Re: [RFC PATCH] common receive API + r8169 use

[Stephen Hemminger <shemminger@vyatta.com>]

On Tue,  2 Aug 2011 22:24:35 +0200 (CEST)
Michał Mirosław <mirq-linux@rere.qmqm.pl> wrote:

> Here is a preliminary version of common RX path for network drivers. The idea
> is an extension to Eric Dumazet's patch introducing build_skb() (it's
> incorporated here for easier testing).
> 
> Future plans:
>  - extend this API to devices which can do split buffer receives correctly
>    and use napi_gro_frags() instead;
>  - implement DaveM's idea of RX buffer handling (fill first, process
>    if buffers available) in parallel to my version (process first, refill
>    later);
>  - get rid of indirect calls in fast path (process_buffer() and
>    add_buffer()) - ideas? inline netdev_rx_poll() and pass callback to it?
> 
> Version rebased on v3.0 is running succesfully on one laptop with r8169 on
> board since about a week. No problems showed up yet. For net-next this
> needs retesting because of changes in device reset handling.

1. Don't put #ifdef code in, just go with the new code.
2. Get rid of the inline on all those functions. Anything over 3 lines
   really shouldn't be inlined.
3. What is the performance difference (if any)?