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.

CVE-2019-11479 -- tcp mss hardcoded to 48

Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Jonathan Looney <jtl@netflix.com>
Acked-by: 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>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Tyler Hicks <tyhicks@canonical.com>
Gbp-Pq: Topic bugfix/all
Gbp-Pq: Name tcp-add-tcp_min_snd_mss-sysctl.patch

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 960de8fe3f401c7ce4ceee0d5d3d61cb46102319..276b243a4c3b0af988e4b0845242945641b8dc1a 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 e47503b4e4d178e1ef334f4eb11378a9432bfbf8..42864bb84260b0013f9987f1d2599f9c5312a7de 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -113,6 +113,7 @@ 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 891ed2f91467b9345743682a3dd6e818acb48fbd..297016740a4126bc0a150fb5dbea4b1c859896b8 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;
@@ -736,6 +738,15 @@ 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 11101cf8693b1dc2fe898e8fef1c05b22dd1cc9d..b76cf96d5cfed973d1e9b8c45485857db8ab91a0 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2527,6 +2527,7 @@ 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 576379f0e6ada5eba2090a40f926e5a8d3308e49..147ed82b73d3ab64222945e73af9f4cd65626a1d 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1462,8 +1462,7 @@ 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;
 }