Merge drm/drm-next into drm-misc-next

drm-next has been forwarded to 5.0-rc1, and we need it to apply the damage
helper for dirtyfb series from Noralf Trønnes.

Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>

14 files changed, 2452 insertions, 314 deletions

diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 3c7b61ddb0d1..d94f25cde019 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -60,3 +60,13 @@ config NVME_TARGET_FCLOOP
 	  to test NVMe-FC transport interfaces.
 
 	  If unsure, say N.
+
+config NVME_TARGET_TCP
+	tristate "NVMe over Fabrics TCP target support"
+	depends on INET
+	depends on NVME_TARGET
+	help
+	  This enables the NVMe TCP target support, which allows exporting NVMe
+	  devices over TCP.
+
+	  If unsure, say N.
diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
index 8118c93391c6..8c3ad0fb6860 100644
--- a/drivers/nvme/target/Makefile
+++ b/drivers/nvme/target/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_NVME_TARGET_LOOP)		+= nvme-loop.o
 obj-$(CONFIG_NVME_TARGET_RDMA)		+= nvmet-rdma.o
 obj-$(CONFIG_NVME_TARGET_FC)		+= nvmet-fc.o
 obj-$(CONFIG_NVME_TARGET_FCLOOP)	+= nvme-fcloop.o
+obj-$(CONFIG_NVME_TARGET_TCP)		+= nvmet-tcp.o
 
 nvmet-y		+= core.o configfs.o admin-cmd.o fabrics-cmd.o \
 			discovery.o io-cmd-file.o io-cmd-bdev.o
@@ -12,3 +13,4 @@ nvme-loop-y	+= loop.o
 nvmet-rdma-y	+= rdma.o
 nvmet-fc-y	+= fc.o
 nvme-fcloop-y	+= fcloop.o
+nvmet-tcp-y	+= tcp.o
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 1179f6314323..11baeb14c388 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -19,19 +19,6 @@
 #include <asm/unaligned.h>
 #include "nvmet.h"
 
-/*
- * This helper allows us to clear the AEN based on the RAE bit,
- * Please use this helper when processing the log pages which are
- * associated with the AEN.
- */
-static inline void nvmet_clear_aen(struct nvmet_req *req, u32 aen_bit)
-{
-	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
-
-	if (!rae)
-		clear_bit(aen_bit, &req->sq->ctrl->aen_masked);
-}
-
 u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 {
 	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -50,6 +37,34 @@ static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
 	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
 }
 
+static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	u16 status = NVME_SC_SUCCESS;
+	unsigned long flags;
+	off_t offset = 0;
+	u64 slot;
+	u64 i;
+
+	spin_lock_irqsave(&ctrl->error_lock, flags);
+	slot = ctrl->err_counter % NVMET_ERROR_LOG_SLOTS;
+
+	for (i = 0; i < NVMET_ERROR_LOG_SLOTS; i++) {
+		status = nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
+				sizeof(struct nvme_error_slot));
+		if (status)
+			break;
+
+		if (slot == 0)
+			slot = NVMET_ERROR_LOG_SLOTS - 1;
+		else
+			slot--;
+		offset += sizeof(struct nvme_error_slot);
+	}
+	spin_unlock_irqrestore(&ctrl->error_lock, flags);
+	nvmet_req_complete(req, status);
+}
+
 static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		struct nvme_smart_log *slog)
 {
@@ -60,6 +75,7 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	if (!ns) {
 		pr_err("Could not find namespace id : %d\n",
 				le32_to_cpu(req->cmd->get_log_page.nsid));
+		req->error_loc = offsetof(struct nvme_rw_command, nsid);
 		return NVME_SC_INVALID_NS;
 	}
 
@@ -119,6 +135,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 {
 	struct nvme_smart_log *log;
 	u16 status = NVME_SC_INTERNAL;
+	unsigned long flags;
 
 	if (req->data_len != sizeof(*log))
 		goto out;
@@ -134,6 +151,11 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 	if (status)
 		goto out_free_log;
 
+	spin_lock_irqsave(&req->sq->ctrl->error_lock, flags);
+	put_unaligned_le64(req->sq->ctrl->err_counter,
+			&log->num_err_log_entries);
+	spin_unlock_irqrestore(&req->sq->ctrl->error_lock, flags);
+
 	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
 out_free_log:
 	kfree(log);
@@ -189,7 +211,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	if (!status)
 		status = nvmet_zero_sgl(req, len, req->data_len - len);
 	ctrl->nr_changed_ns = 0;
-	nvmet_clear_aen(req, NVME_AEN_CFG_NS_ATTR);
+	nvmet_clear_aen_bit(req, NVME_AEN_BIT_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
@@ -252,7 +274,7 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
 
 	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
 	hdr.ngrps = cpu_to_le16(ngrps);
-	nvmet_clear_aen(req, NVME_AEN_CFG_ANA_CHANGE);
+	nvmet_clear_aen_bit(req, NVME_AEN_BIT_ANA_CHANGE);
 	up_read(&nvmet_ana_sem);
 
 	kfree(desc);
@@ -304,7 +326,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	/* XXX: figure out what to do about RTD3R/RTD3 */
 	id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL);
-	id->ctratt = cpu_to_le32(1 << 0);
+	id->ctratt = cpu_to_le32(NVME_CTRL_ATTR_HID_128_BIT |
+		NVME_CTRL_ATTR_TBKAS);
 
 	id->oacs = 0;
 
@@ -392,6 +415,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	u16 status = 0;
 
 	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
+		req->error_loc = offsetof(struct nvme_identify, nsid);
 		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
 		goto out;
 	}
@@ -512,6 +536,7 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req)
 
 	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid);
 	if (!ns) {
+		req->error_loc = offsetof(struct nvme_identify, nsid);
 		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
 		goto out;
 	}
@@ -569,13 +594,15 @@ static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
 
 static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
 {
-	u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]);
+	u32 write_protect = le32_to_cpu(req->cmd->common.cdw11);
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
 	u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE;
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid);
-	if (unlikely(!req->ns))
+	if (unlikely(!req->ns)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return status;
+	}
 
 	mutex_lock(&subsys->lock);
 	switch (write_protect) {
@@ -599,11 +626,36 @@ static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
 	return status;
 }
 
+u16 nvmet_set_feat_kato(struct nvmet_req *req)
+{
+	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);
+
+	req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
+
+	nvmet_set_result(req, req->sq->ctrl->kato);
+
+	return 0;
+}
+
+u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
+{
+	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);
+
+	if (val32 & ~mask) {
+		req->error_loc = offsetof(struct nvme_common_command, cdw11);
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
+	nvmet_set_result(req, val32);
+
+	return 0;
+}
+
 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[0]);
-	u32 val32;
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 status = 0;
 
 	switch (cdw10 & 0xff) {
@@ -612,19 +664,10 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 			(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
 		break;
 	case NVME_FEAT_KATO:
-		val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
-		req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
-		nvmet_set_result(req, req->sq->ctrl->kato);
+		status = nvmet_set_feat_kato(req);
 		break;
 	case NVME_FEAT_ASYNC_EVENT:
-		val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
-		if (val32 & ~NVMET_AEN_CFG_ALL) {
-			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-			break;
-		}
-
-		WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
-		nvmet_set_result(req, val32);
+		status = nvmet_set_feat_async_event(req, NVMET_AEN_CFG_ALL);
 		break;
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
@@ -633,6 +676,7 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 		status = nvmet_set_feat_write_protect(req);
 		break;
 	default:
+		req->error_loc = offsetof(struct nvme_common_command, cdw10);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
 	}
@@ -646,9 +690,10 @@ static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
 	u32 result;
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid);
-	if (!req->ns)
+	if (!req->ns)  {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
-
+	}
 	mutex_lock(&subsys->lock);
 	if (req->ns->readonly == true)
 		result = NVME_NS_WRITE_PROTECT;
@@ -660,10 +705,20 @@ static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
 	return 0;
 }
 
+void nvmet_get_feat_kato(struct nvmet_req *req)
+{
+	nvmet_set_result(req, req->sq->ctrl->kato * 1000);
+}
+
+void nvmet_get_feat_async_event(struct nvmet_req *req)
+{
+	nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
+}
+
 static void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
-	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 status = 0;
 
 	switch (cdw10 & 0xff) {
@@ -689,7 +744,7 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		break;
 #endif
 	case NVME_FEAT_ASYNC_EVENT:
-		nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
+		nvmet_get_feat_async_event(req);
 		break;
 	case NVME_FEAT_VOLATILE_WC:
 		nvmet_set_result(req, 1);
@@ -699,11 +754,13 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 			(subsys->max_qid-1) | ((subsys->max_qid-1) << 16));
 		break;
 	case NVME_FEAT_KATO:
-		nvmet_set_result(req, req->sq->ctrl->kato * 1000);
+		nvmet_get_feat_kato(req);
 		break;
 	case NVME_FEAT_HOST_ID:
 		/* need 128-bit host identifier flag */
-		if (!(req->cmd->common.cdw10[1] & cpu_to_le32(1 << 0))) {
+		if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) {
+			req->error_loc =
+				offsetof(struct nvme_common_command, cdw11);
 			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 			break;
 		}
@@ -715,6 +772,8 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		status = nvmet_get_feat_write_protect(req);
 		break;
 	default:
+		req->error_loc =
+			offsetof(struct nvme_common_command, cdw10);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
 	}
@@ -722,7 +781,7 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
-static void nvmet_execute_async_event(struct nvmet_req *req)
+void nvmet_execute_async_event(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 
@@ -738,7 +797,7 @@ static void nvmet_execute_async_event(struct nvmet_req *req)
 	schedule_work(&ctrl->async_event_work);
 }
 
-static void nvmet_execute_keep_alive(struct nvmet_req *req)
+void nvmet_execute_keep_alive(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 
@@ -764,13 +823,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 		switch (cmd->get_log_page.lid) {
 		case NVME_LOG_ERROR:
-			/*
-			 * We currently never set the More bit in the status
-			 * field, so all error log entries are invalid and can
-			 * be zeroed out.  This is called a minum viable
-			 * implementation (TM) of this mandatory log page.
-			 */
-			req->execute = nvmet_execute_get_log_page_noop;
+			req->execute = nvmet_execute_get_log_page_error;
 			return 0;
 		case NVME_LOG_SMART:
 			req->execute = nvmet_execute_get_log_page_smart;
@@ -836,5 +889,6 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 	pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
 	       req->sq->qid);
+	req->error_loc = offsetof(struct nvme_common_command, opcode);
 	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 }
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index d895579b6c5d..618bbd006544 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -25,12 +25,16 @@
 static const struct config_item_type nvmet_host_type;
 static const struct config_item_type nvmet_subsys_type;
 
+static LIST_HEAD(nvmet_ports_list);
+struct list_head *nvmet_ports = &nvmet_ports_list;
+
 static const struct nvmet_transport_name {
 	u8		type;
 	const char	*name;
 } nvmet_transport_names[] = {
 	{ NVMF_TRTYPE_RDMA,	"rdma" },
 	{ NVMF_TRTYPE_FC,	"fc" },
+	{ NVMF_TRTYPE_TCP,	"tcp" },
 	{ NVMF_TRTYPE_LOOP,	"loop" },
 };
 
@@ -150,7 +154,8 @@ CONFIGFS_ATTR(nvmet_, addr_traddr);
 static ssize_t nvmet_addr_treq_show(struct config_item *item,
 		char *page)
 {
-	switch (to_nvmet_port(item)->disc_addr.treq) {
+	switch (to_nvmet_port(item)->disc_addr.treq &
+		NVME_TREQ_SECURE_CHANNEL_MASK) {
 	case NVMF_TREQ_NOT_SPECIFIED:
 		return sprintf(page, "not specified\n");
 	case NVMF_TREQ_REQUIRED:
@@ -166,6 +171,7 @@ static ssize_t nvmet_addr_treq_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
+	u8 treq = port->disc_addr.treq & ~NVME_TREQ_SECURE_CHANNEL_MASK;
 
 	if (port->enabled) {
 		pr_err("Cannot modify address while enabled\n");
@@ -174,15 +180,16 @@ static ssize_t nvmet_addr_treq_store(struct config_item *item,
 	}
 
 	if (sysfs_streq(page, "not specified")) {
-		port->disc_addr.treq = NVMF_TREQ_NOT_SPECIFIED;
+		treq |= NVMF_TREQ_NOT_SPECIFIED;
 	} else if (sysfs_streq(page, "required")) {
-		port->disc_addr.treq = NVMF_TREQ_REQUIRED;
+		treq |= NVMF_TREQ_REQUIRED;
 	} else if (sysfs_streq(page, "not required")) {
-		port->disc_addr.treq = NVMF_TREQ_NOT_REQUIRED;
+		treq |= NVMF_TREQ_NOT_REQUIRED;
 	} else {
 		pr_err("Invalid value '%s' for treq\n", page);
 		return -EINVAL;
 	}
+	port->disc_addr.treq = treq;
 
 	return count;
 }
@@ -646,7 +653,8 @@ static int nvmet_port_subsys_allow_link(struct config_item *parent,
 	}
 
 	list_add_tail(&link->entry, &port->subsystems);
-	nvmet_genctr++;
+	nvmet_port_disc_changed(port, subsys);
+
 	up_write(&nvmet_config_sem);
 	return 0;
 
@@ -673,7 +681,8 @@ static void nvmet_port_subsys_drop_link(struct config_item *parent,
 
 found:
 	list_del(&p->entry);
-	nvmet_genctr++;
+	nvmet_port_disc_changed(port, subsys);
+
 	if (list_empty(&port->subsystems))
 		nvmet_disable_port(port);
 	up_write(&nvmet_config_sem);
@@ -722,7 +731,8 @@ static int nvmet_allowed_hosts_allow_link(struct config_item *parent,
 			goto out_free_link;
 	}
 	list_add_tail(&link->entry, &subsys->hosts);
-	nvmet_genctr++;
+	nvmet_subsys_disc_changed(subsys, host);
+
 	up_write(&nvmet_config_sem);
 	return 0;
 out_free_link:
@@ -748,7 +758,8 @@ static void nvmet_allowed_hosts_drop_link(struct config_item *parent,
 
 found:
 	list_del(&p->entry);
-	nvmet_genctr++;
+	nvmet_subsys_disc_changed(subsys, host);
+
 	up_write(&nvmet_config_sem);
 	kfree(p);
 }
@@ -787,7 +798,11 @@ static ssize_t nvmet_subsys_attr_allow_any_host_store(struct config_item *item,
 		goto out_unlock;
 	}
 
-	subsys->allow_any_host = allow_any_host;
+	if (subsys->allow_any_host != allow_any_host) {
+		subsys->allow_any_host = allow_any_host;
+		nvmet_subsys_disc_changed(subsys, NULL);
+	}
+
 out_unlock:
 	up_write(&nvmet_config_sem);
 	return ret ? ret : count;
@@ -936,7 +951,7 @@ static ssize_t nvmet_referral_enable_store(struct config_item *item,
 	if (enable)
 		nvmet_referral_enable(parent, port);
 	else
-		nvmet_referral_disable(port);
+		nvmet_referral_disable(parent, port);
 
 	return count;
 inval:
@@ -962,9 +977,10 @@ static struct configfs_attribute *nvmet_referral_attrs[] = {
 
 static void nvmet_referral_release(struct config_item *item)
 {
+	struct nvmet_port *parent = to_nvmet_port(item->ci_parent->ci_parent);
 	struct nvmet_port *port = to_nvmet_port(item);
 
-	nvmet_referral_disable(port);
+	nvmet_referral_disable(parent, port);
 	kfree(port);
 }
 
@@ -1137,6 +1153,8 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	list_del(&port->global_entry);
+
 	kfree(port->ana_state);
 	kfree(port);
 }
@@ -1189,12 +1207,15 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 			port->ana_state[i] = NVME_ANA_INACCESSIBLE;
 	}
 
+	list_add(&port->global_entry, &nvmet_ports_list);
+
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
 	port->inline_data_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
+	port->disc_addr.treq = NVMF_TREQ_DISABLE_SQFLOW;
 	config_group_init_type_name(&port->group, name, &nvmet_port_type);
 
 	config_group_init_type_name(&port->subsys_group,
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index a5f9bbce863f..88d260f31835 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -45,28 +45,72 @@ u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
 u64 nvmet_ana_chgcnt;
 DECLARE_RWSEM(nvmet_ana_sem);
 
+inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
+{
+	u16 status;
+
+	switch (errno) {
+	case -ENOSPC:
+		req->error_loc = offsetof(struct nvme_rw_command, length);
+		status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
+		break;
+	case -EREMOTEIO:
+		req->error_loc = offsetof(struct nvme_rw_command, slba);
+		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+		break;
+	case -EOPNOTSUPP:
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_dsm:
+		case nvme_cmd_write_zeroes:
+			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
+			break;
+		default:
+			status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		}
+		break;
+	case -ENODATA:
+		req->error_loc = offsetof(struct nvme_rw_command, nsid);
+		status = NVME_SC_ACCESS_DENIED;
+		break;
+	case -EIO:
+		/* FALLTHRU */
+	default:
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+	}
+
+	return status;
+}
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
 u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
 		size_t len)
 {
-	if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
+	if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	}
 	return 0;
 }
 
 u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
 {
-	if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
+	if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	}
 	return 0;
 }
 
 u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
 {
-	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len)
+	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	}
 	return 0;
 }
 
@@ -130,7 +174,7 @@ static void nvmet_async_event_work(struct work_struct *work)
 	}
 }
 
-static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
+void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 		u8 event_info, u8 log_page)
 {
 	struct nvmet_async_event *aen;
@@ -150,13 +194,6 @@ static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	schedule_work(&ctrl->async_event_work);
 }
 
-static bool nvmet_aen_disabled(struct nvmet_ctrl *ctrl, u32 aen)
-{
-	if (!(READ_ONCE(ctrl->aen_enabled) & aen))
-		return true;
-	return test_and_set_bit(aen, &ctrl->aen_masked);
-}
-
 static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
 {
 	u32 i;
@@ -187,7 +224,7 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
 		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
-		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_NS_ATTR))
+		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR))
 			continue;
 		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
 				NVME_AER_NOTICE_NS_CHANGED,
@@ -204,7 +241,7 @@ void nvmet_send_ana_event(struct nvmet_subsys *subsys,
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
 		if (port && ctrl->port != port)
 			continue;
-		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_ANA_CHANGE))
+		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_ANA_CHANGE))
 			continue;
 		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
 				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
@@ -299,6 +336,15 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 {
 	struct nvmet_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvmet_ctrl, ka_work);
+	bool cmd_seen = ctrl->cmd_seen;
+
+	ctrl->cmd_seen = false;
+	if (cmd_seen) {
+		pr_debug("ctrl %d reschedule traffic based keep-alive timer\n",
+			ctrl->cntlid);
+		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		return;
+	}
 
 	pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n",
 		ctrl->cntlid, ctrl->kato);
@@ -595,26 +641,58 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	return ns;
 }
 
-static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
+static void nvmet_update_sq_head(struct nvmet_req *req)
 {
-	u32 old_sqhd, new_sqhd;
-	u16 sqhd;
-
-	if (status)
-		nvmet_set_status(req, status);
-
 	if (req->sq->size) {
+		u32 old_sqhd, new_sqhd;
+
 		do {
 			old_sqhd = req->sq->sqhd;
 			new_sqhd = (old_sqhd + 1) % req->sq->size;
 		} while (cmpxchg(&req->sq->sqhd, old_sqhd, new_sqhd) !=
 					old_sqhd);
 	}
-	sqhd = req->sq->sqhd & 0x0000FFFF;
-	req->rsp->sq_head = cpu_to_le16(sqhd);
+	req->rsp->sq_head = cpu_to_le16(req->sq->sqhd & 0x0000FFFF);
+}
+
+static void nvmet_set_error(struct nvmet_req *req, u16 status)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvme_error_slot *new_error_slot;
+	unsigned long flags;
+
+	req->rsp->status = cpu_to_le16(status << 1);
+
+	if (!ctrl || req->error_loc == NVMET_NO_ERROR_LOC)
+		return;
+
+	spin_lock_irqsave(&ctrl->error_lock, flags);
+	ctrl->err_counter++;
+	new_error_slot =
+		&ctrl->slots[ctrl->err_counter % NVMET_ERROR_LOG_SLOTS];
+
+	new_error_slot->error_count = cpu_to_le64(ctrl->err_counter);
+	new_error_slot->sqid = cpu_to_le16(req->sq->qid);
+	new_error_slot->cmdid = cpu_to_le16(req->cmd->common.command_id);
+	new_error_slot->status_field = cpu_to_le16(status << 1);
+	new_error_slot->param_error_location = cpu_to_le16(req->error_loc);
+	new_error_slot->lba = cpu_to_le64(req->error_slba);
+	new_error_slot->nsid = req->cmd->common.nsid;
+	spin_unlock_irqrestore(&ctrl->error_lock, flags);
+
+	/* set the more bit for this request */
+	req->rsp->status |= cpu_to_le16(1 << 14);
+}
+
+static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
+{
+	if (!req->sq->sqhd_disabled)
+		nvmet_update_sq_head(req);
 	req->rsp->sq_id = cpu_to_le16(req->sq->qid);
 	req->rsp->command_id = req->cmd->common.command_id;
 
+	if (unlikely(status))
+		nvmet_set_error(req, status);
 	if (req->ns)
 		nvmet_put_namespace(req->ns);
 	req->ops->queue_response(req);
@@ -735,14 +813,20 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 		return ret;
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
-	if (unlikely(!req->ns))
+	if (unlikely(!req->ns)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	}
 	ret = nvmet_check_ana_state(req->port, req->ns);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return ret;
+	}
 	ret = nvmet_io_cmd_check_access(req);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return ret;
+	}
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -763,10 +847,14 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	req->sg_cnt = 0;
 	req->transfer_len = 0;
 	req->rsp->status = 0;
+	req->rsp->sq_head = 0;
 	req->ns = NULL;
+	req->error_loc = NVMET_NO_ERROR_LOC;
+	req->error_slba = 0;
 
 	/* no support for fused commands yet */
 	if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
+		req->error_loc = offsetof(struct nvme_common_command, flags);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto fail;
 	}
@@ -777,6 +865,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	 * byte aligned.
 	 */
 	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
+		req->error_loc = offsetof(struct nvme_common_command, flags);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto fail;
 	}
@@ -801,6 +890,9 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		goto fail;
 	}
 
+	if (sq->ctrl)
+		sq->ctrl->cmd_seen = true;
+
 	return true;
 
 fail:
@@ -819,9 +911,10 @@ EXPORT_SYMBOL_GPL(nvmet_req_uninit);
 
 void nvmet_req_execute(struct nvmet_req *req)
 {
-	if (unlikely(req->data_len != req->transfer_len))
+	if (unlikely(req->data_len != req->transfer_len)) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
-	else
+	} else
 		req->execute(req);
 }
 EXPORT_SYMBOL_GPL(nvmet_req_execute);
@@ -1027,14 +1120,18 @@ u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
 	return 0;
 }
 
-static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
-		const char *hostnqn)
+bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn)
 {
 	struct nvmet_host_link *p;
 
+	lockdep_assert_held(&nvmet_config_sem);
+
 	if (subsys->allow_any_host)
 		return true;
 
+	if (subsys->type == NVME_NQN_DISC) /* allow all access to disc subsys */
+		return true;
+
 	list_for_each_entry(p, &subsys->hosts, entry) {
 		if (!strcmp(nvmet_host_name(p->host), hostnqn))
 			return true;
@@ -1043,30 +1140,6 @@ static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
 	return false;
 }
 
-static bool nvmet_host_discovery_allowed(struct nvmet_req *req,
-		const char *hostnqn)
-{
-	struct nvmet_subsys_link *s;
-
-	list_for_each_entry(s, &req->port->subsystems, entry) {
-		if (__nvmet_host_allowed(s->subsys, hostnqn))
-			return true;
-	}
-
-	return false;
-}
-
-bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
-		const char *hostnqn)
-{
-	lockdep_assert_held(&nvmet_config_sem);
-
-	if (subsys->type == NVME_NQN_DISC)
-		return nvmet_host_discovery_allowed(req, hostnqn);
-	else
-		return __nvmet_host_allowed(subsys, hostnqn);
-}
-
 /*
  * Note: ctrl->subsys->lock should be held when calling this function
  */
@@ -1117,7 +1190,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
 	down_read(&nvmet_config_sem);
-	if (!nvmet_host_allowed(req, subsys, hostnqn)) {
+	if (!nvmet_host_allowed(subsys, hostnqn)) {
 		pr_info("connect by host %s for subsystem %s not allowed\n",
 			hostnqn, subsysnqn);
 		req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn);
@@ -1175,31 +1248,20 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	ctrl->cntlid = ret;
 
 	ctrl->ops = req->ops;
-	if (ctrl->subsys->type == NVME_NQN_DISC) {
-		/* Don't accept keep-alive timeout for discovery controllers */
-		if (kato) {
-			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-			goto out_remove_ida;
-		}
 
-		/*
-		 * Discovery controllers use some arbitrary high value in order
-		 * to cleanup stale discovery sessions
-		 *
-		 * From the latest base diff RC:
-		 * "The Keep Alive command is not supported by
-		 * Discovery controllers. A transport may specify a
-		 * fixed Discovery controller activity timeout value
-		 * (e.g., 2 minutes).  If no commands are received
-		 * by a Discovery controller within that time
-		 * period, the controller may perform the
-		 * actions for Keep Alive Timer expiration".
-		 */
-		ctrl->kato = NVMET_DISC_KATO;
-	} else {
-		/* keep-alive timeout in seconds */
-		ctrl->kato = DIV_ROUND_UP(kato, 1000);
-	}
+	/*
+	 * Discovery controllers may use some arbitrary high value
+	 * in order to cleanup stale discovery sessions
+	 */
+	if ((ctrl->subsys->type == NVME_NQN_DISC) && !kato)
+		kato = NVMET_DISC_KATO_MS;
+
+	/* keep-alive timeout in seconds */
+	ctrl->kato = DIV_ROUND_UP(kato, 1000);
+
+	ctrl->err_counter = 0;
+	spin_lock_init(&ctrl->error_lock);
+
 	nvmet_start_keep_alive_timer(ctrl);
 
 	mutex_lock(&subsys->lock);
@@ -1210,8 +1272,6 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	*ctrlp = ctrl;
 	return 0;
 
-out_remove_ida:
-	ida_simple_remove(&cntlid_ida, ctrl->cntlid);
 out_free_sqs:
 	kfree(ctrl->sqs);
 out_free_cqs:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index bc0aa0bf1543..d2cb71a0b419 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -18,7 +18,65 @@
 
 struct nvmet_subsys *nvmet_disc_subsys;
 
-u64 nvmet_genctr;
+static u64 nvmet_genctr;
+
+static void __nvmet_disc_changed(struct nvmet_port *port,
+				 struct nvmet_ctrl *ctrl)
+{
+	if (ctrl->port != port)
+		return;
+
+	if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_DISC_CHANGE))
+		return;
+
+	nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+			      NVME_AER_NOTICE_DISC_CHANGED, NVME_LOG_DISC);
+}
+
+void nvmet_port_disc_changed(struct nvmet_port *port,
+			     struct nvmet_subsys *subsys)
+{
+	struct nvmet_ctrl *ctrl;
+
+	nvmet_genctr++;
+
+	list_for_each_entry(ctrl, &nvmet_disc_subsys->ctrls, subsys_entry) {
+		if (subsys && !nvmet_host_allowed(subsys, ctrl->hostnqn))
+			continue;
+
+		__nvmet_disc_changed(port, ctrl);
+	}
+}
+
+static void __nvmet_subsys_disc_changed(struct nvmet_port *port,
+					struct nvmet_subsys *subsys,
+					struct nvmet_host *host)
+{
+	struct nvmet_ctrl *ctrl;
+
+	list_for_each_entry(ctrl, &nvmet_disc_subsys->ctrls, subsys_entry) {
+		if (host && strcmp(nvmet_host_name(host), ctrl->hostnqn))
+			continue;
+
+		__nvmet_disc_changed(port, ctrl);
+	}
+}
+
+void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
+			       struct nvmet_host *host)
+{
+	struct nvmet_port *port;
+	struct nvmet_subsys_link *s;
+
+	nvmet_genctr++;
+
+	list_for_each_entry(port, nvmet_ports, global_entry)
+		list_for_each_entry(s, &port->subsystems, entry) {
+			if (s->subsys != subsys)
+				continue;
+			__nvmet_subsys_disc_changed(port, subsys, host);
+		}
+}
 
 void nvmet_referral_enable(struct nvmet_port *parent, struct nvmet_port *port)
 {
@@ -26,18 +84,18 @@ void nvmet_referral_enable(struct nvmet_port *parent, struct nvmet_port *port)
 	if (list_empty(&port->entry)) {
 		list_add_tail(&port->entry, &parent->referrals);
 		port->enabled = true;
-		nvmet_genctr++;
+		nvmet_port_disc_changed(parent, NULL);
 	}
 	up_write(&nvmet_config_sem);
 }
 
-void nvmet_referral_disable(struct nvmet_port *port)
+void nvmet_referral_disable(struct nvmet_port *parent, struct nvmet_port *port)
 {
 	down_write(&nvmet_config_sem);
 	if (!list_empty(&port->entry)) {
 		port->enabled = false;
 		list_del_init(&port->entry);
-		nvmet_genctr++;
+		nvmet_port_disc_changed(parent, NULL);
 	}
 	up_write(&nvmet_config_sem);
 }
@@ -107,7 +165,7 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 
 	down_read(&nvmet_config_sem);
 	list_for_each_entry(p, &req->port->subsystems, entry) {
-		if (!nvmet_host_allowed(req, p->subsys, ctrl->hostnqn))
+		if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
 			continue;
 		if (residual_len >= entry_size) {
 			char traddr[NVMF_TRADDR_SIZE];
@@ -136,6 +194,8 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 	hdr->numrec = cpu_to_le64(numrec);
 	hdr->recfmt = cpu_to_le16(0);
 
+	nvmet_clear_aen_bit(req, NVME_AEN_BIT_DISC_CHANGE);
+
 	up_read(&nvmet_config_sem);
 
 	status = nvmet_copy_to_sgl(req, 0, hdr, data_len);
@@ -174,6 +234,8 @@ static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
 	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
+	id->oaes = cpu_to_le32(NVMET_DISC_AEN_CFG_OPTIONAL);
+
 	strlcpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn));
 
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
@@ -183,6 +245,51 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_disc_set_features(struct nvmet_req *req)
+{
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+	u16 stat;
+
+	switch (cdw10 & 0xff) {
+	case NVME_FEAT_KATO:
+		stat = nvmet_set_feat_kato(req);
+		break;
+	case NVME_FEAT_ASYNC_EVENT:
+		stat = nvmet_set_feat_async_event(req,
+						  NVMET_DISC_AEN_CFG_OPTIONAL);
+		break;
+	default:
+		req->error_loc =
+			offsetof(struct nvme_common_command, cdw10);
+		stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		break;
+	}
+
+	nvmet_req_complete(req, stat);
+}
+
+static void nvmet_execute_disc_get_features(struct nvmet_req *req)
+{
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+	u16 stat = 0;
+
+	switch (cdw10 & 0xff) {
+	case NVME_FEAT_KATO:
+		nvmet_get_feat_kato(req);
+		break;
+	case NVME_FEAT_ASYNC_EVENT:
+		nvmet_get_feat_async_event(req);
+		break;
+	default:
+		req->error_loc =
+			offsetof(struct nvme_common_command, cdw10);
+		stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		break;
+	}
+
+	nvmet_req_complete(req, stat);
+}
+
 u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -190,10 +297,28 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
 		pr_err("got cmd %d while not ready\n",
 		       cmd->common.opcode);
+		req->error_loc =
+			offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
 	switch (cmd->common.opcode) {
+	case nvme_admin_set_features:
+		req->execute = nvmet_execute_disc_set_features;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_get_features:
+		req->execute = nvmet_execute_disc_get_features;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_async_event:
+		req->execute = nvmet_execute_async_event;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_keep_alive:
+		req->execute = nvmet_execute_keep_alive;
+		req->data_len = 0;
+		return 0;
 	case nvme_admin_get_log_page:
 		req->data_len = nvmet_get_log_page_len(cmd);
 
@@ -204,6 +329,8 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 		default:
 			pr_err("unsupported get_log_page lid %d\n",
 			       cmd->get_log_page.lid);
+			req->error_loc =
+				offsetof(struct nvme_get_log_page_command, lid);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	case nvme_admin_identify:
@@ -216,10 +343,12 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 		default:
 			pr_err("unsupported identify cns %d\n",
 			       cmd->identify.cns);
+			req->error_loc = offsetof(struct nvme_identify, cns);
 			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	default:
 		pr_err("unhandled cmd %d\n", cmd->common.opcode);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index d84ae004cb85..6cf1fd9eb32e 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -17,23 +17,26 @@
 
 static void nvmet_execute_prop_set(struct nvmet_req *req)
 {
+	u64 val = le64_to_cpu(req->cmd->prop_set.value);
 	u16 status = 0;
 
-	if (!(req->cmd->prop_set.attrib & 1)) {
-		u64 val = le64_to_cpu(req->cmd->prop_set.value);
-
-		switch (le32_to_cpu(req->cmd->prop_set.offset)) {
-		case NVME_REG_CC:
-			nvmet_update_cc(req->sq->ctrl, val);
-			break;
-		default:
-			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-			break;
-		}
-	} else {
+	if (req->cmd->prop_set.attrib & 1) {
+		req->error_loc =
+			offsetof(struct nvmf_property_set_command, attrib);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto out;
 	}
 
+	switch (le32_to_cpu(req->cmd->prop_set.offset)) {
+	case NVME_REG_CC:
+		nvmet_update_cc(req->sq->ctrl, val);
+		break;
+	default:
+		req->error_loc =
+			offsetof(struct nvmf_property_set_command, offset);
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+out:
 	nvmet_req_complete(req, status);
 }
 
@@ -69,6 +72,14 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
 		}
 	}
 
+	if (status && req->cmd->prop_get.attrib & 1) {
+		req->error_loc =
+			offsetof(struct nvmf_property_get_command, offset);
+	} else {
+		req->error_loc =
+			offsetof(struct nvmf_property_get_command, attrib);
+	}
+
 	req->rsp->result.u64 = cpu_to_le64(val);
 	nvmet_req_complete(req, status);
 }
@@ -89,6 +100,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
 	default:
 		pr_err("received unknown capsule type 0x%x\n",
 			cmd->fabrics.fctype);
+		req->error_loc = offsetof(struct nvmf_common_command, fctype);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
@@ -105,16 +117,34 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
 	if (old) {
 		pr_warn("queue already connected!\n");
+		req->error_loc = offsetof(struct nvmf_connect_command, opcode);
 		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
 	}
 	if (!sqsize) {
 		pr_warn("queue size zero!\n");
+		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
 		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
 	}
 
 	/* note: convert queue size from 0's-based value to 1's-based value */
 	nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1);
 	nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1);
+
+	if (c->cattr & NVME_CONNECT_DISABLE_SQFLOW) {
+		req->sq->sqhd_disabled = true;
+		req->rsp->sq_head = cpu_to_le16(0xffff);
+	}
+
+	if (ctrl->ops->install_queue) {
+		u16 ret = ctrl->ops->install_queue(req->sq);
+
+		if (ret) {
+			pr_err("failed to install queue %d cntlid %d ret %x\n",
+				qid, ret, ctrl->cntlid);
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
@@ -141,6 +171,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	if (c->recfmt != 0) {
 		pr_warn("invalid connect version (%d).\n",
 			le16_to_cpu(c->recfmt));
+		req->error_loc = offsetof(struct nvmf_connect_command, recfmt);
 		status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
 		goto out;
 	}
@@ -155,8 +186,13 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 
 	status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
 				  le32_to_cpu(c->kato), &ctrl);
-	if (status)
+	if (status) {
+		if (status == (NVME_SC_INVALID_FIELD | NVME_SC_DNR))
+			req->error_loc =
+				offsetof(struct nvme_common_command, opcode);
 		goto out;
+	}
+
 	uuid_copy(&ctrl->hostid, &d->hostid);
 
 	status = nvmet_install_queue(ctrl, req);
@@ -243,11 +279,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
 	if (cmd->common.opcode != nvme_fabrics_command) {
 		pr_err("invalid command 0x%x on unconnected queue.\n",
 			cmd->fabrics.opcode);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 	if (cmd->fabrics.fctype != nvme_fabrics_type_connect) {
 		pr_err("invalid capsule type 0x%x on unconnected queue.\n",
 			cmd->fabrics.fctype);
+		req->error_loc = offsetof(struct nvmf_common_command, fctype);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 409081a03b24..f98f5c5bea26 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -86,8 +86,6 @@ struct nvmet_fc_fcp_iod {
 	spinlock_t			flock;
 
 	struct nvmet_req		req;
-	struct work_struct		work;
-	struct work_struct		done_work;
 	struct work_struct		defer_work;
 
 	struct nvmet_fc_tgtport		*tgtport;
@@ -134,7 +132,6 @@ struct nvmet_fc_tgt_queue {
 	u16				sqsize;
 	u16				ersp_ratio;
 	__le16				sqhd;
-	int				cpu;
 	atomic_t			connected;
 	atomic_t			sqtail;
 	atomic_t			zrspcnt;
@@ -232,8 +229,6 @@ static LIST_HEAD(nvmet_fc_portentry_list);
 
 
 static void nvmet_fc_handle_ls_rqst_work(struct work_struct *work);
-static void nvmet_fc_handle_fcp_rqst_work(struct work_struct *work);
-static void nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work);
 static void nvmet_fc_fcp_rqst_op_defer_work(struct work_struct *work);
 static void nvmet_fc_tgt_a_put(struct nvmet_fc_tgt_assoc *assoc);
 static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
@@ -438,8 +433,6 @@ nvmet_fc_prep_fcp_iodlist(struct nvmet_fc_tgtport *tgtport,
 	int i;
 
 	for (i = 0; i < queue->sqsize; fod++, i++) {
-		INIT_WORK(&fod->work, nvmet_fc_handle_fcp_rqst_work);
-		INIT_WORK(&fod->done_work, nvmet_fc_fcp_rqst_op_done_work);
 		INIT_WORK(&fod->defer_work, nvmet_fc_fcp_rqst_op_defer_work);
 		fod->tgtport = tgtport;
 		fod->queue = queue;
@@ -517,10 +510,7 @@ nvmet_fc_queue_fcp_req(struct nvmet_fc_tgtport *tgtport,
 	fcpreq->hwqid = queue->qid ?
 			((queue->qid - 1) % tgtport->ops->max_hw_queues) : 0;
 
-	if (tgtport->ops->target_features & NVMET_FCTGTFEAT_CMD_IN_ISR)
-		queue_work_on(queue->cpu, queue->work_q, &fod->work);
-	else
-		nvmet_fc_handle_fcp_rqst(tgtport, fod);
+	nvmet_fc_handle_fcp_rqst(tgtport, fod);
 }
 
 static void
@@ -599,30 +589,6 @@ nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue,
 	queue_work(queue->work_q, &fod->defer_work);
 }
 
-static int
-nvmet_fc_queue_to_cpu(struct nvmet_fc_tgtport *tgtport, int qid)
-{
-	int cpu, idx, cnt;
-
-	if (tgtport->ops->max_hw_queues == 1)
-		return WORK_CPU_UNBOUND;
-
-	/* Simple cpu selection based on qid modulo active cpu count */
-	idx = !qid ? 0 : (qid - 1) % num_active_cpus();
-
-	/* find the n'th active cpu */
-	for (cpu = 0, cnt = 0; ; ) {
-		if (cpu_active(cpu)) {
-			if (cnt == idx)
-				break;
-			cnt++;
-		}
-		cpu = (cpu + 1) % num_possible_cpus();
-	}
-
-	return cpu;
-}
-
 static struct nvmet_fc_tgt_queue *
 nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 			u16 qid, u16 sqsize)
@@ -653,7 +619,6 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	queue->qid = qid;
 	queue->sqsize = sqsize;
 	queue->assoc = assoc;
-	queue->cpu = nvmet_fc_queue_to_cpu(assoc->tgtport, qid);
 	INIT_LIST_HEAD(&queue->fod_list);
 	INIT_LIST_HEAD(&queue->avail_defer_list);
 	INIT_LIST_HEAD(&queue->pending_cmd_list);
@@ -2146,25 +2111,11 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 }
 
 static void
-nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work)
-{
-	struct nvmet_fc_fcp_iod *fod =
-		container_of(work, struct nvmet_fc_fcp_iod, done_work);
-
-	nvmet_fc_fod_op_done(fod);
-}
-
-static void
 nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 {
 	struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
-	struct nvmet_fc_tgt_queue *queue = fod->queue;
 
-	if (fod->tgtport->ops->target_features & NVMET_FCTGTFEAT_OPDONE_IN_ISR)
-		/* context switch so completion is not in ISR context */
-		queue_work_on(queue->cpu, queue->work_q, &fod->done_work);
-	else
-		nvmet_fc_fod_op_done(fod);
+	nvmet_fc_fod_op_done(fod);
 }
 
 /*
@@ -2332,19 +2283,6 @@ transport_error:
 	nvmet_fc_abort_op(tgtport, fod);
 }
 
-/*
- * Actual processing routine for received FC-NVME LS Requests from the LLD
- */
-static void
-nvmet_fc_handle_fcp_rqst_work(struct work_struct *work)
-{
-	struct nvmet_fc_fcp_iod *fod =
-		container_of(work, struct nvmet_fc_fcp_iod, work);
-	struct nvmet_fc_tgtport *tgtport = fod->tgtport;
-
-	nvmet_fc_handle_fcp_rqst(tgtport, fod);
-}
-
 /**
  * nvmet_fc_rcv_fcp_req - transport entry point called by an LLDD
  *                       upon the reception of a NVME FCP CMD IU.
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index c1ec3475a140..b6d030d3259f 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -44,13 +44,69 @@ void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
 	}
 }
 
+static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
+{
+	u16 status = NVME_SC_SUCCESS;
+
+	if (likely(blk_sts == BLK_STS_OK))
+		return status;
+	/*
+	 * Right now there exists M : 1 mapping between block layer error
+	 * to the NVMe status code (see nvme_error_status()). For consistency,
+	 * when we reverse map we use most appropriate NVMe Status code from
+	 * the group of the NVMe staus codes used in the nvme_error_status().
+	 */
+	switch (blk_sts) {
+	case BLK_STS_NOSPC:
+		status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_rw_command, length);
+		break;
+	case BLK_STS_TARGET:
+		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_rw_command, slba);
+		break;
+	case BLK_STS_NOTSUPP:
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_dsm:
+		case nvme_cmd_write_zeroes:
+			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
+			break;
+		default:
+			status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		}
+		break;
+	case BLK_STS_MEDIUM:
+		status = NVME_SC_ACCESS_DENIED;
+		req->error_loc = offsetof(struct nvme_rw_command, nsid);
+		break;
+	case BLK_STS_IOERR:
+		/* fallthru */
+	default:
+		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+	}
+
+	switch (req->cmd->common.opcode) {
+	case nvme_cmd_read:
+	case nvme_cmd_write:
+		req->error_slba = le64_to_cpu(req->cmd->rw.slba);
+		break;
+	case nvme_cmd_write_zeroes:
+		req->error_slba =
+			le64_to_cpu(req->cmd->write_zeroes.slba);
+		break;
+	default:
+		req->error_slba = 0;
+	}
+	return status;
+}
+
 static void nvmet_bio_done(struct bio *bio)
 {
 	struct nvmet_req *req = bio->bi_private;
 
-	nvmet_req_complete(req,
-		bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
-
+	nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
 	if (bio != &req->b.inline_bio)
 		bio_put(bio);
 }
@@ -61,7 +117,6 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 	struct bio *bio;
 	struct scatterlist *sg;
 	sector_t sector;
-	blk_qc_t cookie;
 	int op, op_flags = 0, i;
 
 	if (!req->sg_cnt) {
@@ -114,9 +169,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 		sg_cnt--;
 	}
 
-	cookie = submit_bio(bio);
-
-	blk_poll(bdev_get_queue(req->ns->bdev), cookie);
+	submit_bio(bio);
 }
 
 static void nvmet_bdev_execute_flush(struct nvmet_req *req)
@@ -139,18 +192,21 @@ u16 nvmet_bdev_flush(struct nvmet_req *req)
 	return 0;
 }
 
-static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
+static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
+	struct nvmet_ns *ns = req->ns;
 	int ret;
 
 	ret = __blkdev_issue_discard(ns->bdev,
 			le64_to_cpu(range->slba) << (ns->blksize_shift - 9),
 			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
 			GFP_KERNEL, 0, bio);
-	if (ret && ret != -EOPNOTSUPP)
-		return NVME_SC_INTERNAL | NVME_SC_DNR;
-	return 0;
+
+	if (ret)
+		req->error_slba = le64_to_cpu(range->slba);
+
+	return blk_to_nvme_status(req, errno_to_blk_status(ret));
 }
 
 static void nvmet_bdev_execute_discard(struct nvmet_req *req)
@@ -166,7 +222,7 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req)
 		if (status)
 			break;
 
-		status = nvmet_bdev_discard_range(req->ns, &range, &bio);
+		status = nvmet_bdev_discard_range(req, &range, &bio);
 		if (status)
 			break;
 	}
@@ -207,16 +263,16 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 	u16 status = NVME_SC_SUCCESS;
 	sector_t sector;
 	sector_t nr_sector;
+	int ret;
 
 	sector = le64_to_cpu(write_zeroes->slba) <<
 		(req->ns->blksize_shift - 9);
 	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
 		(req->ns->blksize_shift - 9));
 
-	if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
-				GFP_KERNEL, &bio, 0))
-		status = NVME_SC_INTERNAL | NVME_SC_DNR;
-
+	ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
+			GFP_KERNEL, &bio, 0);
+	status = blk_to_nvme_status(req, errno_to_blk_status(ret));
 	if (bio) {
 		bio->bi_private = req;
 		bio->bi_end_io = nvmet_bio_done;
@@ -251,6 +307,7 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 	default:
 		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
 		       req->sq->qid);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 01feebec29ea..517522305e5c 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -83,17 +83,16 @@ static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
 }
 
 static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
-		unsigned long nr_segs, size_t count)
+		unsigned long nr_segs, size_t count, int ki_flags)
 {
 	struct kiocb *iocb = &req->f.iocb;
 	ssize_t (*call_iter)(struct kiocb *iocb, struct iov_iter *iter);
 	struct iov_iter iter;
-	int ki_flags = 0, rw;
-	ssize_t ret;
+	int rw;
 
 	if (req->cmd->rw.opcode == nvme_cmd_write) {
 		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
-			ki_flags = IOCB_DSYNC;
+			ki_flags |= IOCB_DSYNC;
 		call_iter = req->ns->file->f_op->write_iter;
 		rw = WRITE;
 	} else {
@@ -107,17 +106,13 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 	iocb->ki_filp = req->ns->file;
 	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
-	ret = call_iter(iocb, &iter);
-
-	if (ret != -EIOCBQUEUED && iocb->ki_complete)
-		iocb->ki_complete(iocb, ret, 0);
-
-	return ret;
+	return call_iter(iocb, &iter);
 }
 
 static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 {
 	struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
+	u16 status = NVME_SC_SUCCESS;
 
 	if (req->f.bvec != req->inline_bvec) {
 		if (likely(req->f.mpool_alloc == false))
@@ -126,11 +121,12 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 			mempool_free(req->f.bvec, req->ns->bvec_pool);
 	}
 
-	nvmet_req_complete(req, ret != req->data_len ?
-			NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	if (unlikely(ret != req->data_len))
+		status = errno_to_nvme_status(req, ret);
+	nvmet_req_complete(req, status);
 }
 
-static void nvmet_file_execute_rw(struct nvmet_req *req)
+static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 {
 	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
 	struct sg_page_iter sg_pg_iter;
@@ -140,30 +136,14 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 	ssize_t ret = 0;
 	loff_t pos;
 
-	if (!req->sg_cnt || !nr_bvec) {
-		nvmet_req_complete(req, 0);
-		return;
-	}
+
+	if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC)
+		is_sync = true;
 
 	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
 	if (unlikely(pos + req->data_len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
-		return;
-	}
-
-	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
-		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
-				GFP_KERNEL);
-	else
-		req->f.bvec = req->inline_bvec;
-
-	req->f.mpool_alloc = false;
-	if (unlikely(!req->f.bvec)) {
-		/* fallback under memory pressure */
-		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
-		req->f.mpool_alloc = true;
-		if (nr_bvec > NVMET_MAX_MPOOL_BVEC)
-			is_sync = true;
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
+		return true;
 	}
 
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
@@ -177,9 +157,10 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 
 		if (unlikely(is_sync) &&
 		    (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
-			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len);
+			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len, 0);
 			if (ret < 0)
-				goto out;
+				goto complete;
+
 			pos += len;
 			bv_cnt = 0;
 			len = 0;
@@ -187,35 +168,95 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 		nr_bvec--;
 	}
 
-	if (WARN_ON_ONCE(total_len != req->data_len))
+	if (WARN_ON_ONCE(total_len != req->data_len)) {
 		ret = -EIO;
-out:
-	if (unlikely(is_sync || ret)) {
-		nvmet_file_io_done(&req->f.iocb, ret < 0 ? ret : total_len, 0);
-		return;
+		goto complete;
+	}
+
+	if (unlikely(is_sync)) {
+		ret = total_len;
+		goto complete;
 	}
-	req->f.iocb.ki_complete = nvmet_file_io_done;
-	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
+
+	/*
+	 * A NULL ki_complete ask for synchronous execution, which we want
+	 * for the IOCB_NOWAIT case.
+	 */
+	if (!(ki_flags & IOCB_NOWAIT))
+		req->f.iocb.ki_complete = nvmet_file_io_done;
+
+	ret = nvmet_file_submit_bvec(req, pos, bv_cnt, total_len, ki_flags);
+
+	switch (ret) {
+	case -EIOCBQUEUED:
+		return true;
+	case -EAGAIN:
+		if (WARN_ON_ONCE(!(ki_flags & IOCB_NOWAIT)))
+			goto complete;
+		return false;
+	case -EOPNOTSUPP:
+		/*
+		 * For file systems returning error -EOPNOTSUPP, handle
+		 * IOCB_NOWAIT error case separately and retry without
+		 * IOCB_NOWAIT.
+		 */
+		if ((ki_flags & IOCB_NOWAIT))
+			return false;
+		break;
+	}
+
+complete:
+	nvmet_file_io_done(&req->f.iocb, ret, 0);
+	return true;
 }
 
 static void nvmet_file_buffered_io_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
 
-	nvmet_file_execute_rw(req);
+	nvmet_file_execute_io(req, 0);
 }
 
-static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
+static void nvmet_file_submit_buffered_io(struct nvmet_req *req)
 {
 	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
 	queue_work(buffered_io_wq, &req->f.work);
 }
 
+static void nvmet_file_execute_rw(struct nvmet_req *req)
+{
+	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
+
+	if (!req->sg_cnt || !nr_bvec) {
+		nvmet_req_complete(req, 0);
+		return;
+	}
+
+	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
+		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
+				GFP_KERNEL);
+	else
+		req->f.bvec = req->inline_bvec;
+
+	if (unlikely(!req->f.bvec)) {
+		/* fallback under memory pressure */
+		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
+		req->f.mpool_alloc = true;
+	} else
+		req->f.mpool_alloc = false;
+
+	if (req->ns->buffered_io) {
+		if (likely(!req->f.mpool_alloc) &&
+				nvmet_file_execute_io(req, IOCB_NOWAIT))
+			return;
+		nvmet_file_submit_buffered_io(req);
+	} else
+		nvmet_file_execute_io(req, 0);
+}
+
 u16 nvmet_file_flush(struct nvmet_req *req)
 {
-	if (vfs_fsync(req->ns->file, 1) < 0)
-		return NVME_SC_INTERNAL | NVME_SC_DNR;
-	return 0;
+	return errno_to_nvme_status(req, vfs_fsync(req->ns->file, 1));
 }
 
 static void nvmet_file_flush_work(struct work_struct *w)
@@ -236,30 +277,34 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
 	loff_t offset, len;
-	u16 ret;
+	u16 status = 0;
+	int ret;
 	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+		status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
 					sizeof(range));
-		if (ret)
+		if (status)
 			break;
 
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb);
 		len <<= req->ns->blksize_shift;
 		if (offset + len > req->ns->size) {
-			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, -ENOSPC);
 			break;
 		}
 
-		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
-			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+		ret = vfs_fallocate(req->ns->file, mode, offset, len);
+		if (ret) {
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, ret);
 			break;
 		}
 	}
 
-	nvmet_req_complete(req, ret);
+	nvmet_req_complete(req, status);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -299,12 +344,12 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 			req->ns->blksize_shift);
 
 	if (unlikely(offset + len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
 		return;
 	}
 
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) : 0);
 }
 
 static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
@@ -320,10 +365,7 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		if (req->ns->buffered_io)
-			req->execute = nvmet_file_execute_rw_buffered_io;
-		else
-			req->execute = nvmet_file_execute_rw;
+		req->execute = nvmet_file_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
@@ -342,6 +384,7 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	default:
 		pr_err("unhandled cmd for file ns %d on qid %d\n",
 				cmd->common.opcode, req->sq->qid);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 9908082b32c4..4aac1b4a8112 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -345,7 +345,7 @@ static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
 	int i, ret;
 
 	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
-		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i, false);
 		if (ret)
 			return ret;
 		set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index c2b4d9ee6391..3e4719fdba85 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,12 +30,15 @@
 
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
+#define NVMET_NO_ERROR_LOC		((u16)-1)
 
 /*
  * Supported optional AENs:
  */
 #define NVMET_AEN_CFG_OPTIONAL \
 	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_ANA_CHANGE)
+#define NVMET_DISC_AEN_CFG_OPTIONAL \
+	(NVME_AEN_CFG_DISC_CHANGE)
 
 /*
  * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
@@ -104,6 +107,7 @@ struct nvmet_sq {
 	u16			qid;
 	u16			size;
 	u32			sqhd;
+	bool			sqhd_disabled;
 	struct completion	free_done;
 	struct completion	confirm_done;
 };
@@ -137,6 +141,7 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	struct list_head		global_entry;
 	struct config_group		ana_groups_group;
 	struct nvmet_ana_group		ana_default_group;
 	enum nvme_ana_state		*ana_state;
@@ -163,6 +168,8 @@ struct nvmet_ctrl {
 	struct nvmet_cq		**cqs;
 	struct nvmet_sq		**sqs;
 
+	bool			cmd_seen;
+
 	struct mutex		lock;
 	u64			cap;
 	u32			cc;
@@ -194,8 +201,12 @@ struct nvmet_ctrl {
 	char			subsysnqn[NVMF_NQN_FIELD_LEN];
 	char			hostnqn[NVMF_NQN_FIELD_LEN];
 
-	struct device *p2p_client;
-	struct radix_tree_root p2p_ns_map;
+	struct device		*p2p_client;
+	struct radix_tree_root	p2p_ns_map;
+
+	spinlock_t		error_lock;
+	u64			err_counter;
+	struct nvme_error_slot	slots[NVMET_ERROR_LOG_SLOTS];
 };
 
 struct nvmet_subsys {
@@ -273,6 +284,7 @@ struct nvmet_fabrics_ops {
 	void (*delete_ctrl)(struct nvmet_ctrl *ctrl);
 	void (*disc_traddr)(struct nvmet_req *req,
 			struct nvmet_port *port, char *traddr);
+	u16 (*install_queue)(struct nvmet_sq *nvme_sq);
 };
 
 #define NVMET_MAX_INLINE_BIOVEC	8
@@ -308,17 +320,14 @@ struct nvmet_req {
 	void (*execute)(struct nvmet_req *req);
 	const struct nvmet_fabrics_ops *ops;
 
-	struct pci_dev *p2p_dev;
-	struct device *p2p_client;
+	struct pci_dev		*p2p_dev;
+	struct device		*p2p_client;
+	u16			error_loc;
+	u64			error_slba;
 };
 
 extern struct workqueue_struct *buffered_io_wq;
 
-static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
-{
-	req->rsp->status = cpu_to_le16(status << 1);
-}
-
 static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
 {
 	req->rsp->result.u32 = cpu_to_le32(result);
@@ -340,6 +349,27 @@ struct nvmet_async_event {
 	u8			log_page;
 };
 
+static inline void nvmet_clear_aen_bit(struct nvmet_req *req, u32 bn)
+{
+	int rae = le32_to_cpu(req->cmd->common.cdw10) & 1 << 15;
+
+	if (!rae)
+		clear_bit(bn, &req->sq->ctrl->aen_masked);
+}
+
+static inline bool nvmet_aen_bit_disabled(struct nvmet_ctrl *ctrl, u32 bn)
+{
+	if (!(READ_ONCE(ctrl->aen_enabled) & (1 << bn)))
+		return true;
+	return test_and_set_bit(bn, &ctrl->aen_masked);
+}
+
+void nvmet_get_feat_kato(struct nvmet_req *req);
+void nvmet_get_feat_async_event(struct nvmet_req *req);
+u16 nvmet_set_feat_kato(struct nvmet_req *req);
+u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask);
+void nvmet_execute_async_event(struct nvmet_req *req);
+
 u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
 u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
 u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
@@ -355,6 +385,8 @@ void nvmet_req_complete(struct nvmet_req *req, u16 status);
 int nvmet_req_alloc_sgl(struct nvmet_req *req);
 void nvmet_req_free_sgl(struct nvmet_req *req);
 
+void nvmet_execute_keep_alive(struct nvmet_req *req);
+
 void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
 		u16 size);
 void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid,
@@ -395,7 +427,7 @@ int nvmet_enable_port(struct nvmet_port *port);
 void nvmet_disable_port(struct nvmet_port *port);
 
 void nvmet_referral_enable(struct nvmet_port *parent, struct nvmet_port *port);
-void nvmet_referral_disable(struct nvmet_port *port);
+void nvmet_referral_disable(struct nvmet_port *parent, struct nvmet_port *port);
 
 u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
 		size_t len);
@@ -405,6 +437,14 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
 
 u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 
+extern struct list_head *nvmet_ports;
+void nvmet_port_disc_changed(struct nvmet_port *port,
+		struct nvmet_subsys *subsys);
+void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
+		struct nvmet_host *host);
+void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
+		u8 event_info, u8 log_page);
+
 #define NVMET_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
@@ -425,7 +465,7 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 #define NVMET_DEFAULT_ANA_GRPID	1
 
 #define NVMET_KAS		10
-#define NVMET_DISC_KATO		120
+#define NVMET_DISC_KATO_MS		120000
 
 int __init nvmet_init_configfs(void);
 void __exit nvmet_exit_configfs(void);
@@ -434,15 +474,13 @@ int __init nvmet_init_discovery(void);
 void nvmet_exit_discovery(void);
 
 extern struct nvmet_subsys *nvmet_disc_subsys;
-extern u64 nvmet_genctr;
 extern struct rw_semaphore nvmet_config_sem;
 
 extern u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
 extern u64 nvmet_ana_chgcnt;
 extern struct rw_semaphore nvmet_ana_sem;
 
-bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
-		const char *hostnqn);
+bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn);
 
 int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
 int nvmet_file_ns_enable(struct nvmet_ns *ns);
@@ -457,4 +495,6 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req)
 	return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
 			req->ns->blksize_shift;
 }
+
+u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
 #endif /* _NVMET_H */
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 3f7971d3706d..a8d23eb80192 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -196,7 +196,7 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 {
 	unsigned long flags;
 
-	if (rsp->allocated) {
+	if (unlikely(rsp->allocated)) {
 		kfree(rsp);
 		return;
 	}
@@ -529,6 +529,7 @@ static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct nvmet_rdma_rsp *rsp =
 		container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe);
+	struct nvmet_rdma_queue *queue = cq->cq_context;
 
 	nvmet_rdma_release_rsp(rsp);
 
@@ -536,7 +537,7 @@ static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 		     wc->status != IB_WC_WR_FLUSH_ERR)) {
 		pr_err("SEND for CQE 0x%p failed with status %s (%d).\n",
 			wc->wr_cqe, ib_wc_status_msg(wc->status), wc->status);
-		nvmet_rdma_error_comp(rsp->queue);
+		nvmet_rdma_error_comp(queue);
 	}
 }
 
@@ -629,8 +630,11 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 	u64 off = le64_to_cpu(sgl->addr);
 	u32 len = le32_to_cpu(sgl->length);
 
-	if (!nvme_is_write(rsp->req.cmd))
+	if (!nvme_is_write(rsp->req.cmd)) {
+		rsp->req.error_loc =
+			offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
 
 	if (off + len > rsp->queue->dev->inline_data_size) {
 		pr_err("invalid inline data offset!\n");
@@ -695,6 +699,8 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
 			return nvmet_rdma_map_sgl_inline(rsp);
 		default:
 			pr_err("invalid SGL subtype: %#x\n", sgl->type);
+			rsp->req.error_loc =
+				offsetof(struct nvme_common_command, dptr);
 			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		}
 	case NVME_KEY_SGL_FMT_DATA_DESC:
@@ -705,10 +711,13 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
 			return nvmet_rdma_map_sgl_keyed(rsp, sgl, false);
 		default:
 			pr_err("invalid SGL subtype: %#x\n", sgl->type);
+			rsp->req.error_loc =
+				offsetof(struct nvme_common_command, dptr);
 			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		}
 	default:
 		pr_err("invalid SGL type: %#x\n", sgl->type);
+		rsp->req.error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
 	}
 }
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
new file mode 100644
index 000000000000..44b37b202e39
--- /dev/null
+++ b/drivers/nvme/target/tcp.c
@@ -0,0 +1,1737 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe over Fabrics TCP target.
+ * Copyright (c) 2018 Lightbits Labs. All rights reserved.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/nvme-tcp.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <linux/inet.h>
+#include <linux/llist.h>
+#include <crypto/hash.h>
+
+#include "nvmet.h"
+
+#define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
+
+#define NVMET_TCP_RECV_BUDGET		8
+#define NVMET_TCP_SEND_BUDGET		8
+#define NVMET_TCP_IO_WORK_BUDGET	64
+
+enum nvmet_tcp_send_state {
+	NVMET_TCP_SEND_DATA_PDU,
+	NVMET_TCP_SEND_DATA,
+	NVMET_TCP_SEND_R2T,
+	NVMET_TCP_SEND_DDGST,
+	NVMET_TCP_SEND_RESPONSE
+};
+
+enum nvmet_tcp_recv_state {
+	NVMET_TCP_RECV_PDU,
+	NVMET_TCP_RECV_DATA,
+	NVMET_TCP_RECV_DDGST,
+	NVMET_TCP_RECV_ERR,
+};
+
+enum {
+	NVMET_TCP_F_INIT_FAILED = (1 << 0),
+};
+
+struct nvmet_tcp_cmd {
+	struct nvmet_tcp_queue		*queue;
+	struct nvmet_req		req;
+
+	struct nvme_tcp_cmd_pdu		*cmd_pdu;
+	struct nvme_tcp_rsp_pdu		*rsp_pdu;
+	struct nvme_tcp_data_pdu	*data_pdu;
+	struct nvme_tcp_r2t_pdu		*r2t_pdu;
+
+	u32				rbytes_done;
+	u32				wbytes_done;
+
+	u32				pdu_len;
+	u32				pdu_recv;
+	int				sg_idx;
+	int				nr_mapped;
+	struct msghdr			recv_msg;
+	struct kvec			*iov;
+	u32				flags;
+
+	struct list_head		entry;
+	struct llist_node		lentry;
+
+	/* send state */
+	u32				offset;
+	struct scatterlist		*cur_sg;
+	enum nvmet_tcp_send_state	state;
+
+	__le32				exp_ddgst;
+	__le32				recv_ddgst;
+};
+
+enum nvmet_tcp_queue_state {
+	NVMET_TCP_Q_CONNECTING,
+	NVMET_TCP_Q_LIVE,
+	NVMET_TCP_Q_DISCONNECTING,
+};
+
+struct nvmet_tcp_queue {
+	struct socket		*sock;
+	struct nvmet_tcp_port	*port;
+	struct work_struct	io_work;
+	int			cpu;
+	struct nvmet_cq		nvme_cq;
+	struct nvmet_sq		nvme_sq;
+
+	/* send state */
+	struct nvmet_tcp_cmd	*cmds;
+	unsigned int		nr_cmds;
+	struct list_head	free_list;
+	struct llist_head	resp_list;
+	struct list_head	resp_send_list;
+	int			send_list_len;
+	struct nvmet_tcp_cmd	*snd_cmd;
+
+	/* recv state */
+	int			offset;
+	int			left;
+	enum nvmet_tcp_recv_state rcv_state;
+	struct nvmet_tcp_cmd	*cmd;
+	union nvme_tcp_pdu	pdu;
+
+	/* digest state */
+	bool			hdr_digest;
+	bool			data_digest;
+	struct ahash_request	*snd_hash;
+	struct ahash_request	*rcv_hash;
+
+	spinlock_t		state_lock;
+	enum nvmet_tcp_queue_state state;
+
+	struct sockaddr_storage	sockaddr;
+	struct sockaddr_storage	sockaddr_peer;
+	struct work_struct	release_work;
+
+	int			idx;
+	struct list_head	queue_list;
+
+	struct nvmet_tcp_cmd	connect;
+
+	struct page_frag_cache	pf_cache;
+
+	void (*data_ready)(struct sock *);
+	void (*state_change)(struct sock *);
+	void (*write_space)(struct sock *);
+};
+
+struct nvmet_tcp_port {
+	struct socket		*sock;
+	struct work_struct	accept_work;
+	struct nvmet_port	*nport;
+	struct sockaddr_storage addr;
+	int			last_cpu;
+	void (*data_ready)(struct sock *);
+};
+
+static DEFINE_IDA(nvmet_tcp_queue_ida);
+static LIST_HEAD(nvmet_tcp_queue_list);
+static DEFINE_MUTEX(nvmet_tcp_queue_mutex);
+
+static struct workqueue_struct *nvmet_tcp_wq;
+static struct nvmet_fabrics_ops nvmet_tcp_ops;
+static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c);
+static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd);
+
+static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue,
+		struct nvmet_tcp_cmd *cmd)
+{
+	return cmd - queue->cmds;
+}
+
+static inline bool nvmet_tcp_has_data_in(struct nvmet_tcp_cmd *cmd)
+{
+	return nvme_is_write(cmd->req.cmd) &&
+		cmd->rbytes_done < cmd->req.transfer_len;
+}
+
+static inline bool nvmet_tcp_need_data_in(struct nvmet_tcp_cmd *cmd)
+{
+	return nvmet_tcp_has_data_in(cmd) && !cmd->req.rsp->status;
+}
+
+static inline bool nvmet_tcp_need_data_out(struct nvmet_tcp_cmd *cmd)
+{
+	return !nvme_is_write(cmd->req.cmd) &&
+		cmd->req.transfer_len > 0 &&
+		!cmd->req.rsp->status;
+}
+
+static inline bool nvmet_tcp_has_inline_data(struct nvmet_tcp_cmd *cmd)
+{
+	return nvme_is_write(cmd->req.cmd) && cmd->pdu_len &&
+		!cmd->rbytes_done;
+}
+
+static inline struct nvmet_tcp_cmd *
+nvmet_tcp_get_cmd(struct nvmet_tcp_queue *queue)
+{
+	struct nvmet_tcp_cmd *cmd;
+
+	cmd = list_first_entry_or_null(&queue->free_list,
+				struct nvmet_tcp_cmd, entry);
+	if (!cmd)
+		return NULL;
+	list_del_init(&cmd->entry);
+
+	cmd->rbytes_done = cmd->wbytes_done = 0;
+	cmd->pdu_len = 0;
+	cmd->pdu_recv = 0;
+	cmd->iov = NULL;
+	cmd->flags = 0;
+	return cmd;
+}
+
+static inline void nvmet_tcp_put_cmd(struct nvmet_tcp_cmd *cmd)
+{
+	if (unlikely(cmd == &cmd->queue->connect))
+		return;
+
+	list_add_tail(&cmd->entry, &cmd->queue->free_list);
+}
+
+static inline u8 nvmet_tcp_hdgst_len(struct nvmet_tcp_queue *queue)
+{
+	return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0;
+}
+
+static inline u8 nvmet_tcp_ddgst_len(struct nvmet_tcp_queue *queue)
+{
+	return queue->data_digest ? NVME_TCP_DIGEST_LENGTH : 0;
+}
+
+static inline void nvmet_tcp_hdgst(struct ahash_request *hash,
+		void *pdu, size_t len)
+{
+	struct scatterlist sg;
+
+	sg_init_one(&sg, pdu, len);
+	ahash_request_set_crypt(hash, &sg, pdu + len, len);
+	crypto_ahash_digest(hash);
+}
+
+static int nvmet_tcp_verify_hdgst(struct nvmet_tcp_queue *queue,
+	void *pdu, size_t len)
+{
+	struct nvme_tcp_hdr *hdr = pdu;
+	__le32 recv_digest;
+	__le32 exp_digest;
+
+	if (unlikely(!(hdr->flags & NVME_TCP_F_HDGST))) {
+		pr_err("queue %d: header digest enabled but no header digest\n",
+			queue->idx);
+		return -EPROTO;
+	}
+
+	recv_digest = *(__le32 *)(pdu + hdr->hlen);
+	nvmet_tcp_hdgst(queue->rcv_hash, pdu, len);
+	exp_digest = *(__le32 *)(pdu + hdr->hlen);
+	if (recv_digest != exp_digest) {
+		pr_err("queue %d: header digest error: recv %#x expected %#x\n",
+			queue->idx, le32_to_cpu(recv_digest),
+			le32_to_cpu(exp_digest));
+		return -EPROTO;
+	}
+
+	return 0;
+}
+
+static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu)
+{
+	struct nvme_tcp_hdr *hdr = pdu;
+	u8 digest_len = nvmet_tcp_hdgst_len(queue);
+	u32 len;
+
+	len = le32_to_cpu(hdr->plen) - hdr->hlen -
+		(hdr->flags & NVME_TCP_F_HDGST ? digest_len : 0);
+
+	if (unlikely(len && !(hdr->flags & NVME_TCP_F_DDGST))) {
+		pr_err("queue %d: data digest flag is cleared\n", queue->idx);
+		return -EPROTO;
+	}
+
+	return 0;
+}
+
+static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd)
+{
+	struct scatterlist *sg;
+	int i;
+
+	sg = &cmd->req.sg[cmd->sg_idx];
+
+	for (i = 0; i < cmd->nr_mapped; i++)
+		kunmap(sg_page(&sg[i]));
+}
+
+static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd)
+{
+	struct kvec *iov = cmd->iov;
+	struct scatterlist *sg;
+	u32 length, offset, sg_offset;
+
+	length = cmd->pdu_len;
+	cmd->nr_mapped = DIV_ROUND_UP(length, PAGE_SIZE);
+	offset = cmd->rbytes_done;
+	cmd->sg_idx = DIV_ROUND_UP(offset, PAGE_SIZE);
+	sg_offset = offset % PAGE_SIZE;
+	sg = &cmd->req.sg[cmd->sg_idx];
+
+	while (length) {
+		u32 iov_len = min_t(u32, length, sg->length - sg_offset);
+
+		iov->iov_base = kmap(sg_page(sg)) + sg->offset + sg_offset;
+		iov->iov_len = iov_len;
+
+		length -= iov_len;
+		sg = sg_next(sg);
+		iov++;
+	}
+
+	iov_iter_kvec(&cmd->recv_msg.msg_iter, READ, cmd->iov,
+		cmd->nr_mapped, cmd->pdu_len);
+}
+
+static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue)
+{
+	queue->rcv_state = NVMET_TCP_RECV_ERR;
+	if (queue->nvme_sq.ctrl)
+		nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl);
+	else
+		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+}
+
+static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl;
+	u32 len = le32_to_cpu(sgl->length);
+
+	if (!cmd->req.data_len)
+		return 0;
+
+	if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) |
+			  NVME_SGL_FMT_OFFSET)) {
+		if (!nvme_is_write(cmd->req.cmd))
+			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+
+		if (len > cmd->req.port->inline_data_size)
+			return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
+		cmd->pdu_len = len;
+	}
+	cmd->req.transfer_len += len;
+
+	cmd->req.sg = sgl_alloc(len, GFP_KERNEL, &cmd->req.sg_cnt);
+	if (!cmd->req.sg)
+		return NVME_SC_INTERNAL;
+	cmd->cur_sg = cmd->req.sg;
+
+	if (nvmet_tcp_has_data_in(cmd)) {
+		cmd->iov = kmalloc_array(cmd->req.sg_cnt,
+				sizeof(*cmd->iov), GFP_KERNEL);
+		if (!cmd->iov)
+			goto err;
+	}
+
+	return 0;
+err:
+	sgl_free(cmd->req.sg);
+	return NVME_SC_INTERNAL;
+}
+
+static void nvmet_tcp_ddgst(struct ahash_request *hash,
+		struct nvmet_tcp_cmd *cmd)
+{
+	ahash_request_set_crypt(hash, cmd->req.sg,
+		(void *)&cmd->exp_ddgst, cmd->req.transfer_len);
+	crypto_ahash_digest(hash);
+}
+
+static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvme_tcp_data_pdu *pdu = cmd->data_pdu;
+	struct nvmet_tcp_queue *queue = cmd->queue;
+	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
+	u8 ddgst = nvmet_tcp_ddgst_len(cmd->queue);
+
+	cmd->offset = 0;
+	cmd->state = NVMET_TCP_SEND_DATA_PDU;
+
+	pdu->hdr.type = nvme_tcp_c2h_data;
+	pdu->hdr.flags = NVME_TCP_F_DATA_LAST;
+	pdu->hdr.hlen = sizeof(*pdu);
+	pdu->hdr.pdo = pdu->hdr.hlen + hdgst;
+	pdu->hdr.plen =
+		cpu_to_le32(pdu->hdr.hlen + hdgst +
+				cmd->req.transfer_len + ddgst);
+	pdu->command_id = cmd->req.rsp->command_id;
+	pdu->data_length = cpu_to_le32(cmd->req.transfer_len);
+	pdu->data_offset = cpu_to_le32(cmd->wbytes_done);
+
+	if (queue->data_digest) {
+		pdu->hdr.flags |= NVME_TCP_F_DDGST;
+		nvmet_tcp_ddgst(queue->snd_hash, cmd);
+	}
+
+	if (cmd->queue->hdr_digest) {
+		pdu->hdr.flags |= NVME_TCP_F_HDGST;
+		nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
+	}
+}
+
+static void nvmet_setup_r2t_pdu(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvme_tcp_r2t_pdu *pdu = cmd->r2t_pdu;
+	struct nvmet_tcp_queue *queue = cmd->queue;
+	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
+
+	cmd->offset = 0;
+	cmd->state = NVMET_TCP_SEND_R2T;
+
+	pdu->hdr.type = nvme_tcp_r2t;
+	pdu->hdr.flags = 0;
+	pdu->hdr.hlen = sizeof(*pdu);
+	pdu->hdr.pdo = 0;
+	pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst);
+
+	pdu->command_id = cmd->req.cmd->common.command_id;
+	pdu->ttag = nvmet_tcp_cmd_tag(cmd->queue, cmd);
+	pdu->r2t_length = cpu_to_le32(cmd->req.transfer_len - cmd->rbytes_done);
+	pdu->r2t_offset = cpu_to_le32(cmd->rbytes_done);
+	if (cmd->queue->hdr_digest) {
+		pdu->hdr.flags |= NVME_TCP_F_HDGST;
+		nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
+	}
+}
+
+static void nvmet_setup_response_pdu(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvme_tcp_rsp_pdu *pdu = cmd->rsp_pdu;
+	struct nvmet_tcp_queue *queue = cmd->queue;
+	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
+
+	cmd->offset = 0;
+	cmd->state = NVMET_TCP_SEND_RESPONSE;
+
+	pdu->hdr.type = nvme_tcp_rsp;
+	pdu->hdr.flags = 0;
+	pdu->hdr.hlen = sizeof(*pdu);
+	pdu->hdr.pdo = 0;
+	pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst);
+	if (cmd->queue->hdr_digest) {
+		pdu->hdr.flags |= NVME_TCP_F_HDGST;
+		nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
+	}
+}
+
+static void nvmet_tcp_process_resp_list(struct nvmet_tcp_queue *queue)
+{
+	struct llist_node *node;
+
+	node = llist_del_all(&queue->resp_list);
+	if (!node)
+		return;
+
+	while (node) {
+		struct nvmet_tcp_cmd *cmd = llist_entry(node,
+					struct nvmet_tcp_cmd, lentry);
+
+		list_add(&cmd->entry, &queue->resp_send_list);
+		node = node->next;
+		queue->send_list_len++;
+	}
+}
+
+static struct nvmet_tcp_cmd *nvmet_tcp_fetch_cmd(struct nvmet_tcp_queue *queue)
+{
+	queue->snd_cmd = list_first_entry_or_null(&queue->resp_send_list,
+				struct nvmet_tcp_cmd, entry);
+	if (!queue->snd_cmd) {
+		nvmet_tcp_process_resp_list(queue);
+		queue->snd_cmd =
+			list_first_entry_or_null(&queue->resp_send_list,
+					struct nvmet_tcp_cmd, entry);
+		if (unlikely(!queue->snd_cmd))
+			return NULL;
+	}
+
+	list_del_init(&queue->snd_cmd->entry);
+	queue->send_list_len--;
+
+	if (nvmet_tcp_need_data_out(queue->snd_cmd))
+		nvmet_setup_c2h_data_pdu(queue->snd_cmd);
+	else if (nvmet_tcp_need_data_in(queue->snd_cmd))
+		nvmet_setup_r2t_pdu(queue->snd_cmd);
+	else
+		nvmet_setup_response_pdu(queue->snd_cmd);
+
+	return queue->snd_cmd;
+}
+
+static void nvmet_tcp_queue_response(struct nvmet_req *req)
+{
+	struct nvmet_tcp_cmd *cmd =
+		container_of(req, struct nvmet_tcp_cmd, req);
+	struct nvmet_tcp_queue	*queue = cmd->queue;
+
+	llist_add(&cmd->lentry, &queue->resp_list);
+	queue_work_on(cmd->queue->cpu, nvmet_tcp_wq, &cmd->queue->io_work);
+}
+
+static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
+{
+	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
+	int left = sizeof(*cmd->data_pdu) - cmd->offset + hdgst;
+	int ret;
+
+	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->data_pdu),
+			offset_in_page(cmd->data_pdu) + cmd->offset,
+			left, MSG_DONTWAIT | MSG_MORE);
+	if (ret <= 0)
+		return ret;
+
+	cmd->offset += ret;
+	left -= ret;
+
+	if (left)
+		return -EAGAIN;
+
+	cmd->state = NVMET_TCP_SEND_DATA;
+	cmd->offset  = 0;
+	return 1;
+}
+
+static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvmet_tcp_queue *queue = cmd->queue;
+	int ret;
+
+	while (cmd->cur_sg) {
+		struct page *page = sg_page(cmd->cur_sg);
+		u32 left = cmd->cur_sg->length - cmd->offset;
+
+		ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
+					left, MSG_DONTWAIT | MSG_MORE);
+		if (ret <= 0)
+			return ret;
+
+		cmd->offset += ret;
+		cmd->wbytes_done += ret;
+
+		/* Done with sg?*/
+		if (cmd->offset == cmd->cur_sg->length) {
+			cmd->cur_sg = sg_next(cmd->cur_sg);
+			cmd->offset = 0;
+		}
+	}
+
+	if (queue->data_digest) {
+		cmd->state = NVMET_TCP_SEND_DDGST;
+		cmd->offset = 0;
+	} else {
+		nvmet_setup_response_pdu(cmd);
+	}
+	return 1;
+
+}
+
+static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
+		bool last_in_batch)
+{
+	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
+	int left = sizeof(*cmd->rsp_pdu) - cmd->offset + hdgst;
+	int flags = MSG_DONTWAIT;
+	int ret;
+
+	if (!last_in_batch && cmd->queue->send_list_len)
+		flags |= MSG_MORE;
+	else
+		flags |= MSG_EOR;
+
+	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->rsp_pdu),
+		offset_in_page(cmd->rsp_pdu) + cmd->offset, left, flags);
+	if (ret <= 0)
+		return ret;
+	cmd->offset += ret;
+	left -= ret;
+
+	if (left)
+		return -EAGAIN;
+
+	kfree(cmd->iov);
+	sgl_free(cmd->req.sg);
+	cmd->queue->snd_cmd = NULL;
+	nvmet_tcp_put_cmd(cmd);
+	return 1;
+}
+
+static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
+{
+	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
+	int left = sizeof(*cmd->r2t_pdu) - cmd->offset + hdgst;
+	int flags = MSG_DONTWAIT;
+	int ret;
+
+	if (!last_in_batch && cmd->queue->send_list_len)
+		flags |= MSG_MORE;
+	else
+		flags |= MSG_EOR;
+
+	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->r2t_pdu),
+		offset_in_page(cmd->r2t_pdu) + cmd->offset, left, flags);
+	if (ret <= 0)
+		return ret;
+	cmd->offset += ret;
+	left -= ret;
+
+	if (left)
+		return -EAGAIN;
+
+	cmd->queue->snd_cmd = NULL;
+	return 1;
+}
+
+static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvmet_tcp_queue *queue = cmd->queue;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
+	struct kvec iov = {
+		.iov_base = &cmd->exp_ddgst + cmd->offset,
+		.iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset
+	};
+	int ret;
+
+	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
+	if (unlikely(ret <= 0))
+		return ret;
+
+	cmd->offset += ret;
+	nvmet_setup_response_pdu(cmd);
+	return 1;
+}
+
+static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
+		bool last_in_batch)
+{
+	struct nvmet_tcp_cmd *cmd = queue->snd_cmd;
+	int ret = 0;
+
+	if (!cmd || queue->state == NVMET_TCP_Q_DISCONNECTING) {
+		cmd = nvmet_tcp_fetch_cmd(queue);
+		if (unlikely(!cmd))
+			return 0;
+	}
+
+	if (cmd->state == NVMET_TCP_SEND_DATA_PDU) {
+		ret = nvmet_try_send_data_pdu(cmd);
+		if (ret <= 0)
+			goto done_send;
+	}
+
+	if (cmd->state == NVMET_TCP_SEND_DATA) {
+		ret = nvmet_try_send_data(cmd);
+		if (ret <= 0)
+			goto done_send;
+	}
+
+	if (cmd->state == NVMET_TCP_SEND_DDGST) {
+		ret = nvmet_try_send_ddgst(cmd);
+		if (ret <= 0)
+			goto done_send;
+	}
+
+	if (cmd->state == NVMET_TCP_SEND_R2T) {
+		ret = nvmet_try_send_r2t(cmd, last_in_batch);
+		if (ret <= 0)
+			goto done_send;
+	}
+
+	if (cmd->state == NVMET_TCP_SEND_RESPONSE)
+		ret = nvmet_try_send_response(cmd, last_in_batch);
+
+done_send:
+	if (ret < 0) {
+		if (ret == -EAGAIN)
+			return 0;
+		return ret;
+	}
+
+	return 1;
+}
+
+static int nvmet_tcp_try_send(struct nvmet_tcp_queue *queue,
+		int budget, int *sends)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < budget; i++) {
+		ret = nvmet_tcp_try_send_one(queue, i == budget - 1);
+		if (ret <= 0)
+			break;
+		(*sends)++;
+	}
+
+	return ret;
+}
+
+static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
+{
+	queue->offset = 0;
+	queue->left = sizeof(struct nvme_tcp_hdr);
+	queue->cmd = NULL;
+	queue->rcv_state = NVMET_TCP_RECV_PDU;
+}
+
+static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash);
+
+	ahash_request_free(queue->rcv_hash);
+	ahash_request_free(queue->snd_hash);
+	crypto_free_ahash(tfm);
+}
+
+static int nvmet_tcp_alloc_crypto(struct nvmet_tcp_queue *queue)
+{
+	struct crypto_ahash *tfm;
+
+	tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!queue->snd_hash)
+		goto free_tfm;
+	ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL);
+
+	queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!queue->rcv_hash)
+		goto free_snd_hash;
+	ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL);
+
+	return 0;
+free_snd_hash:
+	ahash_request_free(queue->snd_hash);
+free_tfm:
+	crypto_free_ahash(tfm);
+	return -ENOMEM;
+}
+
+
+static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
+{
+	struct nvme_tcp_icreq_pdu *icreq = &queue->pdu.icreq;
+	struct nvme_tcp_icresp_pdu *icresp = &queue->pdu.icresp;
+	struct msghdr msg = {};
+	struct kvec iov;
+	int ret;
+
+	if (le32_to_cpu(icreq->hdr.plen) != sizeof(struct nvme_tcp_icreq_pdu)) {
+		pr_err("bad nvme-tcp pdu length (%d)\n",
+			le32_to_cpu(icreq->hdr.plen));
+		nvmet_tcp_fatal_error(queue);
+	}
+
+	if (icreq->pfv != NVME_TCP_PFV_1_0) {
+		pr_err("queue %d: bad pfv %d\n", queue->idx, icreq->pfv);
+		return -EPROTO;
+	}
+
+	if (icreq->hpda != 0) {
+		pr_err("queue %d: unsupported hpda %d\n", queue->idx,
+			icreq->hpda);
+		return -EPROTO;
+	}
+
+	if (icreq->maxr2t != 0) {
+		pr_err("queue %d: unsupported maxr2t %d\n", queue->idx,
+			le32_to_cpu(icreq->maxr2t) + 1);
+		return -EPROTO;
+	}
+
+	queue->hdr_digest = !!(icreq->digest & NVME_TCP_HDR_DIGEST_ENABLE);
+	queue->data_digest = !!(icreq->digest & NVME_TCP_DATA_DIGEST_ENABLE);
+	if (queue->hdr_digest || queue->data_digest) {
+		ret = nvmet_tcp_alloc_crypto(queue);
+		if (ret)
+			return ret;
+	}
+
+	memset(icresp, 0, sizeof(*icresp));
+	icresp->hdr.type = nvme_tcp_icresp;
+	icresp->hdr.hlen = sizeof(*icresp);
+	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->cpda = 0;
+	if (queue->hdr_digest)
+		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
+	if (queue->data_digest)
+		icresp->digest |= NVME_TCP_DATA_DIGEST_ENABLE;
+
+	iov.iov_base = icresp;
+	iov.iov_len = sizeof(*icresp);
+	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
+	if (ret < 0)
+		goto free_crypto;
+
+	queue->state = NVMET_TCP_Q_LIVE;
+	nvmet_prepare_receive_pdu(queue);
+	return 0;
+free_crypto:
+	if (queue->hdr_digest || queue->data_digest)
+		nvmet_tcp_free_crypto(queue);
+	return ret;
+}
+
+static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
+		struct nvmet_tcp_cmd *cmd, struct nvmet_req *req)
+{
+	int ret;
+
+	/* recover the expected data transfer length */
+	req->data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
+
+	if (!nvme_is_write(cmd->req.cmd) ||
+	    req->data_len > cmd->req.port->inline_data_size) {
+		nvmet_prepare_receive_pdu(queue);
+		return;
+	}
+
+	ret = nvmet_tcp_map_data(cmd);
+	if (unlikely(ret)) {
+		pr_err("queue %d: failed to map data\n", queue->idx);
+		nvmet_tcp_fatal_error(queue);
+		return;
+	}
+
+	queue->rcv_state = NVMET_TCP_RECV_DATA;
+	nvmet_tcp_map_pdu_iovec(cmd);
+	cmd->flags |= NVMET_TCP_F_INIT_FAILED;
+}
+
+static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
+{
+	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
+	struct nvmet_tcp_cmd *cmd;
+
+	cmd = &queue->cmds[data->ttag];
+
+	if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) {
+		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
+			data->ttag, le32_to_cpu(data->data_offset),
+			cmd->rbytes_done);
+		/* FIXME: use path and transport errors */
+		nvmet_req_complete(&cmd->req,
+			NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+		return -EPROTO;
+	}
+
+	cmd->pdu_len = le32_to_cpu(data->data_length);
+	cmd->pdu_recv = 0;
+	nvmet_tcp_map_pdu_iovec(cmd);
+	queue->cmd = cmd;
+	queue->rcv_state = NVMET_TCP_RECV_DATA;
+
+	return 0;
+}
+
+static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue)
+{
+	struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
+	struct nvme_command *nvme_cmd = &queue->pdu.cmd.cmd;
+	struct nvmet_req *req;
+	int ret;
+
+	if (unlikely(queue->state == NVMET_TCP_Q_CONNECTING)) {
+		if (hdr->type != nvme_tcp_icreq) {
+			pr_err("unexpected pdu type (%d) before icreq\n",
+				hdr->type);
+			nvmet_tcp_fatal_error(queue);
+			return -EPROTO;
+		}
+		return nvmet_tcp_handle_icreq(queue);
+	}
+
+	if (hdr->type == nvme_tcp_h2c_data) {
+		ret = nvmet_tcp_handle_h2c_data_pdu(queue);
+		if (unlikely(ret))
+			return ret;
+		return 0;
+	}
+
+	queue->cmd = nvmet_tcp_get_cmd(queue);
+	if (unlikely(!queue->cmd)) {
+		/* This should never happen */
+		pr_err("queue %d: out of commands (%d) send_list_len: %d, opcode: %d",
+			queue->idx, queue->nr_cmds, queue->send_list_len,
+			nvme_cmd->common.opcode);
+		nvmet_tcp_fatal_error(queue);
+		return -ENOMEM;
+	}
+
+	req = &queue->cmd->req;
+	memcpy(req->cmd, nvme_cmd, sizeof(*nvme_cmd));
+
+	if (unlikely(!nvmet_req_init(req, &queue->nvme_cq,
+			&queue->nvme_sq, &nvmet_tcp_ops))) {
+		pr_err("failed cmd %p id %d opcode %d, data_len: %d\n",
+			req->cmd, req->cmd->common.command_id,
+			req->cmd->common.opcode,
+			le32_to_cpu(req->cmd->common.dptr.sgl.length));
+
+		nvmet_tcp_handle_req_failure(queue, queue->cmd, req);
+		return -EAGAIN;
+	}
+
+	ret = nvmet_tcp_map_data(queue->cmd);
+	if (unlikely(ret)) {
+		pr_err("queue %d: failed to map data\n", queue->idx);
+		if (nvmet_tcp_has_inline_data(queue->cmd))
+			nvmet_tcp_fatal_error(queue);
+		else
+			nvmet_req_complete(req, ret);
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	if (nvmet_tcp_need_data_in(queue->cmd)) {
+		if (nvmet_tcp_has_inline_data(queue->cmd)) {
+			queue->rcv_state = NVMET_TCP_RECV_DATA;
+			nvmet_tcp_map_pdu_iovec(queue->cmd);
+			return 0;
+		}
+		/* send back R2T */
+		nvmet_tcp_queue_response(&queue->cmd->req);
+		goto out;
+	}
+
+	nvmet_req_execute(&queue->cmd->req);
+out:
+	nvmet_prepare_receive_pdu(queue);
+	return ret;
+}
+
+static const u8 nvme_tcp_pdu_sizes[] = {
+	[nvme_tcp_icreq]	= sizeof(struct nvme_tcp_icreq_pdu),
+	[nvme_tcp_cmd]		= sizeof(struct nvme_tcp_cmd_pdu),
+	[nvme_tcp_h2c_data]	= sizeof(struct nvme_tcp_data_pdu),
+};
+
+static inline u8 nvmet_tcp_pdu_size(u8 type)
+{
+	size_t idx = type;
+
+	return (idx < ARRAY_SIZE(nvme_tcp_pdu_sizes) &&
+		nvme_tcp_pdu_sizes[idx]) ?
+			nvme_tcp_pdu_sizes[idx] : 0;
+}
+
+static inline bool nvmet_tcp_pdu_valid(u8 type)
+{
+	switch (type) {
+	case nvme_tcp_icreq:
+	case nvme_tcp_cmd:
+	case nvme_tcp_h2c_data:
+		/* fallthru */
+		return true;
+	}
+
+	return false;
+}
+
+static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue)
+{
+	struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
+	int len;
+	struct kvec iov;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
+
+recv:
+	iov.iov_base = (void *)&queue->pdu + queue->offset;
+	iov.iov_len = queue->left;
+	len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
+			iov.iov_len, msg.msg_flags);
+	if (unlikely(len < 0))
+		return len;
+
+	queue->offset += len;
+	queue->left -= len;
+	if (queue->left)
+		return -EAGAIN;
+
+	if (queue->offset == sizeof(struct nvme_tcp_hdr)) {
+		u8 hdgst = nvmet_tcp_hdgst_len(queue);
+
+		if (unlikely(!nvmet_tcp_pdu_valid(hdr->type))) {
+			pr_err("unexpected pdu type %d\n", hdr->type);
+			nvmet_tcp_fatal_error(queue);
+			return -EIO;
+		}
+
+		if (unlikely(hdr->hlen != nvmet_tcp_pdu_size(hdr->type))) {
+			pr_err("pdu %d bad hlen %d\n", hdr->type, hdr->hlen);
+			return -EIO;
+		}
+
+		queue->left = hdr->hlen - queue->offset + hdgst;
+		goto recv;
+	}
+
+	if (queue->hdr_digest &&
+	    nvmet_tcp_verify_hdgst(queue, &queue->pdu, queue->offset)) {
+		nvmet_tcp_fatal_error(queue); /* fatal */
+		return -EPROTO;
+	}
+
+	if (queue->data_digest &&
+	    nvmet_tcp_check_ddgst(queue, &queue->pdu)) {
+		nvmet_tcp_fatal_error(queue); /* fatal */
+		return -EPROTO;
+	}
+
+	return nvmet_tcp_done_recv_pdu(queue);
+}
+
+static void nvmet_tcp_prep_recv_ddgst(struct nvmet_tcp_cmd *cmd)
+{
+	struct nvmet_tcp_queue *queue = cmd->queue;
+
+	nvmet_tcp_ddgst(queue->rcv_hash, cmd);
+	queue->offset = 0;
+	queue->left = NVME_TCP_DIGEST_LENGTH;
+	queue->rcv_state = NVMET_TCP_RECV_DDGST;
+}
+
+static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
+{
+	struct nvmet_tcp_cmd  *cmd = queue->cmd;
+	int ret;
+
+	while (msg_data_left(&cmd->recv_msg)) {
+		ret = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg,
+			cmd->recv_msg.msg_flags);
+		if (ret <= 0)
+			return ret;
+
+		cmd->pdu_recv += ret;
+		cmd->rbytes_done += ret;
+	}
+
+	nvmet_tcp_unmap_pdu_iovec(cmd);
+
+	if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) &&
+	    cmd->rbytes_done == cmd->req.transfer_len) {
+		if (queue->data_digest) {
+			nvmet_tcp_prep_recv_ddgst(cmd);
+			return 0;
+		}
+		nvmet_req_execute(&cmd->req);
+	}
+
+	nvmet_prepare_receive_pdu(queue);
+	return 0;
+}
+
+static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue)
+{
+	struct nvmet_tcp_cmd *cmd = queue->cmd;
+	int ret;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
+	struct kvec iov = {
+		.iov_base = (void *)&cmd->recv_ddgst + queue->offset,
+		.iov_len = queue->left
+	};
+
+	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
+			iov.iov_len, msg.msg_flags);
+	if (unlikely(ret < 0))
+		return ret;
+
+	queue->offset += ret;
+	queue->left -= ret;
+	if (queue->left)
+		return -EAGAIN;
+
+	if (queue->data_digest && cmd->exp_ddgst != cmd->recv_ddgst) {
+		pr_err("queue %d: cmd %d pdu (%d) data digest error: recv %#x expected %#x\n",
+			queue->idx, cmd->req.cmd->common.command_id,
+			queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst),
+			le32_to_cpu(cmd->exp_ddgst));
+		nvmet_tcp_finish_cmd(cmd);
+		nvmet_tcp_fatal_error(queue);
+		ret = -EPROTO;
+		goto out;
+	}
+
+	if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) &&
+	    cmd->rbytes_done == cmd->req.transfer_len)
+		nvmet_req_execute(&cmd->req);
+	ret = 0;
+out:
+	nvmet_prepare_receive_pdu(queue);
+	return ret;
+}
+
+static int nvmet_tcp_try_recv_one(struct nvmet_tcp_queue *queue)
+{
+	int result;
+
+	if (unlikely(queue->rcv_state == NVMET_TCP_RECV_ERR))
+		return 0;
+
+	if (queue->rcv_state == NVMET_TCP_RECV_PDU) {
+		result = nvmet_tcp_try_recv_pdu(queue);
+		if (result != 0)
+			goto done_recv;
+	}
+
+	if (queue->rcv_state == NVMET_TCP_RECV_DATA) {
+		result = nvmet_tcp_try_recv_data(queue);
+		if (result != 0)
+			goto done_recv;
+	}
+
+	if (queue->rcv_state == NVMET_TCP_RECV_DDGST) {
+		result = nvmet_tcp_try_recv_ddgst(queue);
+		if (result != 0)
+			goto done_recv;
+	}
+
+done_recv:
+	if (result < 0) {
+		if (result == -EAGAIN)
+			return 0;
+		return result;
+	}
+	return 1;
+}
+
+static int nvmet_tcp_try_recv(struct nvmet_tcp_queue *queue,
+		int budget, int *recvs)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < budget; i++) {
+		ret = nvmet_tcp_try_recv_one(queue);
+		if (ret <= 0)
+			break;
+		(*recvs)++;
+	}
+
+	return ret;
+}
+
+static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue)
+{
+	spin_lock(&queue->state_lock);
+	if (queue->state != NVMET_TCP_Q_DISCONNECTING) {
+		queue->state = NVMET_TCP_Q_DISCONNECTING;
+		schedule_work(&queue->release_work);
+	}
+	spin_unlock(&queue->state_lock);
+}
+
+static void nvmet_tcp_io_work(struct work_struct *w)
+{
+	struct nvmet_tcp_queue *queue =
+		container_of(w, struct nvmet_tcp_queue, io_work);
+	bool pending;
+	int ret, ops = 0;
+
+	do {
+		pending = false;
+
+		ret = nvmet_tcp_try_recv(queue, NVMET_TCP_RECV_BUDGET, &ops);
+		if (ret > 0) {
+			pending = true;
+		} else if (ret < 0) {
+			if (ret == -EPIPE || ret == -ECONNRESET)
+				kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+			else
+				nvmet_tcp_fatal_error(queue);
+			return;
+		}
+
+		ret = nvmet_tcp_try_send(queue, NVMET_TCP_SEND_BUDGET, &ops);
+		if (ret > 0) {
+			/* transmitted message/data */
+			pending = true;
+		} else if (ret < 0) {
+			if (ret == -EPIPE || ret == -ECONNRESET)
+				kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+			else
+				nvmet_tcp_fatal_error(queue);
+			return;
+		}
+
+	} while (pending && ops < NVMET_TCP_IO_WORK_BUDGET);
+
+	/*
+	 * We exahusted our budget, requeue our selves
+	 */
+	if (pending)
+		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+}
+
+static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
+		struct nvmet_tcp_cmd *c)
+{
+	u8 hdgst = nvmet_tcp_hdgst_len(queue);
+
+	c->queue = queue;
+	c->req.port = queue->port->nport;
+
+	c->cmd_pdu = page_frag_alloc(&queue->pf_cache,
+			sizeof(*c->cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
+	if (!c->cmd_pdu)
+		return -ENOMEM;
+	c->req.cmd = &c->cmd_pdu->cmd;
+
+	c->rsp_pdu = page_frag_alloc(&queue->pf_cache,
+			sizeof(*c->rsp_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
+	if (!c->rsp_pdu)
+		goto out_free_cmd;
+	c->req.rsp = &c->rsp_pdu->cqe;
+
+	c->data_pdu = page_frag_alloc(&queue->pf_cache,
+			sizeof(*c->data_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
+	if (!c->data_pdu)
+		goto out_free_rsp;
+
+	c->r2t_pdu = page_frag_alloc(&queue->pf_cache,
+			sizeof(*c->r2t_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
+	if (!c->r2t_pdu)
+		goto out_free_data;
+
+	c->recv_msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
+
+	list_add_tail(&c->entry, &queue->free_list);
+
+	return 0;
+out_free_data:
+	page_frag_free(c->data_pdu);
+out_free_rsp:
+	page_frag_free(c->rsp_pdu);
+out_free_cmd:
+	page_frag_free(c->cmd_pdu);
+	return -ENOMEM;
+}
+
+static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c)
+{
+	page_frag_free(c->r2t_pdu);
+	page_frag_free(c->data_pdu);
+	page_frag_free(c->rsp_pdu);
+	page_frag_free(c->cmd_pdu);
+}
+
+static int nvmet_tcp_alloc_cmds(struct nvmet_tcp_queue *queue)
+{
+	struct nvmet_tcp_cmd *cmds;
+	int i, ret = -EINVAL, nr_cmds = queue->nr_cmds;
+
+	cmds = kcalloc(nr_cmds, sizeof(struct nvmet_tcp_cmd), GFP_KERNEL);
+	if (!cmds)
+		goto out;
+
+	for (i = 0; i < nr_cmds; i++) {
+		ret = nvmet_tcp_alloc_cmd(queue, cmds + i);
+		if (ret)
+			goto out_free;
+	}
+
+	queue->cmds = cmds;
+
+	return 0;
+out_free:
+	while (--i >= 0)
+		nvmet_tcp_free_cmd(cmds + i);
+	kfree(cmds);
+out:
+	return ret;
+}
+
+static void nvmet_tcp_free_cmds(struct nvmet_tcp_queue *queue)
+{
+	struct nvmet_tcp_cmd *cmds = queue->cmds;
+	int i;
+
+	for (i = 0; i < queue->nr_cmds; i++)
+		nvmet_tcp_free_cmd(cmds + i);
+
+	nvmet_tcp_free_cmd(&queue->connect);
+	kfree(cmds);
+}
+
+static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue)
+{
+	struct socket *sock = queue->sock;
+
+	write_lock_bh(&sock->sk->sk_callback_lock);
+	sock->sk->sk_data_ready =  queue->data_ready;
+	sock->sk->sk_state_change = queue->state_change;
+	sock->sk->sk_write_space = queue->write_space;
+	sock->sk->sk_user_data = NULL;
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+}
+
+static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
+{
+	nvmet_req_uninit(&cmd->req);
+	nvmet_tcp_unmap_pdu_iovec(cmd);
+	sgl_free(cmd->req.sg);
+}
+
+static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
+{
+	struct nvmet_tcp_cmd *cmd = queue->cmds;
+	int i;
+
+	for (i = 0; i < queue->nr_cmds; i++, cmd++) {
+		if (nvmet_tcp_need_data_in(cmd))
+			nvmet_tcp_finish_cmd(cmd);
+	}
+
+	if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) {
+		/* failed in connect */
+		nvmet_tcp_finish_cmd(&queue->connect);
+	}
+}
+
+static void nvmet_tcp_release_queue_work(struct work_struct *w)
+{
+	struct nvmet_tcp_queue *queue =
+		container_of(w, struct nvmet_tcp_queue, release_work);
+
+	mutex_lock(&nvmet_tcp_queue_mutex);
+	list_del_init(&queue->queue_list);
+	mutex_unlock(&nvmet_tcp_queue_mutex);
+
+	nvmet_tcp_restore_socket_callbacks(queue);
+	flush_work(&queue->io_work);
+
+	nvmet_tcp_uninit_data_in_cmds(queue);
+	nvmet_sq_destroy(&queue->nvme_sq);
+	cancel_work_sync(&queue->io_work);
+	sock_release(queue->sock);
+	nvmet_tcp_free_cmds(queue);
+	if (queue->hdr_digest || queue->data_digest)
+		nvmet_tcp_free_crypto(queue);
+	ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
+
+	kfree(queue);
+}
+
+static void nvmet_tcp_data_ready(struct sock *sk)
+{
+	struct nvmet_tcp_queue *queue;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	queue = sk->sk_user_data;
+	if (likely(queue))
+		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void nvmet_tcp_write_space(struct sock *sk)
+{
+	struct nvmet_tcp_queue *queue;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	queue = sk->sk_user_data;
+	if (unlikely(!queue))
+		goto out;
+
+	if (unlikely(queue->state == NVMET_TCP_Q_CONNECTING)) {
+		queue->write_space(sk);
+		goto out;
+	}
+
+	if (sk_stream_is_writeable(sk)) {
+		clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+	}
+out:
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void nvmet_tcp_state_change(struct sock *sk)
+{
+	struct nvmet_tcp_queue *queue;
+
+	write_lock_bh(&sk->sk_callback_lock);
+	queue = sk->sk_user_data;
+	if (!queue)
+		goto done;
+
+	switch (sk->sk_state) {
+	case TCP_FIN_WAIT1:
+	case TCP_CLOSE_WAIT:
+	case TCP_CLOSE:
+		/* FALLTHRU */
+		sk->sk_user_data = NULL;
+		nvmet_tcp_schedule_release_queue(queue);
+		break;
+	default:
+		pr_warn("queue %d unhandled state %d\n",
+			queue->idx, sk->sk_state);
+	}
+done:
+	write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
+{
+	struct socket *sock = queue->sock;
+	struct linger sol = { .l_onoff = 1, .l_linger = 0 };
+	int ret;
+
+	ret = kernel_getsockname(sock,
+		(struct sockaddr *)&queue->sockaddr);
+	if (ret < 0)
+		return ret;
+
+	ret = kernel_getpeername(sock,
+		(struct sockaddr *)&queue->sockaddr_peer);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Cleanup whatever is sitting in the TCP transmit queue on socket
+	 * close. This is done to prevent stale data from being sent should
+	 * the network connection be restored before TCP times out.
+	 */
+	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
+			(char *)&sol, sizeof(sol));
+	if (ret)
+		return ret;
+
+	write_lock_bh(&sock->sk->sk_callback_lock);
+	sock->sk->sk_user_data = queue;
+	queue->data_ready = sock->sk->sk_data_ready;
+	sock->sk->sk_data_ready = nvmet_tcp_data_ready;
+	queue->state_change = sock->sk->sk_state_change;
+	sock->sk->sk_state_change = nvmet_tcp_state_change;
+	queue->write_space = sock->sk->sk_write_space;
+	sock->sk->sk_write_space = nvmet_tcp_write_space;
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+
+	return 0;
+}
+
+static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
+		struct socket *newsock)
+{
+	struct nvmet_tcp_queue *queue;
+	int ret;
+
+	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+	if (!queue)
+		return -ENOMEM;
+
+	INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work);
+	INIT_WORK(&queue->io_work, nvmet_tcp_io_work);
+	queue->sock = newsock;
+	queue->port = port;
+	queue->nr_cmds = 0;
+	spin_lock_init(&queue->state_lock);
+	queue->state = NVMET_TCP_Q_CONNECTING;
+	INIT_LIST_HEAD(&queue->free_list);
+	init_llist_head(&queue->resp_list);
+	INIT_LIST_HEAD(&queue->resp_send_list);
+
+	queue->idx = ida_simple_get(&nvmet_tcp_queue_ida, 0, 0, GFP_KERNEL);
+	if (queue->idx < 0) {
+		ret = queue->idx;
+		goto out_free_queue;
+	}
+
+	ret = nvmet_tcp_alloc_cmd(queue, &queue->connect);
+	if (ret)
+		goto out_ida_remove;
+
+	ret = nvmet_sq_init(&queue->nvme_sq);
+	if (ret)
+		goto out_free_connect;
+
+	port->last_cpu = cpumask_next_wrap(port->last_cpu,
+				cpu_online_mask, -1, false);
+	queue->cpu = port->last_cpu;
+	nvmet_prepare_receive_pdu(queue);
+
+	mutex_lock(&nvmet_tcp_queue_mutex);
+	list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list);
+	mutex_unlock(&nvmet_tcp_queue_mutex);
+
+	ret = nvmet_tcp_set_queue_sock(queue);
+	if (ret)
+		goto out_destroy_sq;
+
+	queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+
+	return 0;
+out_destroy_sq:
+	mutex_lock(&nvmet_tcp_queue_mutex);
+	list_del_init(&queue->queue_list);
+	mutex_unlock(&nvmet_tcp_queue_mutex);
+	nvmet_sq_destroy(&queue->nvme_sq);
+out_free_connect:
+	nvmet_tcp_free_cmd(&queue->connect);
+out_ida_remove:
+	ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
+out_free_queue:
+	kfree(queue);
+	return ret;
+}
+
+static void nvmet_tcp_accept_work(struct work_struct *w)
+{
+	struct nvmet_tcp_port *port =
+		container_of(w, struct nvmet_tcp_port, accept_work);
+	struct socket *newsock;
+	int ret;
+
+	while (true) {
+		ret = kernel_accept(port->sock, &newsock, O_NONBLOCK);
+		if (ret < 0) {
+			if (ret != -EAGAIN)
+				pr_warn("failed to accept err=%d\n", ret);
+			return;
+		}
+		ret = nvmet_tcp_alloc_queue(port, newsock);
+		if (ret) {
+			pr_err("failed to allocate queue\n");
+			sock_release(newsock);
+		}
+	}
+}
+
+static void nvmet_tcp_listen_data_ready(struct sock *sk)
+{
+	struct nvmet_tcp_port *port;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	port = sk->sk_user_data;
+	if (!port)
+		goto out;
+
+	if (sk->sk_state == TCP_LISTEN)
+		schedule_work(&port->accept_work);
+out:
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int nvmet_tcp_add_port(struct nvmet_port *nport)
+{
+	struct nvmet_tcp_port *port;
+	__kernel_sa_family_t af;
+	int opt, ret;
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+
+	switch (nport->disc_addr.adrfam) {
+	case NVMF_ADDR_FAMILY_IP4:
+		af = AF_INET;
+		break;
+	case NVMF_ADDR_FAMILY_IP6:
+		af = AF_INET6;
+		break;
+	default:
+		pr_err("address family %d not supported\n",
+				nport->disc_addr.adrfam);
+		ret = -EINVAL;
+		goto err_port;
+	}
+
+	ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
+			nport->disc_addr.trsvcid, &port->addr);
+	if (ret) {
+		pr_err("malformed ip/port passed: %s:%s\n",
+			nport->disc_addr.traddr, nport->disc_addr.trsvcid);
+		goto err_port;
+	}
+
+	port->nport = nport;
+	port->last_cpu = -1;
+	INIT_WORK(&port->accept_work, nvmet_tcp_accept_work);
+	if (port->nport->inline_data_size < 0)
+		port->nport->inline_data_size = NVMET_TCP_DEF_INLINE_DATA_SIZE;
+
+	ret = sock_create(port->addr.ss_family, SOCK_STREAM,
+				IPPROTO_TCP, &port->sock);
+	if (ret) {
+		pr_err("failed to create a socket\n");
+		goto err_port;
+	}
+
+	port->sock->sk->sk_user_data = port;
+	port->data_ready = port->sock->sk->sk_data_ready;
+	port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready;
+
+	opt = 1;
+	ret = kernel_setsockopt(port->sock, IPPROTO_TCP,
+			TCP_NODELAY, (char *)&opt, sizeof(opt));
+	if (ret) {
+		pr_err("failed to set TCP_NODELAY sock opt %d\n", ret);
+		goto err_sock;
+	}
+
+	ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_REUSEADDR,
+			(char *)&opt, sizeof(opt));
+	if (ret) {
+		pr_err("failed to set SO_REUSEADDR sock opt %d\n", ret);
+		goto err_sock;
+	}
+
+	ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
+			sizeof(port->addr));
+	if (ret) {
+		pr_err("failed to bind port socket %d\n", ret);
+		goto err_sock;
+	}
+
+	ret = kernel_listen(port->sock, 128);
+	if (ret) {
+		pr_err("failed to listen %d on port sock\n", ret);
+		goto err_sock;
+	}
+
+	nport->priv = port;
+	pr_info("enabling port %d (%pISpc)\n",
+		le16_to_cpu(nport->disc_addr.portid), &port->addr);
+
+	return 0;
+
+err_sock:
+	sock_release(port->sock);
+err_port:
+	kfree(port);
+	return ret;
+}
+
+static void nvmet_tcp_remove_port(struct nvmet_port *nport)
+{
+	struct nvmet_tcp_port *port = nport->priv;
+
+	write_lock_bh(&port->sock->sk->sk_callback_lock);
+	port->sock->sk->sk_data_ready = port->data_ready;
+	port->sock->sk->sk_user_data = NULL;
+	write_unlock_bh(&port->sock->sk->sk_callback_lock);
+	cancel_work_sync(&port->accept_work);
+
+	sock_release(port->sock);
+	kfree(port);
+}
+
+static void nvmet_tcp_delete_ctrl(struct nvmet_ctrl *ctrl)
+{
+	struct nvmet_tcp_queue *queue;
+
+	mutex_lock(&nvmet_tcp_queue_mutex);
+	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
+		if (queue->nvme_sq.ctrl == ctrl)
+			kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+	mutex_unlock(&nvmet_tcp_queue_mutex);
+}
+
+static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
+{
+	struct nvmet_tcp_queue *queue =
+		container_of(sq, struct nvmet_tcp_queue, nvme_sq);
+
+	if (sq->qid == 0) {
+		/* Let inflight controller teardown complete */
+		flush_scheduled_work();
+	}
+
+	queue->nr_cmds = sq->size * 2;
+	if (nvmet_tcp_alloc_cmds(queue))
+		return NVME_SC_INTERNAL;
+	return 0;
+}
+
+static void nvmet_tcp_disc_port_addr(struct nvmet_req *req,
+		struct nvmet_port *nport, char *traddr)
+{
+	struct nvmet_tcp_port *port = nport->priv;
+
+	if (inet_addr_is_any((struct sockaddr *)&port->addr)) {
+		struct nvmet_tcp_cmd *cmd =
+			container_of(req, struct nvmet_tcp_cmd, req);
+		struct nvmet_tcp_queue *queue = cmd->queue;
+
+		sprintf(traddr, "%pISc", (struct sockaddr *)&queue->sockaddr);
+	} else {
+		memcpy(traddr, nport->disc_addr.traddr, NVMF_TRADDR_SIZE);
+	}
+}
+
+static struct nvmet_fabrics_ops nvmet_tcp_ops = {
+	.owner			= THIS_MODULE,
+	.type			= NVMF_TRTYPE_TCP,
+	.msdbd			= 1,
+	.has_keyed_sgls		= 0,
+	.add_port		= nvmet_tcp_add_port,
+	.remove_port		= nvmet_tcp_remove_port,
+	.queue_response		= nvmet_tcp_queue_response,
+	.delete_ctrl		= nvmet_tcp_delete_ctrl,
+	.install_queue		= nvmet_tcp_install_queue,
+	.disc_traddr		= nvmet_tcp_disc_port_addr,
+};
+
+static int __init nvmet_tcp_init(void)
+{
+	int ret;
+
+	nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq", WQ_HIGHPRI, 0);
+	if (!nvmet_tcp_wq)
+		return -ENOMEM;
+
+	ret = nvmet_register_transport(&nvmet_tcp_ops);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	destroy_workqueue(nvmet_tcp_wq);
+	return ret;
+}
+
+static void __exit nvmet_tcp_exit(void)
+{
+	struct nvmet_tcp_queue *queue;
+
+	nvmet_unregister_transport(&nvmet_tcp_ops);
+
+	flush_scheduled_work();
+	mutex_lock(&nvmet_tcp_queue_mutex);
+	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
+		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+	mutex_unlock(&nvmet_tcp_queue_mutex);
+	flush_scheduled_work();
+
+	destroy_workqueue(nvmet_tcp_wq);
+}
+
+module_init(nvmet_tcp_init);
+module_exit(nvmet_tcp_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */