[PATCH v3] Allow UDP cmsghdrs through io_uring

[PATCH v3] Allow UDP cmsghdrs through io_uring

[Victor Stewart]

here we go, figured it out. sorry about that.

This patch adds PROTO_CMSG_DATA_ONLY to inet_dgram_ops and inet6_dgram_ops so that UDP_SEGMENT (GSO) and UDP_GRO can be used through io_uring.

GSO and GRO are vital to bring QUIC servers on par with TCP throughputs, and together offer a higher
throughput gain than io_uring alone (rate of data transit
considering), thus io_uring is presently the lesser performance choice.

RE http://vger.kernel.org/lpc_net2018_talks/willemdebruijn-lpc2018-udpgso-paper-DRAFT-1.pdf,
GSO is about +~63% and GRO +~82%.

this patch closes that loophole. 

net/ipv4/af_inet.c  | 1 +
net/ipv6/af_inet6.c | 1 +
net/socket.c        | 8 +++++---
3 files changed, 7 insertions(+), 3 deletions(-)

[PATCH v3] Allow UDP cmsghdrs through io_uring

[Victor Stewart]

---
 net/ipv4/af_inet.c  | 1 +
 net/ipv6/af_inet6.c | 1 +
 net/socket.c        | 8 +++++---
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b7260c8cef2e..c9fd5e7cfd6e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1052,6 +1052,7 @@ EXPORT_SYMBOL(inet_stream_ops);
 
 const struct proto_ops inet_dgram_ops = {
 	.family		   = PF_INET,
+	.flags		   = PROTO_CMSG_DATA_ONLY,
 	.owner		   = THIS_MODULE,
 	.release	   = inet_release,
 	.bind		   = inet_bind,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e648fbebb167..560f45009d06 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -695,6 +695,7 @@ const struct proto_ops inet6_stream_ops = {
 
 const struct proto_ops inet6_dgram_ops = {
 	.family		   = PF_INET6,
+	.flags		   = PROTO_CMSG_DATA_ONLY,
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
 	.bind		   = inet6_bind,
diff --git a/net/socket.c b/net/socket.c
index 6e6cccc2104f..6995835d6355 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2416,9 +2416,11 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg,
 			unsigned int flags)
 {
-	/* disallow ancillary data requests from this path */
-	if (msg->msg_control || msg->msg_controllen)
-		return -EINVAL;
+	if (msg->msg_control || msg->msg_controllen) {
+		/* disallow ancillary data reqs unless cmsg is plain data */
+		if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY))
+			return -EINVAL;
+	}
 
 	return ____sys_sendmsg(sock, msg, flags, NULL, 0);
 }
-- 
2.26.2

Re: [PATCH v3] Allow UDP cmsghdrs through io_uring

[Soheil Hassas Yeganeh]

On Sun, Dec 13, 2020 at 3:43 PM Victor Stewart <v@nametag.social> wrote:
>
> here we go, figured it out. sorry about that.
>
> This patch adds PROTO_CMSG_DATA_ONLY to inet_dgram_ops and inet6_dgram_ops so that UDP_SEGMENT (GSO) and UDP_GRO can be used through io_uring.

The v3 patch doesn't have "Signed-off-by". You can see all the checks
on patchwork:
https://patchwork.kernel.org/project/netdevbpf/patch/20201213204339.24445-2-v@nametag.social/

For patches to netdev, please include the target. Here it should be net-next:
https://www.kernel.org/doc/Documentation/networking/netdev-FAQ.txt
git format-patch --subject-prefix='PATCH net-next v4' ...

Also, since this patch affects udp, it's preferred to include "udp: "
in your commit's subject line.  In other words, the v4 of this patch
should look like the following:

[PATCH net-next v2] udp: allow UDP cmsghdrs through io_uring

Thank you


> GSO and GRO are vital to bring QUIC servers on par with TCP throughputs, and together offer a higher
> throughput gain than io_uring alone (rate of data transit
> considering), thus io_uring is presently the lesser performance choice.
>
> RE http://vger.kernel.org/lpc_net2018_talks/willemdebruijn-lpc2018-udpgso-paper-DRAFT-1.pdf,
> GSO is about +~63% and GRO +~82%.
>
> this patch closes that loophole.
>
> net/ipv4/af_inet.c  | 1 +
> net/ipv6/af_inet6.c | 1 +
> net/socket.c        | 8 +++++---
> 3 files changed, 7 insertions(+), 3 deletions(-)
>
>