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

[chenyu]

On Wed, Jun 15, 2016 at 6:00 PM, Borislav Petkov <bp@xxxxxxxxx> wrote:
> Comments are, as always, appreciated.
>
> ---
> From: Borislav Petkov <bp@xxxxxxx>
> Date: Wed, 15 Jun 2016 11:20:41 +0200
> Subject: [PATCH] Move away from msr.ko
>
> Take care of MSR_IA32_ENERGY_PERF_BIAS.
>
> Not-yet-signed-off-by: Borislav Petkov <bp@xxxxxxx>
[cut]
> +static ssize_t
> +energy_policy_pref_hint_show(struct device *dev, struct device_attribute *attr,
> +                            char *buf)
> +{
> +       u64 epb;
> +
> +       rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
MSR_IA32_ENERGY_PERF_BIAS is of core scope, should we use rdmsr_on_cpu?
> +
> +       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;
> +
> +       rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
rdmsr_on_cpu?
> +
> +       if ((epb & 0xf) == val)
> +               return count;
> +
> +       wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~0xFULL) | val);
wrmsr_on_cpu?



thanks,
Yu