Merge branch 'cpsw-Add-XDP-support'

Ivan Khoronzhuk says:

====================
net: ethernet: ti: cpsw: Add XDP support

This patchset adds XDP support for TI cpsw driver and base it on
page_pool allocator. It was verified on af_xdp socket drop,
af_xdp l2f, ebpf XDP_DROP, XDP_REDIRECT, XDP_PASS, XDP_TX.

It was verified with following configs enabled:
CONFIG_JIT=y
CONFIG_BPFILTER=y
CONFIG_BPF_SYSCALL=y
CONFIG_XDP_SOCKETS=y
CONFIG_BPF_EVENTS=y
CONFIG_HAVE_EBPF_JIT=y
CONFIG_BPF_JIT=y
CONFIG_CGROUP_BPF=y

Link on previous v7:
https://lkml.org/lkml/2019/7/4/715

Also regular tests with iperf2 were done in order to verify impact on
regular netstack performance, compared with base commit:
https://pastebin.com/JSMT0iZ4

v8..v9:
- fix warnings on arm64 caused by typos in type casting

v7..v8:
- corrected dma calculation based on headroom instead of hard start
- minor comment changes

v6..v7:
- rolled back to v4 solution but with small modification
- picked up patch:
  https://www.spinics.net/lists/netdev/msg583145.html
- added changes related to netsec fix and cpsw

v5..v6:
- do changes that is rx_dev while redirect/flush cycle is kept the same
- dropped net: ethernet: ti: davinci_cpdma: return handler status
- other changes desc in patches

v4..v5:
- added two plreliminary patches:
  net: ethernet: ti: davinci_cpdma: allow desc split while down
  net: ethernet: ti: cpsw_ethtool: allow res split while down
- added xdp alocator refcnt on xdp level, avoiding page pool refcnt
- moved flush status as separate argument for cpdma_chan_process
- reworked cpsw code according to last changes to allocator
- added missed statistic counter

v3..v4:
- added page pool user counter
- use same pool for ndevs in dual mac
- restructured page pool create/destroy according to the last changes in API

v2..v3:
- each rxq and ndev has its own page pool

v1..v2:
- combined xdp_xmit functions
- used page allocation w/o refcnt juggle
- unmapped page for skb netstack
- moved rxq/page pool allocation to open/close pair
- added several preliminary patches:
  net: page_pool: add helper function to retrieve dma addresses
  net: page_pool: add helper function to unmap dma addresses
  net: ethernet: ti: cpsw: use cpsw as drv data
  net: ethernet: ti: cpsw_ethtool: simplify slave loops
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -577,8 +577,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		}
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 						 MEM_TYPE_PAGE_POOL, rq->page_pool);
-		if (err)
-			page_pool_free(rq->page_pool);
 	}
 	if (err)
 		goto err_free;
@@ -646,6 +644,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	if (rq->xdp_prog)
 		bpf_prog_put(rq->xdp_prog);
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
+	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
 
 	return err;
@@ -680,6 +679,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	}
 
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
+	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 

drivers/net/ethernet/socionext/netsec.c

@@ -1212,15 +1212,11 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 		}
 	}
 
-	/* Rx is currently using page_pool
-	 * since the pool is created during netsec_setup_rx_dring(), we need to
-	 * free the pool manually if the registration failed
-	 */
+	/* Rx is currently using page_pool */
 	if (id == NETSEC_RING_RX) {
 		if (xdp_rxq_info_is_reg(&dring->xdp_rxq))
 			xdp_rxq_info_unreg(&dring->xdp_rxq);
-		else
-			page_pool_free(dring->page_pool);
+		page_pool_destroy(dring->page_pool);
 	}
 
 	memset(dring->desc, 0, sizeof(struct netsec_desc) * DESC_NUM);

drivers/net/ethernet/ti/Kconfig

@@ -50,6 +50,7 @@ config TI_CPSW
 	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
 	select TI_DAVINCI_MDIO
 	select MFD_SYSCON
+	select PAGE_POOL
 	select REGMAP
 	---help---
 	  This driver supports TI's CPSW Ethernet Switch.

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 &&
@@ -426,43 +701,87 @@ 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);
+	new_page = page_pool_dev_alloc_pages(pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
+		ndev->stats.rx_dropped++;
+		goto requeue;
+	}
+
+	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;
+	}
+
+	/* 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);
-		priv = netdev_priv(ndev);
 	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++;
-		kmemleak_not_leak(new_skb);
-	} else {
-		ndev->stats.rx_dropped++;
-		new_skb = skb;
-	}
 
 requeue:
-	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);
+	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);
-		dev_kfree_skb_any(new_skb);
+		page_pool_recycle_direct(pool, new_page);
 	}
 }
 
@@ -1032,33 +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_idle_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",
@@ -1394,6 +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;
@@ -1422,9 +1754,10 @@ static int cpsw_ndo_open(struct net_device *ndev)
 err_cleanup:
 	if (!cpsw->usage_count) {
 		cpdma_ctlr_stop(cpsw->dma);
-		for_each_slave(priv, cpsw_slave_stop, cpsw);
+		cpsw_destroy_xdp_rxqs(cpsw);
 	}
 
+	for_each_slave(priv, cpsw_slave_stop, cpsw);
 	pm_runtime_put_sync(cpsw->dev);
 	netif_carrier_off(priv->ndev);
 	return ret;
@@ -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,

drivers/net/ethernet/ti/cpsw_ethtool.c

@@ -578,6 +578,18 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
 	return 0;
 }
 
+static void cpsw_fail(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev)
+			dev_close(ndev);
+	}
+}
+
 int cpsw_set_channels_common(struct net_device *ndev,
 			     struct ethtool_channels *chs,
 			     cpdma_handler_fn rx_handler)
@@ -585,7 +597,7 @@ int cpsw_set_channels_common(struct net_device *ndev,
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
 	struct net_device *sl_ndev;
-	int i, ret;
+	int i, new_pools, ret;
 
 	ret = cpsw_check_ch_settings(cpsw, chs);
 	if (ret < 0)
@@ -593,6 +605,8 @@ int cpsw_set_channels_common(struct net_device *ndev,
 
 	cpsw_suspend_data_pass(ndev);
 
+	new_pools = (chs->rx_count != cpsw->rx_ch_num) && cpsw->usage_count;
+
 	ret = cpsw_update_channels_res(priv, chs->rx_count, 1, rx_handler);
 	if (ret)
 		goto err;
@@ -620,15 +634,21 @@ int cpsw_set_channels_common(struct net_device *ndev,
 		}
 	}
 
-	if (cpsw->usage_count)
 	cpsw_split_res(cpsw);
 
+	if (new_pools) {
+		cpsw_destroy_xdp_rxqs(cpsw);
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret)
+			goto err;
+	}
+
 	ret = cpsw_resume_data_pass(ndev);
 	if (!ret)
 		return 0;
 err:
 	dev_err(priv->dev, "cannot update channels number, closing device\n");
-	dev_close(ndev);
+	cpsw_fail(cpsw);
 	return ret;
 }
 
@@ -648,9 +668,8 @@ void cpsw_get_ringparam(struct net_device *ndev,
 int cpsw_set_ringparam(struct net_device *ndev,
 		       struct ethtool_ringparam *ering)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int ret;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	int descs_num, ret;
 
 	/* ignore ering->tx_pending - only rx_pending adjustment is supported */
 
@@ -659,22 +678,34 @@ int cpsw_set_ringparam(struct net_device *ndev,
 	    ering->rx_pending > (cpsw->descs_pool_size - CPSW_MAX_QUEUES))
 		return -EINVAL;
 
-	if (ering->rx_pending == cpdma_get_num_rx_descs(cpsw->dma))
+	descs_num = cpdma_get_num_rx_descs(cpsw->dma);
+	if (ering->rx_pending == descs_num)
 		return 0;
 
 	cpsw_suspend_data_pass(ndev);
 
-	cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+	ret = cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+	if (ret) {
+		if (cpsw_resume_data_pass(ndev))
+			goto err;
+
+		return ret;
+	}
 
-	if (cpsw->usage_count)
-		cpdma_chan_split_pool(cpsw->dma);
+	if (cpsw->usage_count) {
+		cpsw_destroy_xdp_rxqs(cpsw);
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret)
+			goto err;
+	}
 
 	ret = cpsw_resume_data_pass(ndev);
 	if (!ret)
 		return 0;
-
+err:
+	cpdma_set_num_rx_descs(cpsw->dma, descs_num);
 	dev_err(cpsw->dev, "cannot set ring params, closing device\n");
-	dev_close(ndev);
+	cpsw_fail(cpsw);
 	return ret;
 }
 

drivers/net/ethernet/ti/cpsw_priv.h

@@ -346,6 +346,7 @@ struct cpsw_common {
 	int				rx_ch_num, tx_ch_num;
 	int				speed;
 	int				usage_count;
+	struct page_pool		*page_pool[CPSW_MAX_QUEUES];
 };
 
 struct cpsw_priv {
@@ -360,6 +361,10 @@ struct cpsw_priv {
 	int				shp_cfg_speed;
 	int				tx_ts_enabled;
 	int				rx_ts_enabled;
+	struct bpf_prog			*xdp_prog;
+	struct xdp_rxq_info		xdp_rxq[CPSW_MAX_QUEUES];
+	struct xdp_attachment_info	xdpi;
+
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -391,6 +396,8 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv);
 void cpsw_intr_enable(struct cpsw_common *cpsw);
 void cpsw_intr_disable(struct cpsw_common *cpsw);
 void cpsw_tx_handler(void *token, int len, int status);
+int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw);
+void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw);
 
 /* ethtool */
 u32 cpsw_get_msglevel(struct net_device *ndev);

drivers/net/ethernet/ti/davinci_cpdma.c

@@ -139,6 +139,7 @@ struct submit_info {
 	int directed;
 	void *token;
 	void *data;
+	int flags;
 	int len;
 };
 
@@ -184,6 +185,8 @@ static struct cpdma_control_info controls[] = {
 				 (directed << CPDMA_TO_PORT_SHIFT));	\
 	} while (0)
 
+#define CPDMA_DMA_EXT_MAP		BIT(16)
+
 static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr)
 {
 	struct cpdma_desc_pool *pool = ctlr->pool;
@@ -1015,6 +1018,7 @@ static int cpdma_chan_submit_si(struct submit_info *si)
 	struct cpdma_chan		*chan = si->chan;
 	struct cpdma_ctlr		*ctlr = chan->ctlr;
 	int				len = si->len;
+	int				swlen = len;
 	struct cpdma_desc __iomem	*desc;
 	dma_addr_t			buffer;
 	u32				mode;
@@ -1036,15 +1040,21 @@ static int cpdma_chan_submit_si(struct submit_info *si)
 		chan->stats.runt_transmit_buff++;
 	}
 
+	mode = CPDMA_DESC_OWNER | CPDMA_DESC_SOP | CPDMA_DESC_EOP;
+	cpdma_desc_to_port(chan, mode, si->directed);
+
+	if (si->flags & CPDMA_DMA_EXT_MAP) {
+		buffer = (dma_addr_t)si->data;
+		dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir);
+		swlen |= CPDMA_DMA_EXT_MAP;
+	} else {
 		buffer = dma_map_single(ctlr->dev, si->data, len, chan->dir);
 		ret = dma_mapping_error(ctlr->dev, buffer);
 		if (ret) {
 			cpdma_desc_free(ctlr->pool, desc, 1);
 			return -EINVAL;
 		}
-
-	mode = CPDMA_DESC_OWNER | CPDMA_DESC_SOP | CPDMA_DESC_EOP;
-	cpdma_desc_to_port(chan, mode, si->directed);
+	}
 
 	/* Relaxed IO accessors can be used here as there is read barrier
 	 * at the end of write sequence.
@@ -1055,7 +1065,7 @@ static int cpdma_chan_submit_si(struct submit_info *si)
 	writel_relaxed(mode | len, &desc->hw_mode);
 	writel_relaxed((uintptr_t)si->token, &desc->sw_token);
 	writel_relaxed(buffer, &desc->sw_buffer);
-	writel_relaxed(len, &desc->sw_len);
+	writel_relaxed(swlen, &desc->sw_len);
 	desc_read(desc, sw_len);
 
 	__cpdma_chan_submit(chan, desc);
@@ -1079,6 +1089,32 @@ int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
 	si.data = data;
 	si.len = len;
 	si.directed = directed;
+	si.flags = 0;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->state == CPDMA_STATE_TEARDOWN) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -EINVAL;
+	}
+
+	ret = cpdma_chan_submit_si(&si);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	return ret;
+}
+
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+				  dma_addr_t data, int len, int directed)
+{
+	struct submit_info si;
+	unsigned long flags;
+	int ret;
+
+	si.chan = chan;
+	si.token = token;
+	si.data = (void *)data;
+	si.len = len;
+	si.directed = directed;
+	si.flags = CPDMA_DMA_EXT_MAP;
 
 	spin_lock_irqsave(&chan->lock, flags);
 	if (chan->state == CPDMA_STATE_TEARDOWN) {
@@ -1103,6 +1139,32 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 	si.data = data;
 	si.len = len;
 	si.directed = directed;
+	si.flags = 0;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->state != CPDMA_STATE_ACTIVE) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -EINVAL;
+	}
+
+	ret = cpdma_chan_submit_si(&si);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	return ret;
+}
+
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+			     dma_addr_t data, int len, int directed)
+{
+	struct submit_info si;
+	unsigned long flags;
+	int ret;
+
+	si.chan = chan;
+	si.token = token;
+	si.data = (void *)data;
+	si.len = len;
+	si.directed = directed;
+	si.flags = CPDMA_DMA_EXT_MAP;
 
 	spin_lock_irqsave(&chan->lock, flags);
 	if (chan->state != CPDMA_STATE_ACTIVE) {
@@ -1140,10 +1202,17 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
 	uintptr_t			token;
 
 	token      = desc_read(desc, sw_token);
-	buff_dma   = desc_read(desc, sw_buffer);
 	origlen    = desc_read(desc, sw_len);
 
+	buff_dma   = desc_read(desc, sw_buffer);
+	if (origlen & CPDMA_DMA_EXT_MAP) {
+		origlen &= ~CPDMA_DMA_EXT_MAP;
+		dma_sync_single_for_cpu(ctlr->dev, buff_dma, origlen,
+					chan->dir);
+	} else {
 		dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+	}
+
 	cpdma_desc_free(pool, desc, 1);
 	(*chan->handler)((void *)token, outlen, status);
 }
@@ -1354,8 +1423,23 @@ int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr)
 	return ctlr->num_tx_desc;
 }
 
-void cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc)
+int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc)
 {
+	unsigned long flags;
+	int temp, ret;
+
+	spin_lock_irqsave(&ctlr->lock, flags);
+
+	temp = ctlr->num_rx_desc;
 	ctlr->num_rx_desc = num_rx_desc;
 	ctlr->num_tx_desc = ctlr->pool->num_desc - ctlr->num_rx_desc;
+	ret = cpdma_chan_split_pool(ctlr);
+	if (ret) {
+		ctlr->num_rx_desc = temp;
+		ctlr->num_tx_desc = ctlr->pool->num_desc - ctlr->num_rx_desc;
+	}
+
+	spin_unlock_irqrestore(&ctlr->lock, flags);
+
+	return ret;
 }

drivers/net/ethernet/ti/davinci_cpdma.h

@@ -77,8 +77,12 @@ int cpdma_chan_stop(struct cpdma_chan *chan);
 
 int cpdma_chan_get_stats(struct cpdma_chan *chan,
 			 struct cpdma_chan_stats *stats);
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+			     dma_addr_t data, int len, int directed);
 int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		      int len, int directed);
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+				  dma_addr_t data, int len, int directed);
 int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
 			   int len, int directed);
 int cpdma_chan_process(struct cpdma_chan *chan, int quota);
@@ -112,8 +116,7 @@ enum cpdma_control {
 int cpdma_control_get(struct cpdma_ctlr *ctlr, int control);
 int cpdma_control_set(struct cpdma_ctlr *ctlr, int control, int value);
 int cpdma_get_num_rx_descs(struct cpdma_ctlr *ctlr);
-void cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc);
+int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc);
 int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr);
-int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr);
 
 #endif

include/net/page_pool.h

@@ -101,6 +101,12 @@ struct page_pool {
 	struct ptr_ring ring;
 
 	atomic_t pages_state_release_cnt;
+
+	/* A page_pool is strictly tied to a single RX-queue being
+	 * protected by NAPI, due to above pp_alloc_cache. This
+	 * refcnt serves purpose is to simplify drivers error handling.
+	 */
+	refcount_t user_cnt;
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
@@ -134,6 +140,15 @@ static inline void page_pool_free(struct page_pool *pool)
 #endif
 }
 
+/* Drivers use this instead of page_pool_free */
+static inline void page_pool_destroy(struct page_pool *pool)
+{
+	if (!pool)
+		return;
+
+	page_pool_free(pool);
+}
+
 /* Never call this directly, use helpers below */
 void __page_pool_put_page(struct page_pool *pool,
 			  struct page *page, bool allow_direct);
@@ -201,4 +216,14 @@ static inline bool is_page_pool_compiled_in(void)
 #endif
 }
 
+static inline void page_pool_get(struct page_pool *pool)
+{
+	refcount_inc(&pool->user_cnt);
+}
+
+static inline bool page_pool_put(struct page_pool *pool)
+{
+	return refcount_dec_and_test(&pool->user_cnt);
+}
+
 #endif /* _NET_PAGE_POOL_H */

net/core/page_pool.c

@@ -49,6 +49,9 @@ static int page_pool_init(struct page_pool *pool,
 
 	atomic_set(&pool->pages_state_release_cnt, 0);
 
+	/* Driver calling page_pool_create() also call page_pool_destroy() */
+	refcount_set(&pool->user_cnt, 1);
+
 	if (pool->p.flags & PP_FLAG_DMA_MAP)
 		get_device(pool->p.dev);
 
@@ -70,6 +73,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
 		kfree(pool);
 		return ERR_PTR(err);
 	}
+
 	return pool;
 }
 EXPORT_SYMBOL(page_pool_create);
@@ -356,6 +360,10 @@ static void __warn_in_flight(struct page_pool *pool)
 
 void __page_pool_free(struct page_pool *pool)
 {
+	/* Only last user actually free/release resources */
+	if (!page_pool_put(pool))
+		return;
+
 	WARN(pool->alloc.count, "API usage violation");
 	WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
 

net/core/xdp.c

@@ -370,6 +370,9 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 		goto err;
 	}
 
+	if (type == MEM_TYPE_PAGE_POOL)
+		page_pool_get(xdp_alloc->page_pool);
+
 	mutex_unlock(&mem_id_lock);
 
 	trace_mem_connect(xdp_alloc, xdp_rxq);