[PATCH net-next 3/6] net: bcmgenet: add basic XDP support (PASS/DROP)

[Nicolai Buchwitz <nb@tipi-net.de>]

Add XDP program attachment via ndo_bpf and execute XDP programs in the
RX path. Supported actions:

  - XDP_PASS: build SKB from the (possibly modified) xdp_buff and pass
    to the network stack, handling xdp_adjust_head/tail correctly
  - XDP_DROP: return the page to page_pool, no SKB allocated
  - XDP_ABORTED: same as DROP with trace_xdp_exception

XDP_TX and XDP_REDIRECT are not yet supported and will return
XDP_ABORTED.

The XDP hook runs after the HW error checks but before SKB construction,
so dropped packets avoid all SKB allocation overhead.

Advertise NETDEV_XDP_ACT_BASIC in xdp_features.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 153 +++++++++++++++---
 .../net/ethernet/broadcom/genet/bcmgenet.h    |   4 +
 2 files changed, 133 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index dd70e5af2b1e..d43729fc2b1b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -35,6 +35,8 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/phy.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
 
 #include <linux/unaligned.h>
 
@@ -2274,6 +2276,53 @@ static int bcmgenet_rx_refill(struct bcmgenet_rx_ring *ring,
 	return 0;
 }
 
+static struct sk_buff *bcmgenet_xdp_build_skb(struct bcmgenet_rx_ring *ring,
+					      struct xdp_buff *xdp,
+					      struct page *rx_page)
+{
+	unsigned int metasize;
+	struct sk_buff *skb;
+
+	skb = napi_build_skb(xdp->data_hard_start, PAGE_SIZE);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_mark_for_recycle(skb);
+
+	metasize = xdp->data - xdp->data_meta;
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	__skb_put(skb, xdp->data_end - xdp->data);
+
+	if (metasize)
+		skb_metadata_set(skb, metasize);
+
+	return skb;
+}
+
+static unsigned int
+bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring, struct bpf_prog *prog,
+		 struct xdp_buff *xdp, struct page *rx_page)
+{
+	unsigned int act;
+
+	act = bpf_prog_run_xdp(prog, xdp);
+
+	switch (act) {
+	case XDP_PASS:
+		return XDP_PASS;
+	case XDP_DROP:
+		page_pool_put_full_page(ring->page_pool, rx_page, true);
+		return XDP_DROP;
+	default:
+		bpf_warn_invalid_xdp_action(ring->priv->dev, prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(ring->priv->dev, prog, act);
+		page_pool_put_full_page(ring->page_pool, rx_page, true);
+		return XDP_ABORTED;
+	}
+}
+
 /* bcmgenet_desc_rx - descriptor based rx process.
  * this could be called from bottom half, or from NAPI polling method.
  */
@@ -2283,6 +2332,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	struct bcmgenet_rx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = ring->priv;
 	struct net_device *dev = priv->dev;
+	struct bpf_prog *xdp_prog;
 	struct enet_cb *cb;
 	struct sk_buff *skb;
 	u32 dma_length_status;
@@ -2293,6 +2343,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	unsigned int p_index, mask;
 	unsigned int discards;
 
+	xdp_prog = READ_ONCE(priv->xdp_prog);
+
 	/* Clear status before servicing to reduce spurious interrupts */
 	mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
 	bcmgenet_intrl2_1_writel(priv, mask, INTRL2_CPU_CLEAR);
@@ -2345,12 +2397,6 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		hard_start = page_address(rx_page) + rx_off;
 		status = (struct status_64 *)hard_start;
 		dma_length_status = status->length_status;
-		if (dev->features & NETIF_F_RXCSUM) {
-			rx_csum = (__force __be16)(status->rx_csum & 0xffff);
-			if (rx_csum) {
-				/* defer csum setup to after skb is built */
-			}
-		}
 
 		/* DMA flags and length are still valid no matter how
 		 * we got the Receive Status Vector (64B RSB or register)
@@ -2409,26 +2455,52 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 			goto next;
 		} /* error packet */
 
-		/* Build SKB from the page - data starts at hard_start,
-		 * frame begins after RSB(64) + pad(2) = 66 bytes.
-		 */
-		skb = napi_build_skb(hard_start, PAGE_SIZE - GENET_XDP_HEADROOM);
-		if (unlikely(!skb)) {
-			BCMGENET_STATS64_INC(stats, dropped);
-			page_pool_put_full_page(ring->page_pool, rx_page,
-						true);
-			goto next;
-		}
-
-		skb_mark_for_recycle(skb);
+		/* XDP: frame data starts after RSB + pad */
+		if (xdp_prog) {
+			struct xdp_buff xdp;
+			unsigned int xdp_act;
+			int pkt_len;
+
+			pkt_len = len - GENET_RSB_PAD;
+			if (priv->crc_fwd_en)
+				pkt_len -= ETH_FCS_LEN;
+
+			xdp_init_buff(&xdp, PAGE_SIZE, &ring->xdp_rxq);
+			xdp_prepare_buff(&xdp, page_address(rx_page),
+					 GENET_RX_HEADROOM, pkt_len, false);
+
+			xdp_act = bcmgenet_run_xdp(ring, xdp_prog, &xdp,
+						   rx_page);
+			if (xdp_act != XDP_PASS)
+				goto next;
+
+			/* XDP_PASS: build SKB from (possibly modified) xdp */
+			skb = bcmgenet_xdp_build_skb(ring, &xdp, rx_page);
+			if (unlikely(!skb)) {
+				BCMGENET_STATS64_INC(stats, dropped);
+				page_pool_put_full_page(ring->page_pool,
+							rx_page, true);
+				goto next;
+			}
+		} else {
+			/* Build SKB from the page - data starts at
+			 * hard_start, frame begins after RSB(64) + pad(2).
+			 */
+			skb = napi_build_skb(hard_start,
+					     PAGE_SIZE - GENET_XDP_HEADROOM);
+			if (unlikely(!skb)) {
+				BCMGENET_STATS64_INC(stats, dropped);
+				page_pool_put_full_page(ring->page_pool,
+							rx_page, true);
+				goto next;
+			}
 
-		/* Reserve the RSB + pad, then set the data length */
-		skb_reserve(skb, GENET_RSB_PAD);
-		__skb_put(skb, len - GENET_RSB_PAD);
+			skb_mark_for_recycle(skb);
+			skb_reserve(skb, GENET_RSB_PAD);
+			__skb_put(skb, len - GENET_RSB_PAD);
 
-		if (priv->crc_fwd_en) {
-			skb_trim(skb, skb->len - ETH_FCS_LEN);
-			len -= ETH_FCS_LEN;
+			if (priv->crc_fwd_en)
+				skb_trim(skb, skb->len - ETH_FCS_LEN);
 		}
 
 		/* Set up checksum offload */
@@ -3750,6 +3822,37 @@ static int bcmgenet_change_carrier(struct net_device *dev, bool new_carrier)
 	return 0;
 }
 
+static int bcmgenet_xdp_setup(struct net_device *dev,
+			      struct netdev_bpf *xdp)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bpf_prog *old_prog;
+	struct bpf_prog *prog = xdp->prog;
+
+	if (prog && dev->mtu > PAGE_SIZE - GENET_RX_HEADROOM -
+	    SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) {
+		NL_SET_ERR_MSG_MOD(xdp->extack,
+				   "MTU too large for single-page XDP buffer");
+		return -EOPNOTSUPP;
+	}
+
+	old_prog = xchg(&priv->xdp_prog, prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	return 0;
+}
+
+static int bcmgenet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return bcmgenet_xdp_setup(dev, xdp);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_open		= bcmgenet_open,
 	.ndo_stop		= bcmgenet_close,
@@ -3761,6 +3864,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_set_features	= bcmgenet_set_features,
 	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
+	.ndo_bpf		= bcmgenet_xdp,
 };
 
 /* GENET hardware parameters/characteristics */
@@ -4063,6 +4167,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 			 NETIF_F_RXCSUM;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC;
 
 	netdev_sw_irq_coalesce_default_on(dev);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 82a6d29f481d..1459473ac1b0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -16,6 +16,7 @@
 #include <linux/dim.h>
 #include <linux/ethtool.h>
 #include <net/page_pool/helpers.h>
+#include <linux/bpf.h>
 #include <net/xdp.h>
 
 #include "../unimac.h"
@@ -671,6 +672,9 @@ struct bcmgenet_priv {
 	u8 sopass[SOPASS_MAX];
 
 	struct bcmgenet_mib_counters mib;
+
+	/* XDP */
+	struct bpf_prog *xdp_prog;
 };
 
 static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
-- 
2.51.0