[PATCH 10/18] nvme-tcp: fixup send workflow for kTLS

[Sagi Grimberg]

On 3/21/23 14:43, Hannes Reinecke wrote:
> kTLS does not support MSG_EOR flag for sendmsg(), and the ->sendpage()
> call really doesn't bring any benefit as data has to be copied
> anyway.
> So use sock_no_sendpage() or sendmsg() instead, and ensure that the
> MSG_EOR flag is blanked out for kTLS.
> 
> Signed-off-by: Hannes Reinecke <hare at suse.de>
> ---
>   drivers/nvme/host/tcp.c | 33 +++++++++++++++++++++------------
>   1 file changed, 21 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index bbff1f52a167..007d457cacf9 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -1034,13 +1034,19 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
>   		bool last = nvme_tcp_pdu_last_send(req, len);
>   		int req_data_sent = req->data_sent;
>   		int ret, flags = MSG_DONTWAIT;
> +		bool do_sendpage = sendpage_ok(page);
>   
> -		if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
> +		if (!last || queue->data_digest || nvme_tcp_queue_more(queue))
> +			flags |= MSG_MORE;
> +		else if (!test_bit(NVME_TCP_Q_TLS, &queue->flags))
>   			flags |= MSG_EOR;
> -		else
> -			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;

I think its time to move the flags setting to a helper.

>   
> -		if (sendpage_ok(page)) {
> +		if (test_bit(NVME_TCP_Q_TLS, &queue->flags))
> +			do_sendpage = false;
> +
> +		if (do_sendpage) {

The do_sendpage looks redundant to me.

> +			if (flags & MSG_MORE)
> +				flags |= MSG_SENDPAGE_NOTLAST;
>   			ret = kernel_sendpage(queue->sock, page, offset, len,
>   					flags);

I think that the SENDPAGE_NOLAST should be set together with MSG_MORE
regardless.

>   		} else {
> @@ -1088,19 +1094,22 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
>   	bool inline_data = nvme_tcp_has_inline_data(req);
>   	u8 hdgst = nvme_tcp_hdgst_len(queue);
>   	int len = sizeof(*pdu) + hdgst - req->offset;
> -	int flags = MSG_DONTWAIT;
> +	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
> +	struct kvec iov = {
> +		.iov_base = (u8 *)req->pdu + req->offset,
> +		.iov_len = len,
> +	};
>   	int ret;
>   
>   	if (inline_data || nvme_tcp_queue_more(queue))
> -		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
> -	else
> -		flags |= MSG_EOR;
> +		msg.msg_flags |= MSG_MORE;
> +	else if (!test_bit(NVME_TCP_Q_TLS, &queue->flags))
> +		msg.msg_flags |= MSG_EOR;
>   
>   	if (queue->hdr_digest && !req->offset)
>   		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
>   
> -	ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
> -			offset_in_page(pdu) + req->offset, len,  flags);
> +	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);

I'd prefer to do kernel_sednpage/sock_no_sendpage similar to how we do
it for data and data pdu.

>   	if (unlikely(ret <= 0))
>   		return ret;
>   
> @@ -1131,7 +1140,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
>   	if (queue->hdr_digest && !req->offset)
>   		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
>   
> -	if (!req->h2cdata_left)
> +	if (!test_bit(NVME_TCP_Q_TLS, &queue->flags) && !req->h2cdata_left)
>   		ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
>   				offset_in_page(pdu) + req->offset, len,
>   				MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST);

Something is unclear to me. Is kernel_sendpage unsupported with tls? (I
think it is). I understand the motivation to add more checks in the code
for kernel_sendpage vs. sock_no_sendpage given that it should be
perfectly fine to use either.

Did you see any regressions with using kernel_sendpage? If so, isn't
that a bug in the tls code?