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

Groups > linux.kernel > #1525296

Re: [PATCH 1/2] x86/mce: Include the PPIN in machine check records when it is available

Show all headers | View raw

On Thu, Nov 17, 2016 at 04:35:48PM -0800, Luck, Tony wrote:
> From: Tony Luck <tony.luck@intel.com>
> 
> Intel Xeons from Ivy Bridge onwards support a processor identification
> number. On systems that have it, include it in the machine check record.
> I'm told that this would be helpful for users that run large data centers
> with multi-socket servers to keep track of which CPUs are seeing errors.
> 
> Signed-off-by: Tony Luck <tony.luck@intel.com>
> ---
>  arch/x86/include/asm/msr-index.h |  4 ++++
>  arch/x86/include/uapi/asm/mce.h  |  1 +
>  arch/x86/kernel/cpu/mcheck/mce.c | 35 +++++++++++++++++++++++++++++++++++
>  3 files changed, 40 insertions(+)

...

> @@ -2134,8 +2140,37 @@ static int __init mcheck_enable(char *str)
>  }
>  __setup("mce", mcheck_enable);
>  
> +static void mcheck_intel_ppin_init(void)

So this functionality could all be moved to arch/x86/kernel/cpu/intel.c
where you could set an artificial X86_FEATURE_PPIN and get rid of the
have_ppin var.

> +{
> +	unsigned long long msr_ppin_ctl;
> +
> +	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
> +		return;

Then, that check can go.

> +	switch (boot_cpu_data.x86_model) {
> +	case INTEL_FAM6_IVYBRIDGE_X:
> +	case INTEL_FAM6_HASWELL_X:
> +	case INTEL_FAM6_BROADWELL_XEON_D:
> +	case INTEL_FAM6_BROADWELL_X:
> +	case INTEL_FAM6_SKYLAKE_X:
> +		if (rdmsrl_safe(MSR_PPIN_CTL, &msr_ppin_ctl))
> +			return;

I don't think you need to check models - if the RDMSR fails, you're
done.

> +		if (msr_ppin_ctl == 1) {

				 & BIT_ULL(0)

for future robustness in case those other reserved bits get used.

> +			pr_info("PPIN available but disabled\n");

We don't care, do we?

> +			return;
> +		}
> +		/* if PPIN is disabled, but not locked, try to enable */
> +		if (msr_ppin_ctl == 0) {

Also, properly masked off. There are [63:2] reserved bits which might be
assigned someday.

> +			wrmsrl_safe(MSR_PPIN_CTL, 2);
> +			rdmsrl_safe(MSR_PPIN_CTL, &msr_ppin_ctl);

Why aren't we programming a number here? Or are users supposed to do
that?

If so, please design a proper sysfs interface and not make them use
msr-tools.

> +		}
> +		if (msr_ppin_ctl == 2)
> +			have_ppin = 1;

	set_cpu_cap(c, X86_FEATURE_PPIN);

-- 
Regards/Gruss,
    Boris.

SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nürnberg)
-- 

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

Thread

[PATCH 2/2] mcelog: Print the PPIN in machine check records when it is available "Luck, Tony" <tony.luck@intel.com> - 2016-11-18 01:40 +0100
  [PATCH 1/2] x86/mce: Include the PPIN in machine check records when it is available "Luck, Tony" <tony.luck@intel.com> - 2016-11-18 01:40 +0100
    Re: [PATCH 1/2] x86/mce: Include the PPIN in machine check records  when it is available Borislav Petkov <bp@suse.de> - 2016-11-18 14:10 +0100
      Re: [PATCH 1/2] x86/mce: Include the PPIN in machine check records  when it is available "Luck, Tony" <tony.luck@intel.com> - 2016-11-18 17:50 +0100
      Re: [PATCH 1/2] x86/mce: Include the PPIN in machine check records when it is available Andi Kleen <andi@firstfloor.org> - 2016-11-18 18:10 +0100
        Re: [PATCH 1/2] x86/mce: Include the PPIN in machine check records  when it is available Borislav Petkov <bp@suse.de> - 2016-11-18 18:50 +0100
        [PATCH v2] x86/mce: Include the PPIN in machine check records when it is available "Luck, Tony" <tony.luck@intel.com> - 2016-11-18 18:50 +0100
          Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Borislav Petkov <bp@suse.de> - 2016-11-23 12:50 +0100
            Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Henrique de Moraes Holschuh <hmh@hmh.eng.br> - 2016-11-23 14:40 +0100
              Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Borislav Petkov <bp@suse.de> - 2016-11-23 14:40 +0100
                Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Borislav Petkov <bp@suse.de> - 2016-11-23 16:00 +0100
                Re: [PATCH v2] x86/mce: Include the PPIN in machine check records when it is available Tony Luck <tony.luck@gmail.com> - 2016-11-23 17:50 +0100
                Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Borislav Petkov <bp@suse.de> - 2016-11-23 18:00 +0100
                Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Henrique de Moraes Holschuh <hmh@hmh.eng.br> - 2016-11-23 18:30 +0100
                Re: [PATCH v2] x86/mce: Include the PPIN in machine check records when it is available Tony Luck <tony.luck@gmail.com> - 2016-11-23 22:00 +0100
                Re: [PATCH v2] x86/mce: Include the PPIN in machine check records  when it is available Henrique de Moraes Holschuh <hmh@hmh.eng.br> - 2016-11-24 12:30 +0100
            [tip:ras/core] x86/mce: Include the PPIN in MCE records when  available tip-bot for Tony Luck <tipbot@zytor.com> - 2016-11-23 17:00 +0100

csiph-web