Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 643 insertions, 0 deletions

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
new file mode 100644
index 000000000..d332ec60f
--- /dev/null
+++ b/net/ipv6/ip6_input.c
@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *	IPv6 input
+ *	Linux INET6 implementation
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>
+ *	Ian P. Morris		<I.P.Morris@soton.ac.uk>
+ *
+ *	Based in linux/net/ipv4/ip_input.c
+ */
+/* Changes
+ *
+ *	Mitsuru KANDA @USAGI and
+ *	YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#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>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+#include <net/inet_ecn.h>
+#include <net/dst_metadata.h>
+#include <net/inet6_hashtables.h>
+
+static void tcp_v6_early_demux(struct sk_buff *skb)
+{
+	struct net *net = dev_net_rcu(skb->dev);
+	const struct ipv6hdr *hdr;
+	const struct tcphdr *th;
+	struct sock *sk;
+
+	if (skb->pkt_type != PACKET_HOST)
+		return;
+
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) +
+				sizeof(struct tcphdr)))
+		return;
+
+	hdr = ipv6_hdr(skb);
+	th = tcp_hdr(skb);
+
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		return;
+
+	/* Note : We use inet6_iif() here, not tcp_v6_iif() */
+	sk = __inet6_lookup_established(net, &hdr->saddr, th->source,
+					&hdr->daddr, ntohs(th->dest),
+					inet6_iif(skb), inet6_sdif(skb));
+	if (sk) {
+		skb->sk = sk;
+		skb->destructor = sock_edemux;
+		if (sk_fullsock(sk)) {
+			struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
+
+			if (dst)
+				dst = dst_check(dst, sk->sk_rx_dst_cookie);
+			if (dst &&
+			    sk->sk_rx_dst_ifindex == skb->skb_iif)
+				skb_dst_set_noref(skb, dst);
+		}
+	}
+}
+
+static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
+				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);
+
+	return dst_input(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);
+	}
+}
+
+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);
+}
+
+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;
+
+	if (skb->pkt_type == PACKET_OTHERHOST) {
+		dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
+		kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
+		return NULL;
+	}
+
+	rcu_read_lock();
+
+	idev = __in6_dev_get(skb->dev);
+
+	__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(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;
+	}
+
+	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
+
+	/*
+	 * Store incoming device index. When the packet will
+	 * be queued, we cannot refer to skb->dev anymore.
+	 *
+	 * BTW, when we send a packet for our own local address on a
+	 * non-loopback interface (e.g. ethX), it is being delivered
+	 * via the loopback interface (lo) here; skb->dev = loopback_dev.
+	 * It, however, should be considered as if it is being
+	 * 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;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
+		goto err;
+
+	hdr = ipv6_hdr(skb);
+
+	if (hdr->version != 6) {
+		SKB_DR_SET(reason, UNHANDLED_PROTO);
+		goto err;
+	}
+
+	__IP6_ADD_STATS(net, idev,
+			IPSTATS_MIB_NOECTPKTS +
+				(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
+			max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
+	/*
+	 * RFC4291 2.5.3
+	 * The loopback address must not be used as the source address in IPv6
+	 * packets that are sent outside of a single node. [..]
+	 * A packet received on an interface with a destination address
+	 * of loopback must be dropped.
+	 */
+	if ((ipv6_addr_loopback(&hdr->saddr) ||
+	     ipv6_addr_loopback(&hdr->daddr)) &&
+	    !(dev->flags & IFF_LOOPBACK) &&
+	    !netif_is_l3_master(dev))
+		goto err;
+
+	/* RFC4291 Errata ID: 3480
+	 * Interface-Local scope spans only a single interface on a
+	 * node and is useful only for loopback transmission of
+	 * multicast.  Packets with interface-local scope received
+	 * from another node must be discarded.
+	 */
+	if (!(skb->pkt_type == PACKET_LOOPBACK ||
+	      dev->flags & IFF_LOOPBACK) &&
+	    ipv6_addr_is_multicast(&hdr->daddr) &&
+	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
+		goto err;
+
+	/* If enabled, drop unicast packets that were encapsulated in link-layer
+	 * multicast or broadcast to protected against the so-called "hole-196"
+	 * attack in 802.11 wireless.
+	 */
+	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
+	    (skb->pkt_type == PACKET_BROADCAST ||
+	     skb->pkt_type == PACKET_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
+	 * field contains the reserved value 0; if such a packet is received, it
+	 * must be silently dropped.
+	 */
+	if (ipv6_addr_is_multicast(&hdr->daddr) &&
+	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
+		goto err;
+
+	/*
+	 * RFC4291 2.7
+	 * Multicast addresses must not be used as source addresses in IPv6
+	 * packets or appear in any Routing header.
+	 */
+	if (ipv6_addr_is_multicast(&hdr->saddr))
+		goto err;
+
+	skb->transport_header = skb->network_header + sizeof(*hdr);
+	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	pkt_len = ipv6_payload_len(skb, hdr);
+
+	/* pkt_len may be zero if Jumbo payload option is present */
+	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
+		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)))
+			goto err;
+		hdr = ipv6_hdr(skb);
+	}
+
+	if (hdr->nexthdr == NEXTHDR_HOP) {
+		if (ipv6_parse_hopopts(skb) < 0) {
+			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+			rcu_read_unlock();
+			return NULL;
+		}
+	}
+
+	rcu_read_unlock();
+
+	/* Must drop socket now because of tproxy. */
+	if (!skb_sk_is_prefetched(skb))
+		skb_orphan(skb);
+
+	return skb;
+err:
+	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+	SKB_DR_OR(reason, IP_INHDR);
+drop:
+	rcu_read_unlock();
+	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
+ */
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+			      bool have_final)
+{
+	int exthdr_cnt = IP6CB(skb)->flags & IP6SKB_HOPBYHOP ? 1 : 0;
+	const struct inet6_protocol *ipprot;
+	struct inet6_dev *idev;
+	unsigned int nhoff;
+	SKB_DR(reason);
+	bool raw;
+
+	/*
+	 *	Parse extension headers
+	 */
+
+resubmit:
+	idev = ip6_dst_idev(skb_dst(skb));
+	nhoff = IP6CB(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);
+	ipprot = rcu_dereference(inet6_protos[nexthdr]);
+	if (ipprot) {
+		int ret;
+
+		if (have_final) {
+			if (!(ipprot->flags & INET6_PROTO_FINAL)) {
+				/* Once we've seen a final protocol don't
+				 * allow encapsulation on any non-final
+				 * ones. This allows foo in UDP encapsulation
+				 * to work.
+				 */
+				goto discard;
+			}
+		} 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;
+
+
+			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(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);
+		}
+
+		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
+				 * encapsulation. Use return value as nexthdr
+				 * protocol not nhoff (which presumably is
+				 * not set by handler).
+				 */
+				nexthdr = ret;
+				goto resubmit_final;
+			} else {
+				if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) {
+					SKB_DR_SET(reason, IPV6_TOO_MANY_EXTHDRS);
+					goto discard;
+				}
+				goto resubmit;
+			}
+		} else if (ret == 0) {
+			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
+		}
+	} else {
+		if (!raw) {
+			if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				__IP6_INC_STATS(net, idev,
+						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_reason(skb, reason);
+		} else {
+			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
+			consume_skb(skb);
+		}
+	}
+	return;
+
+discard:
+	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+	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)
+{
+	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(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(dev, &hdr->daddr, NULL);
+
+#ifdef CONFIG_IPV6_MROUTE
+	/*
+	 *      IPv6 multicast router mode is now supported ;)
+	 */
+	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))) {
+		/*
+		 * Okay, we try to forward - split and duplicate
+		 * packets.
+		 */
+		struct sk_buff *skb2;
+		struct inet6_skb_parm *opt = IP6CB(skb);
+
+		/* Check for MLD */
+		if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
+			/* Check if this is a mld message */
+			u8 nexthdr = hdr->nexthdr;
+			__be16 frag_off;
+			int offset;
+
+			/* Check if the value of Router Alert
+			 * is for MLD (0x0000).
+			 */
+			if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
+				deliver = false;
+
+				if (!ipv6_ext_hdr(nexthdr)) {
+					/* BUG */
+					goto out;
+				}
+				offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
+							  &nexthdr, &frag_off);
+				if (offset < 0)
+					goto out;
+
+				if (ipv6_is_mld(skb, nexthdr, offset))
+					deliver = true;
+
+				goto out;
+			}
+			/* unknown RA - process it normally */
+		}
+
+		if (deliver) {
+			skb2 = skb_clone(skb, GFP_ATOMIC);
+		} else {
+			skb_orphan(skb);
+			skb2 = skb;
+			skb = NULL;
+		}
+
+		if (skb2)
+			ip6_mr_input(skb2);
+	}
+out:
+#endif
+	if (likely(deliver)) {
+		ip6_input(skb);
+	} else {
+		/* discard */
+		kfree_skb(skb);
+	}
+
+	return 0;
+}