1 files changed, 88 insertions, 102 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index b7e277d8a84d..d5d745c3e345 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -186,30 +186,20 @@ EXPORT_SYMBOL(icmp_err_convert);
  */
 
 struct icmp_control {
-	bool (*handler)(struct sk_buff *skb);
+	enum skb_drop_reason (*handler)(struct sk_buff *skb);
 	short   error;		/* This ICMP is classed as an error message */
 };
 
 static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
 
-/*
- *	The ICMP socket(s). This is the most convenient way to flow control
- *	our ICMP output as well as maintain a clean interface throughout
- *	all layers. All Socketless IP sends will soon be gone.
- *
- *	On SMP we have one ICMP socket per-cpu.
- */
-static struct sock *icmp_sk(struct net *net)
-{
-	return this_cpu_read(*net->ipv4.icmp_sk);
-}
+static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk);
 
 /* Called with BH disabled */
 static inline struct sock *icmp_xmit_lock(struct net *net)
 {
 	struct sock *sk;
 
-	sk = icmp_sk(net);
+	sk = this_cpu_read(ipv4_icmp_sk);
 
 	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
 		/* This can happen if the output path signals a
@@ -217,11 +207,13 @@ static inline struct sock *icmp_xmit_lock(struct net *net)
 		 */
 		return NULL;
 	}
+	sock_net_set(sk, net);
 	return sk;
 }
 
 static inline void icmp_xmit_unlock(struct sock *sk)
 {
+	sock_net_set(sk, &init_net);
 	spin_unlock(&sk->sk_lock.slock);
 }
 
@@ -261,11 +253,12 @@ bool icmp_global_allow(void)
 	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 ;
+		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, sysctl_icmp_msgs_burst);
+	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.
@@ -289,7 +282,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
 		return true;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+	if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
 		return true;
 
 	return false;
@@ -327,7 +320,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 
 	vif = l3mdev_master_ifindex(dst->dev);
 	peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
-	rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+	rc = inet_peer_xrlim_allow(peer,
+				   READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
 	if (peer)
 		inet_putpeer(peer);
 out:
@@ -350,7 +344,7 @@ void icmp_out_count(struct net *net, unsigned char type)
 static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
 			  struct sk_buff *skb)
 {
-	struct icmp_bxm *icmp_param = (struct icmp_bxm *)from;
+	struct icmp_bxm *icmp_param = from;
 	__wsum csum;
 
 	csum = skb_copy_and_csum_bits(icmp_param->skb,
@@ -363,14 +357,13 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
 	return 0;
 }
 
-static void icmp_push_reply(struct icmp_bxm *icmp_param,
+static void icmp_push_reply(struct sock *sk,
+			    struct icmp_bxm *icmp_param,
 			    struct flowi4 *fl4,
 			    struct ipcm_cookie *ipc, struct rtable **rt)
 {
-	struct sock *sk;
 	struct sk_buff *skb;
 
-	sk = icmp_sk(dev_net((*rt)->dst.dev));
 	if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param,
 			   icmp_param->data_len+icmp_param->head_len,
 			   icmp_param->head_len,
@@ -452,7 +445,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	if (IS_ERR(rt))
 		goto out_unlock;
 	if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
-		icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
+		icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt);
 	ip_rt_put(rt);
 out_unlock:
 	icmp_xmit_unlock(sk);
@@ -701,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 
 		rcu_read_lock();
 		if (rt_is_input_route(rt) &&
-		    net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
+		    READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr))
 			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
 
 		if (dev)
@@ -766,7 +759,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	if (!fl4.saddr)
 		fl4.saddr = htonl(INADDR_DUMMY);
 
-	icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
+	icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt);
 ende:
 	ip_rt_put(rt);
 out_unlock:
@@ -848,8 +841,9 @@ static bool icmp_tag_validation(int proto)
  *	ICMP_PARAMETERPROB.
  */
 
-static bool icmp_unreach(struct sk_buff *skb)
+static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
 {
+	enum skb_drop_reason reason = SKB_NOT_DROPPED_YET;
 	const struct iphdr *iph;
 	struct icmphdr *icmph;
 	struct net *net;
@@ -869,8 +863,10 @@ static bool icmp_unreach(struct sk_buff *skb)
 	icmph = icmp_hdr(skb);
 	iph   = (const struct iphdr *)skb->data;
 
-	if (iph->ihl < 5) /* Mangled header, drop. */
+	if (iph->ihl < 5)  { /* Mangled header, drop. */
+		reason = SKB_DROP_REASON_IP_INHDR;
 		goto out_err;
+	}
 
 	switch (icmph->type) {
 	case ICMP_DEST_UNREACH:
@@ -885,7 +881,7 @@ static bool icmp_unreach(struct sk_buff *skb)
 			 * values please see
 			 * Documentation/networking/ip-sysctl.rst
 			 */
-			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
+			switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) {
 			default:
 				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
 						    &iph->daddr);
@@ -938,7 +934,7 @@ static bool icmp_unreach(struct sk_buff *skb)
 	 *	get the other vendor to fix their kit.
 	 */
 
-	if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
+	if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) &&
 	    inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) {
 		net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n",
 				     &ip_hdr(skb)->saddr,
@@ -950,10 +946,10 @@ static bool icmp_unreach(struct sk_buff *skb)
 	icmp_socket_deliver(skb, info);
 
 out:
-	return true;
+	return reason;
 out_err:
 	__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-	return false;
+	return reason ?: SKB_DROP_REASON_NOT_SPECIFIED;
 }
 
 
@@ -961,20 +957,20 @@ out_err:
  *	Handle ICMP_REDIRECT.
  */
 
-static bool icmp_redirect(struct sk_buff *skb)
+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);
-		return false;
+		return SKB_DROP_REASON_PKT_TOO_SMALL;
 	}
 
 	if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
 		/* there aught to be a stat */
-		return false;
+		return SKB_DROP_REASON_NOMEM;
 	}
 
 	icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway));
-	return true;
+	return SKB_NOT_DROPPED_YET;
 }
 
 /*
@@ -991,15 +987,15 @@ static bool icmp_redirect(struct sk_buff *skb)
  *	See also WRT handling of options once they are done and working.
  */
 
-static bool icmp_echo(struct sk_buff *skb)
+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);
 	/* should there be an ICMP stat for ignored echos? */
-	if (net->ipv4.sysctl_icmp_echo_ignore_all)
-		return true;
+	if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
+		return SKB_NOT_DROPPED_YET;
 
 	icmp_param.data.icmph	   = *icmp_hdr(skb);
 	icmp_param.skb		   = skb;
@@ -1010,10 +1006,10 @@ static bool icmp_echo(struct sk_buff *skb)
 	if (icmp_param.data.icmph.type == ICMP_ECHO)
 		icmp_param.data.icmph.type = ICMP_ECHOREPLY;
 	else if (!icmp_build_probe(skb, &icmp_param.data.icmph))
-		return true;
+		return SKB_NOT_DROPPED_YET;
 
 	icmp_reply(&icmp_param, skb);
-	return true;
+	return SKB_NOT_DROPPED_YET;
 }
 
 /*	Helper for icmp_echo and icmpv6_echo_reply.
@@ -1033,7 +1029,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
 	u16 ident_len;
 	u8 status;
 
-	if (!net->ipv4.sysctl_icmp_echo_enable_probe)
+	if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
 		return false;
 
 	/* We currently only support probing interfaces on the proxy node
@@ -1131,7 +1127,7 @@ EXPORT_SYMBOL_GPL(icmp_build_probe);
  *		  MUST be accurate to a few minutes.
  *		  MUST be updated at least at 15Hz.
  */
-static bool icmp_timestamp(struct sk_buff *skb)
+static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb)
 {
 	struct icmp_bxm icmp_param;
 	/*
@@ -1156,17 +1152,17 @@ static bool icmp_timestamp(struct sk_buff *skb)
 	icmp_param.data_len	   = 0;
 	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
 	icmp_reply(&icmp_param, skb);
-	return true;
+	return SKB_NOT_DROPPED_YET;
 
 out_err:
 	__ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
-	return false;
+	return SKB_DROP_REASON_PKT_TOO_SMALL;
 }
 
-static bool icmp_discard(struct sk_buff *skb)
+static enum skb_drop_reason icmp_discard(struct sk_buff *skb)
 {
 	/* pretend it was a success */
-	return true;
+	return SKB_NOT_DROPPED_YET;
 }
 
 /*
@@ -1174,18 +1170,20 @@ static bool icmp_discard(struct sk_buff *skb)
  */
 int icmp_rcv(struct sk_buff *skb)
 {
-	struct icmphdr *icmph;
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = dev_net(rt->dst.dev);
-	bool success;
+	struct icmphdr *icmph;
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
 		int nh;
 
 		if (!(sp && sp->xvec[sp->len - 1]->props.flags &
-				 XFRM_STATE_ICMP))
+				 XFRM_STATE_ICMP)) {
+			reason = SKB_DROP_REASON_XFRM_POLICY;
 			goto drop;
+		}
 
 		if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr)))
 			goto drop;
@@ -1193,8 +1191,11 @@ int icmp_rcv(struct sk_buff *skb)
 		nh = skb_network_offset(skb);
 		skb_set_network_header(skb, sizeof(*icmph));
 
-		if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
+		if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN,
+						skb)) {
+			reason = SKB_DROP_REASON_XFRM_POLICY;
 			goto drop;
+		}
 
 		skb_set_network_header(skb, nh);
 	}
@@ -1216,13 +1217,13 @@ int icmp_rcv(struct sk_buff *skb)
 		/* We can't use icmp_pointers[].handler() because it is an array of
 		 * size NR_ICMP_TYPES + 1 (19 elements) and PROBE has code 42.
 		 */
-		success = icmp_echo(skb);
-		goto success_check;
+		reason = icmp_echo(skb);
+		goto reason_check;
 	}
 
 	if (icmph->type == ICMP_EXT_ECHOREPLY) {
-		success = ping_rcv(skb);
-		goto success_check;
+		reason = ping_rcv(skb);
+		goto reason_check;
 	}
 
 	/*
@@ -1231,8 +1232,10 @@ int icmp_rcv(struct sk_buff *skb)
 	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
 	 *		  discarded.
 	 */
-	if (icmph->type > NR_ICMP_TYPES)
+	if (icmph->type > NR_ICMP_TYPES) {
+		reason = SKB_DROP_REASON_UNHANDLED_PROTO;
 		goto error;
+	}
 
 	/*
 	 *	Parse the ICMP message
@@ -1247,28 +1250,31 @@ int icmp_rcv(struct sk_buff *skb)
 		 */
 		if ((icmph->type == ICMP_ECHO ||
 		     icmph->type == ICMP_TIMESTAMP) &&
-		    net->ipv4.sysctl_icmp_echo_ignore_broadcasts) {
+		    READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) {
+			reason = SKB_DROP_REASON_INVALID_PROTO;
 			goto error;
 		}
 		if (icmph->type != ICMP_ECHO &&
 		    icmph->type != ICMP_TIMESTAMP &&
 		    icmph->type != ICMP_ADDRESS &&
 		    icmph->type != ICMP_ADDRESSREPLY) {
+			reason = SKB_DROP_REASON_INVALID_PROTO;
 			goto error;
 		}
 	}
 
-	success = icmp_pointers[icmph->type].handler(skb);
-success_check:
-	if (success)  {
+	reason = icmp_pointers[icmph->type].handler(skb);
+reason_check:
+	if (!reason)  {
 		consume_skb(skb);
 		return NET_RX_SUCCESS;
 	}
 
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return NET_RX_DROP;
 csum_error:
+	reason = SKB_DROP_REASON_ICMP_CSUM;
 	__ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS);
 error:
 	__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
@@ -1434,46 +1440,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
 	},
 };
 
-static void __net_exit icmp_sk_exit(struct net *net)
-{
-	int i;
-
-	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
-	free_percpu(net->ipv4.icmp_sk);
-	net->ipv4.icmp_sk = NULL;
-}
-
 static int __net_init icmp_sk_init(struct net *net)
 {
-	int i, err;
-
-	net->ipv4.icmp_sk = alloc_percpu(struct sock *);
-	if (!net->ipv4.icmp_sk)
-		return -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		struct sock *sk;
-
-		err = inet_ctl_sock_create(&sk, PF_INET,
-					   SOCK_RAW, IPPROTO_ICMP, net);
-		if (err < 0)
-			goto fail;
-
-		*per_cpu_ptr(net->ipv4.icmp_sk, i) = sk;
-
-		/* Enough space for 2 64K ICMP packets, including
-		 * sk_buff/skb_shared_info struct overhead.
-		 */
-		sk->sk_sndbuf =	2 * SKB_TRUESIZE(64 * 1024);
-
-		/*
-		 * Speedup sock_wfree()
-		 */
-		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
-		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
-	}
-
 	/* Control parameters for ECHO replies. */
 	net->ipv4.sysctl_icmp_echo_ignore_all = 0;
 	net->ipv4.sysctl_icmp_echo_enable_probe = 0;
@@ -1499,18 +1467,36 @@ static int __net_init icmp_sk_init(struct net *net)
 	net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;
 
 	return 0;
-
-fail:
-	icmp_sk_exit(net);
-	return err;
 }
 
 static struct pernet_operations __net_initdata icmp_sk_ops = {
        .init = icmp_sk_init,
-       .exit = icmp_sk_exit,
 };
 
 int __init icmp_init(void)
 {
+	int err, i;
+
+	for_each_possible_cpu(i) {
+		struct sock *sk;
+
+		err = inet_ctl_sock_create(&sk, PF_INET,
+					   SOCK_RAW, IPPROTO_ICMP, &init_net);
+		if (err < 0)
+			return err;
+
+		per_cpu(ipv4_icmp_sk, i) = sk;
+
+		/* Enough space for 2 64K ICMP packets, including
+		 * sk_buff/skb_shared_info struct overhead.
+		 */
+		sk->sk_sndbuf =	2 * SKB_TRUESIZE(64 * 1024);
+
+		/*
+		 * Speedup sock_wfree()
+		 */
+		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
+	}
 	return register_pernet_subsys(&icmp_sk_ops);
 }