Second attempt at blk-mq + nvme hotplug fixes

index 1a41d7a..6d83ee6 100644
@@ -160,6 +160,7 @@ void blk_mq_wake_waiters(struct request_queue *q)
 	queue_for_each_hw_ctx(q, hctx, i)
 		if (blk_mq_hw_queue_mapped(hctx))
 			blk_mq_tag_wakeup_all(hctx->tags, true);
+	wake_up_all(&q->mq_freeze_wq);
 }
 
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)

index 6d83ee6..82930c0 100644
@@ -398,6 +398,12 @@ 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;

index 3b43f50..8bbd082 100644
@@ -195,6 +195,7 @@ 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);

index 82930c0..a976db4 100644
@@ -521,6 +521,12 @@ 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);

index 8bbd082..b509ef5 100644
@@ -202,6 +202,7 @@ 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_complete_request(struct request *rq);
 

index a976db4..f6e1225 100644
@@ -533,6 +533,26 @@ void blk_mq_kick_requeue_list(struct request_queue *q)
 }
 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)
 {

index b509ef5..a09728e 100644
@@ -204,6 +204,7 @@ 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);

index f6e1225..5dbd315b 100644
@@ -414,7 +414,8 @@ void blk_mq_start_request(struct request *rq)
 	if (unlikely(blk_bidi_rq(rq)))
 		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
 
-	blk_add_timer(rq);
+	if (rq->timeout != REQ_NO_TIMEOUT)
+		blk_add_timer(rq);
 
 	/*
 	 * Ensure that ->deadline is visible before set the started

@@ -613,13 +614,14 @@ 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)  ||
+				rq->timeout == REQ_NO_TIMEOUT)
 		return;
 
 	if (time_after_eq(jiffies, rq->deadline)) {

index 92f4b4b..096b4f7f 100644
@@ -198,6 +198,7 @@ struct request {
 
 	unsigned long deadline;
 	struct list_head timeout_list;
+#define REQ_NO_TIMEOUT UINT_MAX
 	unsigned int timeout;
 	int retries;
 

index 5dbd315b..1443c77 100644
@@ -621,8 +621,13 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	struct blk_mq_timeout_data *data = priv;
 
 	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)  ||
-				rq->timeout == REQ_NO_TIMEOUT)
+				rq->timeout == REQ_NO_TIMEOUT) {
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_complete_request(rq);
+		}
 		return;
+	}
 
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))

index f7d083b..ff3012b 100644
@@ -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 */

@@ -664,8 +665,6 @@ 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 +834,7 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	req->timeout = REQ_NO_TIMEOUT;
 	cmd_info = blk_mq_rq_to_pdu(req);
 	nvme_set_info(cmd_info, req, async_req_completion);
 

@@ -1086,8 +1086,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 
 	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
 							nvmeq->qid);
-	if (nvmeq->dev->initialized)
-		nvme_abort_req(req);
+
+	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);
+		return BLK_EH_NOT_HANDLED;
+	}
+	nvme_abort_req(req);
 
 	/*
 	 * The aborted req will be completed on receiving the abort req.

index ff3012b..571577c 100644
@@ -433,7 +433,10 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 		if (!(status & NVME_SC_DNR || blk_noretry_request(req))
 		    && (jiffies - req->start_time) < req->timeout) {
 			blk_mq_requeue_request(req);
-			blk_mq_kick_requeue_list(req->q);
+			spin_lock(req->q->queue_lock);
+			if (!blk_queue_stopped(req->q))
+				blk_mq_kick_requeue_list(req->q);
+			spin_unlock(req->q->queue_lock);
 			return;
 		}
 		req->errors = nvme_error_status(status);

@@ -2391,6 +2394,34 @@ 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;

@@ -2399,8 +2430,10 @@ 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];

@@ -2654,6 +2687,9 @@ 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;

@@ -2791,8 +2827,8 @@ 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);

index 571577c..f20e6c6 100644
@@ -106,7 +106,7 @@ struct nvme_queue {
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
 	u16 q_depth;
-	u16 cq_vector;
+	s16 cq_vector;
 	u16 sq_head;
 	u16 sq_tail;
 	u16 cq_head;

@@ -1186,6 +1186,8 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 		adapter_delete_sq(dev, qid);
 		adapter_delete_cq(dev, qid);
 	}
+	if (!qid)
+		blk_mq_freeze_queue_start(dev->admin_q);
 	nvme_clear_queue(nvmeq);
 }
 

@@ -1372,6 +1374,14 @@ 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) {

@@ -1391,17 +1401,16 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 			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;

@@ -1456,19 +1465,13 @@ 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;

@@ -2251,15 +2254,19 @@ static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
 		set_current_state(TASK_KILLABLE);
 		if (!atomic_read(&dq->refcount))
 			break;
-		if (!schedule_timeout(ADMIN_TIMEOUT) ||
-					fatal_signal_pending(current)) {
+		if (!schedule_timeout(ADMIN_TIMEOUT)) {
+			/*
+			 * 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. 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;
 		}
 	}

@@ -2336,7 +2343,6 @@ 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);
 }

@@ -2448,12 +2454,6 @@ 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;

@@ -2543,6 +2543,7 @@ 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);

@@ -2639,15 +2640,18 @@ static int nvme_dev_start(struct nvme_dev *dev)
 	}
 
 	nvme_init_queue(dev->queues[0], 0);
-
-	result = nvme_setup_io_queues(dev);
+	result = nvme_alloc_admin_tags(dev);
 	if (result)
 		goto disable;
 
-	nvme_set_irq_hints(dev);
+	result = nvme_setup_io_queues(dev);
+	if (result)
+		goto free_tags;
 
 	return result;
 
+ free_tags:
+	nvme_dev_remove_admin(dev);
  disable:
 	nvme_disable_queue(dev, 0);
 	nvme_dev_list_remove(dev);

@@ -2831,7 +2835,6 @@ static void nvme_remove(struct pci_dev *pdev)
 	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);
 }

index f20e6c6..a7f663c 100644
@@ -1067,15 +1067,22 @@ 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);

@@ -2461,8 +2468,10 @@ 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);
+		}
 	}
 }