nvme-tcp: fix possible req->offset corruption
PATCH 1/1 nvme-tcp: fix possible req->offset corruption
With commit db5ad6b7f8cd ("nvme-tcp: try to send request in queue_rq context") r2t and response PDU can get processed while send function is executing.
Current data digest send code uses req->offset after kernel_sendmsg(), this creates a race condition where req->offset gets reset before it is used in send function.
This can happen in two cases -
1. Target sends r2t PDU which resets req->offset.
2. Target send response PDU which completes the req and then req is used for a new command, nvme_tcp_setup_cmd_pdu() resets req->offset.
Fix this by storing req->offset in a local variable and using this local variable after kernel_sendmsg().
--- drivers/nvme/host/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/nvme/host/tcp.c +2 -1
@@ -1048,6 +1048,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)static int nvme_tcp_try_send_ddgst (struct nvme_tcp_request *req) {struct nvme_tcp_queue *queue = req->queue; +size_t offset = req->offset;int ret;struct msghdr msg = { .msg_flags =MSG_DONTWAIT };struct kvec iov = {
@@ -1064,7 +1065,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)if (unlikely (ret <=0 ))return ret; -if (req->offset + ret ==NVME_TCP_DIGEST_LENGTH ) { +if (offset + ret ==NVME_TCP_DIGEST_LENGTH ) {nvme_tcp_done_send_req (queue);return 1 ; }
Signature · 1 line
2.0.2
Quoted 8 lines · Varun Prakash
With commit
db5ad6b7f8cd("nvme-tcp: try to send request inqueue_rqcontext") r2t and response PDU can get processed while send function is executing.Current data digest send code uses
req->offsetafterkernel_sendmsg(), this creates a race condition wherereq->offsetgets reset before it is used in send function.
Quoted 7 lines
This can happen in two cases -
1. Target sends r2t PDU which resetsreq->offset.
2. Target send response PDU which completes the req and then req is used for a new command,nvme_tcp_setup_cmd_pdu()resetsreq->offset.Fix this by storing
req->offsetin a local variable and using this local variable afterkernel_sendmsg().
Nice catch.
Quoted 30 lines
Fixes db5ad6b7f8cd ("nvme-tcp: try to send request in queue_rq context")Signed-off-by Varun Prakash <[email protected]>--- drivers/nvme/host/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)drivers/nvme/host/tcp.c +2
-1@@ -1048,6 +1048,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)static int nvme_tcp_try_send_ddgst (struct nvme_tcp_request *req) {struct nvme_tcp_queue *queue = req->queue; +size_t offset = req->offset;int ret;struct msghdr msg = { .msg_flags =MSG_DONTWAIT };struct kvec iov = {@@ -1064,7 +1065,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)if (unlikely (ret <=0 ))return ret; -if (req->offset + ret ==NVME_TCP_DIGEST_LENGTH ) { +if (offset + ret ==NVME_TCP_DIGEST_LENGTH ) {nvme_tcp_done_send_req (queue);return 1 ; }Signature · 1 line
2.0.2
Thanks,
applied to nvme-5.15.