icmp: add a global rate limitation

Current ICMP rate limiting uses inetpeer cache, which is an RBL tree
protected by a lock, meaning that hosts can be stuck hard if all cpus
want to check ICMP limits.

When say a DNS or NTP server process is restarted, inetpeer tree grows
quick and machine comes to its knees.

iptables can not help because the bottleneck happens before ICMP
messages are even cooked and sent.

This patch adds a new global limitation, using a token bucket filter,
controlled by two new sysctl :

icmp_msgs_per_sec - INTEGER
Limit maximal number of ICMP packets sent per second from this host.
Only messages whose type matches icmp_ratemask are
controlled by this limit.
Default: 1000

icmp_msgs_burst - INTEGER
icmp_msgs_per_sec controls number of ICMP packets sent per second,
while icmp_msgs_burst controls the burst size of these packets.
Default: 50

Note that if we really want to send millions of ICMP messages per
second, we might extend idea and infra added in commit 04ca6973f7c1a
("ip: make IP identifiers less predictable") :
add a token bucket in the ip_idents hash and no longer rely on inetpeer.

Signed-off-by: Eric Dumazet <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/ip-sysctl.txt

···
 	icmp_ratemask (see below) to specific targets.
 	0 to disable any limiting,
 	otherwise the minimal space between responses in milliseconds.
+	Note that another sysctl, icmp_msgs_per_sec limits the number
+	of ICMP packets	sent on all targets.
 	Default: 1000
+
+icmp_msgs_per_sec - INTEGER
+	Limit maximal number of ICMP packets sent per second from this host.
+	Only messages whose type matches icmp_ratemask (see below) are
+	controlled by this limit.
+	Default: 1000
+
+icmp_msgs_burst - INTEGER
+	icmp_msgs_per_sec controls number of ICMP packets sent per second,
+	while icmp_msgs_burst controls the burst size of these packets.
+	Default: 50
 
 icmp_ratemask - INTEGER
 	Mask made of ICMP types for which rates are being limited.

include/net/ip.h

···
 void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 		    u32 info);
 
+bool icmp_global_allow(void);
+extern int sysctl_icmp_msgs_per_sec;
+extern int sysctl_icmp_msgs_burst;
+
 #ifdef CONFIG_PROC_FS
 int ip_misc_proc_init(void);
 #endif

net/ipv4/icmp.c

···
 	spin_unlock_bh(&sk->sk_lock.slock);
 }
 
+int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
+int sysctl_icmp_msgs_burst __read_mostly = 50;
+
+static struct {
+	spinlock_t	lock;
+	u32		credit;
+	u32		stamp;
+} icmp_global = {
+	.lock		= __SPIN_LOCK_UNLOCKED(icmp_global.lock),
+};
+
+/**
+ * icmp_global_allow - Are we allowed to send one more ICMP message ?
+ *
+ * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec.
+ * Returns false if we reached the limit and can not send another packet.
+ * Note: called with BH disabled
+ */
+bool icmp_global_allow(void)
+{
+	u32 credit, delta, incr = 0, now = (u32)jiffies;
+	bool rc = false;
+
+	/* Check if token bucket is empty and cannot be refilled
+	 * without taking the spinlock.
+	 */
+	if (!icmp_global.credit) {
+		delta = min_t(u32, now - icmp_global.stamp, HZ);
+		if (delta < HZ / 50)
+			return false;
+	}
+
+	spin_lock(&icmp_global.lock);
+	delta = min_t(u32, now - icmp_global.stamp, HZ);
+	if (delta >= HZ / 50) {
+		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+		if (incr)
+			icmp_global.stamp = now;
+	}
+	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+	if (credit) {
+		credit--;
+		rc = true;
+	}
+	icmp_global.credit = credit;
+	spin_unlock(&icmp_global.lock);
+	return rc;
+}
+EXPORT_SYMBOL(icmp_global_allow);
+
 /*
  *	Send an ICMP frame.
  */
 
-static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
-				      struct flowi4 *fl4, int type, int code)
+static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
+			       struct flowi4 *fl4, int type, int code)
 {
 	struct dst_entry *dst = &rt->dst;
 	bool rc = true;
···
 		goto out;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) {
-		struct inet_peer *peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
+	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+		goto out;
+
+	rc = false;
+	if (icmp_global_allow()) {
+		struct inet_peer *peer;
+
+		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
 		rc = inet_peer_xrlim_allow(peer,
 					   net->ipv4.sysctl_icmp_ratelimit);
 		if (peer)

net/ipv4/sysctl_net_ipv4.c

···
 		.extra2		= &one,
 	},
 	{
+		.procname	= "icmp_msgs_per_sec",
+		.data		= &sysctl_icmp_msgs_per_sec,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
+	{
+		.procname	= "icmp_msgs_burst",
+		.data		= &sysctl_icmp_msgs_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
+	{
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
 		.maxlen		= sizeof(sysctl_udp_mem),

net/ipv6/icmp.c

···
 /*
  * Check the ICMP output rate limit
  */
-static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
-				      struct flowi6 *fl6)
+static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+			       struct flowi6 *fl6)
 {
-	struct dst_entry *dst;
 	struct net *net = sock_net(sk);
+	struct dst_entry *dst;
 	bool res = false;
 
 	/* Informational messages are not limited. */
···
 	} else {
 		struct rt6_info *rt = (struct rt6_info *)dst;
 		int tmo = net->ipv6.sysctl.icmpv6_time;
-		struct inet_peer *peer;
 
 		/* Give more bandwidth to wider prefixes. */
 		if (rt->rt6i_dst.plen < 128)
 			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
 
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		res = inet_peer_xrlim_allow(peer, tmo);
-		if (peer)
-			inet_putpeer(peer);
+		if (icmp_global_allow()) {
+			struct inet_peer *peer;
+
+			peer = inet_getpeer_v6(net->ipv6.peers,
+					       &rt->rt6i_dst.addr, 1);
+			res = inet_peer_xrlim_allow(peer, tmo);
+			if (peer)
+				inet_putpeer(peer);
+		}
 	}
 	dst_release(dst);
 	return res;