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 9de808ebce05f18c69962a681e541860ab457798..422183f396d557df8f936ed9dbb088b2ce3d8a8b 100644 (file)
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -281,6 +281,7 @@ enum
        LINUX_MIB_TCPKEEPALIVE,                 /* TCPKeepAlive */
        LINUX_MIB_TCPMTUPFAIL,                  /* TCPMTUPFail */
        LINUX_MIB_TCPMTUPSUCCESS,               /* TCPMTUPSuccess */
+       LINUX_MIB_TCPWQUEUETOOBIG,              /* TCPWqueueTooBig */
        __LINUX_MIB_MAX
 };
 

diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index b001ad6681084e2762ee56781afa6e495448409e..555586fc7840d76694f03e6c1c9deaf39cea334c 100644 (file)
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -303,6 +303,7 @@ static const struct snmp_mib snmp4_net_list[] = {
        SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
        SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL),
        SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS),
+       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 8ea892a9436459e782c430655d184cca408eca7c..abacd8a12b3e216fb5bc3fec61fbccd45d33a933 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1161,6 +1161,11 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
        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;