Merge branch 'for-5.9/drivers' into for-5.9/block-merge

* for-5.9/drivers: (38 commits)
  block: add max_active_zones to blk-sysfs
  block: add max_open_zones to blk-sysfs
  s390/dasd: Use struct_size() helper
  s390/dasd: fix inability to use DASD with DIAG driver
  md-cluster: fix wild pointer of unlock_all_bitmaps()
  md/raid5-cache: clear MD_SB_CHANGE_PENDING before flushing stripes
  md: fix deadlock causing by sysfs_notify
  md: improve io stats accounting
  md: raid0/linear: fix dereference before null check on pointer mddev
  rsxx: switch from 'pci_free_consistent()' to 'dma_free_coherent()'
  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
  ...

18 files changed, 690 insertions, 131 deletions

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 71c2c1bf3cc1..e9d83b98d79d 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;
@@ -1986,7 +2061,7 @@ 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;
@@ -2034,6 +2109,28 @@ 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) {
@@ -2164,6 +2261,7 @@ 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,
 };
 
@@ -2190,6 +2288,7 @@ 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 */
@@ -2271,7 +2370,10 @@ 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;
@@ -2819,7 +2921,7 @@ 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 = { };
@@ -2833,27 +2935,55 @@ 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;
 }
 
 /*
@@ -2874,7 +3004,7 @@ 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);
@@ -2886,7 +3016,7 @@ 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;
 	}
@@ -2948,7 +3078,7 @@ 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);
@@ -3406,6 +3536,66 @@ 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,
@@ -3423,6 +3613,8 @@ 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
 };
 
@@ -3519,6 +3711,13 @@ 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;
@@ -3735,7 +3934,7 @@ 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))
@@ -3766,7 +3965,7 @@ 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
@@ -3859,8 +4058,8 @@ 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);
@@ -4004,8 +4203,8 @@ 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);
 }
@@ -4142,11 +4341,16 @@ 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);
 
@@ -4177,6 +4381,7 @@ 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->dev = dev;
 	ctrl->ops = ops;
@@ -4373,6 +4578,8 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
 	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index 2e6477ed420f..23ba8bf678ae 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -62,7 +62,7 @@ static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
 	int ret;
 
 	ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
-			   &data->log, sizeof(data->log), 0);
+			   NVME_CSI_NVM, &data->log, sizeof(data->log), 0);
 
 	return ret <= 0 ? ret : -EIO;
 }
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 69608755d415..8e562d0f2c30 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -593,8 +593,8 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 		dev_meta_off = dev_meta;
 
 		ret = nvme_get_log(ctrl, ns->head->ns_id,
-				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
-				offset);
+				NVME_NVM_LOG_REPORT_CHUNK, 0, NVME_CSI_NVM,
+				dev_meta, len, offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5a37a595411e..74bad4e3d377 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -527,7 +527,7 @@ static int nvme_read_ana_log(struct nvme_ctrl *ctrl)
 	int error;
 
 	mutex_lock(&ctrl->ana_lock);
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0,
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, NVME_CSI_NVM,
 			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
 	if (error) {
 		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 26099eaf1b1c..e536dd919073 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -191,6 +191,12 @@ struct nvme_fault_inject {
 #endif
 };
 
+struct nvme_cel {
+	struct list_head	entry;
+	struct nvme_effects_log	log;
+	u8			csi;
+};
+
 struct nvme_ctrl {
 	bool comp_seen;
 	enum nvme_ctrl_state state;
@@ -232,6 +238,9 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u32 max_zone_append;
+#endif
 	u16 crdt[3];
 	u16 oncs;
 	u16 oacs;
@@ -257,6 +266,7 @@ struct nvme_ctrl {
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
 	struct nvme_effects_log *effects;
+	struct list_head cels;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
@@ -339,6 +349,7 @@ struct nvme_ns_ids {
 	u8	eui64[8];
 	u8	nguid[16];
 	uuid_t	uuid;
+	u8	csi;
 };
 
 /*
@@ -358,6 +369,7 @@ struct nvme_ns_head {
 	struct kref		ref;
 	bool			shared;
 	int			instance;
+	struct nvme_effects_log *effects;
 #ifdef CONFIG_NVME_MULTIPATH
 	struct gendisk		*disk;
 	struct bio_list		requeue_list;
@@ -395,6 +407,9 @@ struct nvme_ns {
 	u16 sgs;
 	u32 sws;
 	u8 pi_type;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u64 zsze;
+#endif
 	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
@@ -560,8 +575,11 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 
-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_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+		struct nvme_ns_head **head, int *srcu_idx);
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
 
 extern const struct attribute_group *nvme_ns_id_attr_groups[];
 extern const struct block_device_operations nvme_ns_head_ops;
@@ -697,6 +715,36 @@ static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+#ifdef CONFIG_BLK_DEV_ZONED
+int nvme_update_zone_info(struct gendisk *disk, 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);
+
+blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
+				       struct nvme_command *cmnd,
+				       enum nvme_zone_mgmt_action action);
+#else
+#define nvme_report_zones NULL
+
+static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_zone_mgmt_action action)
+{
+	return BLK_STS_NOTSUPP;
+}
+
+static inline int nvme_update_zone_info(struct gendisk *disk,
+					struct nvme_ns *ns,
+					unsigned lbaf)
+{
+	dev_warn(ns->ctrl->device,
+		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
+	return -EPROTONOSUPPORT;
+}
+#endif
+
 #ifdef CONFIG_NVM
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 74a2e2e00794..45e94f016ec2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -61,10 +61,10 @@ MODULE_PARM_DESC(sgl_threshold,
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
 static const struct kernel_param_ops io_queue_depth_ops = {
 	.set = io_queue_depth_set,
-	.get = param_get_int,
+	.get = param_get_uint,
 };
 
-static int io_queue_depth = 1024;
+static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
 
@@ -115,7 +115,7 @@ struct nvme_dev {
 	unsigned max_qid;
 	unsigned io_queues[HCTX_MAX_TYPES];
 	unsigned int num_vecs;
-	int q_depth;
+	u16 q_depth;
 	int io_sqes;
 	u32 db_stride;
 	void __iomem *bar;
@@ -151,13 +151,14 @@ struct nvme_dev {
 
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
-	int n = 0, ret;
+	int ret;
+	u16 n;
 
-	ret = kstrtoint(val, 10, &n);
+	ret = kstrtou16(val, 10, &n);
 	if (ret != 0 || n < 2)
 		return -EINVAL;
 
-	return param_set_int(val, kp);
+	return param_set_ushort(val, kp);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -361,7 +362,7 @@ static int nvme_pci_npages_sgl(unsigned int num_seg)
 	return DIV_ROUND_UP(num_seg * sizeof(struct nvme_sgl_desc), PAGE_SIZE);
 }
 
-static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev,
+static size_t nvme_pci_iod_alloc_size(struct nvme_dev *dev,
 		unsigned int size, unsigned int nseg, bool use_sgl)
 {
 	size_t alloc_size;
@@ -500,9 +501,6 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
 	int nseg = blk_rq_nr_phys_segments(req);
 	unsigned int avg_seg_size;
 
-	if (nseg == 0)