UBUNTU: SAUCE: tcp: add tcp_min_snd_mss sysctl

Some TCP peers announce a very small MSS option in their SYN and/or
SYN/ACK messages.

This forces the stack to send packets with a very high network/cpu
overhead.

Linux has enforced a minimal value of 48. Since this value includes
the size of TCP options, and that the options can consume up to 40
bytes, this means that each segment can include only 8 bytes of payload.

In some cases, it can be useful to increase the minimal value
to a saner value.

We still let the default to 48 (TCP_MIN_SND_MSS), for compatibility
reasons.

Note that TCP_MAXSEG socket option enforces a minimal value
of (TCP_MIN_MSS). David Miller increased this minimal value
in commit c39508d6f118 ("tcp: Make TCP_MAXSEG minimum more correct.")
from 64 to 88.

We might in the future merge TCP_MIN_SND_MSS and TCP_MIN_MSS.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Jonathan Looney <jtl@netflix.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Bruce Curtis <brucec@netflix.com>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
CVE-2019-11479

Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index acdfb5d2bcaa44a8a0ecdcfcae14202d1ed75bc3..6a1c95bb60dc8d1c728de78bcbefa50462d26a4b 100644 (file)
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -250,6 +250,14 @@ tcp_base_mss - INTEGER
        Path MTU discovery (MTU probing).  If MTU probing is enabled,
        this is the initial MSS used by the connection.
 
+tcp_min_snd_mss - INTEGER
+       TCP SYN and SYNACK messages usually advertise an ADVMSS option,
+       as described in RFC 1122 and RFC 6691.
+       If this ADVMSS option is smaller than tcp_min_snd_mss,
+       it is silently capped to tcp_min_snd_mss.
+
+       Default : 48 (at least 8 bytes of payload per segment)
+
 tcp_congestion_control - STRING
        Set the congestion control algorithm to be used for new
        connections. The algorithm "reno" is always available, but

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 104a6669e3445c1ac43fee5fba9060c565005b62..da22966724e0592587932dd71f37e8645d1d9696 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -116,6 +116,7 @@ struct netns_ipv4 {
 #endif
        int sysctl_tcp_mtu_probing;
        int sysctl_tcp_base_mss;
+       int sysctl_tcp_min_snd_mss;
        int sysctl_tcp_probe_threshold;
        u32 sysctl_tcp_probe_interval;
 

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ba0fc4b1846561559ac995a444992f98a3187894..b0da38f7487ae3df7981501947d99885c88cefca 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -39,6 +39,8 @@ static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
 static int tcp_adv_win_scale_min = -31;
 static int tcp_adv_win_scale_max = 31;
+static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS;
+static int tcp_min_snd_mss_max = 65535;
 static int ip_privileged_port_min;
 static int ip_privileged_port_max = 65535;
 static int ip_ttl_min = 1;
@@ -747,6 +749,15 @@ static struct ctl_table ipv4_net_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
+       {
+               .procname       = "tcp_min_snd_mss",
+               .data           = &init_net.ipv4.sysctl_tcp_min_snd_mss,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec_minmax,
+               .extra1         = &tcp_min_snd_mss_min,
+               .extra2         = &tcp_min_snd_mss_max,
+       },
        {
                .procname       = "tcp_probe_threshold",
                .data           = &init_net.ipv4.sysctl_tcp_probe_threshold,

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 00852f47a73d2610fa922d26fca2cfb521b29a95..d45db80dde19ba435abf2d8753325f3c987f00ad 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2615,6 +2615,7 @@ static int __net_init tcp_sk_init(struct net *net)
        net->ipv4.sysctl_tcp_ecn_fallback = 1;
 
        net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+       net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
        net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
        net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
 

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1284f013bfe0eadf15b0a064fc13a0922f9cd269..2a153cafa5108c6eed343a356e869507b68235f5 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1464,8 +1464,7 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
        mss_now -= icsk->icsk_ext_hdr_len;
 
        /* Then reserve room for full set of TCP options and 8 bytes of data */
-       if (mss_now < TCP_MIN_SND_MSS)
-               mss_now = TCP_MIN_SND_MSS;
+       mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
        return mss_now;
 }