Merge tag 'nvme-5.14-2021-06-08' of git://git.infradead.org/nvme into for-5.14/drivers

Pull NVMe updates from Christoph:

"nvme updates for Linux 5.14

 - improve the APST configuration algorithm (Alexey Bogoslavsky)
 - look for StorageD3Enable on companion ACPI device (Mario Limonciello)
 - allow selecting the network interface for TCP connections
   (Martin Belanger)
 - misc cleanups (Amit Engel, Chaitanya Kulkarni, Colin Ian King, me)"

* tag 'nvme-5.14-2021-06-08' of git://git.infradead.org/nvme:
  nvmet: remove a superfluous variable
  nvmet: move ka_work initialization to nvmet_alloc_ctrl
  nvme: remove nvme_{get,put}_ns_from_disk
  nvme: split nvme_report_zones
  nvme: move the CSI sanity check into nvme_ns_report_zones
  nvme: add a sparse annotation to nvme_ns_head_ctrl_ioctl
  nvme: open code nvme_put_ns_from_disk in nvme_ns_head_ctrl_ioctl
  nvme: open code nvme_{get,put}_ns_from_disk in nvme_ns_head_ioctl
  nvme: open code nvme_put_ns_from_disk in nvme_ns_head_chr_ioctl
  nvme-fabrics: remove extra braces
  nvme-fabrics: remove an extra comment
  nvme-fabrics: remove extra new lines in the switch
  nvme-fabrics: fix the kerneldco comment for nvmf_log_connect_error()
  nvme-tcp: allow selecting the network interface for connections
  nvme-pci: look for StorageD3Enable on companion ACPI device instead
  nvme: extend and modify the APST configuration algorithm
  nvme: remove redundant initialization of variable ret

drivers/nvme/host/core.c

@@ -57,6 +57,26 @@ static bool force_apst;
 module_param(force_apst, bool, 0644);
 MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
 
+static unsigned long apst_primary_timeout_ms = 100;
+module_param(apst_primary_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(apst_primary_timeout_ms,
+	"primary APST timeout in ms");
+
+static unsigned long apst_secondary_timeout_ms = 2000;
+module_param(apst_secondary_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(apst_secondary_timeout_ms,
+	"secondary APST timeout in ms");
+
+static unsigned long apst_primary_latency_tol_us = 15000;
+module_param(apst_primary_latency_tol_us, ulong, 0644);
+MODULE_PARM_DESC(apst_primary_latency_tol_us,
+	"primary APST latency tolerance in us");
+
+static unsigned long apst_secondary_latency_tol_us = 100000;
+module_param(apst_secondary_latency_tol_us, ulong, 0644);
+MODULE_PARM_DESC(apst_secondary_latency_tol_us,
+	"secondary APST latency tolerance in us");
+
 static bool streams;
 module_param(streams, bool, 0644);
 MODULE_PARM_DESC(streams, "turn on support for Streams write directives");
@@ -1522,36 +1542,6 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 
-/*
- * Issue ioctl requests on the first available path.  Note that unlike normal
- * block layer requests we will not retry failed request on another controller.
- */
-struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
-		struct nvme_ns_head **head, int *srcu_idx)
-{
-#ifdef CONFIG_NVME_MULTIPATH
-	if (disk->fops == &nvme_ns_head_ops) {
-		struct nvme_ns *ns;
-
-		*head = disk->private_data;
-		*srcu_idx = srcu_read_lock(&(*head)->srcu);
-		ns = nvme_find_path(*head);
-		if (!ns)
-			srcu_read_unlock(&(*head)->srcu, *srcu_idx);
-		return ns;
-	}
-#endif
-	*head = NULL;
-	*srcu_idx = -1;
-	return disk->private_data;
-}
-
-void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
-{
-	if (head)
-		srcu_read_unlock(&head->srcu, idx);
-}
-
 static int nvme_ns_open(struct nvme_ns *ns)
 {
 
@@ -1948,30 +1938,46 @@ static char nvme_pr_type(enum pr_type type)
 	}
 };
 
+static int nvme_send_ns_head_pr_command(struct block_device *bdev,
+		struct nvme_command *c, u8 data[16])
+{
+	struct nvme_ns_head *head = bdev->bd_disk->private_data;
+	int srcu_idx = srcu_read_lock(&head->srcu);
+	struct nvme_ns *ns = nvme_find_path(head);
+	int ret = -EWOULDBLOCK;
+
+	if (ns) {
+		c->common.nsid = cpu_to_le32(ns->head->ns_id);
+		ret = nvme_submit_sync_cmd(ns->queue, c, data, 16);
+	}
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+	
+static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
+		u8 data[16])
+{
+	c->common.nsid = cpu_to_le32(ns->head->ns_id);
+	return nvme_submit_sync_cmd(ns->queue, c, data, 16);
+}
+
 static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
 				u64 key, u64 sa_key, u8 op)
 {
-	struct nvme_ns_head *head = NULL;
-	struct nvme_ns *ns;
 	struct nvme_command c;
-	int srcu_idx, ret;
 	u8 data[16] = { 0, };
 
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		return -EWOULDBLOCK;
-
 	put_unaligned_le64(key, &data[0]);
 	put_unaligned_le64(sa_key, &data[8]);
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = op;
-	c.common.nsid = cpu_to_le32(ns->head->ns_id);
 	c.common.cdw10 = cpu_to_le32(cdw10);
 
-	ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
-	nvme_put_ns_from_disk(head, srcu_idx);
-	return ret;
+	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
+	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+		return nvme_send_ns_head_pr_command(bdev, &c, data);
+	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, &c, data);
 }
 
 static int nvme_pr_register(struct block_device *bdev, u64 old,
@@ -2053,6 +2059,17 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 EXPORT_SYMBOL_GPL(nvme_sec_submit);
 #endif /* CONFIG_BLK_SED_OPAL */
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int nvme_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	return nvme_ns_report_zones(disk->private_data, sector, nr_zones, cb,
+			data);
+}
+#else
+#define nvme_report_zones	NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 static const struct block_device_operations nvme_bdev_ops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
@@ -2217,14 +2234,54 @@ static int nvme_configure_acre(struct nvme_ctrl *ctrl)
 	return ret;
 }
 
+/*
+ * The function checks whether the given total (exlat + enlat) latency of
+ * a power state allows the latter to be used as an APST transition target.
+ * It does so by comparing the latency to the primary and secondary latency
+ * tolerances defined by module params. If there's a match, the corresponding
+ * timeout value is returned and the matching tolerance index (1 or 2) is
+ * reported.
+ */
+static bool nvme_apst_get_transition_time(u64 total_latency,
+		u64 *transition_time, unsigned *last_index)
+{
+	if (total_latency <= apst_primary_latency_tol_us) {
+		if (*last_index == 1)
+			return false;
+		*last_index = 1;
+		*transition_time = apst_primary_timeout_ms;
+		return true;
+	}
+	if (apst_secondary_timeout_ms &&
+		total_latency <= apst_secondary_latency_tol_us) {
+		if (*last_index <= 2)
+			return false;
+		*last_index = 2;
+		*transition_time = apst_secondary_timeout_ms;
+		return true;
+	}
+	return false;
+}
+
 /*
  * APST (Autonomous Power State Transition) lets us program a table of power
  * state transitions that the controller will perform automatically.
- * We configure it with a simple heuristic: we are willing to spend at most 2%
- * of the time transitioning between power states.  Therefore, when running in
- * any given state, we will enter the next lower-power non-operational state
- * after waiting 50 * (enlat + exlat) microseconds, as long as that state's exit
- * latency is under the requested maximum latency.
+ *
+ * Depending on module params, one of the two supported techniques will be used:
+ *
+ * - If the parameters provide explicit timeouts and tolerances, they will be
+ *   used to build a table with up to 2 non-operational states to transition to.
+ *   The default parameter values were selected based on the values used by
+ *   Microsoft's and Intel's NVMe drivers. Yet, since we don't implement dynamic
+ *   regeneration of the APST table in the event of switching between external
+ *   and battery power, the timeouts and tolerances reflect a compromise
+ *   between values used by Microsoft for AC and battery scenarios.
+ * - If not, we'll configure the table with a simple heuristic: we are willing
+ *   to spend at most 2% of the time transitioning between power states.
+ *   Therefore, when running in any given state, we will enter the next
+ *   lower-power non-operational state after waiting 50 * (enlat + exlat)
+ *   microseconds, as long as that state's exit latency is under the requested
+ *   maximum latency.
  *
  * We will not autonomously enter any non-operational state for which the total
  * latency exceeds ps_max_latency_us.
@@ -2240,6 +2297,7 @@ static int nvme_configure_apst(struct nvme_ctrl *ctrl)
 	int max_ps = -1;
 	int state;
 	int ret;
+	unsigned last_lt_index = UINT_MAX;
 
 	/*
 	 * If APST isn't supported or if we haven't been initialized yet,
@@ -2298,13 +2356,19 @@ static int nvme_configure_apst(struct nvme_ctrl *ctrl)
 			le32_to_cpu(ctrl->psd[state].entry_lat);
 
 		/*
-		 * This state is good.  Use it as the APST idle target for
-		 * higher power states.
+		 * This state is good. It can be used as the APST idle target
+		 * for higher power states.
 		 */
-		transition_ms = total_latency_us + 19;
-		do_div(transition_ms, 20);
-		if (transition_ms > (1 << 24) - 1)
-			transition_ms = (1 << 24) - 1;
+		if (apst_primary_timeout_ms && apst_primary_latency_tol_us) {
+			if (!nvme_apst_get_transition_time(total_latency_us,
+					&transition_ms, &last_lt_index))
+				continue;
+		} else {
+			transition_ms = total_latency_us + 19;
+			do_div(transition_ms, 20);
+			if (transition_ms > (1 << 24) - 1)
+				transition_ms = (1 << 24) - 1;
+		}
 
 		target = cpu_to_le64((state << 3) | (transition_ms << 8));
 		if (max_ps == -1)
@@ -4067,6 +4131,11 @@ static int nvme_class_uevent(struct device *dev, struct kobj_uevent_env *env)
 
 		ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s",
 				opts->host_traddr ?: "none");
+		if (ret)
+			return ret;
+
+		ret = add_uevent_var(env, "NVME_HOST_IFACE=%s",
+				opts->host_iface ?: "none");
 	}
 	return ret;
 }

drivers/nvme/host/fabrics.c

@@ -112,6 +112,9 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 	if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)
 		len += scnprintf(buf + len, size - len, "%shost_traddr=%s",
 				(len) ? "," : "", ctrl->opts->host_traddr);
+	if (ctrl->opts->mask & NVMF_OPT_HOST_IFACE)
+		len += scnprintf(buf + len, size - len, "%shost_iface=%s",
+				(len) ? "," : "", ctrl->opts->host_iface);
 	len += scnprintf(buf + len, size - len, "\n");
 
 	return len;
@@ -254,28 +257,23 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 EXPORT_SYMBOL_GPL(nvmf_reg_write32);
 
 /**
- * nvmf_log_connect_error() - Error-parsing-diagnostic print
- * out function for connect() errors.
- *
- * @ctrl: the specific /dev/nvmeX device that had the error.
- *
- * @errval: Error code to be decoded in a more human-friendly
- *	    printout.
- *
- * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM.
- *
- * @cmd: This is the SQE portion of a submission capsule.
- *
- * @data: This is the "Data" portion of a submission capsule.
+ * nvmf_log_connect_error() - Error-parsing-diagnostic print out function for
+ * 				connect() errors.
+ * @ctrl:	The specific /dev/nvmeX device that had the error.
+ * @errval:	Error code to be decoded in a more human-friendly
+ * 		printout.
+ * @offset:	For use with the NVMe error code
+ * 		NVME_SC_CONNECT_INVALID_PARAM.
+ * @cmd:	This is the SQE portion of a submission capsule.
+ * @data:	This is the "Data" portion of a submission capsule.
  */
 static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 		int errval, int offset, struct nvme_command *cmd,
 		struct nvmf_connect_data *data)
 {
-	int err_sctype = errval & (~NVME_SC_DNR);
+	int err_sctype = errval & ~NVME_SC_DNR;
 
 	switch (err_sctype) {
-
 	case (NVME_SC_CONNECT_INVALID_PARAM):
 		if (offset >> 16) {
 			char *inv_data = "Connect Invalid Data Parameter";
@@ -318,30 +316,30 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 			}
 		}
 		break;
-
 	case NVME_SC_CONNECT_INVALID_HOST:
 		dev_err(ctrl->device,
 			"Connect for subsystem %s is not allowed, hostnqn: %s\n",
 			data->subsysnqn, data->hostnqn);
 		break;
-
 	case NVME_SC_CONNECT_CTRL_BUSY:
 		dev_err(ctrl->device,
 			"Connect command failed: controller is busy or not available\n");
 		break;
-
 	case NVME_SC_CONNECT_FORMAT:
 		dev_err(ctrl->device,
 			"Connect incompatible format: %d",
 			cmd->connect.recfmt);
 		break;
-
+	case NVME_SC_HOST_PATH_ERROR:
+		dev_err(ctrl->device,
+			"Connect command failed: host path error\n");
+		break;
 	default:
 		dev_err(ctrl->device,
 			"Connect command failed, error wo/DNR bit: %d\n",
 			err_sctype);
 		break;
-	} /* switch (err_sctype) */
+	}
 }
 
 /**
@@ -545,6 +543,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_KATO,		"keep_alive_tmo=%d"	},
 	{ NVMF_OPT_HOSTNQN,		"hostnqn=%s"		},
 	{ NVMF_OPT_HOST_TRADDR,		"host_traddr=%s"	},
+	{ NVMF_OPT_HOST_IFACE,		"host_iface=%s"		},
 	{ NVMF_OPT_HOST_ID,		"hostid=%s"		},
 	{ NVMF_OPT_DUP_CONNECT,		"duplicate_connect"	},
 	{ NVMF_OPT_DISABLE_SQFLOW,	"disable_sqflow"	},
@@ -754,6 +753,15 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			kfree(opts->host_traddr);
 			opts->host_traddr = p;
 			break;
+		case NVMF_OPT_HOST_IFACE:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			kfree(opts->host_iface);
+			opts->host_iface = p;
+			break;
 		case NVMF_OPT_HOST_ID:
 			p = match_strdup(args);
 			if (!p) {
@@ -938,6 +946,7 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts)
 	kfree(opts->trsvcid);
 	kfree(opts->subsysnqn);
 	kfree(opts->host_traddr);
+	kfree(opts->host_iface);
 	kfree(opts);
 }
 EXPORT_SYMBOL_GPL(nvmf_free_options);

drivers/nvme/host/fabrics.h

@@ -66,6 +66,7 @@ enum {
 	NVMF_OPT_NR_POLL_QUEUES = 1 << 18,
 	NVMF_OPT_TOS		= 1 << 19,
 	NVMF_OPT_FAIL_FAST_TMO	= 1 << 20,
+	NVMF_OPT_HOST_IFACE	= 1 << 21,
 };
 
 /**
@@ -83,7 +84,9 @@ enum {
  * @trsvcid:	The transport-specific TRSVCID field for a port on the
  *              subsystem which is adding a controller.
  * @host_traddr: A transport-specific field identifying the NVME host port
- *              to use for the connection to the controller.
+ *     to use for the connection to the controller.
+ * @host_iface: A transport-specific field identifying the NVME host
+ *     interface to use for the connection to the controller.
  * @queue_size: Number of IO queue elements.
  * @nr_io_queues: Number of controller IO queues that will be established.
  * @reconnect_delay: Time between two consecutive reconnect attempts.
@@ -108,6 +111,7 @@ struct nvmf_ctrl_options {
 	char			*traddr;
 	char			*trsvcid;
 	char			*host_traddr;
+	char			*host_iface;
 	size_t			queue_size;
 	unsigned int		nr_io_queues;
 	unsigned int		reconnect_delay;

drivers/nvme/host/ioctl.c

@@ -372,12 +372,13 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
 		void __user *argp, struct nvme_ns_head *head, int srcu_idx)
+	__releases(&head->srcu)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
 
 	nvme_get_ctrl(ns->ctrl);
-	nvme_put_ns_from_disk(head, srcu_idx);
+	srcu_read_unlock(&head->srcu, srcu_idx);
 	ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp);
 
 	nvme_put_ctrl(ctrl);
@@ -387,14 +388,15 @@ static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
 int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg)
 {
-	struct nvme_ns_head *head = NULL;
+	struct nvme_ns_head *head = bdev->bd_disk->private_data;
 	void __user *argp = (void __user *)arg;
 	struct nvme_ns *ns;
-	int srcu_idx, ret;
+	int srcu_idx, ret = -EWOULDBLOCK;
 
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		return -EWOULDBLOCK;
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns)
+		goto out_unlock;
 
 	/*
 	 * Handle ioctls that apply to the controller instead of the namespace
@@ -402,12 +404,11 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
 	 * deadlock when deleting namespaces using the passthrough interface.
 	 */
 	if (is_ctrl_ioctl(cmd))
-		ret = nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
-	else {
-		ret = nvme_ns_ioctl(ns, cmd, argp);
-		nvme_put_ns_from_disk(head, srcu_idx);
-	}
+		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
+	ret = nvme_ns_ioctl(ns, cmd, argp);
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
 	return ret;
 }
 
@@ -419,21 +420,19 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
 		container_of(cdev, struct nvme_ns_head, cdev);
 	void __user *argp = (void __user *)arg;
 	struct nvme_ns *ns;
-	int srcu_idx, ret;
+	int srcu_idx, ret = -EWOULDBLOCK;
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
-	if (!ns) {
-		srcu_read_unlock(&head->srcu, srcu_idx);
-		return -EWOULDBLOCK;
-	}
+	if (!ns)
+		goto out_unlock;
 
 	if (is_ctrl_ioctl(cmd))
 		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
 	ret = nvme_ns_ioctl(ns, cmd, argp);
-	nvme_put_ns_from_disk(head, srcu_idx);
-
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
 	return ret;
 }
 #endif /* CONFIG_NVME_MULTIPATH */

drivers/nvme/host/multipath.c

@@ -349,6 +349,25 @@ static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
 	nvme_put_ns_head(disk->private_data);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct nvme_ns_head *head = disk->private_data;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (ns)
+		ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data);
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+#else
+#define nvme_ns_head_report_zones	NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 const struct block_device_operations nvme_ns_head_ops = {
 	.owner		= THIS_MODULE,
 	.submit_bio	= nvme_ns_head_submit_bio,
@@ -356,7 +375,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.release	= nvme_ns_head_release,
 	.ioctl		= nvme_ns_head_ioctl,
 	.getgeo		= nvme_getgeo,
-	.report_zones	= nvme_report_zones,
+	.report_zones	= nvme_ns_head_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 

drivers/nvme/host/nvme.h

@@ -674,9 +674,6 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 void nvme_queue_scan(struct nvme_ctrl *ctrl);
 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);
 bool nvme_tryget_ns_head(struct nvme_ns_head *head);
 void nvme_put_ns_head(struct nvme_ns_head *head);
 int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
@@ -697,6 +694,7 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[];
 extern const struct pr_ops nvme_pr_ops;
 extern const struct block_device_operations nvme_ns_head_ops;
 
+struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 #ifdef CONFIG_NVME_MULTIPATH
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
 {
@@ -718,7 +716,6 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
-struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
@@ -810,17 +807,14 @@ static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
+int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data);
 #ifdef CONFIG_BLK_DEV_ZONED
 int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
-int nvme_report_zones(struct gendisk *disk, sector_t sector,
-		      unsigned int nr_zones, report_zones_cb cb, void *data);
-
 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)

drivers/nvme/host/pci.c

@@ -2831,10 +2831,7 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 #ifdef CONFIG_ACPI
 static bool nvme_acpi_storage_d3(struct pci_dev *dev)
 {
-	struct acpi_device *adev;
-	struct pci_dev *root;
-	acpi_handle handle;
-	acpi_status status;
+	struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
 	u8 val;
 
 	/*
@@ -2842,28 +2839,9 @@ static bool nvme_acpi_storage_d3(struct pci_dev *dev)
 	 * must use D3 to support deep platform power savings during
 	 * suspend-to-idle.
 	 */
-	root = pcie_find_root_port(dev);
-	if (!root)
-		return false;
 
-	adev = ACPI_COMPANION(&root->dev);
 	if (!adev)
 		return false;
-
-	/*
-	 * The property is defined in the PXSX device for South complex ports
-	 * and in the PEGP device for North complex ports.
-	 */
-	status = acpi_get_handle(adev->handle, "PXSX", &handle);
-	if (ACPI_FAILURE(status)) {
-		status = acpi_get_handle(adev->handle, "PEGP", &handle);
-		if (ACPI_FAILURE(status))
-			return false;
-	}
-
-	if (acpi_bus_get_device(handle, &adev))
-		return false;
-
 	if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable",
 			&val))
 		return false;

drivers/nvme/host/rdma.c

@@ -1088,7 +1088,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 
 static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
-	int ret = -EINVAL;
+	int ret;
 	bool changed;
 
 	ret = nvme_rdma_configure_admin_queue(ctrl, new);

drivers/nvme/host/tcp.c

@@ -123,6 +123,7 @@ struct nvme_tcp_ctrl {
 	struct blk_mq_tag_set	admin_tag_set;
 	struct sockaddr_storage addr;
 	struct sockaddr_storage src_addr;
+	struct net_device	*ndev;
 	struct nvme_ctrl	ctrl;
 
 	struct work_struct	err_work;
@@ -1455,6 +1456,20 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 		}
 	}
 
+	if (nctrl->opts->mask & NVMF_OPT_HOST_IFACE) {
+		char *iface = nctrl->opts->host_iface;
+		sockptr_t optval = KERNEL_SOCKPTR(iface);
+
+		ret = sock_setsockopt(queue->sock, SOL_SOCKET, SO_BINDTODEVICE,
+				      optval, strlen(iface));
+		if (ret) {
+			dev_err(nctrl->device,
+			  "failed to bind to interface %s queue %d err %d\n",
+			  iface, qid, ret);
+			goto err_sock;
+		}
+	}
+
 	queue->hdr_digest = nctrl->opts->hdr_digest;
 	queue->data_digest = nctrl->opts->data_digest;
 	if (queue->hdr_digest || queue->data_digest) {
@@ -2515,6 +2530,16 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 		}
 	}
 
+	if (opts->mask & NVMF_OPT_HOST_IFACE) {
+		ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface);
+		if (!ctrl->ndev) {
+			pr_err("invalid interface passed: %s\n",
+			       opts->host_iface);
+			ret = -ENODEV;
+			goto out_free_ctrl;
+		}
+	}
+
 	if (!opts->duplicate_connect && nvme_tcp_existing_controller(opts)) {
 		ret = -EALREADY;
 		goto out_free_ctrl;
@@ -2571,7 +2596,7 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
 			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
 			  NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST |
 			  NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
-			  NVMF_OPT_TOS,
+			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE,
 	.create_ctrl	= nvme_tcp_create_ctrl,
 };
 

drivers/nvme/host/zns.c

@@ -171,8 +171,8 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	return cb(&zone, idx, data);
 }
 
-static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data)
+int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nvme_zone_report *report;
 	struct nvme_command c = { };
@@ -180,6 +180,9 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	unsigned int nz, i;
 	size_t buflen;
 
+	if (ns->head->ids.csi != NVME_CSI_ZNS)
+		return -EINVAL;
+
 	report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen);
 	if (!report)
 		return -ENOMEM;
@@ -227,26 +230,6 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	return ret;
 }
 
-int nvme_report_zones(struct gendisk *disk, sector_t sector,
-		      unsigned int nr_zones, report_zones_cb cb, void *data)
-{
-	struct nvme_ns_head *head = NULL;
-	struct nvme_ns *ns;
-	int srcu_idx, ret;
-
-	ns = nvme_get_ns_from_disk(disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		return -EWOULDBLOCK;
-
-	if (ns->head->ids.csi == NVME_CSI_ZNS)
-		ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data);
-	else
-		ret = -EINVAL;
-	nvme_put_ns_from_disk(head, srcu_idx);
-
-	return ret;
-}
-
 blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *c, enum nvme_zone_mgmt_action action)
 {

drivers/nvme/target/core.c

@@ -412,7 +412,6 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
-	INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
@@ -1352,6 +1351,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	INIT_LIST_HEAD(&ctrl->async_events);
 	INIT_RADIX_TREE(&ctrl->p2p_ns_map, GFP_KERNEL);
 	INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
 
 	memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
 	memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);

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

@@ -174,11 +174,10 @@ static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio,
 {
 	struct blk_integrity *bi;
 	struct bio_integrity_payload *bip;
-	struct block_device *bdev = req->ns->bdev;
 	int rc;
 	size_t resid, len;
 
-	bi = bdev_get_integrity(bdev);
+	bi = bdev_get_integrity(req->ns->bdev);
 	if (unlikely(!bi)) {
 		pr_err("Unable to locate bio_integrity\n");
 		return -ENODEV;