nvme-tcp: strict pdu pacing to avoid send stalls on TLS
PATCH 1/1 nvme-tcp: strict pdu pacing to avoid send stalls on TLS
TLS requires a strict pdu pacing via MSG_EOR to signal the end of a record and subsequent encryption. If we do not set MSG_EOR at the end of a sequence the record won't be closed, encryption doesn't start, and we end up with a send stall as the message will never be passed on to the TCP layer.
So do not check for the queue status when figuring out whether MSG_MORE should be set but rather make it dependent on the current command only.
--- drivers/nvme/host/tcp.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-)
drivers/nvme/host/tcp.c +3 -8
@@ -1049,7 +1049,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)int req_data_sent = req->data_sent;int ret; -if (last && !queue->data_digest && !nvme_tcp_queue_more (queue)) +if (last && !queue->data_digest) msg.msg_flags |=MSG_EOR ;else msg.msg_flags |=MSG_MORE ;
@@ -1105,7 +1105,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)int len =sizeof (*pdu) + hdgst - req->offset;int ret; -if (inline_data ||nvme_tcp_queue_more (queue)) +if (inline_data) msg.msg_flags |=MSG_MORE ;else msg.msg_flags |=MSG_EOR ;
@@ -1175,17 +1175,12 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)size_t offset = req->offset;u32 h2cdata_left = req->h2cdata_left;int ret; -struct msghdr msg = { .msg_flags =MSG_DONTWAIT }; +struct msghdr msg = { .msg_flags =MSG_DONTWAIT |MSG_EOR };struct kvec iov = { .iov_base = (u8 *)&req->ddgst + req->offset, .iov_len =NVME_TCP_DIGEST_LENGTH - req->offset }; -if (nvme_tcp_queue_more (queue)) - msg.msg_flags |=MSG_MORE ; -else - msg.msg_flags |=MSG_EOR ; - ret =kernel_sendmsg (queue->sock, &msg, &iov,1 , iov.iov_len);if (unlikely (ret <=0 ))return ret;
Signature · 1 line
2.35.3
Sagi Grimberg
maintainerQuoted 8 lines · Hannes Reinecke
TLS requires a strict pdu pacing via
MSG_EORto signal the end of a record and subsequent encryption. If we do not setMSG_EORat the end of a sequence the record won't be closed, encryption doesn't start, and we end up with a send stall as the message will never be passed on to the TCP layer.
So do not check for the queue status when figuring out whetherMSG_MOREshould be set but rather make it dependent on the current command only.
How about making nvme_tcp_queue_more take into account nvme_tcp_tls()? so we preserve the behavior without tls.
i.e. something like:
--
drivers/nvme/host/tcp.c +0 -0
@@ -360,12 +360,18 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
} while (ret > 0);
}
-static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) +static inline bool nvme_tcp_queue_has_pending(struct nvme_tcp_queue *queue) {
return !list_empty(&queue->send_list) || !llist_empty(&queue->req_list);
}
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+ return !nvme_tcp_tls(queue->ctrl) &&
+ nvme_tcp_queue_has_pending(queue);
+}
+
static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, bool sync, bool last)
{
@@ -386,7 +392,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, mutex_unlock(&queue->send_mutex);
}
- if (last && nvme_tcp_queue_more(queue))
+ if (last && nvme_tcp_queue_has_pending(queue)) queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); }
--
Quoted 52 lines · Sagi Grimberg
Quoted 8 lines · Hannes Reinecke
TLS requires a strict pdu pacing via
MSG_EORto signal the end of a record and subsequent encryption. If we do not setMSG_EORat the end of a sequence the record won't be closed, encryption doesn't start, and we end up with a send stall as the message will never be passed on to the TCP layer.
So do not check for the queue status when figuring out whetherMSG_MOREshould be set but rather make it dependent on the current command only.How about making
nvme_tcp_queue_moretake into accountnvme_tcp_tls()? so we preserve the behavior without tls.i.e. something like:
drivers/nvme/host/tcp.c +7
-1@@ -360,12 +360,18 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) } while (ret > 0); } -static inline bool nvme_tcp_queue_more (struct nvme_tcp_queue *queue) +static inline bool nvme_tcp_queue_has_pending (struct nvme_tcp_queue *queue) { return !list_empty(&queue->send_list) || !llist_empty(&queue->req_list); } +static inline bool nvme_tcp_queue_more (struct nvme_tcp_queue *queue) +{ + return !nvme_tcp_tls(queue->ctrl) && + nvme_tcp_queue_has_pending(queue); +} + static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,bool sync, bool last)
{drivers/nvme/host/tcp.c +1
-1@@ -386,7 +392,7 @@ static inline void nvme_tcp_queue_request(structnvme_tcp_request *req, mutex_unlock(&queue->send_mutex); } - if (last && nvme_tcp_queue_more(queue)) + if (last && nvme_tcp_queue_has_pending(queue)) queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
Quoted 3 lines
}
Would work as well, I guess.
I'll give it a go.
Cheers,
Hannes