Re: [PATCH -v1.1] x86: Optimize clear_page()

From: Borislav Petkov
Date: Sun Feb 19 2017 - 08:42:05 EST


On Wed, Feb 15, 2017 at 12:19:27PM +0100, Borislav Petkov wrote:
> Here's a fixed version of the breakage the 0day bot reported:
>
> ---
> From: Borislav Petkov <bp@xxxxxxx>
> Date: Thu, 9 Feb 2017 01:34:49 +0100
> Subject: [PATCH -v1.1] x86: Optimize clear_page()
>
> Currently, we CALL clear_page() which then JMPs to the proper function
> chosen by the alternatives.
>
> What we should do instead is CALL the proper function directly. (This
> was something Ingo suggested a while ago). So let's do that.
>
> Measuring our favourite kernel build workload shows that there are no
> significant changes in performance.

...

> Signed-off-by: Borislav Petkov <bp@xxxxxxx>
> [ Forgot to add clobbers. ]
> Reported-by: kernel test robot <fengguang.wu@xxxxxxxxx>

Fengguang just confirmed too:

"Yes it works fine for 300 boots.

Tested-by: Fengguang Wu <fengguang.wu@xxxxxxxxx>"

--
Regards/Gruss,
Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.