Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr

From	Borislav Petkov <bp@alien8.de>
Newsgroups	linux.kernel
Subject	Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr
Date	2016-06-15 16:10 +0200
Message-ID	<rKjG2-3xJ-27@gated-at.bofh.it> (permalink)
References	<rKfVL-1co-3@gated-at.bofh.it> <rKgfe-1jj-51@gated-at.bofh.it> <rKgoN-1mz-5@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, Jun 15, 2016 at 12:36:22PM +0200, Borislav Petkov wrote:
> Ah, yes, good point. Will change.

Ok, got a bit more involved - I also need to disable preemption around
smp_call_function_single(). Here's what I have now. It seems to work
too.

static ssize_t
energy_policy_pref_hint_show(struct device *dev, struct device_attribute *attr,
                             char *buf)
{
        u64 epb;

        preempt_disable();
        if (rdmsrl_on_cpu(dev->id, MSR_IA32_ENERGY_PERF_BIAS, &epb))
                epb = -1;
        preempt_enable();

        return sprintf(buf, "%d\n", (unsigned int)(epb & 0xFULL));
}

static ssize_t
energy_policy_pref_hint_store(struct device *dev, struct device_attribute *attr,
                              const char *buf, size_t count)
{
        u32 val;
        u64 epb;

        if (kstrtou32(buf, 10, &val) < 0)
                return -EINVAL;

        if (val > 15)
                return -EINVAL;

        preempt_disable();

        if (rdmsrl_on_cpu(dev->id, MSR_IA32_ENERGY_PERF_BIAS, &epb)) {
                count = -EINVAL;
                goto out;
        }

        if ((epb & 0xf) == val)
                goto out;

        if (wrmsrl_on_cpu(dev->id, MSR_IA32_ENERGY_PERF_BIAS, (epb & ~0xFULL) | val))
                count = -EINVAL;

out:
        preempt_enable();
        return count;
}

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.

Thread

[RFC PATCH] x86: Move away from /dev/cpu/*/msr Borislav Petkov <bp@alien8.de> - 2016-06-15 12:10 +0200
  Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr chenyu <yu.chen.surf@gmail.com> - 2016-06-15 12:30 +0200
    Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Borislav Petkov <bp@alien8.de> - 2016-06-15 12:40 +0200
      Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Borislav Petkov <bp@alien8.de> - 2016-06-15 16:10 +0200
  Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Len Brown <lenb@kernel.org> - 2016-06-15 18:50 +0200
    Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Borislav Petkov <bp@alien8.de> - 2016-06-15 19:00 +0200
      Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Len Brown <lenb@kernel.org> - 2016-06-15 19:30 +0200
        Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Borislav Petkov <bp@alien8.de> - 2016-06-15 19:40 +0200
          Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Len Brown <lenb@kernel.org> - 2016-06-15 19:50 +0200
            Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Borislav Petkov <bp@alien8.de> - 2016-06-15 20:00 +0200
  Re: [RFC PATCH] x86: Move away from /dev/cpu/*/msr Andi Kleen <andi@firstfloor.org> - 2016-06-20 23:20 +0200

csiph-web