[INET]: local port range robustness

Expansion of original idea from Denis V. Lunev <den@openvz.org>

Add robustness and locking to the local_port_range sysctl.
1. Enforce that low < high when setting.
2. Use seqlock to ensure atomic update.

The locking might seem like overkill, but there are
cases where sysadmin might want to change value in the
middle of a DoS attack.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 110 insertions, 30 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index fbe7714..3cef128 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -33,6 +33,19 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg);
  * This array holds the first and last local port number.
  */
 int sysctl_local_port_range[2] = { 32768, 61000 };
+DEFINE_SEQLOCK(sysctl_port_range_lock);
+
+void inet_get_local_port_range(int *low, int *high)
+{
+	unsigned seq;
+	do {
+		seq = read_seqbegin(&sysctl_port_range_lock);
+
+		*low = sysctl_local_port_range[0];
+		*high = sysctl_local_port_range[1];
+	} while (read_seqretry(&sysctl_port_range_lock, seq));
+}
+EXPORT_SYMBOL(inet_get_local_port_range);
 
 int inet_csk_bind_conflict(const struct sock *sk,
 			   const struct inet_bind_bucket *tb)
@@ -77,10 +90,11 @@ int inet_csk_get_port(struct inet_hashinfo *hashinfo,
 
 	local_bh_disable();
 	if (!snum) {
-		int low = sysctl_local_port_range[0];
-		int high = sysctl_local_port_range[1];
-		int remaining = (high - low) + 1;
-		int rover = net_random() % (high - low) + low;
+		int remaining, rover, low, high;
+
+		inet_get_local_port_range(&low, &high);
+		remaining = high - low;
+		rover = net_random() % remaining + low;
 
 		do {
 			head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index fb66262..fac6398 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -279,19 +279,18 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row,
 	int ret;
 
 	if (!snum) {
-		int low = sysctl_local_port_range[0];
-		int high = sysctl_local_port_range[1];
-		int range = high - low;
-		int i;
-		int port;
+		int i, remaining, low, high, port;
 		static u32 hint;
 		u32 offset = hint + inet_sk_port_offset(sk);
 		struct hlist_node *node;
 		struct inet_timewait_sock *tw = NULL;
 
+		inet_get_local_port_range(&low, &high);
+		remaining = high - low;
+
 		local_bh_disable();
-		for (i = 1; i <= range; i++) {
-			port = low + (i + offset) % range;
+		for (i = 1; i <= remaining; i++) {
+			port = low + (i + offset) % remaining;
 			head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)];
 			spin_lock(&head->lock);
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 53ef0f4..eb286ab 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -12,6 +12,7 @@
 #include <linux/sysctl.h>
 #include <linux/igmp.h>
 #include <linux/inetdevice.h>
+#include <linux/seqlock.h>
 #include <net/snmp.h>
 #include <net/icmp.h>
 #include <net/ip.h>
@@ -89,6 +90,74 @@ static int ipv4_sysctl_forward_strategy(ctl_table *table,
 	return 1;
 }
 
+extern seqlock_t sysctl_port_range_lock;
+extern int sysctl_local_port_range[2];
+
+/* Update system visible IP port range */
+static void set_local_port_range(int range[2])
+{
+	write_seqlock(&sysctl_port_range_lock);
+	sysctl_local_port_range[0] = range[0];
+	sysctl_local_port_range[1] = range[1];
+	write_sequnlock(&sysctl_port_range_lock);
+}
+
+/* Validate changes from /proc interface. */
+static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp,
+				 void __user *buffer,
+				 size_t *lenp, loff_t *ppos)
+{
+	int ret;
+	int range[2] = { sysctl_local_port_range[0],
+			 sysctl_local_port_range[1] };
+	ctl_table tmp = {
+		.data = &range,
+		.maxlen = sizeof(range),
+		.mode = table->mode,
+		.extra1 = &ip_local_port_range_min,
+		.extra2 = &ip_local_port_range_max,
+	};
+
+	ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos);
+
+	if (write && ret == 0) {
+		if (range[1] <= range[0])
+			ret = -EINVAL;
+		else
+			set_local_port_range(range);
+	}
+
+	return ret;
+}
+
+/* Validate changes from sysctl interface. */
+static int ipv4_sysctl_local_port_range(ctl_table *table, int __user *name,
+					 int nlen, void __user *oldval,
+					 size_t __user *oldlenp,
+					void __user *newval, size_t newlen)
+{
+	int ret;
+	int range[2] = { sysctl_local_port_range[0],
+			 sysctl_local_port_range[1] };
+	ctl_table tmp = {
+		.data = &range,
+		.maxlen = sizeof(range),
+		.mode = table->mode,
+		.extra1 = &ip_local_port_range_min,
+		.extra2 = &ip_local_port_range_max,
+	};
+
+	ret = sysctl_intvec(&tmp, name, nlen, oldval, oldlenp, newval, newlen);
+	if (ret == 0 && newval && newlen) {
+		if (range[1] <= range[0])
+			ret = -EINVAL;
+		else
+			set_local_port_range(range);
+	}
+	return ret;
+}
+
+
 static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp,
 				       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -427,10 +496,8 @@ ctl_table ipv4_table[] = {
 		.data		= &sysctl_local_port_range,
 		.maxlen		= sizeof(sysctl_local_port_range),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= ip_local_port_range_min,
-		.extra2		= ip_local_port_range_max
+		.proc_handler	= &ipv4_local_port_range,
+		.strategy	= &ipv4_sysctl_local_port_range,
 	},
 	{
 		.ctl_name	= NET_IPV4_ICMP_ECHO_IGNORE_ALL,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8855e64..38cf73a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2470,6 +2470,5 @@ EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
 EXPORT_SYMBOL(tcp_proc_register);
 EXPORT_SYMBOL(tcp_proc_unregister);
 #endif
-EXPORT_SYMBOL(sysctl_local_port_range);
 EXPORT_SYMBOL(sysctl_tcp_low_latency);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ef4d901..cb9fc58 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -147,11 +147,11 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 	write_lock_bh(&udp_hash_lock);
 
 	if (!snum) {
-		int i;
-		int low = sysctl_local_port_range[0];
-		int high = sysctl_local_port_range[1];
+		int i, low, high;
 		unsigned rover, best, best_size_so_far;
 
+		inet_get_local_port_range(&low, &high);
+
 		best_size_so_far = UINT_MAX;
 		best = rover = net_random() % (high - low) + low;
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index ae6b0e7..1c2c276 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -254,18 +254,18 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 	int ret;
 
 	if (snum == 0) {
-		const int low = sysctl_local_port_range[0];
-		const int high = sysctl_local_port_range[1];
-		const int range = high - low;
-		int i, port;
+		int i, port, low, high, remaining;
 		static u32 hint;
 		const u32 offset = hint + inet6_sk_port_offset(sk);
 		struct hlist_node *node;
 		struct inet_timewait_sock *tw = NULL;
 
+		inet_get_local_port_range(&low, &high);
+		remaining = high - low;
+
 		local_bh_disable();
-		for (i = 1; i <= range; i++) {
-			port = low + (i + offset) % range;
+		for (i = 1; i <= remaining; i++) {
+			port = low + (i + offset) % remaining;
 			head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)];
 			spin_lock(&head->lock);
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 7cd58ef..9c6a4b5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5315,11 +5315,12 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 
 	if (snum == 0) {
 		/* Search for an available port. */
-		unsigned int low = sysctl_local_port_range[0];
-		unsigned int high = sysctl_local_port_range[1];
-		unsigned int remaining = (high - low) + 1;
-		unsigned int rover = net_random() % remaining + low;
-		int index;
+		int low, high, remaining, index;
+		unsigned int rover;
+
+		inet_get_local_port_range(&low, &high);
+		remaining = (high - low) + 1;
+		rover = net_random() % remaining + low;
 
 		do {
 			rover++;