linux/net/ipv4/datagram.c
Guillaume Nault a3522a2edb ipv4: Set the routing scope properly in ip_route_output_ports().
Set scope automatically in ip_route_output_ports() (using the socket
SOCK_LOCALROUTE flag). This way, callers don't have to overload the
tos with the RTO_ONLINK flag, like RT_CONN_FLAGS() does.

For callers that don't pass a struct sock, this doesn't change anything
as the scope is still set to RT_SCOPE_UNIVERSE when sk is NULL.

Callers that passed a struct sock and used RT_CONN_FLAGS(sk) or
RT_CONN_FLAGS_TOS(sk, tos) for the tos are modified to use
ip_sock_tos(sk) and RT_TOS(tos) respectively, as overloading tos with
the RTO_ONLINK flag now becomes unnecessary.

In drivers/net/amt.c, all ip_route_output_ports() calls use a 0 tos
parameter, ignoring the SOCK_LOCALROUTE flag of the socket. But the sk
parameter is a kernel socket, which doesn't have any configuration path
for setting SOCK_LOCALROUTE anyway. Therefore, ip_route_output_ports()
will continue to initialise scope with RT_SCOPE_UNIVERSE and amt.c
doesn't need to be modified.

Also, remove RT_CONN_FLAGS() and RT_CONN_FLAGS_TOS() from route.h as
these macros are now unused.

The objective is to eventually remove RTO_ONLINK entirely to allow
converting ->flowi4_tos to dscp_t. This will ensure proper isolation
between the DSCP and ECN bits, thus minimising the risk of introducing
bugs where TOS values interfere with ECN.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/dacfd2ab40685e20959ab7b53c427595ba229e7d.1707496938.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-12 17:33:05 -08:00

130 lines
3.1 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* common UDP/RAW code
* Linux INET implementation
*
* Authors:
* Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
*/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/in.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/route.h>
#include <net/tcp_states.h>
#include <net/sock_reuseport.h>
int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
struct flowi4 *fl4;
struct rtable *rt;
__be32 saddr;
int oif;
int err;
if (addr_len < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
sk_dst_reset(sk);
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
if (!oif || netif_index_is_l3_master(sock_net(sk), oif))
oif = READ_ONCE(inet->mc_index);
if (!saddr)
saddr = READ_ONCE(inet->mc_addr);
} else if (!oif) {
oif = READ_ONCE(inet->uc_index);
}
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, oif,
sk->sk_protocol, inet->inet_sport,
usin->sin_port, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
goto out;
}
if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) {
ip_rt_put(rt);
err = -EACCES;
goto out;
}
if (!inet->inet_saddr)
inet->inet_saddr = fl4->saddr; /* Update source address */
if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = fl4->saddr;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
inet->inet_daddr = fl4->daddr;
inet->inet_dport = usin->sin_port;
reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
atomic_set(&inet->inet_id, get_random_u16());
sk_dst_set(sk, &rt->dst);
err = 0;
out:
return err;
}
EXPORT_SYMBOL(__ip4_datagram_connect);
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
int res;
lock_sock(sk);
res = __ip4_datagram_connect(sk, uaddr, addr_len);
release_sock(sk);
return res;
}
EXPORT_SYMBOL(ip4_datagram_connect);
/* Because UDP xmit path can manipulate sk_dst_cache without holding
* socket lock, we need to use sk_dst_set() here,
* even if we own the socket lock.
*/
void ip4_datagram_release_cb(struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
struct dst_entry *dst;
struct flowi4 fl4;
struct rtable *rt;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
rcu_read_unlock();
return;
}
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
inet->inet_saddr, inet->inet_dport,
inet->inet_sport, sk->sk_protocol,
ip_sock_rt_tos(sk), sk->sk_bound_dev_if);
dst = !IS_ERR(rt) ? &rt->dst : NULL;
sk_dst_set(sk, dst);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);