From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Giovanni Gherdovich <ggherdovich@suse.cz>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@suse.de>,
Len Brown <lenb@kernel.org>,
"Rafael J . Wysocki" <rjw@rjwysocki.net>,
x86@kernel.org, linux-pm@vger.kernel.org,
linux-kernel@vger.kernel.org,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH 2/2] x86, sched: Bail out of frequency invariance if turbo frequency is unknown
Date: Fri, 1 May 2020 17:06:07 -0700 [thread overview]
Message-ID: <20200502000607.GB3118@ranerica-svr.sc.intel.com> (raw)
In-Reply-To: <20200501130427.GD3762@hirez.programming.kicks-ass.net>
On Fri, May 01, 2020 at 03:04:27PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 28, 2020 at 03:24:50PM +0200, Giovanni Gherdovich wrote:
> > There may be CPUs that support turbo boost but don't declare any turbo
> > ratio, i.e. their MSR_TURBO_RATIO_LIMIT is all zeroes. In that condition
> > scale-invariant calculations can't be performed.
> >
> > Signed-off-by: Giovanni Gherdovich <ggherdovich@suse.cz>
> > Suggested-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> > Fixes: 1567c3e3467c ("x86, sched: Add support for frequency invariance")
> > ---
> > arch/x86/kernel/smpboot.c | 6 ++++--
> > 1 file changed, 4 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> > index 4718f29a3065..ab2a0df7d1fb 100644
> > --- a/arch/x86/kernel/smpboot.c
> > +++ b/arch/x86/kernel/smpboot.c
> > @@ -1991,9 +1991,11 @@ static bool intel_set_max_freq_ratio(void)
> > /*
> > * Some hypervisors advertise X86_FEATURE_APERFMPERF
> > * but then fill all MSR's with zeroes.
> > + * Some CPUs have turbo boost but don't declare any turbo ratio
> > + * in MSR_TURBO_RATIO_LIMIT.
> > */
> > - if (!base_freq) {
> > - pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n");
> > + if (!base_freq || !turbo_freq) {
> > + pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n");
> > return false;
> > }
>
> I've added the below, imagine base_freq > turbo_freq *
> SCHED_CAPACITY_SCALE.
>
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -1975,6 +1975,7 @@ static bool core_set_max_freq_ratio(u64
> static bool intel_set_max_freq_ratio(void)
> {
> u64 base_freq, turbo_freq;
> + u64 turbo_ratio;
>
> if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
> goto out;
> @@ -2008,9 +2009,15 @@ static bool intel_set_max_freq_ratio(voi
> return false;
> }
>
> - arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
> - base_freq);
> + turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq);
> + if (!turbo_ratio) {
> + pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n");
> + return false;
> + }
> +
> + arch_turbo_freq_ratio = turbo_ratio;
I guess this covers more cases in which turbo_ratio can be zero.
Also, FWIW
Tested-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Thanks and BR,
Ricardo
next prev parent reply other threads:[~2020-05-02 0:05 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-28 13:24 [PATCH 0/2] More frequency invariance fixes for x86 Giovanni Gherdovich
2020-04-28 13:24 ` [PATCH 1/2] x86, sched: Prevent divisions by zero in frequency invariant accounting Giovanni Gherdovich
2020-04-29 11:30 ` Rafael J. Wysocki
2020-05-01 13:30 ` Peter Zijlstra
2020-05-02 14:25 ` Giovanni Gherdovich
2020-05-18 22:20 ` Ricardo Neri
2020-05-19 16:46 ` Giovanni Gherdovich
2020-04-28 13:24 ` [PATCH 2/2] x86, sched: Bail out of frequency invariance if turbo frequency is unknown Giovanni Gherdovich
2020-04-29 11:30 ` Rafael J. Wysocki
2020-05-01 13:04 ` Peter Zijlstra
2020-05-02 0:06 ` Ricardo Neri [this message]
2020-05-02 14:26 ` Giovanni Gherdovich
2020-05-02 0:04 ` Ricardo Neri
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200502000607.GB3118@ranerica-svr.sc.intel.com \
--to=ricardo.neri-calderon@linux.intel.com \
--cc=bp@suse.de \
--cc=ggherdovich@suse.cz \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rjw@rjwysocki.net \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).