Commit ae418e95 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'ipv4-consolidate-route-lookups-from-ipv4-sockets' 

Guillaume Nault says:

====================
ipv4: Consolidate route lookups from IPv4 sockets.

Create inet_sk_init_flowi4() so that the different IPv4 code paths that
need to do a route lookup based on an IPv4 socket don't need to
reimplement that logic.
====================

Link: https://patch.msgid.link/cover.1734357769.git.gnault@redhat.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 6ed34721 c63e9f3b

include/net/route.h

+28 −0
Original line number Diff line number Diff line
@@ -28,6 +28,7 @@ 
#include <net/arp.h>

#include <net/ndisc.h>

#include <net/inet_dscp.h>

#include <net/sock.h>

#include <linux/in_route.h>

#include <linux/rtnetlink.h>

#include <linux/rcupdate.h>
@@ -129,6 +130,33 @@ struct in_device; 
int ip_rt_init(void);

void rt_cache_flush(struct net *net);

void rt_flush_dev(struct net_device *dev);



static inline void inet_sk_init_flowi4(const struct inet_sock *inet,

				       struct flowi4 *fl4)

{

	const struct ip_options_rcu *ip4_opt;

	const struct sock *sk;

	__be32 daddr;



	rcu_read_lock();

	ip4_opt = rcu_dereference(inet->inet_opt);



	/* Source routing option overrides the socket destination address */

	if (ip4_opt && ip4_opt->opt.srr)

		daddr = ip4_opt->opt.faddr;

	else

		daddr = inet->inet_daddr;

	rcu_read_unlock();



	sk = &inet->sk;

	flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),

			   ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),

			   sk->sk_protocol, inet_sk_flowi_flags(sk), daddr,

			   inet->inet_saddr, inet->inet_dport,

			   inet->inet_sport, sk->sk_uid);

	security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));

}



struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,

					const struct sk_buff *skb);

struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,

net/ipv4/af_inet.c

+2 −12
Original line number Diff line number Diff line
@@ -1309,8 +1309,6 @@ int inet_sk_rebuild_header(struct sock *sk) 
{

	struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0));

	struct inet_sock *inet = inet_sk(sk);

	__be32 daddr;

	struct ip_options_rcu *inet_opt;

	struct flowi4 *fl4;

	int err;
@@ -1319,17 +1317,9 @@ int inet_sk_rebuild_header(struct sock *sk) 
		return 0;



	/* Reroute. */

	rcu_read_lock();

	inet_opt = rcu_dereference(inet->inet_opt);

	daddr = inet->inet_daddr;

	if (inet_opt && inet_opt->opt.srr)

		daddr = inet_opt->opt.faddr;

	rcu_read_unlock();

	fl4 = &inet->cork.fl.u.ip4;

	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);

	inet_sk_init_flowi4(inet, fl4);

	rt = ip_route_output_flow(sock_net(sk), fl4, sk);

	if (!IS_ERR(rt)) {

		err = 0;

		sk_setup_caps(sk, &rt->dst);

net/ipv4/datagram.c

+2 −9
Original line number Diff line number Diff line
@@ -102,8 +102,6 @@ EXPORT_SYMBOL(ip4_datagram_connect); 
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;
@@ -115,14 +113,9 @@ void ip4_datagram_release_cb(struct sock *sk) 
		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);



	inet_sk_init_flowi4(inet, &fl4);

	rt = ip_route_output_flow(sock_net(sk), &fl4, sk);

	dst = !IS_ERR(rt) ? &rt->dst : NULL;

	sk_dst_set(sk, dst);

net/ipv4/inet_connection_sock.c

+2 −9
Original line number Diff line number Diff line
@@ -1561,20 +1561,13 @@ EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); 
static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)

{

	const struct inet_sock *inet = inet_sk(sk);

	const struct ip_options_rcu *inet_opt;

	__be32 daddr = inet->inet_daddr;

	struct flowi4 *fl4;

	struct rtable *rt;



	rcu_read_lock();

	inet_opt = rcu_dereference(inet->inet_opt);

	if (inet_opt && inet_opt->opt.srr)

		daddr = inet_opt->opt.faddr;

	fl4 = &fl->u.ip4;

	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);

	inet_sk_init_flowi4(inet, fl4);

	rt = ip_route_output_flow(sock_net(sk), fl4, sk);

	if (IS_ERR(rt))

		rt = NULL;

	if (rt)

net/ipv4/ip_output.c

+4 −12
Original line number Diff line number Diff line
@@ -478,24 +478,16 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, 
	/* Make sure we can route this packet. */

	rt = dst_rtable(__sk_dst_check(sk, 0));

	if (!rt) {

		__be32 daddr;

		inet_sk_init_flowi4(inet, fl4);



		/* Use correct destination address if we have options. */

		daddr = inet->inet_daddr;

		if (inet_opt && inet_opt->opt.srr)

			daddr = inet_opt->opt.faddr;

		/* sctp_v4_xmit() uses its own DSCP value */

		fl4->flowi4_tos = tos & INET_DSCP_MASK;



		/* If this fails, retransmit mechanism of transport layer will

		 * keep trying until route appears or the connection times

		 * itself out.

		 */

		rt = ip_route_output_ports(net, fl4, sk,

					   daddr, inet->inet_saddr,

					   inet->inet_dport,

					   inet->inet_sport,

					   sk->sk_protocol,

					   tos & INET_DSCP_MASK,

					   sk->sk_bound_dev_if);

		rt = ip_route_output_flow(net, fl4, sk);

		if (IS_ERR(rt))

			goto no_route;

		sk_setup_caps(sk, &rt->dst);