From 36d60eba862d6842d6da4d3792b3cf1cde1c22b2 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 1 Jul 2020 16:00:06 -0400 Subject: [PATCH] ip: Fix SO_MARK in RST, ACK and ICMP packets [ Upstream commit 0da7536fb47f51df89ccfcb1fa09f249d9accec5 ] When no full socket is available, skbs are sent over a per-netns control socket. Its sk_mark is temporarily adjusted to match that of the real (request or timewait) socket or to reflect an incoming skb, so that the outgoing skb inherits this in __ip_make_skb. Introduction of the socket cookie mark field broke this. Now the skb is set through the cookie and cork: # init sockc.mark from sk_mark or cmsg ip_append_data ip_setup_cork # convert sockc.mark to cork mark ip_push_pending_frames ip_finish_skb __ip_make_skb # set skb->mark to cork mark But I missed these special control sockets. Update all callers of __ip(6)_make_skb that were originally missed. For IPv6, the same two icmp(v6) paths are affected. The third case is not, as commit 92e55f412cff ("tcp: don't annotate mark on control socket from tcp_v6_send_response()") replaced the ctl_sk->sk_mark with passing the mark field directly as a function argument. That commit predates the commit that introduced the bug. Fixes: c6af0c227a22 ("ip: support SO_MARK cmsg") Signed-off-by: Willem de Bruijn Reported-by: Martin KaFai Lau Reviewed-by: Martin KaFai Lau Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/icmp.c | 4 ++-- net/ipv4/ip_output.c | 2 +- net/ipv6/icmp.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ac95ba78b903..73f46cb5e51d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; - sk->sk_mark = mark; + ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -709,10 +709,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; - sk->sk_mark = mark; ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; + ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b268ee1c1b44..b36c4a3159e5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1704,7 +1704,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_mark = fl4.flowi4_mark; + ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 62c997201970..7d3a3894f785 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -535,7 +535,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6)) @@ -552,6 +551,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.flowi6_oif = np->ucast_oif; ipcm6_init_sk(&ipc6, np); + ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); @@ -720,7 +720,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) @@ -748,6 +747,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + ipc6.sockc.mark = mark; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),