[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <877cq6tutm.ffs@tglx>
Date: Mon, 07 Aug 2023 23:18:45 +0200
From: Thomas Gleixner <tglx@...utronix.de>
To: Dave Hansen <dave.hansen@...el.com>,
LKML <linux-kernel@...r.kernel.org>
Cc: x86@...nel.org, Andrew Cooper <andrew.cooper3@...rix.com>,
Tom Lendacky <thomas.lendacky@....com>,
Paolo Bonzini <pbonzini@...hat.com>,
Wei Liu <wei.liu@...nel.org>,
Arjan van de Ven <arjan@...ux.intel.com>,
Juergen Gross <jgross@...e.com>,
Michael Kelley <mikelley@...rosoft.com>,
Peter Keresztes Schmidt <peter@...esztesschmidt.de>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>
Subject: Re: [patch V3 26/60] x86/apic/32: Decrapify the def_bigsmp mechanism
On Mon, Aug 07 2023 at 13:11, Dave Hansen wrote:
> On 8/1/23 03:47, Thomas Gleixner wrote:
> ...
>> -void __init default_setup_apic_routing(void)
>> +void __init x86_32_probe_bigsmp_early(void)
>> {
>> - int version = boot_cpu_apic_version;
>> + if (nr_cpu_ids <= 8 || xen_pv_domain())
>> + return;
> ...
>> +void __init default_setup_apic_routing(void)
>> +{
>> + if (nr_cpu_ids >= 8 && !xen_pv_domain())
>> + apic_bigsmp_force();
>
> I thought bigsmp didn't come into play until 9 or more CPUs. Won't this
> do apic_bigsmp_force() at nr_cpu_ids==8?
>
> Should this be:
>
> if (nr_cpu_ids > 8 && !xen_pv_domain())
> apic_bigsmp_force();
>
> ?
Yes, obviously. Thanks for catching that
Powered by blists - more mailing lists