From 45caeaa5ac0b4b11784ac6f932c0ad4c6b67cda0 Mon Sep 17 00:00:00 2001 From: Jon Maxwell Date: Fri, 10 Mar 2017 16:40:33 +1100 Subject: [PATCH] dccp/tcp: fix routing redirect race MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit As Eric Dumazet pointed out this also needs to be fixed in IPv6. v2: Contains the IPv6 tcp/Ipv6 dccp patches as well. We have seen a few incidents lately where a dst_enty has been freed with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that dst_entry. If the conditions/timings are right a crash then ensues when the freed dst_entry is referenced later on. A Common crashing back trace is: #8 [] page_fault at ffffffff8163e648 [exception RIP: __tcp_ack_snd_check+74] . . #9 [] tcp_rcv_established at ffffffff81580b64 #10 [] tcp_v4_do_rcv at ffffffff8158b54a #11 [] tcp_v4_rcv at ffffffff8158cd02 #12 [] ip_local_deliver_finish at ffffffff815668f4 #13 [] ip_local_deliver at ffffffff81566bd9 #14 [] ip_rcv_finish at ffffffff8156656d #15 [] ip_rcv at ffffffff81566f06 #16 [] __netif_receive_skb_core at ffffffff8152b3a2 #17 [] __netif_receive_skb at ffffffff8152b608 #18 [] netif_receive_skb at ffffffff8152b690 #19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3] #20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3] #21 [] net_rx_action at ffffffff8152bac2 #22 [] __do_softirq at ffffffff81084b4f #23 [] call_softirq at ffffffff8164845c #24 [] do_softirq at ffffffff81016fc5 #25 [] irq_exit at ffffffff81084ee5 #26 [] do_IRQ at ffffffff81648ff8 Of course it may happen with other NIC drivers as well. It's found the freed dst_entry here: 224 static bool tcp_in_quickack_mode(struct sock *sk)↩ 225 {↩ 226 ▹ const struct inet_connection_sock *icsk = inet_csk(sk);↩ 227 ▹ const struct dst_entry *dst = __sk_dst_get(sk);↩ 228 ↩ 229 ▹ return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩ 230 ▹ ▹ (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩ 231 }↩ But there are other backtraces attributed to the same freed dst_entry in netfilter code as well. All the vmcores showed 2 significant clues: - Remote hosts behind the default gateway had always been redirected to a different gateway. A rtable/dst_entry will be added for that host. Making more dst_entrys with lower reference counts. Making this more probable. - All vmcores showed a postitive LockDroppedIcmps value, e.g: LockDroppedIcmps 267 A closer look at the tcp_v4_err() handler revealed that do_redirect() will run regardless of whether user space has the socket locked. This can result in a race condition where the same dst_entry cached in sk->sk_dst_entry can be decremented twice for the same socket via: do_redirect()->__sk_dst_check()-> dst_release(). Which leads to the dst_entry being prematurely freed with another socket pointing to it via sk->sk_dst_cache and a subsequent crash. To fix this skip do_redirect() if usespace has the socket locked. Instead let the redirect take place later when user space does not have the socket locked. The dccp/IPv6 code is very similar in this respect, so fixing it there too. As Eric Garver pointed out the following commit now invalidates routes. Which can set the dst->obsolete flag so that ipv4_dst_check() returns null and triggers the dst_release(). Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.") Cc: Eric Garver Cc: Hannes Sowa Signed-off-by: Jon Maxwell Signed-off-by: David S. Miller --- net/dccp/ipv4.c | 3 ++- net/dccp/ipv6.c | 8 +++++--- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv6/tcp_ipv6.c | 8 +++++--- 4 files changed, 14 insertions(+), 8 deletions(-) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 409d0cfd3447..b99168b0fabf 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) switch (type) { case ICMP_REDIRECT: - dccp_do_redirect(skb, sk); + if (!sock_owned_by_user(sk)) + dccp_do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 233b57367758..d9b6a4e403e7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8f3ec1365497..575e19dcc017 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -431,7 +431,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) switch (type) { case ICMP_REDIRECT: - do_redirect(icmp_skb, sk); + if (!sock_owned_by_user(sk)) + do_redirect(icmp_skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 60a5295a7de6..49fa2e8c3fa9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -391,10 +391,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } -- 2.20.1