1 files changed, 114 insertions, 54 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9a270e49df17..ce1b61519441 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -85,7 +85,7 @@ static LIST_HEAD(nvme_subsystems);
 static DEFINE_MUTEX(nvme_subsystems_lock);
 
 static DEFINE_IDA(nvme_instance_ida);
-static dev_t nvme_chr_devt;
+static dev_t nvme_ctrl_base_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
@@ -93,16 +93,6 @@ static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
 
-static void nvme_update_bdev_size(struct gendisk *disk)
-{
-	struct block_device *bdev = bdget_disk(disk, 0);
-
-	if (bdev) {
-		bd_set_nr_sectors(bdev, get_capacity(disk));
-		bdput(bdev);
-	}
-}
-
 /*
  * Prepare a queue for teardown.
  *
@@ -119,8 +109,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	blk_set_queue_dying(ns->queue);
 	blk_mq_unquiesce_queue(ns->queue);
 
-	set_capacity(ns->disk, 0);
-	nvme_update_bdev_size(ns->disk);
+	set_capacity_and_notify(ns->disk, 0);
 }
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -148,6 +137,38 @@ int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
 
+static void nvme_failfast_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_ctrl, failfast_work);
+
+	if (ctrl->state != NVME_CTRL_CONNECTING)
+		return;
+
+	set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
+	dev_info(ctrl->device, "failfast expired\n");
+	nvme_kick_requeue_lists(ctrl);
+}
+
+static inline void nvme_start_failfast_work(struct nvme_ctrl *ctrl)
+{
+	if (!ctrl->opts || ctrl->opts->fast_io_fail_tmo == -1)
+		return;
+
+	schedule_delayed_work(&ctrl->failfast_work,
+			      ctrl->opts->fast_io_fail_tmo * HZ);
+}
+
+static inline void nvme_stop_failfast_work(struct nvme_ctrl *ctrl)
+{
+	if (!ctrl->opts)
+		return;
+
+	cancel_delayed_work_sync(&ctrl->failfast_work);
+	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
+}
+
+
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
@@ -433,8 +454,17 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	}
 
 	spin_unlock_irqrestore(&ctrl->lock, flags);
-	if (changed && ctrl->state == NVME_CTRL_LIVE)
+	if (!changed)
+		return false;
+
+	if (ctrl->state == NVME_CTRL_LIVE) {
+		if (old_state == NVME_CTRL_CONNECTING)
+			nvme_stop_failfast_work(ctrl);
 		nvme_kick_requeue_lists(ctrl);
+	} else if (ctrl->state == NVME_CTRL_CONNECTING &&
+		old_state == NVME_CTRL_RESETTING) {
+		nvme_start_failfast_work(ctrl);
+	}
 	return changed;
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@@ -518,29 +548,49 @@ static inline void nvme_clear_nvme_request(struct request *req)
 	}
 }
 
-struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
+static inline unsigned int nvme_req_op(struct nvme_command *cmd)
 {
-	unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
-	struct request *req;
+	return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
+}
 
-	if (qid == NVME_QID_ANY) {
-		req = blk_mq_alloc_request(q, op, flags);
-	} else {
-		req = blk_mq_alloc_request_hctx(q, op, flags,
-				qid ? qid - 1 : 0);
-	}
-	if (IS_ERR(req))
-		return req;
+static inline void nvme_init_request(struct request *req,
+		struct nvme_command *cmd)
+{
+	if (req->q->queuedata)
+		req->timeout = NVME_IO_TIMEOUT;
+	else /* no queuedata implies admin queue */
+		req->timeout = NVME_ADMIN_TIMEOUT;
 
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
 	nvme_clear_nvme_request(req);
 	nvme_req(req)->cmd = cmd;
+}
 
+struct request *nvme_alloc_request(struct request_queue *q,
+		struct nvme_command *cmd, blk_mq_req_flags_t flags)
+{
+	struct request *req;
+
+	req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+	if (!IS_ERR(req))
+		nvme_init_request(req, cmd);
 	return req;
 }
 EXPORT_SYMBOL_GPL(nvme_alloc_request);
 
+struct request *nvme_alloc_request_qid(struct request_queue *q,
+		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
+{
+	struct request *req;
+
+	req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+			qid ? qid - 1 : 0);
+	if (!IS_ERR(req))
+		nvme_init_request(req, cmd);
+	return req;
+}
+EXPORT_SYMBOL_GPL(nvme_alloc_request_qid);
+
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
 	struct nvme_command c;
@@ -897,11 +947,15 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	struct request *req;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, flags, qid);
+	if (qid == NVME_QID_ANY)
+		req = nvme_alloc_request(q, cmd, flags);
+	else
+		req = nvme_alloc_request_qid(q, cmd, flags, qid);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+	if (timeout)
+		req->timeout = timeout;
 
 	if (buffer && bufflen) {
 		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
@@ -1067,11 +1121,12 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	void *meta = NULL;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY);
+	req = nvme_alloc_request(q, cmd, 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+	if (timeout)
+		req->timeout = timeout;
 	nvme_req(req)->flags |= NVME_REQ_USERCMD;
 
 	if (ubuffer && bufflen) {
@@ -1141,8 +1196,8 @@ static int nvme_keep_alive(struct nvme_ctrl *ctrl)
 {
 	struct request *rq;
 
-	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED,
-			NVME_QID_ANY);
+	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
+			BLK_MQ_REQ_RESERVED);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -1302,7 +1357,8 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 				      NVME_IDENTIFY_DATA_SIZE);
 	if (status) {
 		dev_warn(ctrl->device,
-			"Identify Descriptors failed (%d)\n", status);
+			"Identify Descriptors failed (nsid=%u, status=0x%x)\n",
+			nsid, status);
 		goto free_data;
 	}
 
@@ -2053,12 +2109,13 @@ static void nvme_update_disk_info(struct gendisk *disk,
 			capacity = 0;
 	}
 
-	set_capacity_revalidate_and_notify(disk, capacity, false);
+	set_capacity_and_notify(disk, capacity);
 
 	nvme_config_discard(disk, ns);
 	nvme_config_write_zeroes(disk, ns);
 
-	if (id->nsattr & NVME_NS_ATTR_RO)
+	if ((id->nsattr & NVME_NS_ATTR_RO) ||
+	    test_bit(NVME_NS_FORCE_RO, &ns->flags))
 		set_disk_ro(disk, true);
 }
 
@@ -2134,7 +2191,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
 		blk_queue_update_readahead(ns->head->disk->queue);
-		nvme_update_bdev_size(ns->head->disk);
 		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
 #endif
@@ -2261,13 +2317,13 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 	cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
 	cmd.common.cdw11 = cpu_to_le32(len);
 
-	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
-				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0, false);
+	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, 0,
+			NVME_QID_ANY, 1, 0, false);
 }
 EXPORT_SYMBOL_GPL(nvme_sec_submit);
 #endif /* CONFIG_BLK_SED_OPAL */
 
-static const struct block_device_operations nvme_fops = {
+static const struct block_device_operations nvme_bdev_ops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
 	.compat_ioctl	= nvme_compat_ioctl,
@@ -3274,7 +3330,7 @@ static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->fops == &nvme_fops)
+	if (disk->fops == &nvme_bdev_ops)
 		return nvme_get_ns_from_dev(dev)->head;
 	else
 		return disk->private_data;
@@ -3383,7 +3439,7 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 	}
 #ifdef CONFIG_NVME_MULTIPATH
 	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
-		if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
+		if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
 			return 0;
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;
@@ -3804,7 +3860,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	struct gendisk *disk;
 	struct nvme_id_ns *id;
 	char disk_name[DISK_NAME_LEN];
-	int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT, ret;
+	int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT;
 
 	if (nvme_identify_ns(ctrl, nsid, ids, &id))
 		return;
@@ -3828,8 +3884,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	ns->ctrl = ctrl;
 	kref_init(&ns->kref);
 
-	ret = nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED);
-	if (ret)
+	if (nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED))
 		goto out_free_queue;
 	nvme_set_disk_name(disk_name, ns, ctrl, &flags);
 
@@ -3837,7 +3892,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	if (!disk)
 		goto out_unlink_ns;
 
-	disk->fops = &nvme_fops;
+	disk->fops = &nvme_bdev_ops;
 	disk->private_data = ns;
 	disk->queue = ns->queue;
 	disk->flags = flags;
@@ -3848,8 +3903,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 		goto out_put_disk;
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
-		ret = nvme_nvm_register(ns, disk_name, node);
-		if (ret) {
+		if (nvme_nvm_register(ns, disk_name, node)) {
 			dev_warn(ctrl->device, "LightNVM init failure\n");
 			goto out_put_disk;
 		}
@@ -3962,8 +4016,6 @@ out:
 	 */
 	if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR)))
 		nvme_ns_remove(ns);
-	else
-		revalidate_disk_size(ns->disk, true);
 }
 
 static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
@@ -4042,8 +4094,11 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 
 		ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd, ns_list,
 					    NVME_IDENTIFY_DATA_SIZE);
-		if (ret)
+		if (ret) {
+			dev_warn(ctrl->device,
+				"Identify NS List failed (status=0x%x)\n", ret);
 			goto free;
+		}
 
 		for (i = 0; i < nr_entries; i++) {
 			u32 nsid = le32_to_cpu(ns_list[i]);
@@ -4346,6 +4401,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
 	nvme_mpath_stop(ctrl);
 	nvme_stop_keep_alive(ctrl);
+	nvme_stop_failfast_work(ctrl);
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fw_act_work);
 }
@@ -4423,6 +4479,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	int ret;
 
 	ctrl->state = NVME_CTRL_NEW;
+	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
@@ -4439,6 +4496,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	init_waitqueue_head(&ctrl->state_wq);
 
 	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 
@@ -4457,7 +4515,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 
 	device_initialize(&ctrl->ctrl_device);
 	ctrl->device = &ctrl->ctrl_device;
-	ctrl->device->devt = MKDEV(MAJOR(nvme_chr_devt), ctrl->instance);
+	ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
+			ctrl->instance);
 	ctrl->device->class = nvme_class;
 	ctrl->device->parent = ctrl->dev;
 	ctrl->device->groups = nvme_dev_attr_groups;
@@ -4666,7 +4725,8 @@ static int __init nvme_core_init(void)
 	if (!nvme_delete_wq)
 		goto destroy_reset_wq;
 
-	result = alloc_chrdev_region(&nvme_chr_devt, 0, NVME_MINORS, "nvme");
+	result = alloc_chrdev_region(&nvme_ctrl_base_chr_devt, 0,
+			NVME_MINORS, "nvme");
 	if (result < 0)
 		goto destroy_delete_wq;
 
@@ -4687,7 +4747,7 @@ static int __init nvme_core_init(void)
 destroy_class:
 	class_destroy(nvme_class);
 unregister_chrdev:
-	unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
+	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 destroy_delete_wq:
 	destroy_workqueue(nvme_delete_wq);
 destroy_reset_wq:
@@ -4702,7 +4762,7 @@ static void __exit nvme_core_exit(void)
 {
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
-	unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
+	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 	destroy_workqueue(nvme_delete_wq);
 	destroy_workqueue(nvme_reset_wq);
 	destroy_workqueue(nvme_wq);