| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20190617170354.37770-4-edumazet@google.com>
Date: Mon, 17 Jun 2019 10:03:53 -0700
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Jonathan Looney <jtl@...flix.com>,
Neal Cardwell <ncardwell@...gle.com>,
Tyler Hicks <tyhicks@...onical.com>,
Yuchung Cheng <ycheng@...gle.com>,
Bruce Curtis <brucec@...flix.com>,
Jonathan Lemon <jonathan.lemon@...il.com>
Subject: [PATCH net 3/4] 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@...gle.com>
Suggested-by: Jonathan Looney <jtl@...flix.com>
Acked-by: Neal Cardwell <ncardwell@...gle.com>
Cc: Yuchung Cheng <ycheng@...gle.com>
Cc: Tyler Hicks <tyhicks@...onical.com>
Cc: Bruce Curtis <brucec@...flix.com>
Cc: Jonathan Lemon <jonathan.lemon@...il.com>
---
Documentation/networking/ip-sysctl.txt | 8 ++++++++
include/net/netns/ipv4.h | 1 +
net/ipv4/sysctl_net_ipv4.c | 11 +++++++++++
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_output.c | 3 +--
5 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 288aa264ac26d98637a5bb1babc334bfc699bef1..22f6b8b1110ad20c36e7ceea6d67fd2cc938eb7b 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -255,6 +255,14 @@ 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 7698460a3dd1e5070e12d406b3ee58834688cdc9..623cfbb7b8dcbb2a6d8325ec010aff78bbdf8839 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -117,6 +117,7 @@ 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 fa213bd8e233b577114815ca2227f08264e7df06..b6f14af926faf80f1686549bee7154c584dc63e6 100644
--- 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;
@@ -769,6 +771,15 @@ 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 bc86f9735f4577d50d94f42b10edb6ba95bb7a05..cfa81190a1b1af30d05f4f6cd84c05b025a6afeb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2628,6 +2628,7 @@ 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 1bb1c46b4abad100622d3f101a0a3ca0a6c8e881..00c01a01b547ec67c971dc25a74c9258563cf871 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1459,8 +1459,7 @@ 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;
}
--
2.22.0.410.gd8fdbe21b5-goog
Powered by blists - more mailing lists