tcp: add tcp_min_snd_mss sysctl

commit 5f3e2bf008c2221478101ee72f5cb4654b9fc363 upstream.

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>
Signed-off-by: David S. Miller <davem@davemloft.net>
[Salvatore Bonaccorso: Backport for context changes in 4.9.168]
[bwh: Backported to 3.16: Make the sysctl global, consistent with
 net.ipv4.tcp_base_mss]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 0df5824..5ec1ae9 100644 (file)
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -160,6 +160,14 @@ 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/tcp.h b/include/net/tcp.h
index 2ed5c18..fe95819 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -247,6 +247,7 @@ extern int sysctl_tcp_tso_win_divisor;
 extern int sysctl_tcp_abc;
 extern int sysctl_tcp_mtu_probing;
 extern int sysctl_tcp_base_mss;
+extern int sysctl_tcp_min_snd_mss;
 extern int sysctl_tcp_workaround_signed_windows;
 extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_max_ssthresh;

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 253dd80..41be2ad 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,8 @@ static int tcp_retr1_max = 255;
 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_min_snd_mss_min = TCP_MIN_SND_MSS;
+static int tcp_min_snd_mss_max = 65535;
 static int tcp_adv_win_scale_max = 31;
 static int ip_ttl_min = 1;
 static int ip_ttl_max = 255;
@@ -551,6 +553,15 @@ static struct ctl_table ipv4_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
+       {
+               .procname       = "tcp_min_snd_mss",
+               .data           = &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_workaround_signed_windows",
                .data           = &sysctl_tcp_workaround_signed_windows,

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cb1130c..a3a1ac5 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -56,6 +56,7 @@ int sysctl_tcp_tso_win_divisor __read_mostly = 3;
 
 int sysctl_tcp_mtu_probing __read_mostly = 0;
 int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
+int sysctl_tcp_min_snd_mss __read_mostly = TCP_MIN_SND_MSS;
 
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
@@ -1172,8 +1173,7 @@ int tcp_mtu_to_mss(const 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, sysctl_tcp_min_snd_mss);
 
        /* Now subtract TCP options size, not including SACKs */
        mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);