1 files changed, 57 insertions, 42 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8cb15ee5b249..3c1c29dd3020 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -45,6 +45,7 @@ struct nvme_tcp_request {
 	u32			pdu_len;
 	u32			pdu_sent;
 	u16			ttag;
+	__le16			status;
 	struct list_head	entry;
 	struct llist_node	lentry;
 	__le32			ddgst;
@@ -273,6 +274,12 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
 	} while (ret > 0);
 }
 
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+	return !list_empty(&queue->send_list) ||
+		!llist_empty(&queue->req_list) || queue->more_requests;
+}
+
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		bool sync, bool last)
 {
@@ -293,9 +300,10 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		nvme_tcp_send_all(queue);
 		queue->more_requests = false;
 		mutex_unlock(&queue->send_mutex);
-	} else if (last) {
-		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 	}
+
+	if (last && nvme_tcp_queue_more(queue))
+		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 }
 
 static void nvme_tcp_process_req_list(struct nvme_tcp_queue *queue)
@@ -485,18 +493,23 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		struct nvme_completion *cqe)
 {
+	struct nvme_tcp_request *req;
 	struct request *rq;
 
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), cqe->command_id);
+	rq = nvme_find_rq(nvme_tcp_tagset(queue), cqe->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag 0x%x not found\n",
-			nvme_tcp_queue_id(queue), cqe->command_id);
+			"got bad cqe.command_id %#x on queue %d\n",
+			cqe->command_id, nvme_tcp_queue_id(queue));
 		nvme_tcp_error_recovery(&queue->ctrl->ctrl);
 		return -EINVAL;
 	}
 
-	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
+	req = blk_mq_rq_to_pdu(rq);
+	if (req->status == cpu_to_le16(NVME_SC_SUCCESS))
+		req->status = cqe->status;
+
+	if (!nvme_try_complete_req(rq, req->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
@@ -508,11 +521,11 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue,
 {
 	struct request *rq;
 
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+	rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag %#x not found\n",
-			nvme_tcp_queue_id(queue), pdu->command_id);
+			"got bad c2hdata.command_id %#x on queue %d\n",
+			pdu->command_id, nvme_tcp_queue_id(queue));
 		return -ENOENT;
 	}
 
@@ -606,8 +619,8 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
 	data->hdr.plen =
 		cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst);
 	data->ttag = pdu->ttag;
-	data->command_id = rq->tag;
-	data->data_offset = cpu_to_le32(req->data_sent);
+	data->command_id = nvme_cid(rq);
+	data->data_offset = pdu->r2t_offset;
 	data->data_length = cpu_to_le32(req->pdu_len);
 	return 0;
 }
@@ -619,11 +632,11 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	struct request *rq;
 	int ret;
 
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+	rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag %#x not found\n",
-			nvme_tcp_queue_id(queue), pdu->command_id);
+			"got bad r2t.command_id %#x on queue %d\n",
+			pdu->command_id, nvme_tcp_queue_id(queue));
 		return -ENOENT;
 	}
 	req = blk_mq_rq_to_pdu(rq);
@@ -702,17 +715,9 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 			      unsigned int *offset, size_t *len)
 {
 	struct nvme_tcp_data_pdu *pdu = (void *)queue->pdu;
-	struct nvme_tcp_request *req;
-	struct request *rq;
-
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
-	if (!rq) {
-		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag %#x not found\n",
-			nvme_tcp_queue_id(queue), pdu->command_id);
-		return -ENOENT;
-	}
-	req = blk_mq_rq_to_pdu(rq);
+	struct request *rq =
+		nvme_cid_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
 	while (true) {
 		int recv_len, ret;
@@ -766,7 +771,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 			queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
 		} else {
 			if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-				nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+				nvme_tcp_end_request(rq,
+						le16_to_cpu(req->status));
 				queue->nr_cqe++;
 			}
 			nvme_tcp_init_recv_ctx(queue);
@@ -796,18 +802,24 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 		return 0;
 
 	if (queue->recv_ddgst != queue->exp_ddgst) {
+		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+					pdu->command_id);
+		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+		req->status = cpu_to_le16(NVME_SC_DATA_XFER_ERROR);
+
 		dev_err(queue->ctrl->ctrl.device,
 			"data digest error: recv %#x expected %#x\n",
 			le32_to_cpu(queue->recv_ddgst),
 			le32_to_cpu(queue->exp_ddgst));
-		return -EIO;
 	}
 
 	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-		struct request *rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue),
-						pdu->command_id);
+		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+					pdu->command_id);
+		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
-		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+		nvme_tcp_end_request(rq, le16_to_cpu(req->status));
 		queue->nr_cqe++;
 	}
 
@@ -901,12 +913,6 @@ done:
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
-static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
-{
-	return !list_empty(&queue->send_list) ||
-		!llist_empty(&queue->req_list) || queue->more_requests;
-}
-
 static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)
 {
 	queue->request = NULL;
@@ -947,7 +953,15 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 			nvme_tcp_ddgst_update(queue->snd_hash, page,
 					offset, ret);
 
-		/* fully successful last write*/
+		/*
+		 * update the request iterator except for the last payload send
+		 * in the request where we don't want to modify it as we may
+		 * compete with the RX path completing the request.
+		 */
+		if (req->data_sent + ret < req->data_len)
+			nvme_tcp_advance_req(req, ret);
+
+		/* fully successful last send in current PDU */
 		if (last && ret == len) {
 			if (queue->data_digest) {
 				nvme_tcp_ddgst_final(queue->snd_hash,
@@ -959,7 +973,6 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 			}
 			return 1;
 		}
-		nvme_tcp_advance_req(req, ret);
 	}
 	return -EAGAIN;
 }
@@ -1140,8 +1153,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 				pending = true;
 			else if (unlikely(result < 0))
 				break;
-		} else
-			pending = !llist_empty(&queue->req_list);
+		}
 
 		result = nvme_tcp_try_recv(queue);
 		if (result > 0)
@@ -1228,6 +1240,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 
 	sock_release(queue->sock);
 	kfree(queue->pdu);
+	mutex_destroy(&queue->send_mutex);
 	mutex_destroy(&queue->queue_lock);
 }
 
@@ -1533,6 +1546,7 @@ err_sock:
 	sock_release(queue->sock);
 	queue->sock = NULL;
 err_destroy_mutex:
+	mutex_destroy(&queue->send_mutex);
 	mutex_destroy(&queue->queue_lock);
 	return ret;
 }
@@ -1769,13 +1783,13 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	if (ret)
 		return ret;
 
-	ctrl->queue_count = nr_io_queues + 1;
-	if (ctrl->queue_count < 2) {
+	if (nr_io_queues == 0) {
 		dev_err(ctrl->device,
 			"unable to set any I/O queues\n");
 		return -ENOMEM;
 	}
 
+	ctrl->queue_count = nr_io_queues + 1;
 	dev_info(ctrl->device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
@@ -2299,6 +2313,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 		return ret;
 
 	req->state = NVME_TCP_SEND_CMD_PDU;
+	req->status = cpu_to_le16(NVME_SC_SUCCESS);
 	req->offset = 0;
 	req->data_sent = 0;
 	req->pdu_len = 0;