NVMe: Move error handling to failed reset handler

This moves failed queue handling out of the namespace removal path and
into the reset failure path, fixing a hanging condition if the controller
fails or link down during del_gendisk. Previously the driver had to see
the controller as degraded prior to calling del_gendisk to setup the
queues to fail. But, if the controller happened to fail after this,
there was no task to end outstanding requests.

On failure, all namespace states are set to dead. This has capacity
revalidate to 0, and ends all new requests with error status.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

drivers/nvme/host/core.c

@@ -557,6 +557,10 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	u16 old_ms;
 	unsigned short bs;
 
+	if (test_bit(NVME_NS_DEAD, &ns->flags)) {
+		set_capacity(disk, 0);
+		return -ENODEV;
+	}
 	if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
 		dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n",
 				__func__, ns->ctrl->instance, ns->ns_id);
@@ -1186,32 +1190,15 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
-	bool kill;
-
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
-	kill = nvme_io_incapable(ns->ctrl) &&
-			!blk_queue_dying(ns->queue);
-	if (kill) {
-		blk_set_queue_dying(ns->queue);
-
-		/*
-		 * The controller was shutdown first if we got here through
-		 * device removal. The shutdown may requeue outstanding
-		 * requests. These need to be aborted immediately so
-		 * del_gendisk doesn't block indefinitely for their completion.
-		 */
-		blk_mq_abort_requeue_list(ns->queue);
-	}
 	if (ns->disk->flags & GENHD_FL_UP) {
 		if (blk_get_integrity(ns->disk))
 			blk_integrity_unregister(ns->disk);
 		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_attr_group);
 		del_gendisk(ns->disk);
-	}
-	if (kill || !blk_queue_dying(ns->queue)) {
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
@@ -1413,6 +1400,38 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	return ret;
 }
 
+/**
+ * nvme_kill_queues(): Ends all namespace queues
+ * @ctrl: the dead controller that needs to end
+ *
+ * Call this function when the driver determines it is unable to get the
+ * controller in a state capable of servicing IO.
+ */
+void nvme_kill_queues(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (!kref_get_unless_zero(&ns->kref))
+			continue;
+
+		/*
+		 * Revalidating a dead namespace sets capacity to 0. This will
+		 * end buffered writers dirtying pages that can't be synced.
+		 */
+		if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+			revalidate_disk(ns->disk);
+
+		blk_set_queue_dying(ns->queue);
+		blk_mq_abort_requeue_list(ns->queue);
+		blk_mq_start_stopped_hw_queues(ns->queue, true);
+
+		nvme_put_ns(ns);
+	}
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+
 void nvme_stop_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;

drivers/nvme/host/nvme.h

@@ -117,6 +117,7 @@ struct nvme_ns {
 	unsigned long flags;
 
 #define NVME_NS_REMOVING 0
+#define NVME_NS_DEAD     1
 
 	u64 mode_select_num_blocks;
 	u32 mode_select_block_len;
@@ -246,6 +247,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
+void nvme_kill_queues(struct nvme_ctrl *ctrl);
 
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags);

drivers/nvme/host/pci.c

@@ -690,7 +690,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	spin_lock_irq(&nvmeq->q_lock);
 	if (unlikely(nvmeq->cq_vector < 0)) {
-		ret = BLK_MQ_RQ_QUEUE_BUSY;
+		if (ns && !test_bit(NVME_NS_DEAD, &ns->flags))
+			ret = BLK_MQ_RQ_QUEUE_BUSY;
+		else
+			ret = BLK_MQ_RQ_QUEUE_ERROR;
 		spin_unlock_irq(&nvmeq->q_lock);
 		goto out;
 	}
@@ -1261,6 +1264,12 @@ static struct blk_mq_ops nvme_mq_ops = {
 static void nvme_dev_remove_admin(struct nvme_dev *dev)
 {
 	if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) {
+		/*
+		 * If the controller was reset during removal, it's possible
+		 * user requests may be waiting on a stopped queue. Start the
+		 * queue to flush these to completion.
+		 */
+		blk_mq_start_stopped_hw_queues(dev->ctrl.admin_q, true);
 		blk_cleanup_queue(dev->ctrl.admin_q);
 		blk_mq_free_tag_set(&dev->admin_tagset);
 	}
@@ -1901,6 +1910,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
 	dev_warn(dev->dev, "Removing after probe failure status: %d\n", status);
 
 	kref_get(&dev->ctrl.kref);
+	nvme_dev_disable(dev, false);
 	if (!schedule_work(&dev->remove_work))
 		nvme_put_ctrl(&dev->ctrl);
 }
@@ -1973,6 +1983,7 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work)
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
+	nvme_kill_queues(&dev->ctrl);
 	if (pci_get_drvdata(pdev))
 		pci_stop_and_remove_bus_device_locked(pdev);
 	nvme_put_ctrl(&dev->ctrl);