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, 436 insertions, 0 deletions

diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
new file mode 100644
index 000000000..6eb21a4f5
--- /dev/null
+++ b/net/netfilter/nft_cmp.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/if_arp.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables_offload.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_cmp_expr {
+	struct nft_data		data;
+	u8			sreg;
+	u8			len;
+	enum nft_cmp_ops	op:8;
+};
+
+void nft_cmp_eval(const struct nft_expr *expr,
+		  struct nft_regs *regs,
+		  const struct nft_pktinfo *pkt)
+{
+	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+	int d;
+
+	d = memcmp(&regs->data[priv->sreg], &priv->data, priv->len);
+	switch (priv->op) {
+	case NFT_CMP_EQ:
+		if (d != 0)
+			goto mismatch;
+		break;
+	case NFT_CMP_NEQ:
+		if (d == 0)
+			goto mismatch;
+		break;
+	case NFT_CMP_LT:
+		if (d == 0)
+			goto mismatch;
+		fallthrough;
+	case NFT_CMP_LTE:
+		if (d > 0)
+			goto mismatch;
+		break;
+	case NFT_CMP_GT:
+		if (d == 0)
+			goto mismatch;
+		fallthrough;
+	case NFT_CMP_GTE:
+		if (d < 0)
+			goto mismatch;
+		break;
+	}
+	return;
+
+mismatch:
+	regs->verdict.code = NFT_BREAK;
+}
+
+static const struct nla_policy nft_cmp_policy[NFTA_CMP_MAX + 1] = {
+	[NFTA_CMP_SREG]		= { .type = NLA_U32 },
+	[NFTA_CMP_OP]		= { .type = NLA_U32 },
+	[NFTA_CMP_DATA]		= { .type = NLA_NESTED },
+};
+
+static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_cmp_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data),
+	};
+	int err;
+
+	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return err;
+
+	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	priv->op  = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
+	priv->len = desc.len;
+	return 0;
+}
+
+static int nft_cmp_dump(struct sk_buff *skb,
+			const struct nft_expr *expr, bool reset)
+{
+	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(priv->op)))
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+union nft_cmp_offload_data {
+	u16	val16;
+	u32	val32;
+	u64	val64;
+};
+
+static void nft_payload_n2h(union nft_cmp_offload_data *data,
+			    const u8 *val, u32 len)
+{
+	switch (len) {
+	case 2:
+		data->val16 = ntohs(*((__be16 *)val));
+		break;
+	case 4:
+		data->val32 = ntohl(*((__be32 *)val));
+		break;
+	case 8:
+		data->val64 = be64_to_cpu(*((__be64 *)val));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
+static int __nft_cmp_offload(struct nft_offload_ctx *ctx,
+			     struct nft_flow_rule *flow,
+			     const struct nft_cmp_expr *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->sreg];
+	union nft_cmp_offload_data _data, _datamask;
+	u8 *mask = (u8 *)&flow->match.mask;
+	u8 *key = (u8 *)&flow->match.key;
+	u8 *data, *datamask;
+
+	if (priv->op != NFT_CMP_EQ || priv->len > reg->len)
+		return -EOPNOTSUPP;
+
+	if (reg->flags & NFT_OFFLOAD_F_NETWORK2HOST) {
+		nft_payload_n2h(&_data, (u8 *)&priv->data, reg->len);
+		nft_payload_n2h(&_datamask, (u8 *)&reg->mask, reg->len);
+		data = (u8 *)&_data;
+		datamask = (u8 *)&_datamask;
+	} else {
+		data = (u8 *)&priv->data;
+		datamask = (u8 *)&reg->mask;
+	}
+
+	memcpy(key + reg->offset, data, reg->len);
+	memcpy(mask + reg->offset, datamask, reg->len);
+
+	flow->match.dissector.used_keys |= BIT(reg->key);
+	flow->match.dissector.offset[reg->key] = reg->base_offset;
+
+	if (reg->key == FLOW_DISSECTOR_KEY_META &&
+	    reg->offset == offsetof(struct nft_flow_key, meta.ingress_iftype) &&
+	    nft_reg_load16(priv->data.data) != ARPHRD_ETHER)
+		return -EOPNOTSUPP;
+
+	nft_offload_update_dependency(ctx, &priv->data, reg->len);
+
+	return 0;
+}
+
+static int nft_cmp_offload(struct nft_offload_ctx *ctx,
+			   struct nft_flow_rule *flow,
+			   const struct nft_expr *expr)
+{
+	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+
+	return __nft_cmp_offload(ctx, flow, priv);
+}
+
+static const struct nft_expr_ops nft_cmp_ops = {
+	.type		= &nft_cmp_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp_expr)),
+	.eval		= nft_cmp_eval,
+	.init		= nft_cmp_init,
+	.dump		= nft_cmp_dump,
+	.reduce		= NFT_REDUCE_READONLY,
+	.offload	= nft_cmp_offload,
+};
+
+/* Calculate the mask for the nft_cmp_fast expression. On big endian the
+ * mask needs to include the *upper* bytes when interpreting that data as
+ * something smaller than the full u32, therefore a cpu_to_le32 is done.
+ */
+static u32 nft_cmp_fast_mask(unsigned int len)
+{
+	__le32 mask = cpu_to_le32(~0U >> (sizeof_field(struct nft_cmp_fast_expr,
+					  data) * BITS_PER_BYTE - len));
+
+	return (__force u32)mask;
+}
+
+static int nft_cmp_fast_init(const struct nft_ctx *ctx,
+			     const struct nft_expr *expr,
+			     const struct nlattr * const tb[])
+{
+	struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data data;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(data),
+	};
+	int err;
+
+	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return err;
+
+	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	desc.len *= BITS_PER_BYTE;
+
+	priv->mask = nft_cmp_fast_mask(desc.len);
+	priv->data = data.data[0] & priv->mask;
+	priv->len  = desc.len;
+	priv->inv  = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ;
+	return 0;
+}
+
+static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx,
+				struct nft_flow_rule *flow,
+				const struct nft_expr *expr)
+{
+	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_cmp_expr cmp = {
+		.data	= {
+			.data	= {
+				[0] = priv->data,
+			},
+		},
+		.sreg	= priv->sreg,
+		.len	= priv->len / BITS_PER_BYTE,
+		.op	= priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ,
+	};
+
+	return __nft_cmp_offload(ctx, flow, &cmp);
+}
+
+static int nft_cmp_fast_dump(struct sk_buff *skb,
+			     const struct nft_expr *expr, bool reset)
+{
+	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ;
+	struct nft_data data;
+
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op)))
+		goto nla_put_failure;
+
+	data.data[0] = priv->data;
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &data,
+			  NFT_DATA_VALUE, priv->len / BITS_PER_BYTE) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+const struct nft_expr_ops nft_cmp_fast_ops = {
+	.type		= &nft_cmp_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp_fast_expr)),
+	.eval		= NULL,	/* inlined */
+	.init		= nft_cmp_fast_init,
+	.dump		= nft_cmp_fast_dump,
+	.reduce		= NFT_REDUCE_READONLY,
+	.offload	= nft_cmp_fast_offload,
+};
+
+static u32 nft_cmp_mask(u32 bitlen)
+{
+	return (__force u32)cpu_to_le32(~0U >> (sizeof(u32) * BITS_PER_BYTE - bitlen));
+}
+
+static void nft_cmp16_fast_mask(struct nft_data *data, unsigned int bitlen)
+{
+	int len = bitlen / BITS_PER_BYTE;
+	int i, words = len / sizeof(u32);
+
+	for (i = 0; i < words; i++) {
+		data->data[i] = 0xffffffff;
+		bitlen -= sizeof(u32) * BITS_PER_BYTE;
+	}
+
+	if (len % sizeof(u32))
+		data->data[i++] = nft_cmp_mask(bitlen);
+
+	for (; i < 4; i++)
+		data->data[i] = 0;
+}
+
+static int nft_cmp16_fast_init(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nlattr * const tb[])
+{
+	struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data),
+	};
+	int err;
+
+	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return err;
+
+	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	nft_cmp16_fast_mask(&priv->mask, desc.len * BITS_PER_BYTE);
+	priv->inv = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ;
+	priv->len = desc.len;
+
+	return 0;
+}
+
+static int nft_cmp16_fast_offload(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_expr *expr)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_cmp_expr cmp = {
+		.data	= priv->data,
+		.sreg	= priv->sreg,
+		.len	= priv->len,
+		.op	= priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ,
+	};
+
+	return __nft_cmp_offload(ctx, flow, &cmp);
+}
+
+static int nft_cmp16_fast_dump(struct sk_buff *skb,
+			       const struct nft_expr *expr, bool reset)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ;
+
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op)))
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+
+const struct nft_expr_ops nft_cmp16_fast_ops = {
+	.type		= &nft_cmp_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp16_fast_expr)),
+	.eval		= NULL,	/* inlined */
+	.init		= nft_cmp16_fast_init,
+	.dump		= nft_cmp16_fast_dump,
+	.reduce		= NFT_REDUCE_READONLY,
+	.offload	= nft_cmp16_fast_offload,
+};
+
+static const struct nft_expr_ops *
+nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
+{
+	struct nft_data data;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(data),
+	};
+	enum nft_cmp_ops op;
+	u8 sreg;
+	int err;
+
+	if (tb[NFTA_CMP_SREG] == NULL ||
+	    tb[NFTA_CMP_OP] == NULL ||
+	    tb[NFTA_CMP_DATA] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
+	switch (op) {
+	case NFT_CMP_EQ:
+	case NFT_CMP_NEQ:
+	case NFT_CMP_LT:
+	case NFT_CMP_LTE:
+	case NFT_CMP_GT:
+	case NFT_CMP_GTE:
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
+
+	if (op == NFT_CMP_EQ || op == NFT_CMP_NEQ) {
+		if (desc.len <= sizeof(u32))
+			return &nft_cmp_fast_ops;
+		else if (desc.len <= sizeof(data) &&
+			 ((sreg >= NFT_REG_1 && sreg <= NFT_REG_4) ||
+			  (sreg >= NFT_REG32_00 && sreg <= NFT_REG32_12 && sreg % 2 == 0)))
+			return &nft_cmp16_fast_ops;
+	}
+	return &nft_cmp_ops;
+}
+
+struct nft_expr_type nft_cmp_type __read_mostly = {
+	.name		= "cmp",
+	.select_ops	= nft_cmp_select_ops,
+	.policy		= nft_cmp_policy,
+	.maxattr	= NFTA_CMP_MAX,
+	.owner		= THIS_MODULE,
+};