Message-Id: <1536567880-15097-3-git-send-email-ilias.apalodimas@linaro.org>
Date:   Mon, 10 Sep 2018 11:24:40 +0300
From:   Ilias Apalodimas <ilias.apalodimas@...aro.org>
To:     netdev@...r.kernel.org, jaswinder.singh@...aro.org
Cc:     ard.biesheuvel@...aro.org, masami.hiramatsu@...aro.org,
        arnd@...db.de, mykyta.iziumtsev@...aro.org, bjorn.topel@...el.com,
        magnus.karlsson@...el.com,
        Ilias Apalodimas <ilias.apalodimas@...aro.org>
Subject: [net-next, PATCH 2/2, v1] net: socionext: add AF_XDP support

Add basic AF_XDP support without zero-copy

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@...aro.org>
---
 drivers/net/ethernet/socionext/netsec.c | 211 ++++++++++++++++++++++++++++++--
 1 file changed, 202 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 666fee2..7464ca6 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -9,6 +9,8 @@
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 
 #include <net/tcp.h>
 #include <net/ip6_checksum.h>
@@ -238,6 +240,11 @@
 
 #define NETSEC_F_NETSEC_VER_MAJOR_NUM(x)	((x) & 0xffff0000)
 
+#define NETSEC_XDP_PASS          0
+#define NETSEC_XDP_CONSUMED      BIT(0)
+#define NETSEC_XDP_TX            BIT(1)
+#define NETSEC_XDP_REDIR         BIT(2)
+
 enum ring_id {
 	NETSEC_RING_TX = 0,
 	NETSEC_RING_RX
@@ -256,11 +263,13 @@ struct netsec_desc_ring {
 	void *vaddr;
 	u16 pkt_cnt;
 	u16 head, tail;
+	struct xdp_rxq_info xdp_rxq;
 };
 
 struct netsec_priv {
 	struct netsec_desc_ring desc_ring[NETSEC_RING_MAX];
 	struct ethtool_coalesce et_coalesce;
+	struct bpf_prog *xdp_prog;
 	spinlock_t reglock; /* protect reg access */
 	struct napi_struct napi;
 	phy_interface_t phy_interface;
@@ -297,6 +306,8 @@ struct netsec_rx_pkt_info {
 };
 
 static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num);
+static u32 netsec_run_xdp(struct netsec_desc *desc, struct netsec_priv *priv,
+			  struct bpf_prog *prog, u16 len);
 
 static void *netsec_alloc_rx_data(struct netsec_priv *priv,
 				  dma_addr_t *dma_addr, u16 *len);
@@ -613,13 +624,23 @@ static int netsec_clean_tx_dring(struct netsec_priv *priv, int budget)
 
 		eop = (entry->attr >> NETSEC_TX_LAST) & 1;
 
-		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
-				 DMA_TO_DEVICE);
-		if (eop) {
-			pkts++;
+		if (desc->skb) {
+			dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
+					 DMA_TO_DEVICE);
+		}
+
+		if (!eop) {
+			*desc = (struct netsec_desc){};
+			continue;
+		}
+
+		if (!desc->skb) {
+			skb_free_frag(desc->addr);
+		} else {
 			bytes += desc->skb->len;
 			dev_kfree_skb(desc->skb);
 		}
+		pkts++;
 		*desc = (struct netsec_desc){};
 	}
 	dring->pkt_cnt -= budget;
@@ -659,8 +680,11 @@ static void nsetsec_adv_desc(u16 *idx)
 static int netsec_process_rx(struct netsec_priv *priv, int budget)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+	struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
 	struct net_device *ndev = priv->ndev;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
+	u32 xdp_flush = 0;
+	u32 xdp_result;
 	int done = 0;
 
 	while (done < budget) {
@@ -707,6 +731,26 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		if (unlikely(!buf_addr))
 			break;
 
+		if (xdp_prog) {
+			xdp_result = netsec_run_xdp(desc, priv, xdp_prog,
+						    pkt_len);
+			if (xdp_result != NETSEC_XDP_PASS) {
+				xdp_flush |= xdp_result & NETSEC_XDP_REDIR;
+
+				dma_unmap_single_attrs(priv->dev,
+						       desc->dma_addr,
+						       desc->len, DMA_TO_DEVICE,
+						       DMA_ATTR_SKIP_CPU_SYNC);
+
+				desc->len = desc_len;
+				desc->dma_addr = dma_handle;
+				desc->addr = buf_addr;
+				netsec_rx_fill(priv, idx, 1);
+				nsetsec_adv_desc(&dring->tail);
+			}
+			continue;
+		}
+
 		skb = build_skb(desc->addr, desc->len);
 		if (unlikely(!skb)) {
 			dma_unmap_single(priv->dev, dma_handle, desc_len,
@@ -740,6 +784,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		nsetsec_adv_desc(&dring->tail);
 	}
 
+	if (xdp_flush & NETSEC_XDP_REDIR)
+		xdp_do_flush_map();
+
 	return done;
 }
 
@@ -892,6 +939,9 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 	if (!dring->vaddr || !dring->desc)
 		return;
 
+	if (xdp_rxq_info_is_reg(&dring->xdp_rxq))
+		xdp_rxq_info_unreg(&dring->xdp_rxq);
+
 	for (idx = 0; idx < DESC_NUM; idx++) {
 		desc = &dring->desc[idx];
 		if (!desc->addr)
@@ -994,7 +1044,7 @@ static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	int i;
+	int i, err;
 
 	for (i = 0; i < DESC_NUM; i++) {
 		struct netsec_desc *desc = &dring->desc[i];
@@ -1003,20 +1053,29 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 		u16 len;
 
 		buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
-		if (!buf) {
-			netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
+		if (!buf)
 			goto err_out;
-		}
 		desc->dma_addr = dma_handle;
 		desc->addr = buf;
 		desc->len = len;
 	}
 
 	netsec_rx_fill(priv, 0, DESC_NUM);
+	err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0);
+	if (err)
+		goto err_out;
+
+	err = xdp_rxq_info_reg_mem_model(&dring->xdp_rxq, MEM_TYPE_PAGE_SHARED,
+					 NULL);
+	if (err) {
+		xdp_rxq_info_unreg(&dring->xdp_rxq);
+		goto err_out;
+	}
 
 	return 0;
 
 err_out:
+	netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
 	return -ENOMEM;
 }
 
@@ -1353,6 +1412,9 @@ static int netsec_netdev_stop(struct net_device *ndev)
 
 	napi_disable(&priv->napi);
 
+	if (priv->xdp_prog)
+		bpf_prog_put(priv->xdp_prog);
+
 	netsec_write(priv, NETSEC_REG_INTEN_CLR, ~0);
 	netsec_stop_gmac(priv);
 
@@ -1420,6 +1482,136 @@ static int netsec_netdev_ioctl(struct net_device *ndev, struct ifreq *ifr,
 	return phy_mii_ioctl(ndev->phydev, ifr, cmd);
 }
 
+static u32 netsec_xmit_xdp(struct netsec_priv *priv, struct xdp_buff *xdp,
+			   struct netsec_desc *rx_desc)
+{
+	struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+	struct netsec_tx_pkt_ctrl tx_ctrl = {};
+	struct netsec_desc tx_desc;
+	int filled;
+	u32 len;
+
+	len = xdp->data_end - xdp->data;
+
+	if (tx_ring->head >= tx_ring->tail)
+		filled = tx_ring->head - tx_ring->tail;
+	else
+		filled = tx_ring->head + DESC_NUM - tx_ring->tail;
+
+	if (DESC_NUM - filled <= 1)
+		return NETSEC_XDP_CONSUMED;
+
+	dma_sync_single_for_device(priv->dev, rx_desc->dma_addr, len,
+				   DMA_TO_DEVICE);
+
+	tx_desc.dma_addr = rx_desc->dma_addr;
+	tx_desc.addr = xdp->data;
+	tx_desc.len = len;
+
+	netsec_set_tx_de(priv, tx_ring, &tx_ctrl, &tx_desc, NULL);
+	netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */
+
+	return NETSEC_XDP_TX;
+}
+
+static u32 netsec_run_xdp(struct netsec_desc *desc, struct netsec_priv *priv,
+			  struct bpf_prog *prog, u16 len)
+
+{
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+	struct xdp_buff xdp;
+	u32 ret = NETSEC_XDP_PASS;
+	int err;
+	u32 act;
+
+	xdp.data_hard_start = desc->addr;
+	xdp.data = desc->addr;
+	xdp_set_data_meta_invalid(&xdp);
+	xdp.data_end = xdp.data + len;
+	xdp.rxq = &dring->xdp_rxq;
+
+	rcu_read_lock();
+	act = bpf_prog_run_xdp(prog, &xdp);
+
+	switch (act) {
+	case XDP_PASS:
+		ret = NETSEC_XDP_PASS;
+		break;
+	case XDP_TX:
+		ret = netsec_xmit_xdp(priv, &xdp, desc);
+		break;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(priv->ndev, &xdp, prog);
+		if (!err) {
+			ret = NETSEC_XDP_REDIR;
+		} else {
+			ret = NETSEC_XDP_CONSUMED;
+			xdp_return_buff(&xdp);
+		}
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(priv->ndev, prog, act);
+		/* fall through -- handle aborts by dropping packet */
+	case XDP_DROP:
+		ret = NETSEC_XDP_CONSUMED;
+		break;
+	}
+
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int netsec_xdp_setup(struct netsec_priv *priv, struct bpf_prog *prog)
+{
+	struct net_device *dev = priv->ndev;
+	struct bpf_prog *old_prog;
+
+	/* For now just support only the usual MTU sized frames */
+	if (prog && dev->mtu > 1500) {
+		netdev_warn(dev, "Jumbo frames not yet supported with XDP\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (netif_running(dev))
+		netsec_netdev_stop(dev);
+
+	/* Detach old prog, if any */
+	old_prog = xchg(&priv->xdp_prog, prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (priv->xdp_prog) {
+		/* Attach BPF program */
+		priv->xdp_prog = bpf_prog_add(priv->xdp_prog, 1);
+		if (IS_ERR(priv->xdp_prog))
+			return PTR_ERR(priv->xdp_prog);
+	}
+
+	if (netif_running(dev))
+		netsec_netdev_open(dev);
+
+	return 0;
+}
+
+static int netsec_xdp(struct net_device *ndev, struct netdev_bpf *xdp)
+{
+	struct netsec_priv *priv = netdev_priv(ndev);
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return netsec_xdp_setup(priv, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops netsec_netdev_ops = {
 	.ndo_init		= netsec_netdev_init,
 	.ndo_uninit		= netsec_netdev_uninit,
@@ -1430,6 +1622,7 @@ static const struct net_device_ops netsec_netdev_ops = {
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= netsec_netdev_ioctl,
+	.ndo_bpf		= netsec_xdp,
 };
 
 static int netsec_of_probe(struct platform_device *pdev,
-- 
2.7.4

Powered by blists - more mailing lists