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, 1011 insertions, 0 deletions

diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
new file mode 100644
index 000000000..e384e0de7
--- /dev/null
+++ b/net/netfilter/nft_meta.c
@@ -0,0 +1,1011 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2014 Intel Corporation
+ * Author: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/random.h>
+#include <linux/smp.h>
+#include <linux/static_key.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/sock.h>
+#include <net/tcp_states.h> /* for TCP_TIME_WAIT */
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nft_meta.h>
+#include <net/netfilter/nf_tables_offload.h>
+
+#include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */
+
+#define NFT_META_SECS_PER_MINUTE	60
+#define NFT_META_SECS_PER_HOUR		3600
+#define NFT_META_SECS_PER_DAY		86400
+#define NFT_META_DAYS_PER_WEEK		7
+
+static u8 nft_meta_weekday(void)
+{
+	time64_t secs = ktime_get_real_seconds();
+	unsigned int dse;
+	u8 wday;
+
+	secs -= NFT_META_SECS_PER_MINUTE * sys_tz.tz_minuteswest;
+	dse = div_u64(secs, NFT_META_SECS_PER_DAY);
+	wday = (4 + dse) % NFT_META_DAYS_PER_WEEK;
+
+	return wday;
+}
+
+static u32 nft_meta_hour(time64_t secs)
+{
+	struct tm tm;
+
+	time64_to_tm(secs, 0, &tm);
+
+	return tm.tm_hour * NFT_META_SECS_PER_HOUR
+		+ tm.tm_min * NFT_META_SECS_PER_MINUTE
+		+ tm.tm_sec;
+}
+
+static noinline_for_stack void
+nft_meta_get_eval_time(enum nft_meta_keys key,
+		       u32 *dest)
+{
+	switch (key) {
+	case NFT_META_TIME_NS:
+		nft_reg_store64(dest, ktime_get_real_ns());
+		break;
+	case NFT_META_TIME_DAY:
+		nft_reg_store8(dest, nft_meta_weekday());
+		break;
+	case NFT_META_TIME_HOUR:
+		*dest = nft_meta_hour(ktime_get_real_seconds());
+		break;
+	default:
+		break;
+	}
+}
+
+static noinline bool
+nft_meta_get_eval_pkttype_lo(const struct nft_pktinfo *pkt,
+			     u32 *dest)
+{
+	const struct sk_buff *skb = pkt->skb;
+
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+			nft_reg_store8(dest, PACKET_MULTICAST);
+		else
+			nft_reg_store8(dest, PACKET_BROADCAST);
+		break;
+	case NFPROTO_IPV6:
+		nft_reg_store8(dest, PACKET_MULTICAST);
+		break;
+	case NFPROTO_NETDEV:
+		switch (skb->protocol) {
+		case htons(ETH_P_IP): {
+			int noff = skb_network_offset(skb);
+			struct iphdr *iph, _iph;
+
+			iph = skb_header_pointer(skb, noff,
+						 sizeof(_iph), &_iph);
+			if (!iph)
+				return false;
+
+			if (ipv4_is_multicast(iph->daddr))
+				nft_reg_store8(dest, PACKET_MULTICAST);
+			else
+				nft_reg_store8(dest, PACKET_BROADCAST);
+
+			break;
+		}
+		case htons(ETH_P_IPV6):
+			nft_reg_store8(dest, PACKET_MULTICAST);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return false;
+		}
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return false;
+	}
+
+	return true;
+}
+
+static noinline bool
+nft_meta_get_eval_skugid(enum nft_meta_keys key,
+			 u32 *dest,
+			 const struct nft_pktinfo *pkt)
+{
+	struct sock *sk = skb_to_full_sk(pkt->skb);
+	struct socket *sock;
+
+	if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk)))
+		return false;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	sock = sk->sk_socket;
+	if (!sock || !sock->file) {
+		read_unlock_bh(&sk->sk_callback_lock);
+		return false;
+	}
+
+	switch (key) {
+	case NFT_META_SKUID:
+		*dest = from_kuid_munged(sock_net(sk)->user_ns,
+					 sock->file->f_cred->fsuid);
+		break;
+	case NFT_META_SKGID:
+		*dest =	from_kgid_munged(sock_net(sk)->user_ns,
+					 sock->file->f_cred->fsgid);
+		break;
+	default:
+		break;
+	}
+
+	read_unlock_bh(&sk->sk_callback_lock);
+	return true;
+}
+
+#ifdef CONFIG_CGROUP_NET_CLASSID
+static noinline bool
+nft_meta_get_eval_cgroup(u32 *dest, const struct nft_pktinfo *pkt)
+{
+	struct sock *sk = skb_to_full_sk(pkt->skb);
+
+	if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk)))
+		return false;
+
+	*dest = sock_cgroup_classid(&sk->sk_cgrp_data);
+	return true;
+}
+#endif
+
+static noinline bool nft_meta_get_eval_kind(enum nft_meta_keys key,
+					    u32 *dest,
+					    const struct nft_pktinfo *pkt)
+{
+	const struct net_device *in = nft_in(pkt), *out = nft_out(pkt);
+
+	switch (key) {
+	case NFT_META_IIFKIND:
+		if (!in || !in->rtnl_link_ops)
+			return false;
+		strncpy((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ);
+		break;
+	case NFT_META_OIFKIND:
+		if (!out || !out->rtnl_link_ops)
+			return false;
+		strncpy((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ);
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static void nft_meta_store_ifindex(u32 *dest, const struct net_device *dev)
+{
+	*dest = dev ? dev->ifindex : 0;
+}
+
+static void nft_meta_store_ifname(u32 *dest, const struct net_device *dev)
+{
+	strncpy((char *)dest, dev ? dev->name : "", IFNAMSIZ);
+}
+
+static bool nft_meta_store_iftype(u32 *dest, const struct net_device *dev)
+{
+	if (!dev)
+		return false;
+
+	nft_reg_store16(dest, dev->type);
+	return true;
+}
+
+static bool nft_meta_store_ifgroup(u32 *dest, const struct net_device *dev)
+{
+	if (!dev)
+		return false;
+
+	*dest = dev->group;
+	return true;
+}
+
+static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest,
+				     const struct nft_pktinfo *pkt)
+{
+	switch (key) {
+	case NFT_META_IIFNAME:
+		nft_meta_store_ifname(dest, nft_in(pkt));
+		break;
+	case NFT_META_OIFNAME:
+		nft_meta_store_ifname(dest, nft_out(pkt));
+		break;
+	case NFT_META_IIF:
+		nft_meta_store_ifindex(dest, nft_in(pkt));
+		break;
+	case NFT_META_OIF:
+		nft_meta_store_ifindex(dest, nft_out(pkt));
+		break;
+	case NFT_META_IFTYPE:
+		if (!nft_meta_store_iftype(dest, pkt->skb->dev))
+			return false;
+		break;
+	case __NFT_META_IIFTYPE:
+		if (!nft_meta_store_iftype(dest, nft_in(pkt)))
+			return false;
+		break;
+	case NFT_META_OIFTYPE:
+		if (!nft_meta_store_iftype(dest, nft_out(pkt)))
+			return false;
+		break;
+	case NFT_META_IIFGROUP:
+		if (!nft_meta_store_ifgroup(dest, nft_in(pkt)))
+			return false;
+		break;
+	case NFT_META_OIFGROUP:
+		if (!nft_meta_store_ifgroup(dest, nft_out(pkt)))
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+static noinline bool
+nft_meta_get_eval_rtclassid(const struct sk_buff *skb, u32 *dest)
+{
+	const struct dst_entry *dst = skb_dst(skb);
+
+	if (!dst)
+		return false;
+
+	*dest = dst->tclassid;
+	return true;
+}
+#endif
+
+static noinline u32 nft_meta_get_eval_sdif(const struct nft_pktinfo *pkt)
+{
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		return inet_sdif(pkt->skb);
+	case NFPROTO_IPV6:
+		return inet6_sdif(pkt->skb);
+	}
+
+	return 0;
+}
+
+static noinline void
+nft_meta_get_eval_sdifname(u32 *dest, const struct nft_pktinfo *pkt)
+{
+	u32 sdif = nft_meta_get_eval_sdif(pkt);
+	const struct net_device *dev;
+
+	dev = sdif ? dev_get_by_index_rcu(nft_net(pkt), sdif) : NULL;
+	nft_meta_store_ifname(dest, dev);
+}
+
+void nft_meta_get_eval(const struct nft_expr *expr,
+		       struct nft_regs *regs,
+		       const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	const struct sk_buff *skb = pkt->skb;
+	u32 *dest = &regs->data[priv->dreg];
+
+	switch (priv->key) {
+	case NFT_META_LEN:
+		*dest = skb->len;
+		break;
+	case NFT_META_PROTOCOL:
+		nft_reg_store16(dest, (__force u16)skb->protocol);
+		break;
+	case NFT_META_NFPROTO:
+		nft_reg_store8(dest, nft_pf(pkt));
+		break;
+	case NFT_META_L4PROTO:
+		if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
+			goto err;
+		nft_reg_store8(dest, pkt->tprot);
+		break;
+	case NFT_META_PRIORITY:
+		*dest = skb->priority;
+		break;
+	case NFT_META_MARK:
+		*dest = skb->mark;
+		break;
+	case NFT_META_IIF:
+	case NFT_META_OIF:
+	case NFT_META_IIFNAME:
+	case NFT_META_OIFNAME:
+	case NFT_META_IIFTYPE:
+	case NFT_META_OIFTYPE:
+	case NFT_META_IIFGROUP:
+	case NFT_META_OIFGROUP:
+		if (!nft_meta_get_eval_ifname(priv->key, dest, pkt))
+			goto err;
+		break;
+	case NFT_META_SKUID:
+	case NFT_META_SKGID:
+		if (!nft_meta_get_eval_skugid(priv->key, dest, pkt))
+			goto err;
+		break;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	case NFT_META_RTCLASSID:
+		if (!nft_meta_get_eval_rtclassid(skb, dest))
+			goto err;
+		break;
+#endif
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+		*dest = skb->secmark;
+		break;
+#endif
+	case NFT_META_PKTTYPE:
+		if (skb->pkt_type != PACKET_LOOPBACK) {
+			nft_reg_store8(dest, skb->pkt_type);
+			break;
+		}
+
+		if (!nft_meta_get_eval_pkttype_lo(pkt, dest))
+			goto err;
+		break;
+	case NFT_META_CPU:
+		*dest = raw_smp_processor_id();
+		break;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case NFT_META_CGROUP:
+		if (!nft_meta_get_eval_cgroup(dest, pkt))
+			goto err;
+		break;
+#endif
+	case NFT_META_PRANDOM:
+		*dest = get_random_u32();
+		break;
+#ifdef CONFIG_XFRM
+	case NFT_META_SECPATH:
+		nft_reg_store8(dest, secpath_exists(skb));
+		break;
+#endif
+	case NFT_META_IIFKIND:
+	case NFT_META_OIFKIND:
+		if (!nft_meta_get_eval_kind(priv->key, dest, pkt))
+			goto err;
+		break;
+	case NFT_META_TIME_NS:
+	case NFT_META_TIME_DAY:
+	case NFT_META_TIME_HOUR:
+		nft_meta_get_eval_time(priv->key, dest);
+		break;
+	case NFT_META_SDIF:
+		*dest = nft_meta_get_eval_sdif(pkt);
+		break;
+	case NFT_META_SDIFNAME:
+		nft_meta_get_eval_sdifname(dest, pkt);
+		break;
+	default:
+		WARN_ON(1);
+		goto err;
+	}
+	return;
+
+err:
+	regs->verdict.code = NFT_BREAK;
+}
+EXPORT_SYMBOL_GPL(nft_meta_get_eval);
+
+void nft_meta_set_eval(const struct nft_expr *expr,
+		       struct nft_regs *regs,
+		       const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *meta = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 *sreg = &regs->data[meta->sreg];
+	u32 value = *sreg;
+	u8 value8;
+
+	switch (meta->key) {
+	case NFT_META_MARK:
+		skb->mark = value;
+		break;
+	case NFT_META_PRIORITY:
+		skb->priority = value;
+		break;
+	case NFT_META_PKTTYPE:
+		value8 = nft_reg_load8(sreg);
+
+		if (skb->pkt_type != value8 &&
+		    skb_pkt_type_ok(value8) &&
+		    skb_pkt_type_ok(skb->pkt_type))
+			skb->pkt_type = value8;
+		break;
+	case NFT_META_NFTRACE:
+		value8 = nft_reg_load8(sreg);
+
+		skb->nf_trace = !!value8;
+		break;
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+		skb->secmark = value;
+		break;
+#endif
+	default:
+		WARN_ON(1);
+	}
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_eval);
+
+const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+	[NFTA_META_DREG]	= { .type = NLA_U32 },
+	[NFTA_META_KEY]		= { .type = NLA_U32 },
+	[NFTA_META_SREG]	= { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(nft_meta_policy);
+
+int nft_meta_get_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	unsigned int len;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_PROTOCOL:
+	case NFT_META_IIFTYPE:
+	case NFT_META_OIFTYPE:
+		len = sizeof(u16);
+		break;
+	case NFT_META_NFPROTO:
+	case NFT_META_L4PROTO:
+	case NFT_META_LEN:
+	case NFT_META_PRIORITY:
+	case NFT_META_MARK:
+	case NFT_META_IIF:
+	case NFT_META_OIF:
+	case NFT_META_SDIF:
+	case NFT_META_SKUID:
+	case NFT_META_SKGID:
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	case NFT_META_RTCLASSID:
+#endif
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+#endif
+	case NFT_META_PKTTYPE:
+	case NFT_META_CPU:
+	case NFT_META_IIFGROUP:
+	case NFT_META_OIFGROUP:
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case NFT_META_CGROUP:
+#endif
+		len = sizeof(u32);
+		break;
+	case NFT_META_IIFNAME:
+	case NFT_META_OIFNAME:
+	case NFT_META_IIFKIND:
+	case NFT_META_OIFKIND:
+	case NFT_META_SDIFNAME:
+		len = IFNAMSIZ;
+		break;
+	case NFT_META_PRANDOM:
+		len = sizeof(u32);
+		break;
+#ifdef CONFIG_XFRM
+	case NFT_META_SECPATH:
+		len = sizeof(u8);
+		break;
+#endif
+	case NFT_META_TIME_NS:
+		len = sizeof(u64);
+		break;
+	case NFT_META_TIME_DAY:
+		len = sizeof(u8);
+		break;
+	case NFT_META_TIME_HOUR:
+		len = sizeof(u32);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->len = len;
+	return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg,
+					NULL, NFT_DATA_VALUE, len);
+}
+EXPORT_SYMBOL_GPL(nft_meta_get_init);
+
+static int nft_meta_get_validate_sdif(const struct nft_ctx *ctx)
+{
+	unsigned int hooks;
+
+	switch (ctx->family) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		hooks = (1 << NF_INET_LOCAL_IN) |
+			(1 << NF_INET_FORWARD);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
+}
+
+static int nft_meta_get_validate_xfrm(const struct nft_ctx *ctx)
+{
+#ifdef CONFIG_XFRM
+	unsigned int hooks;
+
+	switch (ctx->family) {
+	case NFPROTO_NETDEV:
+		hooks = 1 << NF_NETDEV_INGRESS;
+		break;
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		hooks = (1 << NF_INET_PRE_ROUTING) |
+			(1 << NF_INET_LOCAL_IN) |
+			(1 << NF_INET_FORWARD);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
+#else
+	return 0;
+#endif
+}
+
+static int nft_meta_get_validate(const struct nft_ctx *ctx,
+				 const struct nft_expr *expr,
+				 const struct nft_data **data)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
+	switch (priv->key) {
+	case NFT_META_SECPATH:
+		return nft_meta_get_validate_xfrm(ctx);
+	case NFT_META_SDIF:
+	case NFT_META_SDIFNAME:
+		return nft_meta_get_validate_sdif(ctx);
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+int nft_meta_set_validate(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr,
+			  const struct nft_data **data)
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	unsigned int hooks;
+
+	if (priv->key != NFT_META_PKTTYPE)
+		return 0;
+
+	switch (ctx->family) {
+	case NFPROTO_BRIDGE:
+		hooks = 1 << NF_BR_PRE_ROUTING;
+		break;
+	case NFPROTO_NETDEV:
+		hooks = 1 << NF_NETDEV_INGRESS;
+		break;
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		hooks = 1 << NF_INET_PRE_ROUTING;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_validate);
+
+int nft_meta_set_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	unsigned int len;
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_MARK:
+	case NFT_META_PRIORITY:
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+#endif
+		len = sizeof(u32);
+		break;
+	case NFT_META_NFTRACE:
+		len = sizeof(u8);
+		break;
+	case NFT_META_PKTTYPE:
+		len = sizeof(u8);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->len = len;
+	err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len);
+	if (err < 0)
+		return err;
+
+	if (priv->key == NFT_META_NFTRACE)
+		static_branch_inc(&nft_trace_enabled);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_init);
+
+int nft_meta_get_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr, bool reset)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
+		goto nla_put_failure;
+	if (nft_dump_register(skb, NFTA_META_DREG, priv->dreg))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_meta_get_dump);
+
+int nft_meta_set_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr, bool reset)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
+		goto nla_put_failure;
+	if (nft_dump_register(skb, NFTA_META_SREG, priv->sreg))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_dump);
+
+void nft_meta_set_destroy(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
+	if (priv->key == NFT_META_NFTRACE)
+		static_branch_dec(&nft_trace_enabled);
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_destroy);
+
+static int nft_meta_get_offload(struct nft_offload_ctx *ctx,
+				struct nft_flow_rule *flow,
+				const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->key) {
+	case NFT_META_PROTOCOL:
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto,
+					sizeof(__u16), reg);
+		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
+		break;
+	case NFT_META_L4PROTO:
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
+					sizeof(__u8), reg);
+		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
+		break;
+	case NFT_META_IIF:
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta,
+					ingress_ifindex, sizeof(__u32), reg);
+		break;
+	case NFT_META_IIFTYPE:
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta,
+					ingress_iftype, sizeof(__u16), reg);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+bool nft_meta_get_reduce(struct nft_regs_track *track,
+			 const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	const struct nft_meta *meta;
+
+	if (!nft_reg_track_cmp(track, expr, priv->dreg)) {
+		nft_reg_track_update(track, expr, priv->dreg, priv->len);
+		return false;
+	}
+
+	meta = nft_expr_priv(track->regs[priv->dreg].selector);
+	if (priv->key != meta->key ||
+	    priv->dreg != meta->dreg) {
+		nft_reg_track_update(track, expr, priv->dreg, priv->len);
+		return false;
+	}
+
+	if (!track->regs[priv->dreg].bitwise)
+		return true;
+
+	return nft_expr_reduce_bitwise(track, expr);
+}
+EXPORT_SYMBOL_GPL(nft_meta_get_reduce);
+
+static const struct nft_expr_ops nft_meta_get_ops = {
+	.type		= &nft_meta_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_get_eval,
+	.init		= nft_meta_get_init,
+	.dump		= nft_meta_get_dump,
+	.reduce		= nft_meta_get_reduce,
+	.validate	= nft_meta_get_validate,
+	.offload	= nft_meta_get_offload,
+};
+
+static bool nft_meta_set_reduce(struct nft_regs_track *track,
+				const struct nft_expr *expr)
+{
+	int i;
+
+	for (i = 0; i < NFT_REG32_NUM; i++) {
+		if (!track->regs[i].selector)
+			continue;
+
+		if (track->regs[i].selector->ops != &nft_meta_get_ops)
+			continue;
+
+		__nft_reg_track_cancel(track, i);
+	}
+
+	return false;
+}
+
+static const struct nft_expr_ops nft_meta_set_ops = {
+	.type		= &nft_meta_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_set_eval,
+	.init		= nft_meta_set_init,
+	.destroy	= nft_meta_set_destroy,
+	.dump		= nft_meta_set_dump,
+	.reduce		= nft_meta_set_reduce,
+	.validate	= nft_meta_set_validate,
+};
+
+static const struct nft_expr_ops *
+nft_meta_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	if (tb[NFTA_META_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
+		return ERR_PTR(-EINVAL);
+
+#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META)
+	if (ctx->family == NFPROTO_BRIDGE)
+		return ERR_PTR(-EAGAIN);
+#endif
+	if (tb[NFTA_META_DREG])
+		return &nft_meta_get_ops;
+
+	if (tb[NFTA_META_SREG])
+		return &nft_meta_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int nft_meta_inner_init(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	unsigned int len;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_PROTOCOL:
+		len = sizeof(u16);
+		break;
+	case NFT_META_L4PROTO:
+		len = sizeof(u32);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	priv->len = len;
+
+	return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg,
+					NULL, NFT_DATA_VALUE, len);
+}
+
+void nft_meta_inner_eval(const struct nft_expr *expr,
+			 struct nft_regs *regs,
+			 const struct nft_pktinfo *pkt,
+			 struct nft_inner_tun_ctx *tun_ctx)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	u32 *dest = &regs->data[priv->dreg];
+
+	switch (priv->key) {
+	case NFT_META_PROTOCOL:
+		nft_reg_store16(dest, (__force u16)tun_ctx->llproto);
+		break;
+	case NFT_META_L4PROTO:
+		if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH))
+			goto err;
+
+		nft_reg_store8(dest, tun_ctx->l4proto);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		goto err;
+	}
+	return;
+
+err:
+	regs->verdict.code = NFT_BREAK;
+}
+EXPORT_SYMBOL_GPL(nft_meta_inner_eval);
+
+static const struct nft_expr_ops nft_meta_inner_ops = {
+	.type		= &nft_meta_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.init		= nft_meta_inner_init,
+	.dump		= nft_meta_get_dump,
+	/* direct call to nft_meta_inner_eval(). */
+};
+
+struct nft_expr_type nft_meta_type __read_mostly = {
+	.name		= "meta",
+	.select_ops	= nft_meta_select_ops,
+	.inner_ops	= &nft_meta_inner_ops,
+	.policy		= nft_meta_policy,
+	.maxattr	= NFTA_META_MAX,
+	.owner		= THIS_MODULE,
+};
+
+#ifdef CONFIG_NETWORK_SECMARK
+struct nft_secmark {
+	u32 secid;
+	char *ctx;
+};
+
+static const struct nla_policy nft_secmark_policy[NFTA_SECMARK_MAX + 1] = {
+	[NFTA_SECMARK_CTX]     = { .type = NLA_STRING, .len = NFT_SECMARK_CTX_MAXLEN },
+};
+
+static int nft_secmark_compute_secid(struct nft_secmark *priv)
+{
+	u32 tmp_secid = 0;
+	int err;
+
+	err = security_secctx_to_secid(priv->ctx, strlen(priv->ctx), &tmp_secid);
+	if (err)
+		return err;
+
+	if (!tmp_secid)
+		return -ENOENT;
+
+	err = security_secmark_relabel_packet(tmp_secid);
+	if (err)
+		return err;
+
+	priv->secid = tmp_secid;
+	return 0;
+}
+
+static void nft_secmark_obj_eval(struct nft_object *obj, struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
+{
+	const struct nft_secmark *priv = nft_obj_data(obj);
+	struct sk_buff *skb = pkt->skb;
+
+	skb->secmark = priv->secid;
+}
+
+static int nft_secmark_obj_init(const struct nft_ctx *ctx,
+				const struct nlattr * const tb[],
+				struct nft_object *obj)
+{
+	struct nft_secmark *priv = nft_obj_data(obj);
+	int err;
+
+	if (tb[NFTA_SECMARK_CTX] == NULL)
+		return -EINVAL;
+
+	priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL);
+	if (!priv->ctx)
+		return -ENOMEM;
+
+	err = nft_secmark_compute_secid(priv);
+	if (err) {
+		kfree(priv->ctx);
+		return err;
+	}
+
+	security_secmark_refcount_inc();
+
+	return 0;
+}
+
+static int nft_secmark_obj_dump(struct sk_buff *skb, struct nft_object *obj,
+				bool reset)
+{
+	struct nft_secmark *priv = nft_obj_data(obj);
+	int err;
+
+	if (nla_put_string(skb, NFTA_SECMARK_CTX, priv->ctx))
+		return -1;
+
+	if (reset) {
+		err = nft_secmark_compute_secid(priv);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void nft_secmark_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
+{
+	struct nft_secmark *priv = nft_obj_data(obj);
+
+	security_secmark_refcount_dec();
+
+	kfree(priv->ctx);
+}
+
+static const struct nft_object_ops nft_secmark_obj_ops = {
+	.type		= &nft_secmark_obj_type,
+	.size		= sizeof(struct nft_secmark),
+	.init		= nft_secmark_obj_init,
+	.eval		= nft_secmark_obj_eval,
+	.dump		= nft_secmark_obj_dump,
+	.destroy	= nft_secmark_obj_destroy,
+};
+struct nft_object_type nft_secmark_obj_type __read_mostly = {
+	.type		= NFT_OBJECT_SECMARK,
+	.ops		= &nft_secmark_obj_ops,
+	.maxattr	= NFTA_SECMARK_MAX,
+	.policy		= nft_secmark_policy,
+	.owner		= THIS_MODULE,
+};
+#endif /* CONFIG_NETWORK_SECMARK */