1
0
Fork 0
mirror of https://passt.top/passt synced 2025-05-22 09:15:34 +02:00

udp: Handle "spliced" datagrams with per-flow sockets

When forwarding a datagram to a socket, we need to find a socket with a
suitable local address to send it.  Currently we keep track of such sockets
in an array indexed by local port, but this can't properly handle cases
where we have multiple local addresses in active use.

For "spliced" (socket to socket) cases, improve this by instead opening
a socket specifically for the target side of the flow.  We connect() as
well as bind()ing that socket, so that it will only receive the flow's
reply packets, not anything else.  We direct datagrams sent via that socket
using the addresses from the flow table, effectively replacing bespoke
addressing logic with the unified logic in fwd.c

When we create the flow, we also take a duplicate of the originating
socket, and use that to deliver reply datagrams back to the origin, again
using addresses from the flow table entry.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This commit is contained in:
David Gibson 2024-07-18 15:26:47 +10:00 committed by Stefano Brivio
parent a45a7e9798
commit e0647ad80c
9 changed files with 226 additions and 264 deletions

View file

@ -67,6 +67,7 @@ char *epoll_type_str[] = {
[EPOLL_TYPE_TCP_LISTEN] = "listening TCP socket",
[EPOLL_TYPE_TCP_TIMER] = "TCP timer",
[EPOLL_TYPE_UDP] = "UDP socket",
[EPOLL_TYPE_UDP_REPLY] = "UDP reply socket",
[EPOLL_TYPE_PING] = "ICMP/ICMPv6 ping socket",
[EPOLL_TYPE_NSQUIT_INOTIFY] = "namespace inotify watch",
[EPOLL_TYPE_NSQUIT_TIMER] = "namespace timer watch",
@ -349,6 +350,9 @@ loop:
case EPOLL_TYPE_UDP:
udp_buf_sock_handler(&c, ref, eventmask, &now);
break;
case EPOLL_TYPE_UDP_REPLY:
udp_reply_sock_handler(&c, ref, eventmask, &now);
break;
case EPOLL_TYPE_PING:
icmp_sock_handler(&c, ref);
break;