Merge tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round this time around. This contains:

   - NVMe updates via Keith:
        - nvme fabrics spec updates (Guixin, Max)
        - nvme target udpates (Guixin, Evan)
        - nvme attribute refactoring (Daniel)
        - nvme-fc numa fix (Keith)

   - MD updates via Song:
        - Fix/Cleanup RCU usage from conf->disks[i].rdev (Yu Kuai)
        - Fix raid5 hang issue (Junxiao Bi)
        - Add Yu Kuai as Reviewer of the md subsystem
        - Remove deprecated flavors (Song Liu)
        - raid1 read error check support (Li Nan)
        - Better handle events off-by-1 case (Alex Lyakas)

   - Efficiency improvements for passthrough (Kundan)

   - Support for mapping integrity data directly (Keith)

   - Zoned write fix (Damien)

   - rnbd fixes (Kees, Santosh, Supriti)

   - Default to a sane discard size granularity (Christoph)

   - Make the default max transfer size naming less confusing
     (Christoph)

   - Remove support for deprecated host aware zoned model (Christoph)

   - Misc fixes (me, Li, Matthew, Min, Ming, Randy, liyouhong, Daniel,
     Bart, Christoph)"

* tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux: (78 commits)
  block: Treat sequential write preferred zone type as invalid
  block: remove disk_clear_zoned
  sd: remove the !ZBC && blk_queue_is_zoned case in sd_read_block_characteristics
  drivers/block/xen-blkback/common.h: Fix spelling typo in comment
  blk-cgroup: fix rcu lockdep warning in blkg_lookup()
  blk-cgroup: don't use removal safe list iterators
  block: floor the discard granularity to the physical block size
  mtd_blkdevs: use the default discard granularity
  bcache: use the default discard granularity
  zram: use the default discard granularity
  null_blk: use the default discard granularity
  nbd: use the default discard granularity
  ubd: use the default discard granularity
  block: default the discard granularity to sector size
  bcache: discard_granularity should not be smaller than a sector
  block: remove two comments in bio_split_discard
  block: rename and document BLK_DEF_MAX_SECTORS
  loop: don't abuse BLK_DEF_MAX_SECTORS
  aoe: don't abuse BLK_DEF_MAX_SECTORS
  null_blk: don't cap max_hw_sectors to BLK_DEF_MAX_SECTORS
  ...

8 files changed, 303 insertions, 318 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 60f14019f981..0af612387083 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 */
@@ -372,9 +373,12 @@ 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)
@@ -793,8 +797,8 @@ 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 +806,9 @@ 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 +846,7 @@ 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 +874,18 @@ 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 +917,15 @@ 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 +933,12 @@ 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;
@@ -1452,7 +1460,7 @@ 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 = { };
@@ -1671,14 +1679,14 @@ 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 +1704,7 @@ 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);
@@ -1717,25 +1725,26 @@ 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);
 
-	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->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
+		ctrl->max_discard_sectors =
+			nvme_lba_to_sect(head, ctrl->dmrsl);
 
 	if (ctrl->max_discard_sectors == 0) {
 		blk_queue_max_discard_sectors(queue, 0);
@@ -1766,21 +1775,21 @@ 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 +1798,11 @@ 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 +1812,13 @@ 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 +1827,25 @@ 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 +1857,7 @@ 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 +1868,8 @@ 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 +1878,9 @@ 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 +1903,11 @@ 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 +1915,7 @@ 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 +1932,7 @@ 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 +1958,20 @@ 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 +1994,7 @@ 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 +2061,17 @@ 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 +2088,7 @@ 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 +2101,7 @@ 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,
@@ -3026,6 +3036,42 @@ 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 +3184,9 @@ 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 +3445,8 @@ 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 +3706,7 @@ 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))
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 043f2d7798c1..16847a316421 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3498,10 +3498,6 @@ 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;
@@ -3546,6 +3542,8 @@ 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 */
 
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 4939ed35638f..093e46f16e6c 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -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 == sizeof(struct t10_pi_tuple)) {
 		/*
 		 * 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 0a88d7bdc5e3..2dd4137a08b2 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -579,7 +579,7 @@ 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;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index e7411dac00f7..4be7f6822966 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>
 
@@ -450,13 +451,27 @@ 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;
 	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 +513,6 @@ 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
@@ -523,9 +527,9 @@ struct nvme_ns {
 };
 
 /* 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);
 }
 
 /*
@@ -873,10 +877,12 @@ 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;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 81e2621169e5..c89503da24d7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1423,7 +1423,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		goto mr_put;
 
 	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->pi_type);
+				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));
@@ -2017,7 +2017,7 @@ 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;
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index c6b7fbd4d34d..ac24ad102380 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -114,12 +114,97 @@ 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)
+		goto out_free_id;
+
+	ns->head->nuse = le64_to_cpu(id->nuse);
+
+out_free_id:
+	kfree(id);
+
+	return ret;
+}
+
+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,
@@ -127,7 +212,7 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	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);
@@ -157,13 +242,13 @@ 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,
 };
 
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index ec8557810c21..499bbb0eee8d 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)