Re: [PATCH 0/4] x86/platform/UV: Update TSC support

From	Peter Zijlstra <peterz@infradead.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH 0/4] x86/platform/UV: Update TSC support
Date	2017-09-29 20:50 +0200
Message-ID	<uv8wi-1rx-19@gated-at.bofh.it> (permalink)
References	<uuLq1-3SB-3@gated-at.bofh.it> <uuZ9E-3QF-3@gated-at.bofh.it> <uv5oK-7Wg-31@gated-at.bofh.it> <uv6kP-5s-13@gated-at.bofh.it> <uv7qx-Nr-5@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Fri, Sep 29, 2017 at 10:39:28AM -0700, Mike Travis wrote:
> >That's where it comes from. But normal systems really _should_ have it
> >at 0 and its a useful sanity check IMO. We really want to know when the
> >BIOS does a funny behind our backs.
> >
> 
> How about a more generic flag, such as "multi_tsc_sync_sources"?  That could
> trigger both disabling the "TSC == 0 on socket 0" check as well as disabling
> X86_FEATURE_ART where appropriate?  Or I could clear the feature ART cap
> separately in the UV system init code if they are not really related?

I _think_ the X86_FEATURE_ART is an artificial flag. We key off of
cpuid_level here.

So that multi_tsc_sync_sources or a more explicit is_uv_system() would
be required.

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH 0/4] x86/platform/UV: Update TSC support <mike.travis@hpe.com> - 2017-09-28 20:20 +0200
  Re: [PATCH 0/4] x86/platform/UV: Update TSC support Peter Zijlstra <peterz@infradead.org> - 2017-09-29 10:50 +0200
    Re: [PATCH 0/4] x86/platform/UV: Update TSC support Mike Travis <mike.travis@hpe.com> - 2017-09-29 17:30 +0200
      Re: [PATCH 0/4] x86/platform/UV: Update TSC support Peter Zijlstra <peterz@infradead.org> - 2017-09-29 18:30 +0200
        Re: [PATCH 0/4] x86/platform/UV: Update TSC support Mike Travis <mike.travis@hpe.com> - 2017-09-29 19:40 +0200
          Re: [PATCH 0/4] x86/platform/UV: Update TSC support Peter Zijlstra <peterz@infradead.org> - 2017-09-29 20:50 +0200

csiph-web