Re: [tip:x86/urgent] x86/cpu: Use indirect call to measure performance in init_amd_k6()

From: Mikulas Patocka
Date: Wed Jul 12 2017 - 22:20:24 EST




On Wed, 12 Jul 2017, Borislav Petkov wrote:

> On Wed, Jul 12, 2017 at 06:09:57AM -0700, tip-bot for Mikulas Patocka wrote:
> > Commit-ID: 429ed86b5c99b388543f6f7f6983b1230326f2bb
> > Gitweb: http://git.kernel.org/tip/429ed86b5c99b388543f6f7f6983b1230326f2bb
> > Author: Mikulas Patocka <mpatocka@xxxxxxxxxx>
> > AuthorDate: Tue, 11 Jul 2017 07:44:05 -0400
> > Committer: Ingo Molnar <mingo@xxxxxxxxxx>
> > CommitDate: Wed, 12 Jul 2017 10:42:32 +0200
> >
> > x86/cpu: Use indirect call to measure performance in init_amd_k6()
> >
> > This old piece of code is supposed to measure the performance of indirect
> > calls to determine if the processor is buggy or not, however the compiler
> > optimizer turns it into a direct call.
>
> Are you booting on a real K6 or qemu?

I tested it on K6-3 and it doesn't trigger the warning, the loop with the
indirect call takes 9 million cycles (it took 4 million cycles with the
direct call).

I don't have the old K6 revision with the bug.

Mikulas

> --
> Regards/Gruss,
> Boris.
>
> ECO tip #101: Trim your mails when you reply.
> --