Merge tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
     - Device initialization memory leak fixes (Keith)
     - More constants defined (Weiwen)
     - Target debugfs support (Hannes)
     - PCIe subsystem reset enhancements (Keith)
     - Queue-depth multipath policy (Redhat and PureStorage)
     - Implement get_unique_id (Christoph)
     - Authentication error fixes (Gaosheng)

 - MD updates via Song
     - sync_action fix and refactoring (Yu Kuai)
     - Various small fixes (Christoph Hellwig, Li Nan, and Ofir Gal, Yu
       Kuai, Benjamin Marzinski, Christophe JAILLET, Yang Li)

 - Fix loop detach/open race (Gulam)

 - Fix lower control limit for blk-throttle (Yu)

 - Add module descriptions to various drivers (Jeff)

 - Add support for atomic writes for block devices, and statx reporting
   for same. Includes SCSI and NVMe (John, Prasad, Alan)

 - Add IO priority information to block trace points (Dongliang)

 - Various zone improvements and tweaks (Damien)

 - mq-deadline tag reservation improvements (Bart)

 - Ignore direct reclaim swap writes in writeback throttling (Baokun)

 - Block integrity improvements and fixes (Anuj)

 - Add basic support for rust based block drivers. Has a dummy null_blk
   variant for now (Andreas)

 - Series converting driver settings to queue limits, and cleanups and
   fixes related to that (Christoph)

 - Cleanup for poking too deeply into the bvec internals, in preparation
   for DMA mapping API changes (Christoph)

 - Various minor tweaks and fixes (Jiapeng, John, Kanchan, Mikulas,
   Ming, Zhu, Damien, Christophe, Chaitanya)

* tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux: (206 commits)
  floppy: add missing MODULE_DESCRIPTION() macro
  loop: add missing MODULE_DESCRIPTION() macro
  ublk_drv: add missing MODULE_DESCRIPTION() macro
  xen/blkback: add missing MODULE_DESCRIPTION() macro
  block/rnbd: Constify struct kobj_type
  block: take offset into account in blk_bvec_map_sg again
  block: fix get_max_segment_size() warning
  loop: Don't bother validating blocksize
  virtio_blk: Don't bother validating blocksize
  null_blk: Don't bother validating blocksize
  block: Validate logical block size in blk_validate_limits()
  virtio_blk: Fix default logical block size fallback
  nvmet-auth: fix nvmet_auth hash error handling
  nvme: implement ->get_unique_id
  block: pass a phys_addr_t to get_max_segment_size
  block: add a bvec_phys helper
  blk-lib: check for kill signal in ioctl BLKZEROOUT
  block: limit the Write Zeroes to manually writing zeroes fallback
  block: refacto blkdev_issue_zeroout
  block: move read-only and supported checks into (__)blkdev_issue_zeroout
  ...

15 files changed, 506 insertions, 195 deletions

diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index b309c8be720f..a3caef75aa0a 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config NVME_CORE
 	tristate
-	select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
 
 config BLK_DEV_NVME
 	tristate "NVM Express block device"
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 0cfa39361d3b..b1387dc459a3 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1388,7 +1388,7 @@ static void devm_apple_nvme_mempool_destroy(void *data)
 	mempool_destroy(data);
 }
 
-static int apple_nvme_probe(struct platform_device *pdev)
+static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct apple_nvme *anv;
@@ -1396,7 +1396,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
 
 	anv = devm_kzalloc(dev, sizeof(*anv), GFP_KERNEL);
 	if (!anv)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	anv->dev = get_device(dev);
 	anv->adminq.is_adminq = true;
@@ -1516,10 +1516,30 @@ static int apple_nvme_probe(struct platform_device *pdev)
 		goto put_dev;
 	}
 
+	return anv;
+put_dev:
+	put_device(anv->dev);
+	return ERR_PTR(ret);
+}
+
+static int apple_nvme_probe(struct platform_device *pdev)
+{
+	struct apple_nvme *anv;
+	int ret;
+
+	anv = apple_nvme_alloc(pdev);
+	if (IS_ERR(anv))
+		return PTR_ERR(anv);
+
+	ret = nvme_add_ctrl(&anv->ctrl);
+	if (ret)
+		goto out_put_ctrl;
+
 	anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
 	if (IS_ERR(anv->ctrl.admin_q)) {
 		ret = -ENOMEM;
-		goto put_dev;
+		anv->ctrl.admin_q = NULL;
+		goto out_uninit_ctrl;
 	}
 
 	nvme_reset_ctrl(&anv->ctrl);
@@ -1527,8 +1547,10 @@ static int apple_nvme_probe(struct platform_device *pdev)
 
 	return 0;
 
-put_dev:
-	put_device(anv->dev);
+out_uninit_ctrl:
+	nvme_uninit_ctrl(&anv->ctrl);
+out_put_ctrl:
+	nvme_put_ctrl(&anv->ctrl);
 	return ret;
 }
 
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 6f2ebb5fcdb0..2b9e6cfaf2a8 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -173,7 +173,7 @@ static const char * const nvme_statuses[] = {
 
 const char *nvme_get_error_status_str(u16 status)
 {
-	status &= 0x7ff;
+	status &= NVME_SCT_SC_MASK;
 	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
 		return nvme_statuses[status];
 	return "Unknown";
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 782090ce0bc1..19917253ba7b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -110,7 +110,7 @@ struct workqueue_struct *nvme_delete_wq;
 EXPORT_SYMBOL_GPL(nvme_delete_wq);
 
 static LIST_HEAD(nvme_subsystems);
-static DEFINE_MUTEX(nvme_subsystems_lock);
+DEFINE_MUTEX(nvme_subsystems_lock);
 
 static DEFINE_IDA(nvme_instance_ida);
 static dev_t nvme_ctrl_base_chr_devt;
@@ -261,7 +261,7 @@ void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
 
 static blk_status_t nvme_error_status(u16 status)
 {
-	switch (status & 0x7ff) {
+	switch (status & NVME_SCT_SC_MASK) {
 	case NVME_SC_SUCCESS:
 		return BLK_STS_OK;
 	case NVME_SC_CAP_EXCEEDED:
@@ -307,7 +307,7 @@ static void nvme_retry_req(struct request *req)
 	u16 crd;
 
 	/* The mask and shift result must be <= 3 */
-	crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
+	crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11;
 	if (crd)
 		delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
 
@@ -329,10 +329,10 @@ static void nvme_log_error(struct request *req)
 		       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 */
-		       nr->status & NVME_SC_MORE ? "MORE " : "",
-		       nr->status & NVME_SC_DNR  ? "DNR "  : "");
+		       NVME_SCT(nr->status),		/* Status Code Type */
+		       nr->status & NVME_SC_MASK,	/* Status Code */
+		       nr->status & NVME_STATUS_MORE ? "MORE " : "",
+		       nr->status & NVME_STATUS_DNR  ? "DNR "  : "");
 		return;
 	}
 
@@ -341,10 +341,10 @@ static void nvme_log_error(struct request *req)
 			   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 "  : "");
+			   NVME_SCT(nr->status),	/* Status Code Type */
+			   nr->status & NVME_SC_MASK,	/* Status Code */
+			   nr->status & NVME_STATUS_MORE ? "MORE " : "",
+			   nr->status & NVME_STATUS_DNR  ? "DNR "  : "");
 }
 
 static void nvme_log_err_passthru(struct request *req)
@@ -359,10 +359,10 @@ static void nvme_log_err_passthru(struct request *req)
 		     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 "  : "",
+		NVME_SCT(nr->status),		/* Status Code Type */
+		nr->status & NVME_SC_MASK,	/* Status Code */
+		nr->status & NVME_STATUS_MORE ? "MORE " : "",
+		nr->status & NVME_STATUS_DNR  ? "DNR "  : "",
 		nr->cmd->common.cdw10,
 		nr->cmd->common.cdw11,
 		nr->cmd->common.cdw12,
@@ -384,11 +384,11 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 		return COMPLETE;
 
 	if (blk_noretry_request(req) ||
-	    (nvme_req(req)->status & NVME_SC_DNR) ||
+	    (nvme_req(req)->status & NVME_STATUS_DNR) ||
 	    nvme_req(req)->retries >= nvme_max_retries)
 		return COMPLETE;
 
-	if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
+	if ((nvme_req(req)->status & NVME_SCT_SC_MASK) == NVME_SC_AUTH_REQUIRED)
 		return AUTHENTICATE;
 
 	if (req->cmd_flags & REQ_NVME_MPATH) {
@@ -927,6 +927,36 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 	return BLK_STS_OK;
 }
 
+/*
+ * NVMe does not support a dedicated command to issue an atomic write. A write
+ * which does adhere to the device atomic limits will silently be executed
+ * non-atomically. The request issuer should ensure that the write is within
+ * the queue atomic writes limits, but just validate this in case it is not.
+ */
+static bool nvme_valid_atomic_write(struct request *req)
+{
+	struct request_queue *q = req->q;
+	u32 boundary_bytes = queue_atomic_write_boundary_bytes(q);
+
+	if (blk_rq_bytes(req) > queue_atomic_write_unit_max_bytes(q))
+		return false;
+
+	if (boundary_bytes) {
+		u64 mask = boundary_bytes - 1, imask = ~mask;
+		u64 start = blk_rq_pos(req) << SECTOR_SHIFT;
+		u64 end = start + blk_rq_bytes(req) - 1;
+
+		/* If greater then must be crossing a boundary */
+		if (blk_rq_bytes(req) > boundary_bytes)
+			return false;
+
+		if ((start & imask) != (end & imask))
+			return false;
+	}
+
+	return true;
+}
+
 static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		struct request *req, struct nvme_command *cmnd,
 		enum nvme_opcode op)
@@ -942,6 +972,9 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
+	if (req->cmd_flags & REQ_ATOMIC && !nvme_valid_atomic_write(req))
+		return BLK_STS_INVAL;
+
 	cmnd->rw.opcode = op;
 	cmnd->rw.flags = 0;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
@@ -1224,7 +1257,7 @@ EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU);
 
 /*
  * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1:
- * 
+ *
  *   The host should send Keep Alive commands at half of the Keep Alive Timeout
  *   accounting for transport roundtrip times [..].
  */
@@ -1724,11 +1757,12 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head)
+static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head,
+		struct queue_limits *lim)
 {
-	struct blk_integrity integrity = { };
+	struct blk_integrity *bi = &lim->integrity;
 
-	blk_integrity_unregister(disk);
+	memset(bi, 0, sizeof(*bi));
 
 	if (!head->ms)
 		return true;
@@ -1745,17 +1779,16 @@ static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head)
 	case NVME_NS_DPS_PI_TYPE3:
 		switch (head->guard_type) {
 		case NVME_NVM_NS_16B_GUARD:
-			integrity.profile = &t10_pi_type3_crc;
-			integrity.tag_size = sizeof(u16) + sizeof(u32);
-			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			bi->csum_type = BLK_INTEGRITY_CSUM_CRC;
+			bi->tag_size = sizeof(u16) + sizeof(u32);
+			bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
 			break;
 		case NVME_NVM_NS_64B_GUARD:
-			integrity.profile = &ext_pi_type3_crc64;
-			integrity.tag_size = sizeof(u16) + 6;
-			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			bi->csum_type = BLK_INTEGRITY_CSUM_CRC64;
+			bi->tag_size = sizeof(u16) + 6;
+			bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
 			break;
 		default:
-			integrity.profile = NULL;
 			break;
 		}
 		break;
@@ -1763,28 +1796,27 @@ static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head)
 	case NVME_NS_DPS_PI_TYPE2:
 		switch (head->guard_type) {
 		case NVME_NVM_NS_16B_GUARD:
-			integrity.profile = &t10_pi_type1_crc;
-			integrity.tag_size = sizeof(u16);
-			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			bi->csum_type = BLK_INTEGRITY_CSUM_CRC;
+			bi->tag_size = sizeof(u16);
+			bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE |
+				     BLK_INTEGRITY_REF_TAG;
 			break;
 		case NVME_NVM_NS_64B_GUARD:
-			integrity.profile = &ext_pi_type1_crc64;
-			integrity.tag_size = sizeof(u16);
-			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			bi->csum_type = BLK_INTEGRITY_CSUM_CRC64;
+			bi->tag_size = sizeof(u16);
+			bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE |
+				     BLK_INTEGRITY_REF_TAG;
 			break;
 		default:
-			integrity.profile = NULL;
 			break;
 		}
 		break;
 	default:
-		integrity.profile = NULL;
 		break;
 	}
 
-	integrity.tuple_size = head->ms;
-	integrity.pi_offset = head->pi_offset;
-	blk_integrity_register(disk, &integrity);
+	bi->tuple_size = head->ms;
+	bi->pi_offset = head->pi_offset;
 	return true;
 }
 
@@ -1922,6 +1954,23 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
 	}
 }
 
+
+static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns,
+			struct nvme_id_ns *id, struct queue_limits *lim,
+			u32 bs, u32 atomic_bs)
+{
+	unsigned int boundary = 0;
+
+	if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) {
+		if (le16_to_cpu(id->nabspf))
+			boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
+	}
+	lim->atomic_write_hw_max = atomic_bs;
+	lim->atomic_write_hw_boundary = boundary;
+	lim->atomic_write_hw_unit_min = bs;
+	lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs);
+}
+
 static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
 {
 	return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1;
@@ -1968,13 +2017,16 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
 			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+
+		nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
 	}
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
 		/* NPWG = Namespace Preferred Write Granularity */
 		phys_bs = bs * (1 + le16_to_cpu(id->npwg));
 		/* NOWS = Namespace Optimal Write Size */
-		io_opt = bs * (1 + le16_to_cpu(id->nows));
+		if (id->nows)
+			io_opt = bs * (1 + le16_to_cpu(id->nows));
 	}
 
 	/*
@@ -2058,7 +2110,6 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
 static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
-	bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
 	struct queue_limits lim;
 	struct nvme_id_ns_nvm *nvm = NULL;
 	struct nvme_zone_info zi = {};
@@ -2107,11 +2158,11 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    ns->head->ids.csi == NVME_CSI_ZNS)
 		nvme_update_zone_info(ns, &lim, &zi);
-	ret = queue_limits_commit_update(ns->disk->queue, &lim);
-	if (ret) {
-		blk_mq_unfreeze_queue(ns->disk->queue);
-		goto out;
-	}
+
+	if (ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT)
+		lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
+	else
+		lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
 
 	/*
 	 * Register a metadata profile for PI, or the plain non-integrity NVMe
@@ -2119,9 +2170,15 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	 * I/O to namespaces with metadata except when the namespace supports
 	 * PI, as it can strip/insert in that case.
 	 */
-	if (!nvme_init_integrity(ns->disk, ns->head))
+	if (!nvme_init_integrity(ns->disk, ns->head, &lim))
 		capacity = 0;
 
+	ret = queue_limits_commit_update(ns->disk->queue, &lim);
+	if (ret) {
+		blk_mq_unfreeze_queue(ns->disk->queue);
+		goto out;
+	}
+
 	set_capacity_and_notify(ns->disk, capacity);
 
 	/*
@@ -2133,7 +2190,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
 		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
-	blk_queue_write_cache(ns->disk->queue, vwc, vwc);
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
@@ -2193,14 +2249,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		struct queue_limits lim;
 
 		blk_mq_freeze_queue(ns->head->disk->queue);
-		if (unsupported)
-			ns->head->disk->flags |= GENHD_FL_HIDDEN;
-		else
-			nvme_init_integrity(ns->head->disk, ns->head);
-		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
-		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
-		nvme_mpath_revalidate_paths(ns);
-
 		/*
 		 * queue_limits mixes values that are the hardware limitations
 		 * for bio splitting with what is the device configuration.
@@ -2223,13 +2271,48 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		lim.io_opt = ns_lim->io_opt;
 		queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
 					ns->head->disk->disk_name);
+		if (unsupported)
+			ns->head->disk->flags |= GENHD_FL_HIDDEN;
+		else
+			nvme_init_integrity(ns->head->disk, ns->head, &lim);
 		ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
+
+		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
+		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
+		nvme_mpath_revalidate_paths(ns);
+
 		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
 
 	return ret;
 }
 
+int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16],
+		enum blk_unique_id type)
+{
+	struct nvme_ns_ids *ids = &ns->head->ids;
+
+	if (type != BLK_UID_EUI64)
+		return -EINVAL;
+
+	if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) {
+		memcpy(id, &ids->nguid, sizeof(ids->nguid));
+		return sizeof(ids->nguid);
+	}
+	if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) {
+		memcpy(id, &ids->eui64, sizeof(ids->eui64));
+		return sizeof(ids->eui64);
+	}
+
+	return -EINVAL;
+}
+
+static int nvme_get_unique_id(struct gendisk *disk, u8 id[16],
+		enum blk_unique_id type)
+{
+	return nvme_ns_get_unique_id(disk->private_data, id, type);
+}
+
 #ifdef CONFIG_BLK_SED_OPAL
 static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 		bool send)
@@ -2285,6 +2368,7 @@ const struct block_device_operations nvme_bdev_ops = {
 	.open		= nvme_open,
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
+	.get_unique_id	= nvme_get_unique_id,
 	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
@@ -3721,6 +3805,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
 
 static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 {
+	struct queue_limits lim = { };
 	struct nvme_ns *ns;
 	struct gendisk *disk;
 	int node = ctrl->numa_node;
@@ -3729,7 +3814,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	if (!ns)
 		return;
 
-	disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns);
+	if (ctrl->opts && ctrl->opts->data_digest)
+		lim.features |= BLK_FEAT_STABLE_WRITES;
+	if (ctrl->ops->supports_pci_p2pdma &&
+	    ctrl->ops->supports_pci_p2pdma(ctrl))
+		lim.features |= BLK_FEAT_PCI_P2PDMA;
+
+	disk = blk_mq_alloc_disk(ctrl->tagset, &lim, ns);
 	if (IS_ERR(disk))
 		goto out_free_ns;
 	disk->fops = &nvme_bdev_ops;
@@ -3737,15 +3828,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
 	ns->disk = disk;
 	ns->queue = disk->queue;
-
-	if (ctrl->opts && ctrl->opts->data_digest)
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
-
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
-	if (ctrl->ops->supports_pci_p2pdma &&
-	    ctrl->ops->supports_pci_p2pdma(ctrl))
-		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
-
 	ns->ctrl = ctrl;
 	kref_init(&ns->kref);
 
@@ -3887,7 +3969,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
 
 static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info)
 {
-	int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
+	int ret = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
 
 	if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) {
 		dev_err(ns->ctrl->device,
@@ -3903,7 +3985,7 @@ out:
 	 *
 	 * TODO: we should probably schedule a delayed retry here.
 	 */
-	if (ret > 0 && (ret & NVME_SC_DNR))
+	if (ret > 0 && (ret & NVME_STATUS_DNR))
 		nvme_ns_remove(ns);
 }
 
@@ -4095,7 +4177,7 @@ static void nvme_scan_work(struct work_struct *work)
 		 * they report) but don't actually support it.
 		 */
 		ret = nvme_scan_ns_list(ctrl);
-		if (ret > 0 && ret & NVME_SC_DNR)
+		if (ret > 0 && ret & NVME_STATUS_DNR)
 			nvme_scan_ns_sequential(ctrl);
 	}
 	mutex_unlock(&ctrl->scan_lock);
@@ -4489,13 +4571,15 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		return ret;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
-		ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL);
+		struct queue_limits lim = {
+			.features	= BLK_FEAT_SKIP_TAGSET_QUIESCE,
+		};
+
+		ctrl->connect_q = blk_mq_alloc_queue(set, &lim, NULL);
         	if (IS_ERR(ctrl->connect_q)) {
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
 		}
-		blk_queue_flag_set(QUEUE_FLAG_SKIP_TAGSET_QUIESCE,
-				   ctrl->connect_q);
 	}
 
 	ctrl->tagset = set;
@@ -4613,6 +4697,9 @@ static void nvme_free_ctrl(struct device *dev)
  * Initialize a NVMe controller structures.  This needs to be called during
  * earliest initialization so that we have the initialized structured around
  * during probing.
+ *
+ * On success, the caller must use the nvme_put_ctrl() to release this when
+ * needed, which also invokes the ops->free_ctrl() callback.
  */
 int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		const struct nvme_ctrl_ops *ops, unsigned long quirks)
@@ -4661,6 +4748,12 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		goto out;
 	ctrl->instance = ret;
 
+	ret = nvme_auth_init_ctrl(ctrl);
+	if (ret)
+		goto out_release_instance;
+
+	nvme_mpath_init_ctrl(ctrl);
+
 	device_initialize(&ctrl->ctrl_device);
 	ctrl->device = &ctrl->ctrl_device;
 	ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
@@ -4673,16 +4766,36 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		ctrl->device->groups = nvme_dev_attr_groups;
 	ctrl->device->release = nvme_free_ctrl;
 	dev_set_drvdata(ctrl->device, ctrl);
+
+	return ret;
+
+out_release_instance:
+	ida_free(&nvme_instance_ida, ctrl->instance);
+out:
+	if (ctrl->discard_page)
+		__free_page(ctrl->discard_page);
+	cleanup_srcu_struct(&ctrl->srcu);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+
+/*
+ * On success, returns with an elevated controller reference and caller must
+ * use nvme_uninit_ctrl() to properly free resources associated with the ctrl.
+ */
+int nvme_add_ctrl(struct nvme_ctrl *ctrl)
+{
+	int ret;
+
 	ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance);
 	if (ret)
-		goto out_release_instance;
+		return ret;
 
-	nvme_get_ctrl(ctrl);
 	cdev_init(&ctrl->cdev, &nvme_dev_fops);
-	ctrl->cdev.owner = ops->module;
+	ctrl->cdev.owner = ctrl->ops->module;
 	ret = cdev_device_add(&ctrl->cdev, ctrl->device);
 	if (ret)
-		goto out_free_name;
+		return ret;
 
 	/*
 	 * Initialize latency tolerance controls.  The sysfs files won't
@@ -4693,28 +4806,11 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		min(default_ps_max_latency_us, (unsigned long)S32_MAX));
 
 	nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));
-	nvme_mpath_init_ctrl(ctrl);
-	ret = nvme_auth_init_ctrl(ctrl);
-	if (ret)
-		goto out_free_cdev;
+	nvme_get_ctrl(ctrl);
 
 	return 0;
-out_free_cdev:
-	nvme_fault_inject_fini(&ctrl->fault_inject);
-	dev_pm_qos_hide_latency_tolerance(ctrl->device);
-	cdev_device_del(&ctrl->cdev, ctrl->device);
-out_free_name:
-	nvme_put_ctrl(ctrl);
-	kfree_const(ctrl->device->kobj.name);
-out_release_instance:
-	ida_free(&nvme_instance_ida, ctrl->instance);
-out:
-	if (ctrl->discard_page)
-		__free_page(ctrl->discard_page);
-	cleanup_srcu_struct(&ctrl->srcu);
-	return ret;
 }
-EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+EXPORT_SYMBOL_GPL(nvme_add_ctrl);
 
 /* let I/O to all namespaces fail in preparation for surprise removal */
 void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index ceb9c0ed3120..44e342a46f39 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -187,7 +187,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	if (unlikely(ret != 0))
 		dev_err(ctrl->device,
 			"Property Get error: %d, offset %#x\n",
-			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+			ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
 
 	return ret;
 }
@@ -233,7 +233,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	if (unlikely(ret != 0))
 		dev_err(ctrl->device,
 			"Property Get error: %d, offset %#x\n",
-			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+			ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvmf_reg_read64);
@@ -275,11 +275,26 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",
-			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+			ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvmf_reg_write32);
 
+int nvmf_subsystem_reset(struct nvme_ctrl *ctrl)
+{
+	int ret;
+
+	if (!nvme_wait_reset(ctrl))
+		return -EBUSY;
+
+	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, NVME_SUBSYS_RESET);
+	if (ret)
+		return ret;
+
+	return nvme_try_sched_reset(ctrl);
+}
+EXPORT_SYMBOL_GPL(nvmf_subsystem_reset);
+
 /**
  * nvmf_log_connect_error() - Error-parsing-diagnostic print out function for
  * 				connect() errors.
@@ -295,7 +310,7 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 		int errval, int offset, struct nvme_command *cmd,
 		struct nvmf_connect_data *data)
 {
-	int err_sctype = errval & ~NVME_SC_DNR;
+	int err_sctype = errval & ~NVME_STATUS_DNR;
 
 	if (errval < 0) {
 		dev_err(ctrl->device,
@@ -573,7 +588,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
  */
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status)
 {
-	if (status > 0 && (status & NVME_SC_DNR))
+	if (status > 0 && (status & NVME_STATUS_DNR))
 		return false;
 
 	if (status == -EKEYREJECTED)
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 602135910ae9..21d75dc4a3a0 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -217,6 +217,7 @@ static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts)
 int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
+int nvmf_subsystem_reset(struct nvme_ctrl *ctrl);
 int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
 int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
 int nvmf_register_transport(struct nvmf_transport_ops *ops);
diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c
index 1ba10a5c656d..1d1b6441a339 100644
--- a/drivers/nvme/host/fault_inject.c
+++ b/drivers/nvme/host/fault_inject.c
@@ -75,7 +75,7 @@ void nvme_should_fail(struct request *req)
 		/* inject status code and DNR bit */
 		status = fault_inject->status;
 		if (fault_inject->dont_retry)
-			status |= NVME_SC_DNR;
+			status |= NVME_STATUS_DNR;
 		nvme_req(req)->status =	status;
 	}
 }
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index f0b081332749..b81af7919e94 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3132,7 +3132,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (ctrl->ctrl.icdoff) {
 		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
 				ctrl->ctrl.icdoff);
-		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
 		goto out_stop_keep_alive;
 	}
 
@@ -3140,7 +3140,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) {
 		dev_err(ctrl->ctrl.device,
 			"Mandatory sgls are not supported!\n");
-		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
 		goto out_stop_keep_alive;
 	}
 
@@ -3325,7 +3325,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 		queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay);
 	} else {
 		if (portptr->port_state == FC_OBJSTATE_ONLINE) {
-			if (status > 0 && (status & NVME_SC_DNR))
+			if (status > 0 && (status & NVME_STATUS_DNR))
 				dev_warn(ctrl->ctrl.device,
 					 "NVME-FC{%d}: reconnect failure\n",
 					 ctrl->cnum);
@@ -3382,6 +3382,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
+	.subsystem_reset	= nvmf_subsystem_reset,
 	.free_ctrl		= nvme_fc_free_ctrl,
 	.submit_async_event	= nvme_fc_submit_async_event,
 	.delete_ctrl		= nvme_fc_delete_ctrl,
@@ -3444,12 +3445,11 @@ nvme_fc_existing_controller(struct nvme_fc_rport *rport,
 	return found;
 }
 
-static struct nvme_ctrl *
-nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
+static struct nvme_fc_ctrl *
+nvme_fc_alloc_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	struct nvme_fc_lport *lport, struct nvme_fc_rport *rport)
 {
 	struct nvme_fc_ctrl *ctrl;
-	unsigned long flags;
 	int ret, idx, ctrl_loss_tmo;
 
 	if (!(rport->remoteport.port_role &
@@ -3538,7 +3538,35 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	if (lport->dev)
 		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
 
-	/* at this point, teardown path changes to ref counting on nvme ctrl */
+	return ctrl;
+
+out_free_queues:
+	kfree(ctrl->queues);
+out_free_ida:
+	put_device(ctrl->dev);
+	ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum);
+out_free_ctrl:
+	kfree(ctrl);
+out_fail:
+	/* exit via here doesn't follow ctlr ref points */
+	return ERR_PTR(ret);
+}
+
+static struct nvme_ctrl *
+nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
+	struct nvme_fc_lport *lport, struct nvme_fc_rport *rport)
+{
+	struct nvme_fc_ctrl *ctrl;
+	unsigned long flags;
+	int ret;
+
+	ctrl = nvme_fc_alloc_ctrl(dev, opts, lport, rport);
+	if (IS_ERR(ctrl))
+		return ERR_CAST(ctrl);
+
+	ret = nvme_add_ctrl(&ctrl->ctrl);
+	if (ret)
+		goto out_put_ctrl;
 
 	ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
 			&nvme_fc_admin_mq_ops,
@@ -3584,6 +3612,7 @@ fail_ctrl:
 	/* initiate nvme ctrl ref counting teardown */
 	nvme_uninit_ctrl(&ctrl->ctrl);
 
+out_put_ctrl:
 	/* Remove core ctrl ref. */
 	nvme_put_ctrl(&ctrl->ctrl);
 
@@ -3597,20 +3626,8 @@ fail_ctrl:
 	nvme_fc_rport_get(rport);
 
 	return ERR_PTR(-EIO);
-
-out_free_queues:
-	kfree(ctrl->queues);
-out_free_ida:
-	put_device(ctrl->dev);
-	ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum);
-out_free_ctrl:
-	kfree(ctrl);
-out_fail:
-	/* exit via here doesn't follow ctlr ref points */
-	return ERR_PTR(ret);
 }
 
-
 struct nvmet_fc_traddr {
 	u64	nn;
 	u64	pn;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index d8b6b4648eaf..91d9eb3c22ef 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -17,6 +17,7 @@ MODULE_PARM_DESC(multipath,
 static const char *nvme_iopolicy_names[] = {
 	[NVME_IOPOLICY_NUMA]	= "numa",
 	[NVME_IOPOLICY_RR]	= "round-robin",
+	[NVME_IOPOLICY_QD]      = "queue-depth",
 };
 
 static int iopolicy = NVME_IOPOLICY_NUMA;
@@ -29,6 +30,8 @@ static int nvme_set_iopolicy(const char *val, const struct kernel_param *kp)
 		iopolicy = NVME_IOPOLICY_NUMA;
 	else if (!strncmp(val, "round-robin", 11))
 		iopolicy = NVME_IOPOLICY_RR;
+	else if (!strncmp(val, "queue-depth", 11))
+		iopolicy = NVME_IOPOLICY_QD;
 	else
 		return -EINVAL;
 
@@ -43,7 +46,7 @@ static int nvme_get_iopolicy(char *buf, const struct kernel_param *kp)
 module_param_call(iopolicy, nvme_set_iopolicy, nvme_get_iopolicy,
 	&iopolicy, 0644);
 MODULE_PARM_DESC(iopolicy,
-	"Default multipath I/O policy; 'numa' (default) or 'round-robin'");
+	"Default multipath I/O policy; 'numa' (default), 'round-robin' or 'queue-depth'");
 
 void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
 {
@@ -83,7 +86,7 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
-	u16 status = nvme_req(req)->status & 0x7ff;
+	u16 status = nvme_req(req)->status & NVME_SCT_SC_MASK;
 	unsigned long flags;
 	struct bio *bio;
 
@@ -128,6 +131,11 @@ void nvme_mpath_start_request(struct request *rq)
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct gendisk *disk = ns->head->disk;
 
+	if (READ_ONCE(ns->head->subsys->iopolicy) == NVME_IOPOLICY_QD) {
+		atomic_inc(&ns->ctrl->nr_active);
+		nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
+	}
+
 	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq))
 		return;
 
@@ -141,6 +149,9 @@ void nvme_mpath_end_request(struct request *rq)
 {
 	struct nvme_ns *ns = rq->q->queuedata;
 
+	if (nvme_req(rq)->flags & NVME_MPATH_CNT_ACTIVE)
+		atomic_dec_if_positive(&ns->ctrl->nr_active);
+
 	if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
 		return;
 	bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
@@ -291,10 +302,15 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
 	return list_first_or_null_rcu(&head->list, struct nvme_ns, siblings);
 }
 
-static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
-		int node, struct nvme_ns *old)
+static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns, *found = NULL;
+	int node = numa_node_id();
+	struct nvme_ns *old = srcu_dereference(head->current_path[node],
+					       &head->srcu);
+
+	if (unlikely(!old))
+		return __nvme_find_path(head, node);
 
 	if (list_is_singular(&head->list)) {
 		if (nvme_path_is_disabled(old))
@@ -334,13 +350,49 @@ out:
 	return found;
 }
 
+static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
+{
+	struct nvme_ns *best_opt = NULL, *best_nonopt = NULL, *ns;
+	unsigned int min_depth_opt = UINT_MAX, min_depth_nonopt = UINT_MAX;
+	unsigned int depth;
+
+	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		if (nvme_path_is_disabled(ns))
+			continue;
+
+		depth = atomic_read(&ns->ctrl->nr_active);
+
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
+			if (depth < min_depth_opt) {
+				min_depth_opt = depth;
+				best_opt = ns;
+			}
+			break;
+		case NVME_ANA_NONOPTIMIZED:
+			if (depth < min_depth_nonopt) {
+				min_depth_nonopt = depth;
+				best_nonopt = ns;
+			}
+			break;
+		default:
+			break;
+		}
+
+		if (min_depth_opt == 0)
+			return best_opt;
+	}
+
+	return best_opt ? best_opt : best_nonopt;
+}
+
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
 	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
 		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
-inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
 {
 	int node = numa_node_id();
 	struct nvme_ns *ns;
@@ -348,14 +400,23 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	ns = srcu_dereference(head->current_path[node], &head->srcu);
 	if (unlikely(!ns))
 		return __nvme_find_path(head, node);
-
-	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
-		return nvme_round_robin_path(head, node, ns);
 	if (unlikely(!nvme_path_is_optimized(ns)))
 		return __nvme_find_path(head, node);
 	return ns;
 }
 
+inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+{
+	switch (READ_ONCE(head->subsys->iopolicy)) {
+	case NVME_IOPOLICY_QD:
+		return nvme_queue_depth_path(head);
+	case NVME_IOPOLICY_RR:
+		return nvme_round_robin_path(head);
+	default:
+		return nvme_numa_path(head);
+	}
+}
+
 static bool nvme_available_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns;
@@ -427,6 +488,21 @@ static void nvme_ns_head_release(struct gendisk *disk)
 	nvme_put_ns_head(disk->private_data);
 }
 
+static int nvme_ns_head_get_unique_id(struct gendisk *disk, u8 id[16],
+		enum blk_unique_id type)
+{
+	struct nvme_ns_head *head = disk->private_data;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (ns)
+		ret = nvme_ns_get_unique_id(ns, id, type);
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+
 #ifdef CONFIG_BLK_DEV_ZONED
 static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data)
@@ -454,6 +530,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.ioctl		= nvme_ns_head_ioctl,
 	.compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= nvme_getgeo,
+	.get_unique_id	= nvme_ns_head_get_unique_id,
 	.report_zones	= nvme_ns_head_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
@@ -521,7 +598,6 @@ static void nvme_requeue_work(struct work_struct *work)
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 {
 	struct queue_limits lim;
-	bool vwc = false;
 
 	mutex_init(&head->lock);
 	bio_list_init(&head->requeue_list);
@@ -539,6 +615,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	blk_set_stacking_limits(&lim);
 	lim.dma_alignment = 3;
+	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
 	if (head->ids.csi != NVME_CSI_ZNS)
 		lim.max_zone_append_sectors = 0;
 
@@ -549,24 +626,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	head->disk->private_data = head;
 	sprintf(head->disk->disk_name, "nvme%dn%d",
 			ctrl->subsys->instance, head->instance);
-
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue);
-	/*
-	 * This assumes all controllers that refer to a namespace either
-	 * support poll queues or not.  That is not a strict guarantee,
-	 * but if the assumption is wrong the effect is only suboptimal
-	 * performance but not correctness problem.
-	 */
-	if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL &&
-	    ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
-		blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
-
-	/* we need to propagate up the VMC settings */
-	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
-		vwc = true;
-	blk_queue_write_cache(head->disk->queue, vwc, vwc);
 	return 0;
 }
 
@@ -803,6 +862,29 @@ static ssize_t nvme_subsys_iopolicy_show(struct device *dev,
 			  nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]);
 }
 
+static void nvme_subsys_iopolicy_update(struct nvme_subsystem *subsys,
+		int iopolicy)
+{
+	struct nvme_ctrl *ctrl;
+	int old_iopolicy = READ_ONCE(subsys->iopolicy);
+
+	if (old_iopolicy == iopolicy)
+		return;
+
+	WRITE_ONCE(subsys->iopolicy, iopolicy);
+
+	/* iopolicy changes clear the mpath by design */
+	mutex_lock(&nvme_subsystems_lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		nvme_mpath_clear_ctrl_paths(ctrl);
+	mutex_unlock(&nvme_subsystems_lock);
+
+	pr_notice("subsysnqn %s iopolicy changed from %s to %s\n",
+			subsys->subnqn,
+			nvme_iopolicy_names[old_iopolicy],
+			nvme_iopolicy_names[iopolicy]);
+}
+
 static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -812,7 +894,7 @@ static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
 
 	for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) {
 		if (sysfs_streq(buf, nvme_iopolicy_names[i])) {
-			WRITE_ONCE(subsys->iopolicy, i);
+			nvme_subsys_iopolicy_update(subsys, i);
 			return count;
 		}
 	}
@@ -875,9 +957,6 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid)
 		nvme_mpath_set_live(ns);
 	}
 
-	if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
-				   ns->head->disk->queue);
 #ifdef CONFIG_BLK_DEV_ZONED
 	if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
 		ns->head->disk->nr_zones = ns->disk->nr_zones;
@@ -923,6 +1002,9 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	    !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
 		return 0;
 
+	/* initialize this in the identify path to cover controller resets */
+	atomic_set(&ctrl->nr_active, 0);
+
 	if (!ctrl->max_namespaces ||
 	    ctrl->max_namespaces > le32_to_cpu(id->nn)) {
 		dev_err(ctrl->device,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 68b400f9c42d..f900e44243ae 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -49,6 +49,7 @@ extern unsigned int admin_timeout;
 extern struct workqueue_struct *nvme_wq;
 extern struct workqueue_struct *nvme_reset_wq;
 extern struct workqueue_struct *nvme_delete_wq;
+extern struct mutex nvme_subsystems_lock;
 
 /*
  * List of workarounds for devices that required behavior not specified in
@@ -195,6 +196,7 @@ enum {
 	NVME_REQ_CANCELLED		= (1 << 0),
 	NVME_REQ_USERCMD		= (1 << 1),
 	NVME_MPATH_IO_STATS		= (1 << 2),
+	NVME_MPATH_CNT_ACTIVE		= (1 << 3),
 };
 
 static inline struct nvme_request *nvme_req(struct request *req)
@@ -360,6 +362,7 @@ struct nvme_ctrl {
 	size_t ana_log_size;
 	struct timer_list anatt_timer;
 	struct work_struct ana_work;
+	atomic_t nr_active;
 #endif
 
 #ifdef CONFIG_NVME_HOST_AUTH
@@ -408,6 +411,7 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
 enum nvme_iopolicy {
 	NVME_IOPOLICY_NUMA,
 	NVME_IOPOLICY_RR,
+	NVME_IOPOLICY_QD,
 };
 
 struct nvme_subsystem {
@@ -551,6 +555,7 @@ struct nvme_ctrl_ops {
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 	void (*free_ctrl)(struct nvme_ctrl *ctrl);
 	void (*submit_async_event)(struct nvme_ctrl *ctrl);
+	int (*subsystem_reset)(struct nvme_ctrl *ctrl);
 	void (*delete_ctrl)(struct nvme_ctrl *ctrl);
 	void (*stop_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
@@ -649,18 +654,9 @@ int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
 
 static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
 {
-	int ret;
-
-	if (!ctrl->subsystem)
+	if (!ctrl->subsystem || !ctrl->ops->subsystem_reset)
 		return -ENOTTY;
-	if (!nvme_wait_reset(ctrl))
-		return -EBUSY;
-
-	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65);
-	if (ret)
-		return ret;
-
-	return nvme_try_sched_reset(ctrl);
+	return ctrl->ops->subsystem_reset(ctrl);
 }
 
 /*
@@ -689,7 +685,7 @@ static inline u32 nvme_bytes_to_numd(size_t len)
 
 static inline bool nvme_is_ana_error(u16 status)
 {
-	switch (status & 0x7ff) {
+	switch (status & NVME_SCT_SC_MASK) {
 	case NVME_SC_ANA_TRANSITION:
 	case NVME_SC_ANA_INACCESSIBLE:
 	case NVME_SC_ANA_PERSISTENT_LOSS:
@@ -702,7 +698,7 @@ static inline bool nvme_is_ana_error(u16 status)
 static inline bool nvme_is_path_error(u16 status)
 {
 	/* check for a status code type of 'path related status' */
-	return (status & 0x700) == 0x300;
+	return (status & NVME_SCT_MASK) == NVME_SCT_PATH;
 }
 
 /*
@@ -792,6 +788,7 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, bool shutdown);
 int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
 int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		const struct nvme_ctrl_ops *ops, unsigned long quirks);
+int nvme_add_ctrl(struct nvme_ctrl *ctrl);
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
 void nvme_start_ctrl(struct nvme_ctrl *ctrl);
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
@@ -877,7 +874,7 @@ enum {
 	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 */
+	/* Retry command when NVME_STATUS_DNR is not set in the result */
 	NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
 };
 
@@ -1062,6 +1059,9 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16],
+		enum blk_unique_id type);
+
 struct nvme_zone_info {
 	u64 zone_size;
 	unsigned int max_open_zones;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 102a9fb0c65f..21f8e1b9801f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -826,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
 		struct nvme_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	struct bio_vec bv = rq_integrity_vec(req);
 
-	iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
-			rq_dma_dir(req), 0);
+	iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
 	if (dma_mapping_error(dev->dev, iod->meta_dma))
 		return BLK_STS_IOERR;
 	cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
@@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
 	        struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
 		dma_unmap_page(dev->dev, iod->meta_dma,
-			       rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
+			       rq_integrity_vec(req).bv_len, rq_dma_dir(req));
 	}
 
 	if (blk_rq_nr_phys_segments(req))
@@ -1143,6 +1143,41 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
 	spin_unlock(&nvmeq->sq_lock);
 }
 
+static int nvme_pci_subsystem_reset(struct nvme_ctrl *ctrl)
+{
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
+	int ret = 0;
+
+	/*
+	 * Taking the shutdown_lock ensures the BAR mapping is not being
+	 * altered by reset_work. Holding this lock before the RESETTING state
+	 * change, if successful, also ensures nvme_remove won't be able to
+	 * proceed to iounmap until we're done.
+	 */
+	mutex_lock(&dev->shutdown_lock);
+	if (!dev->bar_mapped_size) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
+	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	writel(NVME_SUBSYS_RESET, dev->bar + NVME_REG_NSSR);
+	nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE);
+
+	/*
+	 * Read controller status to flush the previous write and trigger a
+	 * pcie read error.
+	 */
+	readl(dev->bar + NVME_REG_CSTS);
+unlock:
+	mutex_unlock(&dev->shutdown_lock);
+	return ret;
+}
+
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 {
 	struct nvme_command c = { };
@@ -2859,6 +2894,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.reg_read64		= nvme_pci_reg_read64,
 	.free_ctrl		= nvme_pci_free_ctrl,
 	.submit_async_event	= nvme_pci_submit_async_event,
+	.subsystem_reset	= nvme_pci_subsystem_reset,
 	.get_address		= nvme_pci_get_address,
 	.print_device_info	= nvme_pci_print_device_info,
 	.supports_pci_p2pdma	= nvme_pci_supports_pci_p2pdma,
@@ -3015,6 +3051,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
+	result = nvme_add_ctrl(&dev->ctrl);
+	if (result)
+		goto out_put_ctrl;
+
 	result = nvme_dev_map(dev);
 	if (result)
 		goto out_uninit_ctrl;
@@ -3101,6 +3141,7 @@ out_dev_unmap:
 	nvme_dev_unmap(dev);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&dev->ctrl);
+out_put_ctrl:
 	nvme_put_ctrl(&dev->ctrl);
 	return result;
 }
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 8fa1ffcdaed4..7347ddf85f00 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -72,12 +72,12 @@ static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
 	return nvme_submit_sync_cmd(ns->queue, c, data, data_len);
 }
 
-static int nvme_sc_to_pr_err(int nvme_sc)
+static int nvme_status_to_pr_err(int status)
 {
-	if (nvme_is_path_error(nvme_sc))
+	if (nvme_is_path_error(status))
 		return PR_STS_PATH_FAILED;
 
-	switch (nvme_sc & 0x7ff) {
+	switch (status & NVME_SCT_SC_MASK) {
 	case NVME_SC_SUCCESS:
 		return PR_STS_SUCCESS;
 	case NVME_SC_RESERVATION_CONFLICT:
@@ -121,7 +121,7 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
 	if (ret < 0)
 		return ret;
 
-	return nvme_sc_to_pr_err(ret);
+	return nvme_status_to_pr_err(ret);
 }
 
 static int nvme_pr_register(struct block_device *bdev, u64 old,
@@ -196,7 +196,7 @@ retry:
 	if (ret < 0)
 		return ret;
 
-	return nvme_sc_to_pr_err(ret);
+	return nvme_status_to_pr_err(ret);
 }
 
 static int nvme_pr_read_keys(struct block_device *bdev,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 51a62b0c645a..2eb33842f971 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2201,6 +2201,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
+	.subsystem_reset	= nvmf_subsystem_reset,
 	.free_ctrl		= nvme_rdma_free_ctrl,
 	.submit_async_event	= nvme_rdma_submit_async_event,
 	.delete_ctrl		= nvme_rdma_delete_ctrl,
@@ -2237,12 +2238,11 @@ nvme_rdma_existing_controller(struct nvmf_ctrl_options *opts)
 	return found;
 }
 
-static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
+static struct nvme_rdma_ctrl *nvme_rdma_alloc_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
 	struct nvme_rdma_ctrl *ctrl;
 	int ret;
-	bool changed;
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
 	if (!ctrl)
@@ -2304,6 +2304,30 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_kfree_queues;
 
+	return ctrl;
+
+out_kfree_queues:
+	kfree(ctrl->queues);
+out_free_ctrl:
+	kfree(ctrl);
+	return ERR_PTR(ret);
+}
+
+static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvme_rdma_ctrl *ctrl;
+	bool changed;
+	int ret;
+
+	ctrl = nvme_rdma_alloc_ctrl(dev, opts);
+	if (IS_ERR(ctrl))
+		return ERR_CAST(ctrl);
+
+	ret = nvme_add_ctrl(&ctrl->ctrl);
+	if (ret)
+		goto out_put_ctrl;
+
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
@@ -2322,15 +2346,11 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
 	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
-out_kfree_queues:
-	kfree(ctrl->queues);
-out_free_ctrl:
-	kfree(ctrl);
-	return ERR_PTR(ret);
 }
 
 static struct nvmf_transport_ops nvme_rdma_transport = {
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8b5e4327fe83..a2a47d3ab99f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2662,6 +2662,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
+	.subsystem_reset	= nvmf_subsystem_reset,
 	.free_ctrl		= nvme_tcp_free_ctrl,
 	.submit_async_event	= nvme_tcp_submit_async_event,
 	.delete_ctrl		= nvme_tcp_delete_ctrl,
@@ -2686,7 +2687,7 @@ nvme_tcp_existing_controller(struct nvmf_ctrl_options *opts)
 	return found;
 }
 
-static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
+static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
 	struct nvme_tcp_ctrl *ctrl;
@@ -2761,6 +2762,28 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_kfree_queues;
 
+	return ctrl;
+out_kfree_queues:
+	kfree(ctrl->queues);
+out_free_ctrl:
+	kfree(ctrl);
+	return ERR_PTR(ret);
+}
+
+static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvme_tcp_ctrl *ctrl;
+	int ret;
+
+	ctrl = nvme_tcp_alloc_ctrl(dev, opts);
+	if (IS_ERR(ctrl))
+		return ERR_CAST(ctrl);
+
+	ret = nvme_add_ctrl(&ctrl->ctrl);
+	if (ret)
+		goto out_put_ctrl;
+
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		WARN_ON_ONCE(1);
 		ret = -EINTR;
@@ -2782,15 +2805,11 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
 	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
-out_kfree_queues:
-	kfree(ctrl->queues);
-out_free_ctrl:
-	kfree(ctrl);
-	return ERR_PTR(ret);
 }
 
 static struct nvmf_transport_ops nvme_tcp_transport = {
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 77aa0f440a6d..9a06f9d98cd6 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -108,13 +108,12 @@ free_data:
 void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
 		struct nvme_zone_info *zi)
 {
-	lim->zoned = 1;
+	lim->features |= BLK_FEAT_ZONED;
 	lim->max_open_zones = zi->max_open_zones;
 	lim->max_active_zones = zi->max_active_zones;
 	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
 	lim->chunk_sectors = ns->head->zsze =
 		nvme_lba_to_sect(ns->head, zi->zone_size);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
 }
 
 static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,