Skip to contentSkip to conversation

spectre v2 microcodes blacklist (march update)

DISCUSSION Alexander Sergeyev 2 participants 2 messages Mar 3, 2018 – Mar 5, 2018

lore
Share & tools
lore
#0 lore raw

Hi,

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

It looks like the following:

Quoted 1 line

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

#1 lore raw

Hi,

2018-03-03 22:02 GMT+01:00 Alexander Sergeyev <[email protected]>:

Quoted 12 lines

Hi,

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

It looks like the following:

Quoted 3 lines

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.

Quoted 5 lines

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.

Quoted 3 lines

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

Regards,
Jack