| Message ID | 20230824123131.7673-1-liangchen.linux@gmail.com (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 215eb9f962091ebaab96be2c18cf5d0f5174a4d6 |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [net-next] veth: Avoid NAPI scheduling on failed SKB forwarding | expand |
Hello: This patch was applied to netdev/net-next.git (main) by Jakub Kicinski <kuba@kernel.org>: On Thu, 24 Aug 2023 20:31:31 +0800 you wrote: > When an skb fails to be forwarded to the peer(e.g., skb data buffer > length exceeds MTU), it will not be added to the peer's receive queue. > Therefore, we should schedule the peer's NAPI poll function only when > skb forwarding is successful to avoid unnecessary overhead. > > Signed-off-by: Liang Chen <liangchen.linux@gmail.com> > > [...] Here is the summary with links: - [net-next] veth: Avoid NAPI scheduling on failed SKB forwarding https://git.kernel.org/netdev/net-next/c/215eb9f96209 You are awesome, thank you!
diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 614f3e3efab0..e163c6927f56 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -373,14 +373,13 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) { if (!use_napi) dev_lstats_add(dev, length); + else + __veth_xdp_flush(rq); } else { drop: atomic64_inc(&priv->dropped); } - if (use_napi) - __veth_xdp_flush(rq); - rcu_read_unlock(); return NETDEV_TX_OK;
When an skb fails to be forwarded to the peer(e.g., skb data buffer length exceeds MTU), it will not be added to the peer's receive queue. Therefore, we should schedule the peer's NAPI poll function only when skb forwarding is successful to avoid unnecessary overhead. Signed-off-by: Liang Chen <liangchen.linux@gmail.com> --- drivers/net/veth.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)