linux-kernel - Re: [Patch v2 2/2] x86/tsc: use logical_packages as a better estimation of socket numbers

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 for Android: free password hash cracker in your pocket

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

Date:   Fri, 16 Jun 2023 11:23:12 +0000
From:   "Zhang, Rui" <rui.zhang@...el.com>
To:     "peterz@...radead.org" <peterz@...radead.org>
CC:     "bp@...en8.de" <bp@...en8.de>,
        "dave.hansen@...ux.intel.com" <dave.hansen@...ux.intel.com>,
        "Tang, Feng" <feng.tang@...el.com>,
        "Chen, Tim C" <tim.c.chen@...el.com>,
        "hpa@...or.com" <hpa@...or.com>,
        "tglx@...utronix.de" <tglx@...utronix.de>,
        "x86@...nel.org" <x86@...nel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "paulmck@...nel.org" <paulmck@...nel.org>,
        "mingo@...hat.com" <mingo@...hat.com>,
        "Woodhouse, David" <dwmw@...zon.co.uk>
Subject: Re: [Patch v2 2/2] x86/tsc: use logical_packages as a better
 estimation of socket numbers

On Fri, 2023-06-16 at 11:42 +0200, Peter Zijlstra wrote:
> On Fri, Jun 16, 2023 at 09:19:18AM +0000, Zhang, Rui wrote:
> 
> > According to the MADT, there are indeed 40 valid CPUs. And then 80
> > CPUs
> > with 
> > 
> > APIC ID         : FF
> > enabled         : 0
> > Online capable  : 0
> > 
> > a dumb question, why are these CPUs added into the possible_mask?
> > I can dig into this later but I just don't have a quick answer at
> > the
> > moment.
> 
> I really don't know.. I've not gotten around to reading that part of
> the
> x86 code yet.
> 
> 
I did a double check.

The MADT is composed of

1. 40 valid LAPIC entries.
2. 80 invalid LAPIC entries with
	APIC ID : FF
	Enabled : 0
	Online capable: 0
   I'm mot sure why "Online capable" is decoded because this new bit is
   introduced in ACPI 6.3. Maybe a problem in the acpica tool?
   These entries are ignored because of the invalid APIC ID.
3. 120 x2APIC entries with
	APIC ID : valid value
	Enabled : 0
   As "Online capable bit" is not supported, these 120 x2APIC entries
   are counted as possible CPUs.

That is why we got 160 possible CPUs.

thanks,
rui