1 files changed, 127 insertions, 12 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 840ae475074d..25e486e6e805 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -217,6 +217,19 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
+static inline bool nvme_tcp_recv_pdu_supported(enum nvme_tcp_pdu_type type)
+{
+	switch (type) {
+	case nvme_tcp_c2h_term:
+	case nvme_tcp_c2h_data:
+	case nvme_tcp_r2t:
+	case nvme_tcp_rsp:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * Check if the queue is TLS encrypted
  */
@@ -440,7 +453,8 @@ nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
 			return NULL;
 	}
 
-	list_del(&req->entry);
+	list_del_init(&req->entry);
+	init_llist_node(&req->lentry);
 	return req;
 }
 
@@ -548,6 +562,8 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
 	req->queue = queue;
 	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	nvme_req(rq)->cmd = &pdu->cmd;
+	init_llist_node(&req->lentry);
+	INIT_LIST_HEAD(&req->entry);
 
 	return 0;
 }
@@ -752,6 +768,14 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 		return -EPROTO;
 	}
 
+	if (llist_on_list(&req->lentry) ||
+	    !list_empty(&req->entry)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d unexpected r2t while processing request\n",
+			rq->tag);
+		return -EPROTO;
+	}
+
 	req->pdu_len = 0;
 	req->h2cdata_left = r2t_length;
 	req->h2cdata_offset = r2t_offset;
@@ -763,6 +787,40 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	return 0;
 }
 
+static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
+		struct nvme_tcp_term_pdu *pdu)
+{
+	u16 fes;
+	const char *msg;
+	u32 plen = le32_to_cpu(pdu->hdr.plen);
+
+	static const char * const msg_table[] = {
+		[NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field",
+		[NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
+		[NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
+		[NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
+		[NVME_TCP_FES_DATA_LIMIT_EXCEEDED] = "Data Transfer Limit Exceeded",
+		[NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
+	};
+
+	if (plen < NVME_TCP_MIN_C2HTERM_PLEN ||
+	    plen > NVME_TCP_MAX_C2HTERM_PLEN) {
+		dev_err(queue->ctrl->ctrl.device,
+			"Received a malformed C2HTermReq PDU (plen = %u)\n",
+			plen);
+		return;
+	}
+
+	fes = le16_to_cpu(pdu->fes);
+	if (fes && fes < ARRAY_SIZE(msg_table))
+		msg = msg_table[fes];
+	else
+		msg = "Unknown";
+
+	dev_err(queue->ctrl->ctrl.device,
+		"Received C2HTermReq (FES = %s)\n", msg);
+}
+
 static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		unsigned int *offset, size_t *len)
 {
@@ -784,6 +842,25 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		return 0;
 
 	hdr = queue->pdu;
+	if (unlikely(hdr->hlen != sizeof(struct nvme_tcp_rsp_pdu))) {
+		if (!nvme_tcp_recv_pdu_supported(hdr->type))
+			goto unsupported_pdu;
+
+		dev_err(queue->ctrl->ctrl.device,
+			"pdu type %d has unexpected header length (%d)\n",
+			hdr->type, hdr->hlen);
+		return -EPROTO;
+	}
+
+	if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
+		/*
+		 * C2HTermReq never includes Header or Data digests.
+		 * Skip the checks.
+		 */
+		nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu);
+		return -EINVAL;
+	}
+
 	if (queue->hdr_digest) {
 		ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen);
 		if (unlikely(ret))
@@ -807,10 +884,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		nvme_tcp_init_recv_ctx(queue);
 		return nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
 	default:
-		dev_err(queue->ctrl->ctrl.device,
-			"unsupported pdu type (%d)\n", hdr->type);
-		return -EINVAL;
+		goto unsupported_pdu;
 	}
+
+unsupported_pdu:
+	dev_err(queue->ctrl->ctrl.device,
+		"unsupported pdu type (%d)\n", hdr->type);
+	return -EINVAL;
 }
 
 static inline void nvme_tcp_end_request(struct request *rq, u16 status)
@@ -1280,7 +1360,7 @@ static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
 	queue->nr_cqe = 0;
 	consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
 	release_sock(sk);
-	return consumed;
+	return consumed == -EAGAIN ? 0 : consumed;
 }
 
 static void nvme_tcp_io_work(struct work_struct *w)
@@ -1308,6 +1388,11 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		else if (unlikely(result < 0))
 			return;
 
+		/* did we get some space after spending time in recv? */
+		if (nvme_tcp_queue_has_pending(queue) &&
+		    sk_stream_is_writeable(queue->sock->sk))
+			pending = true;
+
 		if (!pending || !queue->rd_enabled)
 			return;
 
@@ -1452,11 +1537,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	msg.msg_flags = MSG_WAITALL;
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
-	if (ret < sizeof(*icresp)) {
+	if (ret >= 0 && ret < sizeof(*icresp))
+		ret = -ECONNRESET;
+	if (ret < 0) {
 		pr_warn("queue %d: failed to receive icresp, error %d\n",
 			nvme_tcp_queue_id(queue), ret);
-		if (ret >= 0)
-			ret = -ECONNRESET;
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;
@@ -1875,7 +1960,7 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
 	cancel_work_sync(&queue->io_work);
 }
 
-static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+static void nvme_tcp_stop_queue_nowait(struct nvme_ctrl *nctrl, int qid)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
@@ -1894,6 +1979,31 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	mutex_unlock(&queue->queue_lock);
 }
 
+static void nvme_tcp_wait_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	int timeout = 100;
+
+	while (timeout > 0) {
+		if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags) ||
+		    !sk_wmem_alloc_get(queue->sock->sk))
+			return;
+		msleep(2);
+		timeout -= 2;
+	}
+	dev_warn(nctrl->device,
+		 "qid %d: timeout draining sock wmem allocation expired\n",
+		 qid);
+}
+
+static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	nvme_tcp_stop_queue_nowait(nctrl, qid);
+	nvme_tcp_wait_queue(nctrl, qid);
+}
+
+
 static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue)
 {
 	write_lock_bh(&queue->sock->sk->sk_callback_lock);
@@ -1961,7 +2071,9 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
 	int i;
 
 	for (i = 1; i < ctrl->queue_count; i++)
-		nvme_tcp_stop_queue(ctrl, i);
+		nvme_tcp_stop_queue_nowait(ctrl, i);
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvme_tcp_wait_queue(ctrl, i);
 }
 
 static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
@@ -2498,6 +2610,8 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	ctrl->async_req.offset = 0;
 	ctrl->async_req.curr_bio = NULL;
 	ctrl->async_req.data_len = 0;
+	init_llist_node(&ctrl->async_req.lentry);
+	INIT_LIST_HEAD(&ctrl->async_req.entry);
 
 	nvme_tcp_queue_request(&ctrl->async_req, true, true);
 }
@@ -2667,6 +2781,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;
+	int ret;
 
 	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return 0;
@@ -2674,9 +2789,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	set_bit(NVME_TCP_Q_POLLING, &queue->flags);
 	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
 		sk_busy_loop(sk, true);
-	nvme_tcp_try_recv(queue);
+	ret = nvme_tcp_try_recv(queue);
 	clear_bit(NVME_TCP_Q_POLLING, &queue->flags);
-	return queue->nr_cqe;
+	return ret < 0 ? ret : queue->nr_cqe;
 }
 
 static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)