[PATCH net-next v5 1/6] net: bcmgenet: convert RX path to page_pool

[PATCH net-next v5 1/6] net: bcmgenet: convert RX path to page_pool

[Nicolai Buchwitz]

Replace the per-packet __netdev_alloc_skb() + dma_map_single() in the
RX path with page_pool, which provides efficient page recycling and
DMA mapping management. This is a prerequisite for XDP support (which
requires stable page-backed buffers rather than SKB linear data).

Key changes:
- Create a page_pool per RX ring (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)
- bcmgenet_rx_refill() allocates pages via page_pool_alloc_pages()
- bcmgenet_desc_rx() builds SKBs from pages via napi_build_skb() with
  skb_mark_for_recycle() for automatic page_pool return
- Buffer layout reserves XDP_PACKET_HEADROOM (256 bytes) before the HW
  RSB (64 bytes) + alignment pad (2 bytes) for future XDP headroom

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 drivers/net/ethernet/broadcom/Kconfig         |   1 +
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 217 +++++++++++-------
 .../net/ethernet/broadcom/genet/bcmgenet.h    |   4 +
 3 files changed, 144 insertions(+), 78 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index cd7dddeb91dd..e3b9a5272406 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -78,6 +78,7 @@ config BCMGENET
 	select BCM7XXX_PHY
 	select MDIO_BCM_UNIMAC
 	select DIMLIB
+	select PAGE_POOL
 	select BROADCOM_PHY if ARCH_BCM2835
 	help
 	  This driver supports the built-in Ethernet MACs found in the
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 482a31e7b72b..f32acacadcf0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -52,6 +52,14 @@
 #define RX_BUF_LENGTH		2048
 #define SKB_ALIGNMENT		32
 
+/* Page pool RX buffer layout:
+ * XDP_PACKET_HEADROOM | RSB(64) + pad(2) | frame data | skb_shared_info
+ * The HW writes the 64B RSB + 2B alignment padding before the frame.
+ */
+#define GENET_XDP_HEADROOM	XDP_PACKET_HEADROOM
+#define GENET_RSB_PAD		(sizeof(struct status_64) + 2)
+#define GENET_RX_HEADROOM	(GENET_XDP_HEADROOM + GENET_RSB_PAD)
+
 /* Tx/Rx DMA register offset, skip 256 descriptors */
 #define WORDS_PER_BD(p)		(p->hw_params->words_per_bd)
 #define DMA_DESC_SIZE		(WORDS_PER_BD(priv) * sizeof(u32))
@@ -1895,21 +1903,13 @@ static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev,
 }
 
 /* Simple helper to free a receive control block's resources */
-static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev,
-					   struct enet_cb *cb)
+static void bcmgenet_free_rx_cb(struct enet_cb *cb,
+				struct page_pool *pool)
 {
-	struct sk_buff *skb;
-
-	skb = cb->skb;
-	cb->skb = NULL;
-
-	if (dma_unmap_addr(cb, dma_addr)) {
-		dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr),
-				 dma_unmap_len(cb, dma_len), DMA_FROM_DEVICE);
-		dma_unmap_addr_set(cb, dma_addr, 0);
+	if (cb->rx_page) {
+		page_pool_put_full_page(pool, cb->rx_page, false);
+		cb->rx_page = NULL;
 	}
-
-	return skb;
 }
 
 /* Unlocked version of the reclaim routine */
@@ -2248,46 +2248,30 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	goto out;
 }
 
-static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
-					  struct enet_cb *cb)
+static int bcmgenet_rx_refill(struct bcmgenet_rx_ring *ring,
+			      struct enet_cb *cb)
 {
-	struct device *kdev = &priv->pdev->dev;
-	struct sk_buff *skb;
-	struct sk_buff *rx_skb;
+	struct bcmgenet_priv *priv = ring->priv;
 	dma_addr_t mapping;
+	struct page *page;
 
-	/* Allocate a new Rx skb */
-	skb = __netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT,
-				 GFP_ATOMIC | __GFP_NOWARN);
-	if (!skb) {
+	page = page_pool_alloc_pages(ring->page_pool,
+				     GFP_ATOMIC | __GFP_NOWARN);
+	if (!page) {
 		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, priv->dev,
-			  "%s: Rx skb allocation failed\n", __func__);
-		return NULL;
-	}
-
-	/* DMA-map the new Rx skb */
-	mapping = dma_map_single(kdev, skb->data, priv->rx_buf_len,
-				 DMA_FROM_DEVICE);
-	if (dma_mapping_error(kdev, mapping)) {
-		priv->mib.rx_dma_failed++;
-		dev_kfree_skb_any(skb);
-		netif_err(priv, rx_err, priv->dev,
-			  "%s: Rx skb DMA mapping failed\n", __func__);
-		return NULL;
+			  "%s: Rx page allocation failed\n", __func__);
+		return -ENOMEM;
 	}
 
-	/* Grab the current Rx skb from the ring and DMA-unmap it */
-	rx_skb = bcmgenet_free_rx_cb(kdev, cb);
+	/* page_pool handles DMA mapping via PP_FLAG_DMA_MAP */
+	mapping = page_pool_get_dma_addr(page) + GENET_XDP_HEADROOM;
 
-	/* Put the new Rx skb on the ring */
-	cb->skb = skb;
-	dma_unmap_addr_set(cb, dma_addr, mapping);
-	dma_unmap_len_set(cb, dma_len, priv->rx_buf_len);
+	cb->rx_page = page;
+	cb->rx_page_offset = GENET_XDP_HEADROOM;
 	dmadesc_set_addr(priv, cb->bd_addr, mapping);
 
-	/* Return the current Rx skb to caller */
-	return rx_skb;
+	return 0;
 }
 
 /* bcmgenet_desc_rx - descriptor based rx process.
@@ -2339,25 +2323,28 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	while ((rxpktprocessed < rxpkttoprocess) &&
 	       (rxpktprocessed < budget)) {
 		struct status_64 *status;
+		struct page *rx_page;
+		unsigned int rx_off;
 		__be16 rx_csum;
+		void *hard_start;
 
 		cb = &priv->rx_cbs[ring->read_ptr];
-		skb = bcmgenet_rx_refill(priv, cb);
 
-		if (unlikely(!skb)) {
+		/* Save the received page before refilling */
+		rx_page = cb->rx_page;
+		rx_off = cb->rx_page_offset;
+
+		if (bcmgenet_rx_refill(ring, cb)) {
 			BCMGENET_STATS64_INC(stats, dropped);
 			goto next;
 		}
 
-		status = (struct status_64 *)skb->data;
+		page_pool_dma_sync_for_cpu(ring->page_pool, rx_page, 0,
+					   RX_BUF_LENGTH);
+
+		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) {
-				skb->csum = (__force __wsum)ntohs(rx_csum);
-				skb->ip_summed = CHECKSUM_COMPLETE;
-			}
-		}
 
 		/* DMA flags and length are still valid no matter how
 		 * we got the Receive Status Vector (64B RSB or register)
@@ -2373,7 +2360,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		if (unlikely(len > RX_BUF_LENGTH)) {
 			netif_err(priv, rx_status, dev, "oversized packet\n");
 			BCMGENET_STATS64_INC(stats, length_errors);
-			dev_kfree_skb_any(skb);
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
 			goto next;
 		}
 
@@ -2381,7 +2369,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
 			BCMGENET_STATS64_INC(stats, fragmented_errors);
-			dev_kfree_skb_any(skb);
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
 			goto next;
 		}
 
@@ -2409,24 +2398,48 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 						DMA_RX_RXER)) == DMA_RX_RXER)
 				u64_stats_inc(&stats->errors);
 			u64_stats_update_end(&stats->syncp);
-			dev_kfree_skb_any(skb);
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
 			goto next;
 		} /* error packet */
 
-		skb_put(skb, len);
+		/* 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;
+		}
 
-		/* remove RSB and hardware 2bytes added for IP alignment */
-		skb_pull(skb, 66);
-		len -= 66;
+		skb_mark_for_recycle(skb);
+
+		/* Reserve the RSB + pad, then set the data length */
+		skb_reserve(skb, GENET_RSB_PAD);
+		__skb_put(skb, len - GENET_RSB_PAD);
 
 		if (priv->crc_fwd_en) {
-			skb_trim(skb, len - ETH_FCS_LEN);
+			skb_trim(skb, skb->len - ETH_FCS_LEN);
 			len -= ETH_FCS_LEN;
 		}
 
+		/* Set up checksum offload */
+		if (dev->features & NETIF_F_RXCSUM) {
+			rx_csum = (__force __be16)(status->rx_csum & 0xffff);
+			if (rx_csum) {
+				skb->csum = (__force __wsum)ntohs(rx_csum);
+				skb->ip_summed = CHECKSUM_COMPLETE;
+			}
+		}
+
+		len = skb->len;
 		bytes_processed += len;
 
-		/*Finish setting up the received SKB and send it to the kernel*/
+		/* Finish setting up the received SKB and send it to the
+		 * kernel.
+		 */
 		skb->protocol = eth_type_trans(skb, priv->dev);
 
 		u64_stats_update_begin(&stats->syncp);
@@ -2495,12 +2508,11 @@ static void bcmgenet_dim_work(struct work_struct *work)
 	dim->state = DIM_START_MEASURE;
 }
 
-/* Assign skb to RX DMA descriptor. */
+/* Assign page_pool pages to RX DMA descriptors. */
 static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 				     struct bcmgenet_rx_ring *ring)
 {
 	struct enet_cb *cb;
-	struct sk_buff *skb;
 	int i;
 
 	netif_dbg(priv, hw, priv->dev, "%s\n", __func__);
@@ -2508,10 +2520,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 	/* loop here for each buffer needing assign */
 	for (i = 0; i < ring->size; i++) {
 		cb = ring->cbs + i;
-		skb = bcmgenet_rx_refill(priv, cb);
-		if (skb)
-			dev_consume_skb_any(skb);
-		if (!cb->skb)
+		if (bcmgenet_rx_refill(ring, cb))
 			return -ENOMEM;
 	}
 
@@ -2520,16 +2529,18 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 
 static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 {
-	struct sk_buff *skb;
+	struct bcmgenet_rx_ring *ring;
 	struct enet_cb *cb;
-	int i;
+	int q, i;
 
-	for (i = 0; i < priv->num_rx_bds; i++) {
-		cb = &priv->rx_cbs[i];
-
-		skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb);
-		if (skb)
-			dev_consume_skb_any(skb);
+	for (q = 0; q <= priv->hw_params->rx_queues; q++) {
+		ring = &priv->rx_rings[q];
+		if (!ring->page_pool)
+			continue;
+		for (i = 0; i < ring->size; i++) {
+			cb = ring->cbs + i;
+			bcmgenet_free_rx_cb(cb, ring->page_pool);
+		}
 	}
 }
 
@@ -2747,6 +2758,31 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	netif_napi_add_tx(priv->dev, &ring->napi, bcmgenet_tx_poll);
 }
 
+static int bcmgenet_rx_ring_create_pool(struct bcmgenet_priv *priv,
+					struct bcmgenet_rx_ring *ring)
+{
+	struct page_pool_params pp_params = {
+		.order = 0,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.pool_size = ring->size,
+		.nid = NUMA_NO_NODE,
+		.dev = &priv->pdev->dev,
+		.dma_dir = DMA_FROM_DEVICE,
+		.offset = GENET_XDP_HEADROOM,
+		.max_len = RX_BUF_LENGTH,
+	};
+	int err;
+
+	ring->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(ring->page_pool)) {
+		err = PTR_ERR(ring->page_pool);
+		ring->page_pool = NULL;
+		return err;
+	}
+
+	return 0;
+}
+
 /* Initialize a RDMA ring */
 static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 				 unsigned int index, unsigned int size,
@@ -2754,7 +2790,7 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 {
 	struct bcmgenet_rx_ring *ring = &priv->rx_rings[index];
 	u32 words_per_bd = WORDS_PER_BD(priv);
-	int ret;
+	int ret, i;
 
 	ring->priv = priv;
 	ring->index = index;
@@ -2765,10 +2801,19 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 	ring->cb_ptr = start_ptr;
 	ring->end_ptr = end_ptr - 1;
 
-	ret = bcmgenet_alloc_rx_buffers(priv, ring);
+	ret = bcmgenet_rx_ring_create_pool(priv, ring);
 	if (ret)
 		return ret;
 
+	ret = bcmgenet_alloc_rx_buffers(priv, ring);
+	if (ret) {
+		for (i = 0; i < ring->size; i++)
+			bcmgenet_free_rx_cb(ring->cbs + i, ring->page_pool);
+		page_pool_destroy(ring->page_pool);
+		ring->page_pool = NULL;
+		return ret;
+	}
+
 	bcmgenet_init_dim(ring, bcmgenet_dim_work);
 	bcmgenet_init_rx_coalesce(ring);
 
@@ -2961,6 +3006,20 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
 	}
 }
 
+static void bcmgenet_destroy_rx_page_pools(struct bcmgenet_priv *priv)
+{
+	struct bcmgenet_rx_ring *ring;
+	unsigned int i;
+
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
+		ring = &priv->rx_rings[i];
+		if (ring->page_pool) {
+			page_pool_destroy(ring->page_pool);
+			ring->page_pool = NULL;
+		}
+	}
+}
+
 /* Initialize Rx queues
  *
  * Queues 0-15 are priority queues. Hardware Filtering Block (HFB) can be
@@ -3032,6 +3091,7 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	}
 
 	bcmgenet_free_rx_buffers(priv);
+	bcmgenet_destroy_rx_page_pools(priv);
 	kfree(priv->rx_cbs);
 	kfree(priv->tx_cbs);
 }
@@ -3108,6 +3168,7 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 	if (ret) {
 		netdev_err(priv->dev, "failed to initialize Rx queues\n");
 		bcmgenet_free_rx_buffers(priv);
+		bcmgenet_destroy_rx_page_pools(priv);
 		kfree(priv->rx_cbs);
 		kfree(priv->tx_cbs);
 		return ret;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 9e4110c7fdf6..11a0ec563a89 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -15,6 +15,7 @@
 #include <linux/phy.h>
 #include <linux/dim.h>
 #include <linux/ethtool.h>
+#include <net/page_pool/helpers.h>
 
 #include "../unimac.h"
 
@@ -469,6 +470,8 @@ struct bcmgenet_rx_stats64 {
 
 struct enet_cb {
 	struct sk_buff      *skb;
+	struct page         *rx_page;
+	unsigned int        rx_page_offset;
 	void __iomem *bd_addr;
 	DEFINE_DMA_UNMAP_ADDR(dma_addr);
 	DEFINE_DMA_UNMAP_LEN(dma_len);
@@ -575,6 +578,7 @@ struct bcmgenet_rx_ring {
 	struct bcmgenet_net_dim dim;
 	u32		rx_max_coalesced_frames;
 	u32		rx_coalesce_usecs;
+	struct page_pool *page_pool;
 	struct bcmgenet_priv *priv;
 };
 
-- 
2.51.0

[PATCH net-next v5 2/6] net: bcmgenet: register xdp_rxq_info for each RX ring

[Nicolai Buchwitz]

Register an xdp_rxq_info per RX ring and associate it with the ring's
page_pool via MEM_TYPE_PAGE_POOL. This is required infrastructure for
XDP program execution: the XDP framework needs to know the memory model
backing each RX queue for correct page lifecycle management.

No functional change - XDP programs are not yet attached or executed.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 18 ++++++++++++++++++
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  2 ++
 2 files changed, 20 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f32acacadcf0..9f81192d9e31 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2780,7 +2780,23 @@ static int bcmgenet_rx_ring_create_pool(struct bcmgenet_priv *priv,
 		return err;
 	}
 
+	err = xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, ring->index, 0);
+	if (err)
+		goto err_free_pp;
+
+	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 ring->page_pool);
+	if (err)
+		goto err_unreg_rxq;
+
 	return 0;
+
+err_unreg_rxq:
+	xdp_rxq_info_unreg(&ring->xdp_rxq);
+err_free_pp:
+	page_pool_destroy(ring->page_pool);
+	ring->page_pool = NULL;
+	return err;
 }
 
 /* Initialize a RDMA ring */
@@ -2809,6 +2825,7 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 	if (ret) {
 		for (i = 0; i < ring->size; i++)
 			bcmgenet_free_rx_cb(ring->cbs + i, ring->page_pool);
+		xdp_rxq_info_unreg(&ring->xdp_rxq);
 		page_pool_destroy(ring->page_pool);
 		ring->page_pool = NULL;
 		return ret;
@@ -3014,6 +3031,7 @@ static void bcmgenet_destroy_rx_page_pools(struct bcmgenet_priv *priv)
 	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		if (ring->page_pool) {
+			xdp_rxq_info_unreg(&ring->xdp_rxq);
 			page_pool_destroy(ring->page_pool);
 			ring->page_pool = NULL;
 		}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 11a0ec563a89..82a6d29f481d 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 <net/xdp.h>
 
 #include "../unimac.h"
 
@@ -579,6 +580,7 @@ struct bcmgenet_rx_ring {
 	u32		rx_max_coalesced_frames;
 	u32		rx_coalesce_usecs;
 	struct page_pool *page_pool;
+	struct xdp_rxq_info xdp_rxq;
 	struct bcmgenet_priv *priv;
 };
 
-- 
2.51.0

[PATCH net-next v5 3/6] net: bcmgenet: add basic XDP support (PASS/DROP)

[Nicolai Buchwitz]

Add XDP program attachment via ndo_bpf and execute XDP programs in the
RX path. XDP_PASS builds an SKB from the xdp_buff (handling
xdp_adjust_head/tail), XDP_DROP returns the page to page_pool without
SKB allocation.

XDP_TX and XDP_REDIRECT are not yet supported and return XDP_ABORTED.

Advertise NETDEV_XDP_ACT_BASIC in xdp_features.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 150 +++++++++++++++---
 .../net/ethernet/broadcom/genet/bcmgenet.h    |   4 +
 2 files changed, 136 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9f81192d9e31..b45ba2c2857e 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 +2276,54 @@ 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 +2333,7 @@ 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 +2344,8 @@ 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);
@@ -2403,26 +2456,52 @@ 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, true);
+
+			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 */
@@ -3745,6 +3824,39 @@ 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) {
+		synchronize_net();
+		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,
@@ -3756,6 +3868,7 @@ 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 */
@@ -4058,6 +4171,7 @@ 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

Re: [PATCH net-next v5 3/6] net: bcmgenet: add basic XDP support (PASS/DROP)

[Jakub Kicinski]

On Sun, 29 Mar 2026 00:05:06 +0100 Nicolai Buchwitz wrote:
> @@ -2403,26 +2456,52 @@ 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, true);
> +
> +			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;
> +			}

The large branches here are quite unusual, normally drivers fully
prepare the xdp_buff and if there's no xdp prog attached act as
if there was one and it returned XDP_PASS. Saves LoC and therefore bugs.

>  
> -		/* 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 */

AI points out that :

  The status_64 structure is located at the start of the page
  before the frame data. Since this resides inside the XDP headroom, if an XDP
  program expands the header backwards (e.g., via bpf_xdp_adjust_head() or
  metadata via bpf_xdp_adjust_meta()), could it physically overwrite
  status->rx_csum?

  Since the driver reads status->rx_csum after executing the XDP program, it
  could risk reading garbage data if the headroom was used. Should the driver
  skip setting CHECKSUM_COMPLETE when an XDP program is loaded?

> @@ -3745,6 +3824,39 @@ 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) {
> +		synchronize_net();

Why? BPF prog gets freed after a RCU grace period I think?

> +		bpf_prog_put(old_prog);

Re: [PATCH net-next v5 3/6] net: bcmgenet: add basic XDP support (PASS/DROP)

[Nicolai Buchwitz]

On 2.4.2026 05:27, Jakub Kicinski wrote:
> On Sun, 29 Mar 2026 00:05:06 +0100 Nicolai Buchwitz wrote:
>> @@ -2403,26 +2456,52 @@ 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, true);
>> +
>> +			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;
>> +			}
> 
> The large branches here are quite unusual, normally drivers fully
> prepare the xdp_buff and if there's no xdp prog attached act as
> if there was one and it returned XDP_PASS. Saves LoC and therefore 
> bugs.

Agreed, will refactor to always prepare xdp_buff and use
bcmgenet_xdp_build_skb for both paths in v6.

> 
>> 
>> -		/* 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 */
> 
> AI points out that :
> 
>   The status_64 structure is located at the start of the page
>   before the frame data. Since this resides inside the XDP headroom, if 
> an XDP
>   program expands the header backwards (e.g., via bpf_xdp_adjust_head() 
> or
>   metadata via bpf_xdp_adjust_meta()), could it physically overwrite
>   status->rx_csum?
> 
>   Since the driver reads status->rx_csum after executing the XDP 
> program, it
>   could risk reading garbage data if the headroom was used. Should the 
> driver
>   skip setting CHECKSUM_COMPLETE when an XDP program is loaded?

Makes sense, status->rx_csum is read after XDP runs and an
adjust_head could overwrite the RSB. I'll save rx_csum before
running the XDP program rather than skipping CHECKSUM_COMPLETE
entirely, so XDP_PASS packets that weren't modified still benefit
from HW checksum offload.

> 
>> @@ -3745,6 +3824,39 @@ 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) {
>> +		synchronize_net();
> 
> Why? BPF prog gets freed after a RCU grace period I think?

You're right, bpf_prog_put handles this via call_rcu. Will remove
the synchronize_net().

> 
>> +		bpf_prog_put(old_prog);

Thanks
Nicolai

[PATCH net-next v5 4/6] net: bcmgenet: add XDP_TX support

[Nicolai Buchwitz]

Implement XDP_TX using ring 16 (DESC_INDEX), the hardware default
descriptor ring, dedicated to XDP TX for isolation from SKB TX queues.

Ring 16 gets 32 BDs carved from ring 0's allocation. TX completion is
piggybacked on RX NAPI poll since ring 16's INTRL2_1 bit collides with
RX ring 0, similar to how bnxt, ice, and other XDP drivers handle TX
completion within the RX poll path.

The GENET MAC has TBUF_64B_EN set globally, requiring every TX buffer
to start with a 64-byte struct status_64 (TSB). For local XDP_TX, the
TSB is prepended by backing xdp->data into the RSB area (unused after
BPF execution) and zeroing it. For foreign frames redirected from other
devices, the TSB is written into the xdp_frame headroom.

The page_pool DMA direction is changed from DMA_FROM_DEVICE to
DMA_BIDIRECTIONAL to allow TX reuse of the existing DMA mapping.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 224 ++++++++++++++++--
 .../net/ethernet/broadcom/genet/bcmgenet.h    |   3 +
 2 files changed, 205 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b45ba2c2857e..687c3b12d44f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -48,8 +48,10 @@
 
 #define GENET_Q0_RX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->rx_queues * priv->hw_params->rx_bds_per_q)
+#define GENET_Q16_TX_BD_CNT	32
 #define GENET_Q0_TX_BD_CNT	\
-	(TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->tx_bds_per_q)
+	(TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->tx_bds_per_q \
+	 - GENET_Q16_TX_BD_CNT)
 
 #define RX_BUF_LENGTH		2048
 #define SKB_ALIGNMENT		32
@@ -1893,6 +1895,14 @@ static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev,
 		if (cb == GENET_CB(skb)->last_cb)
 			return skb;
 
+	} else if (cb->xdpf) {
+		if (cb->xdp_dma_map)
+			dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr),
+					 dma_unmap_len(cb, dma_len),
+					 DMA_TO_DEVICE);
+		dma_unmap_addr_set(cb, dma_addr, 0);
+		xdp_return_frame(cb->xdpf);
+		cb->xdpf = NULL;
 	} else if (dma_unmap_addr(cb, dma_addr)) {
 		dma_unmap_page(dev,
 			       dma_unmap_addr(cb, dma_addr),
@@ -1925,10 +1935,16 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	unsigned int pkts_compl = 0;
 	unsigned int txbds_ready;
 	unsigned int c_index;
+	struct enet_cb *tx_cb;
 	struct sk_buff *skb;
 
-	/* Clear status before servicing to reduce spurious interrupts */
-	bcmgenet_intrl2_1_writel(priv, (1 << ring->index), INTRL2_CPU_CLEAR);
+	/* Clear status before servicing to reduce spurious interrupts.
+	 * Ring DESC_INDEX (XDP TX) has no interrupt; skip the clear to
+	 * avoid clobbering RX ring 0's bit at the same position.
+	 */
+	if (ring->index != DESC_INDEX)
+		bcmgenet_intrl2_1_writel(priv, BIT(ring->index),
+					 INTRL2_CPU_CLEAR);
 
 	/* Compute how many buffers are transmitted since last xmit call */
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
@@ -1941,8 +1957,15 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 
 	/* Reclaim transmitted buffers */
 	while (txbds_processed < txbds_ready) {
-		skb = bcmgenet_free_tx_cb(&priv->pdev->dev,
-					  &priv->tx_cbs[ring->clean_ptr]);
+		tx_cb = &priv->tx_cbs[ring->clean_ptr];
+		if (tx_cb->xdpf) {
+			pkts_compl++;
+			bytes_compl += tx_cb->xdp_dma_map
+				? tx_cb->xdpf->len
+				: tx_cb->xdpf->len -
+				  sizeof(struct status_64);
+		}
+		skb = bcmgenet_free_tx_cb(&priv->pdev->dev, tx_cb);
 		if (skb) {
 			pkts_compl++;
 			bytes_compl += GENET_CB(skb)->bytes_sent;
@@ -1964,8 +1987,11 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	u64_stats_add(&stats->bytes, bytes_compl);
 	u64_stats_update_end(&stats->syncp);
 
-	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->index),
-				  pkts_compl, bytes_compl);
+	/* Ring DESC_INDEX (XDP TX) has no netdev TX queue; skip BQL */
+	if (ring->index != DESC_INDEX)
+		netdev_tx_completed_queue(netdev_get_tx_queue(dev,
+							      ring->index),
+					  pkts_compl, bytes_compl);
 
 	return txbds_processed;
 }
@@ -2042,6 +2068,9 @@ static void bcmgenet_tx_reclaim_all(struct net_device *dev)
 	do {
 		bcmgenet_tx_reclaim(dev, &priv->tx_rings[i++], true);
 	} while (i <= priv->hw_params->tx_queues && netif_is_multiqueue(dev));
+
+	/* Also reclaim XDP TX ring */
+	bcmgenet_tx_reclaim(dev, &priv->xdp_tx_ring, true);
 }
 
 /* Reallocate the SKB to put enough headroom in front of it and insert
@@ -2299,11 +2328,96 @@ static struct sk_buff *bcmgenet_xdp_build_skb(struct bcmgenet_rx_ring *ring,
 	return skb;
 }
 
+static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
+				     struct xdp_frame *xdpf, bool dma_map)
+{
+	struct bcmgenet_tx_ring *ring = &priv->xdp_tx_ring;
+	struct device *kdev = &priv->pdev->dev;
+	struct enet_cb *tx_cb_ptr;
+	dma_addr_t mapping;
+	unsigned int dma_len;
+	u32 len_stat;
+
+	spin_lock(&ring->lock);
+
+	if (ring->free_bds < 1) {
+		spin_unlock(&ring->lock);
+		return false;
+	}
+
+	tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
+
+	if (dma_map) {
+		void *tsb_start;
+
+		/* The GENET MAC has TBUF_64B_EN set globally, so hardware
+		 * expects a 64-byte TSB prefix on every TX buffer.  For
+		 * redirected frames (ndo_xdp_xmit) we prepend a zeroed TSB
+		 * using the frame's headroom.
+		 */
+		if (unlikely(xdpf->headroom < sizeof(struct status_64))) {
+			bcmgenet_put_txcb(priv, ring);
+			spin_unlock(&ring->lock);
+			return false;
+		}
+
+		tsb_start = xdpf->data - sizeof(struct status_64);
+		memset(tsb_start, 0, sizeof(struct status_64));
+
+		dma_len = xdpf->len + sizeof(struct status_64);
+		mapping = dma_map_single(kdev, tsb_start, dma_len,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(kdev, mapping)) {
+			tx_cb_ptr->skb = NULL;
+			tx_cb_ptr->xdpf = NULL;
+			bcmgenet_put_txcb(priv, ring);
+			spin_unlock(&ring->lock);
+			return false;
+		}
+	} else {
+		struct page *page = virt_to_page(xdpf->data);
+
+		/* For local XDP_TX the caller already prepended the TSB
+		 * into xdpf->data/len, so dma_len == xdpf->len.
+		 */
+		dma_len = xdpf->len;
+		mapping = page_pool_get_dma_addr(page) +
+			  sizeof(*xdpf) + xdpf->headroom;
+		dma_sync_single_for_device(kdev, mapping, dma_len,
+					   DMA_BIDIRECTIONAL);
+	}
+
+	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, dma_len);
+	tx_cb_ptr->skb = NULL;
+	tx_cb_ptr->xdpf = xdpf;
+	tx_cb_ptr->xdp_dma_map = dma_map;
+
+	len_stat = (dma_len << DMA_BUFLENGTH_SHIFT) |
+		   (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
+		   DMA_TX_APPEND_CRC | DMA_SOP | DMA_EOP;
+
+	dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, len_stat);
+
+	ring->free_bds--;
+	ring->prod_index++;
+	ring->prod_index &= DMA_P_INDEX_MASK;
+
+	bcmgenet_tdma_ring_writel(priv, ring->index, ring->prod_index,
+				  TDMA_PROD_INDEX);
+
+	spin_unlock(&ring->lock);
+
+	return true;
+}
+
 static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 				     struct bpf_prog *prog,
 				     struct xdp_buff *xdp,
 				     struct page *rx_page)
 {
+	struct bcmgenet_priv *priv = ring->priv;
+	struct xdp_frame *xdpf;
 	unsigned int act;
 
 	act = bpf_prog_run_xdp(prog, xdp);
@@ -2311,14 +2425,42 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 	switch (act) {
 	case XDP_PASS:
 		return XDP_PASS;
+	case XDP_TX:
+		/* Prepend a zeroed TSB (Transmit Status Block).  The GENET
+		 * MAC has TBUF_64B_EN set globally, so hardware expects every
+		 * TX buffer to begin with a 64-byte struct status_64.  Back
+		 * up xdp->data into the RSB area (which is no longer needed
+		 * after the BPF program ran) and zero it.
+		 */
+		if (xdp->data - xdp->data_hard_start <
+		    sizeof(struct status_64)) {
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
+			return XDP_DROP;
+		}
+		xdp->data -= sizeof(struct status_64);
+		xdp->data_meta -= sizeof(struct status_64);
+		memset(xdp->data, 0, sizeof(struct status_64));
+
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf)) {
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
+			return XDP_DROP;
+		}
+		if (unlikely(!bcmgenet_xdp_xmit_frame(priv, xdpf, false))) {
+			xdp_return_frame_rx_napi(xdpf);
+			return XDP_DROP;
+		}
+		return XDP_TX;
 	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);
+		bpf_warn_invalid_xdp_action(priv->dev, prog, act);
 		fallthrough;
 	case XDP_ABORTED:
-		trace_xdp_exception(ring->priv->dev, prog, act);
+		trace_xdp_exception(priv->dev, prog, act);
 		page_pool_put_full_page(ring->page_pool, rx_page, true);
 		return XDP_ABORTED;
 	}
@@ -2556,9 +2698,15 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcmgenet_rx_ring *ring = container_of(napi,
 			struct bcmgenet_rx_ring, napi);
+	struct bcmgenet_priv *priv = ring->priv;
 	struct dim_sample dim_sample = {};
 	unsigned int work_done;
 
+	/* Reclaim completed XDP TX frames (ring 16 has no interrupt) */
+	if (priv->xdp_prog)
+		bcmgenet_tx_reclaim(priv->dev,
+				    &priv->xdp_tx_ring, false);
+
 	work_done = bcmgenet_desc_rx(ring, budget);
 
 	if (work_done < budget && napi_complete_done(napi, work_done))
@@ -2789,10 +2937,11 @@ static void bcmgenet_init_rx_coalesce(struct bcmgenet_rx_ring *ring)
 
 /* Initialize a Tx ring along with corresponding hardware registers */
 static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
+				  struct bcmgenet_tx_ring *ring,
 				  unsigned int index, unsigned int size,
-				  unsigned int start_ptr, unsigned int end_ptr)
+				  unsigned int start_ptr,
+				  unsigned int end_ptr)
 {
-	struct bcmgenet_tx_ring *ring = &priv->tx_rings[index];
 	u32 words_per_bd = WORDS_PER_BD(priv);
 	u32 flow_period_val = 0;
 
@@ -2833,8 +2982,11 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
 				  DMA_END_ADDR);
 
-	/* Initialize Tx NAPI */
-	netif_napi_add_tx(priv->dev, &ring->napi, bcmgenet_tx_poll);
+	/* Initialize Tx NAPI for priority queues only; ring DESC_INDEX
+	 * (XDP TX) has its completions handled inline in RX NAPI.
+	 */
+	if (index != DESC_INDEX)
+		netif_napi_add_tx(priv->dev, &ring->napi, bcmgenet_tx_poll);
 }
 
 static int bcmgenet_rx_ring_create_pool(struct bcmgenet_priv *priv,
@@ -2846,7 +2998,7 @@ static int bcmgenet_rx_ring_create_pool(struct bcmgenet_priv *priv,
 		.pool_size = ring->size,
 		.nid = NUMA_NO_NODE,
 		.dev = &priv->pdev->dev,
-		.dma_dir = DMA_FROM_DEVICE,
+		.dma_dir = DMA_BIDIRECTIONAL,
 		.offset = GENET_XDP_HEADROOM,
 		.max_len = RX_BUF_LENGTH,
 	};
@@ -2980,6 +3132,7 @@ static int bcmgenet_tdma_disable(struct bcmgenet_priv *priv)
 
 	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
 	mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	mask |= BIT(DESC_INDEX);
 	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
 	reg &= ~mask;
 	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
@@ -3025,14 +3178,18 @@ static int bcmgenet_rdma_disable(struct bcmgenet_priv *priv)
  * with queue 1 being the highest priority queue.
  *
  * Queue 0 is the default Tx queue with
- * GENET_Q0_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
+ * GENET_Q0_TX_BD_CNT = 256 - 4 * 32 - 32 = 96 descriptors.
+ *
+ * Ring 16 (DESC_INDEX) is used for XDP TX with
+ * GENET_Q16_TX_BD_CNT = 32 descriptors.
  *
  * The transmit control block pool is then partitioned as follows:
- * - Tx queue 0 uses tx_cbs[0..127]
- * - Tx queue 1 uses tx_cbs[128..159]
- * - Tx queue 2 uses tx_cbs[160..191]
- * - Tx queue 3 uses tx_cbs[192..223]
- * - Tx queue 4 uses tx_cbs[224..255]
+ * - Tx queue 0 uses tx_cbs[0..95]
+ * - Tx queue 1 uses tx_cbs[96..127]
+ * - Tx queue 2 uses tx_cbs[128..159]
+ * - Tx queue 3 uses tx_cbs[160..191]
+ * - Tx queue 4 uses tx_cbs[192..223]
+ * - Tx queue 16 uses tx_cbs[224..255]
  */
 static void bcmgenet_init_tx_queues(struct net_device *dev)
 {
@@ -3045,7 +3202,8 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 
 	/* Initialize Tx priority queues */
 	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
-		bcmgenet_init_tx_ring(priv, i, end - start, start, end);
+		bcmgenet_init_tx_ring(priv, &priv->tx_rings[i],
+				      i, end - start, start, end);
 		start = end;
 		end += priv->hw_params->tx_bds_per_q;
 		dma_priority[DMA_PRIO_REG_INDEX(i)] |=
@@ -3053,13 +3211,19 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 			<< DMA_PRIO_REG_SHIFT(i);
 	}
 
+	/* Initialize ring 16 (descriptor ring) for XDP TX */
+	bcmgenet_init_tx_ring(priv, &priv->xdp_tx_ring,
+			      DESC_INDEX, GENET_Q16_TX_BD_CNT,
+			      TOTAL_DESC - GENET_Q16_TX_BD_CNT, TOTAL_DESC);
+
 	/* Set Tx queue priorities */
 	bcmgenet_tdma_writel(priv, dma_priority[0], DMA_PRIORITY_0);
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
 	bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);
 
-	/* Configure Tx queues as descriptor rings */
+	/* Configure Tx queues as descriptor rings, including ring 16 */
 	ring_mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	ring_mask |= BIT(DESC_INDEX);
 	bcmgenet_tdma_writel(priv, ring_mask, DMA_RING_CFG);
 
 	/* Enable Tx rings */
@@ -3773,6 +3937,21 @@ static void bcmgenet_get_stats64(struct net_device *dev,
 		stats->tx_dropped += tx_dropped;
 	}
 
+	/* Include XDP TX ring (DESC_INDEX) stats */
+	tx_stats = &priv->xdp_tx_ring.stats64;
+	do {
+		start = u64_stats_fetch_begin(&tx_stats->syncp);
+		tx_bytes = u64_stats_read(&tx_stats->bytes);
+		tx_packets = u64_stats_read(&tx_stats->packets);
+		tx_errors = u64_stats_read(&tx_stats->errors);
+		tx_dropped = u64_stats_read(&tx_stats->dropped);
+	} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
+
+	stats->tx_bytes += tx_bytes;
+	stats->tx_packets += tx_packets;
+	stats->tx_errors += tx_errors;
+	stats->tx_dropped += tx_dropped;
+
 	for (q = 0; q <= priv->hw_params->rx_queues; q++) {
 		rx_stats = &priv->rx_rings[q].stats64;
 		do {
@@ -4278,6 +4457,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		u64_stats_init(&priv->rx_rings[i].stats64.syncp);
 	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		u64_stats_init(&priv->tx_rings[i].stats64.syncp);
+	u64_stats_init(&priv->xdp_tx_ring.stats64.syncp);
 
 	/* libphy will determine the link state */
 	netif_carrier_off(dev);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 1459473ac1b0..8966d32efe2f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -472,6 +472,8 @@ struct bcmgenet_rx_stats64 {
 
 struct enet_cb {
 	struct sk_buff      *skb;
+	struct xdp_frame    *xdpf;
+	bool                xdp_dma_map;
 	struct page         *rx_page;
 	unsigned int        rx_page_offset;
 	void __iomem *bd_addr;
@@ -611,6 +613,7 @@ struct bcmgenet_priv {
 	unsigned int num_tx_bds;
 
 	struct bcmgenet_tx_ring tx_rings[GENET_MAX_MQ_CNT + 1];
+	struct bcmgenet_tx_ring xdp_tx_ring;
 
 	/* receive variables */
 	void __iomem *rx_bds;
-- 
2.51.0

Re: [PATCH net-next v5 4/6] net: bcmgenet: add XDP_TX support

[Jakub Kicinski]

This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
---
net: bcmgenet: add XDP_TX support

This commit implements XDP_TX using ring 16, which is dedicated to XDP TX
for isolation from SKB TX queues. It also changes the page_pool DMA
direction to bidirectional to allow TX reuse of the existing DMA mapping.

> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> index b45ba2c2857e..687c3b12d44f 100644
> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
[ ... ]
> @@ -2299,11 +2328,96 @@ static struct sk_buff *bcmgenet_xdp_build_skb(struct bcmgenet_rx_ring *ring,
>  	return skb;
>  }
>  
> +static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
> +				     struct xdp_frame *xdpf, bool dma_map)
> +{
[ ... ]
> +	} else {
> +		struct page *page = virt_to_page(xdpf->data);
> +
> +		/* For local XDP_TX the caller already prepended the TSB
> +		 * into xdpf->data/len, so dma_len == xdpf->len.
> +		 */
> +		dma_len = xdpf->len;
> +		mapping = page_pool_get_dma_addr(page) +
> +			  sizeof(*xdpf) + xdpf->headroom;

When the RX page pool is created in bcmgenet_rx_ring_create_pool(), it is
initialized with .offset = GENET_XDP_HEADROOM. Does the DMA address
calculation here need to include this GENET_XDP_HEADROOM offset? Without it,
it appears the hardware might be given a DMA address that is 256 bytes
before the actual packet data, transmitting uninitialized memory.

[ ... ]
> @@ -2311,14 +2425,42 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
>  	switch (act) {
>  	case XDP_PASS:
>  		return XDP_PASS;
> +	case XDP_TX:
> +		/* Prepend a zeroed TSB (Transmit Status Block).  The GENET
> +		 * MAC has TBUF_64B_EN set globally, so hardware expects every
> +		 * TX buffer to begin with a 64-byte struct status_64.  Back
> +		 * up xdp->data into the RSB area (which is no longer needed
> +		 * after the BPF program ran) and zero it.
> +		 */
> +		if (xdp->data - xdp->data_hard_start <
> +		    sizeof(struct status_64)) {
> +			page_pool_put_full_page(ring->page_pool, rx_page,
> +						true);
> +			return XDP_DROP;
> +		}
> +		xdp->data -= sizeof(struct status_64);
> +		xdp->data_meta -= sizeof(struct status_64);
> +		memset(xdp->data, 0, sizeof(struct status_64));
> +
> +		xdpf = xdp_convert_buff_to_frame(xdp);

Does this headroom check account for the additional sizeof(struct xdp_frame)
required by xdp_convert_buff_to_frame()? 

If metadata is present, xdp->data_meta could potentially underflow 
xdp->data_hard_start. If the remaining headroom minus metasize becomes
negative in xdp_convert_buff_to_frame(), could it undergo integer promotion
to a large unsigned value and bypass the internal safety check? This might
cause the struct xdp_frame to overwrite the newly zeroed status_64 block.

[ ... ]
> @@ -2556,9 +2698,15 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
>  {
>  	struct bcmgenet_rx_ring *ring = container_of(napi,
>  			struct bcmgenet_rx_ring, napi);
> +	struct bcmgenet_priv *priv = ring->priv;
>  	struct dim_sample dim_sample = {};
>  	unsigned int work_done;
>  
> +	/* Reclaim completed XDP TX frames (ring 16 has no interrupt) */
> +	if (priv->xdp_prog)
> +		bcmgenet_tx_reclaim(priv->dev,
> +				    &priv->xdp_tx_ring, false);
> +

What happens to in-flight frames if the XDP program is detached at runtime
and priv->xdp_prog becomes NULL? Will this permanently lose track of the
page pool buffers and DMA mappings since the NAPI poll stops reclaiming
them?

Additionally, if the interface is the target of an XDP_REDIRECT from another
device, a local XDP program is not required and priv->xdp_prog could be
NULL. Does this mean the transmitted frames for redirected traffic will
never be reclaimed, eventually filling the TX ring?
-- 
pw-bot: cr

Re: [PATCH net-next v5 4/6] net: bcmgenet: add XDP_TX support

[Nicolai Buchwitz]

On 2.4.2026 05:27, Jakub Kicinski wrote:
> This is an AI-generated review of your patch. The human sending this
> email has considered the AI review valid, or at least plausible.
> ---
> net: bcmgenet: add XDP_TX support
> 
> This commit implements XDP_TX using ring 16, which is dedicated to XDP 
> TX
> for isolation from SKB TX queues. It also changes the page_pool DMA
> direction to bidirectional to allow TX reuse of the existing DMA 
> mapping.
> 
>> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c 
>> b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> index b45ba2c2857e..687c3b12d44f 100644
>> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> [ ... ]
>> @@ -2299,11 +2328,96 @@ static struct sk_buff 
>> *bcmgenet_xdp_build_skb(struct bcmgenet_rx_ring *ring,
>>  	return skb;
>>  }
>> 
>> +static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
>> +				     struct xdp_frame *xdpf, bool dma_map)
>> +{
> [ ... ]
>> +	} else {
>> +		struct page *page = virt_to_page(xdpf->data);
>> +
>> +		/* For local XDP_TX the caller already prepended the TSB
>> +		 * into xdpf->data/len, so dma_len == xdpf->len.
>> +		 */
>> +		dma_len = xdpf->len;
>> +		mapping = page_pool_get_dma_addr(page) +
>> +			  sizeof(*xdpf) + xdpf->headroom;
> 
> When the RX page pool is created in bcmgenet_rx_ring_create_pool(), it 
> is
> initialized with .offset = GENET_XDP_HEADROOM. Does the DMA address
> calculation here need to include this GENET_XDP_HEADROOM offset? 
> Without it,
> it appears the hardware might be given a DMA address that is 256 bytes
> before the actual packet data, transmitting uninitialized memory.

The DMA address calculation is correct. page_pool_get_dma_addr()
returns the base DMA address of the page, not offset by the pool's
.offset parameter. sizeof(*xdpf) + xdpf->headroom correctly offsets
to xdpf->data where the TSB starts.

> 
> [ ... ]
>> @@ -2311,14 +2425,42 @@ static unsigned int bcmgenet_run_xdp(struct 
>> bcmgenet_rx_ring *ring,
>>  	switch (act) {
>>  	case XDP_PASS:
>>  		return XDP_PASS;
>> +	case XDP_TX:
>> +		/* Prepend a zeroed TSB (Transmit Status Block).  The GENET
>> +		 * MAC has TBUF_64B_EN set globally, so hardware expects every
>> +		 * TX buffer to begin with a 64-byte struct status_64.  Back
>> +		 * up xdp->data into the RSB area (which is no longer needed
>> +		 * after the BPF program ran) and zero it.
>> +		 */
>> +		if (xdp->data - xdp->data_hard_start <
>> +		    sizeof(struct status_64)) {
>> +			page_pool_put_full_page(ring->page_pool, rx_page,
>> +						true);
>> +			return XDP_DROP;
>> +		}
>> +		xdp->data -= sizeof(struct status_64);
>> +		xdp->data_meta -= sizeof(struct status_64);
>> +		memset(xdp->data, 0, sizeof(struct status_64));
>> +
>> +		xdpf = xdp_convert_buff_to_frame(xdp);
> 
> Does this headroom check account for the additional sizeof(struct 
> xdp_frame)
> required by xdp_convert_buff_to_frame()?

The TSB headroom check doesn't account for sizeof(struct xdp_frame), but 
xdp_update_frame_from_buff() has its own check that returns -ENOSPC if 
headroom - metasize < sizeof(*xdp_frame). We handle the NULL return by 
dropping the frame. I'll tighten the check to include sizeof(struct 
xdp_frame) to fail early.

> 
> If metadata is present, xdp->data_meta could potentially underflow
> xdp->data_hard_start. If the remaining headroom minus metasize becomes
> negative in xdp_convert_buff_to_frame(), could it undergo integer 
> promotion
> to a large unsigned value and bypass the internal safety check? This 
> might
> cause the struct xdp_frame to overwrite the newly zeroed status_64 
> block.

xdp_update_frame_from_buff() handles this - it clamps metasize to >= 0 
and checks (headroom - metasize) < sizeof(*xdp_frame), returning NULL on 
insufficient space.

> 
> [ ... ]
>> @@ -2556,9 +2698,15 @@ static int bcmgenet_rx_poll(struct napi_struct 
>> *napi, int budget)
>>  {
>>  	struct bcmgenet_rx_ring *ring = container_of(napi,
>>  			struct bcmgenet_rx_ring, napi);
>> +	struct bcmgenet_priv *priv = ring->priv;
>>  	struct dim_sample dim_sample = {};
>>  	unsigned int work_done;
>> 
>> +	/* Reclaim completed XDP TX frames (ring 16 has no interrupt) */
>> +	if (priv->xdp_prog)
>> +		bcmgenet_tx_reclaim(priv->dev,
>> +				    &priv->xdp_tx_ring, false);
>> +
> 
> What happens to in-flight frames if the XDP program is detached at 
> runtime
> and priv->xdp_prog becomes NULL? Will this permanently lose track of 
> the
> page pool buffers and DMA mappings since the NAPI poll stops reclaiming
> them?

Good catch. The reclaim in rx_poll is gated on priv->xdp_prog, so
in-flight frames on the TX ring would never be reclaimed after detach.
I'll change the condition to check for pending frames on the ring
instead.

> 
> Additionally, if the interface is the target of an XDP_REDIRECT from 
> another
> device, a local XDP program is not required and priv->xdp_prog could be
> NULL. Does this mean the transmitted frames for redirected traffic will
> never be reclaimed, eventually filling the TX ring?

The redirect-without-local-prog case can't happen since
xdp_features_set_redirect_target is tied to program attachment.
But the detach race is real - will fix in v6.

Thanks
Nicolai

[PATCH net-next v5 5/6] net: bcmgenet: add XDP_REDIRECT and ndo_xdp_xmit support

[Nicolai Buchwitz]

Add XDP_REDIRECT support and implement ndo_xdp_xmit for receiving
redirected frames from other devices.

XDP_REDIRECT calls xdp_do_redirect() in the RX path with
xdp_do_flush() once per NAPI poll cycle. ndo_xdp_xmit batches frames
into ring 16 under a single spinlock acquisition.

Advertise NETDEV_XDP_ACT_REDIRECT and NETDEV_XDP_ACT_NDO_XMIT in
xdp_features.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 87 ++++++++++++++++---
 1 file changed, 73 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 687c3b12d44f..0a857625af4a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2328,22 +2328,22 @@ static struct sk_buff *bcmgenet_xdp_build_skb(struct bcmgenet_rx_ring *ring,
 	return skb;
 }
 
+/* Submit a single XDP frame to the TX ring. Caller must hold ring->lock.
+ * Returns true on success. Does not ring the doorbell - caller must
+ * write TDMA_PROD_INDEX after batching.
+ */
 static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
+				     struct bcmgenet_tx_ring *ring,
 				     struct xdp_frame *xdpf, bool dma_map)
 {
-	struct bcmgenet_tx_ring *ring = &priv->xdp_tx_ring;
 	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
 	dma_addr_t mapping;
 	unsigned int dma_len;
 	u32 len_stat;
 
-	spin_lock(&ring->lock);
-
-	if (ring->free_bds < 1) {
-		spin_unlock(&ring->lock);
+	if (ring->free_bds < 1)
 		return false;
-	}
 
 	tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
 
@@ -2357,7 +2357,6 @@ static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
 		 */
 		if (unlikely(xdpf->headroom < sizeof(struct status_64))) {
 			bcmgenet_put_txcb(priv, ring);
-			spin_unlock(&ring->lock);
 			return false;
 		}
 
@@ -2371,7 +2370,6 @@ static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
 			tx_cb_ptr->skb = NULL;
 			tx_cb_ptr->xdpf = NULL;
 			bcmgenet_put_txcb(priv, ring);
-			spin_unlock(&ring->lock);
 			return false;
 		}
 	} else {
@@ -2403,12 +2401,14 @@ static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
 	ring->prod_index++;
 	ring->prod_index &= DMA_P_INDEX_MASK;
 
+	return true;
+}
+
+static void bcmgenet_xdp_ring_doorbell(struct bcmgenet_priv *priv,
+				       struct bcmgenet_tx_ring *ring)
+{
 	bcmgenet_tdma_ring_writel(priv, ring->index, ring->prod_index,
 				  TDMA_PROD_INDEX);
-
-	spin_unlock(&ring->lock);
-
-	return true;
 }
 
 static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
@@ -2417,6 +2417,7 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 				     struct page *rx_page)
 {
 	struct bcmgenet_priv *priv = ring->priv;
+	struct bcmgenet_tx_ring *tx_ring;
 	struct xdp_frame *xdpf;
 	unsigned int act;
 
@@ -2448,11 +2449,25 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 						true);
 			return XDP_DROP;
 		}
-		if (unlikely(!bcmgenet_xdp_xmit_frame(priv, xdpf, false))) {
+
+		tx_ring = &priv->xdp_tx_ring;
+		spin_lock(&tx_ring->lock);
+		if (unlikely(!bcmgenet_xdp_xmit_frame(priv, tx_ring,
+						      xdpf, false))) {
+			spin_unlock(&tx_ring->lock);
 			xdp_return_frame_rx_napi(xdpf);
 			return XDP_DROP;
 		}
+		bcmgenet_xdp_ring_doorbell(priv, tx_ring);
+		spin_unlock(&tx_ring->lock);
 		return XDP_TX;
+	case XDP_REDIRECT:
+		if (unlikely(xdp_do_redirect(priv->dev, xdp, prog))) {
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
+			return XDP_DROP;
+		}
+		return XDP_REDIRECT;
 	case XDP_DROP:
 		page_pool_put_full_page(ring->page_pool, rx_page, true);
 		return XDP_DROP;
@@ -2476,6 +2491,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	struct bcmgenet_priv *priv = ring->priv;
 	struct net_device *dev = priv->dev;
 	struct bpf_prog *xdp_prog;
+	bool xdp_flush = false;
 	struct enet_cb *cb;
 	struct sk_buff *skb;
 	u32 dma_length_status;
@@ -2614,6 +2630,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 			xdp_act = bcmgenet_run_xdp(ring, xdp_prog, &xdp,
 						   rx_page);
+			if (xdp_act == XDP_REDIRECT)
+				xdp_flush = true;
 			if (xdp_act != XDP_PASS)
 				goto next;
 
@@ -2687,6 +2705,9 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		bcmgenet_rdma_ring_writel(priv, ring->index, ring->c_index, RDMA_CONS_INDEX);
 	}
 
+	if (xdp_flush)
+		xdp_do_flush();
+
 	ring->dim.bytes = bytes_processed;
 	ring->dim.packets = rxpktprocessed;
 
@@ -4017,12 +4038,18 @@ static int bcmgenet_xdp_setup(struct net_device *dev,
 		return -EOPNOTSUPP;
 	}
 
+	if (!prog)
+		xdp_features_clear_redirect_target(dev);
+
 	old_prog = xchg(&priv->xdp_prog, prog);
 	if (old_prog) {
 		synchronize_net();
 		bpf_prog_put(old_prog);
 	}
 
+	if (prog)
+		xdp_features_set_redirect_target(dev, false);
+
 	return 0;
 }
 
@@ -4036,6 +4063,36 @@ static int bcmgenet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+static int bcmgenet_xdp_xmit(struct net_device *dev, int num_frames,
+			     struct xdp_frame **frames, u32 flags)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_tx_ring *ring = &priv->xdp_tx_ring;
+	int sent = 0;
+	int i;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	if (unlikely(!netif_running(dev)))
+		return -ENETDOWN;
+
+	spin_lock(&ring->lock);
+
+	for (i = 0; i < num_frames; i++) {
+		if (!bcmgenet_xdp_xmit_frame(priv, ring, frames[i], true))
+			break;
+		sent++;
+	}
+
+	if (sent)
+		bcmgenet_xdp_ring_doorbell(priv, ring);
+
+	spin_unlock(&ring->lock);
+
+	return sent;
+}
+
 static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_open		= bcmgenet_open,
 	.ndo_stop		= bcmgenet_close,
@@ -4048,6 +4105,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
 	.ndo_bpf		= bcmgenet_xdp,
+	.ndo_xdp_xmit		= bcmgenet_xdp_xmit,
 };
 
 /* GENET hardware parameters/characteristics */
@@ -4350,7 +4408,8 @@ 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;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			    NETDEV_XDP_ACT_NDO_XMIT;
 
 	netdev_sw_irq_coalesce_default_on(dev);
 
-- 
2.51.0

[PATCH net-next v5 6/6] net: bcmgenet: add XDP statistics counters

[Nicolai Buchwitz]

Expose per-action XDP counters via ethtool -S: xdp_pass, xdp_drop,
xdp_tx, xdp_tx_err, xdp_redirect, and xdp_redirect_err.

These use the existing soft MIB infrastructure and are incremented in
bcmgenet_run_xdp() alongside the existing driver statistics.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 15 +++++++++++++++
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  6 ++++++
 2 files changed, 21 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0a857625af4a..29703398d28c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1170,6 +1170,13 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	STAT_GENET_SOFT_MIB("tx_realloc_tsb", mib.tx_realloc_tsb),
 	STAT_GENET_SOFT_MIB("tx_realloc_tsb_failed",
 			    mib.tx_realloc_tsb_failed),
+	/* XDP counters */
+	STAT_GENET_SOFT_MIB("xdp_pass", mib.xdp_pass),
+	STAT_GENET_SOFT_MIB("xdp_drop", mib.xdp_drop),
+	STAT_GENET_SOFT_MIB("xdp_tx", mib.xdp_tx),
+	STAT_GENET_SOFT_MIB("xdp_tx_err", mib.xdp_tx_err),
+	STAT_GENET_SOFT_MIB("xdp_redirect", mib.xdp_redirect),
+	STAT_GENET_SOFT_MIB("xdp_redirect_err", mib.xdp_redirect_err),
 	/* Per TX queues */
 	STAT_GENET_Q(0),
 	STAT_GENET_Q(1),
@@ -2425,6 +2432,7 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 
 	switch (act) {
 	case XDP_PASS:
+		priv->mib.xdp_pass++;
 		return XDP_PASS;
 	case XDP_TX:
 		/* Prepend a zeroed TSB (Transmit Status Block).  The GENET
@@ -2437,6 +2445,7 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 		    sizeof(struct status_64)) {
 			page_pool_put_full_page(ring->page_pool, rx_page,
 						true);
+			priv->mib.xdp_tx_err++;
 			return XDP_DROP;
 		}
 		xdp->data -= sizeof(struct status_64);
@@ -2456,19 +2465,24 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 						      xdpf, false))) {
 			spin_unlock(&tx_ring->lock);
 			xdp_return_frame_rx_napi(xdpf);
+			priv->mib.xdp_tx_err++;
 			return XDP_DROP;
 		}
 		bcmgenet_xdp_ring_doorbell(priv, tx_ring);
 		spin_unlock(&tx_ring->lock);
+		priv->mib.xdp_tx++;
 		return XDP_TX;
 	case XDP_REDIRECT:
 		if (unlikely(xdp_do_redirect(priv->dev, xdp, prog))) {
+			priv->mib.xdp_redirect_err++;
 			page_pool_put_full_page(ring->page_pool, rx_page,
 						true);
 			return XDP_DROP;
 		}
+		priv->mib.xdp_redirect++;
 		return XDP_REDIRECT;
 	case XDP_DROP:
+		priv->mib.xdp_drop++;
 		page_pool_put_full_page(ring->page_pool, rx_page, true);
 		return XDP_DROP;
 	default:
@@ -2476,6 +2490,7 @@ static unsigned int bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring,
 		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(priv->dev, prog, act);
+		priv->mib.xdp_drop++;
 		page_pool_put_full_page(ring->page_pool, rx_page, true);
 		return XDP_ABORTED;
 	}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 8966d32efe2f..c4e85c185702 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -156,6 +156,12 @@ struct bcmgenet_mib_counters {
 	u32	tx_dma_failed;
 	u32	tx_realloc_tsb;
 	u32	tx_realloc_tsb_failed;
+	u32	xdp_pass;
+	u32	xdp_drop;
+	u32	xdp_tx;
+	u32	xdp_tx_err;
+	u32	xdp_redirect;
+	u32	xdp_redirect_err;
 };
 
 struct bcmgenet_tx_stats64 {
-- 
2.51.0