linux-kernel - Re: [patch v5 00/19] x86/cpu: Rework topology evaluation

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]

Message-ID: <c1dc5df7401e21262ab7cf373b59119fe29e32a4.camel@intel.com>
Date: Wed, 31 Jan 2024 07:40:15 +0000
From: "Zhang, Rui" <rui.zhang@...el.com>
To: "tglx@...utronix.de" <tglx@...utronix.de>, "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>
CC: "arjan@...ux.intel.com" <arjan@...ux.intel.com>, "mhklinux@...look.com"
	<mhklinux@...look.com>, "andrew.cooper3@...rix.com"
	<andrew.cooper3@...rix.com>, "ray.huang@....com" <ray.huang@....com>,
	"thomas.lendacky@....com" <thomas.lendacky@....com>, "Wang, Wendy"
	<wendy.wang@...el.com>, "Sivanich, Dimitri" <dimitri.sivanich@....com>,
	"Tang, Feng" <feng.tang@...el.com>, "kan.liang@...ux.intel.com"
	<kan.liang@...ux.intel.com>, "Mehta, Sohil" <sohil.mehta@...el.com>,
	"peterz@...radead.org" <peterz@...radead.org>, "paulmck@...nel.org"
	<paulmck@...nel.org>, "kprateek.nayak@....com" <kprateek.nayak@....com>,
	"jgross@...e.com" <jgross@...e.com>, "andy@...radead.org"
	<andy@...radead.org>, "x86@...nel.org" <x86@...nel.org>
Subject: Re: [patch v5 00/19] x86/cpu: Rework topology evaluation

Hi, Thomas,

Wendy and I have tested all the three patch sets on a couple of
platforms, except the issue raised, no other problem is observed.

 Tested-by: Zhang Rui <rui.zhang@...el.com>
 Tested-by: Wang Wendy <wendy.wang@...el.com>

BTW, one behavior change in this patch series is that die_id become
platform unique instead of package unique.
By my understanding, this won't break any kernel user, but we have some
redundant code left where we compare both package id and die id. for
example, in match_smt(),

if (c->topo.pkg_id == o->topo.pkg_id &&
                   c->topo.die_id == o->topo.die_id &&
                   c->topo.core_id == o->topo.core_id) {
                return topology_sane(c, o, "smt");
        }

thanks,
rui


On Tue, 2024-01-23 at 13:53 +0100, Thomas Gleixner wrote:
> This is a follow up on V4 of this work:
> 
>   https://lore.kernel.org/all/20230814085006.593997112@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. V4:
> 
>   - Add DIEGRP level explicitly
> 
> This applies on Linus tree and is available from git:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/tglx/devel.git topo-
> cpuid-v5
> 
> Thanks,
> 
>         tglx
> ---
>  arch/x86/kernel/cpu/topology.c          |  167 ---------------------
> -
>  b/arch/x86/events/amd/core.c            |    2 
>  b/arch/x86/include/asm/apic.h           |    1 
>  b/arch/x86/include/asm/cpuid.h          |   36 ++++
>  b/arch/x86/include/asm/processor.h      |    5 
>  b/arch/x86/include/asm/topology.h       |   39 +++++
>  b/arch/x86/kernel/amd_nb.c              |    4 
>  b/arch/x86/kernel/apic/apic_flat_64.c   |    7 
>  b/arch/x86/kernel/apic/apic_noop.c      |    3 
>  b/arch/x86/kernel/apic/apic_numachip.c  |    7 
>  b/arch/x86/kernel/apic/bigsmp_32.c      |    6 
>  b/arch/x86/kernel/apic/local.h          |    1 
>  b/arch/x86/kernel/apic/probe_32.c       |    6 
>  b/arch/x86/kernel/apic/x2apic_cluster.c |    1 
>  b/arch/x86/kernel/apic/x2apic_phys.c    |    6 
>  b/arch/x86/kernel/apic/x2apic_uv_x.c    |   63 +-------
>  b/arch/x86/kernel/cpu/Makefile          |    3 
>  b/arch/x86/kernel/cpu/amd.c             |  146 -------------------
>  b/arch/x86/kernel/cpu/cacheinfo.c       |    6 
>  b/arch/x86/kernel/cpu/centaur.c         |    4 
>  b/arch/x86/kernel/cpu/common.c          |   91 +-----------
>  b/arch/x86/kernel/cpu/cpu.h             |   13 -
>  b/arch/x86/kernel/cpu/debugfs.c         |   40 +++++
>  b/arch/x86/kernel/cpu/hygon.c           |  129 -----------------
>  b/arch/x86/kernel/cpu/intel.c           |   25 ---
>  b/arch/x86/kernel/cpu/mce/amd.c         |    4 
>  b/arch/x86/kernel/cpu/mce/inject.c      |    7 
>  b/arch/x86/kernel/cpu/topology.h        |   56 +++++++
>  b/arch/x86/kernel/cpu/topology_amd.c    |  182
> ++++++++++++++++++++++++
>  b/arch/x86/kernel/cpu/topology_common.c |  241
> ++++++++++++++++++++++++++++++++
>  b/arch/x86/kernel/cpu/topology_ext.c    |  130 +++++++++++++++++
>  b/arch/x86/kernel/cpu/zhaoxin.c         |    4 
>  b/arch/x86/kernel/smpboot.c             |   12 +
>  b/arch/x86/kernel/vsmp_64.c             |   13 -
>  b/arch/x86/mm/amdtopology.c             |   35 ++--
>  b/arch/x86/xen/apic.c                   |    6 
>  b/arch/x86/xen/smp_pv.c                 |    3 
>  b/drivers/edac/amd64_edac.c             |    4 
>  b/drivers/edac/mce_amd.c                |    4 
>  39 files changed, 792 insertions(+), 720 deletions(-)
> 
>