Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Thomas Gleixner <tglx@linutronix.de>
To:     Dave Hansen <dave.hansen@intel.com>,
        LKML <linux-kernel@vger.kernel.org>
Cc:     x86@kernel.org, Andrew Cooper <andrew.cooper3@citrix.com>,
        Tom Lendacky <thomas.lendacky@amd.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Wei Liu <wei.liu@kernel.org>,
        Arjan van de Ven <arjan@linux.intel.com>,
        Juergen Gross <jgross@suse.com>,
        Michael Kelley <mikelley@microsoft.com>,
        Peter Keresztes Schmidt <peter@keresztesschmidt.de>,
        "Peter Zijlstra (Intel)" <peterz@infradead.org>
Subject: Re: [patch V3 26/60] x86/apic/32: Decrapify the def_bigsmp mechanism
In-Reply-To: <09100858-3be2-a9f2-e0af-b6cad67d760b@intel.com>
References: <20230801103042.936020332@linutronix.de>
 <20230801103816.584394452@linutronix.de>
 <09100858-3be2-a9f2-e0af-b6cad67d760b@intel.com>
Date:   Mon, 07 Aug 2023 23:18:45 +0200
Message-ID: <877cq6tutm.ffs@tglx>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

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