7 files changed, 231 insertions, 29 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 72a7e41f3018..9d6f75cfa77c 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -6,6 +6,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/module.h>
 #include <linux/rculist.h>
+#include <linux/part_stat.h>
 
 #include <generated/utsrelease.h>
 #include <asm/unaligned.h>
@@ -322,12 +323,25 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
 	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
 }
 
+static void nvmet_id_set_model_number(struct nvme_id_ctrl *id,
+				      struct nvmet_subsys *subsys)
+{
+	const char *model = NVMET_DEFAULT_CTRL_MODEL;
+	struct nvmet_subsys_model *subsys_model;
+
+	rcu_read_lock();
+	subsys_model = rcu_dereference(subsys->model);
+	if (subsys_model)
+		model = subsys_model->number;
+	memcpy_and_pad(id->mn, sizeof(id->mn), model, strlen(model), ' ');
+	rcu_read_unlock();
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvme_id_ctrl *id;
 	u16 status = 0;
-	const char model[] = "Linux";
 
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
 	if (!id) {
@@ -342,7 +356,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	memset(id->sn, ' ', sizeof(id->sn));
 	bin2hex(id->sn, &ctrl->subsys->serial,
 		min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
-	memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');
+	nvmet_id_set_model_number(id, ctrl->subsys);
 	memcpy_and_pad(id->fr, sizeof(id->fr),
 		       UTS_RELEASE, strlen(UTS_RELEASE), ' ');
 
@@ -356,8 +370,12 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	/* we support multiple ports, multiples hosts and ANA: */
 	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
 
-	/* no limit on data transfer sizes for now */
-	id->mdts = 0;
+	/* Limit MDTS according to transport capability */
+	if (ctrl->ops->get_mdts)
+		id->mdts = ctrl->ops->get_mdts(ctrl);
+	else
+		id->mdts = 0;
+
 	id->cntlid = cpu_to_le16(ctrl->cntlid);
 	id->ver = cpu_to_le32(ctrl->subsys->ver);
 
@@ -720,13 +738,22 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+	u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
 	u16 status = 0;
+	u16 nsqr;
+	u16 ncqr;
 
 	if (!nvmet_check_data_len(req, 0))
 		return;
 
 	switch (cdw10 & 0xff) {
 	case NVME_FEAT_NUM_QUEUES:
+		ncqr = (cdw11 >> 16) & 0xffff;
+		nsqr = cdw11 & 0xffff;
+		if (ncqr == 0xffff || nsqr == 0xffff) {
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			break;
+		}
 		nvmet_set_result(req,
 			(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
 		break;
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 98613a45bd3b..7aa10788b7c8 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -395,14 +395,12 @@ static ssize_t nvmet_ns_device_uuid_store(struct config_item *item,
 	struct nvmet_subsys *subsys = ns->subsys;
 	int ret = 0;
 
-
 	mutex_lock(&subsys->lock);
 	if (ns->enabled) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
 
-
 	if (uuid_parse(page, &ns->uuid))
 		ret = -EINVAL;
 
@@ -815,10 +813,10 @@ static ssize_t nvmet_subsys_attr_version_show(struct config_item *item,
 				(int)NVME_MAJOR(subsys->ver),
 				(int)NVME_MINOR(subsys->ver),
 				(int)NVME_TERTIARY(subsys->ver));
-	else
-		return snprintf(page, PAGE_SIZE, "%d.%d\n",
-				(int)NVME_MAJOR(subsys->ver),
-				(int)NVME_MINOR(subsys->ver));
+
+	return snprintf(page, PAGE_SIZE, "%d.%d\n",
+			(int)NVME_MAJOR(subsys->ver),
+			(int)NVME_MINOR(subsys->ver));
 }
 
 static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
@@ -828,7 +826,6 @@ static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
 	int major, minor, tertiary = 0;
 	int ret;
 
-
 	ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary);
 	if (ret != 2 && ret != 3)
 		return -EINVAL;
@@ -852,20 +849,151 @@ static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item,
 static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item,
 					      const char *page, size_t count)
 {
-	struct nvmet_subsys *subsys = to_subsys(item);
+	u64 serial;
+
+	if (sscanf(page, "%llx\n", &serial) != 1)
+		return -EINVAL;
 
 	down_write(&nvmet_config_sem);
-	sscanf(page, "%llx\n", &subsys->serial);
+	to_subsys(item)->serial = serial;
 	up_write(&nvmet_config_sem);
 
 	return count;
 }
 CONFIGFS_ATTR(nvmet_subsys_, attr_serial);
 
+static ssize_t nvmet_subsys_attr_cntlid_min_show(struct config_item *item,
+						 char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->cntlid_min);
+}
+
+static ssize_t nvmet_subsys_attr_cntlid_min_store(struct config_item *item,
+						  const char *page, size_t cnt)
+{
+	u16 cntlid_min;
+
+	if (sscanf(page, "%hu\n", &cntlid_min) != 1)
+		return -EINVAL;
+
+	if (cntlid_min == 0)
+		return -EINVAL;
+
+	down_write(&nvmet_config_sem);
+	if (cntlid_min >= to_subsys(item)->cntlid_max)
+		goto out_unlock;
+	to_subsys(item)->cntlid_min = cntlid_min;
+	up_write(&nvmet_config_sem);
+	return cnt;
+
+out_unlock:
+	up_write(&nvmet_config_sem);
+	return -EINVAL;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_min);
+
+static ssize_t nvmet_subsys_attr_cntlid_max_show(struct config_item *item,
+						 char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->cntlid_max);
+}
+
+static ssize_t nvmet_subsys_attr_cntlid_max_store(struct config_item *item,
+						  const char *page, size_t cnt)
+{
+	u16 cntlid_max;
+
+	if (sscanf(page, "%hu\n", &cntlid_max) != 1)
+		return -EINVAL;
+
+	if (cntlid_max == 0)
+		return -EINVAL;
+
+	down_write(&nvmet_config_sem);
+	if (cntlid_max <= to_subsys(item)->cntlid_min)
+		goto out_unlock;
+	to_subsys(item)->cntlid_max = cntlid_max;
+	up_write(&nvmet_config_sem);
+	return cnt;
+
+out_unlock:
+	up_write(&nvmet_config_sem);
+	return -EINVAL;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_max);
+
+static ssize_t nvmet_subsys_attr_model_show(struct config_item *item,
+					    char *page)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+	struct nvmet_subsys_model *subsys_model;
+	char *model = NVMET_DEFAULT_CTRL_MODEL;
+	int ret;
+
+	rcu_read_lock();
+	subsys_model = rcu_dereference(subsys->model);
+	if (subsys_model)
+		model = subsys_model->number;
+	ret = snprintf(page, PAGE_SIZE, "%s\n", model);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/* See Section 1.5 of NVMe 1.4 */
+static bool nvmet_is_ascii(const char c)
+{
+	return c >= 0x20 && c <= 0x7e;
+}
+
+static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
+					     const char *page, size_t count)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+	struct nvmet_subsys_model *new_model;
+	char *new_model_number;
+	int pos = 0, len;
+
+	len = strcspn(page, "\n");
+	if (!len)
+		return -EINVAL;
+
+	for (pos = 0; pos < len; pos++) {
+		if (!nvmet_is_ascii(page[pos]))
+			return -EINVAL;
+	}
+
+	new_model_number = kstrndup(page, len, GFP_KERNEL);
+	if (!new_model_number)
+		return -ENOMEM;
+
+	new_model = kzalloc(sizeof(*new_model) + len + 1, GFP_KERNEL);
+	if (!new_model) {
+		kfree(new_model_number);
+		return -ENOMEM;
+	}
+	memcpy(new_model->number, new_model_number, len);
+
+	down_write(&nvmet_config_sem);
+	mutex_lock(&subsys->lock);
+	new_model = rcu_replace_pointer(subsys->model, new_model,
+					mutex_is_locked(&subsys->lock));
+	mutex_unlock(&subsys->lock);
+	up_write(&nvmet_config_sem);
+
+	kfree_rcu(new_model, rcuhead);
+
+	return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_model);
+
 static struct configfs_attribute *nvmet_subsys_attrs[] = {
 	&nvmet_subsys_attr_attr_allow_any_host,
 	&nvmet_subsys_attr_attr_version,
 	&nvmet_subsys_attr_attr_serial,
+	&nvmet_subsys_attr_attr_cntlid_min,
+	&nvmet_subsys_attr_attr_cntlid_max,
+	&nvmet_subsys_attr_attr_model,
 	NULL,
 };
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 576de773b4db..b685f99d56a1 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1289,8 +1289,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	if (!ctrl->sqs)
 		goto out_free_cqs;
 
+	if (subsys->cntlid_min > subsys->cntlid_max)
+		goto out_free_cqs;
+
 	ret = ida_simple_get(&cntlid_ida,
-			     NVME_CNTLID_MIN, NVME_CNTLID_MAX,
+			     subsys->cntlid_min, subsys->cntlid_max,
 			     GFP_KERNEL);
 	if (ret < 0) {
 		status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
@@ -1438,7 +1441,8 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 		kfree(subsys);
 		return ERR_PTR(-ENOMEM);
 	}
-
+	subsys->cntlid_min = NVME_CNTLID_MIN;
+	subsys->cntlid_max = NVME_CNTLID_MAX;
 	kref_init(&subsys->ref);
 
 	mutex_init(&subsys->lock);
@@ -1457,6 +1461,7 @@ static void nvmet_subsys_free(struct kref *ref)
 	WARN_ON_ONCE(!list_empty(&subsys->namespaces));
 
 	kfree(subsys->subsysnqn);
+	kfree_rcu(subsys->model, rcuhead);
 	kfree(subsys);
 }
 
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 4df4ebde208a..0d54e730cbf2 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -485,7 +485,6 @@ out_destroy_admin:
 out_disable:
 	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
 	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
 }
 
 static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
@@ -618,8 +617,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device,
 		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
 
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index eda28b22a2c8..421dff3ea143 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -23,6 +23,7 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 #define NVMET_NO_ERROR_LOC		((u16)-1)
+#define NVMET_DEFAULT_CTRL_MODEL	"Linux"
 
 /*
  * Supported optional AENs:
@@ -202,6 +203,11 @@ struct nvmet_ctrl {
 	struct nvme_error_slot	slots[NVMET_ERROR_LOG_SLOTS];
 };
 
+struct nvmet_subsys_model {
+	struct rcu_head		rcuhead;
+	char			number[];
+};
+
 struct nvmet_subsys {
 	enum nvme_subsys_type	type;
 
@@ -211,6 +217,8 @@ struct nvmet_subsys {
 	struct list_head	namespaces;
 	unsigned int		nr_namespaces;
 	unsigned int		max_nsid;
+	u16			cntlid_min;
+	u16			cntlid_max;
 
 	struct list_head	ctrls;
 
@@ -227,6 +235,8 @@ struct nvmet_subsys {
 
 	struct config_group	namespaces_group;
 	struct config_group	allowed_hosts_group;
+
+	struct nvmet_subsys_model	__rcu *model;
 };
 
 static inline struct nvmet_subsys *to_subsys(struct config_item *item)
@@ -279,6 +289,7 @@ struct nvmet_fabrics_ops {
 			struct nvmet_port *port, char *traddr);
 	u16 (*install_queue)(struct nvmet_sq *nvme_sq);
 	void (*discovery_chg)(struct nvmet_port *port);
+	u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
 };
 
 #define NVMET_MAX_INLINE_BIOVEC	8
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 37d262a65877..c90c06839d64 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -31,6 +31,9 @@
 #define NVMET_RDMA_MAX_INLINE_SGE		4
 #define NVMET_RDMA_MAX_INLINE_DATA_SIZE		max_t(int, SZ_16K, PAGE_SIZE)
 
+/* Assume mpsmin == device_page_size == 4KB */
+#define NVMET_RDMA_MAX_MDTS			8
+
 struct nvmet_rdma_cmd {
 	struct ib_sge		sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
 	struct ib_cqe		cqe;
@@ -143,12 +146,6 @@ static int num_pages(int len)
 	return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
 }
 
-/* XXX: really should move to a generic header sooner or later.. */
-static inline u32 get_unaligned_le24(const u8 *p)
-{
-	return (u32)p[0] | (u32)p[1] << 8 | (u32)p[2] << 16;
-}
-
 static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp)
 {
 	return nvme_is_write(rsp->req.cmd) &&
@@ -975,7 +972,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 {
 	struct ib_qp_init_attr qp_attr;
 	struct nvmet_rdma_device *ndev = queue->dev;
-	int comp_vector, nr_cqe, ret, i;
+	int comp_vector, nr_cqe, ret, i, factor;
 
 	/*
 	 * Spread the io queues across completion vectors,
@@ -1008,7 +1005,9 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	qp_attr.qp_type = IB_QPT_RC;
 	/* +1 for drain */
 	qp_attr.cap.max_send_wr = queue->send_queue_size + 1;
-	qp_attr.cap.max_rdma_ctxs = queue->send_queue_size;
+	factor = rdma_rw_mr_factor(ndev->device, queue->cm_id->port_num,
+				   1 << NVMET_RDMA_MAX_MDTS);
+	qp_attr.cap.max_rdma_ctxs = queue->send_queue_size * factor;
 	qp_attr.cap.max_send_sge = max(ndev->device->attrs.max_sge_rd,
 					ndev->device->attrs.max_send_sge);
 
@@ -1602,6 +1601,11 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
 	}
 }
 
+static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
+{
+	return NVMET_RDMA_MAX_MDTS;
+}
+
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
@@ -1612,6 +1616,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.queue_response		= nvmet_rdma_queue_response,
 	.delete_ctrl		= nvmet_rdma_delete_ctrl,
 	.disc_traddr		= nvmet_rdma_disc_port_addr,
+	.get_mdts		= nvmet_rdma_get_mdts,
 };
 
 static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 5bb5342b8d0c..f0da04e960f4 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -19,6 +19,16 @@
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
 
+/* Define the socket priority to use for connections were it is desirable
+ * that the NIC consider performing optimized packet processing or filtering.
+ * A non-zero value being sufficient to indicate general consideration of any
+ * possible optimization.  Making it a module param allows for alternative
+ * values that may be unique for some NIC implementations.
+ */
+static int so_priority;
+module_param(so_priority, int, 0644);
+MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority");
+
 #define NVMET_TCP_RECV_BUDGET		8
 #define NVMET_TCP_SEND_BUDGET		8
 #define NVMET_TCP_IO_WORK_BUDGET	64
@@ -622,7 +632,7 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 	return 1;
 }
 
-static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
 	struct nvmet_tcp_queue *queue = cmd->queue;
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
@@ -632,6 +642,9 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
 	};
 	int ret;
 
+	if (!last_in_batch && cmd->queue->send_list_len)
+		msg.msg_flags |= MSG_MORE;
+
 	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
 	if (unlikely(ret <= 0))
 		return ret;
@@ -672,7 +685,7 @@ static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
 	}
 
 	if (cmd->state == NVMET_TCP_SEND_DDGST) {
-		ret = nvmet_try_send_ddgst(cmd);
+		ret = nvmet_try_send_ddgst(cmd, last_in_batch);
 		if (ret <= 0)
 			goto done_send;
 	}
@@ -794,7 +807,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0xffff); /* FIXME: support r2t */
+	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@@ -1439,6 +1452,13 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 	if (ret)
 		return ret;
 
+	if (so_priority > 0) {
+		ret = kernel_setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
+				(char *)&so_priority, sizeof(so_priority));
+		if (ret)
+			return ret;
+	}
+
 	/* Set socket type of service */
 	if (inet->rcv_tos > 0) {
 		int tos = inet->rcv_tos;
@@ -1628,6 +1648,15 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 		goto err_sock;
 	}
 
+	if (so_priority > 0) {
+		ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_PRIORITY,
+				(char *)&so_priority, sizeof(so_priority));
+		if (ret) {
+			pr_err("failed to set SO_PRIORITY sock opt %d\n", ret);
+			goto err_sock;
+		}
+	}
+
 	ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
 			sizeof(port->addr));
 	if (ret) {