[PATCH bpf] veth: store queue_mapping independently of XDP prog presence

[PATCH bpf] veth: store queue_mapping independently of XDP prog presence

[Maciej Fijalkowski]

Currently, veth_xmit() would call the skb_record_rx_queue() only when
there is XDP program loaded on peer interface in native mode.

If peer has XDP prog in generic mode, then netif_receive_generic_xdp()
has a call to netif_get_rxqueue(skb), so for multi-queue veth it will
not be possible to grab a correct rxq.

To fix that, store queue_mapping independently of XDP prog presence on
peer interface.

Fixes: 638264dc9022 ("veth: Support per queue XDP ring")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
---
 drivers/net/veth.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index aa1a66ad2ce5..34e49c75db42 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -302,8 +302,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (rxq < rcv->real_num_rx_queues) {
 		rq = &rcv_priv->rq[rxq];
 		rcv_xdp = rcu_access_pointer(rq->xdp_prog);
-		if (rcv_xdp)
-			skb_record_rx_queue(skb, rxq);
+		skb_record_rx_queue(skb, rxq);
 	}
 
 	skb_tx_timestamp(skb);
-- 
2.20.1

Re: [PATCH bpf] veth: store queue_mapping independently of XDP prog presence

[Toshiaki Makita]

On 2021/03/04 0:29, Maciej Fijalkowski wrote:
> Currently, veth_xmit() would call the skb_record_rx_queue() only when
> there is XDP program loaded on peer interface in native mode.
> 
> If peer has XDP prog in generic mode, then netif_receive_generic_xdp()
> has a call to netif_get_rxqueue(skb), so for multi-queue veth it will
> not be possible to grab a correct rxq.
> 
> To fix that, store queue_mapping independently of XDP prog presence on
> peer interface.
> 
> Fixes: 638264dc9022 ("veth: Support per queue XDP ring")
> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>

I did like this in order to keep the default behavior for non-xdp case,
but generic XDP should behave the same as native XDP, so

Acked-by: Toshiaki Makita <toshiaki.makita1@gmail.com>

Re: [PATCH bpf] veth: store queue_mapping independently of XDP prog presence

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to bpf/bpf.git (refs/heads/master):

On Wed,  3 Mar 2021 16:29:03 +0100 you wrote:
> Currently, veth_xmit() would call the skb_record_rx_queue() only when
> there is XDP program loaded on peer interface in native mode.
> 
> If peer has XDP prog in generic mode, then netif_receive_generic_xdp()
> has a call to netif_get_rxqueue(skb), so for multi-queue veth it will
> not be possible to grab a correct rxq.
> 
> [...]

Here is the summary with links:
  - [bpf] veth: store queue_mapping independently of XDP prog presence
    https://git.kernel.org/bpf/bpf/c/edbea9220251

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html