1 files changed, 260 insertions, 74 deletions

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 9ee208a348f5..168ec07e31cc 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	IPv6 input
  *	Linux INET6 implementation
@@ -7,11 +8,6 @@
  *	Ian P. Morris		<I.P.Morris@soton.ac.uk>
  *
  *	Based in linux/net/ipv4/ip_input.c
- *
- *	This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 /* Changes
  *
@@ -29,12 +25,14 @@
 #include <linux/icmpv6.h>
 #include <linux/mroute6.h>
 #include <linux/slab.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
 
 #include <net/sock.h>
 #include <net/snmp.h>
+#include <net/udp.h>
 
 #include <net/ipv6.h>
 #include <net/protocol.h>
@@ -47,40 +45,118 @@
 #include <net/inet_ecn.h>
 #include <net/dst_metadata.h>
 
-int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
+				struct sk_buff *skb)
 {
-	void (*edemux)(struct sk_buff *skb);
+	if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
+	    !skb_dst(skb) && !skb->sk) {
+		switch (ipv6_hdr(skb)->nexthdr) {
+		case IPPROTO_TCP:
+			if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
+				tcp_v6_early_demux(skb);
+			break;
+		case IPPROTO_UDP:
+			if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
+				udp_v6_early_demux(skb);
+			break;
+		}
+	}
 
+	if (!skb_valid_dst(skb))
+		ip6_route_input(skb);
+}
+
+int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
 	 */
 	skb = l3mdev_ip6_rcv(skb);
 	if (!skb)
 		return NET_RX_SUCCESS;
+	ip6_rcv_finish_core(net, sk, skb);
 
-	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
-		const struct inet6_protocol *ipprot;
+	return dst_input(skb);
+}
 
-		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
-		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
-			edemux(skb);
+static void ip6_sublist_rcv_finish(struct list_head *head)
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		skb_list_del_init(skb);
+		dst_input(skb);
 	}
-	if (!skb_valid_dst(skb))
-		ip6_route_input(skb);
+}
 
-	return dst_input(skb);
+static bool ip6_can_use_hint(const struct sk_buff *skb,
+			     const struct sk_buff *hint)
+{
+	return hint && !skb_dst(skb) &&
+	       ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
 }
 
-int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *ip6_extract_route_hint(const struct net *net,
+					      struct sk_buff *skb)
+{
+	if (fib6_routes_require_src(net) || fib6_has_custom_rules(net) ||
+	    IP6CB(skb)->flags & IP6SKB_MULTIPATH)
+		return NULL;
+
+	return skb;
+}
+
+static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
+				struct list_head *head)
+{
+	struct sk_buff *skb, *next, *hint = NULL;
+	struct dst_entry *curr_dst = NULL;
+	LIST_HEAD(sublist);
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct dst_entry *dst;
+
+		skb_list_del_init(skb);
+		/* if ingress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip6_rcv(skb);
+		if (!skb)
+			continue;
+
+		if (ip6_can_use_hint(skb, hint))
+			skb_dst_copy(skb, hint);
+		else
+			ip6_rcv_finish_core(net, sk, skb);
+		dst = skb_dst(skb);
+		if (curr_dst != dst) {
+			hint = ip6_extract_route_hint(net, skb);
+
+			/* dispatch old sublist */
+			if (!list_empty(&sublist))
+				ip6_sublist_rcv_finish(&sublist);
+			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
+			curr_dst = dst;
+		}
+		list_add_tail(&skb->list, &sublist);
+	}
+	/* dispatch final sublist */
+	ip6_sublist_rcv_finish(&sublist);
+}
+
+static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
+				    struct net *net)
 {
+	enum skb_drop_reason reason;
 	const struct ipv6hdr *hdr;
 	u32 pkt_len;
 	struct inet6_dev *idev;
-	struct net *net = dev_net(skb->dev);
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
-		kfree_skb(skb);
-		return NET_RX_DROP;
+		dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
+		kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
+		return NULL;
 	}
 
 	rcu_read_lock();
@@ -89,9 +165,12 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 
 	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
 
+	SKB_DR_SET(reason, NOT_SPECIFIED);
 	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
-	    !idev || unlikely(idev->cnf.disable_ipv6)) {
+	    !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+		if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6)))
+			SKB_DR_SET(reason, IPV6DISABLED);
 		goto drop;
 	}
 
@@ -108,15 +187,19 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	 * arrived via the sending interface (ethX), because of the
 	 * nature of scoping architecture. --yoshfuji
 	 */
-	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
+	IP6CB(skb)->iif = skb_valid_dst(skb) ?
+				ip6_dst_idev(skb_dst(skb))->dev->ifindex :
+				dev->ifindex;
 
 	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
 		goto err;
 
 	hdr = ipv6_hdr(skb);
 
-	if (hdr->version != 6)
+	if (hdr->version != 6) {
+		SKB_DR_SET(reason, UNHANDLED_PROTO);
 		goto err;
+	}
 
 	__IP6_ADD_STATS(net, idev,
 			IPSTATS_MIB_NOECTPKTS +
@@ -131,7 +214,8 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	 */
 	if ((ipv6_addr_loopback(&hdr->saddr) ||
 	     ipv6_addr_loopback(&hdr->daddr)) &&
-	     !(dev->flags & IFF_LOOPBACK))
+	    !(dev->flags & IFF_LOOPBACK) &&
+	    !netif_is_l3_master(dev))
 		goto err;
 
 	/* RFC4291 Errata ID: 3480
@@ -153,8 +237,10 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
 	    (skb->pkt_type == PACKET_BROADCAST ||
 	     skb->pkt_type == PACKET_MULTICAST) &&
-	    idev->cnf.drop_unicast_in_l2_multicast)
+	    READ_ONCE(idev->cnf.drop_unicast_in_l2_multicast)) {
+		SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST);
 		goto err;
+	}
 
 	/* RFC4291 2.7
 	 * Nodes must not originate a packet to a multicast address whose scope
@@ -183,12 +269,11 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 		if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
 			__IP6_INC_STATS(net,
 					idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+			SKB_DR_SET(reason, PKT_TOO_SMALL);
 			goto drop;
 		}
-		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
-			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
-			goto drop;
-		}
+		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
+			goto err;
 		hdr = ipv6_hdr(skb);
 	}
 
@@ -196,51 +281,106 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 		if (ipv6_parse_hopopts(skb) < 0) {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 			rcu_read_unlock();
-			return NET_RX_DROP;
+			return NULL;
 		}
 	}
 
 	rcu_read_unlock();
 
 	/* Must drop socket now because of tproxy. */
-	skb_orphan(skb);
+	if (!skb_sk_is_prefetched(skb))
+		skb_orphan(skb);
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
-		       net, NULL, skb, dev, NULL,
-		       ip6_rcv_finish);
+	return skb;
 err:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+	SKB_DR_OR(reason, IP_INHDR);
 drop:
 	rcu_read_unlock();
-	kfree_skb(skb);
-	return NET_RX_DROP;
+	kfree_skb_reason(skb, reason);
+	return NULL;
+}
+
+int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct net *net = dev_net(skb->dev);
+
+	skb = ip6_rcv_core(skb, dev, net);
+	if (skb == NULL)
+		return NET_RX_DROP;
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
+		       net, NULL, skb, dev, NULL,
+		       ip6_rcv_finish);
 }
 
+static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
+			    struct net *net)
+{
+	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
+		     head, dev, NULL, ip6_rcv_finish);
+	ip6_list_rcv_finish(net, NULL, head);
+}
+
+/* Receive a list of IPv6 packets */
+void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
+		   struct net_device *orig_dev)
+{
+	struct net_device *curr_dev = NULL;
+	struct net *curr_net = NULL;
+	struct sk_buff *skb, *next;
+	LIST_HEAD(sublist);
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
+		struct net *net = dev_net(dev);
+
+		skb_list_del_init(skb);
+		skb = ip6_rcv_core(skb, dev, net);
+		if (skb == NULL)
+			continue;
+
+		if (curr_dev != dev || curr_net != net) {
+			/* dispatch old sublist */
+			if (!list_empty(&sublist))
+				ip6_sublist_rcv(&sublist, curr_dev, curr_net);
+			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
+			curr_dev = dev;
+			curr_net = net;
+		}
+		list_add_tail(&skb->list, &sublist);
+	}
+	/* dispatch final sublist */
+	if (!list_empty(&sublist))
+		ip6_sublist_rcv(&sublist, curr_dev, curr_net);
+}
+
+INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
+
 /*
  *	Deliver the packet to the host
  */
-
-
-static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+			      bool have_final)
 {
 	const struct inet6_protocol *ipprot;
 	struct inet6_dev *idev;
 	unsigned int nhoff;
-	int nexthdr;
+	SKB_DR(reason);
 	bool raw;
-	bool have_final = false;
 
 	/*
 	 *	Parse extension headers
 	 */
 
-	rcu_read_lock();
 resubmit:
 	idev = ip6_dst_idev(skb_dst(skb));
-	if (!pskb_pull(skb, skb_transport_offset(skb)))
-		goto discard;
 	nhoff = IP6CB(skb)->nhoff;
-	nexthdr = skb_network_header(skb)[nhoff];
+	if (!have_final) {
+		if (!pskb_pull(skb, skb_transport_offset(skb)))
+			goto discard;
+		nexthdr = skb_network_header(skb)[nhoff];
+	}
 
 resubmit_final:
 	raw = raw6_local_deliver(skb, nexthdr);
@@ -259,29 +399,44 @@ resubmit_final:
 			}
 		} else if (ipprot->flags & INET6_PROTO_FINAL) {
 			const struct ipv6hdr *hdr;
+			int sdif = inet6_sdif(skb);
+			struct net_device *dev;
 
 			/* Only do this once for first final protocol */
 			have_final = true;
 
-			/* Free reference early: we don't need it any more,
-			   and it may hold ip_conntrack module loaded
-			   indefinitely. */
-			nf_reset(skb);
 
 			skb_postpull_rcsum(skb, skb_network_header(skb),
 					   skb_network_header_len(skb));
 			hdr = ipv6_hdr(skb);
+
+			/* skb->dev passed may be master dev for vrfs. */
+			if (sdif) {
+				dev = dev_get_by_index_rcu(net, sdif);
+				if (!dev)
+					goto discard;
+			} else {
+				dev = skb->dev;
+			}
+
 			if (ipv6_addr_is_multicast(&hdr->daddr) &&
-			    !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
-			    &hdr->saddr) &&
-			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
+			    !ipv6_chk_mcast_addr(dev, &hdr->daddr,
+						 &hdr->saddr) &&
+			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) {
+				SKB_DR_SET(reason, IP_INADDRERRORS);
 				goto discard;
+			}
+		}
+		if (!(ipprot->flags & INET6_PROTO_NOPOLICY)) {
+			if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				SKB_DR_SET(reason, XFRM_POLICY);
+				goto discard;
+			}
+			nf_reset_ct(skb);
 		}
-		if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
-		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
-			goto discard;
 
-		ret = ipprot->handler(skb);
+		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
+				      skb);
 		if (ret > 0) {
 			if (ipprot->flags & INET6_PROTO_FINAL) {
 				/* Not an extension header, most likely UDP
@@ -304,49 +459,81 @@ resubmit_final:
 						IPSTATS_MIB_INUNKNOWNPROTOS);
 				icmpv6_send(skb, ICMPV6_PARAMPROB,
 					    ICMPV6_UNK_NEXTHDR, nhoff);
+				SKB_DR_SET(reason, IP_NOPROTO);
+			} else {
+				SKB_DR_SET(reason, XFRM_POLICY);
 			}
-			kfree_skb(skb);
+			kfree_skb_reason(skb, reason);
 		} else {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
 			consume_skb(skb);
 		}
 	}
-	rcu_read_unlock();
-	return 0;
+	return;
 
 discard:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
-	rcu_read_unlock();
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
+}
+
+static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) {
+		__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+				IPSTATS_MIB_INDISCARDS);
+		kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM);
+		return 0;
+	}
+
+	skb_clear_delivery_time(skb);
+	ip6_protocol_deliver_rcu(net, skb, 0, false);
+
 	return 0;
 }
 
 
 int ip6_input(struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
-		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
-		       ip6_input_finish);
+	int res;
+
+	rcu_read_lock();
+	res = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
+		      dev_net_rcu(skb->dev), NULL, skb, skb->dev, NULL,
+		      ip6_input_finish);
+	rcu_read_unlock();
+
+	return res;
 }
 EXPORT_SYMBOL_GPL(ip6_input);
 
 int ip6_mc_input(struct sk_buff *skb)
 {
+	struct net_device *dev = skb->dev;
+	int sdif = inet6_sdif(skb);
 	const struct ipv6hdr *hdr;
 	bool deliver;
 
-	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
-			 ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST,
-			 skb->len);
+	__IP6_UPD_PO_STATS(skb_dst_dev_net_rcu(skb),
+			   __in6_dev_get_safely(dev), IPSTATS_MIB_INMCAST,
+			   skb->len);
+
+	/* skb->dev passed may be master dev for vrfs. */
+	if (sdif) {
+		dev = dev_get_by_index_rcu(dev_net_rcu(dev), sdif);
+		if (!dev) {
+			kfree_skb(skb);
+			return -ENODEV;
+		}
+	}
 
 	hdr = ipv6_hdr(skb);
-	deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
+	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
 
 #ifdef CONFIG_IPV6_MROUTE
 	/*
 	 *      IPv6 multicast router mode is now supported ;)
 	 */
-	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
+	if (atomic_read(&dev_net_rcu(skb->dev)->ipv6.devconf_all->mc_forwarding) &&
 	    !(ipv6_addr_type(&hdr->daddr) &
 	      (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
 	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
@@ -387,22 +574,21 @@ int ip6_mc_input(struct sk_buff *skb)
 			/* unknown RA - process it normally */
 		}
 
-		if (deliver)
+		if (deliver) {
 			skb2 = skb_clone(skb, GFP_ATOMIC);
-		else {
+		} else {
 			skb2 = skb;
 			skb = NULL;
 		}
 
-		if (skb2) {
+		if (skb2)
 			ip6_mr_input(skb2);
-		}
 	}
 out:
 #endif
-	if (likely(deliver))
+	if (likely(deliver)) {
 		ip6_input(skb);
-	else {
+	} else {
 		/* discard */
 		kfree_skb(skb);
 	}