Merge branch 'tcp-fixes'

Eric Dumazet says:

====================
tcp: make sack processing more robust

Jonathan Looney brought to our attention multiple problems
in TCP stack at the sender side.

SACK processing can be abused by malicious peers to either
cause overflows, or increase of memory usage.

First two patches fix the immediate problems.

Since the malicious peers abuse senders by advertizing a very
small MSS in their SYN or SYNACK packet, the last two
patches add a new sysctl so that admins can chose a higher
limit for MSS clamping.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

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

include/linux/tcp.h

@@ -484,4 +484,8 @@ 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 */

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;
 

include/net/tcp.h

@@ -51,6 +51,8 @@ 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

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
 };
 

net/ipv4/proc.c

@@ -287,6 +287,7 @@ 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
 };
 

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,

net/ipv4/tcp.c

@@ -3873,6 +3873,7 @@ 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));
 

net/ipv4/tcp_input.c

@@ -1302,7 +1302,7 @@ 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,
@@ -1368,6 +1368,21 @@ 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.
  */
@@ -1473,7 +1488,7 @@ 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;
@@ -1491,11 +1506,10 @@ 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;

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;
 

net/ipv4/tcp_output.c

@@ -1296,6 +1296,11 @@ 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;
 
@@ -1454,8 +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 < 48)
-		mss_now = 48;
+	mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
 	return mss_now;
 }
 
@@ -2747,7 +2751,7 @@ 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);

net/ipv4/tcp_timer.c

@@ -155,6 +155,7 @@ 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);