diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 1b5581a30d77..c7a81ace35d0 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -769,8 +769,21 @@ icmp_ratelimit - INTEGER 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. Significant bits: IHGFEDCBA9876543210 diff --git a/include/net/ip.h b/include/net/ip.h index 14bfc8e1bcf9..fcd9068fb8c3 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -548,6 +548,10 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, 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 diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ea7d4afe8205..5882f584910e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -231,12 +231,62 @@ static inline void icmp_xmit_unlock(struct sock *sk) 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; @@ -253,8 +303,14 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, 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) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1599966f4639..8a25509c35b3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -730,6 +730,22 @@ static struct ctl_table ipv4_table[] = { .extra1 = &zero, .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, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 394bb824fe4b..141e1f3ab74e 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -170,11 +170,11 @@ static bool is_ineligible(const struct sk_buff *skb) /* * 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. */ @@ -199,16 +199,20 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } 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;