Re: [PATCH v4 1/3] x86: Use native RDTSC(P) execution when guest and host frequencies are the same

[Boris Ostrovsky <boris.ostrovsky@oracle.com>]

On 04/16/2014 05:54 AM, Jan Beulich wrote:
>>>> On 16.04.14 at 03:27, <boris.ostrovsky@oracle.com> wrote:
>> @@ -1889,10 +1890,14 @@ void tsc_set_info(struct domain *d,
>>           d->arch.vtsc_offset = get_s_time() - elapsed_nsec;
>>           d->arch.tsc_khz = gtsc_khz ? gtsc_khz : cpu_khz;
>>           set_time_scale(&d->arch.vtsc_to_ns, d->arch.tsc_khz * 1000 );
>> -        /* use native TSC if initial host has safe TSC, has not migrated
>> -         * yet and tsc_khz == cpu_khz */
>> -        if ( host_tsc_is_safe() && incarnation == 0 &&
>> -                d->arch.tsc_khz == cpu_khz )
>> +        /*
>> +         * Use native TSC if initial host has safe TSC and either has not
>> +         * migrated yet or tsc_khz == cpu_khz (either "naturally" or via
>> +         * TSC scaling)
>> +         */
>> +        if ( host_tsc_is_safe() &&
>> +             (incarnation == 0 || d->arch.tsc_khz == cpu_khz ||
>> +              cpu_has_tsc_ratio) )
> Can't you drop checking incarnation to be zero then? In that case,
> afaict d->arch.tsc_khz == cpu_khz due to gtsc_khz being passed
> in as zero from arch_domain_create().

Yes, it's pointless. I was thinking that maybe toolstack may pass 
gtsc_khz != cpu_khz during initial boot (it doesn't do it now, but 
theoretically it could) but then we shouldn't be using vtsc=0 in that 
case anyway.

-boris