nvme: code command_id with a genctr for use-after-free validation

We cannot detect a (perhaps buggy) controller that is sending us
a completion for a request that was already completed (for example
sending a completion twice), this phenomenon was seen in the wild
a few times.

So to protect against this, we use the upper 4 msbits of the nvme sqe
command_id to use as a 4-bit generation counter and verify it matches
the existing request generation that is incrementing on every execution.

The 16-bit command_id structure now is constructed by:
| xxxx | xxxxxxxxxxxx |
  gen    request tag

This means that we are giving up some possible queue depth as 12 bits
allow for a maximum queue depth of 4095 instead of 65536, however we
never create such long queues anyways so no real harm done.

Suggested-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Tested-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 13 insertions, 13 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d649b446da66..0a97ba02f61e 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -487,11 +487,11 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 {
 	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;
 	}
@@ -508,11 +508,11 @@ 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;
 	}
 
@@ -606,7 +606,7 @@ 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->command_id = nvme_cid(rq);
 	data->data_offset = cpu_to_le32(req->data_sent);
 	data->data_length = cpu_to_le32(req->pdu_len);
 	return 0;
@@ -619,11 +619,11 @@ 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);
@@ -703,7 +703,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 {
 	struct nvme_tcp_data_pdu *pdu = (void *)queue->pdu;
 	struct request *rq =
-		blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+		nvme_cid_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
 	while (true) {
@@ -796,8 +796,8 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 	}
 
 	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);
 
 		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
 		queue->nr_cqe++;