From 9ab1265d52314fce1b51e8665ea6dbc9ac1a027c Mon Sep 17 00:00:00 2001 From: Evan Nimmo Date: Tue, 2 Mar 2021 08:00:04 +1300 Subject: xfrm: Use actual socket sk instead of skb socket for xfrm_output_resume A situation can occur where the interface bound to the sk is different to the interface bound to the sk attached to the skb. The interface bound to the sk is the correct one however this information is lost inside xfrm_output2 and instead the sk on the skb is used in xfrm_output_resume instead. This assumes that the sk bound interface and the bound interface attached to the sk within the skb are the same which can lead to lookup failures inside ip_route_me_harder resulting in the packet being dropped. We have an l2tp v3 tunnel with ipsec protection. The tunnel is in the global VRF however we have an encapsulated dot1q tunnel interface that is within a different VRF. We also have a mangle rule that marks the packets causing them to be processed inside ip_route_me_harder. Prior to commit 31c70d5956fc ("l2tp: keep original skb ownership") this worked fine as the sk attached to the skb was changed from the dot1q encapsulated interface to the sk for the tunnel which meant the interface bound to the sk and the interface bound to the skb were identical. Commit 46d6c5ae953c ("netfilter: use actual socket sk rather than skb sk when routing harder") fixed some of these issues however a similar problem existed in the xfrm code. Fixes: 31c70d5956fc ("l2tp: keep original skb ownership") Signed-off-by: Evan Nimmo Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_output.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'net/xfrm/xfrm_output.c') diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a7ab19353313..b81ca117dac7 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -503,22 +503,22 @@ out: return err; } -int xfrm_output_resume(struct sk_buff *skb, int err) +int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err) { struct net *net = xs_net(skb_dst(skb)->xfrm); while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset_ct(skb); - err = skb_dst(skb)->ops->local_out(net, skb->sk, skb); + err = skb_dst(skb)->ops->local_out(net, sk, skb); if (unlikely(err != 1)) goto out; if (!skb_dst(skb)->xfrm) - return dst_output(net, skb->sk, skb); + return dst_output(net, sk, skb); err = nf_hook(skb_dst(skb)->ops->family, - NF_INET_POST_ROUTING, net, skb->sk, skb, + NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; @@ -534,7 +534,7 @@ EXPORT_SYMBOL_GPL(xfrm_output_resume); static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { - return xfrm_output_resume(skb, 1); + return xfrm_output_resume(sk, skb, 1); } static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) -- cgit v1.2.3 From 68dc022d04eb0fd60a540e242dcb11ec1bee07e2 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 19 Mar 2021 18:27:58 +0800 Subject: xfrm: BEET mode doesn't support fragments for inner packets BEET mode replaces the IP(6) Headers with new IP(6) Headers when sending packets. However, when it's a fragment before the replacement, currently kernel keeps the fragment flag and replace the address field then encaps it with ESP. It would cause in RX side the fragments to get reassembled before decapping with ESP, which is incorrect. In Xiumei's testing, these fragments went over an xfrm interface and got encapped with ESP in the device driver, and the traffic was broken. I don't have a good way to fix it, but only to warn this out in dmesg. Reported-by: Xiumei Mu Signed-off-by: Xin Long Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_output.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'net/xfrm/xfrm_output.c') diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index b81ca117dac7..e4cb0ff4dcf4 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -660,6 +660,12 @@ static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + if (x->outer_mode.encap == XFRM_MODE_BEET && + ip_is_fragment(ip_hdr(skb))) { + net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n"); + return -EAFNOSUPPORT; + } + err = xfrm4_tunnel_check_size(skb); if (err) return err; @@ -705,8 +711,15 @@ out: static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) + unsigned int ptr = 0; int err; + if (x->outer_mode.encap == XFRM_MODE_BEET && + ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) { + net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n"); + return -EAFNOSUPPORT; + } + err = xfrm6_tunnel_check_size(skb); if (err) return err; -- cgit v1.2.3