[PATCH net] net: ti: icssg-prueth: fix XDP_TX from the AF_XDP zero-copy RX path

Meghana Malladi m-malladi at ti.com
Mon Jun 22 01:05:24 PDT 2026


Hi David,

Thanks for the fix.

On 6/21/26 03:07, David Carlier wrote:
> On XDP_TX from the zero-copy RX path, emac_run_xdp() converts the xsk
> buffer via xdp_convert_zc_to_xdp_frame(), which clones the data into a
> fresh MEM_TYPE_PAGE_ORDER0 page that is not DMA mapped. Transmitting it
> as PRUETH_TX_BUFF_TYPE_XDP_TX derives the DMA address with
> page_pool_get_dma_addr(), reading an uninitialized page->dma_addr, so
> the device DMAs from a bogus address (corrupt TX, or an IOMMU fault).
> 
> Pick the TX buffer type from the frame's memory type: keep
> PRUETH_TX_BUFF_TYPE_XDP_TX for page_pool frames and use
> PRUETH_TX_BUFF_TYPE_XDP_NDO for the cloned zero-copy frame. The
> completion path already unmaps PRUETH_SWDATA_XDPF buffers.
> 

Is it safe to unconditionally unmap the buffer for the case where 
frame's memory type is PRUETH_TX_BUFF_TYPE_XDP_TX? In this case the DMA 
mapping is done with rx_chn->dma_dev, where as in completion path we are 
unmapping with tx_chn->dma_dev unconditionally.

> Fixes: 7a64bb388df3 ("net: ti: icssg-prueth: Add AF_XDP zero copy for RX")
> Cc: stable at vger.kernel.org
> Signed-off-by: David Carlier <devnexen at gmail.com>
> ---
>   drivers/net/ethernet/ti/icssg/icssg_common.c | 13 ++++++++++++-
>   1 file changed, 12 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
> index 82ddef9c17d5..302e700ea17d 100644
> --- a/drivers/net/ethernet/ti/icssg/icssg_common.c
> +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
> @@ -804,6 +804,7 @@ EXPORT_SYMBOL_GPL(emac_xmit_xdp_frame);
>    */
>   static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, u32 *len)
>   {
> +	enum prueth_tx_buff_type tx_buff_type;
>   	struct net_device *ndev = emac->ndev;
>   	struct netdev_queue *netif_txq;
>   	int cpu = smp_processor_id();
> @@ -826,11 +827,21 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, u32 *len
>   			goto drop;
>   		}
>   
> +		/* In AF_XDP zero-copy mode xdp_convert_buff_to_frame()
> +		 * clones the xsk buffer into a fresh MEM_TYPE_PAGE_ORDER0
> +		 * page that is not DMA mapped. Such a frame must be mapped
> +		 * via the NDO path; only a page pool-backed frame already
> +		 * carries a usable page_pool DMA address.
> +		 */
> +		tx_buff_type = xdpf->mem_type == MEM_TYPE_PAGE_POOL ?
> +				PRUETH_TX_BUFF_TYPE_XDP_TX :
> +				PRUETH_TX_BUFF_TYPE_XDP_NDO;
> +
>   		q_idx = cpu % emac->tx_ch_num;
>   		netif_txq = netdev_get_tx_queue(ndev, q_idx);
>   		__netif_tx_lock(netif_txq, cpu);
>   		result = emac_xmit_xdp_frame(emac, xdpf, q_idx,
> -					     PRUETH_TX_BUFF_TYPE_XDP_TX);
> +					     tx_buff_type);
>   		__netif_tx_unlock(netif_txq);
>   		if (result == ICSSG_XDP_CONSUMED) {
>   			ndev->stats.tx_dropped++;



More information about the linux-arm-kernel mailing list