Merge branch 'nvme-5.9' of git://git.infradead.org/nvme into for-5.9/drivers

Pull NVMe updates from Christoph:

"Below is the current large chunk we have in the nvme tree for 5.9:

 - ZNS support (Aravind, Keith, Matias, Niklas)
  - misc cleanups and optimizations
     (Baolin, Chaitanya, David, Dongli, Max, Sagi)"

* 'nvme-5.9' of git://git.infradead.org/nvme: (28 commits)
  nvme: remove ns->disk checks
  nvme-pci: use standard block status symbolic names
  nvme-pci: use the consistent return type of nvme_pci_iod_alloc_size()
  nvme-pci: add a blank line after declarations
  nvme-pci: fix some comments issues
  nvme-pci: remove redundant segment validation
  nvme: document quirked Intel models
  nvme: expose reconnect_delay and ctrl_loss_tmo via sysfs
  nvme: support for zoned namespaces
  nvme: support for multiple Command Sets Supported and Effects log pages
  nvme: implement multiple I/O Command Set support
  null_blk: introduce zone capacity for zoned device
  block: add capacity field to zone descriptors
  nvme: use USEC_PER_SEC instead of magic numbers
  nvmet-tcp: simplify nvmet_process_resp_list
  nvme-tcp: optimize network stack with setting msg flags according to batch size
  nvme-tcp: leverage request plugging
  nvme-tcp: have queue prod/cons send list become a llist
  nvme-fcloop: verify wwnn and wwpn format
  nvmet: use unsigned type for u64
  ...

26 files changed, 862 insertions, 140 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 9357d7302398..bbad5e8bbffe 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -86,9 +86,10 @@ config BLK_DEV_ZONED
 	select MQ_IOSCHED_DEADLINE
 	help
 	Block layer zoned block device support. This option enables
-	support for ZAC/ZBC host-managed and host-aware zoned block devices.
+	support for ZAC/ZBC/ZNS host-managed and host-aware zoned block
+	devices.
 
-	Say yes here if you have a ZAC or ZBC storage device.
+	Say yes here if you have a ZAC, ZBC, or ZNS storage device.
 
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 23831fa8701d..81152a260354 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -312,6 +312,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 		return ret;
 
 	rep.nr_zones = ret;
+	rep.flags = BLK_ZONE_REP_CAPACITY;
 	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
 		return -EFAULT;
 	return 0;
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index 81b311c9d781..daed4a9c3436 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -49,6 +49,7 @@ struct nullb_device {
 	unsigned long completion_nsec; /* time in ns to complete a request */
 	unsigned long cache_size; /* disk cache size in MB */
 	unsigned long zone_size; /* zone size in MB if device is zoned */
+	unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
 	unsigned int zone_nr_conv; /* number of conventional zones */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int home_node; /* home node for the device */
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 907c6858aec0..47a9dad880af 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -200,6 +200,10 @@ static unsigned long g_zone_size = 256;
 module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
 MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
 
+static unsigned long g_zone_capacity;
+module_param_named(zone_capacity, g_zone_capacity, ulong, 0444);
+MODULE_PARM_DESC(zone_capacity, "Zone capacity in MB when block device is zoned. Can be less than or equal to zone size. Default: Zone size");
+
 static unsigned int g_zone_nr_conv;
 module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444);
 MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0");
@@ -341,6 +345,7 @@ NULLB_DEVICE_ATTR(mbps, uint, NULL);
 NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
 NULLB_DEVICE_ATTR(zoned, bool, NULL);
 NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
@@ -457,6 +462,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_badblocks,
 	&nullb_device_attr_zoned,
 	&nullb_device_attr_zone_size,
+	&nullb_device_attr_zone_capacity,
 	&nullb_device_attr_zone_nr_conv,
 	NULL,
 };
@@ -510,7 +516,8 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n");
+	return snprintf(page, PAGE_SIZE,
+			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -571,6 +578,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->use_per_node_hctx = g_use_per_node_hctx;
 	dev->zoned = g_zoned;
 	dev->zone_size = g_zone_size;
+	dev->zone_capacity = g_zone_capacity;
 	dev->zone_nr_conv = g_zone_nr_conv;
 	return dev;
 }
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index cc47606d8ffe..3d25c9ad2383 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -28,6 +28,15 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		return -EINVAL;
 	}
 
+	if (!dev->zone_capacity)
+		dev->zone_capacity = dev->zone_size;
+
+	if (dev->zone_capacity > dev->zone_size) {
+		pr_err("null_blk: zone capacity (%lu MB) larger than zone size (%lu MB)\n",
+					dev->zone_capacity, dev->zone_size);
+		return -EINVAL;
+	}
+
 	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
 	dev->nr_zones = dev_size >>
 				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
@@ -47,6 +56,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 
 		zone->start = sector;
 		zone->len = dev->zone_size_sects;
+		zone->capacity = zone->len;
 		zone->wp = zone->start + zone->len;
 		zone->type = BLK_ZONE_TYPE_CONVENTIONAL;
 		zone->cond = BLK_ZONE_COND_NOT_WP;
@@ -59,6 +69,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 
 		zone->start = zone->wp = sector;
 		zone->len = dev->zone_size_sects;
+		zone->capacity = dev->zone_capacity << ZONE_SIZE_SHIFT;
 		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
 		zone->cond = BLK_ZONE_COND_EMPTY;
 
@@ -185,6 +196,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			return BLK_STS_IOERR;
 		}
 
+		if (zone->wp + nr_sectors > zone->start + zone->capacity)
+			return BLK_STS_IOERR;
+
 		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
 			zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
@@ -193,7 +207,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			return ret;
 
 		zone->wp += nr_sectors;
-		if (zone->wp == zone->start + zone->len)
+		if (zone->wp == zone->start + zone->capacity)
 			zone->cond = BLK_ZONE_COND_FULL;
 		return BLK_STS_OK;
 	default:
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index fc7b26be692d..d7f6a87687b8 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -13,6 +13,7 @@ nvme-core-y				:= core.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
+nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
 nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index cd763f31864b..3d00ea4e7146 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -89,7 +89,7 @@ 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 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);
@@ -100,7 +100,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	 * Revalidating a dead namespace sets capacity to 0. This will end
 	 * buffered writers dirtying pages that can't be synced.
 	 */
-	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+	if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
 		return;
 	blk_set_queue_dying(ns->queue);
 	/* Forcibly unquiesce queues to avoid blocking dispatch */
@@ -287,6 +287,10 @@ void nvme_complete_rq(struct request *req)
 			nvme_retry_req(req);
 			return;
 		}
+	} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+		   req_op(req) == REQ_OP_ZONE_APPEND) {
+		req->__sector = nvme_lba_to_sect(req->q->queuedata,
+			le64_to_cpu(nvme_req(req)->result.u64));
 	}
 
 	nvme_trace_bio_complete(req, status);
@@ -555,7 +559,7 @@ static int nvme_configure_directives(struct nvme_ctrl *ctrl)
 		goto out_disable_stream;
 	}
 
-	ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
+	ctrl->nr_streams = min_t(u16, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
 	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
 	return 0;
 
@@ -673,7 +677,8 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 }
 
 static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
-		struct request *req, struct nvme_command *cmnd)
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_opcode op)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u16 control = 0;
@@ -687,7 +692,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.opcode = op;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
 	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);
@@ -716,6 +721,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
+			if (op == nvme_cmd_zone_append)
+				control |= NVME_RW_APPEND_PIREMAP;
 			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
@@ -756,6 +763,19 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
 		break;
+	case REQ_OP_ZONE_RESET_ALL:
+	case REQ_OP_ZONE_RESET:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET);
+		break;
+	case REQ_OP_ZONE_OPEN:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN);
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE);
+		break;
+	case REQ_OP_ZONE_FINISH:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH);
+		break;
 	case REQ_OP_WRITE_ZEROES:
 		ret = nvme_setup_write_zeroes(ns, req, cmd);
 		break;
@@ -763,8 +783,13 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		ret = nvme_setup_discard(ns, req, cmd);
 		break;
 	case REQ_OP_READ:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
+		break;
 	case REQ_OP_WRITE:
-		ret = nvme_setup_rw(ns, req, cmd);
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
+		break;
+	case REQ_OP_ZONE_APPEND:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1056,8 +1081,13 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 	return error;
 }
 
+static bool nvme_multi_css(struct nvme_ctrl *ctrl)
+{
+	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
+}
+
 static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
-		struct nvme_ns_id_desc *cur)
+		struct nvme_ns_id_desc *cur, bool *csi_seen)
 {
 	const char *warn_str = "ctrl returned bogus length:";
 	void *data = cur;
@@ -1087,6 +1117,15 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
 		}
 		uuid_copy(&ids->uuid, data + sizeof(*cur));
 		return NVME_NIDT_UUID_LEN;
+	case NVME_NIDT_CSI:
+		if (cur->nidl != NVME_NIDT_CSI_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN);
+		*csi_seen = true;
+		return NVME_NIDT_CSI_LEN;
 	default:
 		/* Skip unknown types */
 		return cur->nidl;
@@ -1097,10 +1136,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		struct nvme_ns_ids *ids)
 {
 	struct nvme_command c = { };
-	int status;
+	bool csi_seen = false;
+	int status, pos, len;
 	void *data;
-	int pos;
-	int len;
 
 	c.identify.opcode = nvme_admin_identify;
 	c.identify.nsid = cpu_to_le32(nsid);
@@ -1125,7 +1163,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		  * device just because of a temporal retry-able error (such
 		  * as path of transport errors).
 		  */
-		if (status > 0 && (status & NVME_SC_DNR))
+		if (status > 0 && (status & NVME_SC_DNR) && !nvme_multi_css(ctrl))
 			status = 0;
 		goto free_data;
 	}
@@ -1136,12 +1174,19 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		if (cur->nidl == 0)
 			break;
 
-		len = nvme_process_ns_desc(ctrl, ids, cur);
+		len = nvme_process_ns_desc(ctrl, ids, cur, &csi_seen);
 		if (len < 0)
-			goto free_data;
+			break;
 
 		len += sizeof(*cur);
 	}
+
+	if (nvme_multi_css(ctrl) && !csi_seen) {
+		dev_warn(ctrl->device, "Command set not reported for nsid:%d\n",
+			 nsid);
+		status = -EINVAL;
+	}
+
 free_data:
 	kfree(data);
 	return status;
@@ -1350,8 +1395,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	u32 effects = 0;
 
 	if (ns) {
-		if (ctrl->effects)
-			effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
+		if (ns->head->effects)
+			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
 			dev_warn(ctrl->device,
 				 "IO command:%02x has unhandled effects:%08x\n",
@@ -1378,14 +1423,23 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return effects;
 }
 
-static void nvme_update_formats(struct nvme_ctrl *ctrl)
+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 (ns->disk && nvme_revalidate_disk(ns->disk))
+		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);
 }
 
@@ -1397,7 +1451,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 	 * this command.
 	 */
 	if (effects & NVME_CMD_EFFECTS_LBCC)
-		nvme_update_formats(ctrl);
+		nvme_update_formats(ctrl, &effects);
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
 		nvme_unfreeze(ctrl);
 		nvme_mpath_unfreeze(ctrl->subsys);
@@ -1512,7 +1566,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
  * Issue ioctl requests on the first available path.  Note that unlike normal
  * block layer requests we will not retry failed request on another controller.
  */
-static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 		struct nvme_ns_head **head, int *srcu_idx)
 {
 #ifdef CONFIG_NVME_MULTIPATH
@@ -1532,7 +1586,7 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 	return disk->private_data;
 }
 
-static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 {
 	if (head)
 		srcu_read_unlock(&head->srcu, idx);
@@ -1798,7 +1852,7 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
 		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))
+	if (ctrl->vs >= NVME_VS(1, 3, 0) || nvme_multi_css(ctrl))
 		return nvme_identify_ns_descs(ctrl, nsid, ids);
 	return 0;
 }
@@ -1814,7 +1868,8 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 {
 	return uuid_equal(&a->uuid, &b->uuid) &&
 		memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
-		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0;
+		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 &&
+		a->csi == b->csi;
 }
 
 static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
@@ -1924,18 +1979,38 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 static int __nvme_revalidate_disk(struct gendisk *disk, 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;
 	u32 iob;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
 	 * block layer can use before failing read/write for 0 capacity.
 	 */
-	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
+	ns->lba_shift = id->lbaf[lbaf].ds;
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 
+	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 ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
 	    is_power_of_2(ctrl->max_hw_sectors))
 		iob = ctrl->max_hw_sectors;
@@ -1943,7 +2018,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
 
 	ns->features = 0;
-	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	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;
@@ -1985,7 +2060,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	return 0;
 }
 
-static int nvme_revalidate_disk(struct gendisk *disk)
+static int _nvme_revalidate_disk(struct gendisk *disk)
 {
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
@@ -2033,6 +2108,28 @@ out:
 	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
+	return ret;
+}
+
 static char nvme_pr_type(enum pr_type type)
 {
 	switch (type) {
@@ -2163,6 +2260,7 @@ static const struct block_device_operations nvme_fops = {
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
 	.revalidate_disk= nvme_revalidate_disk,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 
@@ -2189,6 +2287,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.ioctl		= nvme_ioctl,
 	.compat_ioctl	= nvme_compat_ioctl,
 	.getgeo		= nvme_getgeo,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 #endif /* CONFIG_NVME_MULTIPATH */
@@ -2270,7 +2369,10 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 
 	ctrl->page_size = 1 << page_shift;
 
-	ctrl->ctrl_config = NVME_CC_CSS_NVM;
+	if (NVME_CAP_CSS(ctrl->cap) & NVME_CAP_CSS_CSI)
+		ctrl->ctrl_config = NVME_CC_CSS_CSI;
+	else
+		ctrl->ctrl_config = NVME_CC_CSS_NVM;
 	ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
 	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
@@ -2818,7 +2920,7 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
@@ -2832,27 +2934,55 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
 	c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));
+	c.get_log_page.csi = csi;
 
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
+static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
 {
+	struct nvme_cel *cel, *ret = NULL;
+
+	spin_lock(&ctrl->lock);
+	list_for_each_entry(cel, &ctrl->cels, entry) {
+		if (cel->csi == csi) {
+			ret = cel;
+			break;
+		}
+	}
+	spin_unlock(&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);
 	int ret;
 
-	if (!ctrl->effects)
-		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
+	if (cel)
+		goto out;
 
-	if (!ctrl->effects)
-		return 0;
+	cel = kzalloc(sizeof(*cel), GFP_KERNEL);
+	if (!cel)
+		return -ENOMEM;
 
-	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
-			ctrl->effects, sizeof(*ctrl->effects), 0);
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi,
+			&cel->log, sizeof(cel->log), 0);
 	if (ret) {
-		kfree(ctrl->effects);
-		ctrl->effects = NULL;
+		kfree(cel);
+		return ret;
 	}
-	return ret;
+
+	cel->csi = csi;
+
+	spin_lock(&ctrl->lock);
+	list_add_tail(&cel->entry, &ctrl->cels);
+	spin_unlock(&ctrl->lock);
+out:
+	*log = &cel->log;
+	return 0;
 }
 
 /*
@@ -2873,7 +3003,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		return ret;
 	}
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
-	ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
+	ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
 
 	if (ctrl->vs >= NVME_VS(1, 1, 0))
 		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
@@ -2885,7 +3015,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
-		ret = nvme_get_effects_log(ctrl);
+		ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
 		if (ret < 0)
 			goto out_free;
 	}
@@ -2947,7 +3077,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	if (id->rtd3e) {
 		/* us -> s */
-		u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000;
+		u32 transition_time = le32_to_cpu(id->rtd3e) / USEC_PER_SEC;
 
 		ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time,
 						 shutdown_timeout, 60);
@@ -3405,6 +3535,66 @@ static ssize_t nvme_sysfs_show_address(struct device *dev,
 }
 static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);
 
+static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+
+	if (ctrl->opts->max_reconnects == -1)
+		return sprintf(buf, "off\n");
+	return sprintf(buf, "%d\n",
+			opts->max_reconnects * opts->reconnect_delay);
+}
+
+static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+	int ctrl_loss_tmo, err;
+
+	err = kstrtoint(buf, 10, &ctrl_loss_tmo);
+	if (err)
+		return -EINVAL;
+
+	else if (ctrl_loss_tmo < 0)
+		opts->max_reconnects = -1;
+	else
+		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+						opts->reconnect_delay);
+	return count;
+}
+static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR,
+	nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store);
+
+static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (ctrl->opts->reconnect_delay == -1)
+		return sprintf(buf, "off\n");
+	return sprintf(buf, "%d\n", ctrl->opts->reconnect_delay);
+}
+
+static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned int v;
+	int err;
+
+	err = kstrtou32(buf, 10, &v);
+	if (err || v > UINT_MAX)
+		return -EINVAL;
+
+	ctrl->opts->reconnect_delay = v;
+	return count;
+}
+static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR,
+	nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store);
+
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -3422,6 +3612,8 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_sqsize.attr,
 	&dev_attr_hostnqn.attr,
 	&dev_attr_hostid.attr,
+	&dev_attr_ctrl_loss_tmo.attr,
+	&dev_attr_reconnect_delay.attr,
 	NULL
 };
 
@@ -3518,6 +3710,13 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		goto out_cleanup_srcu;
 	}
 
+	if (head->ids.csi) {
+		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
+		if (ret)
+			goto out_cleanup_srcu;
+	} else
+		head->effects = ctrl->effects;
+
 	ret = nvme_mpath_alloc_disk(ctrl, head);
 	if (ret)
 		goto out_cleanup_srcu;
@@ -3734,7 +3933,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	nvme_mpath_clear_current_path(ns);
 	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
 
-	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
+	if (ns->disk->flags & GENHD_FL_UP) {
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
 		if (blk_get_integrity(ns->disk))
@@ -3765,7 +3964,7 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	ns = nvme_find_get_ns(ctrl, nsid);
 	if (ns) {
-		if (ns->disk && revalidate_disk(ns->disk))
+		if (revalidate_disk(ns->disk))
 			nvme_ns_remove(ns);
 		nvme_put_ns(ns);
 	} else
@@ -3858,8 +4057,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
-			log_size, 0);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0,
+			NVME_CSI_NVM, log, log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -4003,8 +4202,8 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
-			sizeof(*log), 0))
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM,
+			log, sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
@@ -4141,11 +4340,16 @@ 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);
 
-	kfree(ctrl->effects);
+	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
+		list_del(&cel->entry);
+		kfree(cel);
+	}
+
 	nvme_mpath_uninit(ctrl);
 	__free_page(ctrl->discard_page);
 
@@ -4176,6 +4380,7 @@ 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);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->