Merge tag 'drivers-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Here are the driver updates for 5.10.

  A few SCSI updates in here too, in coordination with Martin as they
  depend on core block changes for the shared tag bitmap.

  This contains:

   - NVMe pull requests via Christoph:
      - fix keep alive timer modification (Amit Engel)
      - order the PCI ID list more sensibly (Andy Shevchenko)
      - cleanup the open by controller helper (Chaitanya Kulkarni)
      - use an xarray for the CSE log lookup (Chaitanya Kulkarni)
      - support ZNS in nvmet passthrough mode (Chaitanya Kulkarni)
      - fix nvme_ns_report_zones (Christoph Hellwig)
      - add a sanity check to nvmet-fc (James Smart)
      - fix interrupt allocation when too many polled queues are
        specified (Jeffle Xu)
      - small nvmet-tcp optimization (Mark Wunderlich)
      - fix a controller refcount leak on init failure (Chaitanya
        Kulkarni)
      - misc cleanups (Chaitanya Kulkarni)
      - major refactoring of the scanning code (Christoph Hellwig)

   - MD updates via Song:
      - Bug fixes in bitmap code, from Zhao Heming
      - Fix a work queue check, from Guoqing Jiang
      - Fix raid5 oops with reshape, from Song Liu
      - Clean up unused code, from Jason Yan
      - Discard improvements, from Xiao Ni
      - raid5/6 page offset support, from Yufen Yu

   - Shared tag bitmap for SCSI/hisi_sas/null_blk (John, Kashyap,
     Hannes)

   - null_blk open/active zone limit support (Niklas)

   - Set of bcache updates (Coly, Dongsheng, Qinglang)"

* tag 'drivers-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (78 commits)
  md/raid5: fix oops during stripe resizing
  md/bitmap: fix memory leak of temporary bitmap
  md: fix the checking of wrong work queue
  md/bitmap: md_bitmap_get_counter returns wrong blocks
  md/bitmap: md_bitmap_read_sb uses wrong bitmap blocks
  md/raid0: remove unused function is_io_in_chunk_boundary()
  nvme-core: remove extra condition for vwc
  nvme-core: remove extra variable
  nvme: remove nvme_identify_ns_list
  nvme: refactor nvme_validate_ns
  nvme: move nvme_validate_ns
  nvme: query namespace identifiers before adding the namespace
  nvme: revalidate zone bitmaps in nvme_update_ns_info
  nvme: remove nvme_update_formats
  nvme: update the known admin effects
  nvme: set the queue limits in nvme_update_ns_info
  nvme: remove the 0 lba_shift check in nvme_update_ns_info
  nvme: clean up the check for too large logic block sizes
  nvme: freeze the queue over ->lba_shift updates
  nvme: factor out a nvme_configure_metadata helper
  ...

4 files changed, 259 insertions, 357 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d2397cfe178f..56e2a22e8a02 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -89,7 +89,6 @@ static dev_t nvme_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
-static int _nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
@@ -968,10 +967,10 @@ static u32 nvme_known_admin_effects(u8 opcode)
 {
 	switch (opcode) {
 	case nvme_admin_format_nvm:
-		return NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
+		return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_NCC |
 			NVME_CMD_EFFECTS_CSE_MASK;
 	case nvme_admin_sanitize_nvm:
-		return NVME_CMD_EFFECTS_CSE_MASK;
+		return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK;
 	default:
 		break;
 	}
@@ -1009,7 +1008,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	 * For simplicity, IO to all namespaces is quiesced even if the command
 	 * effects say only one namespace is affected.
 	 */
-	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
+	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
 		mutex_lock(&ctrl->scan_lock);
 		mutex_lock(&ctrl->subsys->lock);
 		nvme_mpath_start_freeze(ctrl->subsys);
@@ -1020,36 +1019,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return effects;
 }
 
-static void nvme_update_formats(struct nvme_ctrl *ctrl, u32 *effects)
-{
-	struct nvme_ns *ns;
-
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (_nvme_revalidate_disk(ns->disk))
-			nvme_set_queue_dying(ns);
-		else if (blk_queue_is_zoned(ns->disk->queue)) {
-			/*
-			 * IO commands are required to fully revalidate a zoned
-			 * device. Force the command effects to trigger rescan
-			 * work so report zones can run in a context with
-			 * unfrozen IO queues.
-			 */
-			*effects |= NVME_CMD_EFFECTS_NCC;
-		}
-	up_read(&ctrl->namespaces_rwsem);
-}
-
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 {
-	/*
-	 * Revalidate LBA changes prior to unfreezing. This is necessary to
-	 * prevent memory corruption if a logical block size was changed by
-	 * this command.
-	 */
-	if (effects & NVME_CMD_EFFECTS_LBCC)
-		nvme_update_formats(ctrl, &effects);
-	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
+	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
 		nvme_unfreeze(ctrl);
 		nvme_mpath_unfreeze(ctrl->subsys);
 		mutex_unlock(&ctrl->subsys->lock);
@@ -1309,6 +1281,8 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 	int status, pos, len;
 	void *data;
 
+	if (ctrl->vs < NVME_VS(1, 3, 0) && !nvme_multi_css(ctrl))
+		return 0;
 	if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST)
 		return 0;
 
@@ -1352,19 +1326,8 @@ free_data:
 	return status;
 }
 
-static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
-{
-	struct nvme_command c = { };
-
-	c.identify.opcode = nvme_admin_identify;
-	c.identify.cns = NVME_ID_CNS_NS_ACTIVE_LIST;
-	c.identify.nsid = cpu_to_le32(nsid);
-	return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list,
-				    NVME_IDENTIFY_DATA_SIZE);
-}
-
-static int nvme_identify_ns(struct nvme_ctrl *ctrl,
-		unsigned nsid, struct nvme_id_ns **id)
+static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+			struct nvme_ns_ids *ids, struct nvme_id_ns **id)
 {
 	struct nvme_command c = { };
 	int error;
@@ -1381,9 +1344,24 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl,
 	error = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
 	if (error) {
 		dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
-		kfree(*id);
+		goto out_free_id;
 	}
 
+	error = -ENODEV;
+	if ((*id)->ncap == 0) /* namespace not allocated or attached */
+		goto out_free_id;
+
+	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
+	    !memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
+		memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64));
+	if (ctrl->vs >= NVME_VS(1, 2, 0) &&
+	    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
+		memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid));
+
+	return 0;
+
+out_free_id:
+	kfree(*id);
 	return error;
 }
 
@@ -1905,20 +1883,6 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
 					   nvme_lba_to_sect(ns, max_blocks));
 }
 
-static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
-		struct nvme_id_ns *id, struct nvme_ns_ids *ids)
-{
-	memset(ids, 0, sizeof(*ids));
-
-	if (ctrl->vs >= NVME_VS(1, 1, 0))
-		memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
-	if (ctrl->vs >= NVME_VS(1, 2, 0))
-		memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
-	if (ctrl->vs >= NVME_VS(1, 3, 0) || nvme_multi_css(ctrl))
-		return nvme_identify_ns_descs(ctrl, nsid, ids);
-	return 0;
-}
-
 static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
 {
 	return !uuid_is_null(&ids->uuid) ||
@@ -1959,6 +1923,68 @@ static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return 0;
 }
 
+static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+
+	/*
+	 * The PI implementation requires the metadata size to be equal to the
+	 * t10 pi tuple size.
+	 */
+	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	if (ns->ms == sizeof(struct t10_pi_tuple))
+		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+	else
+		ns->pi_type = 0;
+
+	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
+		return 0;
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
+		/*
+		 * The NVMe over Fabrics specification only supports metadata as
+		 * part of the extended data LBA.  We rely on HCA/HBA support to
+		 * remap the separate metadata buffer from the block layer.
+		 */
+		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
+			return -EINVAL;
+		if (ctrl->max_integrity_segments)
+			ns->features |=
+				(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	} else {
+		/*
+		 * For PCIe controllers, we can't easily remap the separate
+		 * metadata buffer from the block layer and thus require a
+		 * separate metadata buffer for block layer metadata/PI support.
+		 * We allow extended LBAs for the passthrough interface, though.
+		 */
+		if (id->flbas & NVME_NS_FLBAS_META_EXT)
+			ns->features |= NVME_NS_EXT_LBAS;
+		else
+			ns->features |= NVME_NS_METADATA_SUPPORTED;
+	}
+
+	return 0;
+}
+
+static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
+		struct request_queue *q)
+{
+	bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
+
+	if (ctrl->max_hw_sectors) {
+		u32 max_segments =
+			(ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
+
+		max_segments = min_not_zero(max_segments, ctrl->max_segments);
+		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
+		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
+	}
+	blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
+	blk_queue_dma_alignment(q, 7);
+	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)
 {
@@ -1966,11 +1992,15 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	unsigned short bs = 1 << ns->lba_shift;
 	u32 atomic_bs, phys_bs, io_opt = 0;
 
+	/*
+	 * The block layer can't support LBA sizes larger than the page size
+	 * yet, so catch this early and don't allow block I/O.
+	 */
 	if (ns->lba_shift > PAGE_SHIFT) {
-		/* unsupported block size, set capacity to 0 later */
+		capacity = 0;
 		bs = (1 << 9);
 	}
-	blk_mq_freeze_queue(disk->queue);
+
 	blk_integrity_unregister(disk);
 
 	atomic_bs = phys_bs = bs;
@@ -2005,13 +2035,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_queue_io_opt(disk->queue, io_opt);
 
 	/*
-	 * The block layer can't support LBA sizes larger than the page size
-	 * yet, so catch this early and don't allow block I/O.
-	 */
-	if (ns->lba_shift > PAGE_SHIFT)
-		capacity = 0;
-
-	/*
 	 * Register a metadata profile for PI, or the plain non-integrity NVMe
 	 * metadata masquerading as Type 0 if supported, otherwise reject block
 	 * I/O to namespaces with metadata except when the namespace supports
@@ -2035,8 +2058,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 		set_disk_ro(disk, true);
 	else
 		set_disk_ro(disk, false);
-
-	blk_mq_unfreeze_queue(disk->queue);
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -2076,151 +2097,49 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
 	blk_queue_chunk_sectors(ns->queue, iob);
 }
 
-static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
+static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
-	struct nvme_ns *ns = disk->private_data;
-	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
 
-	/*
-	 * If identify namespace failed, use default 512 byte block size so
-	 * block layer can use before failing read/write for 0 capacity.
-	 */
+	blk_mq_freeze_queue(ns->disk->queue);
 	ns->lba_shift = id->lbaf[lbaf].ds;
-	if (ns->lba_shift == 0)
-		ns->lba_shift = 9;
+	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
-	switch (ns->head->ids.csi) {
-	case NVME_CSI_NVM:
-		break;
-	case NVME_CSI_ZNS:
-		ret = nvme_update_zone_info(disk, ns, lbaf);
-		if (ret) {
-			dev_warn(ctrl->device,
-				"failed to add zoned namespace:%u ret:%d\n",
-				ns->head->ns_id, ret);
-			return ret;
-		}
-		break;
-	default:
-		dev_warn(ctrl->device, "unknown csi:%u ns:%u\n",
-			ns->head->ids.csi, ns->head->ns_id);
-		return -ENODEV;
+	if (ns->head->ids.csi == NVME_CSI_ZNS) {
+		ret = nvme_update_zone_info(ns, lbaf);
+		if (ret)
+			goto out_unfreeze;
 	}
 
-	ns->features = 0;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
-	/* the PI implementation requires metadata equal t10 pi tuple size */
-	if (ns->ms == sizeof(struct t10_pi_tuple))
-		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
-	else
-		ns->pi_type = 0;
+	ret = nvme_configure_metadata(ns, id);
+	if (ret)
+		goto out_unfreeze;
+	nvme_set_chunk_sectors(ns, id);
+	nvme_update_disk_info(ns->disk, ns, id);
+	blk_mq_unfreeze_queue(ns->disk->queue);
 
-	if (ns->ms) {
-		/*
-		 * For PCIe only the separate metadata pointer is supported,
-		 * as the block layer supplies metadata in a separate bio_vec
-		 * chain. For Fabrics, only metadata as part of extended data
-		 * LBA is supported on the wire per the Fabrics specification,
-		 * but the HBA/HCA will do the remapping from the separate
-		 * metadata buffers for us.
-		 */
-		if (id->flbas & NVME_NS_FLBAS_META_EXT) {
-			ns->features |= NVME_NS_EXT_LBAS;
-			if ((ctrl->ops->flags & NVME_F_FABRICS) &&
-			    (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) &&
-			    ctrl->max_integrity_segments)
-				ns->features |= NVME_NS_METADATA_SUPPORTED;
-		} else {
-			if (WARN_ON_ONCE(ctrl->ops->flags & NVME_F_FABRICS))
-				return -EINVAL;
-			if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
-				ns->features |= NVME_NS_METADATA_SUPPORTED;
-		}
+	if (blk_queue_is_zoned(ns->queue)) {
+		ret = nvme_revalidate_zones(ns);
+		if (ret)
+			return ret;
 	}
 
-	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
 	if (ns->head->disk) {
+		blk_mq_freeze_queue(ns->head->disk->queue);
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
 		blk_queue_update_readahead(ns->head->disk->queue);
 		nvme_update_bdev_size(ns->head->disk);
+		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
 #endif
 	return 0;
-}
-
-static int _nvme_revalidate_disk(struct gendisk *disk)
-{
-	struct nvme_ns *ns = disk->private_data;
-	struct nvme_ctrl *ctrl = ns->ctrl;
-	struct nvme_id_ns *id;
-	struct nvme_ns_ids ids;
-	int ret = 0;
-
-	if (test_bit(NVME_NS_DEAD, &ns->flags)) {
-		set_capacity(disk, 0);
-		return -ENODEV;
-	}
 
-	ret = nvme_identify_ns(ctrl, ns->head->ns_id, &id);
-	if (ret)
-		goto out;
-
-	if (id->ncap == 0) {
-		ret = -ENODEV;
-		goto free_id;
-	}
-
-	ret = nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
-	if (ret)
-		goto free_id;
-
-	if (!nvme_ns_ids_equal(&ns->head->ids, &ids)) {
-		dev_err(ctrl->device,
-			"identifiers changed for nsid %d\n", ns->head->ns_id);
-		ret = -ENODEV;
-		goto free_id;
-	}
-
-	ret = __nvme_revalidate_disk(disk, id);
-free_id:
-	kfree(id);
-out:
-	/*
-	 * Only fail the function if we got a fatal error back from the
-	 * device, otherwise ignore the error and just move on.
-	 */
-	if (ret == -ENOMEM || (ret > 0 && !(ret & NVME_SC_DNR)))
-		ret = 0;
-	else if (ret > 0)
-		ret = blk_status_to_errno(nvme_error_status(ret));
-	return ret;
-}
-
-static int nvme_revalidate_disk(struct gendisk *disk)
-{
-	int ret;
-
-	ret = _nvme_revalidate_disk(disk);
-	if (ret)
-		return ret;
-
-#ifdef CONFIG_BLK_DEV_ZONED
-	if (blk_queue_is_zoned(disk->queue)) {
-		struct nvme_ns *ns = disk->private_data;
-		struct nvme_ctrl *ctrl = ns->ctrl;
-
-		ret = blk_revalidate_disk_zones(disk, NULL);
-		if (!ret)
-			blk_queue_max_zone_append_sectors(disk->queue,
-							  ctrl->max_zone_append);
-	}
-#endif
+out_unfreeze:
+	blk_mq_unfreeze_queue(ns->disk->queue);
 	return ret;
 }
 
@@ -2502,26 +2421,6 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);
 
-static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
-		struct request_queue *q)
-{
-	bool vwc = false;
-
-	if (ctrl->max_hw_sectors) {
-		u32 max_segments =
-			(ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
-
-		max_segments = min_not_zero(max_segments, ctrl->max_segments);
-		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
-		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
-	}
-	blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, 7);
-	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
-		vwc = true;
-	blk_queue_write_cache(q, vwc, vwc);
-}
-
 static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
 {
 	__le64 ts;
@@ -3025,26 +2924,10 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
-{
-	struct nvme_cel *cel, *ret = NULL;
-
-	spin_lock_irq(&ctrl->lock);
-	list_for_each_entry(cel, &ctrl->cels, entry) {
-		if (cel->csi == csi) {
-			ret = cel;
-			break;
-		}
-	}
-	spin_unlock_irq(&ctrl->lock);
-
-	return ret;
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 				struct nvme_effects_log **log)
 {
-	struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
+	struct nvme_cel *cel = xa_load(&ctrl->cels, csi);
 	int ret;
 
 	if (cel)
@@ -3062,10 +2945,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 	}
 
 	cel->csi = csi;
-
-	spin_lock_irq(&ctrl->lock);
-	list_add_tail(&cel->entry, &ctrl->cels);
-	spin_unlock_irq(&ctrl->lock);
+	xa_store(&ctrl->cels, cel->csi, cel, GFP_KERNEL);
 out:
 	*log = &cel->log;
 	return 0;
@@ -3846,25 +3726,16 @@ out:
 }
 
 static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
-		struct nvme_id_ns *id)
+		struct nvme_ns_ids *ids, bool is_shared)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
-	bool is_shared = id->nmic & NVME_NS_NMIC_SHARED;
 	struct nvme_ns_head *head = NULL;
-	struct nvme_ns_ids ids;
 	int ret = 0;
 
-	ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
-	if (ret) {
-		if (ret < 0)
-			return ret;
-		return blk_status_to_errno(nvme_error_status(ret));
-	}
-
 	mutex_lock(&ctrl->subsys->lock);
 	head = nvme_find_ns_head(ctrl->subsys, nsid);
 	if (!head) {
-		head = nvme_alloc_ns_head(ctrl, nsid, &ids);
+		head = nvme_alloc_ns_head(ctrl, nsid, ids);
 		if (IS_ERR(head)) {
 			ret = PTR_ERR(head);
 			goto out_unlock;
@@ -3877,7 +3748,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 				"Duplicate unshared namespace %d\n", nsid);
 			goto out_put_ns_head;
 		}
-		if (!nvme_ns_ids_equal(&head->ids, &ids)) {
+		if (!nvme_ns_ids_equal(&head->ids, ids)) {
 			dev_err(ctrl->device,
 				"IDs don't match for shared namespace %d\n",
 					nsid);
@@ -3925,7 +3796,8 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 }
 EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU);
 
-static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+		struct nvme_ns_ids *ids)
 {
 	struct nvme_ns *ns;
 	struct gendisk *disk;
@@ -3933,9 +3805,12 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	char disk_name[DISK_NAME_LEN];
 	int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT, ret;
 
+	if (nvme_identify_ns(ctrl, nsid, ids, &id))
+		return;
+
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
-		return;
+		goto out_free_id;
 
 	ns->queue = blk_mq_init_queue(ctrl->tagset);
 	if (IS_ERR(ns->queue))
@@ -3950,23 +3825,11 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	ns->queue->queuedata = ns;
 	ns->ctrl = ctrl;
-
 	kref_init(&ns->kref);
-	ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
-
-	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
-	nvme_set_queue_limits(ctrl, ns->queue);
 
-	ret = nvme_identify_ns(ctrl, nsid, &id);
+	ret = nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED);
 	if (ret)
 		goto out_free_queue;
-
-	if (id->ncap == 0)	/* no namespace (legacy quirk) */
-		goto out_free_id;
-
-	ret = nvme_init_ns_head(ns, nsid, id);
-	if (ret)
-		goto out_free_id;
 	nvme_set_disk_name(disk_name, ns, ctrl, &flags);
 
 	disk = alloc_disk_node(0, node);
@@ -3980,7 +3843,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
 	ns->disk = disk;
 
-	if (__nvme_revalidate_disk(disk, id))
+	if (nvme_update_ns_info(ns, id))
 		goto out_put_disk;
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
@@ -4015,12 +3878,12 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		list_del_init(&ns->head->entry);
 	mutex_unlock(&ctrl->subsys->lock);
 	nvme_put_ns_head(ns->head);
- out_free_id:
-	kfree(id);
  out_free_queue:
 	blk_cleanup_queue(ns->queue);
  out_free_ns:
 	kfree(ns);
+ out_free_id:
+	kfree(id);
 }
 
 static void nvme_ns_remove(struct nvme_ns *ns)
@@ -4028,6 +3891,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
+	set_capacity(ns->disk, 0);
 	nvme_fault_inject_fini(&ns->fault_inject);
 
 	mutex_lock(&ns->ctrl->subsys->lock);
@@ -4065,22 +3929,75 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
 	}
 }
 
-static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
+{
+	struct nvme_id_ns *id;
+	int ret = -ENODEV;
+
+	if (test_bit(NVME_NS_DEAD, &ns->flags))
+		goto out;
+
+	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, ids, &id);
+	if (ret)
+		goto out;
+
+	ret = -ENODEV;
+	if (!nvme_ns_ids_equal(&ns->head->ids, ids)) {
+		dev_err(ns->ctrl->device,
+			"identifiers changed for nsid %d\n", ns->head->ns_id);
+		goto out_free_id;
+	}
+
+	ret = nvme_update_ns_info(ns, id);
+
+out_free_id:
+	kfree(id);
+out:
+	/*
+	 * Only remove the namespace if we got a fatal error back from the
+	 * device, otherwise ignore the error and just move on.
+	 *
+	 * TODO: we should probably schedule a delayed retry here.
+	 */
+	if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR)))
+		nvme_ns_remove(ns);
+	else
+		revalidate_disk_size(ns->disk, true);
+}
+
+static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
+	struct nvme_ns_ids ids = { };
 	struct nvme_ns *ns;
-	int ret;
+
+	if (nvme_identify_ns_descs(ctrl, nsid, &ids))
+		return;
 
 	ns = nvme_find_get_ns(ctrl, nsid);
-	if (!ns) {
-		nvme_alloc_ns(ctrl, nsid);
+	if (ns) {
+		nvme_validate_ns(ns, &ids);
+		nvme_put_ns(ns);
 		return;
 	}
 
-	ret = nvme_revalidate_disk(ns->disk);
-	revalidate_disk_size(ns->disk, ret == 0);
-	if (ret)
-		nvme_ns_remove(ns);
-	nvme_put_ns(ns);
+	switch (ids.csi) {
+	case NVME_CSI_NVM:
+		nvme_alloc_ns(ctrl, nsid, &ids);
+		break;
+	case NVME_CSI_ZNS:
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+			dev_warn(ctrl->device,
+				"nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
+				nsid);
+			break;
+		}
+		nvme_alloc_ns(ctrl, nsid, &ids);
+		break;
+	default:
+		dev_warn(ctrl->device, "unknown csi %u for nsid %u\n",
+			ids.csi, nsid);
+		break;
+	}
 }
 
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
@@ -4116,7 +4033,14 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 		return -ENOMEM;
 
 	for (;;) {
-		ret = nvme_identify_ns_list(ctrl, prev, ns_list);
+		struct nvme_command cmd = {
+			.identify.opcode	= nvme_admin_identify,
+			.identify.cns		= NVME_ID_CNS_NS_ACTIVE_LIST,
+			.identify.nsid		= cpu_to_le32(prev),
+		};
+
+		ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd, ns_list,
+					    NVME_IDENTIFY_DATA_SIZE);
 		if (ret)
 			goto free;
 
@@ -4125,7 +4049,7 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 
 			if (!nsid)	/* end of the list? */
 				goto out;
-			nvme_validate_ns(ctrl, nsid);
+			nvme_validate_or_alloc_ns(ctrl, nsid);
 			while (++prev < nsid)
 				nvme_ns_remove_by_nsid(ctrl, prev);
 		}
@@ -4148,7 +4072,7 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl)
 	kfree(id);
 
 	for (i = 1; i <= nn; i++)
-		nvme_validate_ns(ctrl, i);
+		nvme_validate_or_alloc_ns(ctrl, i);
 
 	nvme_remove_invalid_namespaces(ctrl, nn);
 }
@@ -4453,15 +4377,11 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_ctrl *ctrl =
 		container_of(dev, struct nvme_ctrl, ctrl_device);
 	struct nvme_subsystem *subsys = ctrl->subsys;
-	struct nvme_cel *cel, *next;
 
 	if (!subsys || ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
-	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
-		list_del(&cel->entry);
-		kfree(cel);
-	}
+	xa_destroy(&ctrl->cels);
 
 	nvme_mpath_uninit(ctrl);
 	__free_page(ctrl->discard_page);
@@ -4493,7 +4413,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
-	INIT_LIST_HEAD(&ctrl->cels);
+	xa_init(&ctrl->cels);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
@@ -4673,28 +4593,13 @@ void nvme_sync_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_sync_queues);
 
-struct nvme_ctrl *nvme_ctrl_get_by_path(const char *path)
+struct nvme_ctrl *nvme_ctrl_from_file(struct file *file)
 {
-	struct nvme_ctrl *ctrl;
-	struct file *f;
-
-	f = filp_open(path, O_RDWR, 0);
-	if (IS_ERR(f))
-		return ERR_CAST(f);
-
-	if (f->f_op != &nvme_dev_fops) {
-		ctrl = ERR_PTR(-EINVAL);
-		goto out_close;
-	}
-
-	ctrl = f->private_data;
-	nvme_get_ctrl(ctrl);
-
-out_close:
-	filp_close(f, NULL);
-	return ctrl;
+	if (file->f_op != &nvme_dev_fops)
+		return NULL;
+	return file->private_data;
 }
-EXPORT_SYMBOL_NS_GPL(nvme_ctrl_get_by_path, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_ctrl_from_file, NVME_TARGET_PASSTHRU);
 
 /*
  * Check we didn't inadvertently grow the command structure sizes:
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 8ac37430347c..e7c88b40f5bb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -300,7 +300,7 @@ struct nvme_ctrl {
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
 	struct nvme_effects_log *effects;
-	struct list_head cels;
+	struct xarray cels;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
@@ -758,10 +758,9 @@ static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+int nvme_revalidate_zones(struct nvme_ns *ns);
 #ifdef CONFIG_BLK_DEV_ZONED
-int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
-			  unsigned lbaf);
-
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
 int nvme_report_zones(struct gendisk *disk, sector_t sector,
 		      unsigned int nr_zones, report_zones_cb cb, void *data);
 
@@ -778,9 +777,7 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
 	return BLK_STS_NOTSUPP;
 }
 
-static inline int nvme_update_zone_info(struct gendisk *disk,
-					struct nvme_ns *ns,
-					unsigned lbaf)
+static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 {
 	dev_warn(ns->ctrl->device,
 		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
@@ -825,7 +822,7 @@ static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			 u8 opcode);
 void nvme_execute_passthru_rq(struct request *rq);
-struct nvme_ctrl *nvme_ctrl_get_by_path(const char *path);
+struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
 void nvme_put_ns(struct nvme_ns *ns);
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8984796db0c8..e5b02242f3ca 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2038,32 +2038,30 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.calc_sets	= nvme_calc_irq_sets,
 		.priv		= dev,
 	};
-	unsigned int irq_queues, this_p_queues;
+	unsigned int irq_queues, poll_queues;
 
 	/*
-	 * Poll queues don't need interrupts, but we need at least one IO
-	 * queue left over for non-polled IO.
+	 * Poll queues don't need interrupts, but we need at least one I/O queue
+	 * left over for non-polled I/O.
 	 */
-	this_p_queues = dev->nr_poll_queues;
-	if (this_p_queues >= nr_io_queues) {
-		this_p_queues = nr_io_queues - 1;
-		irq_queues = 1;
-	} else {
-		irq_queues = nr_io_queues - this_p_queues + 1;
-	}
-	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
+	poll_queues = min(dev->nr_poll_queues, nr_io_queues - 1);
+	dev->io_queues[HCTX_TYPE_POLL] = poll_queues;
 
-	/* Initialize for the single interrupt case */
+	/*
+	 * Initialize for the single interrupt case, will be updated in
+	 * nvme_calc_irq_sets().
+	 */
 	dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
 	dev->io_queues[HCTX_TYPE_READ] = 0;
 
 	/*
-	 * Some Apple controllers require all queues to use the
-	 * first vector.
+	 * We need interrupts for the admin queue and each non-polled I/O queue,
+	 * but some Apple controllers require all queues to use the first
+	 * vector.
 	 */
-	if (dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR)
-		irq_queues = 1;
-
+	irq_queues = 1;
+	if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
+		irq_queues += (nr_io_queues - poll_queues);
 	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
 			      PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
 }
@@ -3187,7 +3185,6 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
-	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
@@ -3195,6 +3192,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR |
 				NVME_QUIRK_128_BYTES_SQES |
 				NVME_QUIRK_SHARED_TAGS },
+
+	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, nvme_id_table);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 57cfd78731fb..67e87e9f306f 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -7,6 +7,17 @@
 #include <linux/vmalloc.h>
 #include "nvme.h"
 
+int nvme_revalidate_zones(struct nvme_ns *ns)
+{
+	struct request_queue *q = ns->queue;
+	int ret;
+
+	ret = blk_revalidate_disk_zones(ns->disk, NULL);
+	if (!ret)
+		blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
+	return ret;
+}
+
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 {
 	struct nvme_command c = { };
@@ -35,11 +46,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 	return 0;
 }
 
-int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
-			  unsigned lbaf)
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 {
 	struct nvme_effects_log *log = ns->head->effects;
-	struct request_queue *q = disk->queue;
+	struct request_queue *q = ns->queue;
 	struct nvme_command c = { };
 	struct nvme_id_ns_zns *id;
 	int status;
@@ -133,28 +143,6 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	return NULL;
 }
 
-static int __nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
-				  struct nvme_zone_report *report,
-				  size_t buflen)
-{
-	struct nvme_command c = { };
-	int ret;
-
-	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
-	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
-	c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
-	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
-	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
-	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
-	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
-
-	ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
-	if (ret)
-		return ret;
-
-	return le64_to_cpu(report->nr_zones);
-}
-
 static int nvme_zone_parse_entry(struct nvme_ns *ns,
 				 struct nvme_zone_descriptor *entry,
 				 unsigned int idx, report_zones_cb cb,
@@ -182,6 +170,7 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nvme_zone_report *report;
+	struct nvme_command c = { };
 	int ret, zone_idx = 0;
 	unsigned int nz, i;
 	size_t buflen;
@@ -190,14 +179,26 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	if (!report)
 		return -ENOMEM;
 
+	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
+	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
+	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
+	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
+	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
+	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
+
 	sector &= ~(ns->zsze - 1);
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);
-		ret = __nvme_ns_report_zones(ns, sector, report, buflen);
-		if (ret < 0)
+
+		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
+		if (ret) {
+			if (ret > 0)
+				ret = -EIO;
 			goto out_free;
+		}
 
-		nz = min_t(unsigned int, ret, nr_zones);
+		nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones);
 		if (!nz)
 			break;