From 31ad3dd64e689bc79dd819f8f134b9b025240eb8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 4 Apr 2011 16:56:29 +0200 Subject: netfilter: af_info: add network namespace parameter to route hook This is required to eventually replace the rt6_lookup call in xt_addrtype.c with nf_afinfo->route(). Signed-off-by: Florian Westphal Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- net/ipv4/netfilter.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f3c0b549b8e1..f1035f056503 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -221,9 +221,10 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; } -static int nf_ip_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip_route(struct net *net, struct dst_entry **dst, + struct flowi *fl) { - struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4); + struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) return PTR_ERR(rt); *dst = &rt->dst; -- cgit v1.2.3-58-ga151 From 0fae2e7740aca7e384c5f337f458897e7e337d58 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 4 Apr 2011 17:00:54 +0200 Subject: netfilter: af_info: add 'strict' parameter to limit lookup to .oif ipv6 fib lookup can set RT6_LOOKUP_F_IFACE flag to restrict search to an interface, but this flag cannot be set via struct flowi. Also, it cannot be set via ip6_route_output: this function uses the passed sock struct to determine if this flag is required (by testing for nonzero sk_bound_dev_if). Work around this by passing in an artificial struct sk in case 'strict' argument is true. This is required to replace the rt6_lookup call in xt_addrtype.c with nf_afinfo->route(). Signed-off-by: Florian Westphal Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 2 +- net/ipv4/netfilter.c | 2 +- net/ipv6/netfilter.c | 12 ++++++++++-- net/netfilter/nf_conntrack_h323_main.c | 8 ++++---- net/netfilter/xt_TCPMSS.c | 2 +- 5 files changed, 17 insertions(+), 9 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 20ed4528e850..7fa95df60146 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -271,7 +271,7 @@ struct nf_afinfo { unsigned int len, u_int8_t protocol); int (*route)(struct net *net, struct dst_entry **dst, - struct flowi *fl); + struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f1035f056503..4614babdc45f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -222,7 +222,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, } static int nf_ip_route(struct net *net, struct dst_entry **dst, - struct flowi *fl) + struct flowi *fl, bool strict __always_unused) { struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index e008b9b4a779..28bc1f644b7b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -91,9 +91,17 @@ static int nf_ip6_reroute(struct sk_buff *skb, } static int nf_ip6_route(struct net *net, struct dst_entry **dst, - struct flowi *fl) + struct flowi *fl, bool strict) { - *dst = ip6_route_output(net, NULL, &fl->u.ip6); + static const struct ipv6_pinfo fake_pinfo; + static const struct inet_sock fake_sk = { + /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */ + .sk.sk_bound_dev_if = 1, + .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, + }; + const void *sk = strict ? &fake_sk : NULL; + + *dst = ip6_route_output(net, sk, &fl->u.ip6); return (*dst)->error; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 39a453895b4d..18b2ce5c8ced 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -732,9 +732,9 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); fl2.daddr = dst->ip; if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, - flowi4_to_flowi(&fl1))) { + flowi4_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, - flowi4_to_flowi(&fl2))) { + flowi4_to_flowi(&fl2), false)) { if (rt1->rt_gateway == rt2->rt_gateway && rt1->dst.dev == rt2->dst.dev) ret = 1; @@ -756,9 +756,9 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); ipv6_addr_copy(&fl2.daddr, &dst->in6); if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, - flowi6_to_flowi(&fl1))) { + flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, - flowi6_to_flowi(&fl2))) { + flowi6_to_flowi(&fl2), false)) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && rt1->dst.dev == rt2->dst.dev) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 8690125e3b18..9e63b43faeed 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_lock(); ai = nf_get_afinfo(family); if (ai != NULL) - ai->route(&init_net, (struct dst_entry **)&rt, &fl); + ai->route(&init_net, (struct dst_entry **)&rt, &fl, false); rcu_read_unlock(); if (rt != NULL) { -- cgit v1.2.3-58-ga151 From 1b86a58f9d7ce4fe2377687f378fbfb53bdc9b6c Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Thu, 7 Apr 2011 14:04:08 -0700 Subject: ipv4: Fix "Set rt->rt_iif more sanely on output routes." Commit 1018b5c01636c7c6bda31a719bda34fc631db29a ("Set rt->rt_iif more sanely on output routes.") breaks rt_is_{output,input}_route. This became the cause to return "IP_PKTINFO's ->ipi_ifindex == 0". To fix it, this does: 1) Add "int rt_route_iif;" to struct rtable 2) For input routes, always set rt_route_iif to same value as rt_iif 3) For output routes, always set rt_route_iif to zero. Set rt_iif as it is done currently. 4) Change rt_is_{output,input}_route() to test rt_route_iif Signed-off-by: OGAWA Hirofumi Signed-off-by: David S. Miller --- include/net/route.h | 5 +++-- net/ipv4/route.c | 8 ++++++-- net/ipv4/xfrm4_policy.c | 1 + 3 files changed, 10 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/route.h b/include/net/route.h index f88429cad52a..8fce0621cad1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -64,6 +64,7 @@ struct rtable { __be32 rt_dst; /* Path destination */ __be32 rt_src; /* Path source */ + int rt_route_iif; int rt_iif; int rt_oif; __u32 rt_mark; @@ -80,12 +81,12 @@ struct rtable { static inline bool rt_is_input_route(struct rtable *rt) { - return rt->rt_iif != 0; + return rt->rt_route_iif != 0; } static inline bool rt_is_output_route(struct rtable *rt) { - return rt->rt_iif == 0; + return rt->rt_route_iif == 0; } struct ip_rt_acct { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4b0c81180804..1628be530314 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1891,6 +1891,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; rth->dst.dev = init_net.loopback_dev; dev_hold(rth->dst.dev); @@ -2026,6 +2027,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_key_src = saddr; rth->rt_src = saddr; rth->rt_gateway = daddr; + rth->rt_route_iif = in_dev->dev->ifindex; rth->rt_iif = in_dev->dev->ifindex; rth->dst.dev = (out_dev)->dev; dev_hold(rth->dst.dev); @@ -2202,6 +2204,7 @@ local_input: #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; rth->dst.dev = net->loopback_dev; dev_hold(rth->dst.dev); @@ -2401,7 +2404,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_mark = oldflp4->flowi4_mark; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; - rth->rt_iif = 0; + rth->rt_route_iif = 0; + rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex; /* get references to the devices that are to be hold by the routing cache entry */ rth->dst.dev = dev_out; @@ -2716,6 +2720,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_key_dst = ort->rt_key_dst; rt->rt_key_src = ort->rt_key_src; rt->rt_tos = ort->rt_tos; + rt->rt_route_iif = ort->rt_route_iif; rt->rt_iif = ort->rt_iif; rt->rt_oif = ort->rt_oif; rt->rt_mark = ort->rt_mark; @@ -2725,7 +2730,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_dst = ort->rt_dst; rt->rt_src = ort->rt_src; - rt->rt_iif = ort->rt_iif; rt->rt_gateway = ort->rt_gateway; rt->rt_spec_dst = ort->rt_spec_dst; rt->peer = ort->peer; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 13e0e7f659ff..d20a05e970d8 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -74,6 +74,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, rt->rt_key_dst = fl4->daddr; rt->rt_key_src = fl4->saddr; rt->rt_tos = fl4->flowi4_tos; + rt->rt_route_iif = fl4->flowi4_iif; rt->rt_iif = fl4->flowi4_iif; rt->rt_oif = fl4->flowi4_oif; rt->rt_mark = fl4->flowi4_mark; -- cgit v1.2.3-58-ga151