2018-03-03 20:58:57

by Alexander Sergeyev

[permalink] [raw]
Subject: spectre v2 microcodes blacklist (march update)

Hi,

the microcode revision guidance from Intel is revised once again [1] (1 Mar).

It looks like the following:

>Intel document only clears the 0xc2 microcode on *some* parts with CPUID 506E3
>(INTEL_FAM6_SKYLAKE_DESKTOP stepping 3). For the Skylake H/S platform it's OK
>but for Skylake E3 which has the same CPUID it isn't (yet) cleared.

is no longer a problem. CPUID 506E3 with both Skylake H/S and Skylake Xeon E3
is labelled as "production" now.

Could we drop { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 } from
spectre_bad_microcodes?

[1]
https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf


2018-03-05 10:18:37

by 王金浦

[permalink] [raw]
Subject: Re: spectre v2 microcodes blacklist (march update)

Hi,

2018-03-03 22:02 GMT+01:00 Alexander Sergeyev <[email protected]>:
> Hi,
>
> the microcode revision guidance from Intel is revised once again [1] (1
> Mar).
>
> It looks like the following:
>
>> Intel document only clears the 0xc2 microcode on *some* parts with CPUID
>> 506E3 (INTEL_FAM6_SKYLAKE_DESKTOP stepping 3). For the Skylake H/S platform
>> it's OK but for Skylake E3 which has the same CPUID it isn't (yet) cleared.
>
>
> is no longer a problem. CPUID 506E3 with both Skylake H/S and Skylake Xeon
> E3 is labelled as "production" now.
>
> Could we drop { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 } from
> spectre_bad_microcodes?
+1, I have a test machine with cpuid 506e3, dell/intel releases
production BIOS version 0xC2, but due to list as bad_microcode,
IBPB function is disabled.
I would like also vote to get it remove from bad_microcode list.
>
> [1]
> https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf

Regards,
Jack