Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 594 insertions, 0 deletions

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
new file mode 100644
index 000000000..e1ebf5e42
--- /dev/null
+++ b/net/ipv6/ip6_input.c
@@ -0,0 +1,594 @@
+// 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>
+
+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))
+		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;
+	struct list_head sublist;
+
+	INIT_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(idev->cnf.disable_ipv6)) {
+		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+		if (idev && unlikely(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) &&
+	    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 = ntohs(hdr->payload_len);
+
+	/* 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;
+	struct list_head sublist;
+
+	INIT_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)
+{
+	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;
+
+			/* Free reference early: we don't need it any more,
+			   and it may hold ip_conntrack module loaded
+			   indefinitely. */
+			nf_reset_ct(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(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) &&
+		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+			SKB_DR_SET(reason, XFRM_POLICY);
+			goto discard;
+		}
+
+		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 {
+				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)
+{
+	skb_clear_delivery_time(skb);
+	rcu_read_lock();
+	ip6_protocol_deliver_rcu(net, skb, 0, false);
+	rcu_read_unlock();
+
+	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);
+}
+EXPORT_SYMBOL_GPL(ip6_input);
+
+int ip6_mc_input(struct sk_buff *skb)
+{
+	int sdif = inet6_sdif(skb);
+	const struct ipv6hdr *hdr;
+	struct net_device *dev;
+	bool deliver;
+
+	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
+			 __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
+			 skb->len);
+
+	/* skb->dev passed may be master dev for vrfs. */
+	if (sdif) {
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
+		if (!dev) {
+			rcu_read_unlock();
+			kfree_skb(skb);
+			return -ENODEV;
+		}
+	} else {
+		dev = skb->dev;
+	}
+
+	hdr = ipv6_hdr(skb);
+	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
+	if (sdif)
+		rcu_read_unlock();
+
+#ifdef CONFIG_IPV6_MROUTE
+	/*
+	 *      IPv6 multicast router mode is now supported ;)
+	 */
+	if (atomic_read(&dev_net(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 {
+			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;
+}