Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1706891 > unrolled thread

[PATCH] cpufreq: x86: Disable interrupts during MSRs reading

Started byDoug Smythies <doug.smythies@gmail.com>
First post2017-08-08 23:20 +0200
Last post2017-08-10 07:10 +0200
Articles 2 — 2 participants

Back to article view | Back to linux.kernel


Contents

  [PATCH] cpufreq: x86: Disable interrupts during MSRs reading Doug Smythies <doug.smythies@gmail.com> - 2017-08-08 23:20 +0200
    Re: [PATCH] cpufreq: x86: Disable interrupts during MSRs reading Len Brown <lenb@kernel.org> - 2017-08-10 07:10 +0200

#1706891 — [PATCH] cpufreq: x86: Disable interrupts during MSRs reading

FromDoug Smythies <doug.smythies@gmail.com>
Date2017-08-08 23:20 +0200
Subject[PATCH] cpufreq: x86: Disable interrupts during MSRs reading
Message-ID<uck4W-5Pv-19@gated-at.bofh.it>
According to Intel 64 and IA-32 Architectures SDM, Volume 3,
Chapter 14.2, "Software needs to exercise care to avoid delays
between the two RDMSRs (for example interrupts)".

So, disable interrupts during reading MSRs IA32_APERF and IA32_MPERF.

See also:
commit 4ab60c3f32c721e46217e762bcd3e55a8f659c04
cpufreq: intel_pstate: Disable interrupts during MSRs reading

Signed-off-by: Doug Smythies <dsmythies@telus.net>
---
 arch/x86/kernel/cpu/aperfmperf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 7cf7c70..0ee8332 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -40,13 +40,16 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
 	ktime_t now = ktime_get();
 	s64 time_delta = ktime_ms_delta(now, s->time);
+	unsigned long flags;
 
 	/* Don't bother re-computing within the cache threshold time. */
 	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
+	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	local_irq_restore(flags);
 
 	aperf_delta = aperf - s->aperf;
 	mperf_delta = mperf - s->mperf;
-- 
2.7.4

[toc] | [next] | [standalone]


#1708213

FromLen Brown <lenb@kernel.org>
Date2017-08-10 07:10 +0200
Message-ID<ucNTj-13s-1@gated-at.bofh.it>
In reply to#1706891
thanks, Doug!

Rafael,

Reviewed-by: Len Brown <len.brown@intel.com>


On Tue, Aug 8, 2017 at 5:12 PM, Doug Smythies <doug.smythies@gmail.com> wrote:
> According to Intel 64 and IA-32 Architectures SDM, Volume 3,
> Chapter 14.2, "Software needs to exercise care to avoid delays
> between the two RDMSRs (for example interrupts)".
>
> So, disable interrupts during reading MSRs IA32_APERF and IA32_MPERF.
>
> See also:
> commit 4ab60c3f32c721e46217e762bcd3e55a8f659c04
> cpufreq: intel_pstate: Disable interrupts during MSRs reading
>
> Signed-off-by: Doug Smythies <dsmythies@telus.net>
> ---
>  arch/x86/kernel/cpu/aperfmperf.c | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
> index 7cf7c70..0ee8332 100644
> --- a/arch/x86/kernel/cpu/aperfmperf.c
> +++ b/arch/x86/kernel/cpu/aperfmperf.c
> @@ -40,13 +40,16 @@ static void aperfmperf_snapshot_khz(void *dummy)
>         struct aperfmperf_sample *s = this_cpu_ptr(&samples);
>         ktime_t now = ktime_get();
>         s64 time_delta = ktime_ms_delta(now, s->time);
> +       unsigned long flags;
>
>         /* Don't bother re-computing within the cache threshold time. */
>         if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
>                 return;
>
> +       local_irq_save(flags);
>         rdmsrl(MSR_IA32_APERF, aperf);
>         rdmsrl(MSR_IA32_MPERF, mperf);
> +       local_irq_restore(flags);
>
>         aperf_delta = aperf - s->aperf;
>         mperf_delta = mperf - s->mperf;
> --
> 2.7.4
>



-- 
Len Brown, Intel Open Source Technology Center

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web