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, 612 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
new file mode 100644
index 000000000..81afd5ee3
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -0,0 +1,612 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 2020 Felix Fietkau <nbd@nbd.name>
+ */
+
+#include <linux/if_ether.h>
+#include <linux/rhashtable.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/flow_offload.h>
+#include <net/pkt_cls.h>
+#include <net/dsa.h>
+#include "mtk_eth_soc.h"
+#include "mtk_wed.h"
+
+struct mtk_flow_data {
+	struct ethhdr eth;
+
+	union {
+		struct {
+			__be32 src_addr;
+			__be32 dst_addr;
+		} v4;
+
+		struct {
+			struct in6_addr src_addr;
+			struct in6_addr dst_addr;
+		} v6;
+	};
+
+	__be16 src_port;
+	__be16 dst_port;
+
+	u16 vlan_in;
+
+	struct {
+		u16 id;
+		__be16 proto;
+		u8 num;
+	} vlan;
+	struct {
+		u16 sid;
+		u8 num;
+	} pppoe;
+};
+
+static const struct rhashtable_params mtk_flow_ht_params = {
+	.head_offset = offsetof(struct mtk_flow_entry, node),
+	.key_offset = offsetof(struct mtk_flow_entry, cookie),
+	.key_len = sizeof(unsigned long),
+	.automatic_shrinking = true,
+};
+
+static int
+mtk_flow_set_ipv4_addr(struct mtk_eth *eth, struct mtk_foe_entry *foe,
+		       struct mtk_flow_data *data, bool egress)
+{
+	return mtk_foe_entry_set_ipv4_tuple(eth, foe, egress,
+					    data->v4.src_addr, data->src_port,
+					    data->v4.dst_addr, data->dst_port);
+}
+
+static int
+mtk_flow_set_ipv6_addr(struct mtk_eth *eth, struct mtk_foe_entry *foe,
+		       struct mtk_flow_data *data)
+{
+	return mtk_foe_entry_set_ipv6_tuple(eth, foe,
+					    data->v6.src_addr.s6_addr32, data->src_port,
+					    data->v6.dst_addr.s6_addr32, data->dst_port);
+}
+
+static void
+mtk_flow_offload_mangle_eth(const struct flow_action_entry *act, void *eth)
+{
+	void *dest = eth + act->mangle.offset;
+	const void *src = &act->mangle.val;
+
+	if (act->mangle.offset > 8)
+		return;
+
+	if (act->mangle.mask == 0xffff) {
+		src += 2;
+		dest += 2;
+	}
+
+	memcpy(dest, src, act->mangle.mask ? 2 : 4);
+}
+
+static int
+mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_info *info)
+{
+	struct net_device_path_stack stack;
+	struct net_device_path *path;
+	int err;
+
+	if (!dev)
+		return -ENODEV;
+
+	if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED))
+		return -1;
+
+	err = dev_fill_forward_path(dev, addr, &stack);
+	if (err)
+		return err;
+
+	path = &stack.path[stack.num_paths - 1];
+	if (path->type != DEV_PATH_MTK_WDMA)
+		return -1;
+
+	info->wdma_idx = path->mtk_wdma.wdma_idx;
+	info->queue = path->mtk_wdma.queue;
+	info->bss = path->mtk_wdma.bss;
+	info->wcid = path->mtk_wdma.wcid;
+
+	return 0;
+}
+
+
+static int
+mtk_flow_mangle_ports(const struct flow_action_entry *act,
+		      struct mtk_flow_data *data)
+{
+	u32 val = ntohl(act->mangle.val);
+
+	switch (act->mangle.offset) {
+	case 0:
+		if (act->mangle.mask == ~htonl(0xffff))
+			data->dst_port = cpu_to_be16(val);
+		else
+			data->src_port = cpu_to_be16(val >> 16);
+		break;
+	case 2:
+		data->dst_port = cpu_to_be16(val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+mtk_flow_mangle_ipv4(const struct flow_action_entry *act,
+		     struct mtk_flow_data *data)
+{
+	__be32 *dest;
+
+	switch (act->mangle.offset) {
+	case offsetof(struct iphdr, saddr):
+		dest = &data->v4.src_addr;
+		break;
+	case offsetof(struct iphdr, daddr):
+		dest = &data->v4.dst_addr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	memcpy(dest, &act->mangle.val, sizeof(u32));
+
+	return 0;
+}
+
+static int
+mtk_flow_get_dsa_port(struct net_device **dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct dsa_port *dp;
+
+	dp = dsa_port_from_netdev(*dev);
+	if (IS_ERR(dp))
+		return -ENODEV;
+
+	if (dp->cpu_dp->tag_ops->proto != DSA_TAG_PROTO_MTK)
+		return -ENODEV;
+
+	*dev = dsa_port_to_master(dp);
+
+	return dp->index;
+#else
+	return -ENODEV;
+#endif
+}
+
+static int
+mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe,
+			   struct net_device *dev, const u8 *dest_mac,
+			   int *wed_index)
+{
+	struct mtk_wdma_info info = {};
+	int pse_port, dsa_port, queue;
+
+	if (mtk_flow_get_wdma_info(dev, dest_mac, &info) == 0) {
+		mtk_foe_entry_set_wdma(eth, foe, info.wdma_idx, info.queue,
+				       info.bss, info.wcid);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+			switch (info.wdma_idx) {
+			case 0:
+				pse_port = 8;
+				break;
+			case 1:
+				pse_port = 9;
+				break;
+			default:
+				return -EINVAL;
+			}
+		} else {
+			pse_port = 3;
+		}
+		*wed_index = info.wdma_idx;
+		goto out;
+	}
+
+	dsa_port = mtk_flow_get_dsa_port(&dev);
+
+	if (dev == eth->netdev[0])
+		pse_port = 1;
+	else if (dev == eth->netdev[1])
+		pse_port = 2;
+	else
+		return -EOPNOTSUPP;
+
+	if (dsa_port >= 0) {
+		mtk_foe_entry_set_dsa(eth, foe, dsa_port);
+		queue = 3 + dsa_port;
+	} else {
+		queue = pse_port - 1;
+	}
+	mtk_foe_entry_set_queue(eth, foe, queue);
+
+out:
+	mtk_foe_entry_set_pse_port(eth, foe, pse_port);
+
+	return 0;
+}
+
+static int
+mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_action_entry *act;
+	struct mtk_flow_data data = {};
+	struct mtk_foe_entry foe;
+	struct net_device *odev = NULL;
+	struct mtk_flow_entry *entry;
+	int offload_type = 0;
+	int wed_index = -1;
+	u16 addr_type = 0;
+	u8 l4proto = 0;
+	int err = 0;
+	int i;
+
+	if (rhashtable_lookup(&eth->flow_table, &f->cookie, mtk_flow_ht_params))
+		return -EEXIST;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) {
+		struct flow_match_meta match;
+
+		flow_rule_match_meta(rule, &match);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		l4proto = match.key->ip_proto;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	switch (addr_type) {
+	case 0:
+		offload_type = MTK_PPE_PKT_TYPE_BRIDGE;
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+			struct flow_match_eth_addrs match;
+
+			flow_rule_match_eth_addrs(rule, &match);
+			memcpy(data.eth.h_dest, match.key->dst, ETH_ALEN);
+			memcpy(data.eth.h_source, match.key->src, ETH_ALEN);
+		} else {
+			return -EOPNOTSUPP;
+		}
+
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+			struct flow_match_vlan match;
+
+			flow_rule_match_vlan(rule, &match);
+
+			if (match.key->vlan_tpid != cpu_to_be16(ETH_P_8021Q))
+				return -EOPNOTSUPP;
+
+			data.vlan_in = match.key->vlan_id;
+		}
+		break;
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		offload_type = MTK_PPE_PKT_TYPE_IPV4_HNAPT;
+		break;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		offload_type = MTK_PPE_PKT_TYPE_IPV6_ROUTE_5T;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
+				return -EOPNOTSUPP;
+			if (act->mangle.htype == FLOW_ACT_MANGLE_HDR_TYPE_ETH)
+				mtk_flow_offload_mangle_eth(act, &data.eth);
+			break;
+		case FLOW_ACTION_REDIRECT:
+			odev = act->dev;
+			break;
+		case FLOW_ACTION_CSUM:
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+			if (data.vlan.num == 1 ||
+			    act->vlan.proto != htons(ETH_P_8021Q))
+				return -EOPNOTSUPP;
+
+			data.vlan.id = act->vlan.vid;
+			data.vlan.proto = act->vlan.proto;
+			data.vlan.num++;
+			break;
+		case FLOW_ACTION_VLAN_POP:
+			break;
+		case FLOW_ACTION_PPPOE_PUSH:
+			if (data.pppoe.num == 1)
+				return -EOPNOTSUPP;
+
+			data.pppoe.sid = act->pppoe.sid;
+			data.pppoe.num++;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (!is_valid_ether_addr(data.eth.h_source) ||
+	    !is_valid_ether_addr(data.eth.h_dest))
+		return -EINVAL;
+
+	err = mtk_foe_entry_prepare(eth, &foe, offload_type, l4proto, 0,
+				    data.eth.h_source, data.eth.h_dest);
+	if (err)
+		return err;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports ports;
+
+		if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		flow_rule_match_ports(rule, &ports);
+		data.src_port = ports.key->src;
+		data.dst_port = ports.key->dst;
+	} else if (offload_type != MTK_PPE_PKT_TYPE_BRIDGE) {
+		return -EOPNOTSUPP;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_match_ipv4_addrs addrs;
+
+		flow_rule_match_ipv4_addrs(rule, &addrs);
+
+		data.v4.src_addr = addrs.key->src;
+		data.v4.dst_addr = addrs.key->dst;
+
+		mtk_flow_set_ipv4_addr(eth, &foe, &data, false);
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_match_ipv6_addrs addrs;
+
+		flow_rule_match_ipv6_addrs(rule, &addrs);
+
+		data.v6.src_addr = addrs.key->src;
+		data.v6.dst_addr = addrs.key->dst;
+
+		mtk_flow_set_ipv6_addr(eth, &foe, &data);
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		if (act->id != FLOW_ACTION_MANGLE)
+			continue;
+
+		if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		switch (act->mangle.htype) {
+		case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+		case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+			err = mtk_flow_mangle_ports(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+			err = mtk_flow_mangle_ipv4(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+			/* handled earlier */
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		if (err)
+			return err;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		err = mtk_flow_set_ipv4_addr(eth, &foe, &data, true);
+		if (err)
+			return err;
+	}
+
+	if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
+		foe.bridge.vlan = data.vlan_in;
+
+	if (data.vlan.num == 1) {
+		if (data.vlan.proto != htons(ETH_P_8021Q))
+			return -EOPNOTSUPP;
+
+		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.id);
+	}
+	if (data.pppoe.num == 1)
+		mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid);
+
+	err = mtk_flow_set_output_device(eth, &foe, odev, data.eth.h_dest,
+					 &wed_index);
+	if (err)
+		return err;
+
+	if (wed_index >= 0 && (err = mtk_wed_flow_add(wed_index)) < 0)
+		return err;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->cookie = f->cookie;
+	memcpy(&entry->data, &foe, sizeof(entry->data));
+	entry->wed_index = wed_index;
+
+	err = mtk_foe_entry_commit(eth->ppe[entry->ppe_index], entry);
+	if (err < 0)
+		goto free;
+
+	err = rhashtable_insert_fast(&eth->flow_table, &entry->node,
+				     mtk_flow_ht_params);
+	if (err < 0)
+		goto clear;
+
+	return 0;
+
+clear:
+	mtk_foe_entry_clear(eth->ppe[entry->ppe_index], entry);
+free:
+	kfree(entry);
+	if (wed_index >= 0)
+	    mtk_wed_flow_remove(wed_index);
+	return err;
+}
+
+static int
+mtk_flow_offload_destroy(struct mtk_eth *eth, struct flow_cls_offload *f)
+{
+	struct mtk_flow_entry *entry;
+
+	entry = rhashtable_lookup(&eth->flow_table, &f->cookie,
+				  mtk_flow_ht_params);
+	if (!entry)
+		return -ENOENT;
+
+	mtk_foe_entry_clear(eth->ppe[entry->ppe_index], entry);
+	rhashtable_remove_fast(&eth->flow_table, &entry->node,
+			       mtk_flow_ht_params);
+	if (entry->wed_index >= 0)
+		mtk_wed_flow_remove(entry->wed_index);
+	kfree(entry);
+
+	return 0;
+}
+
+static int
+mtk_flow_offload_stats(struct mtk_eth *eth, struct flow_cls_offload *f)
+{
+	struct mtk_flow_entry *entry;
+	u32 idle;
+
+	entry = rhashtable_lookup(&eth->flow_table, &f->cookie,
+				  mtk_flow_ht_params);
+	if (!entry)
+		return -ENOENT;
+
+	idle = mtk_foe_entry_idle_time(eth->ppe[entry->ppe_index], entry);
+	f->stats.lastused = jiffies - idle * HZ;
+
+	return 0;
+}
+
+static DEFINE_MUTEX(mtk_flow_offload_mutex);
+
+static int
+mtk_eth_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+	struct flow_cls_offload *cls = type_data;
+	struct net_device *dev = cb_priv;
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_eth *eth = mac->hw;
+	int err;
+
+	if (!tc_can_offload(dev))
+		return -EOPNOTSUPP;
+
+	if (type != TC_SETUP_CLSFLOWER)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&mtk_flow_offload_mutex);
+	switch (cls->command) {
+	case FLOW_CLS_REPLACE:
+		err = mtk_flow_offload_replace(eth, cls);
+		break;
+	case FLOW_CLS_DESTROY:
+		err = mtk_flow_offload_destroy(eth, cls);
+		break;
+	case FLOW_CLS_STATS:
+		err = mtk_flow_offload_stats(eth, cls);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+	mutex_unlock(&mtk_flow_offload_mutex);
+
+	return err;
+}
+
+static int
+mtk_eth_setup_tc_block(struct net_device *dev, struct flow_block_offload *f)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_eth *eth = mac->hw;
+	static LIST_HEAD(block_cb_list);
+	struct flow_block_cb *block_cb;
+	flow_setup_cb_t *cb;
+
+	if (!eth->soc->offload_version)
+		return -EOPNOTSUPP;
+
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	cb = mtk_eth_setup_tc_block_cb;
+	f->driver_block_list = &block_cb_list;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, dev);
+		if (block_cb) {
+			flow_block_cb_incref(block_cb);
+			return 0;
+		}
+		block_cb = flow_block_cb_alloc(cb, dev, dev, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, dev);
+		if (!block_cb)
+			return -ENOENT;
+
+		if (flow_block_cb_decref(block_cb)) {
+			flow_block_cb_remove(block_cb, f);
+			list_del(&block_cb->driver_list);
+		}
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int mtk_eth_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		     void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+	case TC_SETUP_FT:
+		return mtk_eth_setup_tc_block(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int mtk_eth_offload_init(struct mtk_eth *eth)
+{
+	return rhashtable_init(&eth->flow_table, &mtk_flow_ht_params);
+}