Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 472 insertions, 89 deletions

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 634fc484a0b3..f320f9a0de8b 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -31,6 +31,10 @@
 #include <linux/if_vlan.h>
 #include <linux/kmemleak.h>
 #include <linux/sys_soc.h>
+#include <net/page_pool.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
 
 #include <linux/pinctrl/consumer.h>
 #include <net/pkt_cls.h>
@@ -60,6 +64,10 @@ static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
 module_param(descs_pool_size, int, 0444);
 MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
 
+/* The buf includes headroom compatible with both skb and xdpf */
+#define CPSW_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define CPSW_HEADROOM  ALIGN(CPSW_HEADROOM_NA, sizeof(long))
+
 #define for_each_slave(priv, func, arg...)				\
 	do {								\
 		struct cpsw_slave *slave;				\
@@ -74,6 +82,11 @@ MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
 				(func)(slave++, ##arg);			\
 	} while (0)
 
+#define CPSW_XMETA_OFFSET	ALIGN(sizeof(struct xdp_frame), sizeof(long))
+
+#define CPSW_XDP_CONSUMED		1
+#define CPSW_XDP_PASS			0
+
 static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 				    __be16 proto, u16 vid);
 
@@ -337,24 +350,58 @@ void cpsw_intr_disable(struct cpsw_common *cpsw)
 	return;
 }
 
+static int cpsw_is_xdpf_handle(void *handle)
+{
+	return (unsigned long)handle & BIT(0);
+}
+
+static void *cpsw_xdpf_to_handle(struct xdp_frame *xdpf)
+{
+	return (void *)((unsigned long)xdpf | BIT(0));
+}
+
+static struct xdp_frame *cpsw_handle_to_xdpf(void *handle)
+{
+	return (struct xdp_frame *)((unsigned long)handle & ~BIT(0));
+}
+
+struct __aligned(sizeof(long)) cpsw_meta_xdp {
+	struct net_device *ndev;
+	int ch;
+};
+
 void cpsw_tx_handler(void *token, int len, int status)
 {
+	struct cpsw_meta_xdp	*xmeta;
+	struct xdp_frame	*xdpf;
+	struct net_device	*ndev;
 	struct netdev_queue	*txq;
-	struct sk_buff		*skb = token;
-	struct net_device	*ndev = skb->dev;
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct sk_buff		*skb;
+	int			ch;
+
+	if (cpsw_is_xdpf_handle(token)) {
+		xdpf = cpsw_handle_to_xdpf(token);
+		xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+		ndev = xmeta->ndev;
+		ch = xmeta->ch;
+		xdp_return_frame(xdpf);
+	} else {
+		skb = token;
+		ndev = skb->dev;
+		ch = skb_get_queue_mapping(skb);
+		cpts_tx_timestamp(ndev_to_cpsw(ndev)->cpts, skb);
+		dev_kfree_skb_any(skb);
+	}
 
 	/* Check whether the queue is stopped due to stalled tx dma, if the
 	 * queue is stopped then start the queue as we have free desc for tx
 	 */
-	txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
+	txq = netdev_get_tx_queue(ndev, ch);
 	if (unlikely(netif_tx_queue_stopped(txq)))
 		netif_tx_wake_queue(txq);
 
-	cpts_tx_timestamp(cpsw->cpts, skb);
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += len;
-	dev_kfree_skb_any(skb);
 }
 
 static void cpsw_rx_vlan_encap(struct sk_buff *skb)
@@ -400,24 +447,252 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
 	}
 }
 
+static int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf,
+			     struct page *page)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_meta_xdp *xmeta;
+	struct cpdma_chan *txch;
+	dma_addr_t dma;
+	int ret, port;
+
+	xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+	xmeta->ndev = priv->ndev;
+	xmeta->ch = 0;
+	txch = cpsw->txv[0].ch;
+
+	port = priv->emac_port + cpsw->data.dual_emac;
+	if (page) {
+		dma = page_pool_get_dma_addr(page);
+		dma += xdpf->headroom + sizeof(struct xdp_frame);
+		ret = cpdma_chan_submit_mapped(txch, cpsw_xdpf_to_handle(xdpf),
+					       dma, xdpf->len, port);
+	} else {
+		if (sizeof(*xmeta) > xdpf->headroom) {
+			xdp_return_frame_rx_napi(xdpf);
+			return -EINVAL;
+		}
+
+		ret = cpdma_chan_submit(txch, cpsw_xdpf_to_handle(xdpf),
+					xdpf->data, xdpf->len, port);
+	}
+
+	if (ret) {
+		priv->ndev->stats.tx_dropped++;
+		xdp_return_frame_rx_napi(xdpf);
+	}
+
+	return ret;
+}
+
+static int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
+			struct page *page)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct net_device *ndev = priv->ndev;
+	int ret = CPSW_XDP_CONSUMED;
+	struct xdp_frame *xdpf;
+	struct bpf_prog *prog;
+	u32 act;
+
+	rcu_read_lock();
+
+	prog = READ_ONCE(priv->xdp_prog);
+	if (!prog) {
+		ret = CPSW_XDP_PASS;
+		goto out;
+	}
+
+	act = bpf_prog_run_xdp(prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		ret = CPSW_XDP_PASS;
+		break;
+	case XDP_TX:
+		xdpf = convert_to_xdp_frame(xdp);
+		if (unlikely(!xdpf))
+			goto drop;
+
+		cpsw_xdp_tx_frame(priv, xdpf, page);
+		break;
+	case XDP_REDIRECT:
+		if (xdp_do_redirect(ndev, xdp, prog))
+			goto drop;
+
+		/*  Have to flush here, per packet, instead of doing it in bulk
+		 *  at the end of the napi handler. The RX devices on this
+		 *  particular hardware is sharing a common queue, so the
+		 *  incoming device might change per packet.
+		 */
+		xdp_do_flush_map();
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(ndev, prog, act);
+		/* fall through -- handle aborts by dropping packet */
+	case XDP_DROP:
+		goto drop;
+	}
+out:
+	rcu_read_unlock();
+	return ret;
+drop:
+	rcu_read_unlock();
+	page_pool_recycle_direct(cpsw->page_pool[ch], page);
+	return ret;
+}
+
+static unsigned int cpsw_rxbuf_total_len(unsigned int len)
+{
+	len += CPSW_HEADROOM;
+	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	return SKB_DATA_ALIGN(len);
+}
+
+static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw,
+					       int size)
+{
+	struct page_pool_params pp_params;
+	struct page_pool *pool;
+
+	pp_params.order = 0;
+	pp_params.flags = PP_FLAG_DMA_MAP;
+	pp_params.pool_size = size;
+	pp_params.nid = NUMA_NO_NODE;
+	pp_params.dma_dir = DMA_BIDIRECTIONAL;
+	pp_params.dev = cpsw->dev;
+
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool))
+		dev_err(cpsw->dev, "cannot create rx page pool\n");
+
+	return pool;
+}
+
+static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct xdp_rxq_info *rxq;
+	struct page_pool *pool;
+	int ret;
+
+	pool = cpsw->page_pool[ch];
+	rxq = &priv->xdp_rxq[ch];
+
+	ret = xdp_rxq_info_reg(rxq, priv->ndev, ch);
+	if (ret)
+		return ret;
+
+	ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+	if (ret)
+		xdp_rxq_info_unreg(rxq);
+
+	return ret;
+}
+
+static void cpsw_ndev_destroy_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+	struct xdp_rxq_info *rxq = &priv->xdp_rxq[ch];
+
+	if (!xdp_rxq_info_is_reg(rxq))
+		return;
+
+	xdp_rxq_info_unreg(rxq);
+}
+
+static int cpsw_create_rx_pool(struct cpsw_common *cpsw, int ch)
+{
+	struct page_pool *pool;
+	int ret = 0, pool_size;
+
+	pool_size = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
+	pool = cpsw_create_page_pool(cpsw, pool_size);
+	if (IS_ERR(pool))
+		ret = PTR_ERR(pool);
+	else
+		cpsw->page_pool[ch] = pool;
+
+	return ret;
+}
+
+void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i, ch;
+
+	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		for (i = 0; i < cpsw->data.slaves; i++) {
+			ndev = cpsw->slaves[i].ndev;
+			if (!ndev)
+				continue;
+
+			cpsw_ndev_destroy_xdp_rxq(netdev_priv(ndev), ch);
+		}
+
+		page_pool_destroy(cpsw->page_pool[ch]);
+		cpsw->page_pool[ch] = NULL;
+	}
+}
+
+int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i, ch, ret;
+
+	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		ret = cpsw_create_rx_pool(cpsw, ch);
+		if (ret)
+			goto err_cleanup;
+
+		/* using same page pool is allowed as no running rx handlers
+		 * simultaneously for both ndevs
+		 */
+		for (i = 0; i < cpsw->data.slaves; i++) {
+			ndev = cpsw->slaves[i].ndev;
+			if (!ndev)
+				continue;
+
+			ret = cpsw_ndev_create_xdp_rxq(netdev_priv(ndev), ch);
+			if (ret)
+				goto err_cleanup;
+		}
+	}
+
+	return 0;
+
+err_cleanup:
+	cpsw_destroy_xdp_rxqs(cpsw);
+
+	return ret;
+}
+
 static void cpsw_rx_handler(void *token, int len, int status)
 {
-	struct cpdma_chan	*ch;
-	struct sk_buff		*skb = token;
-	struct sk_buff		*new_skb;
-	struct net_device	*ndev = skb->dev;
-	int			ret = 0, port;
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct page		*new_page, *page = token;
+	void			*pa = page_address(page);
+	struct cpsw_meta_xdp	*xmeta = pa + CPSW_XMETA_OFFSET;
+	struct cpsw_common	*cpsw = ndev_to_cpsw(xmeta->ndev);
+	int			pkt_size = cpsw->rx_packet_max;
+	int			ret = 0, port, ch = xmeta->ch;
+	int			headroom = CPSW_HEADROOM;
+	struct net_device	*ndev = xmeta->ndev;
 	struct cpsw_priv	*priv;
+	struct page_pool	*pool;
+	struct sk_buff		*skb;
+	struct xdp_buff		xdp;
+	dma_addr_t		dma;
 
-	if (cpsw->data.dual_emac) {
+	if (cpsw->data.dual_emac && status >= 0) {
 		port = CPDMA_RX_SOURCE_PORT(status);
-		if (port) {
+		if (port)
 			ndev = cpsw->slaves[--port].ndev;
-			skb->dev = ndev;
-		}
 	}
 
+	priv = netdev_priv(ndev);
+	pool = cpsw->page_pool[ch];
 	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
 		/* In dual emac mode check for all interfaces */
 		if (cpsw->data.dual_emac && cpsw->usage_count &&
@@ -426,47 +701,88 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			 * is already down and the other interface is up
 			 * and running, instead of freeing which results
 			 * in reducing of the number of rx descriptor in
-			 * DMA engine, requeue skb back to cpdma.
+			 * DMA engine, requeue page back to cpdma.
 			 */
-			new_skb = skb;
+			new_page = page;
 			goto requeue;
 		}
 
-		/* the interface is going down, skbs are purged */
-		dev_kfree_skb_any(skb);
+		/* the interface is going down, pages are purged */
+		page_pool_recycle_direct(pool, page);
 		return;
 	}
 
-	new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
-	if (new_skb) {
-		skb_copy_queue_mapping(new_skb, skb);
-		skb_put(skb, len);
-		if (status & CPDMA_RX_VLAN_ENCAP)
-			cpsw_rx_vlan_encap(skb);
-		priv = netdev_priv(ndev);
-		if (priv->rx_ts_enabled)
-			cpts_rx_timestamp(cpsw->cpts, skb);
-		skb->protocol = eth_type_trans(skb, ndev);
-		netif_receive_skb(skb);
-		ndev->stats.rx_bytes += len;
-		ndev->stats.rx_packets++;
-		kmemleak_not_leak(new_skb);
-	} else {
+	new_page = page_pool_dev_alloc_pages(pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
 		ndev->stats.rx_dropped++;
-		new_skb = skb;
+		goto requeue;
 	}
 
-requeue:
-	if (netif_dormant(ndev)) {
-		dev_kfree_skb_any(new_skb);
-		return;
+	if (priv->xdp_prog) {
+		if (status & CPDMA_RX_VLAN_ENCAP) {
+			xdp.data = pa + CPSW_HEADROOM +
+				   CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+			xdp.data_end = xdp.data + len -
+				       CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+		} else {
+			xdp.data = pa + CPSW_HEADROOM;
+			xdp.data_end = xdp.data + len;
+		}
+
+		xdp_set_data_meta_invalid(&xdp);
+
+		xdp.data_hard_start = pa;
+		xdp.rxq = &priv->xdp_rxq[ch];
+
+		ret = cpsw_run_xdp(priv, ch, &xdp, page);
+		if (ret != CPSW_XDP_PASS)
+			goto requeue;
+
+		/* XDP prog might have changed packet data and boundaries */
+		len = xdp.data_end - xdp.data;
+		headroom = xdp.data - xdp.data_hard_start;
+
+		/* XDP prog can modify vlan tag, so can't use encap header */
+		status &= ~CPDMA_RX_VLAN_ENCAP;
 	}
 
-	ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch;
-	ret = cpdma_chan_submit(ch, new_skb, new_skb->data,
-				skb_tailroom(new_skb), 0);
-	if (WARN_ON(ret < 0))
-		dev_kfree_skb_any(new_skb);
+	/* pass skb to netstack if no XDP prog or returned XDP_PASS */
+	skb = build_skb(pa, cpsw_rxbuf_total_len(pkt_size));
+	if (!skb) {
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(pool, page);
+		goto requeue;
+	}
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, len);
+	skb->dev = ndev;
+	if (status & CPDMA_RX_VLAN_ENCAP)
+		cpsw_rx_vlan_encap(skb);
+	if (priv->rx_ts_enabled)
+		cpts_rx_timestamp(cpsw->cpts, skb);
+	skb->protocol = eth_type_trans(skb, ndev);
+
+	/* unmap page as no netstack skb page recycling */
+	page_pool_release_page(pool, page);
+	netif_receive_skb(skb);
+
+	ndev->stats.rx_bytes += len;
+	ndev->stats.rx_packets++;
+
+requeue:
+	xmeta = page_address(new_page) + CPSW_XMETA_OFFSET;
+	xmeta->ndev = ndev;
+	xmeta->ch = ch;
+
+	dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+	ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
+				       pkt_size, 0);
+	if (ret < 0) {
+		WARN_ON(ret == -ENOMEM);
+		page_pool_recycle_direct(pool, new_page);
+	}
 }
 
 void cpsw_split_res(struct cpsw_common *cpsw)
@@ -1035,33 +1351,39 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
 int cpsw_fill_rx_channels(struct cpsw_priv *priv)
 {
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct sk_buff *skb;
+	struct cpsw_meta_xdp *xmeta;
+	struct page_pool *pool;
+	struct page *page;
 	int ch_buf_num;
 	int ch, i, ret;
+	dma_addr_t dma;
 
 	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		pool = cpsw->page_pool[ch];
 		ch_buf_num = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
 		for (i = 0; i < ch_buf_num; i++) {
-			skb = __netdev_alloc_skb_ip_align(priv->ndev,
-							  cpsw->rx_packet_max,
-							  GFP_KERNEL);
-			if (!skb) {
-				cpsw_err(priv, ifup, "cannot allocate skb\n");
+			page = page_pool_dev_alloc_pages(pool);
+			if (!page) {
+				cpsw_err(priv, ifup, "allocate rx page err\n");
 				return -ENOMEM;
 			}
 
-			skb_set_queue_mapping(skb, ch);
-			ret = cpdma_chan_submit(cpsw->rxv[ch].ch, skb,
-						skb->data, skb_tailroom(skb),
-						0);
+			xmeta = page_address(page) + CPSW_XMETA_OFFSET;
+			xmeta->ndev = priv->ndev;
+			xmeta->ch = ch;
+
+			dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM;
+			ret = cpdma_chan_idle_submit_mapped(cpsw->rxv[ch].ch,
+							    page, dma,
+							    cpsw->rx_packet_max,
+							    0);
 			if (ret < 0) {
 				cpsw_err(priv, ifup,
-					 "cannot submit skb to channel %d rx, error %d\n",
+					 "cannot submit page to channel %d rx, error %d\n",
 					 ch, ret);
-				kfree_skb(skb);
+				page_pool_recycle_direct(pool, page);
 				return ret;
 			}
-			kmemleak_not_leak(skb);
 		}
 
 		cpsw_info(priv, ifup, "ch %d rx, submitted %d descriptors\n",
@@ -1397,6 +1719,13 @@ static int cpsw_ndo_open(struct net_device *ndev)
 			enable_irq(cpsw->irqs_table[0]);
 		}
 
+		/* create rxqs for both infs in dual mac as they use same pool
+		 * and must be destroyed together when no users.
+		 */
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret < 0)
+			goto err_cleanup;
+
 		ret = cpsw_fill_rx_channels(priv);
 		if (ret < 0)
 			goto err_cleanup;
@@ -1423,7 +1752,11 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	return 0;
 
 err_cleanup:
-	cpdma_ctlr_stop(cpsw->dma);
+	if (!cpsw->usage_count) {
+		cpdma_ctlr_stop(cpsw->dma);
+		cpsw_destroy_xdp_rxqs(cpsw);
+	}
+
 	for_each_slave(priv, cpsw_slave_stop, cpsw);
 	pm_runtime_put_sync(cpsw->dev);
 	netif_carrier_off(priv->ndev);
@@ -1447,6 +1780,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 		cpsw_intr_disable(cpsw);
 		cpdma_ctlr_stop(cpsw->dma);
 		cpsw_ale_stop(cpsw->ale);
+		cpsw_destroy_xdp_rxqs(cpsw);
 	}
 	for_each_slave(priv, cpsw_slave_stop, cpsw);
 
@@ -2004,6 +2338,64 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf)
+{
+	struct bpf_prog *prog = bpf->prog;
+
+	if (!priv->xdpi.prog && !prog)
+		return 0;
+
+	if (!xdp_attachment_flags_ok(&priv->xdpi, bpf))
+		return -EBUSY;
+
+	WRITE_ONCE(priv->xdp_prog, prog);
+
+	xdp_attachment_setup(&priv->xdpi, bpf);
+
+	return 0;
+}
+
+static int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return cpsw_xdp_prog_setup(priv, bpf);
+
+	case XDP_QUERY_PROG:
+		return xdp_attachment_query(&priv->xdpi, bpf);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+			     struct xdp_frame **frames, u32 flags)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct xdp_frame *xdpf;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	for (i = 0; i < n; i++) {
+		xdpf = frames[i];
+		if (xdpf->len < CPSW_MIN_PACKET_SIZE) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+			continue;
+		}
+
+		if (cpsw_xdp_tx_frame(priv, xdpf, NULL))
+			drops++;
+	}
+
+	return n - drops;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void cpsw_ndo_poll_controller(struct net_device *ndev)
 {
@@ -2032,6 +2424,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
 	.ndo_setup_tc           = cpsw_ndo_setup_tc,
+	.ndo_bpf		= cpsw_ndo_bpf,
+	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
 };
 
 static void cpsw_get_drvinfo(struct net_device *ndev,
@@ -2179,6 +2573,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			return ret;
 		}
 
+		slave_data->slave_node = slave_node;
 		slave_data->phy_node = of_parse_phandle(slave_node,
 							"phy-handle", 0);
 		parp = of_get_property(slave_node, "phy_id", &lenp);
@@ -2262,8 +2657,7 @@ no_phy_slave:
 
 static void cpsw_remove_dt(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
 	struct cpsw_platform_data *data = &cpsw->data;
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *slave_node;
@@ -2330,6 +2724,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 
 	/* register the network device */
 	SET_NETDEV_DEV(ndev, cpsw->dev);
+	ndev->dev.of_node = cpsw->slaves[1].data->slave_node;
 	ret = register_netdev(ndev);
 	if (ret)
 		dev_err(cpsw->dev, "cpsw: error registering net device\n");
@@ -2474,7 +2869,7 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_cpts;
 	}
 
-	platform_set_drvdata(pdev, ndev);
+	platform_set_drvdata(pdev, cpsw);
 	priv = netdev_priv(ndev);
 	priv->cpsw = cpsw;
 	priv->ndev = ndev;
@@ -2507,6 +2902,7 @@ static int cpsw_probe(struct platform_device *pdev)
 
 	/* register the network device */
 	SET_NETDEV_DEV(ndev, dev);
+	ndev->dev.of_node = cpsw->slaves[0].data->slave_node;
 	ret = register_netdev(ndev);
 	if (ret) {
 		dev_err(dev, "error registering net device\n");
@@ -2567,9 +2963,8 @@ clean_runtime_disable_ret:
 
 static int cpsw_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	int ret;
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
+	int i, ret;
 
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
@@ -2577,9 +2972,9 @@ static int cpsw_remove(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (cpsw->data.dual_emac)
-		unregister_netdev(cpsw->slaves[1].ndev);
-	unregister_netdev(ndev);
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
+			unregister_netdev(cpsw->slaves[i].ndev);
 
 	cpts_release(cpsw->cpts);
 	cpdma_ctlr_destroy(cpsw->dma);
@@ -2592,20 +2987,13 @@ static int cpsw_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int cpsw_suspend(struct device *dev)
 {
-	struct net_device	*ndev = dev_get_drvdata(dev);
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
-
-	if (cpsw->data.dual_emac) {
-		int i;
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
 
-		for (i = 0; i < cpsw->data.slaves; i++) {
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_stop(cpsw->slaves[i].ndev);
-		}
-	} else {
-		if (netif_running(ndev))
-			cpsw_ndo_stop(ndev);
-	}
 
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
@@ -2615,25 +3003,20 @@ static int cpsw_suspend(struct device *dev)
 
 static int cpsw_resume(struct device *dev)
 {
-	struct net_device	*ndev = dev_get_drvdata(dev);
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
 
 	/* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */
 	rtnl_lock();
-	if (cpsw->data.dual_emac) {
-		int i;
 
-		for (i = 0; i < cpsw->data.slaves; i++) {
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_open(cpsw->slaves[i].ndev);
-		}
-	} else {
-		if (netif_running(ndev))
-			cpsw_ndo_open(ndev);
-	}
+
 	rtnl_unlock();
 
 	return 0;