Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

16 files changed, 619 insertions, 457 deletions

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 596bb11eeb..c727cd1f26 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -797,6 +797,7 @@ static int apple_nvme_init_request(struct blk_mq_tag_set *set,
 
 static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 	bool dead = false, freeze = false;
 	unsigned long flags;
@@ -808,8 +809,8 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 	if (csts & NVME_CSTS_CFS)
 		dead = true;
 
-	if (anv->ctrl.state == NVME_CTRL_LIVE ||
-	    anv->ctrl.state == NVME_CTRL_RESETTING) {
+	if (state == NVME_CTRL_LIVE ||
+	    state == NVME_CTRL_RESETTING) {
 		freeze = true;
 		nvme_start_freeze(&anv->ctrl);
 	}
@@ -881,7 +882,7 @@ static enum blk_eh_timer_return apple_nvme_timeout(struct request *req)
 	unsigned long flags;
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 
-	if (anv->ctrl.state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(&anv->ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * From rdma.c:
 		 * If we are resetting, connecting or deleting we should
@@ -985,10 +986,10 @@ static void apple_nvme_reset_work(struct work_struct *work)
 	u32 boot_status, aqa;
 	struct apple_nvme *anv =
 		container_of(work, struct apple_nvme, ctrl.reset_work);
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 
-	if (anv->ctrl.state != NVME_CTRL_RESETTING) {
-		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n",
-			 anv->ctrl.state);
+	if (state != NVME_CTRL_RESETTING) {
+		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n", state);
 		ret = -ENODEV;
 		goto out;
 	}
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 72c0525c75..a264b3ae07 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -48,11 +48,6 @@ struct nvme_dhchap_queue_context {
 
 static struct workqueue_struct *nvme_auth_wq;
 
-#define nvme_auth_flags_from_qid(qid) \
-	(qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED
-#define nvme_auth_queue_from_qid(ctrl, qid) \
-	(qid == 0) ? (ctrl)->fabrics_q : (ctrl)->connect_q
-
 static inline int ctrl_max_dhchaps(struct nvme_ctrl *ctrl)
 {
 	return ctrl->opts->nr_io_queues + ctrl->opts->nr_write_queues +
@@ -63,10 +58,15 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 			    void *data, size_t data_len, bool auth_send)
 {
 	struct nvme_command cmd = {};
-	blk_mq_req_flags_t flags = nvme_auth_flags_from_qid(qid);
-	struct request_queue *q = nvme_auth_queue_from_qid(ctrl, qid);
+	nvme_submit_flags_t flags = NVME_SUBMIT_RETRY;
+	struct request_queue *q = ctrl->fabrics_q;
 	int ret;
 
+	if (qid != 0) {
+		flags |= NVME_SUBMIT_NOWAIT | NVME_SUBMIT_RESERVED;
+		q = ctrl->connect_q;
+	}
+
 	cmd.auth_common.opcode = nvme_fabrics_command;
 	cmd.auth_common.secp = NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER;
 	cmd.auth_common.spsp0 = 0x01;
@@ -80,8 +80,7 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 	}
 
 	ret = __nvme_submit_sync_cmd(q, &cmd, NULL, data, data_len,
-				     qid == 0 ? NVME_QID_ANY : qid,
-				     0, flags);
+				     qid == 0 ? NVME_QID_ANY : qid, flags);
 	if (ret > 0)
 		dev_warn(ctrl->device,
 			"qid %d auth_send failed with status %d\n", qid, ret);
@@ -897,7 +896,7 @@ static void nvme_ctrl_auth_work(struct work_struct *work)
 	 * If the ctrl is no connected, bail as reconnect will handle
 	 * authentication.
 	 */
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	/* Authenticate admin queue first */
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 20f46c2308..6f2ebb5fcd 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -171,15 +171,15 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command",
 };
 
-const unsigned char *nvme_get_error_status_str(u16 status)
+const char *nvme_get_error_status_str(u16 status)
 {
 	status &= 0x7ff;
 	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
-		return nvme_statuses[status & 0x7ff];
+		return nvme_statuses[status];
 	return "Unknown";
 }
 
-const unsigned char *nvme_get_opcode_str(u8 opcode)
+const char *nvme_get_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode])
 		return nvme_ops[opcode];
@@ -187,7 +187,7 @@ const unsigned char *nvme_get_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_opcode_str);
 
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode])
 		return nvme_admin_ops[opcode];
@@ -195,7 +195,7 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_admin_opcode_str);
 
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) {
+const char *nvme_get_fabrics_opcode_str(u8 opcode) {
 	if (opcode < ARRAY_SIZE(nvme_fabrics_ops) && nvme_fabrics_ops[opcode])
 		return nvme_fabrics_ops[opcode];
 	return "Unknown";
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 771eac1412..fe3627c5bd 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -20,6 +20,7 @@
 #include <linux/ptrace.h>
 #include <linux/nvme_ioctl.h>
 #include <linux/pm_qos.h>
+#include <linux/ratelimit.h>
 #include <asm/unaligned.h>
 
 #include "nvme.h"
@@ -312,12 +313,12 @@ static void nvme_log_error(struct request *req)
 	struct nvme_request *nr = nvme_req(req);
 
 	if (ns) {
-		pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
+		pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %u blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
 		       ns->disk ? ns->disk->disk_name : "?",
 		       nvme_get_opcode_str(nr->cmd->common.opcode),
 		       nr->cmd->common.opcode,
-		       (unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)),
-		       (unsigned long long)blk_rq_bytes(req) >> ns->lba_shift,
+		       nvme_sect_to_lba(ns->head, blk_rq_pos(req)),
+		       blk_rq_bytes(req) >> ns->head->lba_shift,
 		       nvme_get_error_status_str(nr->status),
 		       nr->status >> 8 & 7,	/* Status Code Type */
 		       nr->status & 0xff,	/* Status Code */
@@ -337,6 +338,30 @@ static void nvme_log_error(struct request *req)
 			   nr->status & NVME_SC_DNR  ? "DNR "  : "");
 }
 
+static void nvme_log_err_passthru(struct request *req)
+{
+	struct nvme_ns *ns = req->q->queuedata;
+	struct nvme_request *nr = nvme_req(req);
+
+	pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s"
+		"cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n",
+		ns ? ns->disk->disk_name : dev_name(nr->ctrl->device),
+		ns ? nvme_get_opcode_str(nr->cmd->common.opcode) :
+		     nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+		nr->cmd->common.opcode,
+		nvme_get_error_status_str(nr->status),
+		nr->status >> 8 & 7,	/* Status Code Type */
+		nr->status & 0xff,	/* Status Code */
+		nr->status & NVME_SC_MORE ? "MORE " : "",
+		nr->status & NVME_SC_DNR  ? "DNR "  : "",
+		nr->cmd->common.cdw10,
+		nr->cmd->common.cdw11,
+		nr->cmd->common.cdw12,
+		nr->cmd->common.cdw13,
+		nr->cmd->common.cdw14,
+		nr->cmd->common.cdw14);
+}
+
 enum nvme_disposition {
 	COMPLETE,
 	RETRY,
@@ -372,17 +397,24 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 static inline void nvme_end_req_zoned(struct request *req)
 {
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-	    req_op(req) == REQ_OP_ZONE_APPEND)
-		req->__sector = nvme_lba_to_sect(req->q->queuedata,
+	    req_op(req) == REQ_OP_ZONE_APPEND) {
+		struct nvme_ns *ns = req->q->queuedata;
+
+		req->__sector = nvme_lba_to_sect(ns->head,
 			le64_to_cpu(nvme_req(req)->result.u64));
+	}
 }
 
 static inline void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET)))
-		nvme_log_error(req);
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -675,10 +707,21 @@ static inline void nvme_clear_nvme_request(struct request *req)
 /* initialize a passthrough request */
 void nvme_init_request(struct request *req, struct nvme_command *cmd)
 {
-	if (req->q->queuedata)
+	struct nvme_request *nr = nvme_req(req);
+	bool logging_enabled;
+
+	if (req->q->queuedata) {
+		struct nvme_ns *ns = req->q->disk->private_data;
+
+		logging_enabled = ns->head->passthru_err_log_enabled;
 		req->timeout = NVME_IO_TIMEOUT;
-	else /* no queuedata implies admin queue */
+	} else { /* no queuedata implies admin queue */
+		logging_enabled = nr->ctrl->passthru_err_log_enabled;
 		req->timeout = NVME_ADMIN_TIMEOUT;
+	}
+
+	if (!logging_enabled)
+		req->rq_flags |= RQF_QUIET;
 
 	/* passthru commands should let the driver set the SGL flags */
 	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
@@ -687,8 +730,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
 	if (req->mq_hctx->type == HCTX_TYPE_POLL)
 		req->cmd_flags |= REQ_POLLED;
 	nvme_clear_nvme_request(req);
-	req->rq_flags |= RQF_QUIET;
-	memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
+	memcpy(nr->cmd, cmd, sizeof(*cmd));
 }
 EXPORT_SYMBOL_GPL(nvme_init_request);
 
@@ -717,7 +759,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
 
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live)
+		bool queue_live, enum nvme_ctrl_state state)
 {
 	struct nvme_request *req = nvme_req(rq);
 
@@ -738,7 +780,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (nvme_ctrl_state(ctrl)) {
+		switch (state) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
@@ -793,8 +835,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	}
 
 	if (queue_max_discard_segments(req->q) == 1) {
-		u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req));
-		u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9);
+		u64 slba = nvme_sect_to_lba(ns->head, blk_rq_pos(req));
+		u32 nlb = blk_rq_sectors(req) >> (ns->head->lba_shift - 9);
 
 		range[0].cattr = cpu_to_le32(0);
 		range[0].nlb = cpu_to_le32(nlb);
@@ -802,8 +844,9 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		n = 1;
 	} else {
 		__rq_for_each_bio(bio, req) {
-			u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
-			u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+			u64 slba = nvme_sect_to_lba(ns->head,
+						    bio->bi_iter.bi_sector);
+			u32 nlb = bio->bi_iter.bi_size >> ns->head->lba_shift;
 
 			if (n < segments) {
 				range[n].cattr = cpu_to_le32(0);
@@ -841,7 +884,7 @@ static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
 	u64 ref48;
 
 	/* both rw and write zeroes share the same reftag format */
-	switch (ns->guard_type) {
+	switch (ns->head->guard_type) {
 	case NVME_NVM_NS_16B_GUARD:
 		cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 		break;
@@ -869,17 +912,18 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 	cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes;
 	cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->write_zeroes.slba =
-		cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+		cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
 	cmnd->write_zeroes.length =
-		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+		cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1);
 
-	if (!(req->cmd_flags & REQ_NOUNMAP) && (ns->features & NVME_NS_DEAC))
+	if (!(req->cmd_flags & REQ_NOUNMAP) &&
+	    (ns->head->features & NVME_NS_DEAC))
 		cmnd->write_zeroes.control |= cpu_to_le16(NVME_WZ_DEAC);
 
-	if (nvme_ns_has_pi(ns)) {
+	if (nvme_ns_has_pi(ns->head)) {
 		cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT);
 
-		switch (ns->pi_type) {
+		switch (ns->head->pi_type) {
 		case NVME_NS_DPS_PI_TYPE1:
 		case NVME_NS_DPS_PI_TYPE2:
 			nvme_set_ref_tag(ns, cmnd, req);
@@ -911,13 +955,15 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	cmnd->rw.cdw2 = 0;
 	cmnd->rw.cdw3 = 0;
 	cmnd->rw.metadata = 0;
-	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
-	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+	cmnd->rw.slba =
+		cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
+	cmnd->rw.length =
+		cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1);
 	cmnd->rw.reftag = 0;
 	cmnd->rw.apptag = 0;
 	cmnd->rw.appmask = 0;
 
-	if (ns->ms) {
+	if (ns->head->ms) {
 		/*
 		 * If formated with metadata, the block layer always provides a
 		 * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled.  Else
@@ -925,12 +971,12 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		 * namespace capacity to zero to prevent any I/O.
 		 */
 		if (!blk_integrity_rq(req)) {
-			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
+			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
 		}
 
-		switch (ns->pi_type) {
+		switch (ns->head->pi_type) {
 		case NVME_NS_DPS_PI_TYPE3:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD;
 			break;
@@ -1043,20 +1089,27 @@ EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head, blk_mq_req_flags_t flags)
+		int qid, nvme_submit_flags_t flags)
 {
 	struct request *req;
 	int ret;
+	blk_mq_req_flags_t blk_flags = 0;
 
+	if (flags & NVME_SUBMIT_NOWAIT)
+		blk_flags |= BLK_MQ_REQ_NOWAIT;
+	if (flags & NVME_SUBMIT_RESERVED)
+		blk_flags |= BLK_MQ_REQ_RESERVED;
 	if (qid == NVME_QID_ANY)
-		req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+		req = blk_mq_alloc_request(q, nvme_req_op(cmd), blk_flags);
 	else
-		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), blk_flags,
 						qid - 1);
 
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	nvme_init_request(req, cmd);
+	if (flags & NVME_SUBMIT_RETRY)
+		req->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
 	if (buffer && bufflen) {
 		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
@@ -1064,7 +1117,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	ret = nvme_execute_rq(req, at_head);
+	ret = nvme_execute_rq(req, flags & NVME_SUBMIT_AT_HEAD);
 	if (result && ret >= 0)
 		*result = nvme_req(req)->result;
  out:
@@ -1077,7 +1130,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
 	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -1100,6 +1153,10 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 		effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
 	} else {
 		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+
+		/* Ignore execution restrictions if any relaxation bits are set */
+		if (effects & NVME_CMD_EFFECTS_CSER_MASK)
+			effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
 	}
 
 	return effects;
@@ -1452,7 +1509,7 @@ free_data:
 	return status;
 }
 
-static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 			struct nvme_id_ns **id)
 {
 	struct nvme_command c = { };
@@ -1552,7 +1609,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 	c.features.dword11 = cpu_to_le32(dword11);
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
-			buffer, buflen, NVME_QID_ANY, 0, 0);
+			buffer, buflen, NVME_QID_ANY, 0);
 	if (ret >= 0 && result)
 		*result = le32_to_cpu(res.u32);
 	return ret;
@@ -1671,14 +1728,14 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
-				u32 max_integrity_segments)
+static void nvme_init_integrity(struct gendisk *disk,
+		struct nvme_ns_head *head, u32 max_integrity_segments)
 {
 	struct blk_integrity integrity = { };
 
-	switch (ns->pi_type) {
+	switch (head->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
-		switch (ns->guard_type) {
+		switch (head->guard_type) {
 		case NVME_NVM_NS_16B_GUARD:
 			integrity.profile = &t10_pi_type3_crc;
 			integrity.tag_size = sizeof(u16) + sizeof(u32);
@@ -1696,7 +1753,7 @@ static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
 		break;
 	case NVME_NS_DPS_PI_TYPE1:
 	case NVME_NS_DPS_PI_TYPE2:
-		switch (ns->guard_type) {
+		switch (head->guard_type) {
 		case NVME_NVM_NS_16B_GUARD:
 			integrity.profile = &t10_pi_type1_crc;
 			integrity.tag_size = sizeof(u16);
@@ -1717,27 +1774,28 @@ static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
 		break;
 	}
 
-	integrity.tuple_size = ns->ms;
+	integrity.tuple_size = head->ms;
 	blk_integrity_register(disk, &integrity);
 	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
 }
 #else
-static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
-				u32 max_integrity_segments)
+static void nvme_init_integrity(struct gendisk *disk,
+		struct nvme_ns_head *head, u32 max_integrity_segments)
 {
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
+static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
+		struct nvme_ns_head *head)
 {
-	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct request_queue *queue = disk->queue;
-	u32 size = queue_logical_block_size(queue);
+	u32 max_discard_sectors;
 
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX))
-		ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl);
-
-	if (ctrl->max_discard_sectors == 0) {
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
+		max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
+	} else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
+		max_discard_sectors = UINT_MAX;
+	} else {
 		blk_queue_max_discard_sectors(queue, 0);
 		return;
 	}
@@ -1745,14 +1803,22 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_granularity = size;
-
-	/* If discard is already enabled, don't reset queue limits */
+	/*
+	 * If discard is already enabled, don't reset queue limits.
+	 *
+	 * This works around the fact that the block layer can't cope well with
+	 * updating the hardware limits when overridden through sysfs.  This is
+	 * harmless because discard limits in NVMe are purely advisory.
+	 */
 	if (queue->limits.max_discard_sectors)
 		return;
 
-	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
-	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
+	blk_queue_max_discard_sectors(queue, max_discard_sectors);
+	if (ctrl->dmrl)
+		blk_queue_max_discard_segments(queue, ctrl->dmrl);
+	else
+		blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
+	queue->limits.discard_granularity = queue_logical_block_size(queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
@@ -1766,21 +1832,21 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 		a->csi == b->csi;
 }
 
-static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
+		struct nvme_id_ns *id)
 {
 	bool first = id->dps & NVME_NS_DPS_PI_FIRST;
 	unsigned lbaf = nvme_lbaf_index(id->flbas);
-	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_command c = { };
 	struct nvme_id_ns_nvm *nvm;
 	int ret = 0;
 	u32 elbaf;
 
-	ns->pi_size = 0;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+	head->pi_size = 0;
+	head->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
-		ns->pi_size = sizeof(struct t10_pi_tuple);
-		ns->guard_type = NVME_NVM_NS_16B_GUARD;
+		head->pi_size = sizeof(struct t10_pi_tuple);
+		head->guard_type = NVME_NVM_NS_16B_GUARD;
 		goto set_pi;
 	}
 
@@ -1789,11 +1855,11 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 		return -ENOMEM;
 
 	c.identify.opcode = nvme_admin_identify;
-	c.identify.nsid = cpu_to_le32(ns->head->ns_id);
+	c.identify.nsid = cpu_to_le32(head->ns_id);
 	c.identify.cns = NVME_ID_CNS_CS_NS;
 	c.identify.csi = NVME_CSI_NVM;
 
-	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, nvm, sizeof(*nvm));
+	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm));
 	if (ret)
 		goto free_data;
 
@@ -1803,13 +1869,13 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (nvme_elbaf_sts(elbaf))
 		goto free_data;
 
-	ns->guard_type = nvme_elbaf_guard_type(elbaf);
-	switch (ns->guard_type) {
+	head->guard_type = nvme_elbaf_guard_type(elbaf);
+	switch (head->guard_type) {
 	case NVME_NVM_NS_64B_GUARD:
-		ns->pi_size = sizeof(struct crc64_pi_tuple);
+		head->pi_size = sizeof(struct crc64_pi_tuple);
 		break;
 	case NVME_NVM_NS_16B_GUARD:
-		ns->pi_size = sizeof(struct t10_pi_tuple);
+		head->pi_size = sizeof(struct t10_pi_tuple);
 		break;
 	default:
 		break;
@@ -1818,25 +1884,25 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 free_data:
 	kfree(nvm);
 set_pi:
-	if (ns->pi_size && (first || ns->ms == ns->pi_size))
-		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+	if (head->pi_size && (first || head->ms == head->pi_size))
+		head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
 	else
-		ns->pi_type = 0;
+		head->pi_type = 0;
 
 	return ret;
 }
 
-static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head, struct nvme_id_ns *id)
 {
-	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
 
-	ret = nvme_init_ms(ns, id);
+	ret = nvme_init_ms(ctrl, head, id);
 	if (ret)
 		return ret;
 
-	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
-	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
+	head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
 		return 0;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
@@ -1848,7 +1914,7 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
 			return 0;
 
-		ns->features |= NVME_NS_EXT_LBAS;
+		head->features |= NVME_NS_EXT_LBAS;
 
 		/*
 		 * The current fabrics transport drivers support namespace
@@ -1859,8 +1925,8 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * Note, this check will need to be modified if any drivers
 		 * gain the ability to use other metadata formats.
 		 */
-		if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
-			ns->features |= NVME_NS_METADATA_SUPPORTED;
+		if (ctrl->max_integrity_segments && nvme_ns_has_pi(head))
+			head->features |= NVME_NS_METADATA_SUPPORTED;
 	} else {
 		/*
 		 * For PCIe controllers, we can't easily remap the separate
@@ -1869,9 +1935,9 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * We allow extended LBAs for the passthrough interface, though.
 		 */
 		if (id->flbas & NVME_NS_FLBAS_META_EXT)
-			ns->features |= NVME_NS_EXT_LBAS;
+			head->features |= NVME_NS_EXT_LBAS;
 		else
-			ns->features |= NVME_NS_METADATA_SUPPORTED;
+			head->features |= NVME_NS_METADATA_SUPPORTED;
 	}
 	return 0;
 }
@@ -1894,11 +1960,11 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 	blk_queue_write_cache(q, vwc, vwc);
 }
 
-static void nvme_update_disk_info(struct gendisk *disk,
-		struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
+		struct nvme_ns_head *head, struct nvme_id_ns *id)
 {
-	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
-	u32 bs = 1U << ns->lba_shift;
+	sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze));
+	u32 bs = 1U << head->lba_shift;
 	u32 atomic_bs, phys_bs, io_opt = 0;
 
 	/*
@@ -1906,7 +1972,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	 * or smaller than a sector size yet, so catch this early and don't
 	 * allow block I/O.
 	 */
-	if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) {
+	if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
 	}
@@ -1923,7 +1989,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ctrl->subsys->awupf) * bs;
 	}
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
@@ -1949,20 +2015,20 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	 * I/O to namespaces with metadata except when the namespace supports
 	 * PI, as it can strip/insert in that case.
 	 */
-	if (ns->ms) {
+	if (head->ms) {
 		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
-		    (ns->features & NVME_NS_METADATA_SUPPORTED))
-			nvme_init_integrity(disk, ns,
-					    ns->ctrl->max_integrity_segments);
-		else if (!nvme_ns_has_pi(ns))
+		    (head->features & NVME_NS_METADATA_SUPPORTED))
+			nvme_init_integrity(disk, head,
+					    ctrl->max_integrity_segments);
+		else if (!nvme_ns_has_pi(head))
 			capacity = 0;
 	}
 
 	set_capacity_and_notify(disk, capacity);
 
-	nvme_config_discard(disk, ns);
+	nvme_config_discard(ctrl, disk, head);
 	blk_queue_max_write_zeroes_sectors(disk->queue,
-					   ns->ctrl->max_zeroes_sectors);
+					   ctrl->max_zeroes_sectors);
 }
 
 static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
@@ -1985,7 +2051,7 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
 	    is_power_of_2(ctrl->max_hw_sectors))
 		iob = ctrl->max_hw_sectors;
 	else
-		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
+		iob = nvme_lba_to_sect(ns->head, le16_to_cpu(id->noiob));
 
 	if (!iob)
 		return;
@@ -2052,16 +2118,17 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
-	ns->lba_shift = id->lbaf[lbaf].ds;
+	ns->head->lba_shift = id->lbaf[lbaf].ds;
+	ns->head->nuse = le64_to_cpu(id->nuse);
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
-	ret = nvme_configure_metadata(ns, id);
+	ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
 	if (ret < 0) {
 		blk_mq_unfreeze_queue(ns->disk->queue);
 		goto out;
 	}
 	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(ns->disk, ns, id);
+	nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id);
 
 	if (ns->head->ids.csi == NVME_CSI_ZNS) {
 		ret = nvme_update_zone_info(ns, lbaf);
@@ -2078,7 +2145,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	 * do not return zeroes.
 	 */
 	if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
-		ns->features |= NVME_NS_DEAC;
+		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2091,7 +2158,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 
 	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
-		nvme_update_disk_info(ns->head->disk, ns, id);
+		nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id);
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns);
 		blk_stack_limits(&ns->head->disk->queue->limits,
@@ -2154,7 +2221,7 @@ static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t l
 	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
-			NVME_QID_ANY, 1, 0);
+			NVME_QID_ANY, NVME_SUBMIT_AT_HEAD);
 }
 
 static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended)
@@ -2920,14 +2987,6 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl_nvm *id;
 	int ret;
 
-	if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
-		ctrl->max_discard_sectors = UINT_MAX;
-		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
-	} else {
-		ctrl->max_discard_sectors = 0;
-		ctrl->max_discard_segments = 0;
-	}
-
 	/*
 	 * Even though NVMe spec explicitly states that MDTS is not applicable
 	 * to the write-zeroes, we are cautious and limit the size to the
@@ -2957,8 +3016,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	if (ret)
 		goto free_data;
 
-	if (id->dmrl)
-		ctrl->max_discard_segments = id->dmrl;
+	ctrl->dmrl = id->dmrl;
 	ctrl->dmrsl = le32_to_cpu(id->dmrsl);
 	if (id->wzsl)
 		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);
@@ -3026,6 +3084,42 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	return 0;
 }
 
+static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	/*
+	 * In fabrics we need to verify the cntlid matches the
+	 * admin connect
+	 */
+	if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
+		dev_err(ctrl->device,
+			"Mismatching cntlid: Connect %u vs Identify %u, rejecting\n",
+			ctrl->cntlid, le16_to_cpu(id->cntlid));
+		return -EINVAL;
+	}
+
+	if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
+		dev_err(ctrl->device,
+			"keep-alive support is mandatory for fabrics\n");
+		return -EINVAL;
+	}
+
+	if (!nvme_discovery_ctrl(ctrl) && ctrl->ioccsz < 4) {
+		dev_err(ctrl->device,
+			"I/O queue command capsule supported size %d < 4\n",
+			ctrl->ioccsz);
+		return -EINVAL;
+	}
+
+	if (!nvme_discovery_ctrl(ctrl) && ctrl->iorcsz < 1) {
+		dev_err(ctrl->device,
+			"I/O queue response capsule supported size %d < 1\n",
+			ctrl->iorcsz);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int nvme_init_identify(struct nvme_ctrl *ctrl)
 {
 	struct nvme_id_ctrl *id;
@@ -3138,25 +3232,9 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
 		ctrl->maxcmd = le16_to_cpu(id->maxcmd);
 
-		/*
-		 * In fabrics we need to verify the cntlid matches the
-		 * admin connect
-		 */
-		if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
-			dev_err(ctrl->device,
-				"Mismatching cntlid: Connect %u vs Identify "
-				"%u, rejecting\n",
-				ctrl->cntlid, le16_to_cpu(id->cntlid));
-			ret = -EINVAL;
-			goto out_free;
-		}
-
-		if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
-			dev_err(ctrl->device,
-				"keep-alive support is mandatory for fabrics\n");
-			ret = -EINVAL;
+		ret = nvme_check_ctrl_fabric_info(ctrl, id);
+		if (ret)
 			goto out_free;
-		}
 	} else {
 		ctrl->hmpre = le32_to_cpu(id->hmpre);
 		ctrl->hmmin = le32_to_cpu(id->hmmin);
@@ -3415,6 +3493,8 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->ns_id = info->nsid;
 	head->ids = info->ids;
 	head->shared = info->is_shared;
+	ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
+	ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
 	kref_init(&head->ref);
 
 	if (head->ids.csi) {
@@ -3674,7 +3754,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	up_write(&ctrl->namespaces_rwsem);
 	nvme_get_ctrl(ctrl);
 
-	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups))
+	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
 		goto out_cleanup_ns_from_list;
 
 	if (!nvme_ns_head_multipath(ns->head))
@@ -3683,6 +3763,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	nvme_mpath_add_disk(ns, info->anagrpid);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 
+	/*
+	 * Set ns->disk->device->driver_data to ns so we can access
+	 * ns->head->passthru_err_log_enabled in
+	 * nvme_io_passthru_err_log_enabled_[store | show]().
+	 */
+	dev_set_drvdata(disk_to_dev(ns->disk), ns);
+
 	return;
 
  out_cleanup_ns_from_list:
@@ -4488,6 +4575,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	int ret;
 
 	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
+	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
@@ -4825,5 +4913,6 @@ static void __exit nvme_core_exit(void)
 
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host core framework");
 module_init(nvme_core_init);
 module_exit(nvme_core_exit);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index aa88606a44..495c171dae 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.value = cpu_to_le64(val);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",
@@ -387,8 +387,8 @@ static struct nvmf_connect_data *nvmf_connect_data_prep(struct nvme_ctrl *ctrl,
 
 	uuid_copy(&data->hostid, &ctrl->opts->host->id);
 	data->cntlid = cpu_to_le16(cntlid);
-	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
-	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+	strscpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strscpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
 
 	return data;
 }
@@ -450,8 +450,10 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
-			data, sizeof(*data), NVME_QID_ANY, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), NVME_QID_ANY,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_NOWAIT |
+			NVME_SUBMIT_RESERVED);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
@@ -525,11 +527,14 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res,
-			data, sizeof(*data), qid, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), qid,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_RESERVED |
+			NVME_SUBMIT_NOWAIT);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
+		goto out_free_data;
 	}
 	result = le32_to_cpu(res.u32);
 	if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) {
@@ -1488,6 +1493,7 @@ static void __exit nvmf_exit(void)
 }
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("NVMe host fabrics library");
 
 module_init(nvmf_init);
 module_exit(nvmf_exit);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index e4acccc315..37c974c38d 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -178,9 +178,11 @@ static inline bool
 nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 			struct nvmf_ctrl_options *opts)
 {
-	if (ctrl->state == NVME_CTRL_DELETING ||
-	    ctrl->state == NVME_CTRL_DELETING_NOIO ||
-	    ctrl->state == NVME_CTRL_DEAD ||
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state == NVME_CTRL_DELETING ||
+	    state == NVME_CTRL_DELETING_NOIO ||
+	    state == NVME_CTRL_DEAD ||
 	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
 	    !uuid_equal(&opts->host->id, &ctrl->opts->host->id))
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e0f4129c3a..68a5d97165 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1211,10 +1211,10 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 	/* Linux supports only Dynamic controllers */
 	assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff);
 	uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id);
-	strncpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn,
-		min(FCNVME_ASSOC_HOSTNQN_LEN, NVMF_NQN_SIZE));
-	strncpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn,
-		min(FCNVME_ASSOC_SUBNQN_LEN, NVMF_NQN_SIZE));
+	strscpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn,
+		sizeof(assoc_rqst->assoc_cmd.hostnqn));
+	strscpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn,
+		sizeof(assoc_rqst->assoc_cmd.subnqn));
 
 	lsop->queue = queue;
 	lsreq->rqstaddr = assoc_rqst;
@@ -2567,6 +2567,7 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
+	u16 qnum = op->queue->qnum;
 	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
 	struct nvme_command *sqe = &cmdiu->sqe;
 
@@ -2575,10 +2576,11 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 	 * will detect the aborted io and will fail the connection.
 	 */
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d w10/11: "
+		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d (%s) w10/11: "
 		"x%08x/x%08x\n",
-		ctrl->cnum, op->queue->qnum, sqe->common.opcode,
-		sqe->connect.fctype, sqe->common.cdw10, sqe->common.cdw11);
+		ctrl->cnum, qnum, sqe->common.opcode, sqe->fabrics.fctype,
+		nvme_fabrics_opcode_str(qnum, sqe),
+		sqe->common.cdw10, sqe->common.cdw11);
 	if (__nvme_fc_abort_op(ctrl, op))
 		nvme_fc_error_recovery(ctrl, "io timeout abort failed");
 
@@ -3491,10 +3493,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	ctrl->ctrl.opts = opts;
 	ctrl->ctrl.nr_reconnects = 0;
-	if (lport->dev)
-		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
-	else
-		ctrl->ctrl.numa_node = NUMA_NO_NODE;
 	INIT_LIST_HEAD(&ctrl->ctrl_list);
 	ctrl->lport = lport;
 	ctrl->rport = rport;
@@ -3539,6 +3537,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
 	if (ret)
 		goto out_free_queues;
+	if (lport->dev)
+		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
 
 	/* at this point, teardown path changes to ref counting on nvme ctrl */
 
@@ -3570,8 +3570,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	flush_delayed_work(&ctrl->connect_work);
 
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
-		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
+		"NVME-FC{%d}: new ctrl: NQN \"%s\", hostnqn: %s\n",
+		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl), opts->host->nqn);
 
 	return &ctrl->ctrl;
 
@@ -3971,4 +3971,5 @@ static void __exit nvme_fc_exit_module(void)
 module_init(nvme_fc_init_module);
 module_exit(nvme_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe host FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 4939ed3563..3dfd5ae99a 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -5,7 +5,7 @@
  */
 #include <linux/ptrace.h>	/* for force_successful_syscall_return */
 #include <linux/nvme_ioctl.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include "nvme.h"
 
 enum {
@@ -97,58 +97,6 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval)
 	return (void __user *)ptrval;
 }
 
-static void *nvme_add_user_metadata(struct request *req, void __user *ubuf,
-		unsigned len, u32 seed)
-{
-	struct bio_integrity_payload *bip;
-	int ret = -ENOMEM;
-	void *buf;
-	struct bio *bio = req->bio;
-
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	if (req_op(req) == REQ_OP_DRV_OUT) {
-		ret = -EFAULT;
-		if (copy_from_user(buf, ubuf, len))
-			goto out_free_meta;
-	} else {
-		memset(buf, 0, len);
-	}
-
-	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
-	if (IS_ERR(bip)) {
-		ret = PTR_ERR(bip);
-		goto out_free_meta;
-	}
-
-	bip->bip_iter.bi_sector = seed;
-	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
-			offset_in_page(buf));
-	if (ret != len) {
-		ret = -ENOMEM;
-		goto out_free_meta;
-	}
-
-	req->cmd_flags |= REQ_INTEGRITY;
-	return buf;
-out_free_meta:
-	kfree(buf);
-out:
-	return ERR_PTR(ret);
-}
-
-static int nvme_finish_user_metadata(struct request *req, void __user *ubuf,
-		void *meta, unsigned len, int ret)
-{
-	if (!ret && req_op(req) == REQ_OP_DRV_IN &&
-	    copy_to_user(ubuf, meta, len))
-		ret = -EFAULT;
-	kfree(meta);
-	return ret;
-}
-
 static struct request *nvme_alloc_user_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_opf_t rq_flags,
 		blk_mq_req_flags_t blk_flags)
@@ -165,14 +113,12 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
-		unsigned int flags)
+		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
 {
 	struct request_queue *q = req->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	struct bio *bio = NULL;
-	void *meta = NULL;
 	int ret;
 
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
@@ -194,18 +140,17 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 
 	if (ret)
 		goto out;
+
 	bio = req->bio;
-	if (bdev)
+	if (bdev) {
 		bio_set_dev(bio, bdev);
-
-	if (bdev && meta_buffer && meta_len) {
-		meta = nvme_add_user_metadata(req, meta_buffer, meta_len,
-				meta_seed);
-		if (IS_ERR(meta)) {
-			ret = PTR_ERR(meta);
-			goto out_unmap;
+		if (meta_buffer && meta_len) {
+			ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
+						     meta_seed);
+			if (ret)
+				goto out_unmap;
+			req->cmd_flags |= REQ_INTEGRITY;
 		}
-		*metap = meta;
 	}
 
 	return ret;
@@ -226,7 +171,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_ctrl *ctrl;
 	struct request *req;
-	void *meta = NULL;
 	struct bio *bio;
 	u32 effects;
 	int ret;
@@ -238,7 +182,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	req->timeout = timeout;
 	if (ubuffer && bufflen) {
 		ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
-				meta_len, meta_seed, &meta, NULL, flags);
+				meta_len, meta_seed, NULL, flags);
 		if (ret)
 			return ret;
 	}
@@ -250,9 +194,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	ret = nvme_execute_rq(req, false);
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
-	if (meta)
-		ret = nvme_finish_user_metadata(req, meta_buffer, meta,
-						meta_len, ret);
 	if (bio)
 		blk_rq_unmap_user(bio);
 	blk_mq_free_request(req);
@@ -284,10 +225,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		return -EINVAL;
 	}
 
-	length = (io.nblocks + 1) << ns->lba_shift;
+	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->ms == sizeof(struct t10_pi_tuple)) {
+	    (ns->head->ms == ns->head->pi_size)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
@@ -297,11 +238,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		meta_len = 0;
 		metadata = NULL;
 	} else {
-		meta_len = (io.nblocks + 1) * ns->ms;
+		meta_len = (io.nblocks + 1) * ns->head->ms;
 		metadata = nvme_to_user_ptr(io.metadata);
 	}
 
-	if (ns->features & NVME_NS_EXT_LBAS) {
+	if (ns->head->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {
@@ -447,19 +388,10 @@ struct nvme_uring_data {
  * Expect build errors if this grows larger than that.
  */
 struct nvme_uring_cmd_pdu {
-	union {
-		struct bio *bio;
-		struct request *req;
-	};
-	u32 meta_len;
-	u32 nvme_status;
-	union {
-		struct {
-			void *meta; /* kernel-resident buffer */
-			void __user *meta_buffer;
-		};
-		u64 result;
-	} u;
+	struct request *req;
+	struct bio *bio;
+	u64 result;
+	int status;
 };
 
 static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
@@ -468,31 +400,6 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
 	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd,
-				    unsigned issue_flags)
-{
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-	struct request *req = pdu->req;
-	int status;
-	u64 result;
-
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		status = -EINTR;
-	else
-		status = nvme_req(req)->status;
-
-	result = le64_to_cpu(nvme_req(req)->result.u64);
-
-	if (pdu->meta_len)
-		status = nvme_finish_user_metadata(req, pdu->u.meta_buffer,
-					pdu->u.meta, pdu->meta_len, status);
-	if (req->bio)
-		blk_rq_unmap_user(req->bio);
-	blk_mq_free_request(req);
-
-	io_uring_cmd_done(ioucmd, status, result, issue_flags);
-}
-
 static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 			       unsigned issue_flags)
 {
@@ -500,8 +407,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 
 	if (pdu->bio)
 		blk_rq_unmap_user(pdu->bio);
-
-	io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags);
+	io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
 }
 
 static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
@@ -510,53 +416,24 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	struct io_uring_cmd *ioucmd = req->end_io_data;
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
-	req->bio = pdu->bio;
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
-		pdu->nvme_status = -EINTR;
-	} else {
-		pdu->nvme_status = nvme_req(req)->status;
-		if (!pdu->nvme_status)
-			pdu->nvme_status = blk_status_to_errno(err);
-	}
-	pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+		pdu->status = -EINTR;
+	else
+		pdu->status = nvme_req(req)->status;
+	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
 	 * For iopoll, complete it directly.
 	 * Otherwise, move the completion to task work.
 	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
+	if (blk_rq_is_poll(req))
 		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
+	else
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
 
 	return RQ_END_IO_FREE;
 }
 
-static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req,
-						     blk_status_t err)
-{
-	struct io_uring_cmd *ioucmd = req->end_io_data;
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-
-	req->bio = pdu->bio;
-	pdu->req = req;
-
-	/*
-	 * For iopoll, complete it directly.
-	 * Otherwise, move the completion to task work.
-	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
-		nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb);
-	}
-
-	return RQ_END_IO_NONE;
-}
-
 static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec)
 {
@@ -568,7 +445,6 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct request *req;
 	blk_opf_t rq_flags = REQ_ALLOC_CACHE;
 	blk_mq_req_flags_t blk_flags = 0;
-	void *meta = NULL;
 	int ret;
 
 	c.common.opcode = READ_ONCE(cmd->opcode);
@@ -616,27 +492,16 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (d.addr && d.data_len) {
 		ret = nvme_map_user_request(req, d.addr,
 			d.data_len, nvme_to_user_ptr(d.metadata),
-			d.metadata_len, 0, &meta, ioucmd, vec);
+			d.metadata_len, 0, ioucmd, vec);
 		if (ret)
 			return ret;
 	}
 
-	if (blk_rq_is_poll(req)) {
-		ioucmd->flags |= IORING_URING_CMD_POLLED;
-		WRITE_ONCE(ioucmd->cookie, req);
-	}
-
 	/* to free bio on completion, as req->bio will be null at that time */
 	pdu->bio = req->bio;
-	pdu->meta_len = d.metadata_len;
+	pdu->req = req;
 	req->end_io_data = ioucmd;
-	if (pdu->meta_len) {
-		pdu->u.meta = meta;
-		pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata);
-		req->end_io = nvme_uring_cmd_end_io_meta;
-	} else {
-		req->end_io = nvme_uring_cmd_end_io;
-	}
+	req->end_io = nvme_uring_cmd_end_io;
 	blk_execute_rq_nowait(req, false);
 	return -EIOCBQUEUED;
 }
@@ -787,16 +652,12 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
 				 struct io_comp_batch *iob,
 				 unsigned int poll_flags)
 {
-	struct request *req;
-	int ret = 0;
-
-	if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
-		return 0;
+	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
+	struct request *req = pdu->req;
 
-	req = READ_ONCE(ioucmd->cookie);
 	if (req && blk_rq_is_poll(req))
-		ret = blk_rq_poll(req, iob, poll_flags);
-	return ret;
+		return blk_rq_poll(req, iob, poll_flags);
+	return 0;
 }
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0a88d7bdc5..74de1e64ae 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -156,7 +156,7 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
 	up_read(&ctrl->namespaces_rwsem);
@@ -223,13 +223,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl);
+
 	/*
 	 * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should
 	 * still be able to complete assuming that the controller is connected.
 	 * Otherwise it will fail immediately and return to the requeue list.
 	 */
-	if (ns->ctrl->state != NVME_CTRL_LIVE &&
-	    ns->ctrl->state != NVME_CTRL_DELETING)
+	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
 	    !test_bit(NVME_NS_READY, &ns->flags))
@@ -331,7 +332,7 @@ out:
 
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
-	return ns->ctrl->state == NVME_CTRL_LIVE &&
+	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
 		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
@@ -358,7 +359,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
 			continue;
-		switch (ns->ctrl->state) {
+		switch (nvme_ctrl_state(ns->ctrl)) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
@@ -579,7 +580,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	 */
 	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		rc = device_add_disk(&head->subsys->dev, head->disk,
-				     nvme_ns_id_attr_groups);
+				     nvme_ns_attr_groups);
 		if (rc) {
 			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
 			return;
@@ -667,7 +668,7 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	 * controller is ready.
 	 */
 	if (nvme_state_is_live(ns->ana_state) &&
-	    ns->ctrl->state == NVME_CTRL_LIVE)
+	    nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -748,7 +749,7 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	nvme_read_ana_log(ctrl);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index e7411dac00..7b87763e2f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -16,6 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
 #include <linux/t10-pi.h>
+#include <linux/ratelimit_types.h>
 
 #include <trace/events/block.h>
 
@@ -262,6 +263,7 @@ enum nvme_ctrl_flags {
 struct nvme_ctrl {
 	bool comp_seen;
 	bool identified;
+	bool passthru_err_log_enabled;
 	enum nvme_ctrl_state state;
 	spinlock_t lock;
 	struct mutex scan_lock;
@@ -302,14 +304,13 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
-	u32 max_discard_sectors;
-	u32 max_discard_segments;
 	u32 max_zeroes_sectors;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u32 max_zone_append;
 #endif
 	u16 crdt[3];
 	u16 oncs;
+	u8 dmrl;
 	u32 dmrsl;
 	u16 oacs;
 	u16 sqsize;
@@ -450,13 +451,28 @@ struct nvme_ns_head {
 	struct list_head	list;
 	struct srcu_struct      srcu;
 	struct nvme_subsystem	*subsys;
-	unsigned		ns_id;
 	struct nvme_ns_ids	ids;
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
+	bool			passthru_err_log_enabled;
 	int			instance;
 	struct nvme_effects_log *effects;
+	u64			nuse;
+	unsigned		ns_id;
+	int			lba_shift;
+	u16			ms;
+	u16			pi_size;
+	u8			pi_type;
+	u8			guard_type;
+	u16			sgs;
+	u32			sws;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u64			zsze;
+#endif
+	unsigned long		features;
+
+	struct ratelimit_state	rs_nuse;
 
 	struct cdev		cdev;
 	struct device		cdev_device;
@@ -498,17 +514,6 @@ struct nvme_ns {
 	struct kref kref;
 	struct nvme_ns_head *head;
 
-	int lba_shift;
-	u16 ms;
-	u16 pi_size;
-	u16 sgs;
-	u32 sws;
-	u8 pi_type;
-	u8 guard_type;
-#ifdef CONFIG_BLK_DEV_ZONED
-	u64 zsze;
-#endif
-	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
 #define NVME_NS_ANA_PENDING	2
@@ -519,13 +524,12 @@ struct nvme_ns {
 	struct device		cdev_device;
 
 	struct nvme_fault_inject fault_inject;
-
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
-static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
+static inline bool nvme_ns_has_pi(struct nvme_ns_head *head)
 {
-	return ns->pi_type && ns->ms == ns->pi_size;
+	return head->pi_type && head->ms == head->pi_size;
 }
 
 struct nvme_ctrl_ops {
@@ -657,17 +661,17 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
 /*
  * Convert a 512B sector number to a device logical block number.
  */
-static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector)
+static inline u64 nvme_sect_to_lba(struct nvme_ns_head *head, sector_t sector)
 {
-	return sector >> (ns->lba_shift - SECTOR_SHIFT);
+	return sector >> (head->lba_shift - SECTOR_SHIFT);
 }
 
 /*
  * Convert a device logical block number to a 512B sector number.
  */
-static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba)
+static inline sector_t nvme_lba_to_sect(struct nvme_ns_head *head, u64 lba)
 {
-	return lba << (ns->lba_shift - SECTOR_SHIFT);
+	return lba << (head->lba_shift - SECTOR_SHIFT);
 }
 
 /*
@@ -802,17 +806,18 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *req);
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live);
+		bool queue_live, enum nvme_ctrl_state state);
 
 static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live)
 {
-	if (likely(ctrl->state == NVME_CTRL_LIVE))
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (likely(state == NVME_CTRL_LIVE))
 		return true;
-	if (ctrl->ops->flags & NVME_F_FABRICS &&
-	    ctrl->state == NVME_CTRL_DELETING)
+	if (ctrl->ops->flags & NVME_F_FABRICS && state == NVME_CTRL_DELETING)
 		return queue_live;
-	return __nvme_check_ready(ctrl, rq, queue_live);
+	return __nvme_check_ready(ctrl, rq, queue_live, state);
 }
 
 /*
@@ -833,12 +838,27 @@ static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl,
 		(ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS);
 }
 
+/*
+ * Flags for __nvme_submit_sync_cmd()
+ */
+typedef __u32 __bitwise nvme_submit_flags_t;
+
+enum {
+	/* Insert request at the head of the queue */
+	NVME_SUBMIT_AT_HEAD  = (__force nvme_submit_flags_t)(1 << 0),
+	/* Set BLK_MQ_REQ_NOWAIT when allocating request */
+	NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
+	/* Set BLK_MQ_REQ_RESERVED when allocating request */
+	NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
+	/* Retry command when NVME_SC_DNR is not set in the result */
+	NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
+};
+
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head,
-		blk_mq_req_flags_t flags);
+		int qid, nvme_submit_flags_t flags);
 int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
 		      unsigned int dword11, void *buffer, size_t buflen,
 		      u32 *result);
@@ -873,10 +893,12 @@ int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
 int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+		struct nvme_id_ns **id);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 
-extern const struct attribute_group *nvme_ns_id_attr_groups[];
+extern const struct attribute_group *nvme_ns_attr_groups[];
 extern const struct pr_ops nvme_pr_ops;
 extern const struct block_device_operations nvme_ns_head_ops;
 extern const struct attribute_group nvme_dev_attrs_group;
@@ -926,6 +948,10 @@ extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
 
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return disk->fops == &nvme_ns_head_ops;
+}
 #else
 #define multipath false
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
@@ -1003,6 +1029,10 @@ static inline void nvme_mpath_start_request(struct request *rq)
 static inline void nvme_mpath_end_request(struct request *rq)
 {
 }
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return false;
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
@@ -1031,7 +1061,10 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
-	return dev_to_disk(dev)->private_data;
+	struct gendisk *disk = dev_to_disk(dev);
+
+	WARN_ON(nvme_disk_is_ns_head(disk));
+	return disk->private_data;
 }
 
 #ifdef CONFIG_NVME_HWMON
@@ -1108,35 +1141,42 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
 }
 
 #ifdef CONFIG_NVME_VERBOSE_ERRORS
-const unsigned char *nvme_get_error_status_str(u16 status);
-const unsigned char *nvme_get_opcode_str(u8 opcode);
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode);
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode);
+const char *nvme_get_error_status_str(u16 status);
+const char *nvme_get_opcode_str(u8 opcode);
+const char *nvme_get_admin_opcode_str(u8 opcode);
+const char *nvme_get_fabrics_opcode_str(u8 opcode);
 #else /* CONFIG_NVME_VERBOSE_ERRORS */
-static inline const unsigned char *nvme_get_error_status_str(u16 status)
+static inline const char *nvme_get_error_status_str(u16 status)
 {
 	return "I/O Error";
 }
-static inline const unsigned char *nvme_get_opcode_str(u8 opcode)
+static inline const char *nvme_get_opcode_str(u8 opcode)
 {
 	return "I/O Cmd";
 }
-static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+static inline const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	return "Admin Cmd";
 }
 
-static inline const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode)
+static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
 {
 	return "Fabrics Cmd";
 }
 #endif /* CONFIG_NVME_VERBOSE_ERRORS */
 
-static inline const unsigned char *nvme_opcode_str(int qid, u8 opcode, u8 fctype)
+static inline const char *nvme_opcode_str(int qid, u8 opcode)
 {
-	if (opcode == nvme_fabrics_command)
-		return nvme_get_fabrics_opcode_str(fctype);
 	return qid ? nvme_get_opcode_str(opcode) :
 		nvme_get_admin_opcode_str(opcode);
 }
+
+static inline const char *nvme_fabrics_opcode_str(
+		int qid, const struct nvme_command *cmd)
+{
+	if (nvme_is_fabrics(cmd))
+		return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
+
+	return nvme_opcode_str(qid, cmd->common.opcode);
+}
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 61af7ff1a9..8e0bb96926 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1284,6 +1284,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct request *abort_req;
 	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
+	u8 opcode;
 
 	/* If PCI error recovery process is happening, we cannot reset or
 	 * the recovery mechanism will surely fail.
@@ -1310,8 +1311,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 
 	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, completion polled\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, completion polled\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		return BLK_EH_DONE;
 	}
 
@@ -1327,8 +1328,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
-			 "I/O %d QID %d timeout, disable controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, disable controller\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
@@ -1343,10 +1344,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * command was already aborted once before and still hasn't been
 	 * returned to the driver, or if this is the admin queue.
 	 */
+	opcode = nvme_req(req)->cmd->common.opcode;
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, reset controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
+			 req->tag, nvme_cid(req), opcode,
+			 nvme_opcode_str(nvmeq->qid, opcode), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
@@ -1362,10 +1365,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
-		"I/O %d (%s) QID %d timeout, aborting\n",
-		 req->tag,
-		 nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
-		 nvmeq->qid);
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n",
+		 req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode),
+		 nvmeq->qid, blk_op_str(req_op(req)), req_op(req),
+		 blk_rq_bytes(req));
 
 	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
 					 BLK_MQ_REQ_NOWAIT);
@@ -2743,10 +2746,10 @@ static void nvme_reset_work(struct work_struct *work)
 	 * controller around but remove all namespaces.
 	 */
 	if (dev->online_queues > 1) {
+		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
 		nvme_pci_update_nr_queues(dev);
-		nvme_dbbuf_set(dev);
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");
@@ -3360,6 +3363,9 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_VDEVICE(REDHAT, 0x0010),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x126f, 0x2262),	/* Silicon Motion generic */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x126f, 0x2263),	/* Silicon Motion unidentified */
 		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
 				NVME_QUIRK_BOGUS_NID, },
@@ -3408,6 +3414,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1c5c, 0x174a),   /* SK Hynix P31 SSD */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1c5c, 0x1D59),   /* SK Hynix BC901 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
@@ -3538,5 +3546,6 @@ static void __exit nvme_exit(void)
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host PCIe transport driver");
 module_init(nvme_init);
 module_exit(nvme_exit);
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 391b1465eb..fc3eed00f9 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -98,7 +98,7 @@ static int nvme_send_pr_command(struct block_device *bdev,
 		struct nvme_command *c, void *data, unsigned int data_len)
 {
 	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
-	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+	    nvme_disk_is_ns_head(bdev->bd_disk))
 		return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
 
 	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 81e2621169..20fdd40b18 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1410,6 +1410,8 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct bio *bio = rq->bio;
 	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	u32 xfer_len;
 	int nr;
 
 	req->mr = ib_mr_pool_get(queue->qp, &queue->qp->sig_mrs);
@@ -1422,8 +1424,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	if (unlikely(nr))
 		goto mr_put;
 
-	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->pi_type);
+	nvme_rdma_set_sig_attrs(bi, c, req->mr->sig_attrs, ns->head->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
@@ -1441,7 +1442,11 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		     IB_ACCESS_REMOTE_WRITE;
 
 	sg->addr = cpu_to_le64(req->mr->iova);
-	put_unaligned_le24(req->mr->length, sg->length);
+	xfer_len = req->mr->length;
+	/* Check if PI is added by the HW */
+	if (!pi_count)
+		xfer_len += (xfer_len >> bi->interval_exp) * ns->head->pi_size;
+	put_unaligned_le24(xfer_len, sg->length);
 	put_unaligned_le32(req->mr->rkey, sg->key);
 	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
 
@@ -1946,9 +1951,13 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	struct nvme_command *cmd = req->req.cmd;
+	int qid = nvme_rdma_queue_idx(queue);
 
-	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
-		 rq->tag, nvme_rdma_queue_idx(queue));
+	dev_warn(ctrl->ctrl.device,
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
@@ -2017,7 +2026,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	    queue->pi_support &&
 	    (c->common.opcode == nvme_cmd_write ||
 	     c->common.opcode == nvme_cmd_read) &&
-	    nvme_ns_has_pi(ns))
+	    nvme_ns_has_pi(ns->head))
 		req->use_sig_mr = true;
 	else
 		req->use_sig_mr = false;
@@ -2291,8 +2300,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_rdma_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
@@ -2395,4 +2404,5 @@ static void __exit nvme_rdma_cleanup_module(void)
 module_init(nvme_rdma_init_module);
 module_exit(nvme_rdma_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host RDMA transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index c6b7fbd4d3..09fcaa519e 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -35,16 +35,71 @@ static ssize_t nvme_sysfs_rescan(struct device *dev,
 }
 static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
 
+static ssize_t nvme_adm_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf,
+			  ctrl->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	bool passthru_err_log_enabled;
+	int err;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+
+	ctrl->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
 static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->fops == &nvme_bdev_ops)
-		return nvme_get_ns_from_dev(dev)->head;
-	else
+	if (nvme_disk_is_ns_head(disk))
 		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
 }
 
+static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+
+	return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	bool passthru_err_log_enabled;
+	int err;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+	head->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_adm_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_adm_passthru_err_log_enabled_show, nvme_adm_passthru_err_log_enabled_store);
+
+static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
+
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
@@ -114,20 +169,103 @@ static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(nsid);
 
-static struct attribute *nvme_ns_id_attrs[] = {
+static ssize_t csi_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ids.csi);
+}
+static DEVICE_ATTR_RO(csi);
+
+static ssize_t metadata_bytes_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ms);
+}
+static DEVICE_ATTR_RO(metadata_bytes);
+
+static int ns_head_update_nuse(struct nvme_ns_head *head)
+{
+	struct nvme_id_ns *id;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	/* Avoid issuing commands too often by rate limiting the update */
+	if (!__ratelimit(&head->rs_nuse))
+		return 0;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns)
+		goto out_unlock;
+
+	ret = nvme_identify_ns(ns->ctrl, head->ns_id, &id);
+	if (ret)
+		goto out_unlock;
+
+	head->nuse = le64_to_cpu(id->nuse);
+	kfree(id);
+
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+
+static int ns_update_nuse(struct nvme_ns *ns)
+{
+	struct nvme_id_ns *id;
+	int ret;
+
+	/* Avoid issuing commands too often by rate limiting the update. */
+	if (!__ratelimit(&ns->head->rs_nuse))
+		return 0;
+
+	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
+	if (ret)
+		return ret;
+
+	ns->head->nuse = le64_to_cpu(id->nuse);
+	kfree(id);
+	return 0;
+}
+
+static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct block_device *bdev = disk->part0;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
+	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+		ret = ns_head_update_nuse(head);
+	else
+		ret = ns_update_nuse(bdev->bd_disk->private_data);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu\n", head->nuse);
+}
+static DEVICE_ATTR_RO(nuse);
+
+static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_wwid.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
+	&dev_attr_csi.attr,
 	&dev_attr_nsid.attr,
+	&dev_attr_metadata_bytes.attr,
+	&dev_attr_nuse.attr,
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
 #endif
+	&dev_attr_io_passthru_err_log_enabled.attr,
 	NULL,
 };
 
-static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
+static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -148,7 +286,8 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 	}
 #ifdef CONFIG_NVME_MULTIPATH
 	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
-		if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
+		/* per-path attr */
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;
@@ -157,13 +296,13 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static const struct attribute_group nvme_ns_id_attr_group = {
-	.attrs		= nvme_ns_id_attrs,
-	.is_visible	= nvme_ns_id_attrs_are_visible,
+static const struct attribute_group nvme_ns_attr_group = {
+	.attrs		= nvme_ns_attrs,
+	.is_visible	= nvme_ns_attrs_are_visible,
 };
 
-const struct attribute_group *nvme_ns_id_attr_groups[] = {
-	&nvme_ns_id_attr_group,
+const struct attribute_group *nvme_ns_attr_groups[] = {
+	&nvme_ns_attr_group,
 	NULL,
 };
 
@@ -226,6 +365,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 				     char *buf)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned state = (unsigned)nvme_ctrl_state(ctrl);
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
@@ -236,9 +376,8 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_DEAD]	= "dead",
 	};
 
-	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
-	    state_name[ctrl->state])
-		return sysfs_emit(buf, "%s\n", state_name[ctrl->state]);
+	if (state < ARRAY_SIZE(state_name) && state_name[state])
+		return sysfs_emit(buf, "%s\n", state_name[state]);
 
 	return sysfs_emit(buf, "unknown state\n");
 }
@@ -570,6 +709,7 @@ static struct attribute *nvme_dev_attrs[] = {
 #ifdef CONFIG_NVME_TCP_TLS
 	&dev_attr_tls_key.attr,
 #endif
+	&dev_attr_adm_passthru_err_log_enabled.attr,
 	NULL
 };
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 08805f0278..a6d596e056 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1922,14 +1922,13 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 						      ctrl->opts->subsysnqn);
 		if (!pskid) {
 			dev_err(ctrl->device, "no valid PSK found\n");
-			ret = -ENOKEY;
-			goto out_free_queue;
+			return -ENOKEY;
 		}
 	}
 
 	ret = nvme_tcp_alloc_queue(ctrl, 0, pskid);
 	if (ret)
-		goto out_free_queue;
+		return ret;
 
 	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
 	if (ret)
@@ -2429,13 +2428,13 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
-	u8 opc = pdu->cmd.common.opcode, fctype = pdu->cmd.fabrics.fctype;
+	struct nvme_command *cmd = &pdu->cmd;
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
-		"queue %d: timeout cid %#x type %d opcode %#x (%s)\n",
-		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
-		opc, nvme_opcode_str(qid, opc, fctype));
+		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*
@@ -2754,8 +2753,8 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
@@ -2827,4 +2826,5 @@ static void __exit nvme_tcp_cleanup_module(void)
 module_init(nvme_tcp_init_module);
 module_exit(nvme_tcp_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host TCP transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index ec8557810c..499bbb0eee 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -11,7 +11,7 @@ int nvme_revalidate_zones(struct nvme_ns *ns)
 {
 	struct request_queue *q = ns->queue;
 
-	blk_queue_chunk_sectors(q, ns->zsze);
+	blk_queue_chunk_sectors(q, ns->head->zsze);
 	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
 
 	return blk_revalidate_disk_zones(ns->disk, NULL);
@@ -99,16 +99,17 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
-	if (!is_power_of_2(ns->zsze)) {
+	ns->head->zsze =
+		nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
+	if (!is_power_of_2(ns->head->zsze)) {
 		dev_warn(ns->ctrl->device,
 			"invalid zone size:%llu for namespace:%u\n",
-			ns->zsze, ns->head->ns_id);
+			ns->head->zsze, ns->head->ns_id);
 		status = -ENODEV;
 		goto free_data;
 	}
 
-	disk_set_zoned(ns->disk, BLK_ZONED_HM);
+	disk_set_zoned(ns->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
 	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
@@ -128,7 +129,7 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 				   sizeof(struct nvme_zone_descriptor);
 
 	nr_zones = min_t(unsigned int, nr_zones,
-			 get_capacity(ns->disk) >> ilog2(ns->zsze));
+			 get_capacity(ns->disk) >> ilog2(ns->head->zsze));
 
 	bufsize = sizeof(struct nvme_zone_report) +
 		nr_zones * sizeof(struct nvme_zone_descriptor);
@@ -147,7 +148,8 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	return NULL;
 }
 
-static int nvme_zone_parse_entry(struct nvme_ns *ns,
+static int nvme_zone_parse_entry(struct nvme_ctrl *ctrl,
+				 struct nvme_ns_head *head,
 				 struct nvme_zone_descriptor *entry,
 				 unsigned int idx, report_zones_cb cb,
 				 void *data)
@@ -155,20 +157,20 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	struct blk_zone zone = { };
 
 	if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
-		dev_err(ns->ctrl->device, "invalid zone type %#x\n",
+		dev_err(ctrl->device, "invalid zone type %#x\n",
 				entry->zt);
 		return -EINVAL;
 	}
 
 	zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
 	zone.cond = entry->zs >> 4;
-	zone.len = ns->zsze;
-	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
-	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
+	zone.len = head->zsze;
+	zone.capacity = nvme_lba_to_sect(head, le64_to_cpu(entry->zcap));
+	zone.start = nvme_lba_to_sect(head, le64_to_cpu(entry->zslba));
 	if (zone.cond == BLK_ZONE_COND_FULL)
 		zone.wp = zone.start + zone.len;
 	else
-		zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+		zone.wp = nvme_lba_to_sect(head, le64_to_cpu(entry->wp));
 
 	return cb(&zone, idx, data);
 }
@@ -196,11 +198,11 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
 	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
 
-	sector &= ~(ns->zsze - 1);
+	sector &= ~(ns->head->zsze - 1);
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);
 
-		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, sector));
 		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
 		if (ret) {
 			if (ret > 0)
@@ -213,14 +215,15 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 			break;
 
 		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
-			ret = nvme_zone_parse_entry(ns, &report->entries[i],
+			ret = nvme_zone_parse_entry(ns->ctrl, ns->head,
+						    &report->entries[i],
 						    zone_idx, cb, data);
 			if (ret)
 				goto out_free;
 			zone_idx++;
 		}
 
-		sector += ns->zsze * nz;
+		sector += ns->head->zsze * nz;
 	}
 
 	if (zone_idx > 0)
@@ -239,7 +242,7 @@ blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 
 	c->zms.opcode = nvme_cmd_zone_mgmt_send;
 	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
-	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
 	c->zms.zsa = action;
 
 	if (req_op(req) == REQ_OP_ZONE_RESET_ALL)