Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block layer fixes from Jens Axboe:
 "The major part is an update to the NVMe driver, fixing various issues
  around surprise removal and hung controllers.  Most of that is from
  Keith, and parts are simple blk-mq fixes or exports/additions of minor
  functions to aid this effort, and parts are changes directly to the
  NVMe driver.

  Apart from the above, this contains:

   - Small blk-mq change from me, killing an unused member of the
     hardware queue structure.

   - Small fix from Ming Lei, fixing up a few drivers that didn't
     properly check for ERR_PTR() returns from blk_mq_init_queue()"

* 'for-linus' of git://git.kernel.dk/linux-block:
  NVMe: Fix locking on abort handling
  NVMe: Start and stop h/w queues on reset
  NVMe: Command abort handling fixes
  NVMe: Admin queue removal handling
  NVMe: Reference count admin queue usage
  NVMe: Start all requests
  blk-mq: End unstarted requests on a dying queue
  blk-mq: Allow requests to never expire
  blk-mq: Add helper to abort requeued requests
  blk-mq: Let drivers cancel requeue_work
  blk-mq: Export if requests were started
  blk-mq: Wake tasks entering queue on dying
  blk-mq: get rid of ->cmd_size in the hardware queue
  block: fix checking return value of blk_mq_init_queue
  block: wake up waiters when a queue is marked dying
  NVMe: Fix double free irq
  blk-mq: Export freeze/unfreeze functions
  blk-mq: Exit queue on alloc failure

block/blk-core.c

@@ -473,6 +473,25 @@ void blk_queue_bypass_end(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
 
+void blk_set_queue_dying(struct request_queue *q)
+{
+	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+
+	if (q->mq_ops)
+		blk_mq_wake_waiters(q);
+	else {
+		struct request_list *rl;
+
+		blk_queue_for_each_rl(rl, q) {
+			if (rl->rq_pool) {
+				wake_up(&rl->wait[BLK_RW_SYNC]);
+				wake_up(&rl->wait[BLK_RW_ASYNC]);
+			}
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(blk_set_queue_dying);
+
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -486,7 +505,7 @@ void blk_cleanup_queue(struct request_queue *q)
 
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
 	mutex_lock(&q->sysfs_lock);
-	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+	blk_set_queue_dying(q);
 	spin_lock_irq(lock);
 
 	/*

block/blk-mq-tag.c

@@ -68,9 +68,9 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 }
 
 /*
- * Wakeup all potentially sleeping on normal (non-reserved) tags
+ * Wakeup all potentially sleeping on tags
  */
-static void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags)
+void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 {
 	struct blk_mq_bitmap_tags *bt;
 	int i, wake_index;
@@ -85,6 +85,12 @@ static void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags)
 
 		wake_index = bt_index_inc(wake_index);
 	}
+
+	if (include_reserve) {
+		bt = &tags->breserved_tags;
+		if (waitqueue_active(&bt->bs[0].wait))
+			wake_up(&bt->bs[0].wait);
+	}
 }
 
 /*
@@ -100,7 +106,7 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 
 	atomic_dec(&tags->active_queues);
 
-	blk_mq_tag_wakeup_all(tags);
+	blk_mq_tag_wakeup_all(tags, false);
 }
 
 /*
@@ -584,7 +590,7 @@ int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int tdepth)
 	 * static and should never need resizing.
 	 */
 	bt_update_count(&tags->bitmap_tags, tdepth);
-	blk_mq_tag_wakeup_all(tags);
+	blk_mq_tag_wakeup_all(tags, false);
 	return 0;
 }
 

block/blk-mq-tag.h

@@ -54,6 +54,7 @@ extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
 extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
+extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 
 enum {
 	BLK_MQ_TAG_CACHE_MIN	= 1,

block/blk-mq.c

@@ -107,7 +107,7 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref)
 	wake_up_all(&q->mq_freeze_wq);
 }
 
-static void blk_mq_freeze_queue_start(struct request_queue *q)
+void blk_mq_freeze_queue_start(struct request_queue *q)
 {
 	bool freeze;
 
@@ -120,6 +120,7 @@ static void blk_mq_freeze_queue_start(struct request_queue *q)
 		blk_mq_run_queues(q, false);
 	}
 }
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
 
 static void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
@@ -136,7 +137,7 @@ void blk_mq_freeze_queue(struct request_queue *q)
 	blk_mq_freeze_queue_wait(q);
 }
 
-static void blk_mq_unfreeze_queue(struct request_queue *q)
+void blk_mq_unfreeze_queue(struct request_queue *q)
 {
 	bool wake;
 
@@ -149,6 +150,24 @@ static void blk_mq_unfreeze_queue(struct request_queue *q)
 		wake_up_all(&q->mq_freeze_wq);
 	}
 }
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+
+void blk_mq_wake_waiters(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		if (blk_mq_hw_queue_mapped(hctx))
+			blk_mq_tag_wakeup_all(hctx->tags, true);
+
+	/*
+	 * If we are called because the queue has now been marked as
+	 * dying, we need to ensure that processes currently waiting on
+	 * the queue are notified as well.
+	 */
+	wake_up_all(&q->mq_freeze_wq);
+}
 
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 {
@@ -258,8 +277,10 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 		ctx = alloc_data.ctx;
 	}
 	blk_mq_put_ctx(ctx);
-	if (!rq)
+	if (!rq) {
+		blk_mq_queue_exit(q);
 		return ERR_PTR(-EWOULDBLOCK);
+	}
 	return rq;
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
@@ -383,6 +404,12 @@ void blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
+int blk_mq_request_started(struct request *rq)
+{
+	return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+}
+EXPORT_SYMBOL_GPL(blk_mq_request_started);
+
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -500,12 +527,38 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
 }
 EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 
+void blk_mq_cancel_requeue_work(struct request_queue *q)
+{
+	cancel_work_sync(&q->requeue_work);
+}
+EXPORT_SYMBOL_GPL(blk_mq_cancel_requeue_work);
+
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
 	kblockd_schedule_work(&q->requeue_work);
 }
 EXPORT_SYMBOL(blk_mq_kick_requeue_list);
 
+void blk_mq_abort_requeue_list(struct request_queue *q)
+{
+	unsigned long flags;
+	LIST_HEAD(rq_list);
+
+	spin_lock_irqsave(&q->requeue_lock, flags);
+	list_splice_init(&q->requeue_list, &rq_list);
+	spin_unlock_irqrestore(&q->requeue_lock, flags);
+
+	while (!list_empty(&rq_list)) {
+		struct request *rq;
+
+		rq = list_first_entry(&rq_list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		rq->errors = -EIO;
+		blk_mq_end_request(rq, rq->errors);
+	}
+}
+EXPORT_SYMBOL(blk_mq_abort_requeue_list);
+
 static inline bool is_flush_request(struct request *rq,
 		struct blk_flush_queue *fq, unsigned int tag)
 {
@@ -566,13 +619,24 @@ void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		break;
 	}
 }
-		
+
 static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, void *priv, bool reserved)
 {
 	struct blk_mq_timeout_data *data = priv;
 
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
+		/*
+		 * If a request wasn't started before the queue was
+		 * marked dying, kill it here or it'll go unnoticed.
+		 */
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_complete_request(rq);
+		}
+		return;
+	}
+	if (rq->cmd_flags & REQ_NO_TIMEOUT)
 		return;
 
 	if (time_after_eq(jiffies, rq->deadline)) {
@@ -1601,7 +1665,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	hctx->queue = q;
 	hctx->queue_num = hctx_idx;
 	hctx->flags = set->flags;
-	hctx->cmd_size = set->cmd_size;
 
 	blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
 					blk_mq_hctx_notify, hctx);

block/blk-mq.h

@@ -32,6 +32,7 @@ void blk_mq_free_queue(struct request_queue *q);
 void blk_mq_clone_flush_request(struct request *flush_rq,
 		struct request *orig_rq);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
+void blk_mq_wake_waiters(struct request_queue *q);
 
 /*
  * CPU hotplug helpers

block/blk-timeout.c

@@ -190,6 +190,9 @@ void blk_add_timer(struct request *req)
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
+	if (req->cmd_flags & REQ_NO_TIMEOUT)
+		return;
+
 	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
 	if (!q->mq_ops && !q->rq_timed_out_fn)
 		return;

drivers/block/null_blk.c

@@ -530,7 +530,7 @@ static int null_add_dev(void)
 			goto out_cleanup_queues;
 
 		nullb->q = blk_mq_init_queue(&nullb->tag_set);
-		if (!nullb->q) {
+		if (IS_ERR(nullb->q)) {
 			rv = -ENOMEM;
 			goto out_cleanup_tags;
 		}

drivers/block/nvme-core.c

@@ -215,6 +215,7 @@ static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
 	cmd->fn = handler;
 	cmd->ctx = ctx;
 	cmd->aborted = 0;
+	blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
 }
 
 /* Special values must be less than 0x1000 */
@@ -431,8 +432,13 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	if (unlikely(status)) {
 		if (!(status & NVME_SC_DNR || blk_noretry_request(req))
 		    && (jiffies - req->start_time) < req->timeout) {
+			unsigned long flags;
+
 			blk_mq_requeue_request(req);
-			blk_mq_kick_requeue_list(req->q);
+			spin_lock_irqsave(req->q->queue_lock, flags);
+			if (!blk_queue_stopped(req->q))
+				blk_mq_kick_requeue_list(req->q);
+			spin_unlock_irqrestore(req->q->queue_lock, flags);
 			return;
 		}
 		req->errors = nvme_error_status(status);
@@ -664,8 +670,6 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 		}
 	}
 
-	blk_mq_start_request(req);
-
 	nvme_set_info(cmd, iod, req_completion);
 	spin_lock_irq(&nvmeq->q_lock);
 	if (req->cmd_flags & REQ_DISCARD)
@@ -835,6 +839,7 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	req->cmd_flags |= REQ_NO_TIMEOUT;
 	cmd_info = blk_mq_rq_to_pdu(req);
 	nvme_set_info(cmd_info, req, async_req_completion);
 
@@ -1016,14 +1021,19 @@ static void nvme_abort_req(struct request *req)
 	struct nvme_command cmd;
 
 	if (!nvmeq->qid || cmd_rq->aborted) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&dev_list_lock, flags);
 		if (work_busy(&dev->reset_work))
-			return;
+			goto out;
 		list_del_init(&dev->node);
 		dev_warn(&dev->pci_dev->dev,
 			"I/O %d QID %d timeout, reset controller\n",
 							req->tag, nvmeq->qid);
 		dev->reset_workfn = nvme_reset_failed_dev;
 		queue_work(nvme_workq, &dev->reset_work);
+ out:
+		spin_unlock_irqrestore(&dev_list_lock, flags);
 		return;
 	}
 
@@ -1064,15 +1074,22 @@ static void nvme_cancel_queue_ios(struct blk_mq_hw_ctx *hctx,
 	void *ctx;
 	nvme_completion_fn fn;
 	struct nvme_cmd_info *cmd;
-	static struct nvme_completion cqe = {
-		.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
-	};
+	struct nvme_completion cqe;
+
+	if (!blk_mq_request_started(req))
+		return;
 
 	cmd = blk_mq_rq_to_pdu(req);
 
 	if (cmd->ctx == CMD_CTX_CANCELLED)
 		return;
 
+	if (blk_queue_dying(req->q))
+		cqe.status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
+	else
+		cqe.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
+
+
 	dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
 						req->tag, nvmeq->qid);
 	ctx = cancel_cmd_info(cmd, &fn);
@@ -1084,17 +1101,29 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = cmd->nvmeq;
 
-	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
-							nvmeq->qid);
-	if (nvmeq->dev->initialized)
-		nvme_abort_req(req);
-
 	/*
 	 * The aborted req will be completed on receiving the abort req.
 	 * We enable the timer again. If hit twice, it'll cause a device reset,
 	 * as the device then is in a faulty state.
 	 */
-	return BLK_EH_RESET_TIMER;
+	int ret = BLK_EH_RESET_TIMER;
+
+	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
+							nvmeq->qid);
+
+	spin_lock_irq(&nvmeq->q_lock);
+	if (!nvmeq->dev->initialized) {
+		/*
+		 * Force cancelled command frees the request, which requires we
+		 * return BLK_EH_NOT_HANDLED.
+		 */
+		nvme_cancel_queue_ios(nvmeq->hctx, req, nvmeq, reserved);
+		ret = BLK_EH_NOT_HANDLED;
+	} else
+		nvme_abort_req(req);
+	spin_unlock_irq(&nvmeq->q_lock);
+
+	return ret;
 }
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -1131,10 +1160,16 @@ static void nvme_free_queues(struct nvme_dev *dev, int lowest)
  */
 static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
-	int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+	int vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
+	if (nvmeq->cq_vector == -1) {
+		spin_unlock_irq(&nvmeq->q_lock);
+		return 1;
+	}
+	vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
 	nvmeq->dev->online_queues--;
+	nvmeq->cq_vector = -1;
 	spin_unlock_irq(&nvmeq->q_lock);
 
 	irq_set_affinity_hint(vector, NULL);
@@ -1169,11 +1204,13 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 		adapter_delete_sq(dev, qid);
 		adapter_delete_cq(dev, qid);
 	}
+	if (!qid && dev->admin_q)
+		blk_mq_freeze_queue_start(dev->admin_q);
 	nvme_clear_queue(nvmeq);
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
-							int depth, int vector)
+							int depth)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
 	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
@@ -1199,7 +1236,6 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
-	nvmeq->cq_vector = vector;
 	nvmeq->qid = qid;
 	dev->queue_count++;
 	dev->queues[qid] = nvmeq;
@@ -1244,6 +1280,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
 
+	nvmeq->cq_vector = qid - 1;
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
 		return result;
@@ -1355,6 +1392,14 @@ static struct blk_mq_ops nvme_mq_ops = {
 	.timeout	= nvme_timeout,
 };
 
+static void nvme_dev_remove_admin(struct nvme_dev *dev)
+{
+	if (dev->admin_q && !blk_queue_dying(dev->admin_q)) {
+		blk_cleanup_queue(dev->admin_q);
+		blk_mq_free_tag_set(&dev->admin_tagset);
+	}
+}
+
 static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 {
 	if (!dev->admin_q) {
@@ -1370,21 +1415,20 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 			return -ENOMEM;
 
 		dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
-		if (!dev->admin_q) {
+		if (IS_ERR(dev->admin_q)) {
 			blk_mq_free_tag_set(&dev->admin_tagset);
 			return -ENOMEM;
 		}
-	}
+		if (!blk_get_queue(dev->admin_q)) {
+			nvme_dev_remove_admin(dev);
+			return -ENODEV;
+		}
+	} else
+		blk_mq_unfreeze_queue(dev->admin_q);
 
 	return 0;
 }
 
-static void nvme_free_admin_tags(struct nvme_dev *dev)
-{
-	if (dev->admin_q)
-		blk_mq_free_tag_set(&dev->admin_tagset);
-}
-
 static int nvme_configure_admin_queue(struct nvme_dev *dev)
 {
 	int result;
@@ -1416,7 +1460,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	nvmeq = dev->queues[0];
 	if (!nvmeq) {
-		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH, 0);
+		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
 		if (!nvmeq)
 			return -ENOMEM;
 	}
@@ -1439,18 +1483,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	if (result)
 		goto free_nvmeq;
 
-	result = nvme_alloc_admin_tags(dev);
-	if (result)
-		goto free_nvmeq;
-
+	nvmeq->cq_vector = 0;
 	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
 	if (result)
-		goto free_tags;
+		goto free_nvmeq;
 
 	return result;
 
- free_tags:
-	nvme_free_admin_tags(dev);
  free_nvmeq:
 	nvme_free_queues(dev, 0);
 	return result;
@@ -1944,7 +1983,7 @@ static void nvme_create_io_queues(struct nvme_dev *dev)
 	unsigned i;
 
 	for (i = dev->queue_count; i <= dev->max_qid; i++)
-		if (!nvme_alloc_queue(dev, i, dev->q_depth, i - 1))
+		if (!nvme_alloc_queue(dev, i, dev->q_depth))
 			break;
 
 	for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
@@ -2235,13 +2274,18 @@ static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
 			break;
 		if (!schedule_timeout(ADMIN_TIMEOUT) ||
 					fatal_signal_pending(current)) {
+			/*
+			 * Disable the controller first since we can't trust it
+			 * at this point, but leave the admin queue enabled
+			 * until all queue deletion requests are flushed.
+			 * FIXME: This may take a while if there are more h/w
+			 * queues than admin tags.
+			 */
 			set_current_state(TASK_RUNNING);
-
 			nvme_disable_ctrl(dev, readq(&dev->bar->cap));
-			nvme_disable_queue(dev, 0);
-
-			send_sig(SIGKILL, dq->worker->task, 1);
+			nvme_clear_queue(dev->queues[0]);
 			flush_kthread_worker(dq->worker);
+			nvme_disable_queue(dev, 0);
 			return;
 		}
 	}
@@ -2318,7 +2362,6 @@ static void nvme_del_queue_start(struct kthread_work *work)
 {
 	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
 							cmdinfo.work);
-	allow_signal(SIGKILL);
 	if (nvme_delete_sq(nvmeq))
 		nvme_del_queue_end(nvmeq);
 }
@@ -2376,6 +2419,34 @@ static void nvme_dev_list_remove(struct nvme_dev *dev)
 		kthread_stop(tmp);
 }
 
+static void nvme_freeze_queues(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns;
+
+	list_for_each_entry(ns, &dev->namespaces, list) {
+		blk_mq_freeze_queue_start(ns->queue);
+
+		spin_lock(ns->queue->queue_lock);
+		queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
+		spin_unlock(ns->queue->queue_lock);
+
+		blk_mq_cancel_requeue_work(ns->queue);
+		blk_mq_stop_hw_queues(ns->queue);
+	}
+}
+
+static void nvme_unfreeze_queues(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns;
+
+	list_for_each_entry(ns, &dev->namespaces, list) {
+		queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns->queue);
+		blk_mq_unfreeze_queue(ns->queue);
+		blk_mq_start_stopped_hw_queues(ns->queue, true);
+		blk_mq_kick_requeue_list(ns->queue);
+	}
+}
+
 static void nvme_dev_shutdown(struct nvme_dev *dev)
 {
 	int i;
@@ -2384,8 +2455,10 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	dev->initialized = 0;
 	nvme_dev_list_remove(dev);
 
-	if (dev->bar)
+	if (dev->bar) {
+		nvme_freeze_queues(dev);
 		csts = readl(&dev->bar->csts);
+	}
 	if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
 		for (i = dev->queue_count - 1; i >= 0; i--) {
 			struct nvme_queue *nvmeq = dev->queues[i];
@@ -2400,12 +2473,6 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	nvme_dev_unmap(dev);
 }
 
-static void nvme_dev_remove_admin(struct nvme_dev *dev)
-{
-	if (dev->admin_q && !blk_queue_dying(dev->admin_q))
-		blk_cleanup_queue(dev->admin_q);
-}
-
 static void nvme_dev_remove(struct nvme_dev *dev)
 {
 	struct nvme_ns *ns;
@@ -2413,8 +2480,10 @@ static void nvme_dev_remove(struct nvme_dev *dev)
 	list_for_each_entry(ns, &dev->namespaces, list) {
 		if (ns->disk->flags & GENHD_FL_UP)
 			del_gendisk(ns->disk);
-		if (!blk_queue_dying(ns->queue))
+		if (!blk_queue_dying(ns->queue)) {
+			blk_mq_abort_requeue_list(ns->queue);
 			blk_cleanup_queue(ns->queue);
+		}
 	}
 }
 
@@ -2495,6 +2564,7 @@ static void nvme_free_dev(struct kref *kref)
 	nvme_free_namespaces(dev);
 	nvme_release_instance(dev);
 	blk_mq_free_tag_set(&dev->tagset);
+	blk_put_queue(dev->admin_q);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2591,15 +2661,20 @@ static int nvme_dev_start(struct nvme_dev *dev)
 	}
 
 	nvme_init_queue(dev->queues[0], 0);
+	result = nvme_alloc_admin_tags(dev);
+	if (result)
+		goto disable;
 
 	result = nvme_setup_io_queues(dev);
 	if (result)
-		goto disable;
+		goto free_tags;
 
 	nvme_set_irq_hints(dev);
 
 	return result;
 
+ free_tags:
+	nvme_dev_remove_admin(dev);
  disable:
 	nvme_disable_queue(dev, 0);
 	nvme_dev_list_remove(dev);
@@ -2639,6 +2714,9 @@ static int nvme_dev_resume(struct nvme_dev *dev)
 		dev->reset_workfn = nvme_remove_disks;
 		queue_work(nvme_workq, &dev->reset_work);
 		spin_unlock(&dev_list_lock);
+	} else {
+		nvme_unfreeze_queues(dev);
+		nvme_set_irq_hints(dev);
 	}
 	dev->initialized = 1;
 	return 0;
@@ -2776,11 +2854,10 @@ static void nvme_remove(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->reset_work);
 	misc_deregister(&dev->miscdev);
-	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
+	nvme_dev_remove(dev);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
-	nvme_free_admin_tags(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }

drivers/block/virtio_blk.c

@@ -638,7 +638,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_put_disk;
 
 	q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set);
-	if (!q) {
+	if (IS_ERR(q)) {
 		err = -ENOMEM;
 		goto out_free_tags;
 	}

include/linux/blk-mq.h

@@ -34,7 +34,6 @@ struct blk_mq_hw_ctx {
 	unsigned long		flags;		/* BLK_MQ_F_* flags */
 
 	struct request_queue	*queue;
-	unsigned int		queue_num;
 	struct blk_flush_queue	*fq;
 
 	void			*driver_data;
@@ -54,7 +53,7 @@ struct blk_mq_hw_ctx {
 	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
 
 	unsigned int		numa_node;
-	unsigned int		cmd_size;	/* per-request extra data */
+	unsigned int		queue_num;
 
 	atomic_t		nr_active;
 
@@ -195,13 +194,16 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
+int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, int error);
 void __blk_mq_end_request(struct request *rq, int error);
 
 void blk_mq_requeue_request(struct request *rq);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head);
+void blk_mq_cancel_requeue_work(struct request_queue *q);
 void blk_mq_kick_requeue_list(struct request_queue *q);
+void blk_mq_abort_requeue_list(struct request_queue *q);
 void blk_mq_complete_request(struct request *rq);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
@@ -212,6 +214,8 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_unfreeze_queue(struct request_queue *q);
+void blk_mq_freeze_queue_start(struct request_queue *q);
 
 /*
  * Driver command data is immediately after the request. So subtract request

include/linux/blk_types.h

@@ -190,6 +190,7 @@ enum rq_flag_bits {
 	__REQ_PM,		/* runtime pm request */
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
+	__REQ_NO_TIMEOUT,	/* requests may never expire */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -243,5 +244,6 @@ enum rq_flag_bits {
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
+#define REQ_NO_TIMEOUT		(1ULL << __REQ_NO_TIMEOUT)
 
 #endif /* __LINUX_BLK_TYPES_H */