From 6596a0229541270fb8d38d989f91b78838e5e9da Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Wed, 19 Jan 2022 10:22:53 +0100 Subject: xfrm: fix MTU regression Commit 749439bfac6e1a2932c582e2699f91d329658196 ("ipv6: fix udpv6 sendmsg crash caused by too small MTU") breaks PMTU for xfrm. A Packet Too Big ICMPv6 message received in response to an ESP packet will prevent all further communication through the tunnel if the reported MTU minus the ESP overhead is smaller than 1280. E.g. in a case of a tunnel-mode ESP with sha256/aes the overhead is 92 bytes. Receiving a PTB with MTU of 1371 or less will result in all further packets in the tunnel dropped. A ping through the tunnel fails with "ping: sendmsg: Invalid argument". Apparently the MTU on the xfrm route is smaller than 1280 and fails the check inside ip6_setup_cork() added by 749439bf. We found this by debugging USGv6/ipv6ready failures. Failing tests are: "Phase-2 Interoperability Test Scenario IPsec" / 5.3.11 and 5.4.11 (Tunnel Mode: Fragmentation). Commit b515d2637276a3810d6595e10ab02c13bfd0b63a ("xfrm: xfrm_state_mtu should return at least 1280 for ipv6") attempted to fix this but caused another regression in TCP MSS calculations and had to be reverted. The patch below fixes the situation by dropping the MTU check and instead checking for the underflows described in the 749439bf commit message. Signed-off-by: Jiri Bohac Fixes: 749439bfac6e ("ipv6: fix udpv6 sendmsg crash caused by too small MTU") Signed-off-by: Steffen Klassert --- net/ipv6/ip6_output.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'net/ipv6/ip6_output.c') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2995f8d89e7e..4ff110214dea 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1408,8 +1408,6 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (np->frag_size) mtu = np->frag_size; } - if (mtu < IPV6_MIN_MTU) - return -EINVAL; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; @@ -1471,8 +1469,6 @@ static int __ip6_append_data(struct sock *sk, fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - - sizeof(struct frag_hdr); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + @@ -1480,6 +1476,13 @@ static int __ip6_append_data(struct sock *sk, sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; + if (mtu < fragheaderlen || + ((mtu - fragheaderlen) & ~7) + fragheaderlen < sizeof(struct frag_hdr)) + goto emsgsize; + + maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - + sizeof(struct frag_hdr); + /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ -- cgit v1.2.3 From a1cdec57e03a1352e92fbbe7974039dda4efcec0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 17 Feb 2022 09:05:02 -0800 Subject: net-timestamp: convert sk->sk_tskey to atomic_t UDP sendmsg() can be lockless, this is causing all kinds of data races. This patch converts sk->sk_tskey to remove one of these races. BUG: KCSAN: data-race in __ip_append_data / __ip_append_data read to 0xffff8881035d4b6c of 4 bytes by task 8877 on cpu 1: __ip_append_data+0x1c1/0x1de0 net/ipv4/ip_output.c:994 ip_make_skb+0x13f/0x2d0 net/ipv4/ip_output.c:1636 udp_sendmsg+0x12bd/0x14c0 net/ipv4/udp.c:1249 inet_sendmsg+0x5f/0x80 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae write to 0xffff8881035d4b6c of 4 bytes by task 8880 on cpu 0: __ip_append_data+0x1d8/0x1de0 net/ipv4/ip_output.c:994 ip_make_skb+0x13f/0x2d0 net/ipv4/ip_output.c:1636 udp_sendmsg+0x12bd/0x14c0 net/ipv4/udp.c:1249 inet_sendmsg+0x5f/0x80 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000054d -> 0x0000054e Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 8880 Comm: syz-executor.5 Not tainted 5.17.0-rc2-syzkaller-00167-gdcb85f85fa6f-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 09c2d251b707 ("net-timestamp: add key to disambiguate concurrent datagrams") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/sock.h | 4 ++-- net/can/j1939/transport.c | 2 +- net/core/skbuff.c | 2 +- net/core/sock.c | 4 ++-- net/ipv4/ip_output.c | 2 +- net/ipv6/ip6_output.c | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'net/ipv6/ip6_output.c') diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..50aecd28b355 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -507,7 +507,7 @@ struct sock { #endif u16 sk_tsflags; u8 sk_shutdown; - u32 sk_tskey; + atomic_t sk_tskey; atomic_t sk_zckey; u8 sk_clockid; @@ -2667,7 +2667,7 @@ static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) - *tskey = sk->sk_tskey++; + *tskey = atomic_inc_return(&sk->sk_tskey) - 1; } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index a271688780a2..307ee1174a6e 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -2006,7 +2006,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, /* set the end-packet for broadcast */ session->pkt.last = session->pkt.total; - skcb->tskey = session->sk->sk_tskey++; + skcb->tskey = atomic_inc_return(&session->sk->sk_tskey) - 1; session->tskey = skcb->tskey; return session; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9d0388bed0c1..6a15ce3eb1d3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4730,7 +4730,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) - serr->ee.ee_data -= sk->sk_tskey; + serr->ee.ee_data -= atomic_read(&sk->sk_tskey); } err = sock_queue_err_skb(sk, skb); diff --git a/net/core/sock.c b/net/core/sock.c index 4ff806d71921..6eb174805bf0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -879,9 +879,9 @@ int sock_set_timestamping(struct sock *sk, int optname, if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; - sk->sk_tskey = tcp_sk(sk)->snd_una; + atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { - sk->sk_tskey = 0; + atomic_set(&sk->sk_tskey, 0); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 139cec29ed06..7911916a480b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -991,7 +991,7 @@ static int __ip_append_data(struct sock *sk, if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) - tskey = sk->sk_tskey++; + tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2995f8d89e7e..304a295de84f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1465,7 +1465,7 @@ static int __ip6_append_data(struct sock *sk, if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) - tskey = sk->sk_tskey++; + tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); -- cgit v1.2.3