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, 813 insertions, 0 deletions

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
new file mode 100644
index 000000000..2478aa601
--- /dev/null
+++ b/net/l2tp/l2tp_ip6.c
@@ -0,0 +1,813 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* L2TPv3 IP encapsulation support for IPv6
+ *
+ * Copyright (c) 2012 Katalix Systems Ltd
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/icmp.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/random.h>
+#include <linux/socket.h>
+#include <linux/l2tp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/udp.h>
+#include <net/inet_common.h>
+#include <net/tcp_states.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+#include <net/transp_v6.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+
+#include "l2tp_core.h"
+
+struct l2tp_ip6_sock {
+	/* inet_sock has to be the first member of l2tp_ip6_sock */
+	struct inet_sock	inet;
+
+	u32			conn_id;
+	u32			peer_conn_id;
+
+	/* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see
+	 * inet6_sk_generic
+	 */
+	struct ipv6_pinfo	inet6;
+};
+
+static DEFINE_RWLOCK(l2tp_ip6_lock);
+static struct hlist_head l2tp_ip6_table;
+static struct hlist_head l2tp_ip6_bind_table;
+
+static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
+{
+	return (struct l2tp_ip6_sock *)sk;
+}
+
+static struct sock *__l2tp_ip6_bind_lookup(const struct net *net,
+					   const struct in6_addr *laddr,
+					   const struct in6_addr *raddr,
+					   int dif, u32 tunnel_id)
+{
+	struct sock *sk;
+
+	sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
+		const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk);
+		const struct in6_addr *sk_raddr = &sk->sk_v6_daddr;
+		const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
+		int bound_dev_if;
+
+		if (!net_eq(sock_net(sk), net))
+			continue;
+
+		bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
+		if (bound_dev_if && dif && bound_dev_if != dif)
+			continue;
+
+		if (sk_laddr && !ipv6_addr_any(sk_laddr) &&
+		    !ipv6_addr_any(laddr) && !ipv6_addr_equal(sk_laddr, laddr))
+			continue;
+
+		if (!ipv6_addr_any(sk_raddr) && raddr &&
+		    !ipv6_addr_any(raddr) && !ipv6_addr_equal(sk_raddr, raddr))
+			continue;
+
+		if (l2tp->conn_id != tunnel_id)
+			continue;
+
+		goto found;
+	}
+
+	sk = NULL;
+found:
+	return sk;
+}
+
+/* When processing receive frames, there are two cases to
+ * consider. Data frames consist of a non-zero session-id and an
+ * optional cookie. Control frames consist of a regular L2TP header
+ * preceded by 32-bits of zeros.
+ *
+ * L2TPv3 Session Header Over IP
+ *
+ *  0                   1                   2                   3
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                           Session ID                          |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |               Cookie (optional, maximum 64 bits)...
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *                                                                 |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * L2TPv3 Control Message Header Over IP
+ *
+ *  0                   1                   2                   3
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                      (32 bits of zeros)                       |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |T|L|x|x|S|x|x|x|x|x|x|x|  Ver  |             Length            |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                     Control Connection ID                     |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |               Ns              |               Nr              |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * All control frames are passed to userspace.
+ */
+static int l2tp_ip6_recv(struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	struct sock *sk;
+	u32 session_id;
+	u32 tunnel_id;
+	unsigned char *ptr, *optr;
+	struct l2tp_session *session;
+	struct l2tp_tunnel *tunnel = NULL;
+	struct ipv6hdr *iph;
+
+	if (!pskb_may_pull(skb, 4))
+		goto discard;
+
+	/* Point to L2TP header */
+	optr = skb->data;
+	ptr = skb->data;
+	session_id = ntohl(*((__be32 *)ptr));
+	ptr += 4;
+
+	/* RFC3931: L2TP/IP packets have the first 4 bytes containing
+	 * the session_id. If it is 0, the packet is a L2TP control
+	 * frame and the session_id value can be discarded.
+	 */
+	if (session_id == 0) {
+		__skb_pull(skb, 4);
+		goto pass_up;
+	}
+
+	/* Ok, this is a data packet. Lookup the session. */
+	session = l2tp_session_get(net, session_id);
+	if (!session)
+		goto discard;
+
+	tunnel = session->tunnel;
+	if (!tunnel)
+		goto discard_sess;
+
+	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto discard_sess;
+
+	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
+	l2tp_session_dec_refcount(session);
+
+	return 0;
+
+pass_up:
+	/* Get the tunnel_id from the L2TP header */
+	if (!pskb_may_pull(skb, 12))
+		goto discard;
+
+	if ((skb->data[0] & 0xc0) != 0xc0)
+		goto discard;
+
+	tunnel_id = ntohl(*(__be32 *)&skb->data[4]);
+	iph = ipv6_hdr(skb);
+
+	read_lock_bh(&l2tp_ip6_lock);
+	sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
+				    inet6_iif(skb), tunnel_id);
+	if (!sk) {
+		read_unlock_bh(&l2tp_ip6_lock);
+		goto discard;
+	}
+	sock_hold(sk);
+	read_unlock_bh(&l2tp_ip6_lock);
+
+	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
+		goto discard_put;
+
+	nf_reset_ct(skb);
+
+	return sk_receive_skb(sk, skb, 1);
+
+discard_sess:
+	l2tp_session_dec_refcount(session);
+	goto discard;
+
+discard_put:
+	sock_put(sk);
+
+discard:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int l2tp_ip6_hash(struct sock *sk)
+{
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip6_lock);
+		sk_add_node(sk, &l2tp_ip6_table);
+		write_unlock_bh(&l2tp_ip6_lock);
+	}
+	return 0;
+}
+
+static void l2tp_ip6_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
+	write_lock_bh(&l2tp_ip6_lock);
+	sk_del_node_init(sk);
+	write_unlock_bh(&l2tp_ip6_lock);
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+
+	l2tp_ip6_hash(sk);
+	return 0;
+}
+
+static void l2tp_ip6_close(struct sock *sk, long timeout)
+{
+	write_lock_bh(&l2tp_ip6_lock);
+	hlist_del_init(&sk->sk_bind_node);
+	sk_del_node_init(sk);
+	write_unlock_bh(&l2tp_ip6_lock);
+
+	sk_common_release(sk);
+}
+
+static void l2tp_ip6_destroy_sock(struct sock *sk)
+{
+	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
+
+	lock_sock(sk);
+	ip6_flush_pending_frames(sk);
+	release_sock(sk);
+
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
+}
+
+static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *)uaddr;
+	struct net *net = sock_net(sk);
+	__be32 v4addr = 0;
+	int bound_dev_if;
+	int addr_type;
+	int err;
+
+	if (addr->l2tp_family != AF_INET6)
+		return -EINVAL;
+	if (addr_len < sizeof(*addr))
+		return -EINVAL;
+
+	addr_type = ipv6_addr_type(&addr->l2tp_addr);
+
+	/* l2tp_ip6 sockets are IPv6 only */
+	if (addr_type == IPV6_ADDR_MAPPED)
+		return -EADDRNOTAVAIL;
+
+	/* L2TP is point-point, not multicast */
+	if (addr_type & IPV6_ADDR_MULTICAST)
+		return -EADDRNOTAVAIL;
+
+	lock_sock(sk);
+
+	err = -EINVAL;
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out_unlock;
+
+	if (sk->sk_state != TCP_CLOSE)
+		goto out_unlock;
+
+	bound_dev_if = sk->sk_bound_dev_if;
+
+	/* Check if the address belongs to the host. */
+	rcu_read_lock();
+	if (addr_type != IPV6_ADDR_ANY) {
+		struct net_device *dev = NULL;
+
+		if (addr_type & IPV6_ADDR_LINKLOCAL) {
+			if (addr->l2tp_scope_id)
+				bound_dev_if = addr->l2tp_scope_id;
+
+			/* Binding to link-local address requires an
+			 * interface.
+			 */
+			if (!bound_dev_if)
+				goto out_unlock_rcu;
+
+			err = -ENODEV;
+			dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if);
+			if (!dev)
+				goto out_unlock_rcu;
+		}
+
+		/* ipv4 addr of the socket is invalid.  Only the
+		 * unspecified and mapped address have a v4 equivalent.
+		 */
+		v4addr = LOOPBACK4_IPV6;
+		err = -EADDRNOTAVAIL;
+		if (!ipv6_chk_addr(sock_net(sk), &addr->l2tp_addr, dev, 0))
+			goto out_unlock_rcu;
+	}
+	rcu_read_unlock();
+
+	write_lock_bh(&l2tp_ip6_lock);
+	if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if,
+				   addr->l2tp_conn_id)) {
+		write_unlock_bh(&l2tp_ip6_lock);
+		err = -EADDRINUSE;
+		goto out_unlock;
+	}
+
+	inet->inet_saddr = v4addr;
+	inet->inet_rcv_saddr = v4addr;
+	sk->sk_bound_dev_if = bound_dev_if;
+	sk->sk_v6_rcv_saddr = addr->l2tp_addr;
+	np->saddr = addr->l2tp_addr;
+
+	l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;
+
+	sk_add_bind_node(sk, &l2tp_ip6_bind_table);
+	sk_del_node_init(sk);
+	write_unlock_bh(&l2tp_ip6_lock);
+
+	sock_reset_flag(sk, SOCK_ZAPPED);
+	release_sock(sk);
+	return 0;
+
+out_unlock_rcu:
+	rcu_read_unlock();
+out_unlock:
+	release_sock(sk);
+
+	return err;
+}
+
+static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
+			    int addr_len)
+{
+	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr;
+	struct sockaddr_in6	*usin = (struct sockaddr_in6 *)uaddr;
+	struct in6_addr	*daddr;
+	int	addr_type;
+	int rc;
+
+	if (addr_len < sizeof(*lsa))
+		return -EINVAL;
+
+	if (usin->sin6_family != AF_INET6)
+		return -EINVAL;
+
+	addr_type = ipv6_addr_type(&usin->sin6_addr);
+	if (addr_type & IPV6_ADDR_MULTICAST)
+		return -EINVAL;
+
+	if (addr_type & IPV6_ADDR_MAPPED) {
+		daddr = &usin->sin6_addr;
+		if (ipv4_is_multicast(daddr->s6_addr32[3]))
+			return -EINVAL;
+	}
+
+	lock_sock(sk);
+
+	 /* Must bind first - autobinding does not work */
+	if (sock_flag(sk, SOCK_ZAPPED)) {
+		rc = -EINVAL;
+		goto out_sk;
+	}
+
+	rc = __ip6_datagram_connect(sk, uaddr, addr_len);
+	if (rc < 0)
+		goto out_sk;
+
+	l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
+
+	write_lock_bh(&l2tp_ip6_lock);
+	hlist_del_init(&sk->sk_bind_node);
+	sk_add_bind_node(sk, &l2tp_ip6_bind_table);
+	write_unlock_bh(&l2tp_ip6_lock);
+
+out_sk:
+	release_sock(sk);
+
+	return rc;
+}
+
+static int l2tp_ip6_disconnect(struct sock *sk, int flags)
+{
+	if (sock_flag(sk, SOCK_ZAPPED))
+		return 0;
+
+	return __udp_disconnect(sk, flags);
+}
+
+static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
+			    int peer)
+{
+	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr;
+	struct sock *sk = sock->sk;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct l2tp_ip6_sock *lsk = l2tp_ip6_sk(sk);
+
+	lsa->l2tp_family = AF_INET6;
+	lsa->l2tp_flowinfo = 0;
+	lsa->l2tp_scope_id = 0;
+	lsa->l2tp_unused = 0;
+	if (peer) {
+		if (!lsk->peer_conn_id)
+			return -ENOTCONN;
+		lsa->l2tp_conn_id = lsk->peer_conn_id;
+		lsa->l2tp_addr = sk->sk_v6_daddr;
+		if (np->sndflow)
+			lsa->l2tp_flowinfo = np->flow_label;
+	} else {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+			lsa->l2tp_addr = np->saddr;
+		else
+			lsa->l2tp_addr = sk->sk_v6_rcv_saddr;
+
+		lsa->l2tp_conn_id = lsk->conn_id;
+	}
+	if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
+		lsa->l2tp_scope_id = READ_ONCE(sk->sk_bound_dev_if);
+	return sizeof(*lsa);
+}
+
+static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb)
+{
+	int rc;
+
+	/* Charge it to the socket, dropping if the queue is full. */
+	rc = sock_queue_rcv_skb(sk, skb);
+	if (rc < 0)
+		goto drop;
+
+	return 0;
+
+drop:
+	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
+	kfree_skb(skb);
+	return -1;
+}
+
+static int l2tp_ip6_push_pending_frames(struct sock *sk)
+{
+	struct sk_buff *skb;
+	__be32 *transhdr = NULL;
+	int err = 0;
+
+	skb = skb_peek(&sk->sk_write_queue);
+	if (!skb)
+		goto out;
+
+	transhdr = (__be32 *)skb_transport_header(skb);
+	*transhdr = 0;
+
+	err = ip6_push_pending_frames(sk);
+
+out:
+	return err;
+}
+
+/* Userspace will call sendmsg() on the tunnel socket to send L2TP
+ * control frames.
+ */
+static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+{
+	struct ipv6_txoptions opt_space;
+	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
+	struct in6_addr *daddr, *final_p, final;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt_to_free = NULL;
+	struct ipv6_txoptions *opt = NULL;
+	struct ip6_flowlabel *flowlabel = NULL;
+	struct dst_entry *dst = NULL;
+	struct flowi6 fl6;
+	struct ipcm6_cookie ipc6;
+	int addr_len = msg->msg_namelen;
+	int transhdrlen = 4; /* zero session-id */
+	int ulen;
+	int err;
+
+	/* Rough check on arithmetic overflow,
+	 * better check is made in ip6_append_data().
+	 */
+	if (len > INT_MAX - transhdrlen)
+		return -EMSGSIZE;
+	ulen = len + transhdrlen;
+
+	/* Mirror BSD error message compatibility */
+	if (msg->msg_flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
+	/* Get and verify the address */
+	memset(&fl6, 0, sizeof(fl6));
+
+	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
+
+	ipcm6_init(&ipc6);
+
+	if (lsa) {
+		if (addr_len < SIN6_LEN_RFC2133)
+			return -EINVAL;
+
+		if (lsa->l2tp_family && lsa->l2tp_family != AF_INET6)
+			return -EAFNOSUPPORT;
+
+		daddr = &lsa->l2tp_addr;
+		if (np->sndflow) {
+			fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK;
+			if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
+				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
+				if (IS_ERR(flowlabel))
+					return -EINVAL;
+			}
+		}
+
+		/* Otherwise it will be difficult to maintain
+		 * sk->sk_dst_cache.
+		 */
+		if (sk->sk_state == TCP_ESTABLISHED &&
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
+
+		if (addr_len >= sizeof(struct sockaddr_in6) &&
+		    lsa->l2tp_scope_id &&
+		    ipv6_addr_type(daddr) & IPV6_ADDR_LINKLOCAL)
+			fl6.flowi6_oif = lsa->l2tp_scope_id;
+	} else {
+		if (sk->sk_state != TCP_ESTABLISHED)
+			return -EDESTADDRREQ;
+
+		daddr = &sk->sk_v6_daddr;
+		fl6.flowlabel = np->flow_label;
+	}
+
+	if (fl6.flowi6_oif == 0)
+		fl6.flowi6_oif = READ_ONCE(sk->sk_bound_dev_if);
+
+	if (msg->msg_controllen) {
+		opt = &opt_space;
+		memset(opt, 0, sizeof(struct ipv6_txoptions));
+		opt->tot_len = sizeof(struct ipv6_txoptions);
+		ipc6.opt = opt;
+
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
+		if (err < 0) {
+			fl6_sock_release(flowlabel);
+			return err;
+		}
+		if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) {
+			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
+			if (IS_ERR(flowlabel))
+				return -EINVAL;
+		}
+		if (!(opt->opt_nflen | opt->opt_flen))
+			opt = NULL;
+	}
+
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
+	if (flowlabel)
+		opt = fl6_merge_options(&opt_space, flowlabel, opt);
+	opt = ipv6_fixup_options(&opt_space, opt);
+	ipc6.opt = opt;
+
+	fl6.flowi6_proto = sk->sk_protocol;
+	if (!ipv6_addr_any(daddr))
+		fl6.daddr = *daddr;
+	else
+		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
+	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
+		fl6.saddr = np->saddr;
+
+	final_p = fl6_update_dst(&fl6, opt, &final);
+
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+		fl6.flowi6_oif = np->mcast_oif;
+	else if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->ucast_oif;
+
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
+
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		goto out;
+	}
+
+	if (ipc6.hlimit < 0)
+		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
+
+	if (ipc6.dontfrag < 0)
+		ipc6.dontfrag = np->dontfrag;
+
+	if (msg->msg_flags & MSG_CONFIRM)
+		goto do_confirm;
+
+back_from_confirm:
+	lock_sock(sk);
+	err = ip6_append_data(sk, ip_generic_getfrag, msg,
+			      ulen, transhdrlen, &ipc6,
+			      &fl6, (struct rt6_info *)dst,
+			      msg->msg_flags);
+	if (err)
+		ip6_flush_pending_frames(sk);
+	else if (!(msg->msg_flags & MSG_MORE))
+		err = l2tp_ip6_push_pending_frames(sk);
+	release_sock(sk);
+done:
+	dst_release(dst);
+out:
+	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
+
+	return err < 0 ? err : len;
+
+do_confirm:
+	if (msg->msg_flags & MSG_PROBE)
+		dst_confirm_neigh(dst, &fl6.daddr);
+	if (!(msg->msg_flags & MSG_PROBE) || len)
+		goto back_from_confirm;
+	err = 0;
+	goto done;
+}
+
+static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			    int flags, int *addr_len)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
+	size_t copied = 0;
+	int err = -EOPNOTSUPP;
+	struct sk_buff *skb;
+
+	if (flags & MSG_OOB)
+		goto out;
+
+	if (flags & MSG_ERRQUEUE)
+		return ipv6_recv_error(sk, msg, len, addr_len);
+
+	skb = skb_recv_datagram(sk, flags, &err);
+	if (!skb)
+		goto out;
+
+	copied = skb->len;
+	if (len < copied) {
+		msg->msg_flags |= MSG_TRUNC;
+		copied = len;
+	}
+
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (err)
+		goto done;
+
+	sock_recv_timestamp(msg, sk, skb);
+
+	/* Copy the address. */
+	if (lsa) {
+		lsa->l2tp_family = AF_INET6;
+		lsa->l2tp_unused = 0;
+		lsa->l2tp_addr = ipv6_hdr(skb)->saddr;
+		lsa->l2tp_flowinfo = 0;
+		lsa->l2tp_scope_id = 0;
+		lsa->l2tp_conn_id = 0;
+		if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
+			lsa->l2tp_scope_id = inet6_iif(skb);
+		*addr_len = sizeof(*lsa);
+	}
+
+	if (np->rxopt.all)
+		ip6_datagram_recv_ctl(sk, msg, skb);
+
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
+done:
+	skb_free_datagram(sk, skb);
+out:
+	return err ? err : copied;
+}
+
+static struct proto l2tp_ip6_prot = {
+	.name		   = "L2TP/IPv6",
+	.owner		   = THIS_MODULE,
+	.init		   = l2tp_ip6_open,
+	.close		   = l2tp_ip6_close,
+	.bind		   = l2tp_ip6_bind,
+	.connect	   = l2tp_ip6_connect,
+	.disconnect	   = l2tp_ip6_disconnect,
+	.ioctl		   = l2tp_ioctl,
+	.destroy	   = l2tp_ip6_destroy_sock,
+	.setsockopt	   = ipv6_setsockopt,
+	.getsockopt	   = ipv6_getsockopt,
+	.sendmsg	   = l2tp_ip6_sendmsg,
+	.recvmsg	   = l2tp_ip6_recvmsg,
+	.backlog_rcv	   = l2tp_ip6_backlog_recv,
+	.hash		   = l2tp_ip6_hash,
+	.unhash		   = l2tp_ip6_unhash,
+	.obj_size	   = sizeof(struct l2tp_ip6_sock),
+};
+
+static const struct proto_ops l2tp_ip6_ops = {
+	.family		   = PF_INET6,
+	.owner		   = THIS_MODULE,
+	.release	   = inet6_release,
+	.bind		   = inet6_bind,
+	.connect	   = inet_dgram_connect,
+	.socketpair	   = sock_no_socketpair,
+	.accept		   = sock_no_accept,
+	.getname	   = l2tp_ip6_getname,
+	.poll		   = datagram_poll,
+	.ioctl		   = inet6_ioctl,
+	.gettstamp	   = sock_gettstamp,
+	.listen		   = sock_no_listen,
+	.shutdown	   = inet_shutdown,
+	.setsockopt	   = sock_common_setsockopt,
+	.getsockopt	   = sock_common_getsockopt,
+	.sendmsg	   = inet_sendmsg,
+	.recvmsg	   = sock_common_recvmsg,
+	.mmap		   = sock_no_mmap,
+	.sendpage	   = sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	   = inet6_compat_ioctl,
+#endif
+};
+
+static struct inet_protosw l2tp_ip6_protosw = {
+	.type		= SOCK_DGRAM,
+	.protocol	= IPPROTO_L2TP,
+	.prot		= &l2tp_ip6_prot,
+	.ops		= &l2tp_ip6_ops,
+};
+
+static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
+	.handler	= l2tp_ip6_recv,
+};
+
+static int __init l2tp_ip6_init(void)
+{
+	int err;
+
+	pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n");
+
+	err = proto_register(&l2tp_ip6_prot, 1);
+	if (err != 0)
+		goto out;
+
+	err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
+	if (err)
+		goto out1;
+
+	inet6_register_protosw(&l2tp_ip6_protosw);
+	return 0;
+
+out1:
+	proto_unregister(&l2tp_ip6_prot);
+out:
+	return err;
+}
+
+static void __exit l2tp_ip6_exit(void)
+{
+	inet6_unregister_protosw(&l2tp_ip6_protosw);
+	inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
+	proto_unregister(&l2tp_ip6_prot);
+}
+
+module_init(l2tp_ip6_init);
+module_exit(l2tp_ip6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Chris Elston <celston@katalix.com>");
+MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6");
+MODULE_VERSION("1.0");
+
+/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like
+ * enums
+ */
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP);
+MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP);