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, 477 insertions, 0 deletions

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
new file mode 100644
index 000000000..f6f5b83dd
--- /dev/null
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *  IPv6 IOAM Lightweight Tunnel implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/ioam6.h>
+#include <linux/ioam6_iptunnel.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/lwtunnel.h>
+#include <net/ioam6.h>
+#include <net/netlink.h>
+#include <net/ipv6.h>
+#include <net/dst_cache.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+
+#define IOAM6_MASK_SHORT_FIELDS 0xff100000
+#define IOAM6_MASK_WIDE_FIELDS 0xe00000
+
+struct ioam6_lwt_encap {
+	struct ipv6_hopopt_hdr eh;
+	u8 pad[2];			/* 2-octet padding for 4n-alignment */
+	struct ioam6_hdr ioamh;
+	struct ioam6_trace_hdr traceh;
+} __packed;
+
+struct ioam6_lwt_freq {
+	u32 k;
+	u32 n;
+};
+
+struct ioam6_lwt {
+	struct dst_cache cache;
+	struct ioam6_lwt_freq freq;
+	atomic_t pkt_cnt;
+	u8 mode;
+	struct in6_addr tundst;
+	struct ioam6_lwt_encap	tuninfo;
+};
+
+static struct netlink_range_validation freq_range = {
+	.min = IOAM6_IPTUNNEL_FREQ_MIN,
+	.max = IOAM6_IPTUNNEL_FREQ_MAX,
+};
+
+static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt)
+{
+	return (struct ioam6_lwt *)lwt->data;
+}
+
+static struct ioam6_lwt_encap *ioam6_lwt_info(struct lwtunnel_state *lwt)
+{
+	return &ioam6_lwt_state(lwt)->tuninfo;
+}
+
+static struct ioam6_trace_hdr *ioam6_lwt_trace(struct lwtunnel_state *lwt)
+{
+	return &(ioam6_lwt_state(lwt)->tuninfo.traceh);
+}
+
+static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = {
+	[IOAM6_IPTUNNEL_FREQ_K] = NLA_POLICY_FULL_RANGE(NLA_U32, &freq_range),
+	[IOAM6_IPTUNNEL_FREQ_N] = NLA_POLICY_FULL_RANGE(NLA_U32, &freq_range),
+	[IOAM6_IPTUNNEL_MODE]	= NLA_POLICY_RANGE(NLA_U8,
+						   IOAM6_IPTUNNEL_MODE_MIN,
+						   IOAM6_IPTUNNEL_MODE_MAX),
+	[IOAM6_IPTUNNEL_DST]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+	[IOAM6_IPTUNNEL_TRACE]	= NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)),
+};
+
+static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace)
+{
+	u32 fields;
+
+	if (!trace->type_be32 || !trace->remlen ||
+	    trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4 ||
+	    trace->type.bit12 | trace->type.bit13 | trace->type.bit14 |
+	    trace->type.bit15 | trace->type.bit16 | trace->type.bit17 |
+	    trace->type.bit18 | trace->type.bit19 | trace->type.bit20 |
+	    trace->type.bit21)
+		return false;
+
+	trace->nodelen = 0;
+	fields = be32_to_cpu(trace->type_be32);
+
+	trace->nodelen += hweight32(fields & IOAM6_MASK_SHORT_FIELDS)
+				* (sizeof(__be32) / 4);
+	trace->nodelen += hweight32(fields & IOAM6_MASK_WIDE_FIELDS)
+				* (sizeof(__be64) / 4);
+
+	return true;
+}
+
+static int ioam6_build_state(struct net *net, struct nlattr *nla,
+			     unsigned int family, const void *cfg,
+			     struct lwtunnel_state **ts,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1];
+	struct ioam6_lwt_encap *tuninfo;
+	struct ioam6_trace_hdr *trace;
+	struct lwtunnel_state *lwt;
+	struct ioam6_lwt *ilwt;
+	int len_aligned, err;
+	u32 freq_k, freq_n;
+	u8 mode;
+
+	if (family != AF_INET6)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, IOAM6_IPTUNNEL_MAX, nla,
+			       ioam6_iptunnel_policy, extack);
+	if (err < 0)
+		return err;
+
+	if ((!tb[IOAM6_IPTUNNEL_FREQ_K] && tb[IOAM6_IPTUNNEL_FREQ_N]) ||
+	    (tb[IOAM6_IPTUNNEL_FREQ_K] && !tb[IOAM6_IPTUNNEL_FREQ_N])) {
+		NL_SET_ERR_MSG(extack, "freq: missing parameter");
+		return -EINVAL;
+	} else if (!tb[IOAM6_IPTUNNEL_FREQ_K] && !tb[IOAM6_IPTUNNEL_FREQ_N]) {
+		freq_k = IOAM6_IPTUNNEL_FREQ_MIN;
+		freq_n = IOAM6_IPTUNNEL_FREQ_MIN;
+	} else {
+		freq_k = nla_get_u32(tb[IOAM6_IPTUNNEL_FREQ_K]);
+		freq_n = nla_get_u32(tb[IOAM6_IPTUNNEL_FREQ_N]);
+
+		if (freq_k > freq_n) {
+			NL_SET_ERR_MSG(extack, "freq: k > n is forbidden");
+			return -EINVAL;
+		}
+	}
+
+	if (!tb[IOAM6_IPTUNNEL_MODE])
+		mode = IOAM6_IPTUNNEL_MODE_INLINE;
+	else
+		mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]);
+
+	if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) {
+		NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination");
+		return -EINVAL;
+	}
+
+	if (!tb[IOAM6_IPTUNNEL_TRACE]) {
+		NL_SET_ERR_MSG(extack, "missing trace");
+		return -EINVAL;
+	}
+
+	trace = nla_data(tb[IOAM6_IPTUNNEL_TRACE]);
+	if (!ioam6_validate_trace_hdr(trace)) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_TRACE],
+				    "invalid trace validation");
+		return -EINVAL;
+	}
+
+	len_aligned = ALIGN(trace->remlen * 4, 8);
+	lwt = lwtunnel_state_alloc(sizeof(*ilwt) + len_aligned);
+	if (!lwt)
+		return -ENOMEM;
+
+	ilwt = ioam6_lwt_state(lwt);
+	err = dst_cache_init(&ilwt->cache, GFP_ATOMIC);
+	if (err) {
+		kfree(lwt);
+		return err;
+	}
+
+	atomic_set(&ilwt->pkt_cnt, 0);
+	ilwt->freq.k = freq_k;
+	ilwt->freq.n = freq_n;
+
+	ilwt->mode = mode;
+	if (tb[IOAM6_IPTUNNEL_DST])
+		ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]);
+
+	tuninfo = ioam6_lwt_info(lwt);
+	tuninfo->eh.hdrlen = ((sizeof(*tuninfo) + len_aligned) >> 3) - 1;
+	tuninfo->pad[0] = IPV6_TLV_PADN;
+	tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC;
+	tuninfo->ioamh.opt_type = IPV6_TLV_IOAM;
+	tuninfo->ioamh.opt_len = sizeof(tuninfo->ioamh) - 2 + sizeof(*trace)
+					+ trace->remlen * 4;
+
+	memcpy(&tuninfo->traceh, trace, sizeof(*trace));
+
+	if (len_aligned - trace->remlen * 4) {
+		tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN;
+		tuninfo->traceh.data[trace->remlen * 4 + 1] = 2;
+	}
+
+	lwt->type = LWTUNNEL_ENCAP_IOAM6;
+	lwt->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;
+
+	*ts = lwt;
+
+	return 0;
+}
+
+static int ioam6_do_fill(struct net *net, struct sk_buff *skb)
+{
+	struct ioam6_trace_hdr *trace;
+	struct ioam6_namespace *ns;
+
+	trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb)
+					   + sizeof(struct ipv6_hopopt_hdr) + 2
+					   + sizeof(struct ioam6_hdr));
+
+	ns = ioam6_namespace(net, trace->namespace_id);
+	if (ns)
+		ioam6_fill_trace_data(skb, ns, trace, false);
+
+	return 0;
+}
+
+static int ioam6_do_inline(struct net *net, struct sk_buff *skb,
+			   struct ioam6_lwt_encap *tuninfo)
+{
+	struct ipv6hdr *oldhdr, *hdr;
+	int hdrlen, err;
+
+	hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
+
+	err = skb_cow_head(skb, hdrlen + skb->mac_len);
+	if (unlikely(err))
+		return err;
+
+	oldhdr = ipv6_hdr(skb);
+	skb_pull(skb, sizeof(*oldhdr));
+	skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(*oldhdr));
+
+	skb_push(skb, sizeof(*oldhdr) + hdrlen);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	hdr = ipv6_hdr(skb);
+	memmove(hdr, oldhdr, sizeof(*oldhdr));
+	tuninfo->eh.nexthdr = hdr->nexthdr;
+
+	skb_set_transport_header(skb, sizeof(*hdr));
+	skb_postpush_rcsum(skb, hdr, sizeof(*hdr) + hdrlen);
+
+	memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen);
+
+	hdr->nexthdr = NEXTHDR_HOP;
+	hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr));
+
+	return ioam6_do_fill(net, skb);
+}
+
+static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
+			  struct ioam6_lwt_encap *tuninfo,
+			  struct in6_addr *tundst)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct ipv6hdr *hdr, *inner_hdr;
+	int hdrlen, len, err;
+
+	hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
+	len = sizeof(*hdr) + hdrlen;
+
+	err = skb_cow_head(skb, len + skb->mac_len);
+	if (unlikely(err))
+		return err;
+
+	inner_hdr = ipv6_hdr(skb);
+
+	skb_push(skb, len);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	skb_set_transport_header(skb, sizeof(*hdr));
+
+	tuninfo->eh.nexthdr = NEXTHDR_IPV6;
+	memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen);
+
+	hdr = ipv6_hdr(skb);
+	memcpy(hdr, inner_hdr, sizeof(*hdr));
+
+	hdr->nexthdr = NEXTHDR_HOP;
+	hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr));
+	hdr->daddr = *tundst;
+	ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr,
+			   IPV6_PREFER_SRC_PUBLIC, &hdr->saddr);
+
+	skb_postpush_rcsum(skb, hdr, len);
+
+	return ioam6_do_fill(net, skb);
+}
+
+static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct in6_addr orig_daddr;
+	struct ioam6_lwt *ilwt;
+	int err = -EINVAL;
+	u32 pkt_cnt;
+
+	if (skb->protocol != htons(ETH_P_IPV6))
+		goto drop;
+
+	ilwt = ioam6_lwt_state(dst->lwtstate);
+
+	/* Check for insertion frequency (i.e., "k over n" insertions) */
+	pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt);
+	if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k)
+		goto out;
+
+	orig_daddr = ipv6_hdr(skb)->daddr;
+
+	switch (ilwt->mode) {
+	case IOAM6_IPTUNNEL_MODE_INLINE:
+do_inline:
+		/* Direct insertion - if there is no Hop-by-Hop yet */
+		if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
+			goto out;
+
+		err = ioam6_do_inline(net, skb, &ilwt->tuninfo);
+		if (unlikely(err))
+			goto drop;
+
+		break;
+	case IOAM6_IPTUNNEL_MODE_ENCAP:
+do_encap:
+		/* Encapsulation (ip6ip6) */
+		err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst);
+		if (unlikely(err))
+			goto drop;
+
+		break;
+	case IOAM6_IPTUNNEL_MODE_AUTO:
+		/* Automatic (RFC8200 compliant):
+		 *  - local packets -> INLINE mode
+		 *  - in-transit packets -> ENCAP mode
+		 */
+		if (!skb->dev)
+			goto do_inline;
+
+		goto do_encap;
+	default:
+		goto drop;
+	}
+
+	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+	if (unlikely(err))
+		goto drop;
+
+	if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
+		preempt_disable();
+		dst = dst_cache_get(&ilwt->cache);
+		preempt_enable();
+
+		if (unlikely(!dst)) {
+			struct ipv6hdr *hdr = ipv6_hdr(skb);
+			struct flowi6 fl6;
+
+			memset(&fl6, 0, sizeof(fl6));
+			fl6.daddr = hdr->daddr;
+			fl6.saddr = hdr->saddr;
+			fl6.flowlabel = ip6_flowinfo(hdr);
+			fl6.flowi6_mark = skb->mark;
+			fl6.flowi6_proto = hdr->nexthdr;
+
+			dst = ip6_route_output(net, NULL, &fl6);
+			if (dst->error) {
+				err = dst->error;
+				dst_release(dst);
+				goto drop;
+			}
+
+			preempt_disable();
+			dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
+			preempt_enable();
+		}
+
+		skb_dst_drop(skb);
+		skb_dst_set(skb, dst);
+
+		return dst_output(net, sk, skb);
+	}
+out:
+	return dst->lwtstate->orig_output(net, sk, skb);
+drop:
+	kfree_skb(skb);
+	return err;
+}
+
+static void ioam6_destroy_state(struct lwtunnel_state *lwt)
+{
+	dst_cache_destroy(&ioam6_lwt_state(lwt)->cache);
+}
+
+static int ioam6_fill_encap_info(struct sk_buff *skb,
+				 struct lwtunnel_state *lwtstate)
+{
+	struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate);
+	int err;
+
+	err = nla_put_u32(skb, IOAM6_IPTUNNEL_FREQ_K, ilwt->freq.k);
+	if (err)
+		goto ret;
+
+	err = nla_put_u32(skb, IOAM6_IPTUNNEL_FREQ_N, ilwt->freq.n);
+	if (err)
+		goto ret;
+
+	err = nla_put_u8(skb, IOAM6_IPTUNNEL_MODE, ilwt->mode);
+	if (err)
+		goto ret;
+
+	if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) {
+		err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst);
+		if (err)
+			goto ret;
+	}
+
+	err = nla_put(skb, IOAM6_IPTUNNEL_TRACE, sizeof(ilwt->tuninfo.traceh),
+		      &ilwt->tuninfo.traceh);
+ret:
+	return err;
+}
+
+static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+	struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate);
+	int nlsize;
+
+	nlsize = nla_total_size(sizeof(ilwt->freq.k)) +
+		  nla_total_size(sizeof(ilwt->freq.n)) +
+		  nla_total_size(sizeof(ilwt->mode)) +
+		  nla_total_size(sizeof(ilwt->tuninfo.traceh));
+
+	if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE)
+		nlsize += nla_total_size(sizeof(ilwt->tundst));
+
+	return nlsize;
+}
+
+static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+	struct ioam6_trace_hdr *trace_a = ioam6_lwt_trace(a);
+	struct ioam6_trace_hdr *trace_b = ioam6_lwt_trace(b);
+	struct ioam6_lwt *ilwt_a = ioam6_lwt_state(a);
+	struct ioam6_lwt *ilwt_b = ioam6_lwt_state(b);
+
+	return (ilwt_a->freq.k != ilwt_b->freq.k ||
+		ilwt_a->freq.n != ilwt_b->freq.n ||
+		ilwt_a->mode != ilwt_b->mode ||
+		(ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE &&
+		 !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) ||
+		trace_a->namespace_id != trace_b->namespace_id);
+}
+
+static const struct lwtunnel_encap_ops ioam6_iptun_ops = {
+	.build_state		= ioam6_build_state,
+	.destroy_state		= ioam6_destroy_state,
+	.output		= ioam6_output,
+	.fill_encap		= ioam6_fill_encap_info,
+	.get_encap_size	= ioam6_encap_nlsize,
+	.cmp_encap		= ioam6_encap_cmp,
+	.owner			= THIS_MODULE,
+};
+
+int __init ioam6_iptunnel_init(void)
+{
+	return lwtunnel_encap_add_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6);
+}
+
+void ioam6_iptunnel_exit(void)
+{
+	lwtunnel_encap_del_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6);
+}