Re: [patch V6 00/19] x86/cpu: Rework topology evaluation

[K Prateek Nayak <kprateek.nayak@amd.com>]

Hello Thomas,

On 2/14/2024 2:33 AM, Thomas Gleixner wrote:
> This is a follow up on V5 of this work:
> 
>   https://lore.kernel.org/all/20240117115752.863482697@linutronix.de
> 
> and contains only the not yet applied part which reworks the CPUID
> parsing. This is also preparatory work for the general overhaul of APIC ID
> enumeration and management.
> 
> Changes vs. V5:
> 
>   - Fix the AMD leaf 0x8000008 parsing
>   - Update to generated CPUID leaf structures
>   - Address review comments (coding style, comments, changelogs, boot_cpu_has())
> 
> This applies on Linus tree and is available from git:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/tglx/devel.git topo-cpuid-v6

Tested the above tree comparing the values reported by
"/sys/kernel/debug/x86/topo/cpus/X" and
"/sys/devices/system/cpu/cpuX/topology/*" with those reported by
v6.8-rc4 on the following systems:

- Dual socket 3rd Generation EPYC System (2 x 64C/128T)
- Single socket 4th Generation EPYC System (1 x 96C/192T)
- Dual socket 4th Generation EPYC System (2 x 128C/256T)

Happy to report the values from the sysfs and debugfs with the series
are consistent with values on v6.8-rc4. "amd_node_id" and
"amd_nodes_per_pkg" introduced with the series are consistent with the
values reported in CPUID leaf 0x8000001E ECX on the respective system.

Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>

> 
> [..snip..]
> 

--
Thanks and Regards,
Prateek