Merge tag 'net-next-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking changes from Paolo Abeni:
 "Core:

   - Refactor the forward memory allocation to better cope with memory
     pressure with many open sockets, moving from a per socket cache to
     a per-CPU one

   - Replace rwlocks with RCU for better fairness in ping, raw sockets
     and IP multicast router.

   - Network-side support for IO uring zero-copy send.

   - A few skb drop reason improvements, including codegen the source
     file with string mapping instead of using macro magic.

   - Rename reference tracking helpers to a more consistent netdev_*
     schema.

   - Adapt u64_stats_t type to address load/store tearing issues.

   - Refine debug helper usage to reduce the log noise caused by bots.

  BPF:

   - Improve socket map performance, avoiding skb cloning on read
     operation.

   - Add support for 64 bits enum, to match types exposed by kernel.

   - Introduce support for sleepable uprobes program.

   - Introduce support for enum textual representation in libbpf.

   - New helpers to implement synproxy with eBPF/XDP.

   - Improve loop performances, inlining indirect calls when possible.

   - Removed all the deprecated libbpf APIs.

   - Implement new eBPF-based LSM flavor.

   - Add type match support, which allow accurate queries to the eBPF
     used types.

   - A few TCP congetsion control framework usability improvements.

   - Add new infrastructure to manipulate CT entries via eBPF programs.

   - Allow for livepatch (KLP) and BPF trampolines to attach to the same
     kernel function.

  Protocols:

   - Introduce per network namespace lookup tables for unix sockets,
     increasing scalability and reducing contention.

   - Preparation work for Wi-Fi 7 Multi-Link Operation (MLO) support.

   - Add support to forciby close TIME_WAIT TCP sockets via user-space
     tools.

   - Significant performance improvement for the TLS 1.3 receive path,
     both for zero-copy and not-zero-copy.

   - Support for changing the initial MTPCP subflow priority/backup
     status

   - Introduce virtually contingus buffers for sockets over RDMA, to
     cope better with memory pressure.

   - Extend CAN ethtool support with timestamping capabilities

   - Refactor CAN build infrastructure to allow building only the needed
     features.

  Driver API:

   - Remove devlink mutex to allow parallel commands on multiple links.

   - Add support for pause stats in distributed switch.

   - Implement devlink helpers to query and flash line cards.

   - New helper for phy mode to register conversion.

  New hardware / drivers:

   - Ethernet DSA driver for the rockchip mt7531 on BPI-R2 Pro.

   - Ethernet DSA driver for the Renesas RZ/N1 A5PSW switch.

   - Ethernet DSA driver for the Microchip LAN937x switch.

   - Ethernet PHY driver for the Aquantia AQR113C EPHY.

   - CAN driver for the OBD-II ELM327 interface.

   - CAN driver for RZ/N1 SJA1000 CAN controller.

   - Bluetooth: Infineon CYW55572 Wi-Fi plus Bluetooth combo device.

  Drivers:

   - Intel Ethernet NICs:
      - i40e: add support for vlan pruning
      - i40e: add support for XDP framented packets
      - ice: improved vlan offload support
      - ice: add support for PPPoE offload

   - Mellanox Ethernet (mlx5)
      - refactor packet steering offload for performance and scalability
      - extend support for TC offload
      - refactor devlink code to clean-up the locking schema
      - support stacked vlans for bridge offloads
      - use TLS objects pool to improve connection rate

   - Netronome Ethernet NICs (nfp):
      - extend support for IPv6 fields mangling offload
      - add support for vepa mode in HW bridge
      - better support for virtio data path acceleration (VDPA)
      - enable TSO by default

   - Microsoft vNIC driver (mana)
      - add support for XDP redirect

   - Others Ethernet drivers:
      - bonding: add per-port priority support
      - microchip lan743x: extend phy support
      - Fungible funeth: support UDP segmentation offload and XDP xmit
      - Solarflare EF100: add support for virtual function representors
      - MediaTek SoC: add XDP support

   - Mellanox Ethernet/IB switch (mlxsw):
      - dropped support for unreleased H/W (XM router).
      - improved stats accuracy
      - unified bridge model coversion improving scalability (parts 1-6)
      - support for PTP in Spectrum-2 asics

   - Broadcom PHYs
      - add PTP support for BCM54210E
      - add support for the BCM53128 internal PHY

   - Marvell Ethernet switches (prestera):
      - implement support for multicast forwarding offload

   - Embedded Ethernet switches:
      - refactor OcteonTx MAC filter for better scalability
      - improve TC H/W offload for the Felix driver
      - refactor the Microchip ksz8 and ksz9477 drivers to share the
        probe code (parts 1, 2), add support for phylink mac
        configuration

   - Other WiFi:
      - Microchip wilc1000: diable WEP support and enable WPA3
      - Atheros ath10k: encapsulation offload support

  Old code removal:

   - Neterion vxge ethernet driver: this is untouched since more than 10 years"

* tag 'net-next-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1890 commits)
  doc: sfp-phylink: Fix a broken reference
  wireguard: selftests: support UML
  wireguard: allowedips: don't corrupt stack when detecting overflow
  wireguard: selftests: update config fragments
  wireguard: ratelimiter: use hrtimer in selftest
  net/mlx5e: xsk: Discard unaligned XSK frames on striding RQ
  net: usb: ax88179_178a: Bind only to vendor-specific interface
  selftests: net: fix IOAM test skip return code
  net: usb: make USB_RTL8153_ECM non user configurable
  net: marvell: prestera: remove reduntant code
  octeontx2-pf: Reduce minimum mtu size to 60
  net: devlink: Fix missing mutex_unlock() call
  net/tls: Remove redundant workqueue flush before destroy
  net: txgbe: Fix an error handling path in txgbe_probe()
  net: dsa: Fix spelling mistakes and cleanup code
  Documentation: devlink: add add devlink-selftests to the table of contents
  dccp: put dccp_qpolicy_full() and dccp_qpolicy_push() in the same lock
  net: ionic: fix error check for vlan flags in ionic_set_nic_features()
  net: ice: fix error NETIF_F_HW_VLAN_CTAG_FILTER check in ice_vsi_sync_fltr()
  nfp: flower: add support for tunnel offload without key ID
  ...

5 files changed, 986 insertions, 277 deletions

diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index da4ec235d146..97374fb3ee79 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -17,6 +17,8 @@ config NET_MEDIATEK_SOC
 	select PINCTRL
 	select PHYLINK
 	select DIMLIB
+	select PAGE_POOL
+	select PAGE_POOL_STATS
 	help
 	  This driver supports the gigabit ethernet MACs in the
 	  MediaTek SoC family.
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 59c9a10f83ba..d9426b01f462 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -34,6 +34,10 @@ MODULE_PARM_DESC(msg_level, "Message level (-1=defaults,0=none,...,16=all)");
 #define MTK_ETHTOOL_STAT(x) { #x, \
 			      offsetof(struct mtk_hw_stats, x) / sizeof(u64) }
 
+#define MTK_ETHTOOL_XDP_STAT(x) { #x, \
+				  offsetof(struct mtk_hw_stats, xdp_stats.x) / \
+				  sizeof(u64) }
+
 static const struct mtk_reg_map mtk_reg_map = {
 	.tx_irq_mask		= 0x1a1c,
 	.tx_irq_status		= 0x1a18,
@@ -141,6 +145,13 @@ static const struct mtk_ethtool_stats {
 	MTK_ETHTOOL_STAT(rx_long_errors),
 	MTK_ETHTOOL_STAT(rx_checksum_errors),
 	MTK_ETHTOOL_STAT(rx_flow_control_packets),
+	MTK_ETHTOOL_XDP_STAT(rx_xdp_redirect),
+	MTK_ETHTOOL_XDP_STAT(rx_xdp_pass),
+	MTK_ETHTOOL_XDP_STAT(rx_xdp_drop),
+	MTK_ETHTOOL_XDP_STAT(rx_xdp_tx),
+	MTK_ETHTOOL_XDP_STAT(rx_xdp_tx_errors),
+	MTK_ETHTOOL_XDP_STAT(tx_xdp_xmit),
+	MTK_ETHTOOL_XDP_STAT(tx_xdp_xmit_errors),
 };
 
 static const char * const mtk_clks_source_name[] = {
@@ -990,7 +1001,7 @@ static int txd_to_idx(struct mtk_tx_ring *ring, void *dma, u32 txd_size)
 }
 
 static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf,
-			 bool napi)
+			 struct xdp_frame_bulk *bq, bool napi)
 {
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) {
 		if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) {
@@ -1020,15 +1031,27 @@ static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf,
 		}
 	}
 
-	tx_buf->flags = 0;
-	if (tx_buf->skb &&
-	    (tx_buf->skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC)) {
-		if (napi)
-			napi_consume_skb(tx_buf->skb, napi);
-		else
-			dev_kfree_skb_any(tx_buf->skb);
+	if (tx_buf->data && tx_buf->data != (void *)MTK_DMA_DUMMY_DESC) {
+		if (tx_buf->type == MTK_TYPE_SKB) {
+			struct sk_buff *skb = tx_buf->data;
+
+			if (napi)
+				napi_consume_skb(skb, napi);
+			else
+				dev_kfree_skb_any(skb);
+		} else {
+			struct xdp_frame *xdpf = tx_buf->data;
+
+			if (napi && tx_buf->type == MTK_TYPE_XDP_TX)
+				xdp_return_frame_rx_napi(xdpf);
+			else if (bq)
+				xdp_return_frame_bulk(xdpf, bq);
+			else
+				xdp_return_frame(xdpf);
+		}
 	}
-	tx_buf->skb = NULL;
+	tx_buf->flags = 0;
+	tx_buf->data = NULL;
 }
 
 static void setup_tx_buf(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf,
@@ -1045,7 +1068,7 @@ static void setup_tx_buf(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf,
 			dma_unmap_addr_set(tx_buf, dma_addr1, mapped_addr);
 			dma_unmap_len_set(tx_buf, dma_len1, size);
 		} else {
-			tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
+			tx_buf->data = (void *)MTK_DMA_DUMMY_DESC;
 			txd->txd1 = mapped_addr;
 			txd->txd2 = TX_DMA_PLEN0(size);
 			dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
@@ -1221,7 +1244,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 						    soc->txrx.txd_size);
 			if (new_desc)
 				memset(tx_buf, 0, sizeof(*tx_buf));
-			tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
+			tx_buf->data = (void *)MTK_DMA_DUMMY_DESC;
 			tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
 			tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
 					 MTK_TX_FLAGS_FPORT1;
@@ -1235,7 +1258,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	/* store skb to cleanup */
-	itx_buf->skb = skb;
+	itx_buf->type = MTK_TYPE_SKB;
+	itx_buf->data = skb;
 
 	if (!MTK_HAS_CAPS(soc->caps, MTK_QDMA)) {
 		if (k & 0x1)
@@ -1274,7 +1298,7 @@ err_dma:
 		tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size);
 
 		/* unmap dma */
-		mtk_tx_unmap(eth, tx_buf, false);
+		mtk_tx_unmap(eth, tx_buf, NULL, false);
 
 		itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU;
 		if (!MTK_HAS_CAPS(soc->caps, MTK_QDMA))
@@ -1432,11 +1456,320 @@ static void mtk_update_rx_cpu_idx(struct mtk_eth *eth)
 	}
 }
 
+static bool mtk_page_pool_enabled(struct mtk_eth *eth)
+{
+	return !eth->hwlro;
+}
+
+static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth,
+					      struct xdp_rxq_info *xdp_q,
+					      int id, int size)
+{
+	struct page_pool_params pp_params = {
+		.order = 0,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.pool_size = size,
+		.nid = NUMA_NO_NODE,
+		.dev = eth->dma_dev,
+		.offset = MTK_PP_HEADROOM,
+		.max_len = MTK_PP_MAX_BUF_SIZE,
+	};
+	struct page_pool *pp;
+	int err;
+
+	pp_params.dma_dir = rcu_access_pointer(eth->prog) ? DMA_BIDIRECTIONAL
+							  : DMA_FROM_DEVICE;
+	pp = page_pool_create(&pp_params);
+	if (IS_ERR(pp))
+		return pp;
+
+	err = __xdp_rxq_info_reg(xdp_q, &eth->dummy_dev, eth->rx_napi.napi_id,
+				 id, PAGE_SIZE);
+	if (err < 0)
+		goto err_free_pp;
+
+	err = xdp_rxq_info_reg_mem_model(xdp_q, MEM_TYPE_PAGE_POOL, pp);
+	if (err)
+		goto err_unregister_rxq;
+
+	return pp;
+
+err_unregister_rxq:
+	xdp_rxq_info_unreg(xdp_q);
+err_free_pp:
+	page_pool_destroy(pp);
+
+	return ERR_PTR(err);
+}
+
+static void *mtk_page_pool_get_buff(struct page_pool *pp, dma_addr_t *dma_addr,
+				    gfp_t gfp_mask)
+{
+	struct page *page;
+
+	page = page_pool_alloc_pages(pp, gfp_mask | __GFP_NOWARN);
+	if (!page)
+		return NULL;
+
+	*dma_addr = page_pool_get_dma_addr(page) + MTK_PP_HEADROOM;
+	return page_address(page);
+}
+
+static void mtk_rx_put_buff(struct mtk_rx_ring *ring, void *data, bool napi)
+{
+	if (ring->page_pool)
+		page_pool_put_full_page(ring->page_pool,
+					virt_to_head_page(data), napi);
+	else
+		skb_free_frag(data);
+}
+
+static int mtk_xdp_frame_map(struct mtk_eth *eth, struct net_device *dev,
+			     struct mtk_tx_dma_desc_info *txd_info,
+			     struct mtk_tx_dma *txd, struct mtk_tx_buf *tx_buf,
+			     void *data, u16 headroom, int index, bool dma_map)
+{
+	struct mtk_tx_ring *ring = &eth->tx_ring;
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_tx_dma *txd_pdma;
+
+	if (dma_map) {  /* ndo_xdp_xmit */
+		txd_info->addr = dma_map_single(eth->dma_dev, data,
+						txd_info->size, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(eth->dma_dev, txd_info->addr)))
+			return -ENOMEM;
+
+		tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
+	} else {
+		struct page *page = virt_to_head_page(data);
+
+		txd_info->addr = page_pool_get_dma_addr(page) +
+				 sizeof(struct xdp_frame) + headroom;
+		dma_sync_single_for_device(eth->dma_dev, txd_info->addr,
+					   txd_info->size, DMA_BIDIRECTIONAL);
+	}
+	mtk_tx_set_dma_desc(dev, txd, txd_info);
+
+	tx_buf->flags |= !mac->id ? MTK_TX_FLAGS_FPORT0 : MTK_TX_FLAGS_FPORT1;
+	tx_buf->type = dma_map ? MTK_TYPE_XDP_NDO : MTK_TYPE_XDP_TX;
+	tx_buf->data = (void *)MTK_DMA_DUMMY_DESC;
+
+	txd_pdma = qdma_to_pdma(ring, txd);
+	setup_tx_buf(eth, tx_buf, txd_pdma, txd_info->addr, txd_info->size,
+		     index);
+
+	return 0;
+}
+
+static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf,
+				struct net_device *dev, bool dma_map)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
+	const struct mtk_soc_data *soc = eth->soc;
+	struct mtk_tx_ring *ring = &eth->tx_ring;
+	struct mtk_tx_dma_desc_info txd_info = {
+		.size	= xdpf->len,
+		.first	= true,
+		.last	= !xdp_frame_has_frags(xdpf),
+	};
+	int err, index = 0, n_desc = 1, nr_frags;
+	struct mtk_tx_dma *htxd, *txd, *txd_pdma;
+	struct mtk_tx_buf *htx_buf, *tx_buf;
+	void *data = xdpf->data;
+
+	if (unlikely(test_bit(MTK_RESETTING, &eth->state)))
+		return -EBUSY;
+
+	nr_frags = unlikely(xdp_frame_has_frags(xdpf)) ? sinfo->nr_frags : 0;
+	if (unlikely(atomic_read(&ring->free_count) <= 1 + nr_frags))
+		return -EBUSY;
+
+	spin_lock(&eth->page_lock);
+
+	txd = ring->next_free;
+	if (txd == ring->last_free) {
+		spin_unlock(&eth->page_lock);
+		return -ENOMEM;
+	}
+	htxd = txd;
+
+	tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->txrx.txd_size);
+	memset(tx_buf, 0, sizeof(*tx_buf));
+	htx_buf = tx_buf;
+
+	for (;;) {
+		err = mtk_xdp_frame_map(eth, dev, &txd_info, txd, tx_buf,
+					data, xdpf->headroom, index, dma_map);
+		if (err < 0)
+			goto unmap;
+
+		if (txd_info.last)
+			break;
+
+		if (MTK_HAS_CAPS(soc->caps, MTK_QDMA) || (index & 0x1)) {
+			txd = mtk_qdma_phys_to_virt(ring, txd->txd2);
+			txd_pdma = qdma_to_pdma(ring, txd);
+			if (txd == ring->last_free)
+				goto unmap;
+
+			tx_buf = mtk_desc_to_tx_buf(ring, txd,
+						    soc->txrx.txd_size);
+			memset(tx_buf, 0, sizeof(*tx_buf));
+			n_desc++;
+		}
+
+		memset(&txd_info, 0, sizeof(struct mtk_tx_dma_desc_info));
+		txd_info.size = skb_frag_size(&sinfo->frags[index]);
+		txd_info.last = index + 1 == nr_frags;
+		data = skb_frag_address(&sinfo->frags[index]);
+
+		index++;
+	}
+	/* store xdpf for cleanup */
+	htx_buf->data = xdpf;
+
+	if (!MTK_HAS_CAPS(soc->caps, MTK_QDMA)) {
+		txd_pdma = qdma_to_pdma(ring, txd);
+		if (index & 1)
+			txd_pdma->txd2 |= TX_DMA_LS0;
+		else
+			txd_pdma->txd2 |= TX_DMA_LS1;
+	}
+
+	ring->next_free = mtk_qdma_phys_to_virt(ring, txd->txd2);
+	atomic_sub(n_desc, &ring->free_count);
+
+	/* make sure that all changes to the dma ring are flushed before we
+	 * continue
+	 */
+	wmb();
+
+	if (MTK_HAS_CAPS(soc->caps, MTK_QDMA)) {
+		mtk_w32(eth, txd->txd2, soc->reg_map->qdma.ctx_ptr);
+	} else {
+		int idx;
+
+		idx = txd_to_idx(ring, txd, soc->txrx.txd_size);
+		mtk_w32(eth, NEXT_DESP_IDX(idx, ring->dma_size),
+			MT7628_TX_CTX_IDX0);
+	}
+
+	spin_unlock(&eth->page_lock);
+
+	return 0;
+
+unmap:
+	while (htxd != txd) {
+		txd_pdma = qdma_to_pdma(ring, htxd);
+		tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->txrx.txd_size);
+		mtk_tx_unmap(eth, tx_buf, NULL, false);
+
+		htxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU;
+		if (!MTK_HAS_CAPS(soc->caps, MTK_QDMA))
+			txd_pdma->txd2 = TX_DMA_DESP2_DEF;
+
+		htxd = mtk_qdma_phys_to_virt(ring, htxd->txd2);
+	}
+
+	spin_unlock(&eth->page_lock);
+
+	return err;
+}
+
+static int mtk_xdp_xmit(struct net_device *dev, int num_frame,
+			struct xdp_frame **frames, u32 flags)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_hw_stats *hw_stats = mac->hw_stats;
+	struct mtk_eth *eth = mac->hw;
+	int i, nxmit = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	for (i = 0; i < num_frame; i++) {
+		if (mtk_xdp_submit_frame(eth, frames[i], dev, true))
+			break;
+		nxmit++;
+	}
+
+	u64_stats_update_begin(&hw_stats->syncp);
+	hw_stats->xdp_stats.tx_xdp_xmit += nxmit;
+	hw_stats->xdp_stats.tx_xdp_xmit_errors += num_frame - nxmit;
+	u64_stats_update_end(&hw_stats->syncp);
+
+	return nxmit;
+}
+
+static u32 mtk_xdp_run(struct mtk_eth *eth, struct mtk_rx_ring *ring,
+		       struct xdp_buff *xdp, struct net_device *dev)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_hw_stats *hw_stats = mac->hw_stats;
+	u64 *count = &hw_stats->xdp_stats.rx_xdp_drop;
+	struct bpf_prog *prog;
+	u32 act = XDP_PASS;
+
+	rcu_read_lock();
+
+	prog = rcu_dereference(eth->prog);
+	if (!prog)
+		goto out;
+
+	act = bpf_prog_run_xdp(prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		count = &hw_stats->xdp_stats.rx_xdp_pass;
+		goto update_stats;
+	case XDP_REDIRECT:
+		if (unlikely(xdp_do_redirect(dev, xdp, prog))) {
+			act = XDP_DROP;
+			break;
+		}
+
+		count = &hw_stats->xdp_stats.rx_xdp_redirect;
+		goto update_stats;
+	case XDP_TX: {
+		struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
+
+		if (mtk_xdp_submit_frame(eth, xdpf, dev, false)) {
+			count = &hw_stats->xdp_stats.rx_xdp_tx_errors;
+			act = XDP_DROP;
+			break;
+		}
+
+		count = &hw_stats->xdp_stats.rx_xdp_tx;
+		goto update_stats;
+	}
+	default:
+		bpf_warn_invalid_xdp_action(dev, prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(dev, prog, act);
+		fallthrough;
+	case XDP_DROP:
+		break;
+	}
+
+	page_pool_put_full_page(ring->page_pool,
+				virt_to_head_page(xdp->data), true);
+
+update_stats:
+	u64_stats_update_begin(&hw_stats->syncp);
+	*count = *count + 1;
+	u64_stats_update_end(&hw_stats->syncp);
+out:
+	rcu_read_unlock();
+
+	return act;
+}
+
 static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		       struct mtk_eth *eth)
 {
 	struct dim_sample dim_sample = {};
 	struct mtk_rx_ring *ring;
+	bool xdp_flush = false;
 	int idx;
 	struct sk_buff *skb;
 	u8 *data, *new_data;
@@ -1444,8 +1777,8 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 	int done = 0, bytes = 0;
 
 	while (done < budget) {
+		unsigned int pktlen, *rxdcsum;
 		struct net_device *netdev;
-		unsigned int pktlen;
 		dma_addr_t dma_addr;
 		u32 hash, reason;
 		int mac = 0;
@@ -1477,47 +1810,97 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		if (unlikely(test_bit(MTK_RESETTING, &eth->state)))
 			goto release_desc;
 
+		pktlen = RX_DMA_GET_PLEN0(trxd.rxd2);
+
 		/* alloc new buffer */
-		if (ring->frag_size <= PAGE_SIZE)
-			new_data = napi_alloc_frag(ring->frag_size);
-		else
-			new_data = mtk_max_lro_buf_alloc(GFP_ATOMIC);
-		if (unlikely(!new_data)) {
-			netdev->stats.rx_dropped++;
-			goto release_desc;
-		}
-		dma_addr = dma_map_single(eth->dma_dev,
-					  new_data + NET_SKB_PAD +
-					  eth->ip_align,
-					  ring->buf_size,
-					  DMA_FROM_DEVICE);
-		if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr))) {
-			skb_free_frag(new_data);
-			netdev->stats.rx_dropped++;
-			goto release_desc;
-		}
+		if (ring->page_pool) {
+			struct page *page = virt_to_head_page(data);
+			struct xdp_buff xdp;
+			u32 ret;
+
+			new_data = mtk_page_pool_get_buff(ring->page_pool,
+							  &dma_addr,
+							  GFP_ATOMIC);
+			if (unlikely(!new_data)) {
+				netdev->stats.rx_dropped++;
+				goto release_desc;
+			}
+
+			dma_sync_single_for_cpu(eth->dma_dev,
+				page_pool_get_dma_addr(page) + MTK_PP_HEADROOM,
+				pktlen, page_pool_get_dma_dir(ring->page_pool));
+
+			xdp_init_buff(&xdp, PAGE_SIZE, &ring->xdp_q);
+			xdp_prepare_buff(&xdp, data, MTK_PP_HEADROOM, pktlen,
+					 false);
+			xdp_buff_clear_frags_flag(&xdp);
+
+			ret = mtk_xdp_run(eth, ring, &xdp, netdev);
+			if (ret == XDP_REDIRECT)
+				xdp_flush = true;
 
-		dma_unmap_single(eth->dma_dev, trxd.rxd1,
-				 ring->buf_size, DMA_FROM_DEVICE);
+			if (ret != XDP_PASS)
+				goto skip_rx;
+
+			skb = build_skb(data, PAGE_SIZE);
+			if (unlikely(!skb)) {
+				page_pool_put_full_page(ring->page_pool,
+							page, true);
+				netdev->stats.rx_dropped++;
+				goto skip_rx;
+			}
+
+			skb_reserve(skb, xdp.data - xdp.data_hard_start);
+			skb_put(skb, xdp.data_end - xdp.data);
+			skb_mark_for_recycle(skb);
+		} else {
+			if (ring->frag_size <= PAGE_SIZE)
+				new_data = napi_alloc_frag(ring->frag_size);
+			else
+				new_data = mtk_max_lro_buf_alloc(GFP_ATOMIC);
+
+			if (unlikely(!new_data)) {
+				netdev->stats.rx_dropped++;
+				goto release_desc;
+			}
+
+			dma_addr = dma_map_single(eth->dma_dev,
+				new_data + NET_SKB_PAD + eth->ip_align,
+				ring->buf_size, DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(eth->dma_dev,
+						       dma_addr))) {
+				skb_free_frag(new_data);
+				netdev->stats.rx_dropped++;
+				goto release_desc;
+			}
+
+			dma_unmap_single(eth->dma_dev, trxd.rxd1,
+					 ring->buf_size, DMA_FROM_DEVICE);
+
+			skb = build_skb(data, ring->frag_size);
+			if (unlikely(!skb)) {
+				netdev->stats.rx_dropped++;
+				skb_free_frag(data);
+				goto skip_rx;
+			}
 
-		/* receive data */
-		skb = build_skb(data, ring->frag_size);
-		if (unlikely(!skb)) {
-			skb_free_frag(data);
-			netdev->stats.rx_dropped++;
-			goto skip_rx;
+			skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+			skb_put(skb, pktlen);
 		}
-		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 
-		pktlen = RX_DMA_GET_PLEN0(trxd.rxd2);
 		skb->dev = netdev;
-		skb_put(skb, pktlen);
-		if (trxd.rxd4 & eth->soc->txrx.rx_dma_l4_valid)
+		bytes += skb->len;
+
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+			rxdcsum = &trxd.rxd3;
+		else
+			rxdcsum = &trxd.rxd4;
+
+		if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else
 			skb_checksum_none_assert(skb);
 		skb->protocol = eth_type_trans(skb, netdev);
-		bytes += pktlen;
 
 		hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY;
 		if (hash != MTK_RXD4_FOE_ENTRY) {
@@ -1555,7 +1938,6 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 skip_rx:
 		ring->data[idx] = new_data;
 		rxd->rxd1 = (unsigned int)dma_addr;
-
 release_desc:
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 			rxd->rxd2 = RX_DMA_LSO;
@@ -1563,7 +1945,6 @@ release_desc:
 			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
 
 		ring->calc_idx = idx;
-
 		done++;
 	}
 
@@ -1582,6 +1963,9 @@ rx_done:
 			  &dim_sample);
 	net_dim(&eth->rx_dim, dim_sample);
 
+	if (xdp_flush)
+		xdp_do_flush_map();
+
 	return done;
 }
 
@@ -1590,15 +1974,16 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget,
 {
 	const struct mtk_reg_map *reg_map = eth->soc->reg_map;
 	struct mtk_tx_ring *ring = &eth->tx_ring;
-	struct mtk_tx_dma *desc;
-	struct sk_buff *skb;
 	struct mtk_tx_buf *tx_buf;
+	struct xdp_frame_bulk bq;
+	struct mtk_tx_dma *desc;
 	u32 cpu, dma;
 
 	cpu = ring->last_free_ptr;
 	dma = mtk_r32(eth, reg_map->qdma.drx_ptr);
 
 	desc = mtk_qdma_phys_to_virt(ring, cpu);
+	xdp_frame_bulk_init(&bq);
 
 	while ((cpu != dma) && budget) {
 		u32 next_cpu = desc->txd2;
@@ -1613,22 +1998,26 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget,
 		if (tx_buf->flags & MTK_TX_FLAGS_FPORT1)
 			mac = 1;
 
-		skb = tx_buf->skb;
-		if (!skb)
+		if (!tx_buf->data)
 			break;
 
-		if (skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC) {
-			bytes[mac] += skb->len;
-			done[mac]++;
+		if (tx_buf->data != (void *)MTK_DMA_DUMMY_DESC) {
+			if (tx_buf->type == MTK_TYPE_SKB) {
+				struct sk_buff *skb = tx_buf->data;
+
+				bytes[mac] += skb->len;
+				done[mac]++;
+			}
 			budget--;
 		}
-		mtk_tx_unmap(eth, tx_buf, true);
+		mtk_tx_unmap(eth, tx_buf, &bq, true);
 
 		ring->last_free = desc;
 		atomic_inc(&ring->free_count);
 
 		cpu = next_cpu;
 	}
+	xdp_flush_frame_bulk(&bq);
 
 	ring->last_free_ptr = cpu;
 	mtk_w32(eth, cpu, reg_map->qdma.crx_ptr);
@@ -1640,27 +2029,30 @@ static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget,
 			    unsigned int *done, unsigned int *bytes)
 {
 	struct mtk_tx_ring *ring = &eth->tx_ring;
-	struct mtk_tx_dma *desc;
-	struct sk_buff *skb;
 	struct mtk_tx_buf *tx_buf;
+	struct xdp_frame_bulk bq;
+	struct mtk_tx_dma *desc;
 	u32 cpu, dma;
 
 	cpu = ring->cpu_idx;
 	dma = mtk_r32(eth, MT7628_TX_DTX_IDX0);
+	xdp_frame_bulk_init(&bq);
 
 	while ((cpu != dma) && budget) {
 		tx_buf = &ring->buf[cpu];
-		skb = tx_buf->skb;
-		if (!skb)
+		if (!tx_buf->data)
 			break;
 
-		if (skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC) {
-			bytes[0] += skb->len;
-			done[0]++;
+		if (tx_buf->data != (void *)MTK_DMA_DUMMY_DESC) {
+			if (tx_buf->type == MTK_TYPE_SKB) {
+				struct sk_buff *skb = tx_buf->data;
+
+				bytes[0] += skb->len;
+				done[0]++;
+			}
 			budget--;
 		}
-
-		mtk_tx_unmap(eth, tx_buf, true);
+		mtk_tx_unmap(eth, tx_buf, &bq, true);
 
 		desc = ring->dma + cpu * eth->soc->txrx.txd_size;
 		ring->last_free = desc;
@@ -1668,6 +2060,7 @@ static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget,
 
 		cpu = NEXT_DESP_IDX(cpu, ring->dma_size);
 	}
+	xdp_flush_frame_bulk(&bq);
 
 	ring->cpu_idx = cpu;
 
@@ -1877,7 +2270,7 @@ static void mtk_tx_clean(struct mtk_eth *eth)
 
 	if (ring->buf) {
 		for (i = 0; i < MTK_DMA_SIZE; i++)
-			mtk_tx_unmap(eth, &ring->buf[i], false);
+			mtk_tx_unmap(eth, &ring->buf[i], NULL, false);
 		kfree(ring->buf);
 		ring->buf = NULL;
 	}
@@ -1927,13 +2320,15 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 	if (!ring->data)
 		return -ENOMEM;
 
-	for (i = 0; i < rx_dma_size; i++) {
-		if (ring->frag_size <= PAGE_SIZE)
-			ring->data[i] = netdev_alloc_frag(ring->frag_size);
-		else
-			ring->data[i] = mtk_max_lro_buf_alloc(GFP_KERNEL);
-		if (!ring->data[i])
-			return -ENOMEM;
+	if (mtk_page_pool_enabled(eth)) {
+		struct page_pool *pp;
+
+		pp = mtk_create_page_pool(eth, &ring->xdp_q, ring_no,
+					  rx_dma_size);
+		if (IS_ERR(pp))
+			return PTR_ERR(pp);
+
+		ring->page_pool = pp;
 	}
 
 	ring->dma = dma_alloc_coherent(eth->dma_dev,
@@ -1944,16 +2339,33 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 
 	for (i = 0; i < rx_dma_size; i++) {
 		struct mtk_rx_dma_v2 *rxd;
-
-		dma_addr_t dma_addr = dma_map_single(eth->dma_dev,
-				ring->data[i] + NET_SKB_PAD + eth->ip_align,
-				ring->buf_size,
-				DMA_FROM_DEVICE);
-		if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr)))
-			return -ENOMEM;
+		dma_addr_t dma_addr;
+		void *data;
 
 		rxd = ring->dma + i * eth->soc->txrx.rxd_size;
+		if (ring->page_pool) {
+			data = mtk_page_pool_get_buff(ring->page_pool,
+						      &dma_addr, GFP_KERNEL);
+			if (!data)
+				return -ENOMEM;
+		} else {
+			if (ring->frag_size <= PAGE_SIZE)
+				data = netdev_alloc_frag(ring->frag_size);
+			else
+				data = mtk_max_lro_buf_alloc(GFP_KERNEL);
+
+			if (!data)
+				return -ENOMEM;
+
+			dma_addr = dma_map_single(eth->dma_dev,
+				data + NET_SKB_PAD + eth->ip_align,
+				ring->buf_size, DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(eth->dma_dev,
+						       dma_addr)))
+				return -ENOMEM;
+		}
 		rxd->rxd1 = (unsigned int)dma_addr;
+		ring->data[i] = data;
 
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 			rxd->rxd2 = RX_DMA_LSO;
@@ -1969,6 +2381,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 			rxd->rxd8 = 0;
 		}
 	}
+
 	ring->dma_size = rx_dma_size;
 	ring->calc_idx_update = false;
 	ring->calc_idx = rx_dma_size - 1;
@@ -2020,7 +2433,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring)
 
 			dma_unmap_single(eth->dma_dev, rxd->rxd1,
 					 ring->buf_size, DMA_FROM_DEVICE);
-			skb_free_frag(ring->data[i]);
+			mtk_rx_put_buff(ring, ring->data[i], false);
 		}
 		kfree(ring->data);
 		ring->data = NULL;
@@ -2032,6 +2445,13 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring)
 				  ring->dma, ring->phys);
 		ring->dma = NULL;
 	}
+
+	if (ring->page_pool) {
+		if (xdp_rxq_info_is_reg(&ring->xdp_q))
+			xdp_rxq_info_unreg(&ring->xdp_q);
+		page_pool_destroy(ring->page_pool);
+		ring->page_pool = NULL;
+	}
 }
 
 static int mtk_hwlro_rx_init(struct mtk_eth *eth)
@@ -2639,6 +3059,48 @@ static int mtk_stop(struct net_device *dev)
 	return 0;
 }
 
+static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
+			 struct netlink_ext_ack *extack)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_eth *eth = mac->hw;
+	struct bpf_prog *old_prog;
+	bool need_update;
+
+	if (eth->hwlro) {
+		NL_SET_ERR_MSG_MOD(extack, "XDP not supported with HWLRO");
+		return -EOPNOTSUPP;
+	}
+
+	if (dev->mtu > MTK_PP_MAX_BUF_SIZE) {
+		NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP");
+		return -EOPNOTSUPP;
+	}
+
+	need_update = !!eth->prog != !!prog;
+	if (netif_running(dev) && need_update)
+		mtk_stop(dev);
+
+	old_prog = rcu_replace_pointer(eth->prog, prog, lockdep_rtnl_is_held());
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (netif_running(dev) && need_update)
+		return mtk_open(dev);
+
+	return 0;
+}
+
+static int mtk_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return mtk_xdp_setup(dev, xdp->prog, xdp->extack);
+	default:
+		return -EINVAL;
+	}
+}
+
 static void ethsys_reset(struct mtk_eth *eth, u32 reset_bits)
 {
 	regmap_update_bits(eth->ethsys, ETHSYS_RSTCTRL,
@@ -2934,6 +3396,12 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu)
 	struct mtk_eth *eth = mac->hw;
 	u32 mcr_cur, mcr_new;
 
+	if (rcu_access_pointer(eth->prog) &&
+	    length > MTK_PP_MAX_BUF_SIZE) {
+		netdev_err(dev, "Invalid MTU for XDP mode\n");
+		return -EINVAL;
+	}
+
 	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) {
 		mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
 		mcr_new = mcr_cur & ~MAC_MCR_MAX_RX_MASK;
@@ -3123,11 +3591,18 @@ static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	int i;
 
 	switch (stringset) {
-	case ETH_SS_STATS:
+	case ETH_SS_STATS: {
+		struct mtk_mac *mac = netdev_priv(dev);
+
 		for (i = 0; i < ARRAY_SIZE(mtk_ethtool_stats); i++) {
 			memcpy(data, mtk_ethtool_stats[i].str, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
+		if (mtk_page_pool_enabled(mac->hw))
+			page_pool_ethtool_stats_get_strings(data);
+		break;
+	}
+	default:
 		break;
 	}
 }
@@ -3135,13 +3610,35 @@ static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 static int mtk_get_sset_count(struct net_device *dev, int sset)
 {
 	switch (sset) {
-	case ETH_SS_STATS:
-		return ARRAY_SIZE(mtk_ethtool_stats);
+	case ETH_SS_STATS: {
+		int count = ARRAY_SIZE(mtk_ethtool_stats);
+		struct mtk_mac *mac = netdev_priv(dev);
+
+		if (mtk_page_pool_enabled(mac->hw))
+			count += page_pool_ethtool_stats_get_count();
+		return count;
+	}
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
+static void mtk_ethtool_pp_stats(struct mtk_eth *eth, u64 *data)
+{
+	struct page_pool_stats stats = {};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(eth->rx_ring); i++) {
+		struct mtk_rx_ring *ring = &eth->rx_ring[i];
+
+		if (!ring->page_pool)
+			continue;
+
+		page_pool_get_stats(ring->page_pool, &stats);
+	}
+	page_pool_ethtool_stats_get(data, &stats);
+}
+
 static void mtk_get_ethtool_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
@@ -3169,6 +3666,8 @@ static void mtk_get_ethtool_stats(struct net_device *dev,
 
 		for (i = 0; i < ARRAY_SIZE(mtk_ethtool_stats); i++)
 			*data_dst++ = *(data_src + mtk_ethtool_stats[i].offset);
+		if (mtk_page_pool_enabled(mac->hw))
+			mtk_ethtool_pp_stats(mac->hw, data_dst);
 	} while (u64_stats_fetch_retry_irq(&hwstats->syncp, start));
 }
 
@@ -3261,6 +3760,8 @@ static const struct net_device_ops mtk_netdev_ops = {
 	.ndo_poll_controller	= mtk_poll_controller,
 #endif
 	.ndo_setup_tc		= mtk_eth_setup_tc,
+	.ndo_bpf		= mtk_xdp,
+	.ndo_xdp_xmit		= mtk_xdp_xmit,
 };
 
 static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
@@ -3761,6 +4262,7 @@ static const struct mtk_soc_data mt7986_data = {
 		.txd_size = sizeof(struct mtk_tx_dma_v2),
 		.rxd_size = sizeof(struct mtk_rx_dma_v2),
 		.rx_irq_done_mask = MTK_RX_DONE_INT_V2,
+		.rx_dma_l4_valid = RX_DMA_L4_VALID_V2,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
 	},
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 0a632896451a..7405c97cda66 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -18,6 +18,8 @@
 #include <linux/rhashtable.h>
 #include <linux/dim.h>
 #include <linux/bitfield.h>
+#include <net/page_pool.h>
+#include <linux/bpf_trace.h>
 #include "mtk_ppe.h"
 
 #define MTK_QDMA_PAGE_SIZE	2048
@@ -49,6 +51,11 @@
 #define MTK_HW_FEATURES_MT7628	(NETIF_F_SG | NETIF_F_RXCSUM)
 #define NEXT_DESP_IDX(X, Y)	(((X) + 1) & ((Y) - 1))
 
+#define MTK_PP_HEADROOM		XDP_PACKET_HEADROOM
+#define MTK_PP_PAD		(MTK_PP_HEADROOM + \
+				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define MTK_PP_MAX_BUF_SIZE	(PAGE_SIZE - MTK_PP_PAD)
+
 #define MTK_QRX_OFFSET		0x10
 
 #define MTK_MAX_RX_RING_NUM	4
@@ -563,6 +570,16 @@ struct mtk_tx_dma_v2 {
 struct mtk_eth;
 struct mtk_mac;
 
+struct mtk_xdp_stats {
+	u64 rx_xdp_redirect;
+	u64 rx_xdp_pass;
+	u64 rx_xdp_drop;
+	u64 rx_xdp_tx;
+	u64 rx_xdp_tx_errors;
+	u64 tx_xdp_xmit;
+	u64 tx_xdp_xmit_errors;
+};
+
 /* struct mtk_hw_stats - the structure that holds the traffic statistics.
  * @stats_lock:		make sure that stats operations are atomic
  * @reg_offset:		the status register offset of the SoC
@@ -586,6 +603,8 @@ struct mtk_hw_stats {
 	u64 rx_checksum_errors;
 	u64 rx_flow_control_packets;
 
+	struct mtk_xdp_stats	xdp_stats;
+
 	spinlock_t		stats_lock;
 	u32			reg_offset;
 	struct u64_stats_sync	syncp;
@@ -677,6 +696,12 @@ enum mtk_dev_state {
 	MTK_RESETTING
 };
 
+enum mtk_tx_buf_type {
+	MTK_TYPE_SKB,
+	MTK_TYPE_XDP_TX,
+	MTK_TYPE_XDP_NDO,
+};
+
 /* struct mtk_tx_buf -	This struct holds the pointers to the memory pointed at
  *			by the TX descriptor	s
  * @skb:		The SKB pointer of the packet being sent
@@ -686,7 +711,9 @@ enum mtk_dev_state {
  * @dma_len1:		The length of the second segment
  */
 struct mtk_tx_buf {
-	struct sk_buff *skb;
+	enum mtk_tx_buf_type type;
+	void *data;
+
 	u32 flags;
 	DEFINE_DMA_UNMAP_ADDR(dma_addr0);
 	DEFINE_DMA_UNMAP_LEN(dma_len0);
@@ -745,6 +772,9 @@ struct mtk_rx_ring {
 	bool calc_idx_update;
 	u16 calc_idx;
 	u32 crx_idx_reg;
+	/* page_pool */
+	struct page_pool *page_pool;
+	struct xdp_rxq_info xdp_q;
 };
 
 enum mkt_eth_capabilities {
@@ -1078,6 +1108,8 @@ struct mtk_eth {
 
 	struct mtk_ppe			*ppe;
 	struct rhashtable		flow_table;
+
+	struct bpf_prog			__rcu *prog;
 };
 
 /* struct mtk_mac -	the structure that holds the info about the MACs of the
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index 5d457bc9acc1..25dc3c3aa31d 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -88,32 +88,28 @@ mtk_flow_offload_mangle_eth(const struct flow_action_entry *act, void *eth)
 static int
 mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_info *info)
 {
-	struct net_device_path_ctx ctx = {
-		.dev = dev,
-	};
-	struct net_device_path path = {};
+	struct net_device_path_stack stack;
+	struct net_device_path *path;
+	int err;
 
-	if (!ctx.dev)
+	if (!dev)
 		return -ENODEV;
 
-	memcpy(ctx.daddr, addr, sizeof(ctx.daddr));
-
 	if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED))
 		return -1;
 
-	if (!dev->netdev_ops->ndo_fill_forward_path)
-		return -1;
-
-	if (dev->netdev_ops->ndo_fill_forward_path(&ctx, &path))
-		return -1;
+	err = dev_fill_forward_path(dev, addr, &stack);
+	if (err)
+		return err;
 
-	if (path.type != DEV_PATH_MTK_WDMA)
+	path = &stack.path[stack.num_paths - 1];
+	if (path->type != DEV_PATH_MTK_WDMA)
 		return -1;
 
-	info->wdma_idx = path.mtk_wdma.wdma_idx;
-	info->queue = path.mtk_wdma.queue;
-	info->bss = path.mtk_wdma.bss;
-	info->wcid = path.mtk_wdma.wcid;
+	info->wdma_idx = path->mtk_wdma.wdma_idx;
+	info->queue = path->mtk_wdma.queue;
+	info->bss = path->mtk_wdma.bss;
+	info->wcid = path->mtk_wdma.wcid;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 95839fd84dab..3f0e5e64de50 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/platform_device.h>
@@ -32,6 +33,7 @@
 #define MTK_STAR_SKB_ALIGNMENT			16
 #define MTK_STAR_HASHTABLE_MC_LIMIT		256
 #define MTK_STAR_HASHTABLE_SIZE_MAX		512
+#define MTK_STAR_DESC_NEEDED			(MAX_SKB_FRAGS + 4)
 
 /* Normally we'd use NET_IP_ALIGN but on arm64 its value is 0 and it doesn't
  * work for this controller.
@@ -129,6 +131,11 @@ static const char *const mtk_star_clk_names[] = { "core", "reg", "trans" };
 #define MTK_STAR_REG_INT_MASK			0x0054
 #define MTK_STAR_BIT_INT_MASK_FNRC		BIT(6)
 
+/* Delay-Macro Register */
+#define MTK_STAR_REG_TEST0			0x0058
+#define MTK_STAR_BIT_INV_RX_CLK			BIT(30)
+#define MTK_STAR_BIT_INV_TX_CLK			BIT(31)
+
 /* Misc. Config Register */
 #define MTK_STAR_REG_TEST1			0x005c
 #define MTK_STAR_BIT_TEST1_RST_HASH_MBIST	BIT(31)
@@ -149,6 +156,7 @@ static const char *const mtk_star_clk_names[] = { "core", "reg", "trans" };
 #define MTK_STAR_REG_MAC_CLK_CONF		0x00ac
 #define MTK_STAR_MSK_MAC_CLK_CONF		GENMASK(7, 0)
 #define MTK_STAR_BIT_CLK_DIV_10			0x0a
+#define MTK_STAR_BIT_CLK_DIV_50			0x32
 
 /* Counter registers. */
 #define MTK_STAR_REG_C_RXOKPKT			0x0100
@@ -181,9 +189,14 @@ static const char *const mtk_star_clk_names[] = { "core", "reg", "trans" };
 #define MTK_STAR_REG_C_RX_TWIST			0x0218
 
 /* Ethernet CFG Control */
-#define MTK_PERICFG_REG_NIC_CFG_CON		0x03c4
-#define MTK_PERICFG_MSK_NIC_CFG_CON_CFG_MII	GENMASK(3, 0)
-#define MTK_PERICFG_BIT_NIC_CFG_CON_RMII	BIT(0)
+#define MTK_PERICFG_REG_NIC_CFG0_CON		0x03c4
+#define MTK_PERICFG_REG_NIC_CFG1_CON		0x03c8
+#define MTK_PERICFG_REG_NIC_CFG_CON_V2		0x0c10
+#define MTK_PERICFG_REG_NIC_CFG_CON_CFG_INTF	GENMASK(3, 0)
+#define MTK_PERICFG_BIT_NIC_CFG_CON_MII		0
+#define MTK_PERICFG_BIT_NIC_CFG_CON_RMII	1
+#define MTK_PERICFG_BIT_NIC_CFG_CON_CLK		BIT(0)
+#define MTK_PERICFG_BIT_NIC_CFG_CON_CLK_V2	BIT(8)
 
 /* Represents the actual structure of descriptors used by the MAC. We can
  * reuse the same structure for both TX and RX - the layout is the same, only
@@ -216,7 +229,8 @@ struct mtk_star_ring_desc_data {
 	struct sk_buff *skb;
 };
 
-#define MTK_STAR_RING_NUM_DESCS			128
+#define MTK_STAR_RING_NUM_DESCS			512
+#define MTK_STAR_TX_THRESH			(MTK_STAR_RING_NUM_DESCS / 4)
 #define MTK_STAR_NUM_TX_DESCS			MTK_STAR_RING_NUM_DESCS
 #define MTK_STAR_NUM_RX_DESCS			MTK_STAR_RING_NUM_DESCS
 #define MTK_STAR_NUM_DESCS_TOTAL		(MTK_STAR_RING_NUM_DESCS * 2)
@@ -231,6 +245,11 @@ struct mtk_star_ring {
 	unsigned int tail;
 };
 
+struct mtk_star_compat {
+	int (*set_interface_mode)(struct net_device *ndev);
+	unsigned char bit_clk_div;
+};
+
 struct mtk_star_priv {
 	struct net_device *ndev;
 
@@ -246,7 +265,8 @@ struct mtk_star_priv {
 	struct mtk_star_ring rx_ring;
 
 	struct mii_bus *mii;
-	struct napi_struct napi;
+	struct napi_struct tx_napi;
+	struct napi_struct rx_napi;
 
 	struct device_node *phy_node;
 	phy_interface_t phy_intf;
@@ -255,6 +275,11 @@ struct mtk_star_priv {
 	int speed;
 	int duplex;
 	int pause;
+	bool rmii_rxc;
+	bool rx_inv;
+	bool tx_inv;
+
+	const struct mtk_star_compat *compat_data;
 
 	/* Protects against concurrent descriptor access. */
 	spinlock_t lock;
@@ -357,19 +382,16 @@ mtk_star_ring_push_head_tx(struct mtk_star_ring *ring,
 	mtk_star_ring_push_head(ring, desc_data, flags);
 }
 
-static unsigned int mtk_star_ring_num_used_descs(struct mtk_star_ring *ring)
+static unsigned int mtk_star_tx_ring_avail(struct mtk_star_ring *ring)
 {
-	return abs(ring->head - ring->tail);
-}
+	u32 avail;
 
-static bool mtk_star_ring_full(struct mtk_star_ring *ring)
-{
-	return mtk_star_ring_num_used_descs(ring) == MTK_STAR_RING_NUM_DESCS;
-}
+	if (ring->tail > ring->head)
+		avail = ring->tail - ring->head - 1;
+	else
+		avail = MTK_STAR_RING_NUM_DESCS - ring->head + ring->tail - 1;
 
-static bool mtk_star_ring_descs_available(struct mtk_star_ring *ring)
-{
-	return mtk_star_ring_num_used_descs(ring) > 0;
+	return avail;
 }
 
 static dma_addr_t mtk_star_dma_map_rx(struct mtk_star_priv *priv,
@@ -414,6 +436,36 @@ static void mtk_star_nic_disable_pd(struct mtk_star_priv *priv)
 			  MTK_STAR_BIT_MAC_CFG_NIC_PD);
 }
 
+static void mtk_star_enable_dma_irq(struct mtk_star_priv *priv,
+				    bool rx, bool tx)
+{
+	u32 value;
+
+	regmap_read(priv->regs, MTK_STAR_REG_INT_MASK, &value);
+
+	if (tx)
+		value &= ~MTK_STAR_BIT_INT_STS_TNTC;
+	if (rx)
+		value &= ~MTK_STAR_BIT_INT_STS_FNRC;
+
+	regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, value);
+}
+
+static void mtk_star_disable_dma_irq(struct mtk_star_priv *priv,
+				     bool rx, bool tx)
+{
+	u32 value;
+
+	regmap_read(priv->regs, MTK_STAR_REG_INT_MASK, &value);
+
+	if (tx)
+		value |= MTK_STAR_BIT_INT_STS_TNTC;
+	if (rx)
+		value |= MTK_STAR_BIT_INT_STS_FNRC;
+
+	regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, value);
+}
+
 /* Unmask the three interrupts we care about, mask all others. */
 static void mtk_star_intr_enable(struct mtk_star_priv *priv)
 {
@@ -429,20 +481,11 @@ static void mtk_star_intr_disable(struct mtk_star_priv *priv)
 	regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, ~0);
 }
 
-static unsigned int mtk_star_intr_read(struct mtk_star_priv *priv)
-{
-	unsigned int val;
-
-	regmap_read(priv->regs, MTK_STAR_REG_INT_STS, &val);
-
-	return val;
-}
-
 static unsigned int mtk_star_intr_ack_all(struct mtk_star_priv *priv)
 {
 	unsigned int val;
 
-	val = mtk_star_intr_read(priv);
+	regmap_read(priv->regs, MTK_STAR_REG_INT_STS, &val);
 	regmap_write(priv->regs, MTK_STAR_REG_INT_STS, val);
 
 	return val;
@@ -714,25 +757,44 @@ static void mtk_star_free_tx_skbs(struct mtk_star_priv *priv)
 	mtk_star_ring_free_skbs(priv, ring, mtk_star_dma_unmap_tx);
 }
 
-/* All processing for TX and RX happens in the napi poll callback.
- *
- * FIXME: The interrupt handling should be more fine-grained with each
- * interrupt enabled/disabled independently when needed. Unfortunatly this
- * turned out to impact the driver's stability and until we have something
- * working properly, we're disabling all interrupts during TX & RX processing
- * or when resetting the counter registers.
- */
+/**
+ * mtk_star_handle_irq - Interrupt Handler.
+ * @irq: interrupt number.
+ * @data: pointer to a network interface device structure.
+ * Description : this is the driver interrupt service routine.
+ * it mainly handles:
+ *  1. tx complete interrupt for frame transmission.
+ *  2. rx complete interrupt for frame reception.
+ *  3. MAC Management Counter interrupt to avoid counter overflow.
+ **/
 static irqreturn_t mtk_star_handle_irq(int irq, void *data)
 {
-	struct mtk_star_priv *priv;
-	struct net_device *ndev;
-
-	ndev = data;
-	priv = netdev_priv(ndev);
+	struct net_device *ndev = data;
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	unsigned int intr_status = mtk_star_intr_ack_all(priv);
+	bool rx, tx;
+
+	rx = (intr_status & MTK_STAR_BIT_INT_STS_FNRC) &&
+	     napi_schedule_prep(&priv->rx_napi);
+	tx = (intr_status & MTK_STAR_BIT_INT_STS_TNTC) &&
+	     napi_schedule_prep(&priv->tx_napi);
+
+	if (rx || tx) {
+		spin_lock(&priv->lock);
+		/* mask Rx and TX Complete interrupt */
+		mtk_star_disable_dma_irq(priv, rx, tx);
+		spin_unlock(&priv->lock);
+
+		if (rx)
+			__napi_schedule(&priv->rx_napi);
+		if (tx)
+			__napi_schedule(&priv->tx_napi);
+	}
 
-	if (netif_running(ndev)) {
-		mtk_star_intr_disable(priv);
-		napi_schedule(&priv->napi);
+	/* interrupt is triggered once any counters reach 0x8000000 */
+	if (intr_status & MTK_STAR_REG_INT_STS_MIB_CNT_TH) {
+		mtk_star_update_stats(priv);
+		mtk_star_reset_counters(priv);
 	}
 
 	return IRQ_HANDLED;
@@ -821,32 +883,26 @@ static void mtk_star_phy_config(struct mtk_star_priv *priv)
 	val <<= MTK_STAR_OFF_PHY_CTRL1_FORCE_SPD;
 
 	val |= MTK_STAR_BIT_PHY_CTRL1_AN_EN;
-	val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_RX;
-	val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_TX;
-	/* Only full-duplex supported for now. */
-	val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_DPX;
-
-	regmap_write(priv->regs, MTK_STAR_REG_PHY_CTRL1, val);
-
 	if (priv->pause) {
-		val = MTK_STAR_VAL_FC_CFG_SEND_PAUSE_TH_2K;
-		val <<= MTK_STAR_OFF_FC_CFG_SEND_PAUSE_TH;
-		val |= MTK_STAR_BIT_FC_CFG_UC_PAUSE_DIR;
+		val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_RX;
+		val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_TX;
+		val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_DPX;
 	} else {
-		val = 0;
+		val &= ~MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_RX;
+		val &= ~MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_TX;
+		val &= ~MTK_STAR_BIT_PHY_CTRL1_FORCE_DPX;
 	}
+	regmap_write(priv->regs, MTK_STAR_REG_PHY_CTRL1, val);
 
+	val = MTK_STAR_VAL_FC_CFG_SEND_PAUSE_TH_2K;
+	val <<= MTK_STAR_OFF_FC_CFG_SEND_PAUSE_TH;
+	val |= MTK_STAR_BIT_FC_CFG_UC_PAUSE_DIR;
 	regmap_update_bits(priv->regs, MTK_STAR_REG_FC_CFG,
 			   MTK_STAR_MSK_FC_CFG_SEND_PAUSE_TH |
 			   MTK_STAR_BIT_FC_CFG_UC_PAUSE_DIR, val);
 
-	if (priv->pause) {
-		val = MTK_STAR_VAL_EXT_CFG_SND_PAUSE_RLS_1K;
-		val <<= MTK_STAR_OFF_EXT_CFG_SND_PAUSE_RLS;
-	} else {
-		val = 0;
-	}
-
+	val = MTK_STAR_VAL_EXT_CFG_SND_PAUSE_RLS_1K;
+	val <<= MTK_STAR_OFF_EXT_CFG_SND_PAUSE_RLS;
 	regmap_update_bits(priv->regs, MTK_STAR_REG_EXT_CFG,
 			   MTK_STAR_MSK_EXT_CFG_SND_PAUSE_RLS, val);
 }
@@ -898,14 +954,7 @@ static void mtk_star_init_config(struct mtk_star_priv *priv)
 	regmap_write(priv->regs, MTK_STAR_REG_SYS_CONF, val);
 	regmap_update_bits(priv->regs, MTK_STAR_REG_MAC_CLK_CONF,
 			   MTK_STAR_MSK_MAC_CLK_CONF,
-			   MTK_STAR_BIT_CLK_DIV_10);
-}
-
-static void mtk_star_set_mode_rmii(struct mtk_star_priv *priv)
-{
-	regmap_update_bits(priv->pericfg, MTK_PERICFG_REG_NIC_CFG_CON,
-			   MTK_PERICFG_MSK_NIC_CFG_CON_CFG_MII,
-			   MTK_PERICFG_BIT_NIC_CFG_CON_RMII);
+			   priv->compat_data->bit_clk_div);
 }
 
 static int mtk_star_enable(struct net_device *ndev)
@@ -951,11 +1000,12 @@ static int mtk_star_enable(struct net_device *ndev)
 
 	/* Request the interrupt */
 	ret = request_irq(ndev->irq, mtk_star_handle_irq,
-			  IRQF_TRIGGER_FALLING, ndev->name, ndev);
+			  IRQF_TRIGGER_NONE, ndev->name, ndev);
 	if (ret)
 		goto err_free_skbs;
 
-	napi_enable(&priv->napi);
+	napi_enable(&priv->tx_napi);
+	napi_enable(&priv->rx_napi);
 
 	mtk_star_intr_ack_all(priv);
 	mtk_star_intr_enable(priv);
@@ -988,7 +1038,8 @@ static void mtk_star_disable(struct net_device *ndev)
 	struct mtk_star_priv *priv = netdev_priv(ndev);
 
 	netif_stop_queue(ndev);
-	napi_disable(&priv->napi);
+	napi_disable(&priv->tx_napi);
+	napi_disable(&priv->rx_napi);
 	mtk_star_intr_disable(priv);
 	mtk_star_dma_disable(priv);
 	mtk_star_intr_ack_all(priv);
@@ -1020,13 +1071,45 @@ static int mtk_star_netdev_ioctl(struct net_device *ndev,
 	return phy_mii_ioctl(ndev->phydev, req, cmd);
 }
 
-static int mtk_star_netdev_start_xmit(struct sk_buff *skb,
-				      struct net_device *ndev)
+static int __mtk_star_maybe_stop_tx(struct mtk_star_priv *priv, u16 size)
+{
+	netif_stop_queue(priv->ndev);
+
+	/* Might race with mtk_star_tx_poll, check again */
+	smp_mb();
+	if (likely(mtk_star_tx_ring_avail(&priv->tx_ring) < size))
+		return -EBUSY;
+
+	netif_start_queue(priv->ndev);
+
+	return 0;
+}
+
+static inline int mtk_star_maybe_stop_tx(struct mtk_star_priv *priv, u16 size)
+{
+	if (likely(mtk_star_tx_ring_avail(&priv->tx_ring) >= size))
+		return 0;
+
+	return __mtk_star_maybe_stop_tx(priv, size);
+}
+
+static netdev_tx_t mtk_star_netdev_start_xmit(struct sk_buff *skb,
+					      struct net_device *ndev)
 {
 	struct mtk_star_priv *priv = netdev_priv(ndev);
 	struct mtk_star_ring *ring = &priv->tx_ring;
 	struct device *dev = mtk_star_get_dev(priv);
 	struct mtk_star_ring_desc_data desc_data;
+	int nfrags = skb_shinfo(skb)->nr_frags;
+
+	if (unlikely(mtk_star_tx_ring_avail(ring) < nfrags + 1)) {
+		if (!netif_queue_stopped(ndev)) {
+			netif_stop_queue(ndev);
+			/* This is a hard error, log it. */
+			pr_err_ratelimited("Tx ring full when queue awake\n");
+		}
+		return NETDEV_TX_BUSY;
+	}
 
 	desc_data.dma_addr = mtk_star_dma_map_tx(priv, skb);
 	if (dma_mapping_error(dev, desc_data.dma_addr))
@@ -1034,17 +1117,11 @@ static int mtk_star_netdev_start_xmit(struct sk_buff *skb,
 
 	desc_data.skb = skb;
 	desc_data.len = skb->len;
-
-	spin_lock_bh(&priv->lock);
-
 	mtk_star_ring_push_head_tx(ring, &desc_data);
 
 	netdev_sent_queue(ndev, skb->len);
 
-	if (mtk_star_ring_full(ring))
-		netif_stop_queue(ndev);
-
-	spin_unlock_bh(&priv->lock);
+	mtk_star_maybe_stop_tx(priv, MTK_STAR_DESC_NEEDED);
 
 	mtk_star_dma_resume_tx(priv);
 
@@ -1076,31 +1153,40 @@ static int mtk_star_tx_complete_one(struct mtk_star_priv *priv)
 	return ret;
 }
 
-static void mtk_star_tx_complete_all(struct mtk_star_priv *priv)
+static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 {
+	struct mtk_star_priv *priv = container_of(napi, struct mtk_star_priv,
+						  tx_napi);
+	int ret = 0, pkts_compl = 0, bytes_compl = 0, count = 0;
 	struct mtk_star_ring *ring = &priv->tx_ring;
 	struct net_device *ndev = priv->ndev;
-	int ret, pkts_compl, bytes_compl;
-	bool wake = false;
-
-	spin_lock(&priv->lock);
-
-	for (pkts_compl = 0, bytes_compl = 0;;
-	     pkts_compl++, bytes_compl += ret, wake = true) {
-		if (!mtk_star_ring_descs_available(ring))
-			break;
+	unsigned int head = ring->head;
+	unsigned int entry = ring->tail;
 
+	while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
 		ret = mtk_star_tx_complete_one(priv);
 		if (ret < 0)
 			break;
+
+		count++;
+		pkts_compl++;
+		bytes_compl += ret;
+		entry = ring->tail;
 	}
 
 	netdev_completed_queue(ndev, pkts_compl, bytes_compl);
 
-	if (wake && netif_queue_stopped(ndev))
+	if (unlikely(netif_queue_stopped(ndev)) &&
+	    (mtk_star_tx_ring_avail(ring) > MTK_STAR_TX_THRESH))
 		netif_wake_queue(ndev);
 
-	spin_unlock(&priv->lock);
+	if (napi_complete(napi)) {
+		spin_lock(&priv->lock);
+		mtk_star_enable_dma_irq(priv, false, true);
+		spin_unlock(&priv->lock);
+	}
+
+	return 0;
 }
 
 static void mtk_star_netdev_get_stats64(struct net_device *ndev,
@@ -1180,7 +1266,7 @@ static const struct ethtool_ops mtk_star_ethtool_ops = {
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
-static int mtk_star_receive_packet(struct mtk_star_priv *priv)
+static int mtk_star_rx(struct mtk_star_priv *priv, int budget)
 {
 	struct mtk_star_ring *ring = &priv->rx_ring;
 	struct device *dev = mtk_star_get_dev(priv);
@@ -1188,107 +1274,85 @@ static int mtk_star_receive_packet(struct mtk_star_priv *priv)
 	struct net_device *ndev = priv->ndev;
 	struct sk_buff *curr_skb, *new_skb;
 	dma_addr_t new_dma_addr;
-	int ret;
+	int ret, count = 0;
 
-	spin_lock(&priv->lock);
-	ret = mtk_star_ring_pop_tail(ring, &desc_data);
-	spin_unlock(&priv->lock);
-	if (ret)
-		return -1;
+	while (count < budget) {
+		ret = mtk_star_ring_pop_tail(ring, &desc_data);
+		if (ret)
+			return -1;
 
-	curr_skb = desc_data.skb;
+		curr_skb = desc_data.skb;
 
-	if ((desc_data.flags & MTK_STAR_DESC_BIT_RX_CRCE) ||
-	    (desc_data.flags & MTK_STAR_DESC_BIT_RX_OSIZE)) {
-		/* Error packet -> drop and reuse skb. */
-		new_skb = curr_skb;
-		goto push_new_skb;
-	}
+		if ((desc_data.flags & MTK_STAR_DESC_BIT_RX_CRCE) ||
+		    (desc_data.flags & MTK_STAR_DESC_BIT_RX_OSIZE)) {
+			/* Error packet -> drop and reuse skb. */
+			new_skb = curr_skb;
+			goto push_new_skb;
+		}
 
-	/* Prepare new skb before receiving the current one. Reuse the current
-	 * skb if we fail at any point.
-	 */
-	new_skb = mtk_star_alloc_skb(ndev);
-	if (!new_skb) {
-		ndev->stats.rx_dropped++;
-		new_skb = curr_skb;
-		goto push_new_skb;
-	}
+		/* Prepare new skb before receiving the current one.
+		 * Reuse the current skb if we fail at any point.
+		 */
+		new_skb = mtk_star_alloc_skb(ndev);
+		if (!new_skb) {
+			ndev->stats.rx_dropped++;
+			new_skb = curr_skb;
+			goto push_new_skb;
+		}
 
-	new_dma_addr = mtk_star_dma_map_rx(priv, new_skb);
-	if (dma_mapping_error(dev, new_dma_addr)) {
-		ndev->stats.rx_dropped++;
-		dev_kfree_skb(new_skb);
-		new_skb = curr_skb;
-		netdev_err(ndev, "DMA mapping error of RX descriptor\n");
-		goto push_new_skb;
-	}
+		new_dma_addr = mtk_star_dma_map_rx(priv, new_skb);
+		if (dma_mapping_error(dev, new_dma_addr)) {
+			ndev->stats.rx_dropped++;
+			dev_kfree_skb(new_skb);
+			new_skb = curr_skb;
+			netdev_err(ndev, "DMA mapping error of RX descriptor\n");
+			goto push_new_skb;
+		}
 
-	/* We can't fail anymore at this point: it's safe to unmap the skb. */
-	mtk_star_dma_unmap_rx(priv, &desc_data);
+		/* We can't fail anymore at this point:
+		 * it's safe to unmap the skb.
+		 */
+		mtk_star_dma_unmap_rx(priv, &desc_data);
 
-	skb_put(desc_data.skb, desc_data.len);
-	desc_data.skb->ip_summed = CHECKSUM_NONE;
-	desc_data.skb->protocol = eth_type_trans(desc_data.skb, ndev);
-	desc_data.skb->dev = ndev;
-	netif_receive_skb(desc_data.skb);
+		skb_put(desc_data.skb, desc_data.len);
+		desc_data.skb->ip_summed = CHECKSUM_NONE;
+		desc_data.skb->protocol = eth_type_trans(desc_data.skb, ndev);
+		desc_data.skb->dev = ndev;
+		netif_receive_skb(desc_data.skb);
 
-	/* update dma_addr for new skb */
-	desc_data.dma_addr = new_dma_addr;
+		/* update dma_addr for new skb */
+		desc_data.dma_addr = new_dma_addr;
 
 push_new_skb:
-	desc_data.len = skb_tailroom(new_skb);
-	desc_data.skb = new_skb;
 
-	spin_lock(&priv->lock);
-	mtk_star_ring_push_head_rx(ring, &desc_data);
-	spin_unlock(&priv->lock);
+		count++;
 
-	return 0;
-}
-
-static int mtk_star_process_rx(struct mtk_star_priv *priv, int budget)
-{
-	int received, ret;
-
-	for (received = 0, ret = 0; received < budget && ret == 0; received++)
-		ret = mtk_star_receive_packet(priv);
+		desc_data.len = skb_tailroom(new_skb);
+		desc_data.skb = new_skb;
+		mtk_star_ring_push_head_rx(ring, &desc_data);
+	}
 
 	mtk_star_dma_resume_rx(priv);
 
-	return received;
+	return count;
 }
 
-static int mtk_star_poll(struct napi_struct *napi, int budget)
+static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct mtk_star_priv *priv;
-	unsigned int status;
-	int received = 0;
-
-	priv = container_of(napi, struct mtk_star_priv, napi);
-
-	status = mtk_star_intr_read(priv);
-	mtk_star_intr_ack_all(priv);
+	int work_done = 0;
 
-	if (status & MTK_STAR_BIT_INT_STS_TNTC)
-		/* Clean-up all TX descriptors. */
-		mtk_star_tx_complete_all(priv);
+	priv = container_of(napi, struct mtk_star_priv, rx_napi);
 
-	if (status & MTK_STAR_BIT_INT_STS_FNRC)
-		/* Receive up to $budget packets. */
-		received = mtk_star_process_rx(priv, budget);
-
-	if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) {
-		mtk_star_update_stats(priv);
-		mtk_star_reset_counters(priv);
+	work_done = mtk_star_rx(priv, budget);
+	if (work_done < budget) {
+		napi_complete_done(napi, work_done);
+		spin_lock(&priv->lock);
+		mtk_star_enable_dma_irq(priv, true, false);
+		spin_unlock(&priv->lock);
 	}
 
-	if (received < budget)
-		napi_complete_done(napi, received);
-
-	mtk_star_intr_enable(priv);
-
-	return received;
+	return work_done;
 }
 
 static void mtk_star_mdio_rwok_clear(struct mtk_star_priv *priv)
@@ -1442,6 +1506,25 @@ static void mtk_star_clk_disable_unprepare(void *data)
 	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 }
 
+static int mtk_star_set_timing(struct mtk_star_priv *priv)
+{
+	struct device *dev = mtk_star_get_dev(priv);
+	unsigned int delay_val = 0;
+
+	switch (priv->phy_intf) {
+	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_RMII:
+		delay_val |= FIELD_PREP(MTK_STAR_BIT_INV_RX_CLK, priv->rx_inv);
+		delay_val |= FIELD_PREP(MTK_STAR_BIT_INV_TX_CLK, priv->tx_inv);
+		break;
+	default:
+		dev_err(dev, "This interface not supported\n");
+		return -EINVAL;
+	}
+
+	return regmap_write(priv->regs, MTK_STAR_REG_TEST0, delay_val);
+}
+
 static int mtk_star_probe(struct platform_device *pdev)
 {
 	struct device_node *of_node;
@@ -1460,6 +1543,7 @@ static int mtk_star_probe(struct platform_device *pdev)
 
 	priv = netdev_priv(ndev);
 	priv->ndev = ndev;
+	priv->compat_data = of_device_get_match_data(&pdev->dev);
 	SET_NETDEV_DEV(ndev, dev);
 	platform_set_drvdata(pdev, ndev);
 
@@ -1510,7 +1594,8 @@ static int mtk_star_probe(struct platform_device *pdev)
 	ret = of_get_phy_mode(of_node, &priv->phy_intf);
 	if (ret) {
 		return ret;
-	} else if (priv->phy_intf != PHY_INTERFACE_MODE_RMII) {
+	} else if (priv->phy_intf != PHY_INTERFACE_MODE_RMII &&
+		   priv->phy_intf != PHY_INTERFACE_MODE_MII) {
 		dev_err(dev, "unsupported phy mode: %s\n",
 			phy_modes(priv->phy_intf));
 		return -EINVAL;
@@ -1522,7 +1607,23 @@ static int mtk_star_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	mtk_star_set_mode_rmii(priv);
+	priv->rmii_rxc = of_property_read_bool(of_node, "mediatek,rmii-rxc");
+	priv->rx_inv = of_property_read_bool(of_node, "mediatek,rxc-inverse");
+	priv->tx_inv = of_property_read_bool(of_node, "mediatek,txc-inverse");
+
+	if (priv->compat_data->set_interface_mode) {
+		ret = priv->compat_data->set_interface_mode(ndev);
+		if (ret) {
+			dev_err(dev, "Failed to set phy interface, err = %d\n", ret);
+			return -EINVAL;
+		}
+	}
+
+	ret = mtk_star_set_timing(priv);
+	if (ret) {
+		dev_err(dev, "Failed to set timing, err = %d\n", ret);
+		return -EINVAL;
+	}
 
 	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 	if (ret) {
@@ -1550,16 +1651,92 @@ static int mtk_star_probe(struct platform_device *pdev)
 	ndev->netdev_ops = &mtk_star_netdev_ops;
 	ndev->ethtool_ops = &mtk_star_ethtool_ops;
 
-	netif_napi_add(ndev, &priv->napi, mtk_star_poll, NAPI_POLL_WEIGHT);
+	netif_napi_add(ndev, &priv->rx_napi, mtk_star_rx_poll,
+		       NAPI_POLL_WEIGHT);
+	netif_napi_add_tx(ndev, &priv->tx_napi, mtk_star_tx_poll);
 
 	return devm_register_netdev(dev, ndev);
 }
 
 #ifdef CONFIG_OF
+static int mt8516_set_interface_mode(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct device *dev = mtk_star_get_dev(priv);
+	unsigned int intf_val, ret, rmii_rxc;
+
+	switch (priv->phy_intf) {
+	case PHY_INTERFACE_MODE_MII:
+		intf_val = MTK_PERICFG_BIT_NIC_CFG_CON_MII;
+		rmii_rxc = 0;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		intf_val = MTK_PERICFG_BIT_NIC_CFG_CON_RMII;
+		rmii_rxc = priv->rmii_rxc ? 0 : MTK_PERICFG_BIT_NIC_CFG_CON_CLK;
+		break;
+	default:
+		dev_err(dev, "This interface not supported\n");
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(priv->pericfg,
+				 MTK_PERICFG_REG_NIC_CFG1_CON,
+				 MTK_PERICFG_BIT_NIC_CFG_CON_CLK,
+				 rmii_rxc);
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(priv->pericfg,
+				  MTK_PERICFG_REG_NIC_CFG0_CON,
+				  MTK_PERICFG_REG_NIC_CFG_CON_CFG_INTF,
+				  intf_val);
+}
+
+static int mt8365_set_interface_mode(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct device *dev = mtk_star_get_dev(priv);
+	unsigned int intf_val;
+
+	switch (priv->phy_intf) {
+	case PHY_INTERFACE_MODE_MII:
+		intf_val = MTK_PERICFG_BIT_NIC_CFG_CON_MII;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		intf_val = MTK_PERICFG_BIT_NIC_CFG_CON_RMII;
+		intf_val |= priv->rmii_rxc ? 0 : MTK_PERICFG_BIT_NIC_CFG_CON_CLK_V2;
+		break;
+	default:
+		dev_err(dev, "This interface not supported\n");
+		return -EINVAL;
+	}
+
+	return regmap_update_bits(priv->pericfg,
+				  MTK_PERICFG_REG_NIC_CFG_CON_V2,
+				  MTK_PERICFG_REG_NIC_CFG_CON_CFG_INTF |
+				  MTK_PERICFG_BIT_NIC_CFG_CON_CLK_V2,
+				  intf_val);
+}
+
+static const struct mtk_star_compat mtk_star_mt8516_compat = {
+	.set_interface_mode = mt8516_set_interface_mode,
+	.bit_clk_div = MTK_STAR_BIT_CLK_DIV_10,
+};
+
+static const struct mtk_star_compat mtk_star_mt8365_compat = {
+	.set_interface_mode = mt8365_set_interface_mode,
+	.bit_clk_div = MTK_STAR_BIT_CLK_DIV_50,
+};
+
 static const struct of_device_id mtk_star_of_match[] = {
-	{ .compatible = "mediatek,mt8516-eth", },
-	{ .compatible = "mediatek,mt8518-eth", },
-	{ .compatible = "mediatek,mt8175-eth", },
+	{ .compatible = "mediatek,mt8516-eth",
+	  .data = &mtk_star_mt8516_compat },
+	{ .compatible = "mediatek,mt8518-eth",
+	  .data = &mtk_star_mt8516_compat },
+	{ .compatible = "mediatek,mt8175-eth",
+	  .data = &mtk_star_mt8516_compat },
+	{ .compatible = "mediatek,mt8365-eth",
+	  .data = &mtk_star_mt8365_compat },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mtk_star_of_match);