1. Patchew
  2. linux
  3. [PATCH net-next 0/6] net: bcmgenet: add XDP support
  4. View patch

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

Nicolai Buchwitz posted 6 patches 3 weeks, 4 days ago
There is a newer version of this series
[PATCH net-next 4/6] net: bcmgenet: add XDP_TX support
Posted by Nicolai Buchwitz 3 weeks, 4 days ago 
Implement XDP_TX by submitting XDP frames through the default TX ring
(DESC_INDEX). The frame is DMA-mapped and placed into a single TX
descriptor with SOP|EOP|APPEND_CRC flags.

The xdp_frame pointer is stored in the TX control block so that
bcmgenet_free_tx_cb() can call xdp_return_frame() on TX completion,
returning the page to the originating page_pool.

The page_pool DMA direction is changed from DMA_FROM_DEVICE to
DMA_BIDIRECTIONAL to support the TX DMA mapping of received pages.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 73 ++++++++++++++++++-
 .../net/ethernet/broadcom/genet/bcmgenet.h    |  1 +
 2 files changed, 71 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index d43729fc2b1b..373ba5878ca1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1893,6 +1893,12 @@ static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev,
 		if (cb == GENET_CB(skb)->last_cb)
 			return skb;
 
+	} else if (cb->xdpf) {
+		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),
@@ -2299,10 +2305,62 @@ 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)
+{
+	struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX];
+	struct device *kdev = &priv->pdev->dev;
+	struct enet_cb *tx_cb_ptr;
+	dma_addr_t mapping;
+	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);
+
+	mapping = dma_map_single(kdev, xdpf->data, xdpf->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;
+	}
+
+	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, xdpf->len);
+	tx_cb_ptr->skb = NULL;
+	tx_cb_ptr->xdpf = xdpf;
+
+	len_stat = (xdpf->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);
@@ -2310,14 +2368,23 @@ bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring, struct bpf_prog *prog,
 	switch (act) {
 	case XDP_PASS:
 		return XDP_PASS;
+	case XDP_TX:
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf) ||
+		    unlikely(!bcmgenet_xdp_xmit_frame(priv, xdpf))) {
+			page_pool_put_full_page(ring->page_pool, rx_page,
+						true);
+			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;
 	}
@@ -2846,7 +2913,7 @@ 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,
 	};
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 1459473ac1b0..192db0defbfc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -472,6 +472,7 @@ struct bcmgenet_rx_stats64 {
 
 struct enet_cb {
 	struct sk_buff      *skb;
+	struct xdp_frame    *xdpf;
 	struct page         *rx_page;
 	unsigned int        rx_page_offset;
 	void __iomem *bd_addr;
-- 
2.51.0
Re: [PATCH net-next 4/6] net: bcmgenet: add XDP_TX support
Posted by Subbaraya Sundeep 3 weeks, 4 days ago 
Hi,

On 2026-03-13 at 14:50:59, Nicolai Buchwitz (nb@tipi-net.de) wrote:
> Implement XDP_TX by submitting XDP frames through the default TX ring
> (DESC_INDEX). The frame is DMA-mapped and placed into a single TX
> descriptor with SOP|EOP|APPEND_CRC flags.
> 
> The xdp_frame pointer is stored in the TX control block so that
> bcmgenet_free_tx_cb() can call xdp_return_frame() on TX completion,
> returning the page to the originating page_pool.
> 
> The page_pool DMA direction is changed from DMA_FROM_DEVICE to
> DMA_BIDIRECTIONAL to support the TX DMA mapping of received pages.
> 
> Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
> ---
>  .../net/ethernet/broadcom/genet/bcmgenet.c    | 73 ++++++++++++++++++-
>  .../net/ethernet/broadcom/genet/bcmgenet.h    |  1 +
>  2 files changed, 71 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> index d43729fc2b1b..373ba5878ca1 100644
> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> @@ -1893,6 +1893,12 @@ static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev,
>  		if (cb == GENET_CB(skb)->last_cb)
>  			return skb;
>  
> +	} else if (cb->xdpf) {
> +		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),
> @@ -2299,10 +2305,62 @@ 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)
> +{
> +	struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX];
> +	struct device *kdev = &priv->pdev->dev;
> +	struct enet_cb *tx_cb_ptr;
> +	dma_addr_t mapping;
> +	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);
> +
> +	mapping = dma_map_single(kdev, xdpf->data, xdpf->len, DMA_TO_DEVICE);

AFAIU you are transmitting the frame received on a RQ which is from the page pool
and already dma mapped. Do you have to do dma_map again?

Thanks,
Sundeep

> +	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;
> +	}
> +
> +	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
> +	dma_unmap_len_set(tx_cb_ptr, dma_len, xdpf->len);
> +	tx_cb_ptr->skb = NULL;
> +	tx_cb_ptr->xdpf = xdpf;
> +
> +	len_stat = (xdpf->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);
> @@ -2310,14 +2368,23 @@ bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring, struct bpf_prog *prog,
>  	switch (act) {
>  	case XDP_PASS:
>  		return XDP_PASS;
> +	case XDP_TX:
> +		xdpf = xdp_convert_buff_to_frame(xdp);
> +		if (unlikely(!xdpf) ||
> +		    unlikely(!bcmgenet_xdp_xmit_frame(priv, xdpf))) {
> +			page_pool_put_full_page(ring->page_pool, rx_page,
> +						true);
> +			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;
>  	}
> @@ -2846,7 +2913,7 @@ 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,
>  	};
> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
> index 1459473ac1b0..192db0defbfc 100644
> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
> @@ -472,6 +472,7 @@ struct bcmgenet_rx_stats64 {
>  
>  struct enet_cb {
>  	struct sk_buff      *skb;
> +	struct xdp_frame    *xdpf;
>  	struct page         *rx_page;
>  	unsigned int        rx_page_offset;
>  	void __iomem *bd_addr;
> -- 
> 2.51.0
>
Re: [PATCH net-next 4/6] net: bcmgenet: add XDP_TX support
Posted by Nicolai Buchwitz 3 weeks, 4 days ago 
On 13.3.2026 12:37, Subbaraya Sundeep wrote:
> Hi,

Hi Sundeep

> 
> On 2026-03-13 at 14:50:59, Nicolai Buchwitz (nb@tipi-net.de) wrote:
>> Implement XDP_TX by submitting XDP frames through the default TX ring
>> (DESC_INDEX). The frame is DMA-mapped and placed into a single TX
>> descriptor with SOP|EOP|APPEND_CRC flags.
>> 
>> The xdp_frame pointer is stored in the TX control block so that
>> bcmgenet_free_tx_cb() can call xdp_return_frame() on TX completion,
>> returning the page to the originating page_pool.
>> 
>> The page_pool DMA direction is changed from DMA_FROM_DEVICE to
>> DMA_BIDIRECTIONAL to support the TX DMA mapping of received pages.
>> 
>> Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
>> ---
>>  .../net/ethernet/broadcom/genet/bcmgenet.c    | 73 
>> ++++++++++++++++++-
>>  .../net/ethernet/broadcom/genet/bcmgenet.h    |  1 +
>>  2 files changed, 71 insertions(+), 3 deletions(-)
>> 
>> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c 
>> b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> index d43729fc2b1b..373ba5878ca1 100644
>> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> @@ -1893,6 +1893,12 @@ static struct sk_buff 
>> *bcmgenet_free_tx_cb(struct device *dev,
>>  		if (cb == GENET_CB(skb)->last_cb)
>>  			return skb;
>> 
>> +	} else if (cb->xdpf) {
>> +		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),
>> @@ -2299,10 +2305,62 @@ 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)
>> +{
>> +	struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX];
>> +	struct device *kdev = &priv->pdev->dev;
>> +	struct enet_cb *tx_cb_ptr;
>> +	dma_addr_t mapping;
>> +	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);
>> +
>> +	mapping = dma_map_single(kdev, xdpf->data, xdpf->len, 
>> DMA_TO_DEVICE);
> 
> AFAIU you are transmitting the frame received on a RQ which is from the 
> page pool
> and already dma mapped. Do you have to do dma_map again?
> 
> Thanks,
> Sundeep
> 

You're right. Since the page_pool is configured with DMA_BIDIRECTIONAL,
the pages are already mapped and we can reuse the existing mapping for
XDP_TX frames. The initial implementation took the simple route of
mapping everything uniformly, but that's unnecessary overhead for the
local XDP_TX case.

In v2 I'll add a bool dma_map parameter to bcmgenet_xdp_xmit_frame()
(following the mvneta/stmmac pattern): XDP_TX will reuse the page_pool
mapping via page_pool_get_dma_addr() + dma_sync_single_for_device(),
while ndo_xdp_xmit will keep dma_map_single() for foreign frames. The
cleanup path will be split accordingly.

Regards
Nicolai

>> [...]

Patchew 2.1-devel-ea86937

© 2016 - 2026 Red Hat, Inc.