tcp: tcp_fragment() should apply sane memory limits

commit f070ef2ac66716357066b683fb0baf55f8191a2e upstream.

Jonathan Looney reported that a malicious peer can force a sender
to fragment its retransmit queue into tiny skbs, inflating memory
usage and/or overflow 32bit counters.

TCP allows an application to queue up to sk_sndbuf bytes,
so we need to give some allowance for non malicious splitting
of retransmit queue.

A new SNMP counter is added to monitor how many times TCP
did not allow to split an skb if the allowance was exceeded.

Note that this counter might increase in the case applications
use SO_SNDBUF socket option to lower sk_sndbuf.

CVE-2019-11478 : tcp_fragment, prevent fragmenting a packet when the
	socket is already using more than half the allowed space

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jonathan Looney <jtl@netflix.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: 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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 86dc24a96c90ab047d5173d625450facd6c6dd79..fd42c1316d3d112ecd8a00d2b499d6f6901c5e81 100644 (file)
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -283,6 +283,7 @@ enum
        LINUX_MIB_TCPACKCOMPRESSED,             /* TCPAckCompressed */
        LINUX_MIB_TCPZEROWINDOWDROP,            /* TCPZeroWindowDrop */
        LINUX_MIB_TCPRCVQDROP,                  /* TCPRcvQDrop */
+       LINUX_MIB_TCPWQUEUETOOBIG,              /* TCPWqueueTooBig */
        __LINUX_MIB_MAX
 };
 

diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index c3610b37bb4ce665b1976d8cc907b6dd0de42ab9..dff6755dc1a7c74ae4b2292581afc114f657b7b8 100644 (file)
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -291,6 +291,7 @@ static const struct snmp_mib snmp4_net_list[] = {
        SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
        SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP),
        SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP),
+       SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG),
        SNMP_MIB_SENTINEL
 };
 

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d0261761e41b139815e9585ce489431330c2161d..e1364478b9148ee44b585534e7d3a85efca4661e 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1299,6 +1299,11 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
        if (nsize < 0)
                nsize = 0;
 
+       if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf)) {
+               NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
+               return -ENOMEM;
+       }
+
        if (skb_unclone(skb, gfp))
                return -ENOMEM;