From bafd4bd4dcfa13145db7f951251eef3e10f8c278 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 9 Sep 2013 10:38:38 +0200 Subject: xfrm: Decode sessions with output interface. The output interface matching does not work on forward policy lookups, the output interface of the flowi is always 0. Fix this by setting the output interface when we decode the session. Signed-off-by: Steffen Klassert --- net/ipv6/xfrm6_policy.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6') diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 23ed03d786c8..08ed2772b7aa 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -138,6 +138,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; + fl6->flowi6_oif = skb_dst(skb)->dev->ifindex; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; -- cgit v1.2.3 From b3b2b9e192d5811f91f9cd92aeec489cecabc92e Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 10 Sep 2013 13:43:09 +0200 Subject: ipsec: Don't update the pmtu on ICMPV6_DEST_UNREACH Currently we update the pmtu in the IPsec protocol error handlers if icmpv6 message type is either ICMPV6_DEST_UNREACH or ICMPV6_PKT_TOOBIG. Updating the pmtu on ICMPV6_DEST_UNREACH is wrong in any case, it causes strangely fragmented packets. Only ICMPV6_PKT_TOOBIG signalizes pmtu discovery, so remove the ICMPV6_DEST_UNREACH check in the IPsec protocol error handlers. Signed-off-by: Steffen Klassert --- net/ipv6/ah6.c | 3 +-- net/ipv6/esp6.c | 3 +-- net/ipv6/ipcomp6.c | 3 +-- 3 files changed, 3 insertions(+), 6 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 73784c3d4642..82e1da3a40b9 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -618,8 +618,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index d3618a78fcac..e67e63f9858d 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -436,8 +436,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 5636a912074a..ce507d9e1c90 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -64,8 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; -- cgit v1.2.3 From bf58175954f2d390300df00f96070312d1b15096 Mon Sep 17 00:00:00 2001 From: Oussama Ghorbel Date: Thu, 10 Oct 2013 18:50:27 +0100 Subject: ipv6: Initialize ip6_tnl.hlen in gre tunnel even if no route is found The ip6_tnl.hlen (gre and ipv6 headers length) is independent from the outgoing interface, so it would be better to initialize it even when no route is found, otherwise its value will be zero. While I'm not sure if this could happen in real life, but doing that will avoid to call the skb_push function with a zero in ip6gre_header function. Suggested-by: Hannes Frederic Sowa Signed-off-by: Oussama Ghorbel Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 1ef1fa2b22a6..bf4a9a084de5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -976,6 +976,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) if (t->parms.o_flags&GRE_SEQ) addend += 4; } + t->hlen = addend; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & @@ -1002,8 +1003,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) } ip6_rt_put(rt); } - - t->hlen = addend; } static int ip6gre_tnl_change(struct ip6_tnl *t, -- cgit v1.2.3 From e36d3ff91130002c7c2d1d6a55556991da1daecc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 19 Oct 2013 12:29:15 +0200 Subject: udp6: respect IPV6_DONTFRAG sockopt in case there are pending frames if up->pending != 0 dontfrag is left with default value -1. That causes that application that do: sendto len>mtu flag MSG_MORE sendto len>mtu flag 0 will receive EMSGSIZE errno as the result of the second sendto. This patch fixes it by respecting IPV6_DONTFRAG socket option. introduced by: commit 4b340ae20d0e2366792abe70f46629e576adaf5e "IPv6: Complete IPV6_DONTFRAG support" Signed-off-by: Jiri Pirko Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/udp.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 72b7eaaf3ca0..18786098fd41 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1225,9 +1225,6 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; - if (dontfrag < 0) - dontfrag = np->dontfrag; - if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1246,6 +1243,8 @@ back_from_confirm: up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, -- cgit v1.2.3 From c547dbf55d5f8cf615ccc0e7265e98db27d3fb8b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 19 Oct 2013 12:29:16 +0200 Subject: ip6_output: do skb ufo init for peeked non ufo skb as well Now, if user application does: sendto lenmtu flag 0 The skb is not treated as fragmented one because it is not initialized that way. So move the initialization to fix this. introduced by: commit e89e9cf539a28df7d0eb1d0a545368e9920b34ac "[IPv4/IPv6]: UFO Scatter-gather approach" Signed-off-by: Jiri Pirko Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a54c45ce4a48..975624b8d2ea 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1008,6 +1008,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, { struct sk_buff *skb; + struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1015,8 +1016,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) { - struct frag_hdr fhdr; - skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); @@ -1036,20 +1035,24 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->transport_header = skb->network_header + fragheaderlen; skb->protocol = htons(ETH_P_IPV6); - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - /* Specify the length of each IPv6 datagram fragment. - * It has to be a multiple of 8. - */ - skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - - sizeof(struct frag_hdr)) & ~7; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); + } else if (skb_is_gso(skb)) { + goto append; } + skb->ip_summed = CHECKSUM_PARTIAL; + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + ipv6_select_ident(&fhdr, rt); + skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + +append: return skb_append_datato_frags(sk, skb, getfrag, from, (length - transhdrlen)); } -- cgit v1.2.3 From 550bab42f83308c9d6ab04a980cc4333cef1c8fa Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 20 Oct 2013 15:43:04 +0300 Subject: ipv6: fill rt6i_gateway with nexthop address Make sure rt6i_gateway contains nexthop information in all routes returned from lookup or when routes are directly attached to skb for generated ICMP packets. The effect of this patch should be a faster version of rt6_nexthop() and the consideration of local addresses as nexthop. Signed-off-by: Julian Anastasov Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 4 ++-- net/ipv6/route.c | 8 ++++++-- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 975624b8d2ea..91fb4e8212f5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -874,7 +874,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c979dd96d82a..c1ee3813e1ae 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -851,7 +851,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; @@ -1338,6 +1337,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1873,7 +1873,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) @@ -2160,6 +2163,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); -- cgit v1.2.3 From c2f17e827b419918c856131f592df9521e1a38e3 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 21 Oct 2013 06:17:15 +0200 Subject: ipv6: probe routes asynchronous in rt6_probe Routes need to be probed asynchronous otherwise the call stack gets exhausted when the kernel attemps to deliver another skb inline, like e.g. xt_TEE does, and we probe at the same time. We update neigh->updated still at once, otherwise we would send to many probes. Cc: Julian Anastasov Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/route.c | 38 +++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c1ee3813e1ae..f54e3a101098 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -476,6 +476,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -499,17 +517,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (neigh) { + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); -- cgit v1.2.3