Re: [PATCH net-next] bcm63xx_enet: convert to build_skb

2020-12-04 Thread Eric Dumazet
On 12/4/20 6:46 AM, Sieng Piaw Liew wrote: > We can increase the efficiency of rx path by using buffers to receive > packets then build SKBs around them just before passing into the network > stack. In contrast, preallocating SKBs too early reduces CPU cache > efficiency. > > Check if we're in

[PATCH net-next] bcm63xx_enet: convert to build_skb

2020-12-03 Thread Sieng Piaw Liew
We can increase the efficiency of rx path by using buffers to receive packets then build SKBs around them just before passing into the network stack. In contrast, preallocating SKBs too early reduces CPU cache efficiency. Check if we're in NAPI context when refilling RX. Normally we're almost alwa