linux/net/ipv4/datagram.c
Guillaume Nault 67e1e2f485 ipv4: Avoid using RTO_ONLINK with ip_route_connect().
Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally,
we don't have to rely on the RTO_ONLINK bit to properly set the scope
of a flowi4 structure. We can just set ->flowi4_scope explicitly and
avoid using RTO_ONLINK in ->flowi4_tos.

This patch converts callers of ip_route_connect(). Instead of setting
the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can:

  1- Drop the tos parameter from ip_route_connect(): its value was
     entirely based on sk, which is also passed as parameter.

  2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option
     instead of always initialising it with RT_SCOPE_UNIVERSE (let's
     define ip_sock_rt_scope() for this purpose).

  3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is
     now properly initialised, we don't need to tell ip_rt_fix_tos() to
     adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(),
     which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK
     bit overload.

Note:
  In the original ip_route_connect() code, __ip_route_output_key()
  might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of
  ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the
  original tos variable. Now that we don't set RTO_ONLINK any more,
  this is not a problem and we can use fl4->flowi4_tos in
  flowi4_update_output().

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2022-04-22 13:06:03 +01:00

128 lines
3.0 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 = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
}
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(sk, true);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
inet->inet_id = prandom_u32();
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,
RT_CONN_FLAGS(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);