1 files changed, 75 insertions, 33 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 11e84ed4de36..e159b78b5f3b 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -110,6 +110,7 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
+	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -420,6 +421,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
@@ -784,11 +786,11 @@ static void nvme_tcp_data_ready(struct sock *sk)
 {
 	struct nvme_tcp_queue *queue;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	queue = sk->sk_user_data;
 	if (likely(queue && queue->rd_enabled))
 		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void nvme_tcp_write_space(struct sock *sk)
@@ -859,12 +861,11 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		else
 			flags |= MSG_MORE;
 
-		/* can't zcopy slab pages */
-		if (unlikely(PageSlab(page))) {
-			ret = sock_no_sendpage(queue->sock, page, offset, len,
+		if (sendpage_ok(page)) {
+			ret = kernel_sendpage(queue->sock, page, offset, len,
 					flags);
 		} else {
-			ret = kernel_sendpage(queue->sock, page, offset, len,
+			ret = sock_no_sendpage(queue->sock, page, offset, len,
 					flags);
 		}
 		if (ret <= 0)
@@ -1319,6 +1320,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 		}
 	}
 
+	/* Set 10 seconds timeout for icresp recvmsg */
+	queue->sock->sk->sk_rcvtimeo = 10 * HZ;
+
 	queue->sock->sk->sk_allocation = GFP_ATOMIC;
 	if (!qid)
 		n = 0;
@@ -1435,7 +1439,6 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 
 	if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return;
-
 	__nvme_tcp_stop_queue(queue);
 }
 
@@ -1503,6 +1506,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
 static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (to_tcp_ctrl(ctrl)->async_req.pdu) {
+		cancel_work_sync(&ctrl->async_event_work);
 		nvme_tcp_free_async_req(to_tcp_ctrl(ctrl));
 		to_tcp_ctrl(ctrl)->async_req.pdu = NULL;
 	}
@@ -1681,17 +1685,33 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(ctrl->tagset,
-			ctrl->queue_count - 1);
 	}
 
 	ret = nvme_tcp_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(ctrl);
+		if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
+		blk_mq_update_nr_hw_queues(ctrl->tagset,
+			ctrl->queue_count - 1);
+		nvme_unfreeze(ctrl);
+	}
+
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(ctrl);
+	nvme_tcp_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->connect_q);
@@ -1777,6 +1797,7 @@ out_free_queue:
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
@@ -1787,13 +1808,17 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		return;
+		goto out;
+	blk_mq_quiesce_queue(ctrl->admin_q);
+	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset) {
@@ -1804,6 +1829,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
+out:
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2042,40 +2069,55 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	nvme_tcp_queue_request(&ctrl->async_req);
 }
 
+static void nvme_tcp_complete_timed_out(struct request *rq)
+{
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
+	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_tcp_timeout(struct request *rq, bool reserved)
 {
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
-	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
-	dev_warn(ctrl->ctrl.device,
+	dev_warn(ctrl->device,
 		"queue %d: timeout request %#x type %d\n",
 		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
 
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+	if (ctrl->state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
-		 * or we are already started error recovery. all outstanding
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * If we are resetting, connecting or deleting we should
+		 * complete immediately because we may block controller
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
-		nvme_tcp_teardown_io_queues(&ctrl->ctrl, false);
-		nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false);
+		nvme_tcp_complete_timed_out(rq);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
-	nvme_tcp_error_recovery(&ctrl->ctrl);
-
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
+	nvme_tcp_error_recovery(ctrl);
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2302,6 +2344,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
@@ -2360,8 +2403,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
 	mutex_unlock(&nvme_tcp_ctrl_mutex);
@@ -2371,6 +2412,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);