Re: [PATCH net 4/4] net: ti: icssg-prueth: Fix kernel panic during concurrent Tx queue access

[Jesper Dangaard Brouer <hawk@kernel.org>]

On 28/04/2025 14.04, Meghana Malladi wrote:
> Add __netif_tx_lock() to ensure that only one packet is being
> transmitted at a time to avoid race conditions in the netif_txq
> struct and prevent packet data corruption. Failing to do so causes
> kernel panic with the following error:
> 
> [ 2184.746764] ------------[ cut here ]------------
> [ 2184.751412] kernel BUG at lib/dynamic_queue_limits.c:99!
> [ 2184.756728] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
> 
> logs: https://gist.github.com/MeghanaMalladiTI/9c7aa5fc3b7fb03f87c74aad487956e9
> 
> The lock is acquired before calling emac_xmit_xdp_frame() and released after the
> call returns. This ensures that the TX queue is protected from concurrent access
> during the transmission of XDP frames.
> 
> Fixes: 62aa3246f462 ("net: ti: icssg-prueth: Add XDP support")
> Signed-off-by: Meghana Malladi <m-malladi@ti.com>
> ---
>   drivers/net/ethernet/ti/icssg/icssg_common.c | 7 ++++++-
>   drivers/net/ethernet/ti/icssg/icssg_prueth.c | 7 ++++++-
>   2 files changed, 12 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
> index a120ff6fec8f..e509b6ff81e7 100644
> --- a/drivers/net/ethernet/ti/icssg/icssg_common.c
> +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
> @@ -660,6 +660,8 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
>   			struct page *page, u32 *len)
>   {
>   	struct net_device *ndev = emac->ndev;
> +	struct netdev_queue *netif_txq;
> +	int cpu = smp_processor_id();
>   	struct bpf_prog *xdp_prog;
>   	struct xdp_frame *xdpf;
>   	u32 pkt_len = *len;
> @@ -679,8 +681,11 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
>   			goto drop;
>   		}
>   
> -		q_idx = smp_processor_id() % emac->tx_ch_num;
> +		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, page, q_idx);
> +		__netif_tx_unlock(netif_txq);
>   		if (result == ICSSG_XDP_CONSUMED) {
>   			ndev->stats.tx_dropped++;
>   			goto drop;
> diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
> index ee35fecf61e7..b31060e7f698 100644
> --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
> +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
> @@ -1075,20 +1075,25 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
>   {
>   	struct prueth_emac *emac = netdev_priv(dev);
>   	struct net_device *ndev = emac->ndev;
> +	struct netdev_queue *netif_txq;
> +	int cpu = smp_processor_id();
>   	struct xdp_frame *xdpf;
>   	unsigned int q_idx;
>   	int nxmit = 0;
>   	u32 err;
>   	int i;
>   
> -	q_idx = smp_processor_id() % emac->tx_ch_num;
> +	q_idx = cpu % emac->tx_ch_num;
> +	netif_txq = netdev_get_tx_queue(ndev, q_idx);
>   
>   	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
>   		return -EINVAL;
>   
>   	for (i = 0; i < n; i++) {
>   		xdpf = frames[i];
> +		__netif_tx_lock(netif_txq, cpu);
>   		err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx);
> +		__netif_tx_unlock(netif_txq);

Why are you taking and releasing this lock in a loop?

XDP gain performance by sending a batch of 'n' packets.
This approach looks like a performance killer.


>   		if (err != ICSSG_XDP_TX) {
>   			ndev->stats.tx_dropped++;
>   			break;