From c09be31461ed140976c60a87364415454a2c3d42 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 17 May 2019 17:17:22 -0700
Subject: [PATCH 1/5] tcp: limit payload size of sacked skbs
commit 3b4929f65b0d8249f19a50245cd88ed1a2f78cff upstream.
Jonathan Looney reported that TCP can trigger the following crash
in tcp_shifted_skb() :
BUG_ON(tcp_skb_pcount(skb) < pcount);
This can happen if the remote peer has advertized the smallest
MSS that linux TCP accepts : 48
An skb can hold 17 fragments, and each fragment can hold 32KB
on x86, or 64KB on PowerPC.
This means that the 16bit witdh of TCP_SKB_CB(skb)->tcp_gso_segs
can overflow.
Note that tcp_sendmsg() builds skbs with less than 64KB
of payload, so this problem needs SACK to be enabled.
SACK blocks allow TCP to coalesce multiple skbs in the retransmit
queue, thus filling the 17 fragments to maximal capacity.
CVE-2019-11477 -- u16 overflow of TCP_SKB_CB(skb)->tcp_gso_segs
Fixes: 832d11c5cd07 ("tcp: Try to restore large SKBs while SACK processing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jonathan Looney <jtl@netflix.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Tyler Hicks <tyhicks@canonical.com>
Cc: Yuchung Cheng <ycheng@google.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>
---
include/linux/tcp.h | 4 ++++
include/net/tcp.h | 2 ++
net/ipv4/tcp.c | 1 +
net/ipv4/tcp_input.c | 26 ++++++++++++++++++++------
net/ipv4/tcp_output.c | 6 +++---
5 files changed, 30 insertions(+), 9 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index d2c8f280e48f..4374196b98ea 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -485,4 +485,8 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
return (user_mss && user_mss < mss) ? user_mss : mss;
}
+
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
+ int shiftlen);
+
#endif /* _LINUX_TCP_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 770917d0caa7..e75661f92daa 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -55,6 +55,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
#define MAX_TCP_HEADER (128 + MAX_HEADER)
#define MAX_TCP_OPTION_SPACE 40
+#define TCP_MIN_SND_MSS 48
+#define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
/*
* Never offer a window over 32767 without using window scaling. Some
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 30c6e94b06c4..364e6fdaa38f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3829,6 +3829,7 @@ void __init tcp_init(void)
unsigned long limit;
unsigned int i;
+ BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
FIELD_SIZEOF(struct sk_buff, cb));
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cfdd70e32755..4a8869d39662 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1315,7 +1315,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
TCP_SKB_CB(skb)->seq += shifted;
tcp_skb_pcount_add(prev, pcount);
- BUG_ON(tcp_skb_pcount(skb) < pcount);
+ WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount);
tcp_skb_pcount_add(skb, -pcount);
/* When we're adding to gso_segs == 1, gso_size will be zero,
@@ -1381,6 +1381,21 @@ static int skb_can_shift(const struct sk_buff *skb)
return !skb_headlen(skb) && skb_is_nonlinear(skb);
}
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from,
+ int pcount, int shiftlen)
+{
+ /* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE)
+ * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need
+ * to make sure not storing more than 65535 * 8 bytes per skb,
+ * even if current MSS is bigger.
+ */
+ if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE))
+ return 0;
+ if (unlikely(tcp_skb_pcount(to) + pcount > 65535))
+ return 0;
+ return skb_shift(to, from, shiftlen);
+}
+
/* Try collapsing SACK blocks spanning across multiple skbs to a single
* skb.
*/
@@ -1486,7 +1501,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
goto fallback;
- if (!skb_shift(prev, skb, len))
+ if (!tcp_skb_shift(prev, skb, pcount, len))
goto fallback;
if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
goto out;
@@ -1504,11 +1519,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
goto out;
len = skb->len;
- if (skb_shift(prev, skb, len)) {
- pcount += tcp_skb_pcount(skb);
- tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
+ pcount = tcp_skb_pcount(skb);
+ if (tcp_skb_shift(prev, skb, pcount, len))
+ tcp_shifted_skb(sk, prev, skb, state, pcount,
len, mss, 0);
- }
out:
return prev;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bd134e3a0473..c8a29601a974 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1457,8 +1457,8 @@ 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 < 48)
- mss_now = 48;
+ if (mss_now < TCP_MIN_SND_MSS)
+ mss_now = TCP_MIN_SND_MSS;
return mss_now;
}
@@ -2727,7 +2727,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
if (next_skb_size <= skb_availroom(skb))
skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size),
next_skb_size);
- else if (!skb_shift(skb, next_skb, next_skb_size))
+ else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size))
return false;
}
tcp_highest_sack_replace(sk, next_skb, skb);
From ec83921899a571ad70d582934ee9e3e07f478848 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 18 May 2019 05:12:05 -0700
Subject: [PATCH 2/5] 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>
---
include/uapi/linux/snmp.h | 1 +
net/ipv4/proc.c | 1 +
net/ipv4/tcp_output.c | 5 +++++
3 files changed, 7 insertions(+)
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index f80135e5feaa..abae27c3001c 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -282,6 +282,7 @@ 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 70289682a670..eab5c02da8ae 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -290,6 +290,7 @@ 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 c8a29601a974..576379f0e6ad 100644
--- 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;
From 7f9f8a37e563c67b24ccd57da1d541a95538e8d9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Jun 2019 09:15:31 -0700
Subject: [PATCH 3/5] 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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
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 2c31208528d5..7eb9366422f5 100644
--- 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 622db6bc2f02..366e2a60010e 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -114,6 +114,7 @@ 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 ce64453d337d..ad132b6e8cfa 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;
@@ -737,6 +739,15 @@ 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 11101cf8693b..b76cf96d5cfe 100644
--- 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 576379f0e6ad..147ed82b73d3 100644
--- 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;
}
From 59222807fcc99951dc769cd50e132e319d73d699 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 8 Jun 2019 10:22:49 -0700
Subject: [PATCH 4/5] tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
commit 967c05aee439e6e5d7d805e195b3a20ef5c433d6 upstream.
If mtu probing is enabled tcp_mtu_probing() could very well end up
with a too small MSS.
Use the new sysctl tcp_min_snd_mss to make sure MSS search
is performed in an acceptable range.
CVE-2019-11479 -- tcp mss hardcoded to 48
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: 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>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/tcp_timer.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b1b5a648def6..17335a370e64 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -166,6 +166,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len);
+ mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss);
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
}
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
From 6500aa436df40a46998f7a56a32e8199a3513e6d Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 17 Jun 2019 19:51:57 +0200
Subject: [PATCH 5/5] Linux 4.19.52
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index dd4be2f32b88..c82ee02ad9be 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 19
-SUBLEVEL = 51
+SUBLEVEL = 52
EXTRAVERSION =
NAME = "People's Front"