nvme-tcp: reject a read that transferred too few bytes

nvme_tcp_recv_data() completes a request once the current C2HData PDU
has been consumed. Nothing compares the total bytes received against
the length the command asked for: struct nvme_tcp_request has no
receive-side counter, queue->data_remaining is per queue, and
blk_mq_end_request() completes for blk_rq_bytes(rq) unconditionally
with no residual concept anywhere above.

A controller can therefore answer a 4096-byte read with 512 bytes and
have it reported as a complete read; user space then gets 4096 bytes of
which 3584 are whatever was already in the page. I reproduced that with
a test target.

Count the bytes received and refuse to complete a successful read whose
count does not match, at the two NVME_TCP_F_DATA_SUCCESS paths and in
nvme_tcp_process_nvme_cqe(). The success test shifts req->status right
by one, because the driver keeps the wire value there and shifts it on
completion, so the check must see what the completion path will see.
Only REQ_OP_READ is checked, because there the length comes from the
sectors the request covers; a passthrough command is built by its
submitter, which picks both command and buffer, so the kernel has
nothing to compare against.

Fixes: 3f2304f8c6 ("nvme-tcp: add NVMe over TCP host driver")
Cc: stable@vger.kernel.org
Signed-off-by: Yehyeong Lee <yhlee@isslab.korea.ac.kr>
Signed-off-by: Keith Busch <kbusch@kernel.org>

drivers/nvme/host/tcp.c

@@ -80,6 +80,7 @@ struct nvme_tcp_request {
 
 	struct bio		*curr_bio;
 	struct iov_iter		iter;
+	u32			data_recvd;
 
 	/* send state */
 	size_t			offset;
@@ -617,6 +618,29 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
+/*
+ * NVMe has no short read: a read that completes successfully must
+ * have transferred everything it asked for.
+ */
+static bool nvme_tcp_data_in_short(struct nvme_tcp_queue *queue,
+				   struct request *rq)
+{
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+	if (le16_to_cpu(req->status) >> 1)
+		return false;
+	if (req_op(rq) != REQ_OP_READ || !req->data_len)
+		return false;
+	if (likely(req->data_recvd == req->data_len))
+		return false;
+
+	dev_err(queue->ctrl->ctrl.device,
+		"queue %d tag %#x short data-in: got %u of %u\n",
+		nvme_tcp_queue_id(queue), rq->tag,
+		req->data_recvd, req->data_len);
+	return true;
+}
+
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		struct nvme_completion *cqe)
 {
@@ -636,6 +660,9 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 	if (req->status == cpu_to_le16(NVME_SC_SUCCESS))
 		req->status = cqe->status;
 
+	if (unlikely(nvme_tcp_data_in_short(queue, rq)))
+		return -EPROTO;
+
 	if (!nvme_try_complete_req(rq, req->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
@@ -958,6 +985,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		*len -= recv_len;
 		*offset += recv_len;
 		queue->data_remaining -= recv_len;
+		req->data_recvd += recv_len;
 	}
 
 	if (!queue->data_remaining) {
@@ -966,6 +994,8 @@ 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) {
+				if (unlikely(nvme_tcp_data_in_short(queue, rq)))
+					return -EPROTO;
 				nvme_tcp_end_request(rq,
 						le16_to_cpu(req->status));
 				queue->nr_cqe++;
@@ -1014,6 +1044,9 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 					pdu->command_id);
 		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
+		if (unlikely(nvme_tcp_data_in_short(queue, rq)))
+			return -EPROTO;
+
 		nvme_tcp_end_request(rq, le16_to_cpu(req->status));
 		queue->nr_cqe++;
 	}
@@ -2746,6 +2779,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 	req->status = cpu_to_le16(NVME_SC_SUCCESS);
 	req->offset = 0;
 	req->data_sent = 0;
+	req->data_recvd = 0;
 	req->pdu_len = 0;
 	req->pdu_sent = 0;
 	req->h2cdata_left = 0;