--- zzzz-none-000/linux-3.10.107/net/ipv4/icmp.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/net/ipv4/icmp.c	2021-02-04 17:41:59.000000000 +0000
@@ -96,6 +96,7 @@
 #include <net/xfrm.h>
 #include <net/inet_common.h>
 #include <net/ip_fib.h>
+#include <net/l3mdev.h>
 
 /*
  *	Build xmit assembly blocks
@@ -190,7 +191,7 @@
  */
 
 struct icmp_control {
-	void (*handler)(struct sk_buff *skb);
+	bool (*handler)(struct sk_buff *skb);
 	short   error;		/* This ICMP is classed as an error message */
 };
 
@@ -205,7 +206,7 @@
  */
 static struct sock *icmp_sk(struct net *net)
 {
-	return net->ipv4.icmp_sk[smp_processor_id()];
+	return *this_cpu_ptr(net->ipv4.icmp_sk);
 }
 
 static inline struct sock *icmp_xmit_lock(struct net *net)
@@ -231,12 +232,62 @@
 	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 +304,15 @@
 		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()) {
+		int vif = l3mdev_master_ifindex(dst->dev);
+		struct inet_peer *peer;
+
+		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
 		rc = inet_peer_xrlim_allow(peer,
 					   net->ipv4.sysctl_icmp_ratelimit);
 		if (peer)
@@ -337,22 +395,27 @@
 	struct sock *sk;
 	struct inet_sock *inet;
 	__be32 daddr, saddr;
+	u32 mark = IP4_REPLY_MARK(net, skb->mark);
 
 	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
 		return;
 
 	sk = icmp_xmit_lock(net);
-	if (sk == NULL)
+	if (!sk)
 		return;
 	inet = inet_sk(sk);
 
 	icmp_param->data.icmph.checksum = 0;
 
 	inet->tos = ip_hdr(skb)->tos;
+	sk->sk_mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
+
 	if (icmp_param->replyopts.opt.opt.optlen) {
 		ipc.opt = &icmp_param->replyopts.opt;
 		if (ipc.opt->opt.srr)
@@ -361,8 +424,10 @@
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
+	fl4.flowi4_mark = mark;
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
+	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
@@ -375,11 +440,27 @@
 	icmp_xmit_unlock(sk);
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+
+/* Source and destination is swapped. See ip_multipath_icmp_hash */
+static int icmp_multipath_hash_skb(const struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+
+	return fib_multipath_hash(iph->daddr, iph->saddr);
+}
+
+#else
+
+#define icmp_multipath_hash_skb(skb) (-1)
+
+#endif
+
 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,
+					__be32 saddr, u8 tos, u32 mark,
 					int type, int code,
 					struct icmp_bxm *param)
 {
@@ -391,12 +472,16 @@
 	fl4->daddr = (param->replyopts.opt.opt.srr ?
 		      param->replyopts.opt.opt.faddr : iph->saddr);
 	fl4->saddr = saddr;
+	fl4->flowi4_mark = mark;
 	fl4->flowi4_tos = RT_TOS(tos);
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
+	fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
+
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
-	rt = __ip_route_output_key(net, fl4);
+	rt = __ip_route_output_key_hash(net, fl4,
+					icmp_multipath_hash_skb(skb_in));
 	if (IS_ERR(rt))
 		return rt;
 
@@ -417,7 +502,8 @@
 	if (err)
 		goto relookup_failed;
 
-	if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) {
+	if (inet_addr_type_dev_table(net, skb_in->dev,
+				     fl4_dec.saddr) == RTN_LOCAL) {
 		rt2 = __ip_route_output_key(net, &fl4_dec);
 		if (IS_ERR(rt2))
 			err = PTR_ERR(rt2);
@@ -433,6 +519,7 @@
 		}
 		/* Ugh! */
 		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);
 
@@ -482,12 +569,13 @@
 {
 	struct iphdr *iph;
 	int room;
-	struct icmp_bxm icmp_param;
+	struct icmp_bxm *icmp_param;
 	struct rtable *rt = skb_rtable(skb_in);
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	__be32 saddr;
 	u8  tos;
+	u32 mark;
 	struct net *net;
 	struct sock *sk;
 
@@ -503,7 +591,8 @@
 	iph = ip_hdr(skb_in);
 
 	if ((u8 *)iph < skb_in->head ||
-	    (skb_in->network_header + sizeof(*iph)) > skb_in->tail)
+	    (skb_network_header(skb_in) + sizeof(*iph)) >
+	    skb_tail_pointer(skb_in))
 		goto out;
 
 	/*
@@ -544,7 +633,7 @@
 						 skb_in->data,
 						 sizeof(_inner_type),
 						 &_inner_type);
-			if (itp == NULL)
+			if (!itp)
 				goto out;
 
 			/*
@@ -557,10 +646,14 @@
 		}
 	}
 
-	sk = icmp_xmit_lock(net);
-	if (sk == NULL)
+	icmp_param = kmalloc(sizeof(*icmp_param), GFP_ATOMIC);
+	if (!icmp_param)
 		return;
 
+	sk = icmp_xmit_lock(net);
+	if (!sk)
+		goto out_free;
+
 	/*
 	 *	Construct source address and options.
 	 */
@@ -584,8 +677,9 @@
 	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
 					   IPTOS_PREC_INTERNETCONTROL) :
 					  iph->tos;
+	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
+	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
 		goto out_unlock;
 
 
@@ -593,19 +687,22 @@
 	 *	Prepare data for ICMP header.
 	 */
 
-	icmp_param.data.icmph.type	 = type;
-	icmp_param.data.icmph.code	 = code;
-	icmp_param.data.icmph.un.gateway = info;
-	icmp_param.data.icmph.checksum	 = 0;
-	icmp_param.skb	  = skb_in;
-	icmp_param.offset = skb_network_offset(skb_in);
+	icmp_param->data.icmph.type	 = type;
+	icmp_param->data.icmph.code	 = code;
+	icmp_param->data.icmph.un.gateway = 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;
+	sk->sk_mark = mark;
 	ipc.addr = iph->saddr;
-	ipc.opt = &icmp_param.replyopts.opt;
+	ipc.opt = &icmp_param->replyopts.opt;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
-	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
-			       type, code, &icmp_param);
+	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
+			       type, code, icmp_param);
 	if (IS_ERR(rt))
 		goto out_unlock;
 
@@ -617,19 +714,21 @@
 	room = dst_mtu(&rt->dst);
 	if (room > 576)
 		room = 576;
-	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
+	room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.opt.optlen;
 	room -= sizeof(struct icmphdr);
 
-	icmp_param.data_len = skb_in->len - icmp_param.offset;
-	if (icmp_param.data_len > room)
-		icmp_param.data_len = room;
-	icmp_param.head_len = sizeof(struct icmphdr);
+	icmp_param->data_len = skb_in->len - icmp_param->offset;
+	if (icmp_param->data_len > room)
+		icmp_param->data_len = room;
+	icmp_param->head_len = sizeof(struct icmphdr);
 
-	icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
+	icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
 ende:
 	ip_rt_put(rt);
 out_unlock:
 	icmp_xmit_unlock(sk);
+out_free:
+	kfree(icmp_param);
 out:;
 }
 EXPORT_SYMBOL(icmp_send);
@@ -644,23 +743,34 @@
 	/* Checkin full IP header plus 8 bytes of protocol to
 	 * avoid additional coding at protocol handlers.
 	 */
-	if (!pskb_may_pull(skb, iph->ihl * 4 + 8))
+	if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) {
+		ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS);
 		return;
+	}
 
 	raw_icmp_error(skb, protocol, info);
 
-	rcu_read_lock();
 	ipprot = rcu_dereference(inet_protos[protocol]);
 	if (ipprot && ipprot->err_handler)
 		ipprot->err_handler(skb, info);
+}
+
+static bool icmp_tag_validation(int proto)
+{
+	bool ok;
+
+	rcu_read_lock();
+	ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation;
 	rcu_read_unlock();
+	return ok;
 }
 
 /*
- *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH.
+ *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ *	ICMP_PARAMETERPROB.
  */
 
-static void icmp_unreach(struct sk_buff *skb)
+static bool icmp_unreach(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	struct icmphdr *icmph;
@@ -692,16 +802,28 @@
 		case ICMP_PORT_UNREACH:
 			break;
 		case ICMP_FRAG_NEEDED:
-			if (ipv4_config.no_pmtu_disc) {
-				LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"),
-					       &iph->daddr);
-			} else {
+			/* for documentation of the ip_no_pmtu_disc
+			 * values please see
+			 * Documentation/networking/ip-sysctl.txt
+			 */
+			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
+			default:
+				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
+						    &iph->daddr);
+				break;
+			case 2:
+				goto out;
+			case 3:
+				if (!icmp_tag_validation(iph->protocol))
+					goto out;
+				/* fall through */
+			case 0:
 				info = ntohs(icmph->un.frag.mtu);
 			}
 			break;
 		case ICMP_SR_FAILED:
-			LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"),
-				       &iph->daddr);
+			net_dbg_ratelimited("%pI4: Source Route Failed\n",
+					    &iph->daddr);
 			break;
 		default:
 			break;
@@ -730,7 +852,7 @@
 	 */
 
 	if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
-	    inet_addr_type(net, iph->daddr) == RTN_BROADCAST) {
+	    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,
 				     icmph->type, icmph->code,
@@ -741,10 +863,10 @@
 	icmp_socket_deliver(skb, info);
 
 out:
-	return;
+	return true;
 out_err:
 	ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
-	goto out;
+	return false;
 }
 
 
@@ -752,17 +874,20 @@
  *	Handle ICMP_REDIRECT.
  */
 
-static void icmp_redirect(struct sk_buff *skb)
+static bool icmp_redirect(struct sk_buff *skb)
 {
 	if (skb->len < sizeof(struct iphdr)) {
 		ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS);
-		return;
+		return false;
 	}
 
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return;
+	if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
+		/* there aught to be a stat */
+		return false;
+	}
 
 	icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway);
+	return true;
 }
 
 /*
@@ -777,7 +902,7 @@
  *	See also WRT handling of options once they are done and working.
  */
 
-static void icmp_echo(struct sk_buff *skb)
+static bool icmp_echo(struct sk_buff *skb)
 {
 	struct net *net;
 
@@ -793,6 +918,8 @@
 		icmp_param.head_len	   = sizeof(struct icmphdr);
 		icmp_reply(&icmp_param, skb);
 	}
+	/* should there be an ICMP stat for ignored echos? */
+	return true;
 }
 
 /*
@@ -802,7 +929,7 @@
  *		  MUST be accurate to a few minutes.
  *		  MUST be updated at least at 15Hz.
  */
-static void icmp_timestamp(struct sk_buff *skb)
+static bool icmp_timestamp(struct sk_buff *skb)
 {
 	struct timespec tv;
 	struct icmp_bxm icmp_param;
@@ -829,15 +956,17 @@
 	icmp_param.data_len	   = 0;
 	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
 	icmp_reply(&icmp_param, skb);
-out:
-	return;
+	return true;
+
 out_err:
 	ICMP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
-	goto out;
+	return false;
 }
 
-static void icmp_discard(struct sk_buff *skb)
+static bool icmp_discard(struct sk_buff *skb)
 {
+	/* pretend it was a success */
+	return true;
 }
 
 /*
@@ -848,6 +977,7 @@
 	struct icmphdr *icmph;
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = dev_net(rt->dst.dev);
+	bool success;
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
@@ -871,16 +1001,8 @@
 
 	ICMP_INC_STATS_BH(net, ICMP_MIB_INMSGS);
 
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_fold(skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		if (__skb_checksum_complete(skb))
-			goto csum_error;
-	}
+	if (skb_checksum_simple_validate(skb))
+		goto csum_error;
 
 	if (!pskb_pull(skb, sizeof(*icmph)))
 		goto error;
@@ -922,7 +1044,12 @@
 		}
 	}
 
-	icmp_pointers[icmph->type].handler(skb);
+	success = icmp_pointers[icmph->type].handler(skb);
+
+	if (success)  {
+		consume_skb(skb);
+		return 0;
+	}
 
 drop:
 	kfree_skb(skb);
@@ -937,7 +1064,8 @@
 void icmp_err(struct sk_buff *skb, u32 info)
 {
 	struct iphdr *iph = (struct iphdr *)skb->data;
-	struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+	int offset = iph->ihl<<2;
+	struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
 	int type = icmp_hdr(skb)->type;
 	int code = icmp_hdr(skb)->code;
 	struct net *net = dev_net(skb->dev);
@@ -947,7 +1075,7 @@
 	 * triggered by ICMP_ECHOREPLY which sent from kernel.
 	 */
 	if (icmph->type != ICMP_ECHOREPLY) {
-		ping_err(skb, info);
+		ping_err(skb, offset, info);
 		return;
 	}
 
@@ -1036,8 +1164,8 @@
 	int i;
 
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
-	kfree(net->ipv4.icmp_sk);
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
+	free_percpu(net->ipv4.icmp_sk);
 	net->ipv4.icmp_sk = NULL;
 }
 
@@ -1045,9 +1173,8 @@
 {
 	int i, err;
 
-	net->ipv4.icmp_sk =
-		kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
-	if (net->ipv4.icmp_sk == NULL)
+	net->ipv4.icmp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.icmp_sk)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
@@ -1058,7 +1185,7 @@
 		if (err < 0)
 			goto fail;
 
-		net->ipv4.icmp_sk[i] = sk;
+		*per_cpu_ptr(net->ipv4.icmp_sk, i) = sk;
 
 		/* Enough space for 2 64K ICMP packets, including
 		 * sk_buff/skb_shared_info struct overhead.
@@ -1099,8 +1226,8 @@
 
 fail:
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
-	kfree(net->ipv4.icmp_sk);
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
+	free_percpu(net->ipv4.icmp_sk);
 	return err;
 }