From b5bdacf3bb027ba0af4d61b38ec289bfc8b64372 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 4 Jan 2016 09:09:27 -0800 Subject: net: Propagate lookup failure in l3mdev_get_saddr to caller Commands run in a vrf context are not failing as expected on a route lookup: root@kenny:~# ip ro ls table vrf-red unreachable default root@kenny:~# ping -I vrf-red -c1 -w1 10.100.1.254 ping: Warning: source address might be selected on device other than vrf-red. PING 10.100.1.254 (10.100.1.254) from 0.0.0.0 vrf-red: 56(84) bytes of data. --- 10.100.1.254 ping statistics --- 2 packets transmitted, 0 received, 100% packet loss, time 999ms Since the vrf table does not have a route for 10.100.1.254 the ping should have failed. The saddr lookup causes a full VRF table lookup. Propogating a lookup failure to the user allows the command to fail as expected: root@kenny:~# ping -I vrf-red -c1 -w1 10.100.1.254 connect: No route to host Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/raw.c | 7 +++++-- net/ipv4/udp.c | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 63e5be0abd86..bc35f1842512 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -601,8 +601,11 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); - if (!saddr && ipc.oif) - l3mdev_get_saddr(net, ipc.oif, &fl4); + if (!saddr && ipc.oif) { + err = l3mdev_get_saddr(net, ipc.oif, &fl4); + if (err < 0) + goto done; + } if (!inet->hdrincl) { rfv.msg = msg; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0c7b0e61b917..c43890848641 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1025,8 +1025,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flow_flags, faddr, saddr, dport, inet->inet_sport); - if (!saddr && ipc.oif) - l3mdev_get_saddr(net, ipc.oif, fl4); + if (!saddr && ipc.oif) { + err = l3mdev_get_saddr(net, ipc.oif, fl4); + if (err < 0) + goto out; + } security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); -- cgit v1.2.2 From 8b8a321ff72c785ed5e8b4cf6eda20b35d427390 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 6 Jan 2016 12:42:38 -0800 Subject: tcp: fix zero cwnd in tcp_cwnd_reduction Patch 3759824da87b ("tcp: PRR uses CRB mode by default and SS mode conditionally") introduced a bug that cwnd may become 0 when both inflight and sndcnt are 0 (cwnd = inflight + sndcnt). This may lead to a div-by-zero if the connection starts another cwnd reduction phase by setting tp->prior_cwnd to the current cwnd (0) in tcp_init_cwnd_reduction(). To prevent this we skip PRR operation when nothing is acked or sacked. Then cwnd must be positive in all cases as long as ssthresh is positive: 1) The proportional reduction mode inflight > ssthresh > 0 2) The reduction bound mode a) inflight == ssthresh > 0 b) inflight < ssthresh sndcnt > 0 since newly_acked_sacked > 0 and inflight < ssthresh Therefore in all cases inflight and sndcnt can not both be 0. We check invalid tp->prior_cwnd to avoid potential div0 bugs. In reality this bug is triggered only with a sequence of less common events. For example, the connection is terminating an ECN-triggered cwnd reduction with an inflight 0, then it receives reordered/old ACKs or DSACKs from prior transmission (which acks nothing). Or the connection is in fast recovery stage that marks everything lost, but fails to retransmit due to local issues, then receives data packets from other end which acks nothing. Fixes: 3759824da87b ("tcp: PRR uses CRB mode by default and SS mode conditionally") Reported-by: Oleksandr Natalenko Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d656eef7f8e..d4c51158470f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2478,6 +2478,9 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, int newly_acked_sacked = prior_unsacked - (tp->packets_out - tp->sacked_out); + if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd)) + return; + tp->prr_delivered += newly_acked_sacked; if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + -- cgit v1.2.2