summaryrefslogtreecommitdiff
path: root/net/ipv4/icmp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/icmp.c')
-rw-r--r--net/ipv4/icmp.c258
1 files changed, 140 insertions, 118 deletions
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e63a3bf99617..717cb7d3607a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -92,6 +92,10 @@
#include <net/inet_common.h>
#include <net/ip_fib.h>
#include <net/l3mdev.h>
+#include <net/addrconf.h>
+#include <net/inet_dscp.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/icmp.h>
/*
* Build xmit assembly blocks
@@ -217,61 +221,56 @@ static inline void icmp_xmit_unlock(struct sock *sk)
spin_unlock(&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 ?
+ * @net: network namespace
*
* 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
+ * Works in tandem with icmp_global_consume().
*/
-bool icmp_global_allow(void)
+bool icmp_global_allow(struct net *net)
{
- u32 credit, delta, incr = 0, now = (u32)jiffies;
- bool rc = false;
+ u32 delta, now, oldstamp;
+ int incr, new, old;
- /* Check if token bucket is empty and cannot be refilled
- * without taking the spinlock. The READ_ONCE() are paired
- * with the following WRITE_ONCE() in this same function.
+ /* Note: many cpus could find this condition true.
+ * Then later icmp_global_consume() could consume more credits,
+ * this is an acceptable race.
*/
- if (!READ_ONCE(icmp_global.credit)) {
- delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ);
- if (delta < HZ / 50)
- return false;
- }
+ if (atomic_read(&net->ipv4.icmp_global_credit) > 0)
+ return true;
- spin_lock(&icmp_global.lock);
- delta = min_t(u32, now - icmp_global.stamp, HZ);
- if (delta >= HZ / 50) {
- incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
- if (incr)
- WRITE_ONCE(icmp_global.stamp, now);
- }
- credit = min_t(u32, icmp_global.credit + incr,
- READ_ONCE(sysctl_icmp_msgs_burst));
- if (credit) {
- /* We want to use a credit of one in average, but need to randomize
- * it for security reasons.
- */
- credit = max_t(int, credit - get_random_u32_below(3), 0);
- rc = true;
+ now = jiffies;
+ oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp);
+ delta = min_t(u32, now - oldstamp, HZ);
+ if (delta < HZ / 50)
+ return false;
+
+ incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec) * delta / HZ;
+ if (!incr)
+ return false;
+
+ if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) {
+ old = atomic_read(&net->ipv4.icmp_global_credit);
+ do {
+ new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst));
+ } while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new));
}
- WRITE_ONCE(icmp_global.credit, credit);
- spin_unlock(&icmp_global.lock);
- return rc;
+ return true;
}
EXPORT_SYMBOL(icmp_global_allow);
+void icmp_global_consume(struct net *net)
+{
+ int credits = get_random_u32_below(3);
+
+ /* Note: this might make icmp_global.credit negative. */
+ if (credits)
+ atomic_sub(credits, &net->ipv4.icmp_global_credit);
+}
+EXPORT_SYMBOL(icmp_global_consume);
+
static bool icmpv4_mask_allow(struct net *net, int type, int code)
{
if (type > NR_ICMP_TYPES)
@@ -288,14 +287,16 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
return false;
}
-static bool icmpv4_global_allow(struct net *net, int type, int code)
+static bool icmpv4_global_allow(struct net *net, int type, int code,
+ bool *apply_ratelimit)
{
if (icmpv4_mask_allow(net, type, code))
return true;
- if (icmp_global_allow())
+ if (icmp_global_allow(net)) {
+ *apply_ratelimit = true;
return true;
-
+ }
__ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
return false;
}
@@ -305,29 +306,31 @@ static bool icmpv4_global_allow(struct net *net, int type, int code)
*/
static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
- struct flowi4 *fl4, int type, int code)
+ struct flowi4 *fl4, int type, int code,
+ bool apply_ratelimit)
{
struct dst_entry *dst = &rt->dst;
struct inet_peer *peer;
bool rc = true;
- int vif;
- if (icmpv4_mask_allow(net, type, code))
- goto out;
+ if (!apply_ratelimit)
+ return true;
/* No rate limit on loopback */
if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
goto out;
- vif = l3mdev_master_ifindex(dst->dev);
- peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
+ rcu_read_lock();
+ peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr,
+ l3mdev_master_ifindex_rcu(dst->dev));
rc = inet_peer_xrlim_allow(peer,
READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
- if (peer)
- inet_putpeer(peer);
+ rcu_read_unlock();
out:
if (!rc)
__ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST);
+ else
+ icmp_global_consume(net);
return rc;
}
@@ -396,12 +399,12 @@ static void icmp_push_reply(struct sock *sk,
static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
{
- struct ipcm_cookie ipc;
struct rtable *rt = skb_rtable(skb);
- struct net *net = dev_net(rt->dst.dev);
+ struct net *net = dev_net_rcu(rt->dst.dev);
+ bool apply_ratelimit = false;
+ struct ipcm_cookie ipc;
struct flowi4 fl4;
struct sock *sk;
- struct inet_sock *inet;
__be32 daddr, saddr;
u32 mark = IP4_REPLY_MARK(net, skb->mark);
int type = icmp_param->data.icmph.type;
@@ -410,22 +413,21 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb))
return;
- /* Needed by both icmp_global_allow and icmp_xmit_lock */
+ /* Needed by both icmpv4_global_allow and icmp_xmit_lock */
local_bh_disable();
- /* global icmp_msgs_per_sec */
- if (!icmpv4_global_allow(net, type, code))
+ /* is global icmp_msgs_per_sec exhausted ? */
+ if (!icmpv4_global_allow(net, type, code, &apply_ratelimit))
goto out_bh_enable;
sk = icmp_xmit_lock(net);
if (!sk)
goto out_bh_enable;
- inet = inet_sk(sk);
icmp_param->data.icmph.checksum = 0;
ipcm_init(&ipc);
- inet->tos = ip_hdr(skb)->tos;
+ ipc.tos = ip_hdr(skb)->tos;
ipc.sockc.mark = mark;
daddr = ipc.addr = ip_hdr(skb)->saddr;
saddr = fib_compute_spec_dst(skb);
@@ -440,14 +442,14 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
fl4.saddr = saddr;
fl4.flowi4_mark = mark;
fl4.flowi4_uid = sock_net_uid(net, NULL);
- fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
+ fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(skb)));
fl4.flowi4_proto = IPPROTO_ICMP;
fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
goto out_unlock;
- if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
+ if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit))
icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt);
ip_rt_put(rt);
out_unlock:
@@ -473,15 +475,14 @@ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb)
return route_lookup_dev;
}
-static struct rtable *icmp_route_lookup(struct net *net,
- struct flowi4 *fl4,
+static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4,
struct sk_buff *skb_in,
- const struct iphdr *iph,
- __be32 saddr, u8 tos, u32 mark,
- int type, int code,
- struct icmp_bxm *param)
+ const struct iphdr *iph, __be32 saddr,
+ dscp_t dscp, u32 mark, int type,
+ int code, struct icmp_bxm *param)
{
struct net_device *route_lookup_dev;
+ struct dst_entry *dst, *dst2;
struct rtable *rt, *rt2;
struct flowi4 fl4_dec;
int err;
@@ -492,7 +493,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->saddr = saddr;
fl4->flowi4_mark = mark;
fl4->flowi4_uid = sock_net_uid(net, NULL);
- fl4->flowi4_tos = RT_TOS(tos);
+ fl4->flowi4_tos = inet_dscp_to_dsfield(dscp);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
fl4->fl4_icmp_code = code;
@@ -507,16 +508,20 @@ static struct rtable *icmp_route_lookup(struct net *net,
/* No need to clone since we're just using its address. */
rt2 = rt;
- rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
- flowi4_to_flowi(fl4), NULL, 0);
- if (!IS_ERR(rt)) {
+ dst = xfrm_lookup(net, &rt->dst,
+ flowi4_to_flowi(fl4), NULL, 0);
+ rt = dst_rtable(dst);
+ if (!IS_ERR(dst)) {
if (rt != rt2)
return rt;
- } else if (PTR_ERR(rt) == -EPERM) {
+ if (inet_addr_type_dev_table(net, route_lookup_dev,
+ fl4->daddr) == RTN_LOCAL)
+ return rt;
+ } else if (PTR_ERR(dst) == -EPERM) {
rt = NULL;
- } else
+ } else {
return rt;
-
+ }
err = xfrm_decode_session_reverse(net, skb_in, flowi4_to_flowi(&fl4_dec), AF_INET);
if (err)
goto relookup_failed;
@@ -540,7 +545,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
orefdst = skb_in->_skb_refdst; /* save old refdst */
skb_dst_set(skb_in, NULL);
err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr,
- RT_TOS(tos), rt2->dst.dev);
+ dscp, rt2->dst.dev) ? -EINVAL : 0;
dst_release(&rt2->dst);
rt2 = skb_rtable(skb_in);
@@ -550,19 +555,19 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst,
- flowi4_to_flowi(&fl4_dec), NULL,
- XFRM_LOOKUP_ICMP);
- if (!IS_ERR(rt2)) {
+ dst2 = xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL,
+ XFRM_LOOKUP_ICMP);
+ rt2 = dst_rtable(dst2);
+ if (!IS_ERR(dst2)) {
dst_release(&rt->dst);
memcpy(fl4, &fl4_dec, sizeof(*fl4));
rt = rt2;
- } else if (PTR_ERR(rt2) == -EPERM) {
+ } else if (PTR_ERR(dst2) == -EPERM) {
if (rt)
dst_release(&rt->dst);
return rt2;
} else {
- err = PTR_ERR(rt2);
+ err = PTR_ERR(dst2);
goto relookup_failed;
}
return rt;
@@ -591,6 +596,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
int room;
struct icmp_bxm icmp_param;
struct rtable *rt = skb_rtable(skb_in);
+ bool apply_ratelimit = false;
struct ipcm_cookie ipc;
struct flowi4 fl4;
__be32 saddr;
@@ -600,12 +606,14 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
struct sock *sk;
if (!rt)
- goto out;
+ return;
+
+ rcu_read_lock();
if (rt->dst.dev)
- net = dev_net(rt->dst.dev);
+ net = dev_net_rcu(rt->dst.dev);
else if (skb_in->dev)
- net = dev_net(skb_in->dev);
+ net = dev_net_rcu(skb_in->dev);
else
goto out;
@@ -672,7 +680,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
}
}
- /* Needed by both icmp_global_allow and icmp_xmit_lock */
+ /* Needed by both icmpv4_global_allow and icmp_xmit_lock */
local_bh_disable();
/* Check global sysctl_icmp_msgs_per_sec ratelimit, unless
@@ -680,7 +688,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
* loopback, then peer ratelimit still work (in icmpv4_xrlim_allow)
*/
if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) &&
- !icmpv4_global_allow(net, type, code))
+ !icmpv4_global_allow(net, type, code, &apply_ratelimit))
goto out_bh_enable;
sk = icmp_xmit_lock(net);
@@ -727,19 +735,20 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
icmp_param.data.icmph.checksum = 0;
icmp_param.skb = skb_in;
icmp_param.offset = skb_network_offset(skb_in);
- inet_sk(sk)->tos = tos;
ipcm_init(&ipc);
+ ipc.tos = tos;
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts.opt;
ipc.sockc.mark = mark;
- rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
- type, code, &icmp_param);
+ rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr,
+ inet_dsfield_to_dscp(tos), mark, type, code,
+ &icmp_param);
if (IS_ERR(rt))
goto out_unlock;
/* peer icmp_ratelimit */
- if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code))
+ if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit))
goto ende;
/* RFC says return as much as we can without exceeding 576 bytes. */
@@ -767,6 +776,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
if (!fl4.saddr)
fl4.saddr = htonl(INADDR_DUMMY);
+ trace_icmp_send(skb_in, type, code);
+
icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
@@ -774,7 +785,8 @@ out_unlock:
icmp_xmit_unlock(sk);
out_bh_enable:
local_bh_enable();
-out:;
+out:
+ rcu_read_unlock();
}
EXPORT_SYMBOL(__icmp_send);
@@ -823,7 +835,7 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
* avoid additional coding at protocol handlers.
*/
if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) {
- __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
+ __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS);
return;
}
@@ -857,7 +869,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
struct net *net;
u32 info = 0;
- net = dev_net(skb_dst(skb)->dev);
+ net = dev_net_rcu(skb_dst(skb)->dev);
/*
* Incomplete header ?
@@ -968,7 +980,7 @@ out_err:
static enum skb_drop_reason icmp_redirect(struct sk_buff *skb)
{
if (skb->len < sizeof(struct iphdr)) {
- __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
+ __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS);
return SKB_DROP_REASON_PKT_TOO_SMALL;
}
@@ -1000,7 +1012,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb)
struct icmp_bxm icmp_param;
struct net *net;
- net = dev_net(skb_dst(skb)->dev);
+ net = dev_net_rcu(skb_dst(skb)->dev);
/* should there be an ICMP stat for ignored echos? */
if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
return SKB_NOT_DROPPED_YET;
@@ -1029,9 +1041,11 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb)
bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
{
+ struct net *net = dev_net_rcu(skb->dev);
struct icmp_ext_hdr *ext_hdr, _ext_hdr;
struct icmp_ext_echo_iio *iio, _iio;
- struct net *net = dev_net(skb->dev);
+ struct inet6_dev *in6_dev;
+ struct in_device *in_dev;
struct net_device *dev;
char buff[IFNAMSIZ];
u16 ident_len;
@@ -1115,10 +1129,15 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
/* Fill bits in reply message */
if (dev->flags & IFF_UP)
status |= ICMP_EXT_ECHOREPLY_ACTIVE;
- if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list)
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev && rcu_access_pointer(in_dev->ifa_list))
status |= ICMP_EXT_ECHOREPLY_IPV4;
- if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list))
+
+ in6_dev = __in6_dev_get(dev);
+ if (in6_dev && !list_empty(&in6_dev->addr_list))
status |= ICMP_EXT_ECHOREPLY_IPV6;
+
dev_put(dev);
icmphdr->un.echo.sequence |= htons(status);
return true;
@@ -1163,7 +1182,7 @@ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb)
return SKB_NOT_DROPPED_YET;
out_err:
- __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
+ __ICMP_INC_STATS(dev_net_rcu(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
return SKB_DROP_REASON_PKT_TOO_SMALL;
}
@@ -1180,7 +1199,7 @@ int icmp_rcv(struct sk_buff *skb)
{
enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
struct rtable *rt = skb_rtable(skb);
- struct net *net = dev_net(rt->dst.dev);
+ struct net *net = dev_net_rcu(rt->dst.dev);
struct icmphdr *icmph;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
@@ -1229,22 +1248,6 @@ int icmp_rcv(struct sk_buff *skb)
goto reason_check;
}
- if (icmph->type == ICMP_EXT_ECHOREPLY) {
- reason = ping_rcv(skb);
- goto reason_check;
- }
-
- /*
- * 18 is the highest 'known' ICMP type. Anything else is a mystery
- *
- * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
- * discarded.
- */
- if (icmph->type > NR_ICMP_TYPES) {
- reason = SKB_DROP_REASON_UNHANDLED_PROTO;
- goto error;
- }
-
/*
* Parse the ICMP message
*/
@@ -1271,6 +1274,23 @@ int icmp_rcv(struct sk_buff *skb)
}
}
+ if (icmph->type == ICMP_EXT_ECHOREPLY ||
+ icmph->type == ICMP_ECHOREPLY) {
+ reason = ping_rcv(skb);
+ return reason ? NET_RX_DROP : NET_RX_SUCCESS;
+ }
+
+ /*
+ * 18 is the highest 'known' ICMP type. Anything else is a mystery
+ *
+ * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
+ * discarded.
+ */
+ if (icmph->type > NR_ICMP_TYPES) {
+ reason = SKB_DROP_REASON_UNHANDLED_PROTO;
+ goto error;
+ }
+
reason = icmp_pointers[icmph->type].handler(skb);
reason_check:
if (!reason) {
@@ -1353,9 +1373,9 @@ int icmp_err(struct sk_buff *skb, u32 info)
struct iphdr *iph = (struct iphdr *)skb->data;
int offset = iph->ihl<<2;
struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
+ struct net *net = dev_net_rcu(skb->dev);
int type = icmp_hdr(skb)->type;
int code = icmp_hdr(skb)->code;
- struct net *net = dev_net(skb->dev);
/*
* Use ping_err to handle all icmp errors except those
@@ -1473,6 +1493,8 @@ static int __net_init icmp_sk_init(struct net *net)
net->ipv4.sysctl_icmp_ratelimit = 1 * HZ;
net->ipv4.sysctl_icmp_ratemask = 0x1818;
net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;
+ net->ipv4.sysctl_icmp_msgs_per_sec = 1000;
+ net->ipv4.sysctl_icmp_msgs_burst = 50;
return 0;
}