linux-kernel - Re: [PATCH v7 1/4] x86/msr: Add MSR(140H) and PHIR3MWAIT bit to msr-info.h

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sun, 30 Oct 2016 19:14:17 -0600 (MDT)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     Grzegorz Andrejczuk <grzegorz.andrejczuk@...el.com>
cc:     mingo@...hat.com, hpa@...or.com, x86@...nel.org, bp@...e.de,
        dave.hansen@...ux.intel.com, lukasz.daniluk@...el.com,
        james.h.cownie@...el.com, jacob.jun.pan@...el.com,
        Piotr.Luc@...el.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v7 1/4] x86/msr: Add MSR(140H) and PHIR3MWAIT bit to
 msr-info.h

On Fri, 28 Oct 2016, Grzegorz Andrejczuk wrote:

> Subject: x86/msr: Add MSR(140H) and PHIR3MWAIT bit to msr-info.h

What kind of information is this: MSR(140h)? None at all. That MSR has a
name. So why not using it?

x86/msr: Add MSR_MISC_FEATURE_ENABLES and PHIR3MWAIT bit

Hmm? You might have noticed that I removed the 'to msr-info.h' part. I did
this because it's useless information. We can see that from the patch.

> Intel Xeon Phi x200 (codenamed Knights Landing) has MSR
> MISC_FEATURE_ENABLES 0x140.

And that tells us what?

> Setting 2nd bit of this register makes MONITOR and MWAIT instructions
> do not cause invalid-opcode exception when called from ring different
> than 0.

Can you please be a bit more careful with your changelogs? I give you an
example for a proper one:

  Intel Xeon Phi x200 (codenamed Knights Landing) allows to enable MONITOR
  and MWAIT instructions outside of ring 0.

  The feature is controlled by MSR MISC_FEATURE_ENABLES (0x144). Setting
  bit 0 of this register enables it, so MONITOR and MWAIT instructions do
  not cause invalid-opcode exceptions when invoked outside of ring 0.

  The feature MSR is not yet documented in the SDM. Here is the relevant
  documentation:

Can you spot the difference? 

Hint: Copy and paste are dangerous

> --- a/arch/x86/include/asm/msr-index.h
> +++ b/arch/x86/include/asm/msr-index.h
> @@ -540,6 +540,11 @@
>  #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
>  #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
>  
> +/* Intel Xeon Phi x200 ring 3 MONITOR/MWAIT */
> +#define MSR_MISC_FEATURE_ENABLES	0x00000140
> +#define MSR_MISC_FEATURE_ENABLES_PHIR3MWAIT_BIT	1
> +#define MSR_MISC_FEATURE_ENABLES_PHIR3MWAIT	(1ULL << MSR_MISC_FEATURE_ENABLES_PHIR3MWAIT_BIT)
> +

See comment on patch 4/4 why this bit mask is not required.

Thanks,

	tglx