[PATCH 6.1 041/109] nvmet-tcp: Fix a possible sporadic response drops in weakly ordered arch

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

6.1-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Meir Elisha <meir.elisha@volumez.com>

[ 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: bdaf13279192 ("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>
---
 drivers/nvme/target/tcp.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 81574500a57c7..125e22bd34e2a 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -520,10 +520,16 @@ 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);
 
@@ -532,7 +538,7 @@ 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;
@@ -784,8 +790,9 @@ 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)
-- 
2.39.5