
 
 static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)

drivers/nvme/target/fabrics-cmd-auth.c

@@ -295,13 +295,11 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
 			status = 0;
 		}
 		goto done_kfree;
-		break;
 	case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2:
 		req->sq->authenticated = true;
 		pr_debug("%s: ctrl %d qid %d ctrl authenticated\n",
 			 __func__, ctrl->cntlid, req->sq->qid);
 		goto done_kfree;
-		break;
 	case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2:
 		status = nvmet_auth_failure2(d);
 		if (status) {
@@ -312,7 +310,6 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
 			status = 0;
 		}
 		goto done_kfree;
-		break;
 	default:
 		req->sq->dhchap_status =
 			NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE;
@@ -320,7 +317,6 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
 			NVME_AUTH_DHCHAP_MESSAGE_FAILURE2;
 		req->sq->authenticated = false;
 		goto done_kfree;
-		break;
 	}
 done_failure1:
 	req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE;
@@ -483,15 +479,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
 			status = NVME_SC_INTERNAL;
 			break;
 		}
-		if (status) {
-			req->sq->dhchap_status = status;
-			nvmet_auth_failure1(req, d, al);
-			pr_warn("ctrl %d qid %d: challenge status (%x)\n",
-				ctrl->cntlid, req->sq->qid,
-				req->sq->dhchap_status);
-			status = 0;
-			break;
-		}
 		req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_REPLY;
 		break;
 	case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1:

drivers/nvme/target/fcloop.c

@@ -645,8 +645,6 @@ fcloop_fcp_recv_work(struct work_struct *work)
 	}
 	if (ret)
 		fcloop_call_host_done(fcpreq, tfcp_req, ret);
-
-	return;
 }
 
 static void
@@ -1168,6 +1166,7 @@ __wait_localport_unreg(struct fcloop_lport *lport)
 
 	ret = nvme_fc_unregister_localport(lport->localport);
 
+	if (!ret)
 		wait_for_completion(&lport->unreg_done);
 
 	kfree(lport);

drivers/nvme/target/nvmet.h

@@ -109,8 +109,8 @@ struct nvmet_sq {
 	u32			sqhd;
 	bool			sqhd_disabled;
 #ifdef CONFIG_NVME_TARGET_AUTH
-	struct delayed_work	auth_expired_work;
 	bool			authenticated;
+	struct delayed_work	auth_expired_work;
 	u16			dhchap_tid;
 	u16			dhchap_status;
 	int			dhchap_step;

include/linux/nvme-fc-driver.h

@@ -185,7 +185,6 @@ enum nvmefc_fcp_datadir {
  * @first_sgl: memory for 1st scatter/gather list segment for payload data
  * @sg_cnt:    number of elements in the scatter/gather list
  * @io_dir:    direction of the FCP request (see NVMEFC_FCP_xxx)
- * @sqid:      The nvme SQID the command is being issued on
  * @done:      The callback routine the LLDD is to invoke upon completion of
  *             the FCP operation. req argument is the pointer to the original
  *             FCP IO operation.
@@ -194,12 +193,13 @@ enum nvmefc_fcp_datadir {
  *             while processing the operation. The length of the buffer
  *             corresponds to the fcprqst_priv_sz value specified in the
  *             nvme_fc_port_template supplied by the LLDD.
+ * @sqid:      The nvme SQID the command is being issued on
  *
  * Values set by the LLDD indicating completion status of the FCP operation.
  * Must be set prior to calling the done() callback.
+ * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @transferred_length: amount of payload data, in bytes, that were
  *             transferred. Should equal payload_length on success.
- * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @status:    Completion status of the FCP operation. must be 0 upon success,
  *             negative errno value upon failure (ex: -EIO). Note: this is
  *             NOT a reflection of the NVME CQE completion status. Only the
@@ -219,14 +219,14 @@ struct nvmefc_fcp_req {
 	int			sg_cnt;
 	enum nvmefc_fcp_datadir	io_dir;
 
-	__le16			sqid;
-
 	void (*done)(struct nvmefc_fcp_req *req);
 
 	void			*private;
 
-	u32			transferred_length;
+	__le16			sqid;
+
 	u16			rcv_rsplen;
+	u32			transferred_length;
 	u32			status;
 } __aligned(sizeof(u64));	/* alignment for other things alloc'd with */