diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index f046e73..5dfd123 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -4,5 +4,5 @@
 #
 
 obj-$(CONFIG_NET_MEDIATEK_SOC)			+= mtk_eth.o
-mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o mtk_eth_dbg.o
+mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o mtk_eth_dbg.o mtk_ppe.o mtk_ppe_debugfs.o mtk_ppe_offload.o
 obj-$(CONFIG_NET_MEDIATEK_HNAT)			+= mtk_hnat/
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 532e961..9ea2155 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2638,12 +2638,17 @@ static int mtk_open(struct net_device *dev)
 
 	/* we run 2 netdevs on the same dma ring so we only bring it up once */
 	if (!refcount_read(&eth->dma_refcnt)) {
-		int err = mtk_start_dma(eth);
+		u32 gdm_config = MTK_GDMA_TO_PDMA;
+		int err;
 
+		err = mtk_start_dma(eth);
 		if (err)
 			return err;
 
-		mtk_gdm_config(eth, MTK_GDMA_TO_PDMA);
+		if (eth->soc->offload_version && mtk_ppe_start(&eth->ppe) == 0)
+			gdm_config = MTK_GDMA_TO_PPE;
+
+		mtk_gdm_config(eth, gdm_config);
 
 		/* Indicates CDM to parse the MTK special tag from CPU */
 		if (netdev_uses_dsa(dev)) {
@@ -2735,6 +2740,9 @@ static int mtk_stop(struct net_device *dev)
 
 	mtk_dma_free(eth);
 
+	if (eth->soc->offload_version)
+		mtk_ppe_stop(&eth->ppe);
+
 	return 0;
 }
 
@@ -3277,6 +3285,7 @@ static const struct net_device_ops mtk_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= mtk_poll_controller,
 #endif
+	.ndo_setup_tc		= mtk_eth_setup_tc,
 };
 
 static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
@@ -3558,6 +3567,17 @@ static int mtk_probe(struct platform_device *pdev)
 			goto err_free_dev;
 	}
 
+	if (eth->soc->offload_version) {
+		err = mtk_ppe_init(&eth->ppe, eth->dev,
+				   eth->base + MTK_ETH_PPE_BASE, 2);
+		if (err)
+			goto err_free_dev;
+
+		err = mtk_eth_offload_init(eth);
+		if (err)
+			goto err_free_dev;
+	}
+
 	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->netdev[i])
 			continue;
@@ -3649,6 +3669,7 @@ static const struct mtk_soc_data mt7621_data = {
 	.required_clks = MT7621_CLKS_BITMAP,
 	.required_pctl = false,
 	.has_sram = false,
+	.offload_version = 2,
 };
 
 static const struct mtk_soc_data mt7622_data = {
@@ -3658,6 +3679,7 @@ static const struct mtk_soc_data mt7622_data = {
 	.required_clks = MT7622_CLKS_BITMAP,
 	.required_pctl = false,
 	.has_sram = false,
+	.offload_version = 2,
 };
 
 static const struct mtk_soc_data mt7623_data = {
@@ -3666,6 +3688,7 @@ static const struct mtk_soc_data mt7623_data = {
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 	.has_sram = false,
+	.offload_version = 2,
 };
 
 static const struct mtk_soc_data mt7629_data = {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 00c5280..a59ac67 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -15,6 +15,8 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/refcount.h>
 #include <linux/phylink.h>
+#include <linux/rhashtable.h>
+#include "mtk_ppe.h"
 
 #define MTK_QDMA_PAGE_SIZE	2048
 #define	MTK_MAX_RX_LENGTH	1536
@@ -37,7 +39,8 @@
 				 NETIF_F_HW_VLAN_CTAG_TX | \
 				 NETIF_F_SG | NETIF_F_TSO | \
 				 NETIF_F_TSO6 | \
-				 NETIF_F_IPV6_CSUM)
+				 NETIF_F_IPV6_CSUM |\
+				 NETIF_F_HW_TC)
 #define MTK_SET_FEATURES	(NETIF_F_LRO | \
 				 NETIF_F_HW_VLAN_CTAG_RX)
 #define MTK_HW_FEATURES_MT7628	(NETIF_F_SG | NETIF_F_RXCSUM)
@@ -95,6 +98,7 @@
 #define MTK_GDMA_TCS_EN		BIT(21)
 #define MTK_GDMA_UCS_EN		BIT(20)
 #define MTK_GDMA_TO_PDMA	0x0
+#define MTK_GDMA_TO_PPE		0x4444
 #define MTK_GDMA_DROP_ALL	0x7777
 
 /* Unicast Filter MAC Address Register - Low */
@@ -524,6 +528,12 @@
 
 #define RX_DMA_GET_SPORT(_x) 	(((_x) >> RX_DMA_SPORT_SHIFT) & RX_DMA_SPORT_MASK)
 
+/* PDMA V1 descriptor rxd4 */
+#define MTK_RXD4_FOE_ENTRY	GENMASK(13, 0)
+#define MTK_RXD4_PPE_CPU_REASON	GENMASK(18, 14)
+#define MTK_RXD4_SRC_PORT	GENMASK(21, 19)
+#define MTK_RXD4_ALG		GENMASK(31, 22)
+
 /* PDMA V2 descriptor rxd3 */
 #define RX_DMA_VTAG_V2          BIT(0)
 #define RX_DMA_L4_VALID_V2      BIT(2)
@@ -1120,6 +1130,7 @@ struct mtk_soc_data {
 	u32		caps;
 	u32		required_clks;
 	bool		required_pctl;
+	u8		offload_version;
 	netdev_features_t hw_features;
 	bool		has_sram;
 };
@@ -1221,7 +1232,10 @@ struct mtk_eth {
 	u32				tx_int_status_reg;
 	u32				rx_dma_l4_valid;
 	int				ip_align;
 	spinlock_t			syscfg0_lock;
+
+	struct mtk_ppe			ppe;
+	struct rhashtable		flow_table;
 };
 
 /* struct mtk_mac -	the structure that holds the info about the MACs of the
@@ -1266,4 +1280,9 @@ int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id);
 
+int mtk_eth_offload_init(struct mtk_eth *eth);
+int mtk_eth_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		     void *type_data);
+
+
 #endif /* MTK_ETH_H */
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
new file mode 100644
index 0000000..b14d64e
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Felix Fietkau <nbd@nbd.name> */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include "mtk_ppe.h"
+#include "mtk_ppe_regs.h"
+
+static void ppe_w32(struct mtk_ppe *ppe, u32 reg, u32 val)
+{
+	writel(val, ppe->base + reg);
+}
+
+static u32 ppe_r32(struct mtk_ppe *ppe, u32 reg)
+{
+	return readl(ppe->base + reg);
+}
+
+static u32 ppe_m32(struct mtk_ppe *ppe, u32 reg, u32 mask, u32 set)
+{
+	u32 val;
+
+	val = ppe_r32(ppe, reg);
+	val &= ~mask;
+	val |= set;
+	ppe_w32(ppe, reg, val);
+
+	return val;
+}
+
+static u32 ppe_set(struct mtk_ppe *ppe, u32 reg, u32 val)
+{
+	return ppe_m32(ppe, reg, 0, val);
+}
+
+static u32 ppe_clear(struct mtk_ppe *ppe, u32 reg, u32 val)
+{
+	return ppe_m32(ppe, reg, val, 0);
+}
+
+static int mtk_ppe_wait_busy(struct mtk_ppe *ppe)
+{
+	int ret;
+	u32 val;
+
+	ret = readl_poll_timeout(ppe->base + MTK_PPE_GLO_CFG, val,
+				 !(val & MTK_PPE_GLO_CFG_BUSY),
+				 20, MTK_PPE_WAIT_TIMEOUT_US);
+
+	if (ret)
+		dev_err(ppe->dev, "PPE table busy");
+
+	return ret;
+}
+
+static void mtk_ppe_cache_clear(struct mtk_ppe *ppe)
+{
+	ppe_set(ppe, MTK_PPE_CACHE_CTL, MTK_PPE_CACHE_CTL_CLEAR);
+	ppe_clear(ppe, MTK_PPE_CACHE_CTL, MTK_PPE_CACHE_CTL_CLEAR);
+}
+
+static void mtk_ppe_cache_enable(struct mtk_ppe *ppe, bool enable)
+{
+	mtk_ppe_cache_clear(ppe);
+
+	ppe_m32(ppe, MTK_PPE_CACHE_CTL, MTK_PPE_CACHE_CTL_EN,
+		enable * MTK_PPE_CACHE_CTL_EN);
+}
+
+static u32 mtk_ppe_hash_entry(struct mtk_foe_entry *e)
+{
+	u32 hv1, hv2, hv3;
+	u32 hash;
+
+	switch (FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, e->ib1)) {
+		case MTK_PPE_PKT_TYPE_BRIDGE:
+			hv1 = e->bridge.src_mac_lo;
+			hv1 ^= ((e->bridge.src_mac_hi & 0xffff) << 16);
+			hv2 = e->bridge.src_mac_hi >> 16;
+			hv2 ^= e->bridge.dest_mac_lo;
+			hv3 = e->bridge.dest_mac_hi;
+			break;
+		case MTK_PPE_PKT_TYPE_IPV4_ROUTE:
+		case MTK_PPE_PKT_TYPE_IPV4_HNAPT:
+			hv1 = e->ipv4.orig.ports;
+			hv2 = e->ipv4.orig.dest_ip;
+			hv3 = e->ipv4.orig.src_ip;
+			break;
+		case MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		case MTK_PPE_PKT_TYPE_IPV6_ROUTE_5T:
+			hv1 = e->ipv6.src_ip[3] ^ e->ipv6.dest_ip[3];
+			hv1 ^= e->ipv6.ports;
+
+			hv2 = e->ipv6.src_ip[2] ^ e->ipv6.dest_ip[2];
+			hv2 ^= e->ipv6.dest_ip[0];
+
+			hv3 = e->ipv6.src_ip[1] ^ e->ipv6.dest_ip[1];
+			hv3 ^= e->ipv6.src_ip[0];
+			break;
+		case MTK_PPE_PKT_TYPE_IPV4_DSLITE:
+		case MTK_PPE_PKT_TYPE_IPV6_6RD:
+		default:
+			WARN_ON_ONCE(1);
+			return MTK_PPE_HASH_MASK;
+	}
+
+	hash = (hv1 & hv2) | ((~hv1) & hv3);
+	hash = (hash >> 24) | ((hash & 0xffffff) << 8);
+	hash ^= hv1 ^ hv2 ^ hv3;
+	hash ^= hash >> 16;
+	hash <<= 1;
+	hash &= MTK_PPE_ENTRIES - 1;
+
+	return hash;
+}
+
+static inline struct mtk_foe_mac_info *
+mtk_foe_entry_l2(struct mtk_foe_entry *entry)
+{
+	int type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1);
+
+	if (type >= MTK_PPE_PKT_TYPE_IPV4_DSLITE)
+		return &entry->ipv6.l2;
+
+	return &entry->ipv4.l2;
+}
+
+static inline u32 *
+mtk_foe_entry_ib2(struct mtk_foe_entry *entry)
+{
+	int type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1);
+
+	if (type >= MTK_PPE_PKT_TYPE_IPV4_DSLITE)
+		return &entry->ipv6.ib2;
+
+	return &entry->ipv4.ib2;
+}
+
+int mtk_foe_entry_prepare(struct mtk_foe_entry *entry, int type, int l4proto,
+			  u8 pse_port, u8 *src_mac, u8 *dest_mac)
+{
+	struct mtk_foe_mac_info *l2;
+	u32 ports_pad, val;
+
+	memset(entry, 0, sizeof(*entry));
+
+	val = FIELD_PREP(MTK_FOE_IB1_STATE, MTK_FOE_STATE_BIND) |
+	      FIELD_PREP(MTK_FOE_IB1_PACKET_TYPE, type) |
+	      FIELD_PREP(MTK_FOE_IB1_UDP, l4proto == IPPROTO_UDP) |
+	      MTK_FOE_IB1_BIND_TTL |
+	      MTK_FOE_IB1_BIND_CACHE;
+	entry->ib1 = val;
+
+	val = FIELD_PREP(MTK_FOE_IB2_PORT_MG, 0x3f) |
+	      FIELD_PREP(MTK_FOE_IB2_PORT_AG, 0x1f) |
+	      FIELD_PREP(MTK_FOE_IB2_DEST_PORT, pse_port);
+
+	if (is_multicast_ether_addr(dest_mac))
+		val |= MTK_FOE_IB2_MULTICAST;
+
+	ports_pad = 0xa5a5a500 | (l4proto & 0xff);
+	if (type == MTK_PPE_PKT_TYPE_IPV4_ROUTE)
+		entry->ipv4.orig.ports = ports_pad;
+	if (type == MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T)
+		entry->ipv6.ports = ports_pad;
+
+	if (type >= MTK_PPE_PKT_TYPE_IPV4_DSLITE) {
+		entry->ipv6.ib2 = val;
+		l2 = &entry->ipv6.l2;
+	} else {
+		entry->ipv4.ib2 = val;
+		l2 = &entry->ipv4.l2;
+	}
+
+	l2->dest_mac_hi = get_unaligned_be32(dest_mac);
+	l2->dest_mac_lo = get_unaligned_be16(dest_mac + 4);
+	l2->src_mac_hi = get_unaligned_be32(src_mac);
+	l2->src_mac_lo = get_unaligned_be16(src_mac + 4);
+
+	if (type >= MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T)
+		l2->etype = ETH_P_IPV6;
+	else
+		l2->etype = ETH_P_IP;
+
+	return 0;
+}
+
+int mtk_foe_entry_set_pse_port(struct mtk_foe_entry *entry, u8 port)
+{
+	u32 *ib2 = mtk_foe_entry_ib2(entry);
+	u32 val;
+
+	val = *ib2;
+	val &= ~MTK_FOE_IB2_DEST_PORT;
+	val |= FIELD_PREP(MTK_FOE_IB2_DEST_PORT, port);
+	*ib2 = val;
+
+	return 0;
+}
+
+int mtk_foe_entry_set_ipv4_tuple(struct mtk_foe_entry *entry, bool egress,
+				 __be32 src_addr, __be16 src_port,
+				 __be32 dest_addr, __be16 dest_port)
+{
+	int type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1);
+	struct mtk_ipv4_tuple *t;
+
+	switch (type) {
+	case MTK_PPE_PKT_TYPE_IPV4_HNAPT:
+		if (egress) {
+			t = &entry->ipv4.new;
+			break;
+		}
+		fallthrough;
+	case MTK_PPE_PKT_TYPE_IPV4_DSLITE:
+	case MTK_PPE_PKT_TYPE_IPV4_ROUTE:
+		t = &entry->ipv4.orig;
+		break;
+	case MTK_PPE_PKT_TYPE_IPV6_6RD:
+		entry->ipv6_6rd.tunnel_src_ip = be32_to_cpu(src_addr);
+		entry->ipv6_6rd.tunnel_dest_ip = be32_to_cpu(dest_addr);
+		return 0;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	t->src_ip = be32_to_cpu(src_addr);
+	t->dest_ip = be32_to_cpu(dest_addr);
+
+	if (type == MTK_PPE_PKT_TYPE_IPV4_ROUTE)
+		return 0;
+
+	t->src_port = be16_to_cpu(src_port);
+	t->dest_port = be16_to_cpu(dest_port);
+
+	return 0;
+}
+
+int mtk_foe_entry_set_ipv6_tuple(struct mtk_foe_entry *entry,
+				 __be32 *src_addr, __be16 src_port,
+				 __be32 *dest_addr, __be16 dest_port)
+{
+	int type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1);
+	u32 *src, *dest;
+	int i;
+
+	switch (type) {
+	case MTK_PPE_PKT_TYPE_IPV4_DSLITE:
+		src = entry->dslite.tunnel_src_ip;
+		dest = entry->dslite.tunnel_dest_ip;
+		break;
+	case MTK_PPE_PKT_TYPE_IPV6_ROUTE_5T:
+	case MTK_PPE_PKT_TYPE_IPV6_6RD:
+		entry->ipv6.src_port = be16_to_cpu(src_port);
+		entry->ipv6.dest_port = be16_to_cpu(dest_port);
+		fallthrough;
+	case MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		src = entry->ipv6.src_ip;
+		dest = entry->ipv6.dest_ip;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	};
+
+	for (i = 0; i < 4; i++)
+		src[i] = be32_to_cpu(src_addr[i]);
+	for (i = 0; i < 4; i++)
+		dest[i] = be32_to_cpu(dest_addr[i]);
+
+	return 0;
+}
+
+int mtk_foe_entry_set_dsa(struct mtk_foe_entry *entry, int port)
+{
+	struct mtk_foe_mac_info *l2 = mtk_foe_entry_l2(entry);
+
+	l2->etype = BIT(port);
+
+	if (!(entry->ib1 & MTK_FOE_IB1_BIND_VLAN_LAYER))
+		entry->ib1 |= FIELD_PREP(MTK_FOE_IB1_BIND_VLAN_LAYER, 1);
+	else
+		l2->etype |= BIT(8);
+
+	entry->ib1 &= ~MTK_FOE_IB1_BIND_VLAN_TAG;
+
+	return 0;
+}
+
+int mtk_foe_entry_set_vlan(struct mtk_foe_entry *entry, int vid)
+{
+	struct mtk_foe_mac_info *l2 = mtk_foe_entry_l2(entry);
+
+	switch (FIELD_GET(MTK_FOE_IB1_BIND_VLAN_LAYER, entry->ib1)) {
+	case 0:
+		entry->ib1 |= MTK_FOE_IB1_BIND_VLAN_TAG |
+			      FIELD_PREP(MTK_FOE_IB1_BIND_VLAN_LAYER, 1);
+		l2->vlan1 = vid;
+		return 0;
+	case 1:
+		if (!(entry->ib1 & MTK_FOE_IB1_BIND_VLAN_TAG)) {
+			l2->vlan1 = vid;
+			l2->etype |= BIT(8);
+		} else {
+			l2->vlan2 = vid;
+			entry->ib1 += FIELD_PREP(MTK_FOE_IB1_BIND_VLAN_LAYER, 1);
+		}
+		return 0;
+	default:
+		return -ENOSPC;
+	}
+}
+
+int mtk_foe_entry_set_pppoe(struct mtk_foe_entry *entry, int sid)
+{
+	struct mtk_foe_mac_info *l2 = mtk_foe_entry_l2(entry);
+
+	if (!(entry->ib1 & MTK_FOE_IB1_BIND_VLAN_LAYER) ||
+	    (entry->ib1 & MTK_FOE_IB1_BIND_VLAN_TAG))
+		l2->etype = ETH_P_PPP_SES;
+
+	entry->ib1 |= MTK_FOE_IB1_BIND_PPPOE;
+	l2->pppoe_id = sid;
+
+	return 0;
+}
+
+static inline bool mtk_foe_entry_usable(struct mtk_foe_entry *entry)
+{
+	return !(entry->ib1 & MTK_FOE_IB1_STATIC) &&
+	       FIELD_GET(MTK_FOE_IB1_STATE, entry->ib1) != MTK_FOE_STATE_BIND;
+}
+
+int mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_foe_entry *entry,
+			 u16 timestamp)
+{
+	struct mtk_foe_entry *hwe;
+	u32 hash;
+
+	timestamp &= MTK_FOE_IB1_BIND_TIMESTAMP;
+	entry->ib1 &= ~MTK_FOE_IB1_BIND_TIMESTAMP;
+	entry->ib1 |= FIELD_PREP(MTK_FOE_IB1_BIND_TIMESTAMP, timestamp);
+
+	hash = mtk_ppe_hash_entry(entry);
+	hwe = &ppe->foe_table[hash];
+	if (!mtk_foe_entry_usable(hwe)) {
+		hwe++;
+		hash++;
+
+		if (!mtk_foe_entry_usable(hwe))
+			return -ENOSPC;
+	}
+
+	memcpy(&hwe->data, &entry->data, sizeof(hwe->data));
+	wmb();
+	hwe->ib1 = entry->ib1;
+
+	dma_wmb();
+
+	mtk_ppe_cache_clear(ppe);
+
+	return hash;
+}
+
+int mtk_ppe_init(struct mtk_ppe *ppe, struct device *dev, void __iomem *base,
+		 int version)
+{
+	struct mtk_foe_entry *foe;
+
+	/* need to allocate a separate device, since it PPE DMA access is
+	 * not coherent.
+	 */
+	ppe->base = base;
+	ppe->dev = dev;
+	ppe->version = version;
+
+	foe = dmam_alloc_coherent(ppe->dev, MTK_PPE_ENTRIES * sizeof(*foe),
+				  &ppe->foe_phys, GFP_KERNEL);
+	if (!foe)
+		return -ENOMEM;
+
+	ppe->foe_table = foe;
+
+	mtk_ppe_debugfs_init(ppe);
+
+	return 0;
+}
+
+static void mtk_ppe_init_foe_table(struct mtk_ppe *ppe)
+{
+	static const u8 skip[] = { 12, 25, 38, 51, 76, 89, 102 };
+	int i, k;
+
+	memset(ppe->foe_table, 0, MTK_PPE_ENTRIES * sizeof(ppe->foe_table));
+
+	if (!IS_ENABLED(CONFIG_SOC_MT7621))
+		return;
+
+	/* skip all entries that cross the 1024 byte boundary */
+	for (i = 0; i < MTK_PPE_ENTRIES; i += 128)
+		for (k = 0; k < ARRAY_SIZE(skip); k++)
+			ppe->foe_table[i + skip[k]].ib1 |= MTK_FOE_IB1_STATIC;
+}
+
+int mtk_ppe_start(struct mtk_ppe *ppe)
+{
+	u32 val;
+
+	mtk_ppe_init_foe_table(ppe);
+	ppe_w32(ppe, MTK_PPE_TB_BASE, ppe->foe_phys);
+
+	val = MTK_PPE_TB_CFG_ENTRY_80B |
+	      MTK_PPE_TB_CFG_AGE_NON_L4 |
+	      MTK_PPE_TB_CFG_AGE_UNBIND |
+	      MTK_PPE_TB_CFG_AGE_TCP |
+	      MTK_PPE_TB_CFG_AGE_UDP |
+	      MTK_PPE_TB_CFG_AGE_TCP_FIN |
+	      FIELD_PREP(MTK_PPE_TB_CFG_SEARCH_MISS,
+			 MTK_PPE_SEARCH_MISS_ACTION_FORWARD_BUILD) |
+	      FIELD_PREP(MTK_PPE_TB_CFG_KEEPALIVE,
+			 MTK_PPE_KEEPALIVE_DISABLE) |
+	      FIELD_PREP(MTK_PPE_TB_CFG_HASH_MODE, 1) |
+	      FIELD_PREP(MTK_PPE_TB_CFG_SCAN_MODE,
+			 MTK_PPE_SCAN_MODE_KEEPALIVE_AGE) |
+	      FIELD_PREP(MTK_PPE_TB_CFG_ENTRY_NUM,
+			 MTK_PPE_ENTRIES_SHIFT);
+	ppe_w32(ppe, MTK_PPE_TB_CFG, val);
+
+	ppe_w32(ppe, MTK_PPE_IP_PROTO_CHK,
+		MTK_PPE_IP_PROTO_CHK_IPV4 | MTK_PPE_IP_PROTO_CHK_IPV6);
+
+	mtk_ppe_cache_enable(ppe, true);
+
+	val = MTK_PPE_FLOW_CFG_IP4_TCP_FRAG |
+	      MTK_PPE_FLOW_CFG_IP4_UDP_FRAG |
+	      MTK_PPE_FLOW_CFG_IP6_3T_ROUTE |
+	      MTK_PPE_FLOW_CFG_IP6_5T_ROUTE |
+	      MTK_PPE_FLOW_CFG_IP6_6RD |
+	      MTK_PPE_FLOW_CFG_IP4_NAT |
+	      MTK_PPE_FLOW_CFG_IP4_NAPT |
+	      MTK_PPE_FLOW_CFG_IP4_DSLITE |
+	      MTK_PPE_FLOW_CFG_L2_BRIDGE |
+	      MTK_PPE_FLOW_CFG_IP4_NAT_FRAG;
+	ppe_w32(ppe, MTK_PPE_FLOW_CFG, val);
+
+	val = FIELD_PREP(MTK_PPE_UNBIND_AGE_MIN_PACKETS, 1000) |
+	      FIELD_PREP(MTK_PPE_UNBIND_AGE_DELTA, 3);
+	ppe_w32(ppe, MTK_PPE_UNBIND_AGE, val);
+
+	val = FIELD_PREP(MTK_PPE_BIND_AGE0_DELTA_UDP, 12) |
+	      FIELD_PREP(MTK_PPE_BIND_AGE0_DELTA_NON_L4, 1);
+	ppe_w32(ppe, MTK_PPE_BIND_AGE0, val);
+
+	val = FIELD_PREP(MTK_PPE_BIND_AGE1_DELTA_TCP_FIN, 1) |
+	      FIELD_PREP(MTK_PPE_BIND_AGE1_DELTA_TCP, 7);
+	ppe_w32(ppe, MTK_PPE_BIND_AGE1, val);
+
+	val = MTK_PPE_BIND_LIMIT0_QUARTER | MTK_PPE_BIND_LIMIT0_HALF;
+	ppe_w32(ppe, MTK_PPE_BIND_LIMIT0, val);
+
+	val = MTK_PPE_BIND_LIMIT1_FULL |
+	      FIELD_PREP(MTK_PPE_BIND_LIMIT1_NON_L4, 1);
+	ppe_w32(ppe, MTK_PPE_BIND_LIMIT1, val);
+
+	val = FIELD_PREP(MTK_PPE_BIND_RATE_BIND, 30) |
+	      FIELD_PREP(MTK_PPE_BIND_RATE_PREBIND, 1);
+	ppe_w32(ppe, MTK_PPE_BIND_RATE, val);
+
+	/* enable PPE */
+	val = MTK_PPE_GLO_CFG_EN |
+	      MTK_PPE_GLO_CFG_IP4_L4_CS_DROP |
+	      MTK_PPE_GLO_CFG_IP4_CS_DROP |
+	      MTK_PPE_GLO_CFG_FLOW_DROP_UPDATE;
+	ppe_w32(ppe, MTK_PPE_GLO_CFG, val);
+
+	ppe_w32(ppe, MTK_PPE_DEFAULT_CPU_PORT, 0);
+
+	return 0;
+}
+
+int mtk_ppe_stop(struct mtk_ppe *ppe)
+{
+	u32 val;
+	int i;
+
+	for (i = 0; i < MTK_PPE_ENTRIES; i++)
+		ppe->foe_table[i].ib1 = FIELD_PREP(MTK_FOE_IB1_STATE,
+						   MTK_FOE_STATE_INVALID);
+
+	mtk_ppe_cache_enable(ppe, false);
+
+	/* disable offload engine */
+	ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN);
+	ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0);
+
+	/* disable aging */
+	val = MTK_PPE_TB_CFG_AGE_NON_L4 |
+	      MTK_PPE_TB_CFG_AGE_UNBIND |
+	      MTK_PPE_TB_CFG_AGE_TCP |
+	      MTK_PPE_TB_CFG_AGE_UDP |
+	      MTK_PPE_TB_CFG_AGE_TCP_FIN;
+	ppe_clear(ppe, MTK_PPE_TB_CFG, val);
+
+	return mtk_ppe_wait_busy(ppe);
+}
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h
new file mode 100644
index 0000000..242fb8f
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.h
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Felix Fietkau <nbd@nbd.name> */
+
+#ifndef __MTK_PPE_H
+#define __MTK_PPE_H
+
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
+
+#define MTK_ETH_PPE_BASE		0xc00
+
+#define MTK_PPE_ENTRIES_SHIFT		3
+#define MTK_PPE_ENTRIES			(1024 << MTK_PPE_ENTRIES_SHIFT)
+#define MTK_PPE_HASH_MASK		(MTK_PPE_ENTRIES - 1)
+#define MTK_PPE_WAIT_TIMEOUT_US		1000000
+
+#define MTK_FOE_IB1_UNBIND_TIMESTAMP	GENMASK(7, 0)
+#define MTK_FOE_IB1_UNBIND_PACKETS	GENMASK(23, 8)
+#define MTK_FOE_IB1_UNBIND_PREBIND	BIT(24)
+
+#define MTK_FOE_IB1_BIND_TIMESTAMP	GENMASK(14, 0)
+#define MTK_FOE_IB1_BIND_KEEPALIVE	BIT(15)
+#define MTK_FOE_IB1_BIND_VLAN_LAYER	GENMASK(18, 16)
+#define MTK_FOE_IB1_BIND_PPPOE		BIT(19)
+#define MTK_FOE_IB1_BIND_VLAN_TAG	BIT(20)
+#define MTK_FOE_IB1_BIND_PKT_SAMPLE	BIT(21)
+#define MTK_FOE_IB1_BIND_CACHE		BIT(22)
+#define MTK_FOE_IB1_BIND_TUNNEL_DECAP	BIT(23)
+#define MTK_FOE_IB1_BIND_TTL		BIT(24)
+
+#define MTK_FOE_IB1_PACKET_TYPE		GENMASK(27, 25)
+#define MTK_FOE_IB1_STATE		GENMASK(29, 28)
+#define MTK_FOE_IB1_UDP			BIT(30)
+#define MTK_FOE_IB1_STATIC		BIT(31)
+
+enum {
+	MTK_PPE_PKT_TYPE_IPV4_HNAPT = 0,
+	MTK_PPE_PKT_TYPE_IPV4_ROUTE = 1,
+	MTK_PPE_PKT_TYPE_BRIDGE = 2,
+	MTK_PPE_PKT_TYPE_IPV4_DSLITE = 3,
+	MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T = 4,
+	MTK_PPE_PKT_TYPE_IPV6_ROUTE_5T = 5,
+	MTK_PPE_PKT_TYPE_IPV6_6RD = 7,
+};
+
+#define MTK_FOE_IB2_QID			GENMASK(3, 0)
+#define MTK_FOE_IB2_PSE_QOS		BIT(4)
+#define MTK_FOE_IB2_DEST_PORT		GENMASK(7, 5)
+#define MTK_FOE_IB2_MULTICAST		BIT(8)
+
+#define MTK_FOE_IB2_WHNAT_QID2		GENMASK(13, 12)
+#define MTK_FOE_IB2_WHNAT_DEVIDX	BIT(16)
+#define MTK_FOE_IB2_WHNAT_NAT		BIT(17)
+
+#define MTK_FOE_IB2_PORT_MG		GENMASK(17, 12)
+
+#define MTK_FOE_IB2_PORT_AG		GENMASK(23, 18)
+
+#define MTK_FOE_IB2_DSCP		GENMASK(31, 24)
+
+#define MTK_FOE_VLAN2_WHNAT_BSS		GEMMASK(5, 0)
+#define MTK_FOE_VLAN2_WHNAT_WCID	GENMASK(13, 6)
+#define MTK_FOE_VLAN2_WHNAT_RING	GENMASK(15, 14)
+
+enum {
+	MTK_FOE_STATE_INVALID,
+	MTK_FOE_STATE_UNBIND,
+	MTK_FOE_STATE_BIND,
+	MTK_FOE_STATE_FIN
+};
+
+struct mtk_foe_mac_info {
+	u16 vlan1;
+	u16 etype;
+
+	u32 dest_mac_hi;
+
+	u16 vlan2;
+	u16 dest_mac_lo;
+
+	u32 src_mac_hi;
+
+	u16 pppoe_id;
+	u16 src_mac_lo;
+};
+
+struct mtk_foe_bridge {
+	u32 dest_mac_hi;
+
+	u16 src_mac_lo;
+	u16 dest_mac_lo;
+
+	u32 src_mac_hi;
+
+	u32 ib2;
+
+	u32 _rsv[5];
+
+	u32 udf_tsid;
+	struct mtk_foe_mac_info l2;
+};
+
+struct mtk_ipv4_tuple {
+	u32 src_ip;
+	u32 dest_ip;
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 _pad[3]; /* fill with 0xa5a5a5 */
+		};
+		u32 ports;
+	};
+};
+
+struct mtk_foe_ipv4 {
+	struct mtk_ipv4_tuple orig;
+
+	u32 ib2;
+
+	struct mtk_ipv4_tuple new;
+
+	u16 timestamp;
+	u16 _rsv0[3];
+
+	u32 udf_tsid;
+
+	struct mtk_foe_mac_info l2;
+};
+
+struct mtk_foe_ipv4_dslite {
+	struct mtk_ipv4_tuple ip4;
+
+	u32 tunnel_src_ip[4];
+	u32 tunnel_dest_ip[4];
+
+	u8 flow_label[3];
+	u8 priority;
+
+	u32 udf_tsid;
+
+	u32 ib2;
+
+	struct mtk_foe_mac_info l2;
+};
+
+struct mtk_foe_ipv6 {
+	u32 src_ip[4];
+	u32 dest_ip[4];
+
+	union {
+		struct {
+			u8 protocol;
+			u8 _pad[3]; /* fill with 0xa5a5a5 */
+		}; /* 3-tuple */
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		}; /* 5-tuple */
+		u32 ports;
+	};
+
+	u32 _rsv[3];
+
+	u32 udf;
+
+	u32 ib2;
+	struct mtk_foe_mac_info l2;
+};
+
+struct mtk_foe_ipv6_6rd {
+	u32 src_ip[4];
+	u32 dest_ip[4];
+	u16 dest_port;
+	u16 src_port;
+
+	u32 tunnel_src_ip;
+	u32 tunnel_dest_ip;
+
+	u16 hdr_csum;
+	u8 dscp;
+	u8 ttl;
+
+	u8 flag;
+	u8 pad;
+	u8 per_flow_6rd_id;
+	u8 pad2;
+
+	u32 ib2;
+	struct mtk_foe_mac_info l2;
+};
+
+struct mtk_foe_entry {
+	u32 ib1;
+
+	union {
+		struct mtk_foe_bridge bridge;
+		struct mtk_foe_ipv4 ipv4;
+		struct mtk_foe_ipv4_dslite dslite;
+		struct mtk_foe_ipv6 ipv6;
+		struct mtk_foe_ipv6_6rd ipv6_6rd;
+		u32 data[19];
+	};
+};
+
+enum {
+	MTK_PPE_CPU_REASON_TTL_EXCEEDED			= 0x02,
+	MTK_PPE_CPU_REASON_OPTION_HEADER		= 0x03,
+	MTK_PPE_CPU_REASON_NO_FLOW			= 0x07,
+	MTK_PPE_CPU_REASON_IPV4_FRAG			= 0x08,
+	MTK_PPE_CPU_REASON_IPV4_DSLITE_FRAG		= 0x09,
+	MTK_PPE_CPU_REASON_IPV4_DSLITE_NO_TCP_UDP	= 0x0a,
+	MTK_PPE_CPU_REASON_IPV6_6RD_NO_TCP_UDP		= 0x0b,
+	MTK_PPE_CPU_REASON_TCP_FIN_SYN_RST		= 0x0c,
+	MTK_PPE_CPU_REASON_UN_HIT			= 0x0d,
+	MTK_PPE_CPU_REASON_HIT_UNBIND			= 0x0e,
+	MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED	= 0x0f,
+	MTK_PPE_CPU_REASON_HIT_BIND_TCP_FIN		= 0x10,
+	MTK_PPE_CPU_REASON_HIT_TTL_1			= 0x11,
+	MTK_PPE_CPU_REASON_HIT_BIND_VLAN_VIOLATION	= 0x12,
+	MTK_PPE_CPU_REASON_KEEPALIVE_UC_OLD_HDR		= 0x13,
+	MTK_PPE_CPU_REASON_KEEPALIVE_MC_NEW_HDR		= 0x14,
+	MTK_PPE_CPU_REASON_KEEPALIVE_DUP_OLD_HDR	= 0x15,
+	MTK_PPE_CPU_REASON_HIT_BIND_FORCE_CPU		= 0x16,
+	MTK_PPE_CPU_REASON_TUNNEL_OPTION_HEADER		= 0x17,
+	MTK_PPE_CPU_REASON_MULTICAST_TO_CPU		= 0x18,
+	MTK_PPE_CPU_REASON_MULTICAST_TO_GMAC1_CPU	= 0x19,
+	MTK_PPE_CPU_REASON_HIT_PRE_BIND			= 0x1a,
+	MTK_PPE_CPU_REASON_PACKET_SAMPLING		= 0x1b,
+	MTK_PPE_CPU_REASON_EXCEED_MTU			= 0x1c,
+	MTK_PPE_CPU_REASON_PPE_BYPASS			= 0x1e,
+	MTK_PPE_CPU_REASON_INVALID			= 0x1f,
+};
+
+struct mtk_ppe {
+	struct device *dev;
+	void __iomem *base;
+	int version;
+
+	struct mtk_foe_entry *foe_table;
+	dma_addr_t foe_phys;
+
+	void *acct_table;
+};
+
+int mtk_ppe_init(struct mtk_ppe *ppe, struct device *dev, void __iomem *base,
+		 int version);
+int mtk_ppe_start(struct mtk_ppe *ppe);
+int mtk_ppe_stop(struct mtk_ppe *ppe);
+
+static inline void
+mtk_foe_entry_clear(struct mtk_ppe *ppe, u16 hash)
+{
+	ppe->foe_table[hash].ib1 = 0;
+	dma_wmb();
+}
+
+static inline int
+mtk_foe_entry_timestamp(struct mtk_ppe *ppe, u16 hash)
+{
+	u32 ib1 = READ_ONCE(ppe->foe_table[hash].ib1);
+
+	if (FIELD_GET(MTK_FOE_IB1_STATE, ib1) != MTK_FOE_STATE_BIND)
+		return -1;
+
+	return FIELD_GET(MTK_FOE_IB1_BIND_TIMESTAMP, ib1);
+}
+
+int mtk_foe_entry_prepare(struct mtk_foe_entry *entry, int type, int l4proto,
+			  u8 pse_port, u8 *src_mac, u8 *dest_mac);
+int mtk_foe_entry_set_pse_port(struct mtk_foe_entry *entry, u8 port);
+int mtk_foe_entry_set_ipv4_tuple(struct mtk_foe_entry *entry, bool orig,
+				 __be32 src_addr, __be16 src_port,
+				 __be32 dest_addr, __be16 dest_port);
+int mtk_foe_entry_set_ipv6_tuple(struct mtk_foe_entry *entry,
+				 __be32 *src_addr, __be16 src_port,
+				 __be32 *dest_addr, __be16 dest_port);
+int mtk_foe_entry_set_dsa(struct mtk_foe_entry *entry, int port);
+int mtk_foe_entry_set_vlan(struct mtk_foe_entry *entry, int vid);
+int mtk_foe_entry_set_pppoe(struct mtk_foe_entry *entry, int sid);
+int mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_foe_entry *entry,
+			 u16 timestamp);
+int mtk_ppe_debugfs_init(struct mtk_ppe *ppe);
+
+#endif
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c
new file mode 100644
index 0000000..8ae9efa
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Felix Fietkau <nbd@nbd.name> */
+
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+#include "mtk_eth_soc.h"
+
+struct mtk_flow_addr_info
+{
+	void *src, *dest;
+	u16 *src_port, *dest_port;
+	bool ipv6;
+};
+
+static const char *mtk_foe_entry_state_str(int state)
+{
+	static const char * const state_str[] = {
+		[MTK_FOE_STATE_INVALID] = "INV",
+		[MTK_FOE_STATE_UNBIND] = "UNB",
+		[MTK_FOE_STATE_BIND] = "BND",
+		[MTK_FOE_STATE_FIN] = "FIN",
+	};
+
+	if (state >= ARRAY_SIZE(state_str) || !state_str[state])
+		return "UNK";
+
+	return state_str[state];
+}
+
+static const char *mtk_foe_pkt_type_str(int type)
+{
+	static const char * const type_str[] = {
+		[MTK_PPE_PKT_TYPE_IPV4_HNAPT] = "IPv4 5T",
+		[MTK_PPE_PKT_TYPE_IPV4_ROUTE] = "IPv4 3T",
+		[MTK_PPE_PKT_TYPE_BRIDGE] = "L2",
+		[MTK_PPE_PKT_TYPE_IPV4_DSLITE] = "DS-LITE",
+		[MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T] = "IPv6 3T",
+		[MTK_PPE_PKT_TYPE_IPV6_ROUTE_5T] = "IPv6 5T",
+		[MTK_PPE_PKT_TYPE_IPV6_6RD] = "6RD",
+	};
+
+	if (type >= ARRAY_SIZE(type_str) || !type_str[type])
+		return "UNKNOWN";
+
+	return type_str[type];
+}
+
+static void
+mtk_print_addr(struct seq_file *m, u32 *addr, bool ipv6)
+{
+	u32 n_addr[4];
+	int i;
+
+	if (!ipv6) {
+		seq_printf(m, "%pI4h", addr);
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(n_addr); i++)
+		n_addr[i] = htonl(addr[i]);
+	seq_printf(m, "%pI6", n_addr);
+}
+
+static void
+mtk_print_addr_info(struct seq_file *m, struct mtk_flow_addr_info *ai)
+{
+	mtk_print_addr(m, ai->src, ai->ipv6);
+	if (ai->src_port)
+		seq_printf(m, ":%d", *ai->src_port);
+	seq_printf(m, "->");
+	mtk_print_addr(m, ai->dest, ai->ipv6);
+	if (ai->dest_port)
+		seq_printf(m, ":%d", *ai->dest_port);
+}
+
+static int
+mtk_ppe_debugfs_foe_show(struct seq_file *m, void *private, bool bind)
+{
+	struct mtk_ppe *ppe = m->private;
+	int i, count;
+
+	for (i = 0, count = 0; i < MTK_PPE_ENTRIES; i++) {
+		struct mtk_foe_entry *entry = &ppe->foe_table[i];
+		struct mtk_foe_mac_info *l2;
+		struct mtk_flow_addr_info ai = {};
+		unsigned char h_source[ETH_ALEN];
+		unsigned char h_dest[ETH_ALEN];
+		int type, state;
+		u32 ib2;
+
+
+		state = FIELD_GET(MTK_FOE_IB1_STATE, entry->ib1);
+		if (!state)
+			continue;
+
+		if (bind && state != MTK_FOE_STATE_BIND)
+			continue;
+
+		type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1);
+		seq_printf(m, "%05x %s %7s", i,
+			   mtk_foe_entry_state_str(state),
+			   mtk_foe_pkt_type_str(type));
+
+		switch (type) {
+		case MTK_PPE_PKT_TYPE_IPV4_HNAPT:
+		case MTK_PPE_PKT_TYPE_IPV4_DSLITE:
+			ai.src_port = &entry->ipv4.orig.src_port;
+			ai.dest_port = &entry->ipv4.orig.dest_port;
+			fallthrough;
+		case MTK_PPE_PKT_TYPE_IPV4_ROUTE:
+			ai.src = &entry->ipv4.orig.src_ip;
+			ai.dest = &entry->ipv4.orig.dest_ip;
+			break;
+		case MTK_PPE_PKT_TYPE_IPV6_ROUTE_5T:
+			ai.src_port = &entry->ipv6.src_port;
+			ai.dest_port = &entry->ipv6.dest_port;
+			fallthrough;
+		case MTK_PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		case MTK_PPE_PKT_TYPE_IPV6_6RD:
+			ai.src = &entry->ipv6.src_ip;
+			ai.dest = &entry->ipv6.dest_ip;
+			ai.ipv6 = true;
+			break;
+		}
+
+		seq_printf(m, " orig=");
+		mtk_print_addr_info(m, &ai);
+
+		switch (type) {
+		case MTK_PPE_PKT_TYPE_IPV4_HNAPT:
+		case MTK_PPE_PKT_TYPE_IPV4_DSLITE:
+			ai.src_port = &entry->ipv4.new.src_port;
+			ai.dest_port = &entry->ipv4.new.dest_port;
+			fallthrough;
+		case MTK_PPE_PKT_TYPE_IPV4_ROUTE:
+			ai.src = &entry->ipv4.new.src_ip;
+			ai.dest = &entry->ipv4.new.dest_ip;
+			seq_printf(m, " new=");
+			mtk_print_addr_info(m, &ai);
+			break;
+		}
+
+		if (type >= MTK_PPE_PKT_TYPE_IPV4_DSLITE) {
+			l2 = &entry->ipv6.l2;
+			ib2 = entry->ipv6.ib2;
+		} else {
+			l2 = &entry->ipv4.l2;
+			ib2 = entry->ipv4.ib2;
+		}
+
+		*((__be32 *)h_source) = htonl(l2->src_mac_hi);
+		*((__be16 *)&h_source[4]) = htons(l2->src_mac_lo);
+		*((__be32 *)h_dest) = htonl(l2->dest_mac_hi);
+		*((__be16 *)&h_dest[4]) = htons(l2->dest_mac_lo);
+
+		seq_printf(m, " eth=%pM->%pM etype=%04x"
+			      " vlan=%d,%d ib1=%08x ib2=%08x\n",
+			   h_source, h_dest, ntohs(l2->etype),
+			   l2->vlan1, l2->vlan2, entry->ib1, ib2);
+	}
+
+	return 0;
+}
+
+static int
+mtk_ppe_debugfs_foe_show_all(struct seq_file *m, void *private)
+{
+	return mtk_ppe_debugfs_foe_show(m, private, false);
+}
+
+static int
+mtk_ppe_debugfs_foe_show_bind(struct seq_file *m, void *private)
+{
+	return mtk_ppe_debugfs_foe_show(m, private, true);
+}
+
+static int
+mtk_ppe_debugfs_foe_open_all(struct inode *inode, struct file *file)
+{
+	return single_open(file, mtk_ppe_debugfs_foe_show_all,
+			   inode->i_private);
+}
+
+static int
+mtk_ppe_debugfs_foe_open_bind(struct inode *inode, struct file *file)
+{
+	return single_open(file, mtk_ppe_debugfs_foe_show_bind,
+			   inode->i_private);
+}
+
+int mtk_ppe_debugfs_init(struct mtk_ppe *ppe)
+{
+	static const struct file_operations fops_all = {
+		.open = mtk_ppe_debugfs_foe_open_all,
+		.read = seq_read,
+		.llseek = seq_lseek,
+		.release = single_release,
+	};
+
+	static const struct file_operations fops_bind = {
+		.open = mtk_ppe_debugfs_foe_open_bind,
+		.read = seq_read,
+		.llseek = seq_lseek,
+		.release = single_release,
+	};
+
+	struct dentry *root;
+
+	root = debugfs_create_dir("mtk_ppe", NULL);
+	if (!root)
+		return -ENOMEM;
+
+	debugfs_create_file("entries", S_IRUGO, root, ppe, &fops_all);
+	debugfs_create_file("bind", S_IRUGO, root, ppe, &fops_bind);
+
+	return 0;
+}
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 0000000..d6bcffe
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -0,0 +1,499 @@
+// 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/if_ether.h>
+#include <linux/ip.h>
+#include <net/flow_offload.h>
+#include <net/pkt_cls.h>
+#include <net/dsa.h>
+#include "mtk_eth_soc.h"
+
+struct mtk_flow_data {
+	struct ethhdr eth;
+
+	union {
+		struct {
+			__be32 src_addr;
+			__be32 dst_addr;
+		} v4;
+	};
+
+	__be16 src_port;
+	__be16 dst_port;
+
+	struct {
+		u16 id;
+		__be16 proto;
+		u8 num;
+	} vlan;
+	struct {
+		u16 sid;
+		u8 num;
+	} pppoe;
+};
+
+struct mtk_flow_entry {
+	struct rhash_head node;
+	unsigned long cookie;
+	u16 hash;
+};
+
+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 u32
+mtk_eth_timestamp(struct mtk_eth *eth)
+{
+	return mtk_r32(eth, 0x0010) & MTK_FOE_IB1_BIND_TIMESTAMP;
+}
+
+static int
+mtk_flow_set_ipv4_addr(struct mtk_foe_entry *foe, struct mtk_flow_data *data,
+		       bool egress)
+{
+	return mtk_foe_entry_set_ipv4_tuple(foe, egress,
+					    data->v4.src_addr, data->src_port,
+					    data->v4.dst_addr, 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_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 = dp->cpu_dp->master;
+
+	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)
+{
+	int pse_port, dsa_port;
+
+	dsa_port = mtk_flow_get_dsa_port(&dev);
+	if (dsa_port >= 0)
+		mtk_foe_entry_set_dsa(foe, dsa_port);
+
+	if (dev == eth->netdev[0])
+		pse_port = 1;
+	else if (dev == eth->netdev[1])
+		pse_port = 2;
+	else
+		return -EOPNOTSUPP;
+
+	mtk_foe_entry_set_pse_port(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;
+	u16 addr_type = 0;
+	u32 timestamp;
+	u8 l4proto = 0;
+	int err = 0;
+	int hash;
+	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;
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			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;
+		}
+	}
+
+	switch (addr_type) {
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		offload_type = MTK_PPE_PKT_TYPE_IPV4_HNAPT;
+		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(&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;
+
+		flow_rule_match_ports(rule, &ports);
+		data.src_port = ports.key->src;
+		data.dst_port = ports.key->dst;
+	} else {
+		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(&foe, &data, false);
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		if (act->id != FLOW_ACTION_MANGLE)
+			continue;
+
+		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(&foe, &data, true);
+		if (err)
+			return err;
+	}
+
+	if (data.vlan.num == 1) {
+		if (data.vlan.proto != htons(ETH_P_8021Q))
+			return -EOPNOTSUPP;
+
+		mtk_foe_entry_set_vlan(&foe, data.vlan.id);
+	}
+	if (data.pppoe.num == 1)
+		mtk_foe_entry_set_pppoe(&foe, data.pppoe.sid);
+
+	err = mtk_flow_set_output_device(eth, &foe, odev);
+	if (err)
+		return err;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->cookie = f->cookie;
+	timestamp = mtk_eth_timestamp(eth);
+	hash = mtk_foe_entry_commit(&eth->ppe, &foe, timestamp);
+	if (hash < 0) {
+		err = hash;
+		goto free;
+	}
+
+	entry->hash = hash;
+	err = rhashtable_insert_fast(&eth->flow_table, &entry->node,
+				     mtk_flow_ht_params);
+	if (err < 0)
+		goto clear_flow;
+
+	return 0;
+clear_flow:
+	mtk_foe_entry_clear(&eth->ppe, hash);
+free:
+	kfree(entry);
+	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->hash);
+	rhashtable_remove_fast(&eth->flow_table, &entry->node,
+			       mtk_flow_ht_params);
+	kfree(entry);
+
+	return 0;
+}
+
+static int
+mtk_flow_offload_stats(struct mtk_eth *eth, struct flow_cls_offload *f)
+{
+	struct mtk_flow_entry *entry;
+	int timestamp;
+	u32 idle;
+
+	entry = rhashtable_lookup(&eth->flow_table, &f->cookie,
+				  mtk_flow_ht_params);
+	if (!entry)
+		return -ENOENT;
+
+	timestamp = mtk_foe_entry_timestamp(&eth->ppe, entry->hash);
+	if (timestamp < 0)
+		return -ETIMEDOUT;
+
+	idle = mtk_eth_timestamp(eth) - timestamp;
+	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->ppe.foe_table)
+		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)
+{
+	if (type == TC_SETUP_FT)
+		return mtk_eth_setup_tc_block(dev, type_data);
+
+	return -EOPNOTSUPP;
+}
+
+int mtk_eth_offload_init(struct mtk_eth *eth)
+{
+	if (!eth->ppe.foe_table)
+		return 0;
+
+	return rhashtable_init(&eth->flow_table, &mtk_flow_ht_params);
+}
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_regs.h b/drivers/net/ethernet/mediatek/mtk_ppe_regs.h
new file mode 100644
index 0000000..0c45ea0
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_regs.h
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Felix Fietkau <nbd@nbd.name> */
+
+#ifndef __MTK_PPE_REGS_H
+#define __MTK_PPE_REGS_H
+
+#define MTK_PPE_GLO_CFG				0x200
+#define MTK_PPE_GLO_CFG_EN			BIT(0)
+#define MTK_PPE_GLO_CFG_TSID_EN			BIT(1)
+#define MTK_PPE_GLO_CFG_IP4_L4_CS_DROP		BIT(2)
+#define MTK_PPE_GLO_CFG_IP4_CS_DROP		BIT(3)
+#define MTK_PPE_GLO_CFG_TTL0_DROP		BIT(4)
+#define MTK_PPE_GLO_CFG_PPE_BSWAP		BIT(5)
+#define MTK_PPE_GLO_CFG_PSE_HASH_OFS		BIT(6)
+#define MTK_PPE_GLO_CFG_MCAST_TB_EN		BIT(7)
+#define MTK_PPE_GLO_CFG_FLOW_DROP_KA		BIT(8)
+#define MTK_PPE_GLO_CFG_FLOW_DROP_UPDATE	BIT(9)
+#define MTK_PPE_GLO_CFG_UDP_LITE_EN		BIT(10)
+#define MTK_PPE_GLO_CFG_UDP_LEN_DROP		BIT(11)
+#define MTK_PPE_GLO_CFG_MCAST_ENTRIES		GNEMASK(13, 12)
+#define MTK_PPE_GLO_CFG_BUSY			BIT(31)
+
+#define MTK_PPE_FLOW_CFG			0x204
+#define MTK_PPE_FLOW_CFG_IP4_TCP_FRAG		BIT(6)
+#define MTK_PPE_FLOW_CFG_IP4_UDP_FRAG		BIT(7)
+#define MTK_PPE_FLOW_CFG_IP6_3T_ROUTE		BIT(8)
+#define MTK_PPE_FLOW_CFG_IP6_5T_ROUTE		BIT(9)
+#define MTK_PPE_FLOW_CFG_IP6_6RD		BIT(10)
+#define MTK_PPE_FLOW_CFG_IP4_NAT		BIT(12)
+#define MTK_PPE_FLOW_CFG_IP4_NAPT		BIT(13)
+#define MTK_PPE_FLOW_CFG_IP4_DSLITE		BIT(14)
+#define MTK_PPE_FLOW_CFG_L2_BRIDGE		BIT(15)
+#define MTK_PPE_FLOW_CFG_IP_PROTO_BLACKLIST	BIT(16)
+#define MTK_PPE_FLOW_CFG_IP4_NAT_FRAG		BIT(17)
+#define MTK_PPE_FLOW_CFG_IP4_HASH_FLOW_LABEL	BIT(18)
+#define MTK_PPE_FLOW_CFG_IP4_HASH_GRE_KEY	BIT(19)
+#define MTK_PPE_FLOW_CFG_IP6_HASH_GRE_KEY	BIT(20)
+
+#define MTK_PPE_IP_PROTO_CHK			0x208
+#define MTK_PPE_IP_PROTO_CHK_IPV4		GENMASK(15, 0)
+#define MTK_PPE_IP_PROTO_CHK_IPV6		GENMASK(31, 16)
+
+#define MTK_PPE_TB_CFG				0x21c
+#define MTK_PPE_TB_CFG_ENTRY_NUM		GENMASK(2, 0)
+#define MTK_PPE_TB_CFG_ENTRY_80B		BIT(3)
+#define MTK_PPE_TB_CFG_SEARCH_MISS		GENMASK(5, 4)
+#define MTK_PPE_TB_CFG_AGE_PREBIND		BIT(6)
+#define MTK_PPE_TB_CFG_AGE_NON_L4		BIT(7)
+#define MTK_PPE_TB_CFG_AGE_UNBIND		BIT(8)
+#define MTK_PPE_TB_CFG_AGE_TCP			BIT(9)
+#define MTK_PPE_TB_CFG_AGE_UDP			BIT(10)
+#define MTK_PPE_TB_CFG_AGE_TCP_FIN		BIT(11)
+#define MTK_PPE_TB_CFG_KEEPALIVE		GENMASK(13, 12)
+#define MTK_PPE_TB_CFG_HASH_MODE		GENMASK(15, 14)
+#define MTK_PPE_TB_CFG_SCAN_MODE		GENMASK(17, 16)
+#define MTK_PPE_TB_CFG_HASH_DEBUG		GENMASK(19, 18)
+
+enum {
+	MTK_PPE_SCAN_MODE_DISABLED,
+	MTK_PPE_SCAN_MODE_CHECK_AGE,
+	MTK_PPE_SCAN_MODE_KEEPALIVE_AGE,
+};
+
+enum {
+	MTK_PPE_KEEPALIVE_DISABLE,
+	MTK_PPE_KEEPALIVE_UNICAST_CPU,
+	MTK_PPE_KEEPALIVE_DUP_CPU = 3,
+};
+
+enum {
+	MTK_PPE_SEARCH_MISS_ACTION_DROP,
+	MTK_PPE_SEARCH_MISS_ACTION_FORWARD = 2,
+	MTK_PPE_SEARCH_MISS_ACTION_FORWARD_BUILD = 3,
+};
+
+#define MTK_PPE_TB_BASE				0x220
+
+#define MTK_PPE_TB_USED				0x224
+#define MTK_PPE_TB_USED_NUM			GENMASK(13, 0)
+
+#define MTK_PPE_BIND_RATE			0x228
+#define MTK_PPE_BIND_RATE_BIND			GENMASK(15, 0)
+#define MTK_PPE_BIND_RATE_PREBIND		GENMASK(31, 16)
+
+#define MTK_PPE_BIND_LIMIT0			0x22c
+#define MTK_PPE_BIND_LIMIT0_QUARTER		GENMASK(13, 0)
+#define MTK_PPE_BIND_LIMIT0_HALF		GENMASK(29, 16)
+
+#define MTK_PPE_BIND_LIMIT1			0x230
+#define MTK_PPE_BIND_LIMIT1_FULL		GENMASK(13, 0)
+#define MTK_PPE_BIND_LIMIT1_NON_L4		GENMASK(23, 16)
+
+#define MTK_PPE_KEEPALIVE			0x234
+#define MTK_PPE_KEEPALIVE_TIME			GENMASK(15, 0)
+#define MTK_PPE_KEEPALIVE_TIME_TCP		GENMASK(23, 16)
+#define MTK_PPE_KEEPALIVE_TIME_UDP		GENMASK(31, 24)
+
+#define MTK_PPE_UNBIND_AGE			0x238
+#define MTK_PPE_UNBIND_AGE_MIN_PACKETS		GENMASK(31, 16)
+#define MTK_PPE_UNBIND_AGE_DELTA		GENMASK(7, 0)
+
+#define MTK_PPE_BIND_AGE0			0x23c
+#define MTK_PPE_BIND_AGE0_DELTA_NON_L4		GENMASK(30, 16)
+#define MTK_PPE_BIND_AGE0_DELTA_UDP		GENMASK(14, 0)
+
+#define MTK_PPE_BIND_AGE1			0x240
+#define MTK_PPE_BIND_AGE1_DELTA_TCP_FIN		GENMASK(30, 16)
+#define MTK_PPE_BIND_AGE1_DELTA_TCP		GENMASK(14, 0)
+
+#define MTK_PPE_HASH_SEED			0x244
+
+#define MTK_PPE_DEFAULT_CPU_PORT		0x248
+#define MTK_PPE_DEFAULT_CPU_PORT_MASK(_n)	(GENMASK(2, 0) << ((_n) * 4))
+
+#define MTK_PPE_MTU_DROP			0x308
+
+#define MTK_PPE_VLAN_MTU0			0x30c
+#define MTK_PPE_VLAN_MTU0_NONE			GENMASK(13, 0)
+#define MTK_PPE_VLAN_MTU0_1TAG			GENMASK(29, 16)
+
+#define MTK_PPE_VLAN_MTU1			0x310
+#define MTK_PPE_VLAN_MTU1_2TAG			GENMASK(13, 0)
+#define MTK_PPE_VLAN_MTU1_3TAG			GENMASK(29, 16)
+
+#define MTK_PPE_VPM_TPID			0x318
+
+#define MTK_PPE_CACHE_CTL			0x320
+#define MTK_PPE_CACHE_CTL_EN			BIT(0)
+#define MTK_PPE_CACHE_CTL_LOCK_CLR		BIT(4)
+#define MTK_PPE_CACHE_CTL_REQ			BIT(8)
+#define MTK_PPE_CACHE_CTL_CLEAR			BIT(9)
+#define MTK_PPE_CACHE_CTL_CMD			GENMASK(13, 12)
+
+#define MTK_PPE_MIB_CFG				0x334
+#define MTK_PPE_MIB_CFG_EN			BIT(0)
+#define MTK_PPE_MIB_CFG_RD_CLR			BIT(1)
+
+#define MTK_PPE_MIB_TB_BASE			0x338
+
+#define MTK_PPE_MIB_CACHE_CTL			0x350
+#define MTK_PPE_MIB_CACHE_CTL_EN		BIT(0)
+#define MTK_PPE_MIB_CACHE_CTL_FLUSH		BIT(2)
+
+#endif
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 61824bbb..e002d816 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1362,12 +1362,34 @@ static void ppp_dev_priv_destructor(struct net_device *dev)
 		ppp_destroy_interface(ppp);
 }
 
+static int ppp_fill_forward_path(struct net_device_path_ctx *ctx,
+				 struct net_device_path *path)
+{
+	struct ppp *ppp = netdev_priv(ctx->dev);
+	struct ppp_channel *chan;
+	struct channel *pch;
+
+	if (ppp->flags & SC_MULTILINK)
+		return -EOPNOTSUPP;
+
+	if (list_empty(&ppp->channels))
+		return -ENODEV;
+
+	pch = list_first_entry(&ppp->channels, struct channel, clist);
+	chan = pch->chan;
+	if (!chan->ops->fill_forward_path)
+		return -EOPNOTSUPP;
+
+	return chan->ops->fill_forward_path(ctx, path, chan);
+}
+
 static const struct net_device_ops ppp_netdev_ops = {
 	.ndo_init	 = ppp_dev_init,
 	.ndo_uninit      = ppp_dev_uninit,
 	.ndo_start_xmit  = ppp_start_xmit,
 	.ndo_do_ioctl    = ppp_net_ioctl,
 	.ndo_get_stats64 = ppp_get_stats64,
+	.ndo_fill_forward_path = ppp_fill_forward_path,
 };
 
 static struct device_type ppp_type = {
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 087b0168..df08ec41 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -974,8 +974,31 @@ static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	return __pppoe_xmit(sk, skb);
 }
 
+static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx,
+				   struct net_device_path *path,
+				   const struct ppp_channel *chan)
+{
+	struct sock *sk = (struct sock *)chan->private;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct net_device *dev = po->pppoe_dev;
+
+	if (sock_flag(sk, SOCK_DEAD) ||
+	    !(sk->sk_state & PPPOX_CONNECTED) || !dev)
+		return -1;
+
+	path->type = DEV_PATH_PPPOE;
+	path->encap.proto = htons(ETH_P_PPP_SES);
+	path->encap.id = be16_to_cpu(po->num);
+	memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN);
+	path->dev = ctx->dev;
+	ctx->dev = dev;
+
+	return 0;
+}
+
 static const struct ppp_channel_ops pppoe_chan_ops = {
 	.start_xmit = pppoe_xmit,
+	.fill_forward_path = pppoe_fill_forward_path,
 };
 
 static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c4fadf65..187e90d1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -838,6 +838,59 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct net_device *sb_dev);
 
+enum net_device_path_type {
+	DEV_PATH_ETHERNET = 0,
+	DEV_PATH_VLAN,
+	DEV_PATH_BRIDGE,
+	DEV_PATH_PPPOE,
+	DEV_PATH_DSA,
+};
+
+struct net_device_path {
+	enum net_device_path_type	type;
+	const struct net_device		*dev;
+	union {
+		struct {
+			u16		id;
+			__be16		proto;
+			u8		h_dest[ETH_ALEN];
+		} encap;
+		struct {
+			enum {
+				DEV_PATH_BR_VLAN_KEEP,
+				DEV_PATH_BR_VLAN_TAG,
+				DEV_PATH_BR_VLAN_UNTAG,
+				DEV_PATH_BR_VLAN_UNTAG_HW,
+			}		vlan_mode;
+			u16		vlan_id;
+			__be16		vlan_proto;
+		} bridge;
+		struct {
+			int port;
+			u16 proto;
+		} dsa;
+	};
+};
+
+#define NET_DEVICE_PATH_STACK_MAX	5
+#define NET_DEVICE_PATH_VLAN_MAX	2
+
+struct net_device_path_stack {
+	int			num_paths;
+	struct net_device_path	path[NET_DEVICE_PATH_STACK_MAX];
+};
+
+struct net_device_path_ctx {
+	const struct net_device *dev;
+	const u8		*daddr;
+
+	int			num_vlans;
+	struct {
+		u16		id;
+		__be16		proto;
+	} vlan[NET_DEVICE_PATH_VLAN_MAX];
+};
+
 enum tc_setup_type {
 	TC_SETUP_QDISC_MQPRIO,
 	TC_SETUP_CLSU32,
@@ -853,6 +906,7 @@ enum tc_setup_type {
 	TC_SETUP_ROOT_QDISC,
 	TC_SETUP_QDISC_GRED,
 	TC_SETUP_QDISC_TAPRIO,
+	TC_SETUP_FT,
 };
 
 /* These structures hold the attributes of bpf state that are being passed
@@ -1248,6 +1302,8 @@ struct tlsdev_ops;
  *	Get devlink port instance associated with a given netdev.
  *	Called with a reference on the netdevice and devlink locks only,
  *	rtnl_lock is not held.
+ * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
+ *     Get the forwarding path to reach the real device from the HW destination address
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1445,6 +1501,8 @@ struct net_device_ops {
 	int			(*ndo_xsk_wakeup)(struct net_device *dev,
 						  u32 queue_id, u32 flags);
 	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
+	int                     (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
+                                                         struct net_device_path *path);
 };
 
 /**
@@ -2687,6 +2745,8 @@ void dev_remove_offload(struct packet_offload *po);
 
 int dev_get_iflink(const struct net_device *dev);
 int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+			  struct net_device_path_stack *stack);
 struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
 				      unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h
index 98966064..91f9a928 100644
--- a/include/linux/ppp_channel.h
+++ b/include/linux/ppp_channel.h
@@ -28,6 +28,9 @@ struct ppp_channel_ops {
 	int	(*start_xmit)(struct ppp_channel *, struct sk_buff *);
 	/* Handle an ioctl call that has come in via /dev/ppp. */
 	int	(*ioctl)(struct ppp_channel *, unsigned int, unsigned long);
+	int	(*fill_forward_path)(struct net_device_path_ctx *,
+				     struct net_device_path *,
+				     const struct ppp_channel *);
 };
 
 struct ppp_channel {
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 05f66d48..2e516029 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -561,6 +561,8 @@ struct dsa_switch_ops {
 					  struct sk_buff *skb);
 };
 
+struct dsa_port *dsa_port_from_netdev(struct net_device *netdev);
+
 struct dsa_switch_driver {
 	struct list_head	list;
 	const struct dsa_switch_ops *ops;
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index c6f7bd22..ccca6086 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -138,6 +138,7 @@ enum flow_action_id {
 	FLOW_ACTION_MPLS_PUSH,
 	FLOW_ACTION_MPLS_POP,
 	FLOW_ACTION_MPLS_MANGLE,
+	FLOW_ACTION_PPPOE_PUSH,
 	NUM_FLOW_ACTIONS,
 };
 
@@ -213,6 +214,9 @@ struct flow_action_entry {
 			u8		bos;
 			u8		ttl;
 		} mpls_mangle;
+		struct {				/* FLOW_ACTION_PPPOE_PUSH */
+			u16		sid;
+		} pppoe;
 	};
 };
 
@@ -300,6 +304,18 @@ enum tc_setup_type;
 typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data,
 			    void *cb_priv);
 
+struct flow_block_cb;
+
+struct flow_block_indr {
+	struct list_head		list;
+	struct net_device		*dev;
+	struct Qdisc			*sch;
+	enum flow_block_binder_type	binder_type;
+	void				*data;
+	void				*cb_priv;
+	void				(*cleanup)(struct flow_block_cb *block_cb);
+};
+
 struct flow_block_cb {
 	struct list_head	driver_list;
 	struct list_head	list;
@@ -307,6 +323,7 @@ struct flow_block_cb {
 	void			*cb_ident;
 	void			*cb_priv;
 	void			(*release)(void *cb_priv);
+	struct flow_block_indr	indr;
 	unsigned int		refcnt;
 };
 
diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
index 7b3c873f..e9548319 100644
--- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
@@ -4,7 +4,4 @@
 
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6;
 
-#include <linux/sysctl.h>
-extern struct ctl_table nf_ct_ipv6_sysctl_table[];
-
 #endif /* _NF_CONNTRACK_IPV6_H*/
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 90690e37..c7bfddfc 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -279,6 +279,18 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
 	       !nf_ct_is_dying(ct);
 }
 
+#define	NF_CT_DAY	(86400 * HZ)
+
+/* Set an arbitrary timeout large enough not to ever expire, this save
+ * us a check for the IPS_OFFLOAD_BIT from the packet path via
+ * nf_ct_is_expired().
+ */
+static inline void nf_ct_offload_timeout(struct nf_conn *ct)
+{
+	if (nf_ct_expires(ct) < NF_CT_DAY / 2)
+		ct->timeout = nfct_time_stamp + NF_CT_DAY;
+}
+
 struct kernel_param;
 
 int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp);
diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index f7a060c6..7f44a771 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -65,6 +65,17 @@ static inline void nf_ct_set_acct(struct net *net, bool enable)
 #endif
 }
 
+void nf_ct_acct_add(struct nf_conn *ct, u32 dir, unsigned int packets,
+		    unsigned int bytes);
+
+static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir,
+				     unsigned int bytes)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	nf_ct_acct_add(ct, dir, 1, bytes);
+#endif
+}
+
 void nf_conntrack_acct_pernet_init(struct net *net);
 
 int nf_conntrack_acct_init(void);
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index b37a7d60..ee63c122 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -8,32 +8,95 @@
 #include <linux/rcupdate.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <net/flow_offload.h>
 #include <net/dst.h>
 
 struct nf_flowtable;
+struct nf_flow_rule;
+struct flow_offload;
+enum flow_offload_tuple_dir;
+
+struct nf_flow_key {
+	struct flow_dissector_key_meta			meta;
+	struct flow_dissector_key_control		control;
+	struct flow_dissector_key_control		enc_control;
+	struct flow_dissector_key_basic			basic;
+	union {
+		struct flow_dissector_key_ipv4_addrs	ipv4;
+		struct flow_dissector_key_ipv6_addrs	ipv6;
+	};
+	struct flow_dissector_key_keyid			enc_key_id;
+	union {
+		struct flow_dissector_key_ipv4_addrs	enc_ipv4;
+		struct flow_dissector_key_ipv6_addrs	enc_ipv6;
+	};
+	struct flow_dissector_key_tcp			tcp;
+	struct flow_dissector_key_ports			tp;
+} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
+
+struct nf_flow_match {
+	struct flow_dissector	dissector;
+	struct nf_flow_key	key;
+	struct nf_flow_key	mask;
+};
+
+struct nf_flow_rule {
+	struct nf_flow_match	match;
+	struct flow_rule	*rule;
+};
 
 struct nf_flowtable_type {
 	struct list_head		list;
 	int				family;
 	int				(*init)(struct nf_flowtable *ft);
+	int				(*setup)(struct nf_flowtable *ft,
+						 struct net_device *dev,
+						 enum flow_block_command cmd);
+	int				(*action)(struct net *net,
+						  const struct flow_offload *flow,
+						  enum flow_offload_tuple_dir dir,
+						  struct nf_flow_rule *flow_rule);
 	void				(*free)(struct nf_flowtable *ft);
 	nf_hookfn			*hook;
 	struct module			*owner;
 };
 
+enum nf_flowtable_flags {
+	NF_FLOWTABLE_HW_OFFLOAD		= 0x1,	/* NFT_FLOWTABLE_HW_OFFLOAD */
+	NF_FLOWTABLE_COUNTER		= 0x2,	/* NFT_FLOWTABLE_COUNTER */
+};
+
 struct nf_flowtable {
 	struct list_head		list;
 	struct rhashtable		rhashtable;
+	int				priority;
 	const struct nf_flowtable_type	*type;
 	struct delayed_work		gc_work;
+	unsigned int			flags;
+	struct flow_block		flow_block;
+	struct rw_semaphore		flow_block_lock; /* Guards flow_block */
+	possible_net_t			net;
 };
 
+static inline bool nf_flowtable_hw_offload(struct nf_flowtable *flowtable)
+{
+	return flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD;
+}
+
 enum flow_offload_tuple_dir {
 	FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
 	FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
-	FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX
+};
+#define FLOW_OFFLOAD_DIR_MAX	IP_CT_DIR_MAX
+
+enum flow_offload_xmit_type {
+	FLOW_OFFLOAD_XMIT_NEIGH		= 0,
+	FLOW_OFFLOAD_XMIT_XFRM,
+	FLOW_OFFLOAD_XMIT_DIRECT,
 };
 
+#define NF_FLOW_TABLE_ENCAP_MAX		2
+
 struct flow_offload_tuple {
 	union {
 		struct in_addr		src_v4;
@@ -52,11 +115,31 @@ struct flow_offload_tuple {
 
 	u8				l3proto;
 	u8				l4proto;
-	u8				dir;
+	struct {
+		u16			id;
+		__be16			proto;
+	} encap[NF_FLOW_TABLE_ENCAP_MAX];
 
-	u16				mtu;
+	/* All members above are keys for lookups, see flow_offload_hash(). */
+	struct { }			__hash;
 
-	struct dst_entry		*dst_cache;
+	u8				dir:2,
+					xmit_type:2,
+					encap_num:2,
+					in_vlan_ingress:2;
+	u16				mtu;
+	union {
+		struct {
+			struct dst_entry *dst_cache;
+			u32		dst_cookie;
+		};
+		struct {
+			u32		ifidx;
+			u32		hw_ifidx;
+			u8		h_source[ETH_ALEN];
+			u8		h_dest[ETH_ALEN];
+		} out;
+	};
 };
 
 struct flow_offload_tuple_rhash {
@@ -64,52 +147,139 @@ struct flow_offload_tuple_rhash {
 	struct flow_offload_tuple	tuple;
 };
 
-#define FLOW_OFFLOAD_SNAT	0x1
-#define FLOW_OFFLOAD_DNAT	0x2
-#define FLOW_OFFLOAD_DYING	0x4
-#define FLOW_OFFLOAD_TEARDOWN	0x8
+enum nf_flow_flags {
+	NF_FLOW_SNAT,
+	NF_FLOW_DNAT,
+	NF_FLOW_TEARDOWN,
+	NF_FLOW_HW,
+	NF_FLOW_HW_DYING,
+	NF_FLOW_HW_DEAD,
+	NF_FLOW_HW_PENDING,
+};
+
+enum flow_offload_type {
+	NF_FLOW_OFFLOAD_UNSPEC	= 0,
+	NF_FLOW_OFFLOAD_ROUTE,
+};
 
 struct flow_offload {
 	struct flow_offload_tuple_rhash		tuplehash[FLOW_OFFLOAD_DIR_MAX];
-	u32					flags;
-	union {
-		/* Your private driver data here. */
-		u32		timeout;
-	};
+	struct nf_conn				*ct;
+	unsigned long				flags;
+	u16					type;
+	u32					timeout;
+	struct rcu_head				rcu_head;
 };
 
 #define NF_FLOW_TIMEOUT (30 * HZ)
+#define nf_flowtable_time_stamp	(u32)jiffies
+
+unsigned long flow_offload_get_timeout(struct flow_offload *flow);
+
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+	return (__s32)(timeout - nf_flowtable_time_stamp);
+}
 
 struct nf_flow_route {
 	struct {
-		struct dst_entry	*dst;
+		struct dst_entry		*dst;
+		struct {
+			u32			ifindex;
+			struct {
+				u16		id;
+				__be16		proto;
+			} encap[NF_FLOW_TABLE_ENCAP_MAX];
+			u8			num_encaps:2,
+						ingress_vlans:2;
+		} in;
+		struct {
+			u32			ifindex;
+			u32			hw_ifindex;
+			u8			h_source[ETH_ALEN];
+			u8			h_dest[ETH_ALEN];
+		} out;
+		enum flow_offload_xmit_type	xmit_type;
 	} tuple[FLOW_OFFLOAD_DIR_MAX];
 };
 
-struct flow_offload *flow_offload_alloc(struct nf_conn *ct,
-					struct nf_flow_route *route);
+struct flow_offload *flow_offload_alloc(struct nf_conn *ct);
 void flow_offload_free(struct flow_offload *flow);
 
+static inline int
+nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
+			     flow_setup_cb_t *cb, void *cb_priv)
+{
+	struct flow_block *block = &flow_table->flow_block;
+	struct flow_block_cb *block_cb;
+	int err = 0;
+
+	down_write(&flow_table->flow_block_lock);
+	block_cb = flow_block_cb_lookup(block, cb, cb_priv);
+	if (block_cb) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL);
+	if (IS_ERR(block_cb)) {
+		err = PTR_ERR(block_cb);
+		goto unlock;
+	}
+
+	list_add_tail(&block_cb->list, &block->cb_list);
+
+unlock:
+	up_write(&flow_table->flow_block_lock);
+	return err;
+}
+
+static inline void
+nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
+			     flow_setup_cb_t *cb, void *cb_priv)
+{
+	struct flow_block *block = &flow_table->flow_block;
+	struct flow_block_cb *block_cb;
+
+	down_write(&flow_table->flow_block_lock);
+	block_cb = flow_block_cb_lookup(block, cb, cb_priv);
+	if (block_cb) {
+		list_del(&block_cb->list);
+		flow_block_cb_free(block_cb);
+	} else {
+		WARN_ON(true);
+	}
+	up_write(&flow_table->flow_block_lock);
+}
+
+int flow_offload_route_init(struct flow_offload *flow,
+			    const struct nf_flow_route *route);
+
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
+void flow_offload_refresh(struct nf_flowtable *flow_table,
+			  struct flow_offload *flow);
+
 struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
 						     struct flow_offload_tuple *tuple);
+void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
+			      struct net_device *dev);
 void nf_flow_table_cleanup(struct net_device *dev);
 
 int nf_flow_table_init(struct nf_flowtable *flow_table);
 void nf_flow_table_free(struct nf_flowtable *flow_table);
 
 void flow_offload_teardown(struct flow_offload *flow);
-static inline void flow_offload_dead(struct flow_offload *flow)
-{
-	flow->flags |= FLOW_OFFLOAD_DYING;
-}
 
-int nf_flow_snat_port(const struct flow_offload *flow,
-		      struct sk_buff *skb, unsigned int thoff,
-		      u8 protocol, enum flow_offload_tuple_dir dir);
-int nf_flow_dnat_port(const struct flow_offload *flow,
-		      struct sk_buff *skb, unsigned int thoff,
-		      u8 protocol, enum flow_offload_tuple_dir dir);
+int nf_flow_table_iterate(struct nf_flowtable *flow_table,
+			  void (*iter)(struct flow_offload *flow, void *data),
+			  void *data);
+
+void nf_flow_snat_port(const struct flow_offload *flow,
+		       struct sk_buff *skb, unsigned int thoff,
+		       u8 protocol, enum flow_offload_tuple_dir dir);
+void nf_flow_dnat_port(const struct flow_offload *flow,
+		       struct sk_buff *skb, unsigned int thoff,
+		       u8 protocol, enum flow_offload_tuple_dir dir);
 
 struct flow_ports {
 	__be16 source, dest;
@@ -123,4 +293,25 @@ unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 #define MODULE_ALIAS_NF_FLOWTABLE(family)	\
 	MODULE_ALIAS("nf-flowtable-" __stringify(family))
 
+void nf_flow_offload_add(struct nf_flowtable *flowtable,
+			 struct flow_offload *flow);
+void nf_flow_offload_del(struct nf_flowtable *flowtable,
+			 struct flow_offload *flow);
+void nf_flow_offload_stats(struct nf_flowtable *flowtable,
+			   struct flow_offload *flow);
+
+void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
+int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
+				struct net_device *dev,
+				enum flow_block_command cmd);
+int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow,
+			    enum flow_offload_tuple_dir dir,
+			    struct nf_flow_rule *flow_rule);
+int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow,
+			    enum flow_offload_tuple_dir dir,
+			    struct nf_flow_rule *flow_rule);
+
+int nf_flow_table_offload_init(void);
+void nf_flow_table_offload_exit(void);
+
 #endif /* _NF_FLOW_TABLE_H */
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 806454e7..67bbaa69 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -27,6 +27,10 @@ struct nf_tcp_net {
 	int tcp_loose;
 	int tcp_be_liberal;
 	int tcp_max_retrans;
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	unsigned int offload_timeout;
+	unsigned int offload_pickup;
+#endif
 };
 
 enum udp_conntrack {
@@ -37,6 +41,10 @@ enum udp_conntrack {
 
 struct nf_udp_net {
 	unsigned int timeouts[UDP_CT_MAX];
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	unsigned int offload_timeout;
+	unsigned int offload_pickup;
+#endif
 };
 
 struct nf_icmp_net {
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 336014bf..ae698d11 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -105,14 +105,19 @@ enum ip_conntrack_status {
 	IPS_OFFLOAD_BIT = 14,
 	IPS_OFFLOAD = (1 << IPS_OFFLOAD_BIT),
 
+	/* Conntrack has been offloaded to hardware. */
+	IPS_HW_OFFLOAD_BIT = 15,
+	IPS_HW_OFFLOAD = (1 << IPS_HW_OFFLOAD_BIT),
+
 	/* Be careful here, modifying these bits can make things messy,
 	 * so don't let users modify them directly.
 	 */
 	IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
 				 IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
-				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
+				 IPS_SEQ_ADJUST | IPS_TEMPLATE |
+				 IPS_OFFLOAD | IPS_HW_OFFLOAD),
 
-	__IPS_MAX_BIT = 15,
+	__IPS_MAX_BIT = 16,
 };
 
 /* Connection tracking event types */
diff --git a/include/uapi/linux/netfilter/xt_FLOWOFFLOAD.h b/include/uapi/linux/netfilter/xt_FLOWOFFLOAD.h
new file mode 100644
index 00000000..5841bbe0
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_FLOWOFFLOAD.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _XT_FLOWOFFLOAD_H
+#define _XT_FLOWOFFLOAD_H
+
+#include <linux/types.h>
+
+enum {
+	XT_FLOWOFFLOAD_HW	= 1 << 0,
+
+	XT_FLOWOFFLOAD_MASK	= XT_FLOWOFFLOAD_HW
+};
+
+struct xt_flowoffload_target_info {
+	__u32 flags;
+};
+
+#endif /* _XT_FLOWOFFLOAD_H */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 2a78da40..226ab97e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -744,6 +744,26 @@ static int vlan_dev_get_iflink(const struct net_device *dev)
 	return real_dev->ifindex;
 }
 
+static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx,
+				      struct net_device_path *path)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(ctx->dev);
+
+	path->type = DEV_PATH_VLAN;
+	path->encap.id = vlan->vlan_id;
+	path->encap.proto = vlan->vlan_proto;
+	path->dev = ctx->dev;
+	ctx->dev = vlan->real_dev;
+	if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan))
+		return -ENOSPC;
+
+	ctx->vlan[ctx->num_vlans].id = vlan->vlan_id;
+	ctx->vlan[ctx->num_vlans].proto = vlan->vlan_proto;
+	ctx->num_vlans++;
+
+	return 0;
+}
+
 static const struct ethtool_ops vlan_ethtool_ops = {
 	.get_link_ksettings	= vlan_ethtool_get_link_ksettings,
 	.get_drvinfo	        = vlan_ethtool_get_drvinfo,
@@ -782,6 +802,7 @@ static const struct net_device_ops vlan_netdev_ops = {
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
 	.ndo_get_iflink		= vlan_dev_get_iflink,
+	.ndo_fill_forward_path	= vlan_dev_fill_forward_path,
 };
 
 static void vlan_dev_free(struct net_device *dev)
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 0dd8984a..31073480 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -377,6 +377,54 @@ static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
 	return br_del_if(br, slave_dev);
 }
 
+static int br_fill_forward_path(struct net_device_path_ctx *ctx,
+				struct net_device_path *path)
+{
+	struct net_bridge_fdb_entry *f;
+	struct net_bridge_port *dst;
+	struct net_bridge *br;
+
+	if (netif_is_bridge_port(ctx->dev))
+		return -1;
+
+	br = netdev_priv(ctx->dev);
+
+	br_vlan_fill_forward_path_pvid(br, ctx, path);
+
+	f = br_fdb_find_rcu(br, ctx->daddr, path->bridge.vlan_id);
+	if (!f || !f->dst)
+		return -1;
+
+	dst = READ_ONCE(f->dst);
+	if (!dst)
+		return -1;
+
+	if (br_vlan_fill_forward_path_mode(br, dst, path))
+		return -1;
+
+	path->type = DEV_PATH_BRIDGE;
+	path->dev = dst->br->dev;
+	ctx->dev = dst->dev;
+
+	switch (path->bridge.vlan_mode) {
+	case DEV_PATH_BR_VLAN_TAG:
+		if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan))
+			return -ENOSPC;
+		ctx->vlan[ctx->num_vlans].id = path->bridge.vlan_id;
+		ctx->vlan[ctx->num_vlans].proto = path->bridge.vlan_proto;
+		ctx->num_vlans++;
+		break;
+	case DEV_PATH_BR_VLAN_UNTAG_HW:
+	case DEV_PATH_BR_VLAN_UNTAG:
+		ctx->num_vlans--;
+		break;
+	case DEV_PATH_BR_VLAN_KEEP:
+		break;
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops br_ethtool_ops = {
 	.get_drvinfo    = br_getinfo,
 	.get_link	= ethtool_op_get_link,
@@ -410,6 +458,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_bridge_setlink	 = br_setlink,
 	.ndo_bridge_dellink	 = br_dellink,
 	.ndo_features_check	 = passthru_features_check,
+	.ndo_fill_forward_path	 = br_fill_forward_path,
 };
 
 static struct device_type br_type = {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a736be8a..4bd9e9b5 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -912,6 +912,13 @@ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
 int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
 			 void *ptr);
 
+void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
+				    struct net_device_path_ctx *ctx,
+				    struct net_device_path *path);
+int br_vlan_fill_forward_path_mode(struct net_bridge *br,
+				   struct net_bridge_port *dst,
+				   struct net_device_path *path);
+
 static inline struct net_bridge_vlan_group *br_vlan_group(
 					const struct net_bridge *br)
 {
@@ -1066,6 +1073,19 @@ static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p,
 	return 0;
 }
 
+static inline void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
+						  struct net_device_path_ctx *ctx,
+						  struct net_device_path *path)
+{
+}
+
+static inline int br_vlan_fill_forward_path_mode(struct net_bridge *br,
+						 struct net_bridge_port *dst,
+						 struct net_device_path *path)
+{
+	return 0;
+}
+
 static inline struct net_bridge_vlan_group *br_vlan_group(
 					const struct net_bridge *br)
 {
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 9257292b..bcfd1692 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1268,6 +1268,61 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
 }
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
 
+void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
+				    struct net_device_path_ctx *ctx,
+				    struct net_device_path *path)
+{
+	struct net_bridge_vlan_group *vg;
+	int idx = ctx->num_vlans - 1;
+	u16 vid;
+
+	path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP;
+
+	if (!br_opt_get(br, BROPT_VLAN_ENABLED))
+		return;
+
+	vg = br_vlan_group(br);
+
+	if (idx >= 0 &&
+	    ctx->vlan[idx].proto == br->vlan_proto) {
+		vid = ctx->vlan[idx].id;
+	} else {
+		path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG;
+		vid = br_get_pvid(vg);
+	}
+
+	path->bridge.vlan_id = vid;
+	path->bridge.vlan_proto = br->vlan_proto;
+}
+
+int br_vlan_fill_forward_path_mode(struct net_bridge *br,
+				   struct net_bridge_port *dst,
+				   struct net_device_path *path)
+{
+	struct net_bridge_vlan_group *vg;
+	struct net_bridge_vlan *v;
+
+	if (!br_opt_get(br, BROPT_VLAN_ENABLED))
+		return 0;
+
+	vg = nbp_vlan_group_rcu(dst);
+	v = br_vlan_find(vg, path->bridge.vlan_id);
+	if (!v || !br_vlan_should_use(v))
+		return -EINVAL;
+
+	if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED))
+		return 0;
+
+	if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG)
+		path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP;
+	else if (v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)
+		path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW;
+	else
+		path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG;
+
+	return 0;
+}
+
 int br_vlan_get_info(const struct net_device *dev, u16 vid,
 		     struct bridge_vlan_info *p_vinfo)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d864840..db237a60 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -639,6 +639,52 @@ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
 
+static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack)
+{
+	int k = stack->num_paths++;
+
+	if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX))
+		return NULL;
+
+	return &stack->path[k];
+}
+
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+			  struct net_device_path_stack *stack)
+{
+	const struct net_device *last_dev;
+	struct net_device_path_ctx ctx = {
+		.dev	= dev,
+		.daddr	= daddr,
+	};
+	struct net_device_path *path;
+	int ret = 0;
+
+	stack->num_paths = 0;
+	while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
+		last_dev = ctx.dev;
+		path = dev_fwd_path(stack);
+		if (!path)
+			return -1;
+
+		memset(path, 0, sizeof(struct net_device_path));
+		ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path);
+		if (ret < 0)
+			return -1;
+
+		if (WARN_ON_ONCE(last_dev == ctx.dev))
+			return -1;
+	}
+	path = dev_fwd_path(stack);
+	if (!path)
+		return -1;
+	path->type = DEV_PATH_ETHERNET;
+	path->dev = ctx.dev;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_fill_forward_path);
+
 /**
  *	__dev_get_by_name	- find a device by its name
  *	@net: the applicable net namespace
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index ca80f869..35a1249a 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -329,6 +329,15 @@ int call_dsa_notifiers(unsigned long val, struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(call_dsa_notifiers);
 
+struct dsa_port *dsa_port_from_netdev(struct net_device *netdev)
+{
+	if (!netdev || !dsa_slave_dev_check(netdev))
+		return ERR_PTR(-ENODEV);
+
+	return dsa_slave_to_port(netdev);
+}
+EXPORT_SYMBOL_GPL(dsa_port_from_netdev);
+
 static int __init dsa_init_module(void)
 {
 	int rc;
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index d423ba79..908410de 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -204,6 +204,7 @@ extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
 int dsa_slave_create(struct dsa_port *dp);
 void dsa_slave_destroy(struct net_device *slave_dev);
+bool dsa_slave_dev_check(const struct net_device *dev);
 int dsa_slave_suspend(struct net_device *slave_dev);
 int dsa_slave_resume(struct net_device *slave_dev);
 int dsa_slave_register_notifier(void);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 50feb3d8..69f3bfb0 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -22,8 +22,6 @@
 
 #include "dsa_priv.h"
 
-static bool dsa_slave_dev_check(const struct net_device *dev);
-
 /* slave mii_bus handling ***************************************************/
 static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
 {
@@ -1033,14 +1031,32 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 	}
 }
 
+static int dsa_slave_setup_ft_block(struct dsa_switch *ds, int port,
+				    void *type_data)
+{
+	struct dsa_port *cpu_dp = dsa_to_port(ds, port)->cpu_dp;
+	struct net_device *master = cpu_dp->master;
+
+	if (!master->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	return master->netdev_ops->ndo_setup_tc(master, TC_SETUP_FT, type_data);
+}
+
 static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_switch *ds = dp->ds;
 
-	if (type == TC_SETUP_BLOCK)
+	switch (type) {
+	case TC_SETUP_BLOCK:
 		return dsa_slave_setup_tc_block(dev, type_data);
+	case TC_SETUP_FT:
+		return dsa_slave_setup_ft_block(ds, dp->index, type_data);
+	default:
+		break;
+	}
 
 	if (!ds->ops->port_setup_tc)
 		return -EOPNOTSUPP;
@@ -1226,6 +1242,21 @@ static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev)
 	return dp->ds->devlink ? &dp->devlink_port : NULL;
 }
 
+static int dsa_slave_fill_forward_path(struct net_device_path_ctx *ctx,
+				       struct net_device_path *path)
+{
+	struct dsa_port *dp = dsa_slave_to_port(ctx->dev);
+	struct dsa_port *cpu_dp = dp->cpu_dp;
+
+	path->dev = ctx->dev;
+	path->type = DEV_PATH_DSA;
+	path->dsa.proto = cpu_dp->tag_ops->proto;
+	path->dsa.port = dp->index;
+	ctx->dev = cpu_dp->master;
+
+	return 0;
+}
+
 static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
@@ -1250,6 +1281,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= dsa_slave_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= dsa_slave_vlan_rx_kill_vid,
 	.ndo_get_devlink_port	= dsa_slave_get_devlink_port,
+	.ndo_fill_forward_path	= dsa_slave_fill_forward_path,
 };
 
 static struct device_type dsa_type = {
@@ -1499,7 +1531,7 @@ void dsa_slave_destroy(struct net_device *slave_dev)
 	free_netdev(slave_dev);
 }
 
-static bool dsa_slave_dev_check(const struct net_device *dev)
+bool dsa_slave_dev_check(const struct net_device *dev)
 {
 	return dev->netdev_ops == &dsa_slave_netdev_ops;
 }
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index f17b4021..803b92e4 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -56,8 +56,6 @@ config NF_TABLES_ARP
 	help
 	  This option enables the ARP support for nf_tables.
 
-endif # NF_TABLES
-
 config NF_FLOW_TABLE_IPV4
 	tristate "Netfilter flow table IPv4 module"
 	depends on NF_FLOW_TABLE
@@ -66,6 +64,8 @@ config NF_FLOW_TABLE_IPV4
 
 	  To compile it as a module, choose M here.
 
+endif # NF_TABLES
+
 config NF_DUP_IPV4
 	tristate "Netfilter IPv4 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 69443e9a..0b481d23 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -45,7 +45,6 @@ config NFT_FIB_IPV6
 	  multicast or blackhole.
 
 endif # NF_TABLES_IPV6
-endif # NF_TABLES
 
 config NF_FLOW_TABLE_IPV6
 	tristate "Netfilter flow table IPv6 module"
@@ -55,6 +54,8 @@ config NF_FLOW_TABLE_IPV6
 
 	  To compile it as a module, choose M here.
 
+endif # NF_TABLES
+
 config NF_DUP_IPV6
 	tristate "Netfilter IPv6 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 12b15e32..f6034cf1 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -690,8 +690,6 @@ config NFT_FIB_NETDEV
 
 endif # NF_TABLES_NETDEV
 
-endif # NF_TABLES
-
 config NF_FLOW_TABLE_INET
 	tristate "Netfilter flow table mixed IPv4/IPv6 module"
 	depends on NF_FLOW_TABLE
@@ -700,11 +698,12 @@ config NF_FLOW_TABLE_INET
 
 	  To compile it as a module, choose M here.
 
+endif # NF_TABLES
+
 config NF_FLOW_TABLE
 	tristate "Netfilter flow table module"
 	depends on NETFILTER_INGRESS
 	depends on NF_CONNTRACK
-	depends on NF_TABLES
 	help
 	  This option adds the flow table core infrastructure.
 
@@ -984,6 +983,15 @@ config NETFILTER_XT_TARGET_NOTRACK
 	depends on NETFILTER_ADVANCED
 	select NETFILTER_XT_TARGET_CT
 
+config NETFILTER_XT_TARGET_FLOWOFFLOAD
+	tristate '"FLOWOFFLOAD" target support'
+	depends on NF_FLOW_TABLE
+	depends on NETFILTER_INGRESS
+	help
+	  This option adds a `FLOWOFFLOAD' target, which uses the nf_flow_offload
+	  module to speed up processing of packets by bypassing the usual
+	  netfilter chains
+
 config NETFILTER_XT_TARGET_RATEEST
 	tristate '"RATEEST" target support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4fc075b6..d93a121b 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -120,7 +120,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV)	+= nft_fwd_netdev.o
 
 # flow table infrastructure
 obj-$(CONFIG_NF_FLOW_TABLE)	+= nf_flow_table.o
-nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o
+nf_flow_table-objs		:= nf_flow_table_core.o nf_flow_table_ip.o \
+				   nf_flow_table_offload.o
 
 obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
 
@@ -140,6 +141,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_FLOWOFFLOAD) += xt_FLOWOFFLOAD.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_HMARK) += xt_HMARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 64445366..d8930766 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -864,9 +864,8 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 
-static inline void nf_ct_acct_update(struct nf_conn *ct,
-				     enum ip_conntrack_info ctinfo,
-				     unsigned int len)
+void nf_ct_acct_add(struct nf_conn *ct, u32 dir, unsigned int packets,
+		    unsigned int bytes)
 {
 	struct nf_conn_acct *acct;
 
@@ -874,10 +873,11 @@ static inline void nf_ct_acct_update(struct nf_conn *ct,
 	if (acct) {
 		struct nf_conn_counter *counter = acct->counter;
 
-		atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
-		atomic64_add(len, &counter[CTINFO2DIR(ctinfo)].bytes);
+		atomic64_add(packets, &counter[dir].packets);
+		atomic64_add(bytes, &counter[dir].bytes);
 	}
 }
+EXPORT_SYMBOL_GPL(nf_ct_acct_add);
 
 static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 			     const struct nf_conn *loser_ct)
@@ -891,7 +891,7 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 
 		/* u32 should be fine since we must have seen one packet. */
 		bytes = atomic64_read(&counter[CTINFO2DIR(ctinfo)].bytes);
-		nf_ct_acct_update(ct, ctinfo, bytes);
+		nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), bytes);
 	}
 }
 
@@ -1783,7 +1783,7 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 		WRITE_ONCE(ct->timeout, extra_jiffies);
 acct:
 	if (do_acct)
-		nf_ct_acct_update(ct, ctinfo, skb->len);
+		nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), skb->len);
 }
 EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct);
 
@@ -1791,7 +1791,7 @@ bool nf_ct_kill_acct(struct nf_conn *ct,
 		     enum ip_conntrack_info ctinfo,
 		     const struct sk_buff *skb)
 {
-	nf_ct_acct_update(ct, ctinfo, skb->len);
+	nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), skb->len);
 
 	return nf_ct_delete(ct, 0, 0);
 }
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index b3f4a334..94001eb5 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -397,6 +397,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			msg = "not picking up existing connection ";
 			goto out_invalid;
 		}
+		break;
 	case CT_DCCP_REQUEST:
 		break;
 	case CT_DCCP_INVALID:
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 92375217..ae01b1c5 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1444,6 +1444,11 @@ void nf_conntrack_tcp_init_net(struct net *net)
 	tn->tcp_loose = nf_ct_tcp_loose;
 	tn->tcp_be_liberal = nf_ct_tcp_be_liberal;
 	tn->tcp_max_retrans = nf_ct_tcp_max_retrans;
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	tn->offload_timeout = 30 * HZ;
+	tn->offload_pickup = 120 * HZ;
+#endif
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp =
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 7365b43f..1eee45f5 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -264,6 +264,11 @@ void nf_conntrack_udp_init_net(struct net *net)
 
 	for (i = 0; i < UDP_CT_MAX; i++)
 		un->timeouts[i] = udp_timeouts[i];
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	un->offload_timeout = 30 * HZ;
+	un->offload_pickup = 30 * HZ;
+#endif
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp =
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 9c6259c2..20419961 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -353,7 +353,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
 		goto release;
 
-	if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
+	if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status))
+		seq_puts(s, "[HW_OFFLOAD] ");
+	else if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
 		seq_puts(s, "[OFFLOAD] ");
 	else if (test_bit(IPS_ASSURED_BIT, &ct->status))
 		seq_puts(s, "[ASSURED] ");
@@ -620,11 +622,19 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK,
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD,
+	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP,
+#endif
 	NF_SYSCTL_CT_PROTO_TCP_LOOSE,
 	NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
 	NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD,
+	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP,
+#endif
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6,
 #ifdef CONFIG_NF_CT_PROTO_SCTP
@@ -812,6 +822,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = {
+		.procname	= "nf_flowtable_tcp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = {
+		.procname	= "nf_flowtable_tcp_pickup",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+#endif
 	[NF_SYSCTL_CT_PROTO_TCP_LOOSE] = {
 		.procname	= "nf_conntrack_tcp_loose",
 		.maxlen		= sizeof(int),
@@ -846,6 +870,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD)
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = {
+		.procname	= "nf_flowtable_udp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = {
+		.procname	= "nf_flowtable_udp_pickup",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+#endif
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = {
 		.procname	= "nf_conntrack_icmp_timeout",
 		.maxlen		= sizeof(unsigned int),
@@ -1028,6 +1066,12 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net,
 	XASSIGN(LIBERAL, &tn->tcp_be_liberal);
 	XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans);
 #undef XASSIGN
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout;
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup;
+#endif
+
 }
 
 static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
@@ -1115,6 +1159,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout;
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED];
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED];
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout;
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup;
+#endif
 
 	nf_conntrack_standalone_init_tcp_sysctl(net, table);
 	nf_conntrack_standalone_init_sctp_sysctl(net, table);
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index e1ffc66b..7addad7d 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -7,31 +7,21 @@
 #include <linux/netdevice.h>
 #include <net/ip.h>
 #include <net/ip6_route.h>
-#include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 
-struct flow_offload_entry {
-	struct flow_offload	flow;
-	struct nf_conn		*ct;
-	struct rcu_head		rcu_head;
-};
-
 static DEFINE_MUTEX(flowtable_lock);
 static LIST_HEAD(flowtables);
 
 static void
-flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
-		      struct nf_flow_route *route,
+flow_offload_fill_dir(struct flow_offload *flow,
 		      enum flow_offload_tuple_dir dir)
 {
 	struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
-	struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
-	struct dst_entry *other_dst = route->tuple[!dir].dst;
-	struct dst_entry *dst = route->tuple[dir].dst;
+	struct nf_conntrack_tuple *ctt = &flow->ct->tuplehash[dir].tuple;
 
 	ft->dir = dir;
 
@@ -39,12 +29,10 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 	case NFPROTO_IPV4:
 		ft->src_v4 = ctt->src.u3.in;
 		ft->dst_v4 = ctt->dst.u3.in;
-		ft->mtu = ip_dst_mtu_maybe_forward(dst, true);
 		break;
 	case NFPROTO_IPV6:
 		ft->src_v6 = ctt->src.u3.in6;
 		ft->dst_v6 = ctt->dst.u3.in6;
-		ft->mtu = ip6_dst_mtu_forward(dst);
 		break;
 	}
 
@@ -52,49 +40,32 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 	ft->l4proto = ctt->dst.protonum;
 	ft->src_port = ctt->src.u.tcp.port;
 	ft->dst_port = ctt->dst.u.tcp.port;
-
-	ft->iifidx = other_dst->dev->ifindex;
-	ft->dst_cache = dst;
 }
 
-struct flow_offload *
-flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
+struct flow_offload *flow_offload_alloc(struct nf_conn *ct)
 {
-	struct flow_offload_entry *entry;
 	struct flow_offload *flow;
 
 	if (unlikely(nf_ct_is_dying(ct) ||
 	    !atomic_inc_not_zero(&ct->ct_general.use)))
 		return NULL;
 
-	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
-	if (!entry)
+	flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
+	if (!flow)
 		goto err_ct_refcnt;
 
-	flow = &entry->flow;
+	flow->ct = ct;
 
-	if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst))
-		goto err_dst_cache_original;
-
-	if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst))
-		goto err_dst_cache_reply;
-
-	entry->ct = ct;
-
-	flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_ORIGINAL);
-	flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_REPLY);
+	flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
+	flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_REPLY);
 
 	if (ct->status & IPS_SRC_NAT)
-		flow->flags |= FLOW_OFFLOAD_SNAT;
+		__set_bit(NF_FLOW_SNAT, &flow->flags);
 	if (ct->status & IPS_DST_NAT)
-		flow->flags |= FLOW_OFFLOAD_DNAT;
+		__set_bit(NF_FLOW_DNAT, &flow->flags);
 
 	return flow;
 
-err_dst_cache_reply:
-	dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst);
-err_dst_cache_original:
-	kfree(entry);
 err_ct_refcnt:
 	nf_ct_put(ct);
 
@@ -102,24 +73,111 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
 }
 EXPORT_SYMBOL_GPL(flow_offload_alloc);
 
-static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
+static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple)
 {
-	tcp->state = TCP_CONNTRACK_ESTABLISHED;
-	tcp->seen[0].td_maxwin = 0;
-	tcp->seen[1].td_maxwin = 0;
+	const struct rt6_info *rt;
+
+	if (flow_tuple->l3proto == NFPROTO_IPV6) {
+		rt = (const struct rt6_info *)flow_tuple->dst_cache;
+		return rt6_get_cookie(rt);
+	}
+
+	return 0;
+}
+
+static int flow_offload_fill_route(struct flow_offload *flow,
+				   const struct nf_flow_route *route,
+				   enum flow_offload_tuple_dir dir)
+{
+	struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple;
+	struct dst_entry *dst = route->tuple[dir].dst;
+	int i, j = 0;
+
+	switch (flow_tuple->l3proto) {
+	case NFPROTO_IPV4:
+		flow_tuple->mtu = ip_dst_mtu_maybe_forward(dst, true);
+		break;
+	case NFPROTO_IPV6:
+		flow_tuple->mtu = ip6_dst_mtu_forward(dst);
+		break;
+	}
+
+	flow_tuple->iifidx = route->tuple[dir].in.ifindex;
+	for (i = route->tuple[dir].in.num_encaps - 1; i >= 0; i--) {
+		flow_tuple->encap[j].id = route->tuple[dir].in.encap[i].id;
+		flow_tuple->encap[j].proto = route->tuple[dir].in.encap[i].proto;
+		if (route->tuple[dir].in.ingress_vlans & BIT(i))
+			flow_tuple->in_vlan_ingress |= BIT(j);
+		j++;
+	}
+	flow_tuple->encap_num = route->tuple[dir].in.num_encaps;
+
+	switch (route->tuple[dir].xmit_type) {
+	case FLOW_OFFLOAD_XMIT_DIRECT:
+		memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest,
+		       ETH_ALEN);
+		memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source,
+		       ETH_ALEN);
+		flow_tuple->out.ifidx = route->tuple[dir].out.ifindex;
+		flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex;
+		break;
+	case FLOW_OFFLOAD_XMIT_XFRM:
+	case FLOW_OFFLOAD_XMIT_NEIGH:
+		if (!dst_hold_safe(route->tuple[dir].dst))
+			return -1;
+
+		flow_tuple->dst_cache = dst;
+		flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple);
+		break;
+	}
+	flow_tuple->xmit_type = route->tuple[dir].xmit_type;
+
+	return 0;
+}
+
+static void nft_flow_dst_release(struct flow_offload *flow,
+				 enum flow_offload_tuple_dir dir)
+{
+	if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH ||
+	    flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)
+		dst_release(flow->tuplehash[dir].tuple.dst_cache);
 }
 
-#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
-#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
+int flow_offload_route_init(struct flow_offload *flow,
+			    const struct nf_flow_route *route)
+{
+	int err;
+
+	err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
+	if (err < 0)
+		return err;
+
+	err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
+	if (err < 0)
+		goto err_route_reply;
+
+	flow->type = NF_FLOW_OFFLOAD_ROUTE;
+
+	return 0;
+
+err_route_reply:
+	nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(flow_offload_route_init);
 
-static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 {
-	return (__s32)(timeout - (u32)jiffies);
+	tcp->state = TCP_CONNTRACK_ESTABLISHED;
+	tcp->seen[0].td_maxwin = 0;
+	tcp->seen[1].td_maxwin = 0;
 }
 
 static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	struct net *net = nf_ct_net(ct);
 	int l4num = nf_ct_protonum(ct);
 	unsigned int timeout;
 
@@ -127,12 +185,17 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 	if (!l4proto)
 		return;
 
-	if (l4num == IPPROTO_TCP)
-		timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT;
-	else if (l4num == IPPROTO_UDP)
-		timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT;
-	else
+	if (l4num == IPPROTO_TCP) {
+		struct nf_tcp_net *tn = nf_tcp_pernet(net);
+
+		timeout = tn->offload_pickup;
+	} else if (l4num == IPPROTO_UDP) {
+		struct nf_udp_net *tn = nf_udp_pernet(net);
+
+		timeout = tn->offload_pickup;
+	} else {
 		return;
+	}
 
 	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
 		ct->timeout = nfct_time_stamp + timeout;
@@ -150,17 +213,23 @@ static void flow_offload_fixup_ct(struct nf_conn *ct)
 	flow_offload_fixup_ct_timeout(ct);
 }
 
-void flow_offload_free(struct flow_offload *flow)
+static void flow_offload_route_release(struct flow_offload *flow)
 {
-	struct flow_offload_entry *e;
+	nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
+	nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_REPLY);
+}
 
-	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
-	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
-	e = container_of(flow, struct flow_offload_entry, flow);
-	if (flow->flags & FLOW_OFFLOAD_DYING)
-		nf_ct_delete(e->ct, 0, 0);
-	nf_ct_put(e->ct);
-	kfree_rcu(e, rcu_head);
+void flow_offload_free(struct flow_offload *flow)
+{
+	switch (flow->type) {
+	case NF_FLOW_OFFLOAD_ROUTE:
+		flow_offload_route_release(flow);
+		break;
+	default:
+		break;
+	}
+	nf_ct_put(flow->ct);
+	kfree_rcu(flow, rcu_head);
 }
 EXPORT_SYMBOL_GPL(flow_offload_free);
 
@@ -168,14 +237,14 @@ static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
 {
 	const struct flow_offload_tuple *tuple = data;
 
-	return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
+	return jhash(tuple, offsetof(struct flow_offload_tuple, __hash), seed);
 }
 
 static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
 {
 	const struct flow_offload_tuple_rhash *tuplehash = data;
 
-	return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
+	return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, __hash), seed);
 }
 
 static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -184,7 +253,7 @@ static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
 	const struct flow_offload_tuple *tuple = arg->key;
 	const struct flow_offload_tuple_rhash *x = ptr;
 
-	if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
+	if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, __hash)))
 		return 1;
 
 	return 0;
@@ -198,30 +267,35 @@ static const struct rhashtable_params nf_flow_offload_rhash_params = {
 	.automatic_shrinking	= true,
 };
 
-#define        DAY     (86400 * HZ)
-
-/* Set an arbitrary timeout large enough not to ever expire, this save
- * us a check for the IPS_OFFLOAD_BIT from the packet path via
- * nf_ct_is_expired().
- */
-static void nf_ct_offload_timeout(struct flow_offload *flow)
+unsigned long flow_offload_get_timeout(struct flow_offload *flow)
 {
-	struct flow_offload_entry *entry;
-	struct nf_conn *ct;
+	const struct nf_conntrack_l4proto *l4proto;
+	unsigned long timeout = NF_FLOW_TIMEOUT;
+	struct net *net = nf_ct_net(flow->ct);
+	int l4num = nf_ct_protonum(flow->ct);
 
-	entry = container_of(flow, struct flow_offload_entry, flow);
-	ct = entry->ct;
+	l4proto = nf_ct_l4proto_find(l4num);
+	if (!l4proto)
+		return timeout;
+
+	if (l4num == IPPROTO_TCP) {
+		struct nf_tcp_net *tn = nf_tcp_pernet(net);
+
+		timeout = tn->offload_timeout;
+	} else if (l4num == IPPROTO_UDP) {
+		struct nf_udp_net *tn = nf_udp_pernet(net);
 
-	if (nf_ct_expires(ct) < DAY / 2)
-		ct->timeout = nfct_time_stamp + DAY;
+		timeout = tn->offload_timeout;
+	}
+
+	return timeout;
 }
 
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 {
 	int err;
 
-	nf_ct_offload_timeout(flow);
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+	flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
 
 	err = rhashtable_insert_fast(&flow_table->rhashtable,
 				     &flow->tuplehash[0].node,
@@ -239,10 +313,29 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 		return err;
 	}
 
+	nf_ct_offload_timeout(flow->ct);
+
+	if (nf_flowtable_hw_offload(flow_table)) {
+		__set_bit(NF_FLOW_HW, &flow->flags);
+		nf_flow_offload_add(flow_table, flow);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
 
+void flow_offload_refresh(struct nf_flowtable *flow_table,
+			  struct flow_offload *flow)
+{
+	flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+
+	if (likely(!nf_flowtable_hw_offload(flow_table)))
+		return;
+
+	nf_flow_offload_add(flow_table, flow);
+}
+EXPORT_SYMBOL_GPL(flow_offload_refresh);
+
 static inline bool nf_flow_has_expired(const struct flow_offload *flow)
 {
 	return nf_flow_timeout_delta(flow->timeout) <= 0;
@@ -251,8 +344,6 @@ static inline bool nf_flow_has_expired(const struct flow_offload *flow)
 static void flow_offload_del(struct nf_flowtable *flow_table,
 			     struct flow_offload *flow)
 {
-	struct flow_offload_entry *e;
-
 	rhashtable_remove_fast(&flow_table->rhashtable,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
 			       nf_flow_offload_rhash_params);
@@ -260,28 +351,21 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
 			       nf_flow_offload_rhash_params);
 
-	e = container_of(flow, struct flow_offload_entry, flow);
-	clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
+	clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status);
 
 	if (nf_flow_has_expired(flow))
-		flow_offload_fixup_ct(e->ct);
-	else if (flow->flags & FLOW_OFFLOAD_TEARDOWN)
-		flow_offload_fixup_ct_timeout(e->ct);
-
-	if (!(flow->flags & FLOW_OFFLOAD_TEARDOWN))
-		flow_offload_fixup_ct_state(e->ct);
+		flow_offload_fixup_ct(flow->ct);
+	else
+		flow_offload_fixup_ct_timeout(flow->ct);
 
 	flow_offload_free(flow);
 }
 
 void flow_offload_teardown(struct flow_offload *flow)
 {
-	struct flow_offload_entry *e;
-
-	flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+	set_bit(NF_FLOW_TEARDOWN, &flow->flags);
 
-	e = container_of(flow, struct flow_offload_entry, flow);
-	flow_offload_fixup_ct_state(e->ct);
+	flow_offload_fixup_ct_state(flow->ct);
 }
 EXPORT_SYMBOL_GPL(flow_offload_teardown);
 
@@ -291,7 +375,6 @@ flow_offload_lookup(struct nf_flowtable *flow_table,
 {
 	struct flow_offload_tuple_rhash *tuplehash;
 	struct flow_offload *flow;
-	struct flow_offload_entry *e;
 	int dir;
 
 	tuplehash = rhashtable_lookup(&flow_table->rhashtable, tuple,
@@ -301,19 +384,17 @@ flow_offload_lookup(struct nf_flowtable *flow_table,
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-	if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))
+	if (test_bit(NF_FLOW_TEARDOWN, &flow->flags))
 		return NULL;
 
-	e = container_of(flow, struct flow_offload_entry, flow);
-	if (unlikely(nf_ct_is_dying(e->ct)))
+	if (unlikely(nf_ct_is_dying(flow->ct)))
 		return NULL;
 
 	return tuplehash;
 }
 EXPORT_SYMBOL_GPL(flow_offload_lookup);
 
-static int
-nf_flow_table_iterate(struct nf_flowtable *flow_table,
+int nf_flow_table_iterate(struct nf_flowtable *flow_table,
 		      void (*iter)(struct flow_offload *flow, void *data),
 		      void *data)
 {
@@ -326,7 +407,6 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,
 	rhashtable_walk_start(&hti);
 
 	while ((tuplehash = rhashtable_walk_next(&hti))) {
-
 		if (IS_ERR(tuplehash)) {
 			if (PTR_ERR(tuplehash) != -EAGAIN) {
 				err = PTR_ERR(tuplehash);
@@ -346,23 +426,49 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(nf_flow_table_iterate);
 
-static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
+static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple)
 {
-	struct nf_flowtable *flow_table = data;
-	struct flow_offload_entry *e;
-	bool teardown;
+	struct dst_entry *dst;
 
-	e = container_of(flow, struct flow_offload_entry, flow);
+	if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH ||
+	    tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) {
+		dst = tuple->dst_cache;
+		if (!dst_check(dst, tuple->dst_cookie))
+			return true;
+	}
+
+	return false;
+}
 
-	teardown = flow->flags & (FLOW_OFFLOAD_DYING |
-				  FLOW_OFFLOAD_TEARDOWN);
+static bool nf_flow_has_stale_dst(struct flow_offload *flow)
+{
+	return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) ||
+	       flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple);
+}
 
-	if (!teardown)
-		nf_ct_offload_timeout(flow);
+static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
+{
+	struct nf_flowtable *flow_table = data;
 
-	if (nf_flow_has_expired(flow) || teardown)
-		flow_offload_del(flow_table, flow);
+	if (nf_flow_has_expired(flow) ||
+	    nf_ct_is_dying(flow->ct) ||
+	    nf_flow_has_stale_dst(flow))
+		set_bit(NF_FLOW_TEARDOWN, &flow->flags);
+
+	if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
+		if (test_bit(NF_FLOW_HW, &flow->flags)) {
+			if (!test_bit(NF_FLOW_HW_DYING, &flow->flags))
+				nf_flow_offload_del(flow_table, flow);
+			else if (test_bit(NF_FLOW_HW_DEAD, &flow->flags))
+				flow_offload_del(flow_table, flow);
+		} else {
+			flow_offload_del(flow_table, flow);
+		}
+	} else if (test_bit(NF_FLOW_HW, &flow->flags)) {
+		nf_flow_offload_stats(flow_table, flow);
+	}
 }
 
 static void nf_flow_offload_work_gc(struct work_struct *work)
@@ -374,30 +480,20 @@ static void nf_flow_offload_work_gc(struct work_struct *work)
 	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
 }
 
-static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
-				__be16 port, __be16 new_port)
+static void nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
+				 __be16 port, __be16 new_port)
 {
 	struct tcphdr *tcph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
-		return -1;
-
 	tcph = (void *)(skb_network_header(skb) + thoff);
 	inet_proto_csum_replace2(&tcph->check, skb, port, new_port, false);
-
-	return 0;
 }
 
-static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
-				__be16 port, __be16 new_port)
+static void nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
+				 __be16 port, __be16 new_port)
 {
 	struct udphdr *udph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
-		return -1;
-
 	udph = (void *)(skb_network_header(skb) + thoff);
 	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 		inet_proto_csum_replace2(&udph->check, skb, port,
@@ -405,38 +501,28 @@ static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
 		if (!udph->check)
 			udph->check = CSUM_MANGLED_0;
 	}
-
-	return 0;
 }
 
-static int nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff,
-			    u8 protocol, __be16 port, __be16 new_port)
+static void nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff,
+			     u8 protocol, __be16 port, __be16 new_port)
 {
 	switch (protocol) {
 	case IPPROTO_TCP:
-		if (nf_flow_nat_port_tcp(skb, thoff, port, new_port) < 0)
-			return NF_DROP;
+		nf_flow_nat_port_tcp(skb, thoff, port, new_port);
 		break;
 	case IPPROTO_UDP:
-		if (nf_flow_nat_port_udp(skb, thoff, port, new_port) < 0)
-			return NF_DROP;
+		nf_flow_nat_port_udp(skb, thoff, port, new_port);
 		break;
 	}
-
-	return 0;
 }
 
-int nf_flow_snat_port(const struct flow_offload *flow,
-		      struct sk_buff *skb, unsigned int thoff,
-		      u8 protocol, enum flow_offload_tuple_dir dir)
+void nf_flow_snat_port(const struct flow_offload *flow,
+		       struct sk_buff *skb, unsigned int thoff,
+		       u8 protocol, enum flow_offload_tuple_dir dir)
 {
 	struct flow_ports *hdr;
 	__be16 port, new_port;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*hdr)))
-		return -1;
-
 	hdr = (void *)(skb_network_header(skb) + thoff);
 
 	switch (dir) {
@@ -450,25 +536,19 @@ int nf_flow_snat_port(const struct flow_offload *flow,
 		new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port;
 		hdr->dest = new_port;
 		break;
-	default:
-		return -1;
 	}
 
-	return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
+	nf_flow_nat_port(skb, thoff, protocol, port, new_port);
 }
 EXPORT_SYMBOL_GPL(nf_flow_snat_port);
 
-int nf_flow_dnat_port(const struct flow_offload *flow,
-		      struct sk_buff *skb, unsigned int thoff,
-		      u8 protocol, enum flow_offload_tuple_dir dir)
+void nf_flow_dnat_port(const struct flow_offload *flow, struct sk_buff *skb,
+		       unsigned int thoff, u8 protocol,
+		       enum flow_offload_tuple_dir dir)
 {
 	struct flow_ports *hdr;
 	__be16 port, new_port;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*hdr)))
-		return -1;
-
 	hdr = (void *)(skb_network_header(skb) + thoff);
 
 	switch (dir) {
@@ -482,11 +562,9 @@ int nf_flow_dnat_port(const struct flow_offload *flow,
 		new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port;
 		hdr->source = new_port;
 		break;
-	default:
-		return -1;
 	}
 
-	return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
+	nf_flow_nat_port(skb, thoff, protocol, port, new_port);
 }
 EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
 
@@ -494,7 +572,9 @@ int nf_flow_table_init(struct nf_flowtable *flowtable)
 {
 	int err;
 
-	INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+	INIT_DELAYED_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+	flow_block_init(&flowtable->flow_block);
+	init_rwsem(&flowtable->flow_block_lock);
 
 	err = rhashtable_init(&flowtable->rhashtable,
 			      &nf_flow_offload_rhash_params);
@@ -515,25 +595,24 @@ EXPORT_SYMBOL_GPL(nf_flow_table_init);
 static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
 {
 	struct net_device *dev = data;
-	struct flow_offload_entry *e;
-
-	e = container_of(flow, struct flow_offload_entry, flow);
 
 	if (!dev) {
 		flow_offload_teardown(flow);
 		return;
 	}
-	if (net_eq(nf_ct_net(e->ct), dev_net(dev)) &&
+
+	if (net_eq(nf_ct_net(flow->ct), dev_net(dev)) &&
 	    (flow->tuplehash[0].tuple.iifidx == dev->ifindex ||
 	     flow->tuplehash[1].tuple.iifidx == dev->ifindex))
-		flow_offload_dead(flow);
+		flow_offload_teardown(flow);
 }
 
-static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
-					  struct net_device *dev)
+void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
+			      struct net_device *dev)
 {
 	nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
 	flush_delayed_work(&flowtable->gc_work);
+	nf_flow_table_offload_flush(flowtable);
 }
 
 void nf_flow_table_cleanup(struct net_device *dev)
@@ -542,7 +621,7 @@ void nf_flow_table_cleanup(struct net_device *dev)
 
 	mutex_lock(&flowtable_lock);
 	list_for_each_entry(flowtable, &flowtables, list)
-		nf_flow_table_iterate_cleanup(flowtable, dev);
+		nf_flow_table_gc_cleanup(flowtable, dev);
 	mutex_unlock(&flowtable_lock);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
@@ -552,9 +631,14 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
 	mutex_lock(&flowtable_lock);
 	list_del(&flow_table->list);
 	mutex_unlock(&flowtable_lock);
+
 	cancel_delayed_work_sync(&flow_table->gc_work);
 	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
 	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
+	nf_flow_table_offload_flush(flow_table);
+	if (nf_flowtable_hw_offload(flow_table))
+		nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step,
+				      flow_table);
 	rhashtable_destroy(&flow_table->rhashtable);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_free);
@@ -578,12 +662,23 @@ static struct notifier_block flow_offload_netdev_notifier = {
 
 static int __init nf_flow_table_module_init(void)
 {
-	return register_netdevice_notifier(&flow_offload_netdev_notifier);
+	int ret;
+
+	ret = nf_flow_table_offload_init();
+	if (ret)
+		return ret;
+
+	ret = register_netdevice_notifier(&flow_offload_netdev_notifier);
+	if (ret)
+		nf_flow_table_offload_exit();
+
+	return ret;
 }
 
 static void __exit nf_flow_table_module_exit(void)
 {
 	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+	nf_flow_table_offload_exit();
 }
 
 module_init(nf_flow_table_module_init);
@@ -591,3 +686,4 @@ module_exit(nf_flow_table_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("Netfilter flow table module");
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index e92aa6b7..889cf88d 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -7,11 +7,15 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/neighbour.h>
 #include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_conntrack_acct.h>
 /* For layer 4 checksum field offset. */
 #include <linux/tcp.h>
 #include <linux/udp.h>
@@ -24,9 +28,6 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto,
 	if (proto != IPPROTO_TCP)
 		return 0;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
-		return -1;
-
 	tcph = (void *)(skb_network_header(skb) + thoff);
 	if (unlikely(tcph->fin || tcph->rst)) {
 		flow_offload_teardown(flow);
@@ -36,30 +37,20 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto,
 	return 0;
 }
 
-static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
-			      __be32 addr, __be32 new_addr)
+static void nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
+			       __be32 addr, __be32 new_addr)
 {
 	struct tcphdr *tcph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
-		return -1;
-
 	tcph = (void *)(skb_network_header(skb) + thoff);
 	inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
-
-	return 0;
 }
 
-static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
-			      __be32 addr, __be32 new_addr)
+static void nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
+			       __be32 addr, __be32 new_addr)
 {
 	struct udphdr *udph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
-		return -1;
-
 	udph = (void *)(skb_network_header(skb) + thoff);
 	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 		inet_proto_csum_replace4(&udph->check, skb, addr,
@@ -67,31 +58,25 @@ static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
 		if (!udph->check)
 			udph->check = CSUM_MANGLED_0;
 	}
-
-	return 0;
 }
 
-static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
-				  unsigned int thoff, __be32 addr,
-				  __be32 new_addr)
+static void nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
+				   unsigned int thoff, __be32 addr,
+				   __be32 new_addr)
 {
 	switch (iph->protocol) {
 	case IPPROTO_TCP:
-		if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
+		nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr);
 		break;
 	case IPPROTO_UDP:
-		if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
+		nf_flow_nat_ip_udp(skb, thoff, addr, new_addr);
 		break;
 	}
-
-	return 0;
 }
 
-static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			   struct iphdr *iph, unsigned int thoff,
-			   enum flow_offload_tuple_dir dir)
+static void nf_flow_snat_ip(const struct flow_offload *flow,
+			    struct sk_buff *skb, struct iphdr *iph,
+			    unsigned int thoff, enum flow_offload_tuple_dir dir)
 {
 	__be32 addr, new_addr;
 
@@ -106,17 +91,15 @@ static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
 		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
 		iph->daddr = new_addr;
 		break;
-	default:
-		return -1;
 	}
 	csum_replace4(&iph->check, addr, new_addr);
 
-	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+	nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
 }
 
-static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			   struct iphdr *iph, unsigned int thoff,
-			   enum flow_offload_tuple_dir dir)
+static void nf_flow_dnat_ip(const struct flow_offload *flow,
+			    struct sk_buff *skb, struct iphdr *iph,
+			    unsigned int thoff, enum flow_offload_tuple_dir dir)
 {
 	__be32 addr, new_addr;
 
@@ -131,29 +114,24 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
 		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
 		iph->saddr = new_addr;
 		break;
-	default:
-		return -1;
 	}
 	csum_replace4(&iph->check, addr, new_addr);
 
-	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+	nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
 }
 
-static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			  unsigned int thoff, enum flow_offload_tuple_dir dir)
+static void nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			  unsigned int thoff, enum flow_offload_tuple_dir dir,
+			  struct iphdr *iph)
 {
-	struct iphdr *iph = ip_hdr(skb);
-
-	if (flow->flags & FLOW_OFFLOAD_SNAT &&
-	    (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
-	     nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
-		return -1;
-	if (flow->flags & FLOW_OFFLOAD_DNAT &&
-	    (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
-	     nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
-		return -1;
-
-	return 0;
+	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
+		nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir);
+		nf_flow_snat_ip(flow, skb, iph, thoff, dir);
+	}
+	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
+		nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir);
+		nf_flow_dnat_ip(flow, skb, iph, thoff, dir);
+	}
 }
 
 static bool ip_has_options(unsigned int thoff)
@@ -161,35 +139,70 @@ static bool ip_has_options(unsigned int thoff)
 	return thoff != sizeof(struct iphdr);
 }
 
+static void nf_flow_tuple_encap(struct sk_buff *skb,
+				struct flow_offload_tuple *tuple)
+{
+	struct vlan_ethhdr *veth;
+	struct pppoe_hdr *phdr;
+	int i = 0;
+
+	if (skb_vlan_tag_present(skb)) {
+		tuple->encap[i].id = skb_vlan_tag_get(skb);
+		tuple->encap[i].proto = skb->vlan_proto;
+		i++;
+	}
+	switch (skb->protocol) {
+	case htons(ETH_P_8021Q):
+		veth = (struct vlan_ethhdr *)skb_mac_header(skb);
+		tuple->encap[i].id = ntohs(veth->h_vlan_TCI);
+		tuple->encap[i].proto = skb->protocol;
+		break;
+	case htons(ETH_P_PPP_SES):
+		phdr = (struct pppoe_hdr *)skb_mac_header(skb);
+		tuple->encap[i].id = ntohs(phdr->sid);
+		tuple->encap[i].proto = skb->protocol;
+		break;
+	}
+}
+
 static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
-			    struct flow_offload_tuple *tuple)
+			    struct flow_offload_tuple *tuple, u32 *hdrsize,
+			    u32 offset)
 {
 	struct flow_ports *ports;
 	unsigned int thoff;
 	struct iphdr *iph;
 
-	if (!pskb_may_pull(skb, sizeof(*iph)))
+	if (!pskb_may_pull(skb, sizeof(*iph) + offset))
 		return -1;
 
-	iph = ip_hdr(skb);
-	thoff = iph->ihl * 4;
+	iph = (struct iphdr *)(skb_network_header(skb) + offset);
+	thoff = (iph->ihl * 4);
 
 	if (ip_is_fragment(iph) ||
 	    unlikely(ip_has_options(thoff)))
 		return -1;
 
-	if (iph->protocol != IPPROTO_TCP &&
-	    iph->protocol != IPPROTO_UDP)
+	thoff += offset;
+
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+		*hdrsize = sizeof(struct tcphdr);
+		break;
+	case IPPROTO_UDP:
+		*hdrsize = sizeof(struct udphdr);
+		break;
+	default:
 		return -1;
+	}
 
 	if (iph->ttl <= 1)
 		return -1;
 
-	thoff = iph->ihl * 4;
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+	if (!pskb_may_pull(skb, thoff + *hdrsize))
 		return -1;
 
-	iph = ip_hdr(skb);
+	iph = (struct iphdr *)(skb_network_header(skb) + offset);
 	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
 
 	tuple->src_v4.s_addr	= iph->saddr;
@@ -199,6 +212,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 	tuple->l3proto		= AF_INET;
 	tuple->l4proto		= iph->protocol;
 	tuple->iifidx		= dev->ifindex;
+	nf_flow_tuple_encap(skb, tuple);
 
 	return 0;
 }
@@ -215,14 +229,6 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
-static int nf_flow_offload_dst_check(struct dst_entry *dst)
-{
-	if (unlikely(dst_xfrm(dst)))
-		return dst_check(dst, 0) ? 0 : -1;
-
-	return 0;
-}
-
 static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 				      const struct nf_hook_state *state,
 				      struct dst_entry *dst)
@@ -233,6 +239,91 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
+static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
+{
+	__be16 proto;
+
+	proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
+			     sizeof(struct pppoe_hdr)));
+	switch (proto) {
+	case htons(PPP_IP):
+		return htons(ETH_P_IP);
+	case htons(PPP_IPV6):
+		return htons(ETH_P_IPV6);
+	}
+
+	return 0;
+}
+
+static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto,
+				       u32 *offset)
+{
+	struct vlan_ethhdr *veth;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_8021Q):
+		veth = (struct vlan_ethhdr *)skb_mac_header(skb);
+		if (veth->h_vlan_encapsulated_proto == proto) {
+			*offset += VLAN_HLEN;
+			return true;
+		}
+		break;
+	case htons(ETH_P_PPP_SES):
+		if (nf_flow_pppoe_proto(skb) == proto) {
+			*offset += PPPOE_SES_HLEN;
+			return true;
+		}
+		break;
+	}
+
+	return false;
+}
+
+static void nf_flow_encap_pop(struct sk_buff *skb,
+			      struct flow_offload_tuple_rhash *tuplehash)
+{
+	struct vlan_hdr *vlan_hdr;
+	int i;
+
+	for (i = 0; i < tuplehash->tuple.encap_num; i++) {
+		if (skb_vlan_tag_present(skb)) {
+			__vlan_hwaccel_clear_tag(skb);
+			continue;
+		}
+		switch (skb->protocol) {
+		case htons(ETH_P_8021Q):
+			vlan_hdr = (struct vlan_hdr *)skb->data;
+			__skb_pull(skb, VLAN_HLEN);
+			vlan_set_encap_proto(skb, vlan_hdr);
+			skb_reset_network_header(skb);
+			break;
+		case htons(ETH_P_PPP_SES):
+			skb->protocol = nf_flow_pppoe_proto(skb);
+			skb_pull(skb, PPPOE_SES_HLEN);
+			skb_reset_network_header(skb);
+			break;
+		}
+	}
+}
+
+static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
+				       const struct flow_offload_tuple_rhash *tuplehash,
+				       unsigned short type)
+{
+	struct net_device *outdev;
+
+	outdev = dev_get_by_index_rcu(net, tuplehash->tuple.out.ifidx);
+	if (!outdev)
+		return NF_DROP;
+
+	skb->dev = outdev;
+	dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest,
+			tuplehash->tuple.out.h_source, skb->len);
+	dev_queue_xmit(skb);
+
+	return NF_STOLEN;
+}
+
 unsigned int
 nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 			const struct nf_hook_state *state)
@@ -243,15 +334,18 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	enum flow_offload_tuple_dir dir;
 	struct flow_offload *flow;
 	struct net_device *outdev;
+	u32 hdrsize, offset = 0;
+	unsigned int thoff, mtu;
 	struct rtable *rt;
-	unsigned int thoff;
 	struct iphdr *iph;
 	__be32 nexthop;
+	int ret;
 
-	if (skb->protocol != htons(ETH_P_IP))
+	if (skb->protocol != htons(ETH_P_IP) &&
+	    !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &offset))
 		return NF_ACCEPT;
 
-	if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
+	if (nf_flow_tuple_ip(skb, state->in, &tuple, &hdrsize, offset) < 0)
 		return NF_ACCEPT;
 
 	tuplehash = flow_offload_lookup(flow_table, &tuple);
@@ -260,75 +354,80 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-	rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
-	outdev = rt->dst.dev;
 
-	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
+	mtu = flow->tuplehash[dir].tuple.mtu + offset;
+	if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
 		return NF_ACCEPT;
 
-	if (skb_try_make_writable(skb, sizeof(*iph)))
-		return NF_DROP;
-
-	thoff = ip_hdr(skb)->ihl * 4;
-	if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
-		return NF_ACCEPT;
-
-	if (nf_flow_offload_dst_check(&rt->dst)) {
-		flow_offload_teardown(flow);
+	iph = (struct iphdr *)(skb_network_header(skb) + offset);
+	thoff = (iph->ihl * 4) + offset;
+	if (nf_flow_state_check(flow, iph->protocol, skb, thoff))
 		return NF_ACCEPT;
-	}
 
-	if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
+	if (skb_try_make_writable(skb, thoff + hdrsize))
 		return NF_DROP;
 
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+	flow_offload_refresh(flow_table, flow);
+
+	nf_flow_encap_pop(skb, tuplehash);
+	thoff -= offset;
+
 	iph = ip_hdr(skb);
+	nf_flow_nat_ip(flow, skb, thoff, dir, iph);
+
 	ip_decrease_ttl(iph);
 	skb->tstamp = 0;
 
-	if (unlikely(dst_xfrm(&rt->dst))) {
+	if (flow_table->flags & NF_FLOWTABLE_COUNTER)
+		nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
+
+	if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
+		rt = (struct rtable *)tuplehash->tuple.dst_cache;
 		memset(skb->cb, 0, sizeof(struct inet_skb_parm));
 		IPCB(skb)->iif = skb->dev->ifindex;
 		IPCB(skb)->flags = IPSKB_FORWARDED;
 		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
 	}
 
-	skb->dev = outdev;
-	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
-	skb_dst_set_noref(skb, &rt->dst);
-	neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
+	switch (tuplehash->tuple.xmit_type) {
+	case FLOW_OFFLOAD_XMIT_NEIGH:
+		rt = (struct rtable *)tuplehash->tuple.dst_cache;
+		outdev = rt->dst.dev;
+		skb->dev = outdev;
+		nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
+		skb_dst_set_noref(skb, &rt->dst);
+		neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
+		ret = NF_STOLEN;
+		break;
+	case FLOW_OFFLOAD_XMIT_DIRECT:
+		ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP);
+		if (ret == NF_DROP)
+			flow_offload_teardown(flow);
+		break;
+	}
 
-	return NF_STOLEN;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
 
-static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
-				struct in6_addr *addr,
-				struct in6_addr *new_addr)
+static void nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
+				 struct in6_addr *addr,
+				 struct in6_addr *new_addr,
+				 struct ipv6hdr *ip6h)
 {
 	struct tcphdr *tcph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
-		return -1;
-
 	tcph = (void *)(skb_network_header(skb) + thoff);
 	inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
 				  new_addr->s6_addr32, true);
-
-	return 0;
 }
 
-static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
-				struct in6_addr *addr,
-				struct in6_addr *new_addr)
+static void nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
+				 struct in6_addr *addr,
+				 struct in6_addr *new_addr)
 {
 	struct udphdr *udph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
-		return -1;
-
 	udph = (void *)(skb_network_header(skb) + thoff);
 	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 		inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
@@ -336,32 +435,26 @@ static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
 		if (!udph->check)
 			udph->check = CSUM_MANGLED_0;
 	}
-
-	return 0;
 }
 
-static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
-				    unsigned int thoff, struct in6_addr *addr,
-				    struct in6_addr *new_addr)
+static void nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
+				     unsigned int thoff, struct in6_addr *addr,
+				     struct in6_addr *new_addr)
 {
 	switch (ip6h->nexthdr) {
 	case IPPROTO_TCP:
-		if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
+		nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr, ip6h);
 		break;
 	case IPPROTO_UDP:
-		if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
+		nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr);
 		break;
 	}
-
-	return 0;
 }
 
-static int nf_flow_snat_ipv6(const struct flow_offload *flow,
-			     struct sk_buff *skb, struct ipv6hdr *ip6h,
-			     unsigned int thoff,
-			     enum flow_offload_tuple_dir dir)
+static void nf_flow_snat_ipv6(const struct flow_offload *flow,
+			      struct sk_buff *skb, struct ipv6hdr *ip6h,
+			      unsigned int thoff,
+			      enum flow_offload_tuple_dir dir)
 {
 	struct in6_addr addr, new_addr;
 
@@ -376,17 +469,15 @@ static int nf_flow_snat_ipv6(const struct flow_offload *flow,
 		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
 		ip6h->daddr = new_addr;
 		break;
-	default:
-		return -1;
 	}
 
-	return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+	nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
 }
 
-static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
-			     struct sk_buff *skb, struct ipv6hdr *ip6h,
-			     unsigned int thoff,
-			     enum flow_offload_tuple_dir dir)
+static void nf_flow_dnat_ipv6(const struct flow_offload *flow,
+			      struct sk_buff *skb, struct ipv6hdr *ip6h,
+			      unsigned int thoff,
+			      enum flow_offload_tuple_dir dir)
 {
 	struct in6_addr addr, new_addr;
 
@@ -401,56 +492,60 @@ static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
 		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
 		ip6h->saddr = new_addr;
 		break;
-	default:
-		return -1;
 	}
 
-	return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+	nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
 }
 
-static int nf_flow_nat_ipv6(const struct flow_offload *flow,
-			    struct sk_buff *skb,
-			    enum flow_offload_tuple_dir dir)
+static void nf_flow_nat_ipv6(const struct flow_offload *flow,
+			     struct sk_buff *skb,
+			     enum flow_offload_tuple_dir dir,
+			     struct ipv6hdr *ip6h)
 {
-	struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	unsigned int thoff = sizeof(*ip6h);
 
-	if (flow->flags & FLOW_OFFLOAD_SNAT &&
-	    (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
-	     nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
-		return -1;
-	if (flow->flags & FLOW_OFFLOAD_DNAT &&
-	    (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
-	     nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
-		return -1;
-
-	return 0;
+	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
+		nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir);
+		nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir);
+	}
+	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
+		nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir);
+		nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir);
+	}
 }
 
 static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
-			      struct flow_offload_tuple *tuple)
+			      struct flow_offload_tuple *tuple, u32 *hdrsize,
+			      u32 offset)
 {
 	struct flow_ports *ports;
 	struct ipv6hdr *ip6h;
 	unsigned int thoff;
 
-	if (!pskb_may_pull(skb, sizeof(*ip6h)))
+	thoff = sizeof(*ip6h) + offset;
+	if (!pskb_may_pull(skb, thoff))
 		return -1;
 
-	ip6h = ipv6_hdr(skb);
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
 
-	if (ip6h->nexthdr != IPPROTO_TCP &&
-	    ip6h->nexthdr != IPPROTO_UDP)
+	switch (ip6h->nexthdr) {
+	case IPPROTO_TCP:
+		*hdrsize = sizeof(struct tcphdr);
+		break;
+	case IPPROTO_UDP:
+		*hdrsize = sizeof(struct udphdr);
+		break;
+	default:
 		return -1;
+	}
 
 	if (ip6h->hop_limit <= 1)
 		return -1;
 
-	thoff = sizeof(*ip6h);
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+	if (!pskb_may_pull(skb, thoff + *hdrsize))
 		return -1;
 
-	ip6h = ipv6_hdr(skb);
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
 	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
 
 	tuple->src_v6		= ip6h->saddr;
@@ -460,6 +555,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
 	tuple->l3proto		= AF_INET6;
 	tuple->l4proto		= ip6h->nexthdr;
 	tuple->iifidx		= dev->ifindex;
+	nf_flow_tuple_encap(skb, tuple);
 
 	return 0;
 }
@@ -475,13 +571,17 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	const struct in6_addr *nexthop;
 	struct flow_offload *flow;
 	struct net_device *outdev;
+	unsigned int thoff, mtu;
+	u32 hdrsize, offset = 0;
 	struct ipv6hdr *ip6h;
 	struct rt6_info *rt;
+	int ret;
 
-	if (skb->protocol != htons(ETH_P_IPV6))
+	if (skb->protocol != htons(ETH_P_IPV6) &&
+	    !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &offset))
 		return NF_ACCEPT;
 
-	if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
+	if (nf_flow_tuple_ipv6(skb, state->in, &tuple, &hdrsize, offset) < 0)
 		return NF_ACCEPT;
 
 	tuplehash = flow_offload_lookup(flow_table, &tuple);
@@ -490,44 +590,57 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-	rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
-	outdev = rt->dst.dev;
-
-	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
-		return NF_ACCEPT;
 
-	if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb,
-				sizeof(*ip6h)))
+	mtu = flow->tuplehash[dir].tuple.mtu + offset;
+	if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
 		return NF_ACCEPT;
 
-	if (nf_flow_offload_dst_check(&rt->dst)) {
-		flow_offload_teardown(flow);
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
+	thoff = sizeof(*ip6h) + offset;
+	if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff))
 		return NF_ACCEPT;
-	}
 
-	if (skb_try_make_writable(skb, sizeof(*ip6h)))
+	if (skb_try_make_writable(skb, thoff + hdrsize))
 		return NF_DROP;
 
-	if (nf_flow_nat_ipv6(flow, skb, dir) < 0)
-		return NF_DROP;
+	flow_offload_refresh(flow_table, flow);
+
+	nf_flow_encap_pop(skb, tuplehash);
 
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
 	ip6h = ipv6_hdr(skb);
+	nf_flow_nat_ipv6(flow, skb, dir, ip6h);
+
 	ip6h->hop_limit--;
 	skb->tstamp = 0;
 
-	if (unlikely(dst_xfrm(&rt->dst))) {
+	if (flow_table->flags & NF_FLOWTABLE_COUNTER)
+		nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
+
+	if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
+		rt = (struct rt6_info *)tuplehash->tuple.dst_cache;
 		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 		IP6CB(skb)->iif = skb->dev->ifindex;
 		IP6CB(skb)->flags = IP6SKB_FORWARDED;
 		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
 	}
 
-	skb->dev = outdev;
-	nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
-	skb_dst_set_noref(skb, &rt->dst);
-	neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
+	switch (tuplehash->tuple.xmit_type) {
+	case FLOW_OFFLOAD_XMIT_NEIGH:
+		rt = (struct rt6_info *)tuplehash->tuple.dst_cache;
+		outdev = rt->dst.dev;
+		skb->dev = outdev;
+		nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
+		skb_dst_set_noref(skb, &rt->dst);
+		neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
+		ret = NF_STOLEN;
+		break;
+	case FLOW_OFFLOAD_XMIT_DIRECT:
+		ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6);
+		if (ret == NF_DROP)
+			flow_offload_teardown(flow);
+		break;
+	}
 
-	return NF_STOLEN;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
new file mode 100644
index 00000000..7a8baaa7
--- /dev/null
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -0,0 +1,1154 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/netdevice.h>
+#include <linux/tc_act/tc_csum.h>
+#include <net/flow_offload.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_acct.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+
+static struct workqueue_struct *nf_flow_offload_add_wq;
+static struct workqueue_struct *nf_flow_offload_del_wq;
+static struct workqueue_struct *nf_flow_offload_stats_wq;
+
+struct flow_offload_work {
+	struct list_head	list;
+	enum flow_cls_command	cmd;
+	int			priority;
+	struct nf_flowtable	*flowtable;
+	struct flow_offload	*flow;
+	struct work_struct	work;
+};
+
+#define NF_FLOW_DISSECTOR(__match, __type, __field)	\
+	(__match)->dissector.offset[__type] =		\
+		offsetof(struct nf_flow_key, __field)
+
+static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
+				   struct ip_tunnel_info *tun_info)
+{
+	struct nf_flow_key *mask = &match->mask;
+	struct nf_flow_key *key = &match->key;
+	unsigned int enc_keys;
+
+	if (!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX))
+		return;
+
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_CONTROL, enc_control);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
+	key->enc_key_id.keyid = tunnel_id_to_key32(tun_info->key.tun_id);
+	mask->enc_key_id.keyid = 0xffffffff;
+	enc_keys = BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+		   BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL);
+
+	if (ip_tunnel_info_af(tun_info) == AF_INET) {
+		NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+				  enc_ipv4);
+		key->enc_ipv4.src = tun_info->key.u.ipv4.dst;
+		key->enc_ipv4.dst = tun_info->key.u.ipv4.src;
+		if (key->enc_ipv4.src)
+			mask->enc_ipv4.src = 0xffffffff;
+		if (key->enc_ipv4.dst)
+			mask->enc_ipv4.dst = 0xffffffff;
+		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+	} else {
+		memcpy(&key->enc_ipv6.src, &tun_info->key.u.ipv6.dst,
+		       sizeof(struct in6_addr));
+		memcpy(&key->enc_ipv6.dst, &tun_info->key.u.ipv6.src,
+		       sizeof(struct in6_addr));
+		if (memcmp(&key->enc_ipv6.src, &in6addr_any,
+			   sizeof(struct in6_addr)))
+			memset(&key->enc_ipv6.src, 0xff,
+			       sizeof(struct in6_addr));
+		if (memcmp(&key->enc_ipv6.dst, &in6addr_any,
+			   sizeof(struct in6_addr)))
+			memset(&key->enc_ipv6.dst, 0xff,
+			       sizeof(struct in6_addr));
+		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS);
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+	}
+
+	match->dissector.used_keys |= enc_keys;
+}
+
+static int nf_flow_rule_match(struct nf_flow_match *match,
+			      const struct flow_offload_tuple *tuple,
+			      struct dst_entry *other_dst)
+{
+	struct nf_flow_key *mask = &match->mask;
+	struct nf_flow_key *key = &match->key;
+	struct ip_tunnel_info *tun_info;
+
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_META, meta);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp);
+
+	if (other_dst && other_dst->lwtstate) {
+		tun_info = lwt_tun_info(other_dst->lwtstate);
+		nf_flow_rule_lwt_match(match, tun_info);
+	}
+
+	key->meta.ingress_ifindex = tuple->iifidx;
+	mask->meta.ingress_ifindex = 0xffffffff;
+
+	switch (tuple->l3proto) {
+	case AF_INET:
+		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		key->basic.n_proto = htons(ETH_P_IP);
+		key->ipv4.src = tuple->src_v4.s_addr;
+		mask->ipv4.src = 0xffffffff;
+		key->ipv4.dst = tuple->dst_v4.s_addr;
+		mask->ipv4.dst = 0xffffffff;
+		break;
+       case AF_INET6:
+		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		key->basic.n_proto = htons(ETH_P_IPV6);
+		key->ipv6.src = tuple->src_v6;
+		memset(&mask->ipv6.src, 0xff, sizeof(mask->ipv6.src));
+		key->ipv6.dst = tuple->dst_v6;
+		memset(&mask->ipv6.dst, 0xff, sizeof(mask->ipv6.dst));
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	mask->control.addr_type = 0xffff;
+	match->dissector.used_keys |= BIT(key->control.addr_type);
+	mask->basic.n_proto = 0xffff;
+
+	switch (tuple->l4proto) {
+	case IPPROTO_TCP:
+		key->tcp.flags = 0;
+		mask->tcp.flags = cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16);
+		match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP);
+		break;
+	case IPPROTO_UDP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	key->basic.ip_proto = tuple->l4proto;
+	mask->basic.ip_proto = 0xff;
+
+	key->tp.src = tuple->src_port;
+	mask->tp.src = 0xffff;
+	key->tp.dst = tuple->dst_port;
+	mask->tp.dst = 0xffff;
+
+	match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_META) |
+				      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+				      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+				      BIT(FLOW_DISSECTOR_KEY_PORTS);
+	return 0;
+}
+
+static void flow_offload_mangle(struct flow_action_entry *entry,
+				enum flow_action_mangle_base htype, u32 offset,
+				const __be32 *value, const __be32 *mask)
+{
+	entry->id = FLOW_ACTION_MANGLE;
+	entry->mangle.htype = htype;
+	entry->mangle.offset = offset;
+	memcpy(&entry->mangle.mask, mask, sizeof(u32));
+	memcpy(&entry->mangle.val, value, sizeof(u32));
+}
+
+static inline struct flow_action_entry *
+flow_action_entry_next(struct nf_flow_rule *flow_rule)
+{
+	int i = flow_rule->rule->action.num_entries++;
+
+	return &flow_rule->rule->action.entries[i];
+}
+
+static int flow_offload_eth_src(struct net *net,
+				const struct flow_offload *flow,
+				enum flow_offload_tuple_dir dir,
+				struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule);
+	struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule);
+	const struct flow_offload_tuple *other_tuple, *this_tuple;
+	struct net_device *dev = NULL;
+	const unsigned char *addr;
+	u32 mask, val;
+	u16 val16;
+
+	this_tuple = &flow->tuplehash[dir].tuple;
+
+	switch (this_tuple->xmit_type) {
+	case FLOW_OFFLOAD_XMIT_DIRECT:
+		addr = this_tuple->out.h_source;
+		break;
+	case FLOW_OFFLOAD_XMIT_NEIGH:
+		other_tuple = &flow->tuplehash[!dir].tuple;
+		dev = dev_get_by_index(net, other_tuple->iifidx);
+		if (!dev)
+			return -ENOENT;
+
+		addr = dev->dev_addr;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	mask = ~0xffff0000;
+	memcpy(&val16, addr, 2);
+	val = val16 << 16;
+	flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4,
+			    &val, &mask);
+
+	mask = ~0xffffffff;
+	memcpy(&val, addr + 2, 4);
+	flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8,
+			    &val, &mask);
+
+	if (dev)
+		dev_put(dev);
+
+	return 0;
+}
+
+static int flow_offload_eth_dst(struct net *net,
+				const struct flow_offload *flow,
+				enum flow_offload_tuple_dir dir,
+				struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule);
+	struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule);
+	const struct flow_offload_tuple *other_tuple, *this_tuple;
+	const struct dst_entry *dst_cache;
+	unsigned char ha[ETH_ALEN];
+	struct neighbour *n;
+	const void *daddr;
+	u32 mask, val;
+	u8 nud_state;
+	u16 val16;
+
+	this_tuple = &flow->tuplehash[dir].tuple;
+
+	switch (this_tuple->xmit_type) {
+	case FLOW_OFFLOAD_XMIT_DIRECT:
+		ether_addr_copy(ha, this_tuple->out.h_dest);
+		break;
+	case FLOW_OFFLOAD_XMIT_NEIGH:
+		other_tuple = &flow->tuplehash[!dir].tuple;
+		daddr = &other_tuple->src_v4;
+		dst_cache = this_tuple->dst_cache;
+		n = dst_neigh_lookup(dst_cache, daddr);
+		if (!n)
+			return -ENOENT;
+
+		read_lock_bh(&n->lock);
+		nud_state = n->nud_state;
+		ether_addr_copy(ha, n->ha);
+		read_unlock_bh(&n->lock);
+		neigh_release(n);
+
+		if (!(nud_state & NUD_VALID))
+			return -ENOENT;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	mask = ~0xffffffff;
+	memcpy(&val, ha, 4);
+	flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0,
+			    &val, &mask);
+
+	mask = ~0x0000ffff;
+	memcpy(&val16, ha + 4, 2);
+	val = val16;
+	flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4,
+			    &val, &mask);
+
+	return 0;
+}
+
+static void flow_offload_ipv4_snat(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
+	u32 mask = ~htonl(0xffffffff);
+	__be32 addr;
+	u32 offset;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
+		offset = offsetof(struct iphdr, saddr);
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
+		offset = offsetof(struct iphdr, daddr);
+		break;
+	default:
+		return;
+	}
+
+	flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset,
+			    &addr, &mask);
+}
+
+static void flow_offload_ipv4_dnat(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
+	u32 mask = ~htonl(0xffffffff);
+	__be32 addr;
+	u32 offset;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
+		offset = offsetof(struct iphdr, daddr);
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
+		offset = offsetof(struct iphdr, saddr);
+		break;
+	default:
+		return;
+	}
+
+	flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset,
+			    &addr, &mask);
+}
+
+static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
+				     unsigned int offset,
+				     const __be32 *addr, const __be32 *mask)
+{
+	struct flow_action_entry *entry;
+	int i, j;
+
+	for (i = 0, j = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32), j++) {
+		entry = flow_action_entry_next(flow_rule);
+		flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
+				    offset + i, &addr[j], mask);
+	}
+}
+
+static void flow_offload_ipv6_snat(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	u32 mask = ~htonl(0xffffffff);
+	const __be32 *addr;
+	u32 offset;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr32;
+		offset = offsetof(struct ipv6hdr, saddr);
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr32;
+		offset = offsetof(struct ipv6hdr, daddr);
+		break;
+	default:
+		return;
+	}
+
+	flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
+}
+
+static void flow_offload_ipv6_dnat(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	u32 mask = ~htonl(0xffffffff);
+	const __be32 *addr;
+	u32 offset;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr32;
+		offset = offsetof(struct ipv6hdr, daddr);
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr32;
+		offset = offsetof(struct ipv6hdr, saddr);
+		break;
+	default:
+		return;
+	}
+
+	flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
+}
+
+static int flow_offload_l4proto(const struct flow_offload *flow)
+{
+	u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto;
+	u8 type = 0;
+
+	switch (protonum) {
+	case IPPROTO_TCP:
+		type = FLOW_ACT_MANGLE_HDR_TYPE_TCP;
+		break;
+	case IPPROTO_UDP:
+		type = FLOW_ACT_MANGLE_HDR_TYPE_UDP;
+		break;
+	default:
+		break;
+	}
+
+	return type;
+}
+
+static void flow_offload_port_snat(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
+	u32 mask, port;
+	u32 offset;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port);
+		offset = 0; /* offsetof(struct tcphdr, source); */
+		port = htonl(port << 16);
+		mask = ~htonl(0xffff0000);
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port);
+		offset = 0; /* offsetof(struct tcphdr, dest); */
+		port = htonl(port);
+		mask = ~htonl(0xffff);
+		break;
+	default:
+		return;
+	}
+
+	flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
+			    &port, &mask);
+}
+
+static void flow_offload_port_dnat(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
+	u32 mask, port;
+	u32 offset;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port);
+		offset = 0; /* offsetof(struct tcphdr, dest); */
+		port = htonl(port);
+		mask = ~htonl(0xffff);
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port);
+		offset = 0; /* offsetof(struct tcphdr, source); */
+		port = htonl(port << 16);
+		mask = ~htonl(0xffff0000);
+		break;
+	default:
+		return;
+	}
+
+	flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
+			    &port, &mask);
+}
+
+static void flow_offload_ipv4_checksum(struct net *net,
+				       const struct flow_offload *flow,
+				       struct nf_flow_rule *flow_rule)
+{
+	u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto;
+	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
+
+	entry->id = FLOW_ACTION_CSUM;
+	entry->csum_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR;
+
+	switch (protonum) {
+	case IPPROTO_TCP:
+		entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_TCP;
+		break;
+	case IPPROTO_UDP:
+		entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_UDP;
+		break;
+	}
+}
+
+static void flow_offload_redirect(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
+{
+	const struct flow_offload_tuple *this_tuple, *other_tuple;
+	struct flow_action_entry *entry;
+	struct net_device *dev;
+	int ifindex;
+
+	this_tuple = &flow->tuplehash[dir].tuple;
+	switch (this_tuple->xmit_type) {
+	case FLOW_OFFLOAD_XMIT_DIRECT:
+		this_tuple = &flow->tuplehash[dir].tuple;
+		ifindex = this_tuple->out.hw_ifidx;
+		break;
+	case FLOW_OFFLOAD_XMIT_NEIGH:
+		other_tuple = &flow->tuplehash[!dir].tuple;
+		ifindex = other_tuple->iifidx;
+		break;
+	default:
+		return;
+	}
+
+	dev = dev_get_by_index(net, ifindex);
+	if (!dev)
+		return;
+
+	entry = flow_action_entry_next(flow_rule);
+	entry->id = FLOW_ACTION_REDIRECT;
+	entry->dev = dev;
+}
+
+static void flow_offload_encap_tunnel(const struct flow_offload *flow,
+				      enum flow_offload_tuple_dir dir,
+				      struct nf_flow_rule *flow_rule)
+{
+	const struct flow_offload_tuple *this_tuple;
+	struct flow_action_entry *entry;
+	struct dst_entry *dst;
+
+	this_tuple = &flow->tuplehash[dir].tuple;
+	if (this_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT)
+		return;
+
+	dst = this_tuple->dst_cache;
+	if (dst && dst->lwtstate) {
+		struct ip_tunnel_info *tun_info;
+
+		tun_info = lwt_tun_info(dst->lwtstate);
+		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
+			entry = flow_action_entry_next(flow_rule);
+			entry->id = FLOW_ACTION_TUNNEL_ENCAP;
+			entry->tunnel = tun_info;
+		}
+	}
+}
+
+static void flow_offload_decap_tunnel(const struct flow_offload *flow,
+				      enum flow_offload_tuple_dir dir,
+				      struct nf_flow_rule *flow_rule)
+{
+	const struct flow_offload_tuple *other_tuple;
+	struct flow_action_entry *entry;
+	struct dst_entry *dst;
+
+	other_tuple = &flow->tuplehash[!dir].tuple;
+	if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT)
+		return;
+
+	dst = other_tuple->dst_cache;
+	if (dst && dst->lwtstate) {
+		struct ip_tunnel_info *tun_info;
+
+		tun_info = lwt_tun_info(dst->lwtstate);
+		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
+			entry = flow_action_entry_next(flow_rule);
+			entry->id = FLOW_ACTION_TUNNEL_DECAP;
+		}
+	}
+}
+
+static int
+nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow,
+			  enum flow_offload_tuple_dir dir,
+			  struct nf_flow_rule *flow_rule)
+{
+	const struct flow_offload_tuple *other_tuple;
+	int i;
+
+	flow_offload_decap_tunnel(flow, dir, flow_rule);
+	flow_offload_encap_tunnel(flow, dir, flow_rule);
+
+	if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 ||
+	    flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
+		return -1;
+
+	other_tuple = &flow->tuplehash[!dir].tuple;
+
+	for (i = 0; i < other_tuple->encap_num; i++) {
+		struct flow_action_entry *entry;
+
+		if (other_tuple->in_vlan_ingress & BIT(i))
+			continue;
+
+		entry = flow_action_entry_next(flow_rule);
+
+		switch (other_tuple->encap[i].proto) {
+		case htons(ETH_P_PPP_SES):
+			entry->id = FLOW_ACTION_PPPOE_PUSH;
+			entry->pppoe.sid = other_tuple->encap[i].id;
+			break;
+		case htons(ETH_P_8021Q):
+			entry->id = FLOW_ACTION_VLAN_PUSH;
+			entry->vlan.vid = other_tuple->encap[i].id;
+			entry->vlan.proto = other_tuple->encap[i].proto;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow,
+			    enum flow_offload_tuple_dir dir,
+			    struct nf_flow_rule *flow_rule)
+{
+	if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0)
+		return -1;
+
+	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
+		flow_offload_ipv4_snat(net, flow, dir, flow_rule);
+		flow_offload_port_snat(net, flow, dir, flow_rule);
+	}
+	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
+		flow_offload_ipv4_dnat(net, flow, dir, flow_rule);
+		flow_offload_port_dnat(net, flow, dir, flow_rule);
+	}
+	if (test_bit(NF_FLOW_SNAT, &flow->flags) ||
+	    test_bit(NF_FLOW_DNAT, &flow->flags))
+		flow_offload_ipv4_checksum(net, flow, flow_rule);
+
+	flow_offload_redirect(net, flow, dir, flow_rule);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv4);
+
+int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow,
+			    enum flow_offload_tuple_dir dir,
+			    struct nf_flow_rule *flow_rule)
+{
+	if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0)
+		return -1;
+
+	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
+		flow_offload_ipv6_snat(net, flow, dir, flow_rule);
+		flow_offload_port_snat(net, flow, dir, flow_rule);
+	}
+	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
+		flow_offload_ipv6_dnat(net, flow, dir, flow_rule);
+		flow_offload_port_dnat(net, flow, dir, flow_rule);
+	}
+
+	flow_offload_redirect(net, flow, dir, flow_rule);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv6);
+
+#define NF_FLOW_RULE_ACTION_MAX	16
+
+static struct nf_flow_rule *
+nf_flow_offload_rule_alloc(struct net *net,
+			   const struct flow_offload_work *offload,
+			   enum flow_offload_tuple_dir dir)
+{
+	const struct nf_flowtable *flowtable = offload->flowtable;
+	const struct flow_offload_tuple *tuple, *other_tuple;
+	const struct flow_offload *flow = offload->flow;
+	struct dst_entry *other_dst = NULL;
+	struct nf_flow_rule *flow_rule;
+	int err = -ENOMEM;
+
+	flow_rule = kzalloc(sizeof(*flow_rule), GFP_KERNEL);
+	if (!flow_rule)
+		goto err_flow;
+
+	flow_rule->rule = flow_rule_alloc(NF_FLOW_RULE_ACTION_MAX);
+	if (!flow_rule->rule)
+		goto err_flow_rule;
+
+	flow_rule->rule->match.dissector = &flow_rule->match.dissector;
+	flow_rule->rule->match.mask = &flow_rule->match.mask;
+	flow_rule->rule->match.key = &flow_rule->match.key;
+
+	tuple = &flow->tuplehash[dir].tuple;
+	other_tuple = &flow->tuplehash[!dir].tuple;
+	if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH)
+		other_dst = other_tuple->dst_cache;
+
+	err = nf_flow_rule_match(&flow_rule->match, tuple, other_dst);
+	if (err < 0)
+		goto err_flow_match;
+
+	flow_rule->rule->action.num_entries = 0;
+	if (flowtable->type->action(net, flow, dir, flow_rule) < 0)
+		goto err_flow_match;
+
+	return flow_rule;
+
+err_flow_match:
+	kfree(flow_rule->rule);
+err_flow_rule:
+	kfree(flow_rule);
+err_flow:
+	return NULL;
+}
+
+static void __nf_flow_offload_destroy(struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry;
+	int i;
+
+	for (i = 0; i < flow_rule->rule->action.num_entries; i++) {
+		entry = &flow_rule->rule->action.entries[i];
+		if (entry->id != FLOW_ACTION_REDIRECT)
+			continue;
+
+		dev_put(entry->dev);
+	}
+	kfree(flow_rule->rule);
+	kfree(flow_rule);
+}
+
+static void nf_flow_offload_destroy(struct nf_flow_rule *flow_rule[])
+{
+	int i;
+
+	for (i = 0; i < FLOW_OFFLOAD_DIR_MAX; i++)
+		__nf_flow_offload_destroy(flow_rule[i]);
+}
+
+static int nf_flow_offload_alloc(const struct flow_offload_work *offload,
+				 struct nf_flow_rule *flow_rule[])
+{
+	struct net *net = read_pnet(&offload->flowtable->net);
+
+	flow_rule[0] = nf_flow_offload_rule_alloc(net, offload,
+						  FLOW_OFFLOAD_DIR_ORIGINAL);
+	if (!flow_rule[0])
+		return -ENOMEM;
+
+	flow_rule[1] = nf_flow_offload_rule_alloc(net, offload,
+						  FLOW_OFFLOAD_DIR_REPLY);
+	if (!flow_rule[1]) {
+		__nf_flow_offload_destroy(flow_rule[0]);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nf_flow_offload_init(struct flow_cls_offload *cls_flow,
+				 __be16 proto, int priority,
+				 enum flow_cls_command cmd,
+				 const struct flow_offload_tuple *tuple,
+				 struct netlink_ext_ack *extack)
+{
+	cls_flow->common.protocol = proto;
+	cls_flow->common.prio = priority;
+	cls_flow->common.extack = extack;
+	cls_flow->command = cmd;
+	cls_flow->cookie = (unsigned long)tuple;
+}
+
+static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
+				 struct flow_offload *flow,
+				 struct nf_flow_rule *flow_rule,
+				 enum flow_offload_tuple_dir dir,
+				 int priority, int cmd,
+				 struct flow_stats *stats,
+				 struct list_head *block_cb_list)
+{
+	struct flow_cls_offload cls_flow = {};
+	struct flow_block_cb *block_cb;
+	struct netlink_ext_ack extack;
+	__be16 proto = ETH_P_ALL;
+	int err, i = 0;
+
+	nf_flow_offload_init(&cls_flow, proto, priority, cmd,
+			     &flow->tuplehash[dir].tuple, &extack);
+	if (cmd == FLOW_CLS_REPLACE)
+		cls_flow.rule = flow_rule->rule;
+
+	down_read(&flowtable->flow_block_lock);
+	list_for_each_entry(block_cb, block_cb_list, list) {
+		err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow,
+				   block_cb->cb_priv);
+		if (err < 0)
+			continue;
+
+		i++;
+	}
+	up_read(&flowtable->flow_block_lock);
+
+	if (cmd == FLOW_CLS_STATS)
+		memcpy(stats, &cls_flow.stats, sizeof(*stats));
+
+	return i;
+}
+
+static int flow_offload_tuple_add(struct flow_offload_work *offload,
+				  struct nf_flow_rule *flow_rule,
+				  enum flow_offload_tuple_dir dir)
+{
+	return nf_flow_offload_tuple(offload->flowtable, offload->flow,
+				     flow_rule, dir, offload->priority,
+				     FLOW_CLS_REPLACE, NULL,
+				     &offload->flowtable->flow_block.cb_list);
+}
+
+static void flow_offload_tuple_del(struct flow_offload_work *offload,
+				   enum flow_offload_tuple_dir dir)
+{
+	nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir,
+			      offload->priority, FLOW_CLS_DESTROY, NULL,
+			      &offload->flowtable->flow_block.cb_list);
+}
+
+static int flow_offload_rule_add(struct flow_offload_work *offload,
+				 struct nf_flow_rule *flow_rule[])
+{
+	int ok_count = 0;
+
+	ok_count += flow_offload_tuple_add(offload, flow_rule[0],
+					   FLOW_OFFLOAD_DIR_ORIGINAL);
+	ok_count += flow_offload_tuple_add(offload, flow_rule[1],
+					   FLOW_OFFLOAD_DIR_REPLY);
+	if (ok_count == 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+static void flow_offload_work_add(struct flow_offload_work *offload)
+{
+	struct nf_flow_rule *flow_rule[FLOW_OFFLOAD_DIR_MAX];
+	int err;
+
+	err = nf_flow_offload_alloc(offload, flow_rule);
+	if (err < 0)
+		return;
+
+	err = flow_offload_rule_add(offload, flow_rule);
+	if (err < 0)
+		goto out;
+
+	set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
+
+out:
+	nf_flow_offload_destroy(flow_rule);
+}
+
+static void flow_offload_work_del(struct flow_offload_work *offload)
+{
+	clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
+	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL);
+	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY);
+	set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags);
+}
+
+static void flow_offload_tuple_stats(struct flow_offload_work *offload,
+				     enum flow_offload_tuple_dir dir,
+				     struct flow_stats *stats)
+{
+	nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir,
+			      offload->priority, FLOW_CLS_STATS, stats,
+			      &offload->flowtable->flow_block.cb_list);
+}
+
+static void flow_offload_work_stats(struct flow_offload_work *offload)
+{
+	struct flow_stats stats[FLOW_OFFLOAD_DIR_MAX] = {};
+	u64 lastused;
+
+	flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]);
+	flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]);
+
+	lastused = max_t(u64, stats[0].lastused, stats[1].lastused);
+	offload->flow->timeout = max_t(u64, offload->flow->timeout,
+				       lastused + flow_offload_get_timeout(offload->flow));
+
+	if (offload->flowtable->flags & NF_FLOWTABLE_COUNTER) {
+		if (stats[0].pkts)
+			nf_ct_acct_add(offload->flow->ct,
+				       FLOW_OFFLOAD_DIR_ORIGINAL,
+				       stats[0].pkts, stats[0].bytes);
+		if (stats[1].pkts)
+			nf_ct_acct_add(offload->flow->ct,
+				       FLOW_OFFLOAD_DIR_REPLY,
+				       stats[1].pkts, stats[1].bytes);
+	}
+}
+
+static void flow_offload_work_handler(struct work_struct *work)
+{
+	struct flow_offload_work *offload;
+
+	offload = container_of(work, struct flow_offload_work, work);
+	switch (offload->cmd) {
+		case FLOW_CLS_REPLACE:
+			flow_offload_work_add(offload);
+			break;
+		case FLOW_CLS_DESTROY:
+			flow_offload_work_del(offload);
+			break;
+		case FLOW_CLS_STATS:
+			flow_offload_work_stats(offload);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+	}
+
+	clear_bit(NF_FLOW_HW_PENDING, &offload->flow->flags);
+	kfree(offload);
+}
+
+static void flow_offload_queue_work(struct flow_offload_work *offload)
+{
+	if (offload->cmd == FLOW_CLS_REPLACE)
+		queue_work(nf_flow_offload_add_wq, &offload->work);
+	else if (offload->cmd == FLOW_CLS_DESTROY)
+		queue_work(nf_flow_offload_del_wq, &offload->work);
+	else
+		queue_work(nf_flow_offload_stats_wq, &offload->work);
+}
+
+static struct flow_offload_work *
+nf_flow_offload_work_alloc(struct nf_flowtable *flowtable,
+			   struct flow_offload *flow, unsigned int cmd)
+{
+	struct flow_offload_work *offload;
+
+	if (test_and_set_bit(NF_FLOW_HW_PENDING, &flow->flags))
+		return NULL;
+
+	offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC);
+	if (!offload) {
+		clear_bit(NF_FLOW_HW_PENDING, &flow->flags);
+		return NULL;
+	}
+
+	offload->cmd = cmd;
+	offload->flow = flow;
+	offload->priority = flowtable->priority;
+	offload->flowtable = flowtable;
+	INIT_WORK(&offload->work, flow_offload_work_handler);
+
+	return offload;
+}
+
+
+void nf_flow_offload_add(struct nf_flowtable *flowtable,
+			 struct flow_offload *flow)
+{
+	struct flow_offload_work *offload;
+
+	offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_REPLACE);
+	if (!offload)
+		return;
+
+	flow_offload_queue_work(offload);
+}
+
+void nf_flow_offload_del(struct nf_flowtable *flowtable,
+			 struct flow_offload *flow)
+{
+	struct flow_offload_work *offload;
+
+	offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_DESTROY);
+	if (!offload)
+		return;
+
+	set_bit(NF_FLOW_HW_DYING, &flow->flags);
+	flow_offload_queue_work(offload);
+}
+
+void nf_flow_offload_stats(struct nf_flowtable *flowtable,
+			   struct flow_offload *flow)
+{
+	struct flow_offload_work *offload;
+	__s32 delta;
+
+	delta = nf_flow_timeout_delta(flow->timeout);
+	if ((delta >= (9 * flow_offload_get_timeout(flow)) / 10))
+		return;
+
+	offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS);
+	if (!offload)
+		return;
+
+	flow_offload_queue_work(offload);
+}
+
+void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
+{
+	if (nf_flowtable_hw_offload(flowtable)) {
+		flush_workqueue(nf_flow_offload_add_wq);
+		flush_workqueue(nf_flow_offload_del_wq);
+		flush_workqueue(nf_flow_offload_stats_wq);
+	}
+}
+
+static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
+				     struct flow_block_offload *bo,
+				     enum flow_block_command cmd)
+{
+	struct flow_block_cb *block_cb, *next;
+	int err = 0;
+
+	switch (cmd) {
+	case FLOW_BLOCK_BIND:
+		list_splice(&bo->cb_list, &flowtable->flow_block.cb_list);
+		break;
+	case FLOW_BLOCK_UNBIND:
+		list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) {
+			list_del(&block_cb->list);
+			flow_block_cb_free(block_cb);
+		}
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static void nf_flow_table_block_offload_init(struct flow_block_offload *bo,
+					     struct net *net,
+					     enum flow_block_command cmd,
+					     struct nf_flowtable *flowtable,
+					     struct netlink_ext_ack *extack)
+{
+	memset(bo, 0, sizeof(*bo));
+	bo->net		= net;
+	bo->block	= &flowtable->flow_block;
+	bo->command	= cmd;
+	bo->binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	bo->extack	= extack;
+	INIT_LIST_HEAD(&bo->cb_list);
+}
+
+static void nf_flow_table_indr_cleanup(struct flow_block_cb *block_cb)
+{
+	struct nf_flowtable *flowtable = block_cb->indr.data;
+	struct net_device *dev = block_cb->indr.dev;
+
+	nf_flow_table_gc_cleanup(flowtable, dev);
+	down_write(&flowtable->flow_block_lock);
+	list_del(&block_cb->list);
+	list_del(&block_cb->driver_list);
+	flow_block_cb_free(block_cb);
+	up_write(&flowtable->flow_block_lock);
+}
+
+/* Skip backporting this API to prevent excessive framework changes.
+static int nf_flow_table_indr_offload_cmd(struct flow_block_offload *bo,
+					  struct nf_flowtable *flowtable,
+					  struct net_device *dev,
+					  enum flow_block_command cmd,
+					  struct netlink_ext_ack *extack)
+{
+	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
+					 extack);
+
+	return flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_FT, flowtable, bo,
+					   nf_flow_table_indr_cleanup);
+}
+*/
+
+static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
+				     struct nf_flowtable *flowtable,
+				     struct net_device *dev,
+				     enum flow_block_command cmd,
+				     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
+					 extack);
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
+				struct net_device *dev,
+				enum flow_block_command cmd)
+{
+	struct netlink_ext_ack extack = {};
+	struct flow_block_offload bo;
+	int err;
+
+	if (!nf_flowtable_hw_offload(flowtable))
+		return 0;
+
+	if (dev->netdev_ops->ndo_setup_tc)
+		err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd,
+						&extack);
+/* Skip backporting
+	else
+		err = nf_flow_table_indr_offload_cmd(&bo, flowtable, dev, cmd,
+						     &extack);
+*/
+
+	if (err < 0)
+		return err;
+
+	return nf_flow_table_block_setup(flowtable, &bo, cmd);
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup);
+
+int nf_flow_table_offload_init(void)
+{
+	nf_flow_offload_add_wq  = alloc_workqueue("nf_ft_offload_add",
+						  WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!nf_flow_offload_add_wq)
+		return -ENOMEM;
+
+	nf_flow_offload_del_wq  = alloc_workqueue("nf_ft_offload_del",
+						  WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!nf_flow_offload_del_wq)
+		goto err_del_wq;
+
+	nf_flow_offload_stats_wq  = alloc_workqueue("nf_ft_offload_stats",
+						    WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!nf_flow_offload_stats_wq)
+		goto err_stats_wq;
+
+	return 0;
+
+err_stats_wq:
+	destroy_workqueue(nf_flow_offload_del_wq);
+err_del_wq:
+	destroy_workqueue(nf_flow_offload_add_wq);
+	return -ENOMEM;
+}
+
+void nf_flow_table_offload_exit(void)
+{
+	destroy_workqueue(nf_flow_offload_add_wq);
+	destroy_workqueue(nf_flow_offload_del_wq);
+	destroy_workqueue(nf_flow_offload_stats_wq);
+}
diff --git a/net/netfilter/xt_FLOWOFFLOAD.c b/net/netfilter/xt_FLOWOFFLOAD.c
new file mode 100644
index 00000000..396baed4
--- /dev/null
+++ b/net/netfilter/xt_FLOWOFFLOAD.c
@@ -0,0 +1,658 @@
+/*
+ * Copyright (C) 2018-2021 Felix Fietkau <nbd@nbd.name>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/xt_FLOWOFFLOAD.h>
+#include <net/ip.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_flow_table.h>
+
+struct xt_flowoffload_hook {
+	struct hlist_node list;
+	struct nf_hook_ops ops;
+	struct net *net;
+	bool registered;
+	bool used;
+};
+
+struct xt_flowoffload_table {
+	struct nf_flowtable ft;
+	struct hlist_head hooks;
+	struct delayed_work work;
+};
+
+static DEFINE_SPINLOCK(hooks_lock);
+
+struct xt_flowoffload_table flowtable[2];
+
+static unsigned int
+xt_flowoffload_net_hook(void *priv, struct sk_buff *skb,
+			const struct nf_hook_state *state)
+{
+	struct nf_flowtable *ft = priv;
+
+	if (!atomic_read(&ft->rhashtable.nelems))
+		return NF_ACCEPT;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return nf_flow_offload_ip_hook(priv, skb, state);
+	case htons(ETH_P_IPV6):
+		return nf_flow_offload_ipv6_hook(priv, skb, state);
+	}
+
+	return NF_ACCEPT;
+}
+
+static int
+xt_flowoffload_create_hook(struct xt_flowoffload_table *table,
+			   struct net_device *dev)
+{
+	struct xt_flowoffload_hook *hook;
+	struct nf_hook_ops *ops;
+
+	hook = kzalloc(sizeof(*hook), GFP_ATOMIC);
+	if (!hook)
+		return -ENOMEM;
+
+	ops = &hook->ops;
+	ops->pf = NFPROTO_NETDEV;
+	ops->hooknum = NF_NETDEV_INGRESS;
+	ops->priority = 10;
+	ops->priv = &table->ft;
+	ops->hook = xt_flowoffload_net_hook;
+	ops->dev = dev;
+
+	hlist_add_head(&hook->list, &table->hooks);
+	mod_delayed_work(system_power_efficient_wq, &table->work, 0);
+
+	return 0;
+}
+
+static struct xt_flowoffload_hook *
+flow_offload_lookup_hook(struct xt_flowoffload_table *table,
+			 struct net_device *dev)
+{
+	struct xt_flowoffload_hook *hook;
+
+	hlist_for_each_entry(hook, &table->hooks, list) {
+		if (hook->ops.dev == dev)
+			return hook;
+	}
+
+	return NULL;
+}
+
+static void
+xt_flowoffload_check_device(struct xt_flowoffload_table *table,
+			    struct net_device *dev)
+{
+	struct xt_flowoffload_hook *hook;
+
+	if (!dev)
+		return;
+
+	spin_lock_bh(&hooks_lock);
+	hook = flow_offload_lookup_hook(table, dev);
+	if (hook)
+		hook->used = true;
+	else
+		xt_flowoffload_create_hook(table, dev);
+	spin_unlock_bh(&hooks_lock);
+}
+
+static void
+xt_flowoffload_register_hooks(struct xt_flowoffload_table *table)
+{
+	struct xt_flowoffload_hook *hook;
+
+restart:
+	hlist_for_each_entry(hook, &table->hooks, list) {
+		if (hook->registered)
+			continue;
+
+		hook->registered = true;
+		hook->net = dev_net(hook->ops.dev);
+		spin_unlock_bh(&hooks_lock);
+		nf_register_net_hook(hook->net, &hook->ops);
+		if (table->ft.flags & NF_FLOWTABLE_HW_OFFLOAD)
+			table->ft.type->setup(&table->ft, hook->ops.dev,
+					      FLOW_BLOCK_BIND);
+		spin_lock_bh(&hooks_lock);
+		goto restart;
+	}
+
+}
+
+static bool
+xt_flowoffload_cleanup_hooks(struct xt_flowoffload_table *table)
+{
+	struct xt_flowoffload_hook *hook;
+	bool active = false;
+
+restart:
+	spin_lock_bh(&hooks_lock);
+	hlist_for_each_entry(hook, &table->hooks, list) {
+		if (hook->used || !hook->registered) {
+			active = true;
+			continue;
+		}
+
+		hlist_del(&hook->list);
+		spin_unlock_bh(&hooks_lock);
+		if (table->ft.flags & NF_FLOWTABLE_HW_OFFLOAD)
+			table->ft.type->setup(&table->ft, hook->ops.dev,
+					      FLOW_BLOCK_UNBIND);
+		nf_unregister_net_hook(hook->net, &hook->ops);
+		kfree(hook);
+		goto restart;
+	}
+	spin_unlock_bh(&hooks_lock);
+
+	return active;
+}
+
+static void
+xt_flowoffload_check_hook(struct flow_offload *flow, void *data)
+{
+	struct xt_flowoffload_table *table = data;
+	struct flow_offload_tuple *tuple0 = &flow->tuplehash[0].tuple;
+	struct flow_offload_tuple *tuple1 = &flow->tuplehash[1].tuple;
+	struct xt_flowoffload_hook *hook;
+
+	spin_lock_bh(&hooks_lock);
+	hlist_for_each_entry(hook, &table->hooks, list) {
+		if (hook->ops.dev->ifindex != tuple0->iifidx &&
+		    hook->ops.dev->ifindex != tuple1->iifidx)
+			continue;
+
+		hook->used = true;
+	}
+	spin_unlock_bh(&hooks_lock);
+
+	cond_resched();
+}
+
+static void
+xt_flowoffload_hook_work(struct work_struct *work)
+{
+	struct xt_flowoffload_table *table;
+	struct xt_flowoffload_hook *hook;
+	int err;
+
+	table = container_of(work, struct xt_flowoffload_table, work.work);
+
+	spin_lock_bh(&hooks_lock);
+	xt_flowoffload_register_hooks(table);
+	hlist_for_each_entry(hook, &table->hooks, list)
+		hook->used = false;
+	spin_unlock_bh(&hooks_lock);
+
+	err = nf_flow_table_iterate(&table->ft, xt_flowoffload_check_hook,
+				    table);
+	if (err && err != -EAGAIN)
+		goto out;
+
+	if (!xt_flowoffload_cleanup_hooks(table))
+		return;
+
+out:
+	queue_delayed_work(system_power_efficient_wq, &table->work, HZ);
+}
+
+static bool
+xt_flowoffload_skip(struct sk_buff *skb, int family)
+{
+	if (skb_sec_path(skb))
+		return true;
+
+	if (family == NFPROTO_IPV4) {
+		const struct ip_options *opt = &(IPCB(skb)->opt);
+
+		if (unlikely(opt->optlen))
+			return true;
+	}
+
+	return false;
+}
+
+static bool flow_is_valid_ether_device(const struct net_device *dev)
+{
+	if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER ||
+	    dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr))
+		return false;
+
+	return true;
+}
+
+static void
+xt_flowoffload_route_check_path(struct nf_flow_route *route,
+				const struct nf_conn *ct,
+				enum ip_conntrack_dir dir,
+				struct net_device **out_dev)
+{
+	const struct dst_entry *dst = route->tuple[dir].dst;
+	const void *daddr = &ct->tuplehash[!dir].tuple.src.u3;
+	struct net_device_path_stack stack;
+	enum net_device_path_type prev_type;
+	struct net_device *dev = dst->dev;
+	struct neighbour *n;
+	bool last = false;
+	u8 nud_state;
+	int i;
+
+	route->tuple[!dir].in.ifindex = dev->ifindex;
+	route->tuple[dir].out.ifindex = dev->ifindex;
+
+	if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_XFRM)
+		return;
+
+	if ((dev->flags & IFF_LOOPBACK) ||
+	    dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN ||
+	    !is_valid_ether_addr(dev->dev_addr))
+		return;
+
+	n = dst_neigh_lookup(dst, daddr);
+	if (!n)
+		return;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	memcpy(route->tuple[dir].out.h_dest, n->ha, ETH_ALEN);
+	read_unlock_bh(&n->lock);
+	neigh_release(n);
+
+	if (!(nud_state & NUD_VALID))
+		return;
+
+	if (dev_fill_forward_path(dev, route->tuple[dir].out.h_dest, &stack) ||
+	    !stack.num_paths)
+		return;
+
+	prev_type = DEV_PATH_ETHERNET;
+	for (i = 0; i <= stack.num_paths; i++) {
+		const struct net_device_path *path = &stack.path[i];
+		int n_encaps = route->tuple[!dir].in.num_encaps;
+
+		dev = (struct net_device *)path->dev;
+		if (flow_is_valid_ether_device(dev)) {
+			if (route->tuple[dir].xmit_type != FLOW_OFFLOAD_XMIT_DIRECT) {
+				memcpy(route->tuple[dir].out.h_source,
+				       dev->dev_addr, ETH_ALEN);
+				route->tuple[dir].out.ifindex = dev->ifindex;
+			}
+			route->tuple[dir].xmit_type = FLOW_OFFLOAD_XMIT_DIRECT;
+		}
+
+		switch (path->type) {
+		case DEV_PATH_PPPOE:
+		case DEV_PATH_VLAN:
+			if (n_encaps >= NF_FLOW_TABLE_ENCAP_MAX ||
+			    i == stack.num_paths) {
+				last = true;
+				break;
+			}
+
+			route->tuple[!dir].in.num_encaps++;
+			route->tuple[!dir].in.encap[n_encaps].id = path->encap.id;
+			route->tuple[!dir].in.encap[n_encaps].proto = path->encap.proto;
+			if (path->type == DEV_PATH_PPPOE)
+				memcpy(route->tuple[dir].out.h_dest,
+				       path->encap.h_dest, ETH_ALEN);
+			break;
+		case DEV_PATH_BRIDGE:
+			switch (path->bridge.vlan_mode) {
+			case DEV_PATH_BR_VLAN_TAG:
+				if (n_encaps >= NF_FLOW_TABLE_ENCAP_MAX ||
+				    i == stack.num_paths) {
+					last = true;
+					break;
+				}
+
+				route->tuple[!dir].in.num_encaps++;
+				route->tuple[!dir].in.encap[n_encaps].id =
+					path->bridge.vlan_id;
+				route->tuple[!dir].in.encap[n_encaps].proto =
+					path->bridge.vlan_proto;
+				break;
+			case DEV_PATH_BR_VLAN_UNTAG:
+				route->tuple[!dir].in.num_encaps--;
+				break;
+			case DEV_PATH_BR_VLAN_UNTAG_HW:
+				route->tuple[!dir].in.ingress_vlans |= BIT(n_encaps - 1);
+				break;
+			case DEV_PATH_BR_VLAN_KEEP:
+				break;
+			}
+			break;
+		default:
+			last = true;
+			break;
+		}
+
+		if (last)
+			break;
+	}
+
+	*out_dev = dev;
+	route->tuple[dir].out.hw_ifindex = dev->ifindex;
+	route->tuple[!dir].in.ifindex = dev->ifindex;
+}
+
+static int
+xt_flowoffload_route_dir(struct nf_flow_route *route, const struct nf_conn *ct,
+			 enum ip_conntrack_dir dir,
+			 const struct xt_action_param *par, int ifindex)
+{
+	struct dst_entry *dst = NULL;
+	struct flowi fl;
+
+	memset(&fl, 0, sizeof(fl));
+	switch (xt_family(par)) {
+	case NFPROTO_IPV4:
+		fl.u.ip4.daddr = ct->tuplehash[!dir].tuple.src.u3.ip;
+		fl.u.ip4.flowi4_oif = ifindex;
+		break;
+	case NFPROTO_IPV6:
+		fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.dst.u3.in6;
+		fl.u.ip6.daddr = ct->tuplehash[!dir].tuple.src.u3.in6;
+		fl.u.ip6.flowi6_oif = ifindex;
+		break;
+	}
+
+	nf_route(xt_net(par), &dst, &fl, false, xt_family(par));
+	if (!dst)
+		return -ENOENT;
+
+	route->tuple[dir].dst = dst;
+	if (dst_xfrm(dst))
+		route->tuple[dir].xmit_type = FLOW_OFFLOAD_XMIT_XFRM;
+	else
+		route->tuple[dir].xmit_type = FLOW_OFFLOAD_XMIT_NEIGH;
+
+	return 0;
+}
+
+static int
+xt_flowoffload_route(struct sk_buff *skb, const struct nf_conn *ct,
+		     const struct xt_action_param *par,
+		     struct nf_flow_route *route, enum ip_conntrack_dir dir,
+		     struct net_device **dev)
+{
+	int ret;
+
+	ret = xt_flowoffload_route_dir(route, ct, dir, par,
+				       dev[dir]->ifindex);
+	if (ret)
+		return ret;
+
+	ret = xt_flowoffload_route_dir(route, ct, !dir, par,
+				       dev[!dir]->ifindex);
+	if (ret)
+		return ret;
+
+	xt_flowoffload_route_check_path(route, ct, dir, &dev[!dir]);
+	xt_flowoffload_route_check_path(route, ct, !dir, &dev[dir]);
+
+	return 0;
+}
+
+static unsigned int
+flowoffload_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	struct xt_flowoffload_table *table;
+	const struct xt_flowoffload_target_info *info = par->targinfo;
+	struct tcphdr _tcph, *tcph = NULL;
+	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_dir dir;
+	struct nf_flow_route route = {};
+	struct flow_offload *flow = NULL;
+	struct net_device *devs[2] = {};
+	struct nf_conn *ct;
+	struct net *net;
+
+	if (xt_flowoffload_skip(skb, xt_family(par)))
+		return XT_CONTINUE;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct == NULL)
+		return XT_CONTINUE;
+
+	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
+	case IPPROTO_TCP:
+		if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
+			return XT_CONTINUE;
+
+		tcph = skb_header_pointer(skb, par->thoff,
+					  sizeof(_tcph), &_tcph);
+		if (unlikely(!tcph || tcph->fin || tcph->rst))
+			return XT_CONTINUE;
+		break;
+	case IPPROTO_UDP:
+		break;
+	default:
+		return XT_CONTINUE;
+	}
+
+	if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
+	    ct->status & IPS_SEQ_ADJUST)
+		return XT_CONTINUE;
+
+	if (!nf_ct_is_confirmed(ct))
+		return XT_CONTINUE;
+
+	devs[dir] = xt_out(par);
+	devs[!dir] = xt_in(par);
+
+	if (!devs[dir] || !devs[!dir])
+		return XT_CONTINUE;
+
+	if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
+		return XT_CONTINUE;
+
+	dir = CTINFO2DIR(ctinfo);
+
+	if (xt_flowoffload_route(skb, ct, par, &route, dir, devs) < 0)
+		goto err_flow_route;
+
+	flow = flow_offload_alloc(ct);
+	if (!flow)
+		goto err_flow_alloc;
+
+	if (flow_offload_route_init(flow, &route) < 0)
+		goto err_flow_add;
+
+	if (tcph) {
+		ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+	}
+
+	table = &flowtable[!!(info->flags & XT_FLOWOFFLOAD_HW)];
+	if (flow_offload_add(&table->ft, flow) < 0)
+		goto err_flow_add;
+
+	xt_flowoffload_check_device(table, devs[0]);
+	xt_flowoffload_check_device(table, devs[1]);
+
+	net = read_pnet(&table->ft.net);
+	if (!net)
+		write_pnet(&table->ft.net, xt_net(par));
+
+	dst_release(route.tuple[dir].dst);
+	dst_release(route.tuple[!dir].dst);
+
+	return XT_CONTINUE;
+
+err_flow_add:
+	flow_offload_free(flow);
+err_flow_alloc:
+	dst_release(route.tuple[dir].dst);
+	dst_release(route.tuple[!dir].dst);
+err_flow_route:
+	clear_bit(IPS_OFFLOAD_BIT, &ct->status);
+
+	return XT_CONTINUE;
+}
+
+static int flowoffload_chk(const struct xt_tgchk_param *par)
+{
+	struct xt_flowoffload_target_info *info = par->targinfo;
+
+	if (info->flags & ~XT_FLOWOFFLOAD_MASK)
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct xt_target offload_tg_reg __read_mostly = {
+	.family		= NFPROTO_UNSPEC,
+	.name		= "FLOWOFFLOAD",
+	.revision	= 0,
+	.targetsize	= sizeof(struct xt_flowoffload_target_info),
+	.usersize	= sizeof(struct xt_flowoffload_target_info),
+	.checkentry	= flowoffload_chk,
+	.target		= flowoffload_tg,
+	.me		= THIS_MODULE,
+};
+
+static int flow_offload_netdev_event(struct notifier_block *this,
+				     unsigned long event, void *ptr)
+{
+	struct xt_flowoffload_hook *hook0, *hook1;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (event != NETDEV_UNREGISTER)
+		return NOTIFY_DONE;
+
+	spin_lock_bh(&hooks_lock);
+	hook0 = flow_offload_lookup_hook(&flowtable[0], dev);
+	if (hook0)
+		hlist_del(&hook0->list);
+
+	hook1 = flow_offload_lookup_hook(&flowtable[1], dev);
+	if (hook1)
+		hlist_del(&hook1->list);
+	spin_unlock_bh(&hooks_lock);
+
+	if (hook0) {
+		nf_unregister_net_hook(hook0->net, &hook0->ops);
+		kfree(hook0);
+	}
+
+	if (hook1) {
+		nf_unregister_net_hook(hook1->net, &hook1->ops);
+		kfree(hook1);
+	}
+
+	nf_flow_table_cleanup(dev);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block flow_offload_netdev_notifier = {
+	.notifier_call	= flow_offload_netdev_event,
+};
+
+static unsigned int
+nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
+			  const struct nf_hook_state *state)
+{
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return nf_flow_offload_ip_hook(priv, skb, state);
+	case htons(ETH_P_IPV6):
+		return nf_flow_offload_ipv6_hook(priv, skb, state);
+	}
+
+	return NF_ACCEPT;
+}
+
+static int nf_flow_rule_route_inet(struct net *net,
+				   const struct flow_offload *flow,
+				   enum flow_offload_tuple_dir dir,
+				   struct nf_flow_rule *flow_rule)
+{
+	const struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple;
+	int err;
+
+	switch (flow_tuple->l3proto) {
+	case NFPROTO_IPV4:
+		err = nf_flow_rule_route_ipv4(net, flow, dir, flow_rule);
+		break;
+	case NFPROTO_IPV6:
+		err = nf_flow_rule_route_ipv6(net, flow, dir, flow_rule);
+		break;
+	default:
+		err = -1;
+		break;
+	}
+
+	return err;
+}
+
+static struct nf_flowtable_type flowtable_inet = {
+	.family		= NFPROTO_INET,
+	.init		= nf_flow_table_init,
+	.setup		= nf_flow_table_offload_setup,
+	.action		= nf_flow_rule_route_inet,
+	.free		= nf_flow_table_free,
+	.hook		= nf_flow_offload_inet_hook,
+	.owner		= THIS_MODULE,
+};
+
+static int init_flowtable(struct xt_flowoffload_table *tbl)
+{
+	INIT_DELAYED_WORK(&tbl->work, xt_flowoffload_hook_work);
+	tbl->ft.type = &flowtable_inet;
+
+	return nf_flow_table_init(&tbl->ft);
+}
+
+static int __init xt_flowoffload_tg_init(void)
+{
+	int ret;
+
+	register_netdevice_notifier(&flow_offload_netdev_notifier);
+
+	ret = init_flowtable(&flowtable[0]);
+	if (ret)
+		return ret;
+
+	ret = init_flowtable(&flowtable[1]);
+	if (ret)
+		goto cleanup;
+
+	flowtable[1].ft.flags = NF_FLOWTABLE_HW_OFFLOAD;
+
+	ret = xt_register_target(&offload_tg_reg);
+	if (ret)
+		goto cleanup2;
+
+	return 0;
+
+cleanup2:
+	nf_flow_table_free(&flowtable[1].ft);
+cleanup:
+	nf_flow_table_free(&flowtable[0].ft);
+	return ret;
+}
+
+static void __exit xt_flowoffload_tg_exit(void)
+{
+	xt_unregister_target(&offload_tg_reg);
+	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+	nf_flow_table_free(&flowtable[0].ft);
+	nf_flow_table_free(&flowtable[1].ft);
+}
+
+MODULE_LICENSE("GPL");
+module_init(xt_flowoffload_tg_init);
+module_exit(xt_flowoffload_tg_exit);