Merge tag 'nvme-5.18-2022-03-03' of git://git.infradead.org/nvme into for-5.18/drivers

Pull NVMe updates from Christoph:

"nvme updates for Linux 5.18

 - add vectored-io support for user-passthrough (Kanchan Joshi)
 - add verbose error logging (Alan Adamson)
 - support buffered I/O on block devices in nvmet (Chaitanya Kulkarni)
 - central discovery controller support (Martin Belanger)
 - fix and extended the globally unique idenfier validation (me)
 - move away from the deprecated IDA APIs (Sagi Grimberg)
 - misc code cleanup (Keith Busch, Max Gurtovoy, Qinghua Jin,
   Chaitanya Kulkarni)"

* tag 'nvme-5.18-2022-03-03' of git://git.infradead.org/nvme: (27 commits)
  nvme: check that EUI/GUID/UUID are globally unique
  nvme: check for duplicate identifiers earlier
  nvme: fix the check for duplicate unique identifiers
  nvme: cleanup __nvme_check_ids
  nvme: remove nssa from struct nvme_ctrl
  nvme: explicitly set non-error for directives
  nvme: expose cntrltype and dctype through sysfs
  nvme: send uevent on connection up
  nvme: add vectored-io support for user-passthrough
  nvme: add verbose error logging
  nvme: add a helper to initialize connect_q
  nvme-rdma: add helpers for mapping/unmapping request
  nvmet-tcp: replace ida_simple[get|remove] with the simler ida_[alloc|free]
  nvmet-rdma: replace ida_simple[get|remove] with the simler ida_[alloc|free]
  nvmet-fc: replace ida_simple[get|remove] with the simler ida_[alloc|free]
  nvmet: replace ida_simple[get|remove] with the simler ida_[alloc|free]
  nvme-fc: replace ida_simple[get|remove] with the simler ida_[alloc|free]
  nvme: replace ida_simple[get|remove] with the simler ida_[alloc|free]
  nvmet: allow bdev in buffered_io mode
  nvmet: use i_size_read() to set size for file-ns
  ...

drivers/nvme/host/Kconfig

@@ -24,6 +24,14 @@ config NVME_MULTIPATH
 	   /dev/nvmeXnY device will show up for each NVMe namespace,
 	   even if it is accessible through multiple controllers.
 
+config NVME_VERBOSE_ERRORS
+	bool "NVMe verbose error reporting"
+	depends on NVME_CORE
+	help
+	   This option enables verbose reporting for NVMe errors. The
+	   error translation table will grow the kernel image size by
+	   about 4 KB.
+
 config NVME_HWMON
 	bool "NVMe hardware monitoring"
 	depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON)

drivers/nvme/host/Makefile

@@ -9,7 +9,7 @@ obj-$(CONFIG_NVME_RDMA)			+= nvme-rdma.o
 obj-$(CONFIG_NVME_FC)			+= nvme-fc.o
 obj-$(CONFIG_NVME_TCP)			+= nvme-tcp.o
 
-nvme-core-y				:= core.o ioctl.o
+nvme-core-y				:= core.o ioctl.o constants.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o

drivers/nvme/host/constants.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express device driver verbose errors
+ * Copyright (c) 2022, Oracle and/or its affiliates
+ */
+
+#include <linux/blkdev.h>
+#include "nvme.h"
+
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+static const char * const nvme_ops[] = {
+	[nvme_cmd_flush] = "Flush",
+	[nvme_cmd_write] = "Write",
+	[nvme_cmd_read] = "Read",
+	[nvme_cmd_write_uncor] = "Write Uncorrectable",
+	[nvme_cmd_compare] = "Compare",
+	[nvme_cmd_write_zeroes] = "Write Zeros",
+	[nvme_cmd_dsm] = "Dataset Management",
+	[nvme_cmd_verify] = "Verify",
+	[nvme_cmd_resv_register] = "Reservation Register",
+	[nvme_cmd_resv_report] = "Reservation Report",
+	[nvme_cmd_resv_acquire] = "Reservation Acquire",
+	[nvme_cmd_resv_release] = "Reservation Release",
+	[nvme_cmd_zone_mgmt_send] = "Zone Management Send",
+	[nvme_cmd_zone_mgmt_recv] = "Zone Management Receive",
+	[nvme_cmd_zone_append] = "Zone Management Append",
+};
+
+static const char * const nvme_admin_ops[] = {
+	[nvme_admin_delete_sq] = "Delete SQ",
+	[nvme_admin_create_sq] = "Create SQ",
+	[nvme_admin_get_log_page] = "Get Log Page",
+	[nvme_admin_delete_cq] = "Delete CQ",
+	[nvme_admin_create_cq] = "Create CQ",
+	[nvme_admin_identify] = "Identify",
+	[nvme_admin_abort_cmd] = "Abort Command",
+	[nvme_admin_set_features] = "Set Features",
+	[nvme_admin_get_features] = "Get Features",
+	[nvme_admin_async_event] = "Async Event",
+	[nvme_admin_ns_mgmt] = "Namespace Management",
+	[nvme_admin_activate_fw] = "Activate Firmware",
+	[nvme_admin_download_fw] = "Download Firmware",
+	[nvme_admin_dev_self_test] = "Device Self Test",
+	[nvme_admin_ns_attach] = "Namespace Attach",
+	[nvme_admin_keep_alive] = "Keep Alive",
+	[nvme_admin_directive_send] = "Directive Send",
+	[nvme_admin_directive_recv] = "Directive Receive",
+	[nvme_admin_virtual_mgmt] = "Virtual Management",
+	[nvme_admin_nvme_mi_send] = "NVMe Send MI",
+	[nvme_admin_nvme_mi_recv] = "NVMe Receive MI",
+	[nvme_admin_dbbuf] = "Doorbell Buffer Config",
+	[nvme_admin_format_nvm] = "Format NVM",
+	[nvme_admin_security_send] = "Security Send",
+	[nvme_admin_security_recv] = "Security Receive",
+	[nvme_admin_sanitize_nvm] = "Sanitize NVM",
+	[nvme_admin_get_lba_status] = "Get LBA Status",
+};
+
+static const char * const nvme_statuses[] = {
+	[NVME_SC_SUCCESS] = "Success",
+	[NVME_SC_INVALID_OPCODE] = "Invalid Command Opcode",
+	[NVME_SC_INVALID_FIELD] = "Invalid Field in Command",
+	[NVME_SC_CMDID_CONFLICT] = "Command ID Conflict",
+	[NVME_SC_DATA_XFER_ERROR] = "Data Transfer Error",
+	[NVME_SC_POWER_LOSS] = "Commands Aborted due to Power Loss Notification",
+	[NVME_SC_INTERNAL] = "Internal Error",
+	[NVME_SC_ABORT_REQ] = "Command Abort Requested",
+	[NVME_SC_ABORT_QUEUE] = "Command Aborted due to SQ Deletion",
+	[NVME_SC_FUSED_FAIL] = "Command Aborted due to Failed Fused Command",
+	[NVME_SC_FUSED_MISSING] = "Command Aborted due to Missing Fused Command",
+	[NVME_SC_INVALID_NS] = "Invalid Namespace or Format",
+	[NVME_SC_CMD_SEQ_ERROR] = "Command Sequence Error",
+	[NVME_SC_SGL_INVALID_LAST] = "Invalid SGL Segment Descriptor",
+	[NVME_SC_SGL_INVALID_COUNT] = "Invalid Number of SGL Descriptors",
+	[NVME_SC_SGL_INVALID_DATA] = "Data SGL Length Invalid",
+	[NVME_SC_SGL_INVALID_METADATA] = "Metadata SGL Length Invalid",
+	[NVME_SC_SGL_INVALID_TYPE] = "SGL Descriptor Type Invalid",
+	[NVME_SC_CMB_INVALID_USE] = "Invalid Use of Controller Memory Buffer",
+	[NVME_SC_PRP_INVALID_OFFSET] = "PRP Offset Invalid",
+	[NVME_SC_ATOMIC_WU_EXCEEDED] = "Atomic Write Unit Exceeded",
+	[NVME_SC_OP_DENIED] = "Operation Denied",
+	[NVME_SC_SGL_INVALID_OFFSET] = "SGL Offset Invalid",
+	[NVME_SC_RESERVED] = "Reserved",
+	[NVME_SC_HOST_ID_INCONSIST] = "Host Identifier Inconsistent Format",
+	[NVME_SC_KA_TIMEOUT_EXPIRED] = "Keep Alive Timeout Expired",
+	[NVME_SC_KA_TIMEOUT_INVALID] = "Keep Alive Timeout Invalid",
+	[NVME_SC_ABORTED_PREEMPT_ABORT] = "Command Aborted due to Preempt and Abort",
+	[NVME_SC_SANITIZE_FAILED] = "Sanitize Failed",
+	[NVME_SC_SANITIZE_IN_PROGRESS] = "Sanitize In Progress",
+	[NVME_SC_SGL_INVALID_GRANULARITY] = "SGL Data Block Granularity Invalid",
+	[NVME_SC_CMD_NOT_SUP_CMB_QUEUE] = "Command Not Supported for Queue in CMB",
+	[NVME_SC_NS_WRITE_PROTECTED] = "Namespace is Write Protected",
+	[NVME_SC_CMD_INTERRUPTED] = "Command Interrupted",
+	[NVME_SC_TRANSIENT_TR_ERR] = "Transient Transport Error",
+	[NVME_SC_INVALID_IO_CMD_SET] = "Invalid IO Command Set",
+	[NVME_SC_LBA_RANGE] = "LBA Out of Range",
+	[NVME_SC_CAP_EXCEEDED] = "Capacity Exceeded",
+	[NVME_SC_NS_NOT_READY] = "Namespace Not Ready",
+	[NVME_SC_RESERVATION_CONFLICT] = "Reservation Conflict",
+	[NVME_SC_FORMAT_IN_PROGRESS] = "Format In Progress",
+	[NVME_SC_CQ_INVALID] = "Completion Queue Invalid",
+	[NVME_SC_QID_INVALID] = "Invalid Queue Identifier",
+	[NVME_SC_QUEUE_SIZE] = "Invalid Queue Size",
+	[NVME_SC_ABORT_LIMIT] = "Abort Command Limit Exceeded",
+	[NVME_SC_ABORT_MISSING] = "Reserved", /* XXX */
+	[NVME_SC_ASYNC_LIMIT] = "Asynchronous Event Request Limit Exceeded",
+	[NVME_SC_FIRMWARE_SLOT] = "Invalid Firmware Slot",
+	[NVME_SC_FIRMWARE_IMAGE] = "Invalid Firmware Image",
+	[NVME_SC_INVALID_VECTOR] = "Invalid Interrupt Vector",
+	[NVME_SC_INVALID_LOG_PAGE] = "Invalid Log Page",
+	[NVME_SC_INVALID_FORMAT] = "Invalid Format",
+	[NVME_SC_FW_NEEDS_CONV_RESET] = "Firmware Activation Requires Conventional Reset",
+	[NVME_SC_INVALID_QUEUE] = "Invalid Queue Deletion",
+	[NVME_SC_FEATURE_NOT_SAVEABLE] = "Feature Identifier Not Saveable",
+	[NVME_SC_FEATURE_NOT_CHANGEABLE] = "Feature Not Changeable",
+	[NVME_SC_FEATURE_NOT_PER_NS] = "Feature Not Namespace Specific",
+	[NVME_SC_FW_NEEDS_SUBSYS_RESET] = "Firmware Activation Requires NVM Subsystem Reset",
+	[NVME_SC_FW_NEEDS_RESET] = "Firmware Activation Requires Reset",
+	[NVME_SC_FW_NEEDS_MAX_TIME] = "Firmware Activation Requires Maximum Time Violation",
+	[NVME_SC_FW_ACTIVATE_PROHIBITED] = "Firmware Activation Prohibited",
+	[NVME_SC_OVERLAPPING_RANGE] = "Overlapping Range",
+	[NVME_SC_NS_INSUFFICIENT_CAP] = "Namespace Insufficient Capacity",
+	[NVME_SC_NS_ID_UNAVAILABLE] = "Namespace Identifier Unavailable",
+	[NVME_SC_NS_ALREADY_ATTACHED] = "Namespace Already Attached",
+	[NVME_SC_NS_IS_PRIVATE] = "Namespace Is Private",
+	[NVME_SC_NS_NOT_ATTACHED] = "Namespace Not Attached",
+	[NVME_SC_THIN_PROV_NOT_SUPP] = "Thin Provisioning Not Supported",
+	[NVME_SC_CTRL_LIST_INVALID] = "Controller List Invalid",
+	[NVME_SC_SELT_TEST_IN_PROGRESS] = "Device Self-test In Progress",
+	[NVME_SC_BP_WRITE_PROHIBITED] = "Boot Partition Write Prohibited",
+	[NVME_SC_CTRL_ID_INVALID] = "Invalid Controller Identifier",
+	[NVME_SC_SEC_CTRL_STATE_INVALID] = "Invalid Secondary Controller State",
+	[NVME_SC_CTRL_RES_NUM_INVALID] = "Invalid Number of Controller Resources",
+	[NVME_SC_RES_ID_INVALID] = "Invalid Resource Identifier",
+	[NVME_SC_PMR_SAN_PROHIBITED] = "Sanitize Prohibited",
+	[NVME_SC_ANA_GROUP_ID_INVALID] = "ANA Group Identifier Invalid",
+	[NVME_SC_ANA_ATTACH_FAILED] = "ANA Attach Failed",
+	[NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes",
+	[NVME_SC_INVALID_PI] = "Invalid Protection Information",
+	[NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range",
+	[NVME_SC_ONCS_NOT_SUPPORTED] = "ONCS Not Supported",
+	[NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error",
+	[NVME_SC_ZONE_FULL] = "Zone Is Full",
+	[NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only",
+	[NVME_SC_ZONE_OFFLINE] = "Zone Is Offline",
+	[NVME_SC_ZONE_INVALID_WRITE] = "Zone Invalid Write",
+	[NVME_SC_ZONE_TOO_MANY_ACTIVE] = "Too Many Active Zones",
+	[NVME_SC_ZONE_TOO_MANY_OPEN] = "Too Many Open Zones",
+	[NVME_SC_ZONE_INVALID_TRANSITION] = "Invalid Zone State Transition",
+	[NVME_SC_WRITE_FAULT] = "Write Fault",
+	[NVME_SC_READ_ERROR] = "Unrecovered Read Error",
+	[NVME_SC_GUARD_CHECK] = "End-to-end Guard Check Error",
+	[NVME_SC_APPTAG_CHECK] = "End-to-end Application Tag Check Error",
+	[NVME_SC_REFTAG_CHECK] = "End-to-end Reference Tag Check Error",
+	[NVME_SC_COMPARE_FAILED] = "Compare Failure",
+	[NVME_SC_ACCESS_DENIED] = "Access Denied",
+	[NVME_SC_UNWRITTEN_BLOCK] = "Deallocated or Unwritten Logical Block",
+	[NVME_SC_ANA_PERSISTENT_LOSS] = "Asymmetric Access Persistent Loss",
+	[NVME_SC_ANA_INACCESSIBLE] = "Asymmetric Access Inaccessible",
+	[NVME_SC_ANA_TRANSITION] = "Asymmetric Access Transition",
+	[NVME_SC_HOST_PATH_ERROR] = "Host Pathing Error",
+};
+
+const unsigned char *nvme_get_error_status_str(u16 status)
+{
+	status &= 0x7ff;
+	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
+		return nvme_statuses[status & 0x7ff];
+	return "Unknown";
+}
+
+const unsigned char *nvme_get_opcode_str(u8 opcode)
+{
+	if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode])
+		return nvme_ops[opcode];
+	return "Unknown";
+}
+
+const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+{
+	if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode])
+		return nvme_admin_ops[opcode];
+	return "Unknown";
+}
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */

drivers/nvme/host/core.c

@@ -299,6 +299,37 @@ static void nvme_retry_req(struct request *req)
 	blk_mq_delay_kick_requeue_list(req->q, delay);
 }
 
+static void nvme_log_error(struct request *req)
+{
+	struct nvme_ns *ns = req->q->queuedata;
+	struct nvme_request *nr = nvme_req(req);
+
+	if (ns) {
+		pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
+		       ns->disk ? ns->disk->disk_name : "?",
+		       nvme_get_opcode_str(nr->cmd->common.opcode),
+		       nr->cmd->common.opcode,
+		       (unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)),
+		       (unsigned long long)blk_rq_bytes(req) >> ns->lba_shift,
+		       nvme_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 "  : "");
+		return;
+	}
+
+	pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s\n",
+			   dev_name(nr->ctrl->device),
+			   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 "  : "");
+}
+
 enum nvme_disposition {
 	COMPLETE,
 	RETRY,
@@ -339,6 +370,8 @@ static inline void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
+	if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS))
+		nvme_log_error(req);
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	blk_mq_end_request(req, status);
@@ -561,7 +594,7 @@ static void nvme_free_ns_head(struct kref *ref)
 		container_of(ref, struct nvme_ns_head, ref);
 
 	nvme_mpath_remove_disk(head);
-	ida_simple_remove(&head->subsys->ns_ida, head->instance);
+	ida_free(&head->subsys->ns_ida, head->instance);
 	cleanup_srcu_struct(&head->srcu);
 	nvme_put_subsystem(head->subsys);
 	kfree(head);
@@ -757,6 +790,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
 static int nvme_configure_directives(struct nvme_ctrl *ctrl)
 {
 	struct streams_directive_params s;
+	u16 nssa;
 	int ret;
 
 	if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES))
@@ -772,14 +806,16 @@ static int nvme_configure_directives(struct nvme_ctrl *ctrl)
 	if (ret)
 		goto out_disable_stream;
 
-	ctrl->nssa = le16_to_cpu(s.nssa);
-	if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
+	nssa = le16_to_cpu(s.nssa);
+	if (nssa < BLK_MAX_WRITE_HINTS - 1) {
 		dev_info(ctrl->device, "too few streams (%u) available\n",
-					ctrl->nssa);
+					nssa);
+		/* this condition is not an error: streams are optional */
+		ret = 0;
 		goto out_disable_stream;
 	}
 
-	ctrl->nr_streams = min_t(u16, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
+	ctrl->nr_streams = min_t(u16, nssa, BLK_MAX_WRITE_HINTS - 1);
 	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
 	return 0;
 
@@ -1049,8 +1085,7 @@ EXPORT_SYMBOL_GPL(nvme_setup_cmd);
  * >0: nvme controller's cqe status response
  * <0: kernel error in lieu of controller response
  */
-static int nvme_execute_rq(struct gendisk *disk, struct request *rq,
-		bool at_head)
+static int nvme_execute_rq(struct request *rq, bool at_head)
 {
 	blk_status_t status;
 
@@ -1090,7 +1125,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	ret = nvme_execute_rq(NULL, req, at_head);
+	ret = nvme_execute_rq(req, at_head);
 	if (result && ret >= 0)
 		*result = nvme_req(req)->result;
  out:
@@ -1206,12 +1241,11 @@ int nvme_execute_passthru_rq(struct request *rq)
 	struct nvme_command *cmd = nvme_req(rq)->cmd;
 	struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl;
 	struct nvme_ns *ns = rq->q->queuedata;
-	struct gendisk *disk = ns ? ns->disk : NULL;
 	u32 effects;
 	int  ret;
 
 	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
-	ret = nvme_execute_rq(disk, rq, false);
+	ret = nvme_execute_rq(rq, false);
 	if (effects) /* nothing to be done for zero cmd effects */
 		nvme_passthru_end(ctrl, effects, cmd, ret);
 
@@ -1682,13 +1716,6 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
 }
 
-static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
-{
-	return !uuid_is_null(&ids->uuid) ||
-		memchr_inv(ids->nguid, 0, sizeof(ids->nguid)) ||
-		memchr_inv(ids->eui64, 0, sizeof(ids->eui64));
-}
-
 static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 {
 	return uuid_equal(&a->uuid, &b->uuid) &&
@@ -1979,7 +2006,7 @@ static char nvme_pr_type(enum pr_type type)
 	default:
 		return 0;
 	}
-};
+}
 
 static int nvme_send_ns_head_pr_command(struct block_device *bdev,
 		struct nvme_command *c, u8 data[16])
@@ -2567,7 +2594,7 @@ static void nvme_release_subsystem(struct device *dev)
 		container_of(dev, struct nvme_subsystem, dev);
 
 	if (subsys->instance >= 0)
-		ida_simple_remove(&nvme_instance_ida, subsys->instance);
+		ida_free(&nvme_instance_ida, subsys->instance);
 	kfree(subsys);
 }
 
@@ -2992,6 +3019,9 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->max_namespaces = le32_to_cpu(id->mnan);
 	ctrl->ctratt = le32_to_cpu(id->ctratt);
 
+	ctrl->cntrltype = id->cntrltype;
+	ctrl->dctype = id->dctype;
+
 	if (id->rtd3e) {
 		/* us -> s */
 		u32 transition_time = le32_to_cpu(id->rtd3e) / USEC_PER_SEC;
@@ -3525,6 +3555,40 @@ static ssize_t nvme_ctrl_fast_io_fail_tmo_store(struct device *dev,
 static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR,
 	nvme_ctrl_fast_io_fail_tmo_show, nvme_ctrl_fast_io_fail_tmo_store);
 
+static ssize_t cntrltype_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	static const char * const type[] = {
+		[NVME_CTRL_IO] = "io\n",
+		[NVME_CTRL_DISC] = "discovery\n",
+		[NVME_CTRL_ADMIN] = "admin\n",
+	};
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (ctrl->cntrltype > NVME_CTRL_ADMIN || !type[ctrl->cntrltype])
+		return sysfs_emit(buf, "reserved\n");
+
+	return sysfs_emit(buf, type[ctrl->cntrltype]);
+}
+static DEVICE_ATTR_RO(cntrltype);
+
+static ssize_t dctype_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	static const char * const type[] = {
+		[NVME_DCTYPE_NOT_REPORTED] = "none\n",
+		[NVME_DCTYPE_DDC] = "ddc\n",
+		[NVME_DCTYPE_CDC] = "cdc\n",
+	};
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (ctrl->dctype > NVME_DCTYPE_CDC || !type[ctrl->dctype])
+		return sysfs_emit(buf, "reserved\n");
+
+	return sysfs_emit(buf, type[ctrl->dctype]);
+}
+static DEVICE_ATTR_RO(dctype);
+
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -3546,6 +3610,8 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reconnect_delay.attr,
 	&dev_attr_fast_io_fail_tmo.attr,
 	&dev_attr_kato.attr,
+	&dev_attr_cntrltype.attr,
+	&dev_attr_dctype.attr,
 	NULL
 };
 
@@ -3600,16 +3666,24 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
 	return NULL;
 }
 
-static int __nvme_check_ids(struct nvme_subsystem *subsys,
-		struct nvme_ns_head *new)
+static int nvme_subsys_check_duplicate_ids(struct nvme_subsystem *subsys,
+		struct nvme_ns_ids *ids)
 {
+	bool has_uuid = !uuid_is_null(&ids->uuid);
+	bool has_nguid = memchr_inv(ids->nguid, 0, sizeof(ids->nguid));
+	bool has_eui64 = memchr_inv(ids->eui64, 0, sizeof(ids->eui64));
 	struct nvme_ns_head *h;
 
 	lockdep_assert_held(&subsys->lock);
 
 	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (nvme_ns_ids_valid(&new->ids) &&
-		    nvme_ns_ids_equal(&new->ids, &h->ids))
+		if (has_uuid && uuid_equal(&ids->uuid, &h->ids.uuid))
+			return -EINVAL;
+		if (has_nguid &&
+		    memcmp(&ids->nguid, &h->ids.nguid, sizeof(ids->nguid)) == 0)
+			return -EINVAL;
+		if (has_eui64 &&
+		    memcmp(&ids->eui64, &h->ids.eui64, sizeof(ids->eui64)) == 0)
 			return -EINVAL;
 	}
 
@@ -3618,7 +3692,7 @@ static int __nvme_check_ids(struct nvme_subsystem *subsys,
 
 static void nvme_cdev_rel(struct device *dev)
 {
-	ida_simple_remove(&nvme_ns_chr_minor_ida, MINOR(dev->devt));
+	ida_free(&nvme_ns_chr_minor_ida, MINOR(dev->devt));
 }
 
 void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device)
@@ -3632,7 +3706,7 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
 {
 	int minor, ret;
 
-	minor = ida_simple_get(&nvme_ns_chr_minor_ida, 0, 0, GFP_KERNEL);
+	minor = ida_alloc(&nvme_ns_chr_minor_ida, GFP_KERNEL);
 	if (minor < 0)
 		return minor;
 	cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
@@ -3695,7 +3769,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head = kzalloc(size, GFP_KERNEL);
 	if (!head)
 		goto out;
-	ret = ida_simple_get(&ctrl->subsys->ns_ida, 1, 0, GFP_KERNEL);
+	ret = ida_alloc_min(&ctrl->subsys->ns_ida, 1, GFP_KERNEL);
 	if (ret < 0)
 		goto out_free_head;
 	head->instance = ret;
@@ -3708,13 +3782,6 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->ids = *ids;
 	kref_init(&head->ref);
 
-	ret = __nvme_check_ids(ctrl->subsys, head);
-	if (ret) {
-		dev_err(ctrl->device,
-			"duplicate IDs for nsid %d\n", nsid);
-		goto out_cleanup_srcu;
-	}
-
 	if (head->ids.csi) {
 		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
 		if (ret)
@@ -3734,7 +3801,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 out_cleanup_srcu:
 	cleanup_srcu_struct(&head->srcu);
 out_ida_remove:
-	ida_simple_remove(&ctrl->subsys->ns_ida, head->instance);
+	ida_free(&ctrl->subsys->ns_ida, head->instance);
 out_free_head:
 	kfree(head);
 out:
@@ -3743,16 +3810,56 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	return ERR_PTR(ret);
 }
 
+static int nvme_global_check_duplicate_ids(struct nvme_subsystem *this,
+		struct nvme_ns_ids *ids)
+{
+	struct nvme_subsystem *s;
+	int ret = 0;
+
+	/*
+	 * Note that this check is racy as we try to avoid holding the global
+	 * lock over the whole ns_head creation.  But it is only intended as
+	 * a sanity check anyway.
+	 */
+	mutex_lock(&nvme_subsystems_lock);
+	list_for_each_entry(s, &nvme_subsystems, entry) {
+		if (s == this)
+			continue;
+		mutex_lock(&s->lock);
+		ret = nvme_subsys_check_duplicate_ids(s, ids);
+		mutex_unlock(&s->lock);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&nvme_subsystems_lock);
+
+	return ret;
+}
+
 static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 		struct nvme_ns_ids *ids, bool is_shared)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_ns_head *head = NULL;
-	int ret = 0;
+	int ret;
+
+	ret = nvme_global_check_duplicate_ids(ctrl->subsys, ids);
+	if (ret) {
+		dev_err(ctrl->device,
+			"globally duplicate IDs for nsid %d\n", nsid);
+		return ret;
+	}
 
 	mutex_lock(&ctrl->subsys->lock);
 	head = nvme_find_ns_head(ctrl->subsys, nsid);
 	if (!head) {
+		ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids);
+		if (ret) {
+			dev_err(ctrl->device,
+				"duplicate IDs in subsystem for nsid %d\n",
+				nsid);
+			goto out_unlock;
+		}
 		head = nvme_alloc_ns_head(ctrl, nsid, ids);
 		if (IS_ERR(head)) {
 			ret = PTR_ERR(head);
@@ -4231,6 +4338,13 @@ static int nvme_class_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return ret;
 }
 
+static void nvme_change_uevent(struct nvme_ctrl *ctrl, char *envdata)
+{
+	char *envp[2] = { envdata, NULL };
+
+	kobject_uevent_env(&ctrl->device->kobj, KOBJ_CHANGE, envp);
+}
+
 static void nvme_aen_uevent(struct nvme_ctrl *ctrl)
 {
 	char *envp[2] = { NULL, NULL };
@@ -4398,6 +4512,8 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);
 	}
+
+	nvme_change_uevent(ctrl, "NVME_EVENT=connected");
 }
 EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
@@ -4431,7 +4547,7 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_subsystem *subsys = ctrl->subsys;
 
 	if (!subsys || ctrl->instance != subsys->instance)
-		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
+		ida_free(&nvme_instance_ida, ctrl->instance);
 
 	nvme_free_cels(ctrl);
 	nvme_mpath_uninit(ctrl);
@@ -4490,7 +4606,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		goto out;
 	}
 
-	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
+	ret = ida_alloc(&nvme_instance_ida, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
 	ctrl->instance = ret;
@@ -4531,7 +4647,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	nvme_put_ctrl(ctrl);
 	kfree_const(ctrl->device->kobj.name);
 out_release_instance:
-	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
+	ida_free(&nvme_instance_ida, ctrl->instance);
 out:
 	if (ctrl->discard_page)
 		__free_page(ctrl->discard_page);

drivers/nvme/host/fabrics.c

@@ -144,11 +144,10 @@ EXPORT_SYMBOL_GPL(nvmf_get_address);
  */
 int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	union nvme_result res;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.prop_get.opcode = nvme_fabrics_command;
 	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
 	cmd.prop_get.offset = cpu_to_le32(off);
@@ -272,7 +271,7 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 	int err_sctype = errval & ~NVME_SC_DNR;
 
 	switch (err_sctype) {
-	case (NVME_SC_CONNECT_INVALID_PARAM):
+	case NVME_SC_CONNECT_INVALID_PARAM:
 		if (offset >> 16) {
 			char *inv_data = "Connect Invalid Data Parameter";
 
@@ -873,7 +872,7 @@ static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts,
 		unsigned int required_opts)
 {
 	if ((opts->mask & required_opts) != required_opts) {
-		int i;
+		unsigned int i;
 
 		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
 			if ((opt_tokens[i].token & required_opts) &&
@@ -923,7 +922,7 @@ static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts,
 		unsigned int allowed_opts)
 {
 	if (opts->mask & ~allowed_opts) {
-		int i;
+		unsigned int i;
 
 		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
 			if ((opt_tokens[i].token & opts->mask) &&

drivers/nvme/host/fc.c

@@ -259,7 +259,7 @@ nvme_fc_free_lport(struct kref *ref)
 		complete(&nvme_fc_unload_proceed);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
-	ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num);
+	ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num);
 	ida_destroy(&lport->endp_cnt);
 
 	put_device(lport->dev);
@@ -399,7 +399,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo,
 		goto out_reghost_failed;
 	}
 
-	idx = ida_simple_get(&nvme_fc_local_port_cnt, 0, 0, GFP_KERNEL);
+	idx = ida_alloc(&nvme_fc_local_port_cnt, GFP_KERNEL);
 	if (idx < 0) {
 		ret = -ENOSPC;
 		goto out_fail_kfree;
@@ -439,7 +439,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo,
 	return 0;
 
 out_ida_put:
-	ida_simple_remove(&nvme_fc_local_port_cnt, idx);
+	ida_free(&nvme_fc_local_port_cnt, idx);
 out_fail_kfree:
 	kfree(newrec);
 out_reghost_failed:
@@ -535,7 +535,7 @@ nvme_fc_free_rport(struct kref *ref)
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
 	WARN_ON(!list_empty(&rport->disc_list));
-	ida_simple_remove(&lport->endp_cnt, rport->remoteport.port_num);
+	ida_free(&lport->endp_cnt, rport->remoteport.port_num);
 
 	kfree(rport);
 
@@ -713,7 +713,7 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport,
 		goto out_lport_put;
 	}
 
-	idx = ida_simple_get(&lport->endp_cnt, 0, 0, GFP_KERNEL);
+	idx = ida_alloc(&lport->endp_cnt, GFP_KERNEL);
 	if (idx < 0) {
 		ret = -ENOSPC;
 		goto out_kfree_rport;
@@ -2393,7 +2393,7 @@ nvme_fc_ctrl_free(struct kref *ref)
 	put_device(ctrl->dev);
 	nvme_fc_rport_put(ctrl->rport);
 
-	ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
+	ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum);
 	if (ctrl->ctrl.opts)
 		nvmf_free_options(ctrl->ctrl.opts);
 	kfree(ctrl);
@@ -2916,11 +2916,9 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 
 	ctrl->ctrl.tagset = &ctrl->tag_set;
 
-	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
-	if (IS_ERR(ctrl->ctrl.connect_q)) {
-		ret = PTR_ERR(ctrl->ctrl.connect_q);
+	ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl));
+	if (ret)
 		goto out_free_tag_set;
-	}
 
 	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
@@ -3472,7 +3470,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		goto out_fail;
 	}
 
-	idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL);
+	idx = ida_alloc(&nvme_fc_ctrl_cnt, GFP_KERNEL);
 	if (idx < 0) {
 		ret = -ENOSPC;
 		goto out_free_ctrl;
@@ -3635,7 +3633,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	kfree(ctrl->queues);
 out_free_ida:
 	put_device(ctrl->dev);
-	ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
+	ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum);
 out_free_ctrl:
 	kfree(ctrl);
 out_fail:

drivers/nvme/host/ioctl.c

@@ -56,7 +56,7 @@ static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
 static int nvme_submit_user_cmd(struct request_queue *q,
 		struct nvme_command *cmd, void __user *ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, u64 *result, unsigned timeout)
+		u32 meta_seed, u64 *result, unsigned timeout, bool vec)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
@@ -75,8 +75,22 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	nvme_req(req)->flags |= NVME_REQ_USERCMD;
 
 	if (ubuffer && bufflen) {
-		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
+		if (!vec)
+			ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
 				GFP_KERNEL);
+		else {
+			struct iovec fast_iov[UIO_FASTIOV];
+			struct iovec *iov = fast_iov;
+			struct iov_iter iter;
+
+			ret = import_iovec(rq_data_dir(req), ubuffer, bufflen,
+					UIO_FASTIOV, &iov, &iter);
+			if (ret < 0)
+				goto out;
+			ret = blk_rq_map_user_iov(q, req, NULL, &iter,
+					GFP_KERNEL);
+			kfree(iov);
+		}
 		if (ret)
 			goto out;
 		bio = req->bio;
@@ -170,7 +184,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	return nvme_submit_user_cmd(ns->queue, &c,
 			nvme_to_user_ptr(io.addr), length,
-			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
+			metadata, meta_len, lower_32_bits(io.slba), NULL, 0,
+			false);
 }
 
 static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
@@ -224,7 +239,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			nvme_to_user_ptr(cmd.addr), cmd.data_len,
 			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
-			0, &result, timeout);
+			0, &result, timeout, false);
 
 	if (status >= 0) {
 		if (put_user(result, &ucmd->result))
@@ -235,7 +250,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 }
 
 static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-			struct nvme_passthru_cmd64 __user *ucmd)
+			struct nvme_passthru_cmd64 __user *ucmd, bool vec)
 {
 	struct nvme_passthru_cmd64 cmd;
 	struct nvme_command c;
@@ -270,7 +285,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			nvme_to_user_ptr(cmd.addr), cmd.data_len,
 			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
-			0, &cmd.result, timeout);
+			0, &cmd.result, timeout, vec);
 
 	if (status >= 0) {
 		if (put_user(cmd.result, &ucmd->result))
@@ -296,7 +311,7 @@ static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd,
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
 	case NVME_IOCTL_ADMIN64_CMD:
-		return nvme_user_cmd64(ctrl, NULL, argp);
+		return nvme_user_cmd64(ctrl, NULL, argp, false);
 	default:
 		return sed_ioctl(ctrl->opal_dev, cmd, argp);
 	}
@@ -340,7 +355,9 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
 	case NVME_IOCTL_SUBMIT_IO:
 		return nvme_submit_io(ns, argp);
 	case NVME_IOCTL_IO64_CMD:
-		return nvme_user_cmd64(ns->ctrl, ns, argp);
+		return nvme_user_cmd64(ns->ctrl, ns, argp, false);
+	case NVME_IOCTL_IO64_CMD_VEC:
+		return nvme_user_cmd64(ns->ctrl, ns, argp, true);
 	default:
 		return -ENOTTY;
 	}
@@ -480,7 +497,7 @@ long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
 	case NVME_IOCTL_ADMIN64_CMD:
-		return nvme_user_cmd64(ctrl, NULL, argp);
+		return nvme_user_cmd64(ctrl, NULL, argp, false);
 	case NVME_IOCTL_IO_CMD:
 		return nvme_dev_user_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:

drivers/nvme/host/nvme.h

@@ -280,7 +280,6 @@ struct nvme_ctrl {
 	u16 crdt[3];
 	u16 oncs;
 	u16 oacs;
-	u16 nssa;
 	u16 nr_streams;
 	u16 sqsize;
 	u32 max_namespaces;
@@ -349,6 +348,9 @@ struct nvme_ctrl {
 	unsigned long discard_page_busy;
 
 	struct nvme_fault_inject fault_inject;
+
+	enum nvme_ctrl_type cntrltype;
+	enum nvme_dctype dctype;
 };
 
 enum nvme_iopolicy {
@@ -894,6 +896,14 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 }
 #endif
 
+static inline int nvme_ctrl_init_connect_q(struct nvme_ctrl *ctrl)
+{
+	ctrl->connect_q = blk_mq_init_queue(ctrl->tagset);
+	if (IS_ERR(ctrl->connect_q))
+		return PTR_ERR(ctrl->connect_q);
+	return 0;
+}
+
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
 	return dev_to_disk(dev)->private_data;
@@ -930,4 +940,23 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
 	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
 }
 
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+const unsigned char *nvme_get_error_status_str(u16 status);
+const unsigned char *nvme_get_opcode_str(u8 opcode);
+const unsigned char *nvme_get_admin_opcode_str(u8 opcode);
+#else /* CONFIG_NVME_VERBOSE_ERRORS */
+static inline const unsigned char *nvme_get_error_status_str(u16 status)
+{
+	return "I/O Error";
+}
+static inline const unsigned char *nvme_get_opcode_str(u8 opcode)
+{
+	return "I/O Cmd";
+}
+static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+{
+	return "Admin Cmd";
+}
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */
+
 #endif /* _NVME_H */

drivers/nvme/host/rdma.c

@@ -978,11 +978,9 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			goto out_free_io_queues;
 		}
 
-		ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
-		if (IS_ERR(ctrl->ctrl.connect_q)) {
-			ret = PTR_ERR(ctrl->ctrl.connect_q);
+		ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl));
+		if (ret)
 			goto out_free_tag_set;
-		}
 	}
 
 	ret = nvme_rdma_start_io_queues(ctrl);
@@ -1282,6 +1280,22 @@ static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
 	return ib_post_send(queue->qp, &wr, NULL);
 }
 
+static void nvme_rdma_dma_unmap_req(struct ib_device *ibdev, struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+
+	if (blk_integrity_rq(rq)) {
+		ib_dma_unmap_sg(ibdev, req->metadata_sgl->sg_table.sgl,
+				req->metadata_sgl->nents, rq_dma_dir(rq));
+		sg_free_table_chained(&req->metadata_sgl->sg_table,
+				      NVME_INLINE_METADATA_SG_CNT);
+	}
+
+	ib_dma_unmap_sg(ibdev, req->data_sgl.sg_table.sgl, req->data_sgl.nents,
+			rq_dma_dir(rq));
+	sg_free_table_chained(&req->data_sgl.sg_table, NVME_INLINE_SG_CNT);
+}
+
 static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 		struct request *rq)
 {
@@ -1293,13 +1307,6 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 	if (!blk_rq_nr_phys_segments(rq))
 		return;
 
-	if (blk_integrity_rq(rq)) {
-		ib_dma_unmap_sg(ibdev, req->metadata_sgl->sg_table.sgl,
-				req->metadata_sgl->nents, rq_dma_dir(rq));
-		sg_free_table_chained(&req->metadata_sgl->sg_table,
-				      NVME_INLINE_METADATA_SG_CNT);
-	}
-
 	if (req->use_sig_mr)
 		pool = &queue->qp->sig_mrs;
 
@@ -1308,9 +1315,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 		req->mr = NULL;
 	}
 
-	ib_dma_unmap_sg(ibdev, req->data_sgl.sg_table.sgl, req->data_sgl.nents,
-			rq_dma_dir(rq));
-	sg_free_table_chained(&req->data_sgl.sg_table, NVME_INLINE_SG_CNT);
+	nvme_rdma_dma_unmap_req(ibdev, rq);
 }
 
 static int nvme_rdma_set_sg_null(struct nvme_command *c)
@@ -1521,22 +1526,11 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	return -EINVAL;
 }
 
-static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
-		struct request *rq, struct nvme_command *c)
+static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
+		int *count, int *pi_count)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
-	struct nvme_rdma_device *dev = queue->device;
-	struct ib_device *ibdev = dev->dev;
-	int pi_count = 0;
-	int count, ret;
-
-	req->num_sge = 1;
-	refcount_set(&req->ref, 2); /* send and recv completions */
-
-	c->common.flags |= NVME_CMD_SGL_METABUF;
-
-	if (!blk_rq_nr_phys_segments(rq))
-		return nvme_rdma_set_sg_null(c);
+	int ret;
 
 	req->data_sgl.sg_table.sgl = (struct scatterlist *)(req + 1);
 	ret = sg_alloc_table_chained(&req->data_sgl.sg_table,
@@ -1548,9 +1542,9 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 	req->data_sgl.nents = blk_rq_map_sg(rq->q, rq,
 					    req->data_sgl.sg_table.sgl);
 
-	count = ib_dma_map_sg(ibdev, req->data_sgl.sg_table.sgl,
-			      req->data_sgl.nents, rq_dma_dir(rq));
-	if (unlikely(count <= 0)) {
+	*count = ib_dma_map_sg(ibdev, req->data_sgl.sg_table.sgl,
+			       req->data_sgl.nents, rq_dma_dir(rq));
+	if (unlikely(*count <= 0)) {
 		ret = -EIO;
 		goto out_free_table;
 	}
@@ -1569,16 +1563,50 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 
 		req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq->q,
 				rq->bio, req->metadata_sgl->sg_table.sgl);
-		pi_count = ib_dma_map_sg(ibdev,
-					 req->metadata_sgl->sg_table.sgl,
-					 req->metadata_sgl->nents,
-					 rq_dma_dir(rq));
-		if (unlikely(pi_count <= 0)) {
+		*pi_count = ib_dma_map_sg(ibdev,
+					  req->metadata_sgl->sg_table.sgl,
+					  req->metadata_sgl->nents,
+					  rq_dma_dir(rq));
+		if (unlikely(*pi_count <= 0)) {
 			ret = -EIO;
 			goto out_free_pi_table;
 		}
 	}
 
+	return 0;
+
+out_free_pi_table:
+	sg_free_table_chained(&req->metadata_sgl->sg_table,
+			      NVME_INLINE_METADATA_SG_CNT);
+out_unmap_sg:
+	ib_dma_unmap_sg(ibdev, req->data_sgl.sg_table.sgl, req->data_sgl.nents,
+			rq_dma_dir(rq));
+out_free_table:
+	sg_free_table_chained(&req->data_sgl.sg_table, NVME_INLINE_SG_CNT);
+	return ret;
+}
+
+static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
+		struct request *rq, struct nvme_command *c)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int pi_count = 0;
+	int count, ret;
+
+	req->num_sge = 1;
+	refcount_set(&req->ref, 2); /* send and recv completions */
+
+	c->common.flags |= NVME_CMD_SGL_METABUF;
+
+	if (!blk_rq_nr_phys_segments(rq))
+		return nvme_rdma_set_sg_null(c);
+
+	ret = nvme_rdma_dma_map_req(ibdev, rq, &count, &pi_count);
+	if (unlikely(ret))
+		return ret;
+
 	if (req->use_sig_mr) {
 		ret = nvme_rdma_map_sg_pi(queue, req, c, count, pi_count);
 		goto out;
@@ -1602,23 +1630,12 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 	ret = nvme_rdma_map_sg_fr(queue, req, c, count);
 out:
 	if (unlikely(ret))
-		goto out_unmap_pi_sg;
+		goto out_dma_unmap_req;
 
 	return 0;
 
-out_unmap_pi_sg:
-	if (blk_integrity_rq(rq))
-		ib_dma_unmap_sg(ibdev, req->metadata_sgl->sg_table.sgl,
-				req->metadata_sgl->nents, rq_dma_dir(rq));
-out_free_pi_table:
-	if (blk_integrity_rq(rq))
-		sg_free_table_chained(&req->metadata_sgl->sg_table,
-				      NVME_INLINE_METADATA_SG_CNT);
-out_unmap_sg:
-	ib_dma_unmap_sg(ibdev, req->data_sgl.sg_table.sgl, req->data_sgl.nents,
-			rq_dma_dir(rq));
-out_free_table:
-	sg_free_table_chained(&req->data_sgl.sg_table, NVME_INLINE_SG_CNT);
+out_dma_unmap_req:
+	nvme_rdma_dma_unmap_req(ibdev, rq);
 	return ret;
 }
 

drivers/nvme/host/tcp.c

@@ -1825,11 +1825,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			goto out_free_io_queues;
 		}
 
-		ctrl->connect_q = blk_mq_init_queue(ctrl->tagset);
-		if (IS_ERR(ctrl->connect_q)) {
-			ret = PTR_ERR(ctrl->connect_q);
+		ret = nvme_ctrl_init_connect_q(ctrl);
+		if (ret)
 			goto out_free_tag_set;
-		}
 	}
 
 	ret = nvme_tcp_start_io_queues(ctrl);

drivers/nvme/target/core.c

@@ -1400,7 +1400,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	if (subsys->cntlid_min > subsys->cntlid_max)
 		goto out_free_sqs;
 
-	ret = ida_simple_get(&cntlid_ida,
+	ret = ida_alloc_range(&cntlid_ida,
 			     subsys->cntlid_min, subsys->cntlid_max,
 			     GFP_KERNEL);
 	if (ret < 0) {
@@ -1459,7 +1459,7 @@ static void nvmet_ctrl_free(struct kref *ref)
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fatal_err_work);
 
-	ida_simple_remove(&cntlid_ida, ctrl->cntlid);
+	ida_free(&cntlid_ida, ctrl->cntlid);
 
 	nvmet_async_events_free(ctrl);
 	kfree(ctrl->sqs);

drivers/nvme/target/fc.c

@@ -1115,7 +1115,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	if (!assoc)
 		return NULL;
 
-	idx = ida_simple_get(&tgtport->assoc_cnt, 0, 0, GFP_KERNEL);
+	idx = ida_alloc(&tgtport->assoc_cnt, GFP_KERNEL);
 	if (idx < 0)
 		goto out_free_assoc;
 
@@ -1157,7 +1157,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 out_put:
 	nvmet_fc_tgtport_put(tgtport);
 out_ida:
-	ida_simple_remove(&tgtport->assoc_cnt, idx);
+	ida_free(&tgtport->assoc_cnt, idx);
 out_free_assoc:
 	kfree(assoc);
 	return NULL;
@@ -1183,7 +1183,7 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	/* if pending Rcv Disconnect Association LS, send rsp now */
 	if (oldls)
 		nvmet_fc_xmt_ls_rsp(tgtport, oldls);
-	ida_simple_remove(&tgtport->assoc_cnt, assoc->a_id);
+	ida_free(&tgtport->assoc_cnt, assoc->a_id);
 	dev_info(tgtport->dev,
 		"{%d:%d} Association freed\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
@@ -1383,7 +1383,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 		goto out_regtgt_failed;
 	}
 
-	idx = ida_simple_get(&nvmet_fc_tgtport_cnt, 0, 0, GFP_KERNEL);
+	idx = ida_alloc(&nvmet_fc_tgtport_cnt, GFP_KERNEL);
 	if (idx < 0) {
 		ret = -ENOSPC;
 		goto out_fail_kfree;
@@ -1433,7 +1433,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 out_free_newrec:
 	put_device(dev);
 out_ida_put:
-	ida_simple_remove(&nvmet_fc_tgtport_cnt, idx);
+	ida_free(&nvmet_fc_tgtport_cnt, idx);
 out_fail_kfree:
 	kfree(newrec);
 out_regtgt_failed:
@@ -1460,7 +1460,7 @@ nvmet_fc_free_tgtport(struct kref *ref)
 	/* let the LLDD know we've finished tearing it down */
 	tgtport->ops->targetport_delete(&tgtport->fc_target_port);
 
-	ida_simple_remove(&nvmet_fc_tgtport_cnt,
+	ida_free(&nvmet_fc_tgtport_cnt,
 			tgtport->fc_target_port.port_num);
 
 	ida_destroy(&tgtport->assoc_cnt);

drivers/nvme/target/io-cmd-bdev.c

@@ -76,6 +76,14 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
 {
 	int ret;
 
+	/*
+	 * When buffered_io namespace attribute is enabled that means user want
+	 * this block device to be used as a file, so block device can take
+	 * an advantage of cache.
+	 */
+	if (ns->buffered_io)
+		return -ENOTBLK;
+
 	ns->bdev = blkdev_get_by_path(ns->device_path,
 			FMODE_READ | FMODE_WRITE, NULL);
 	if (IS_ERR(ns->bdev)) {

drivers/nvme/target/io-cmd-file.c

@@ -14,16 +14,9 @@
 #define NVMET_MAX_MPOOL_BVEC		16
 #define NVMET_MIN_MPOOL_OBJ		16
 
-int nvmet_file_ns_revalidate(struct nvmet_ns *ns)
+void nvmet_file_ns_revalidate(struct nvmet_ns *ns)
 {
-	struct kstat stat;
-	int ret;
-
-	ret = vfs_getattr(&ns->file->f_path, &stat, STATX_SIZE,
-			  AT_STATX_FORCE_SYNC);
-	if (!ret)
-		ns->size = stat.size;
-	return ret;
+	ns->size = i_size_read(ns->file->f_mapping->host);
 }
 
 void nvmet_file_ns_disable(struct nvmet_ns *ns)
@@ -43,7 +36,7 @@ void nvmet_file_ns_disable(struct nvmet_ns *ns)
 int nvmet_file_ns_enable(struct nvmet_ns *ns)
 {
 	int flags = O_RDWR | O_LARGEFILE;
-	int ret;
+	int ret = 0;
 
 	if (!ns->buffered_io)
 		flags |= O_DIRECT;
@@ -57,9 +50,7 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns)
 		return ret;
 	}
 
-	ret = nvmet_file_ns_revalidate(ns);
-	if (ret)
-		goto err;
+	nvmet_file_ns_revalidate(ns);
 
 	/*
 	 * i_blkbits can be greater than the universally accepted upper bound,

drivers/nvme/target/loop.c

@@ -543,11 +543,9 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 	if (ret)
 		goto out_destroy_queues;
 
-	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
-	if (IS_ERR(ctrl->ctrl.connect_q)) {
-		ret = PTR_ERR(ctrl->ctrl.connect_q);
+	ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl));
+	if (ret)
 		goto out_free_tagset;
-	}
 
 	ret = nvme_loop_connect_io_queues(ctrl);
 	if (ret)

drivers/nvme/target/nvmet.h

@@ -541,7 +541,7 @@ u16 nvmet_bdev_flush(struct nvmet_req *req);
 u16 nvmet_file_flush(struct nvmet_req *req);
 void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid);
 void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns);
-int nvmet_file_ns_revalidate(struct nvmet_ns *ns);
+void nvmet_file_ns_revalidate(struct nvmet_ns *ns);
 void nvmet_ns_revalidate(struct nvmet_ns *ns);
 u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts);
 

drivers/nvme/target/rdma.c

@@ -1356,7 +1356,7 @@ static void nvmet_rdma_free_queue(struct nvmet_rdma_queue *queue)
 				!queue->host_qid);
 	}
 	nvmet_rdma_free_rsps(queue);
-	ida_simple_remove(&nvmet_rdma_queue_ida, queue->idx);
+	ida_free(&nvmet_rdma_queue_ida, queue->idx);
 	kfree(queue);
 }
 
@@ -1459,7 +1459,7 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 	spin_lock_init(&queue->rsps_lock);
 	INIT_LIST_HEAD(&queue->queue_list);
 
-	queue->idx = ida_simple_get(&nvmet_rdma_queue_ida, 0, 0, GFP_KERNEL);
+	queue->idx = ida_alloc(&nvmet_rdma_queue_ida, GFP_KERNEL);
 	if (queue->idx < 0) {
 		ret = NVME_RDMA_CM_NO_RSC;
 		goto out_destroy_sq;
@@ -1510,7 +1510,7 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 out_free_responses:
 	nvmet_rdma_free_rsps(queue);
 out_ida_remove:
-	ida_simple_remove(&nvmet_rdma_queue_ida, queue->idx);
+	ida_free(&nvmet_rdma_queue_ida, queue->idx);
 out_destroy_sq:
 	nvmet_sq_destroy(&queue->nvme_sq);
 out_free_queue:

drivers/nvme/target/tcp.c

@@ -1473,7 +1473,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
 	nvmet_tcp_free_cmds(queue);
 	if (queue->hdr_digest || queue->data_digest)
 		nvmet_tcp_free_crypto(queue);
-	ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
+	ida_free(&nvmet_tcp_queue_ida, queue->idx);
 
 	page = virt_to_head_page(queue->pf_cache.va);
 	__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
@@ -1613,7 +1613,7 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	init_llist_head(&queue->resp_list);
 	INIT_LIST_HEAD(&queue->resp_send_list);
 
-	queue->idx = ida_simple_get(&nvmet_tcp_queue_ida, 0, 0, GFP_KERNEL);
+	queue->idx = ida_alloc(&nvmet_tcp_queue_ida, GFP_KERNEL);
 	if (queue->idx < 0) {
 		ret = queue->idx;
 		goto out_free_queue;
@@ -1646,7 +1646,7 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 out_free_connect:
 	nvmet_tcp_free_cmd(&queue->connect);
 out_ida_remove:
-	ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
+	ida_free(&nvmet_tcp_queue_ida, queue->idx);
 out_free_queue:
 	kfree(queue);
 	return ret;

include/linux/nvme-fc-driver.h

@@ -721,7 +721,7 @@ enum {
  *
  * Fields with static values for the port. Initialized by the
  * port_info struct supplied to the registration call.
- * @port_num:  NVME-FC transport subsytem port number
+ * @port_num:  NVME-FC transport subsystem port number
  * @node_name: FC WWNN for the port
  * @port_name: FC WWPN for the port
  * @private:   pointer to memory allocated alongside the local port

include/linux/nvme.h

@@ -43,6 +43,12 @@ enum nvme_ctrl_type {
 	NVME_CTRL_ADMIN	= 3,		/* Administrative controller */
 };
 
+enum nvme_dctype {
+	NVME_DCTYPE_NOT_REPORTED	= 0,
+	NVME_DCTYPE_DDC			= 1, /* Direct Discovery Controller */
+	NVME_DCTYPE_CDC			= 2, /* Central Discovery Controller */
+};
+
 /* Address Family codes for Discovery Log Page entry ADRFAM field */
 enum {
 	NVMF_ADDR_FAMILY_PCI	= 0,	/* PCIe */
@@ -320,7 +326,9 @@ struct nvme_id_ctrl {
 	__le16			icdoff;
 	__u8			ctrattr;
 	__u8			msdbd;
-	__u8			rsvd1804[244];
+	__u8			rsvd1804[2];
+	__u8			dctype;
+	__u8			rsvd1807[241];
 	struct nvme_id_power_state	psd[32];
 	__u8			vs[1024];
 };
@@ -1636,6 +1644,7 @@ enum {
 	NVME_SC_HOST_ABORTED_CMD	= 0x371,
 
 	NVME_SC_CRD			= 0x1800,
+	NVME_SC_MORE			= 0x2000,
 	NVME_SC_DNR			= 0x4000,
 };
 

include/uapi/linux/nvme_ioctl.h

@@ -55,7 +55,10 @@ struct nvme_passthru_cmd64 {
 	__u64	metadata;
 	__u64	addr;
 	__u32	metadata_len;
-	__u32	data_len;
+	union {
+		__u32	data_len; /* for non-vectored io */
+		__u32	vec_cnt; /* for vectored io */
+	};
 	__u32	cdw10;
 	__u32	cdw11;
 	__u32	cdw12;
@@ -78,5 +81,6 @@ struct nvme_passthru_cmd64 {
 #define NVME_IOCTL_RESCAN	_IO('N', 0x46)
 #define NVME_IOCTL_ADMIN64_CMD	_IOWR('N', 0x47, struct nvme_passthru_cmd64)
 #define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD_VEC	_IOWR('N', 0x49, struct nvme_passthru_cmd64)
 
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */