54502cca7f
To send frames on the tap interface, the UDP uses a fairly complicated two
level batching. First multiple frames are gathered into a single "message"
for the qemu stream socket, then multiple messages are send with
sendmmsg(). We now have tap_send_frames() which already deals with sending
a number of frames, including batching and handling partial sends. Use
that to considerably simplify things.
This does make a couple of behavioural changes:
* We used to split messages to keep them under 32kiB (except when a
single frame was longer than that). The comments claim this is
needed to stop qemu from closing the connection, but we don't have any
equivalent logic for TCP. I wasn't able to reproduce the problem with
this series, although it was apparently easy to reproduce earlier.
My suspicion is that there was never an inherent need to keep messages
small, however with larger messages (and default kernel buffer sizes)
the chances of needing more than one resend for partial send()s is
greatly increased. We used not to correctly handle that case of
multiple resends, but now we do.
* Previously when we got a partial send on UDP, we would resend the
remainder of the entire "message", including multiple frames. The
common code now only resends the remainder of a single frame, simply
dropping any frames which weren't even partially sent. This is what
TCP always did and is probably a better idea for UDP too.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
66 lines
1.9 KiB
C
66 lines
1.9 KiB
C
/* SPDX-License-Identifier: AGPL-3.0-or-later
|
|
* Copyright (c) 2021 Red Hat GmbH
|
|
* Author: Stefano Brivio <sbrivio@redhat.com>
|
|
*/
|
|
|
|
#ifndef UDP_H
|
|
#define UDP_H
|
|
|
|
#define UDP_TIMER_INTERVAL 1000 /* ms */
|
|
|
|
void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
|
|
const struct timespec *now);
|
|
int udp_tap_handler(struct ctx *c, int af, const void *addr,
|
|
const struct pool *p, const struct timespec *now);
|
|
void udp_sock_init(const struct ctx *c, int ns, sa_family_t af,
|
|
const void *addr, const char *ifname, in_port_t port);
|
|
int udp_init(struct ctx *c);
|
|
void udp_timer(struct ctx *c, const struct timespec *ts);
|
|
void udp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s,
|
|
const struct in_addr *ip_da);
|
|
|
|
/**
|
|
* union udp_epoll_ref - epoll reference portion for TCP connections
|
|
* @bound: Set if this file descriptor is a bound socket
|
|
* @splice: Set if descriptor packets to be "spliced"
|
|
* @orig: Set if a spliced socket which can originate "connections"
|
|
* @ns: Set if this is a socket in the pasta network namespace
|
|
* @v6: Set for IPv6 sockets or connections
|
|
* @port: Source port for connected sockets, bound port otherwise
|
|
* @u32: Opaque u32 value of reference
|
|
*/
|
|
union udp_epoll_ref {
|
|
struct {
|
|
bool splice:1,
|
|
orig:1,
|
|
ns:1,
|
|
v6:1;
|
|
uint32_t port:16;
|
|
} udp;
|
|
uint32_t u32;
|
|
};
|
|
|
|
|
|
/**
|
|
* udp_port_fwd - UDP specific port forwarding configuration
|
|
* @f: Generic forwarding configuration
|
|
* @rdelta: Reversed delta map to translate source ports on return packets
|
|
*/
|
|
struct udp_port_fwd {
|
|
struct port_fwd f;
|
|
in_port_t rdelta[NUM_PORTS];
|
|
};
|
|
|
|
/**
|
|
* struct udp_ctx - Execution context for UDP
|
|
* @fwd_in: Port forwarding configuration for inbound packets
|
|
* @fwd_out: Port forwarding configuration for outbound packets
|
|
* @timer_run: Timestamp of most recent timer run
|
|
*/
|
|
struct udp_ctx {
|
|
struct udp_port_fwd fwd_in;
|
|
struct udp_port_fwd fwd_out;
|
|
struct timespec timer_run;
|
|
};
|
|
|
|
#endif /* UDP_H */
|