1 files changed, 178 insertions, 24 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 032cce3311e7..0ddd6b9af7fc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -45,7 +45,7 @@ module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
 MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
 EXPORT_SYMBOL_GPL(nvme_io_timeout);
 
-unsigned char shutdown_timeout = 5;
+static unsigned char shutdown_timeout = 5;
 module_param(shutdown_timeout, byte, 0644);
 MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
 
@@ -65,11 +65,34 @@ 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");
 
+struct workqueue_struct *nvme_wq;
+EXPORT_SYMBOL_GPL(nvme_wq);
+
 static LIST_HEAD(nvme_ctrl_list);
 static DEFINE_SPINLOCK(dev_list_lock);
 
 static struct class *nvme_class;
 
+int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
+{
+	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
+	if (!queue_work(nvme_wq, &ctrl->reset_work))
+		return -EBUSY;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
+
+static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+{
+	int ret;
+
+	ret = nvme_reset_ctrl(ctrl);
+	if (!ret)
+		flush_work(&ctrl->reset_work);
+	return ret;
+}
+
 static blk_status_t nvme_error_status(struct request *req)
 {
 	switch (nvme_req(req)->status & 0x7ff) {
@@ -157,7 +180,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
-		case NVME_CTRL_RECONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -323,12 +345,22 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	return BLK_STS_OK;
 }
 
-static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
-		struct nvme_command *cmnd)
+static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
+		struct request *req, struct nvme_command *cmnd)
 {
 	u16 control = 0;
 	u32 dsmgmt = 0;
 
+	/*
+	 * If formated with metadata, require the block layer provide a buffer
+	 * unless this namespace is formated such that the metadata can be
+	 * stripped/generated by the controller with PRACT=1.
+	 */
+	if (ns && ns->ms &&
+	    (!ns->pi_type || ns->ms != sizeof(struct t10_pi_tuple)) &&
+	    !blk_integrity_rq(req) && !blk_rq_is_passthrough(req))
+		return BLK_STS_NOTSUPP;
+
 	if (req->cmd_flags & REQ_FUA)
 		control |= NVME_RW_FUA;
 	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
@@ -362,6 +394,7 @@ static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
 
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+	return 0;
 }
 
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
@@ -390,7 +423,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		break;
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
-		nvme_setup_rw(ns, req, cmd);
+		ret = nvme_setup_rw(ns, req, cmd);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -592,7 +625,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	if (nvme_keep_alive(ctrl)) {
 		/* allocation failure, reset the controller */
 		dev_err(ctrl->device, "keep-alive failed\n");
-		ctrl->ops->reset_ctrl(ctrl);
+		nvme_reset_ctrl(ctrl);
 		return;
 	}
 }
@@ -636,6 +669,77 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 	return error;
 }
 
+static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid)
+{
+	struct nvme_command c = { };
+	int status;
+	void *data;
+	int pos;
+	int len;
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.nsid = cpu_to_le32(nsid);
+	c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;
+
+	data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, data,
+				      NVME_IDENTIFY_DATA_SIZE);
+	if (status)
+		goto free_data;
+
+	for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
+		struct nvme_ns_id_desc *cur = data + pos;
+
+		if (cur->nidl == 0)
+			break;
+
+		switch (cur->nidt) {
+		case NVME_NIDT_EUI64:
+			if (cur->nidl != NVME_NIDT_EUI64_LEN) {
+				dev_warn(ns->ctrl->device,
+					 "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
+					 cur->nidl);
+				goto free_data;
+			}
+			len = NVME_NIDT_EUI64_LEN;
+			memcpy(ns->eui, data + pos + sizeof(*cur), len);
+			break;
+		case NVME_NIDT_NGUID:
+			if (cur->nidl != NVME_NIDT_NGUID_LEN) {
+				dev_warn(ns->ctrl->device,
+					 "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
+					 cur->nidl);
+				goto free_data;
+			}
+			len = NVME_NIDT_NGUID_LEN;
+			memcpy(ns->nguid, data + pos + sizeof(*cur), len);
+			break;
+		case NVME_NIDT_UUID:
+			if (cur->nidl != NVME_NIDT_UUID_LEN) {
+				dev_warn(ns->ctrl->device,
+					 "ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
+					 cur->nidl);
+				goto free_data;
+			}
+			len = NVME_NIDT_UUID_LEN;
+			uuid_copy(&ns->uuid, data + pos + sizeof(*cur));
+			break;
+		default:
+			/* Skip unnkown types */
+			len = cur->nidl;
+			break;
+		}
+
+		len += sizeof(*cur);
+	}
+free_data:
+	kfree(data);
+	return status;
+}
+
 static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
 {
 	struct nvme_command c = { };
@@ -745,7 +849,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 	 * access to the admin queue, as that might be only way to fix them up.
 	 */
 	if (status > 0) {
-		dev_err(ctrl->dev, "Could not set queue count (%d)\n", status);
+		dev_err(ctrl->device, "Could not set queue count (%d)\n", status);
 		*count = 0;
 	} else {
 		nr_io_queues = min(result & 0xffff, result >> 16) + 1;
@@ -976,6 +1080,12 @@ static void nvme_init_integrity(struct nvme_ns *ns)
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+static void nvme_set_chunk_size(struct nvme_ns *ns)
+{
+	u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9));
+	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
+}
+
 static void nvme_config_discard(struct nvme_ns *ns)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
@@ -1009,7 +1119,15 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
 	if (ns->ctrl->vs >= NVME_VS(1, 1, 0))
 		memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui));
 	if (ns->ctrl->vs >= NVME_VS(1, 2, 0))
-		memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid));
+		memcpy(ns->nguid, (*id)->nguid, sizeof(ns->nguid));
+	if (ns->ctrl->vs >= NVME_VS(1, 3, 0)) {
+		 /* Don't treat error as fatal we potentially
+		  * already have a NGUID or EUI-64
+		  */
+		if (nvme_identify_ns_descs(ns, ns->ns_id))
+			dev_warn(ns->ctrl->device,
+				 "%s: Identify Descriptors failed\n", __func__);
+	}
 
 	return 0;
 }
@@ -1027,12 +1145,15 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 	bs = 1 << ns->lba_shift;
+	ns->noiob = le16_to_cpu(id->noiob);
 
 	blk_mq_freeze_queue(disk->queue);
 
 	if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
 		nvme_prep_integrity(disk, id, bs);
 	blk_queue_logical_block_size(ns->queue, bs);
+	if (ns->noiob)
+		nvme_set_chunk_size(ns);
 	if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
 		nvme_init_integrity(ns);
 	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
@@ -1276,7 +1397,7 @@ EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
 int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
 {
-	unsigned long timeout = SHUTDOWN_TIMEOUT + jiffies;
+	unsigned long timeout = jiffies + (shutdown_timeout * HZ);
 	u32 csts;
 	int ret;
 
@@ -1575,7 +1696,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
-		dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
+		dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
 		ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
 	}
 
@@ -1603,7 +1724,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	prev_apsta = ctrl->apsta;
 	if (ctrl->quirks & NVME_QUIRK_NO_APST) {
 		if (force_apst && id->apsta) {
-			dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
+			dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
 			ctrl->apsta = 1;
 		} else {
 			ctrl->apsta = 0;
@@ -1627,12 +1748,14 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 			ret = -EINVAL;
 
 		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
-			dev_err(ctrl->dev,
+			dev_err(ctrl->device,
 				"keep-alive support is mandatory for fabrics\n");
 			ret = -EINVAL;
 		}
 	} else {
 		ctrl->cntlid = le16_to_cpu(id->cntlid);
+		ctrl->hmpre = le32_to_cpu(id->hmpre);
+		ctrl->hmmin = le32_to_cpu(id->hmmin);
 	}
 
 	kfree(id);
@@ -1728,7 +1851,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 		return nvme_dev_user_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:
 		dev_warn(ctrl->device, "resetting controller\n");
-		return ctrl->ops->reset_ctrl(ctrl);
+		return nvme_reset_ctrl_sync(ctrl);
 	case NVME_IOCTL_SUBSYS_RESET:
 		return nvme_reset_subsystem(ctrl);
 	case NVME_IOCTL_RESCAN:
@@ -1754,7 +1877,7 @@ static ssize_t nvme_sysfs_reset(struct device *dev,
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 	int ret;
 
-	ret = ctrl->ops->reset_ctrl(ctrl);
+	ret = nvme_reset_ctrl_sync(ctrl);
 	if (ret < 0)
 		return ret;
 	return count;
@@ -1780,8 +1903,8 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 	int serial_len = sizeof(ctrl->serial);
 	int model_len = sizeof(ctrl->model);
 
-	if (memchr_inv(ns->uuid, 0, sizeof(ns->uuid)))
-		return sprintf(buf, "eui.%16phN\n", ns->uuid);
+	if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
+		return sprintf(buf, "eui.%16phN\n", ns->nguid);
 
 	if (memchr_inv(ns->eui, 0, sizeof(ns->eui)))
 		return sprintf(buf, "eui.%8phN\n", ns->eui);
@@ -1796,11 +1919,28 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);
 
+static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+	return sprintf(buf, "%pU\n", ns->nguid);
+}
+static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL);
+
 static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 								char *buf)
 {
 	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
-	return sprintf(buf, "%pU\n", ns->uuid);
+
+	/* For backward compatibility expose the NGUID to userspace if
+	 * we have no UUID set
+	 */
+	if (uuid_is_null(&ns->uuid)) {
+		printk_ratelimited(KERN_WARNING
+				   "No UUID available providing old NGUID\n");
+		return sprintf(buf, "%pU\n", ns->nguid);
+	}
+	return sprintf(buf, "%pU\n", &ns->uuid);
 }
 static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL);
 
@@ -1823,6 +1963,7 @@ static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL);
 static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_wwid.attr,
 	&dev_attr_uuid.attr,
+	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
 	&dev_attr_nsid.attr,
 	NULL,
@@ -1835,7 +1976,12 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
 
 	if (a == &dev_attr_uuid.attr) {
-		if (!memchr_inv(ns->uuid, 0, sizeof(ns->uuid)))
+		if (uuid_is_null(&ns->uuid) ||
+		    !memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
+			return 0;
+	}
+	if (a == &dev_attr_nguid.attr) {
+		if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
 			return 0;
 	}
 	if (a == &dev_attr_eui.attr) {
@@ -2049,7 +2195,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	if (nvme_nvm_ns_supported(ns, id) &&
 				nvme_nvm_register(ns, disk_name, node)) {
-		dev_warn(ctrl->dev, "%s: LightNVM init failure\n", __func__);
+		dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__);
 		goto out_free_id;
 	}
 
@@ -2224,7 +2370,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl)
 	 * removal.
 	 */
 	if (ctrl->state == NVME_CTRL_LIVE)
-		schedule_work(&ctrl->scan_work);
+		queue_work(nvme_wq, &ctrl->scan_work);
 }
 EXPORT_SYMBOL_GPL(nvme_queue_scan);
 
@@ -2279,7 +2425,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		/*FALLTHRU*/
 	case NVME_SC_ABORT_REQ:
 		++ctrl->event_limit;
-		schedule_work(&ctrl->async_event_work);
+		queue_work(nvme_wq, &ctrl->async_event_work);
 		break;
 	default:
 		break;
@@ -2302,7 +2448,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 void nvme_queue_async_events(struct nvme_ctrl *ctrl)
 {
 	ctrl->event_limit = NVME_NR_AERS;
-	schedule_work(&ctrl->async_event_work);
+	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 EXPORT_SYMBOL_GPL(nvme_queue_async_events);
 
@@ -2537,10 +2683,15 @@ int __init nvme_core_init(void)
 {
 	int result;
 
+	nvme_wq = alloc_workqueue("nvme-wq",
+			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+	if (!nvme_wq)
+		return -ENOMEM;
+
 	result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
 							&nvme_dev_fops);
 	if (result < 0)
-		return result;
+		goto destroy_wq;
 	else if (result > 0)
 		nvme_char_major = result;
 
@@ -2552,8 +2703,10 @@ int __init nvme_core_init(void)
 
 	return 0;
 
- unregister_chrdev:
+unregister_chrdev:
 	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
+destroy_wq:
+	destroy_workqueue(nvme_wq);
 	return result;
 }
 
@@ -2561,6 +2714,7 @@ void nvme_core_exit(void)
 {
 	class_destroy(nvme_class);
 	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
+	destroy_workqueue(nvme_wq);
 }
 
 MODULE_LICENSE("GPL");