nvmet-tcp: Fix a possible sporadic response drops in weakly ordered arch

[ Upstream commit a16f88964c647103dad7743a484b216d488a6352 ]

The order in which queue->cmd and rcv_state are updated is crucial.
If these assignments are reordered by the compiler, the worker might not
get queued in nvmet_tcp_queue_response(), hanging the IO. to enforce the
the correct reordering, set rcv_state using smp_store_release().

Fixes: bdaf132791 ("nvmet-tcp: fix a segmentation fault during io parsing error")

Signed-off-by: Meir Elisha <meir.elisha@volumez.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Meir Elisha
2025-02-26 09:28:12 +02:00
committed by Greg Kroah-Hartman
parent 127c8905ea
commit 84cce23da4

View File

@@ -547,10 +547,16 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
struct nvmet_tcp_cmd *cmd =
container_of(req, struct nvmet_tcp_cmd, req);
struct nvmet_tcp_queue *queue = cmd->queue;
enum nvmet_tcp_recv_state queue_state;
struct nvmet_tcp_cmd *queue_cmd;
struct nvme_sgl_desc *sgl;
u32 len;
if (unlikely(cmd == queue->cmd)) {
/* Pairs with store_release in nvmet_prepare_receive_pdu() */
queue_state = smp_load_acquire(&queue->rcv_state);
queue_cmd = READ_ONCE(queue->cmd);
if (unlikely(cmd == queue_cmd)) {
sgl = &cmd->req.cmd->common.dptr.sgl;
len = le32_to_cpu(sgl->length);
@@ -559,7 +565,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
* Avoid using helpers, this might happen before
* nvmet_req_init is completed.
*/
if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
if (queue_state == NVMET_TCP_RECV_PDU &&
len && len <= cmd->req.port->inline_data_size &&
nvme_is_write(cmd->req.cmd))
return;
@@ -823,8 +829,9 @@ static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
{
queue->offset = 0;
queue->left = sizeof(struct nvme_tcp_hdr);
queue->cmd = NULL;
queue->rcv_state = NVMET_TCP_RECV_PDU;
WRITE_ONCE(queue->cmd, NULL);
/* Ensure rcv_state is visible only after queue->cmd is set */
smp_store_release(&queue->rcv_state, NVMET_TCP_RECV_PDU);
}
static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)