Re: Ping: Re: [PATCH] x86: correct vCPU dirty CPU handling

[Andrew Cooper <andrew.cooper3@citrix.com>]

On 15/05/18 09:25, Jan Beulich wrote:
>>>> On 26.04.18 at 12:52, <JBeulich@suse.com> wrote:
>>>>> On 26.04.18 at 11:51, <andrew.cooper3@citrix.com> wrote:
>>> On 26/04/18 10:41, Jan Beulich wrote:
>>>> --- a/xen/arch/x86/mm.c
>>>> +++ b/xen/arch/x86/mm.c
>>>> @@ -1202,11 +1202,23 @@ void put_page_from_l1e(l1_pgentry_t l1e,
>>>>               unlikely(((page->u.inuse.type_info & PGT_count_mask) != 0)) &&
>>>>               (l1e_owner == pg_owner) )
>>>>          {
>>>> +            cpumask_t *mask = this_cpu(scratch_cpumask);
>>>> +
>>>> +            cpumask_clear(mask);
>>>> +
>>>>              for_each_vcpu ( pg_owner, v )
>>>>              {
>>>> -                if ( pv_destroy_ldt(v) )
>>>> -                    flush_tlb_mask(cpumask_of(v->dirty_cpu));
>>>> +                unsigned int cpu;
>>>> +
>>>> +                if ( !pv_destroy_ldt(v) )
>>>> +                    continue;
>>>> +                cpu = read_atomic(&v->dirty_cpu);
>>>> +                if ( is_vcpu_dirty_cpu(cpu) )
>>>> +                    __cpumask_set_cpu(cpu, mask);
>>>>              }
>>>> +
>>>> +            if ( !cpumask_empty(mask) )
>>>> +                flush_tlb_mask(mask);
>>> Thinking about this, what is wrong with:
>>>
>>> bool flush;
>>>
>>> for_each_vcpu ( pg_owner, v )
>>>     if ( pv_destroy_ldt(v) )
>>>         flush = true;
>>>
>>> if ( flush )
>>>    flush_tlb_mask(pg_owner->dirty_cpumask);
>>>
>>> This is far less complicated cpumask handling.  As the loop may be long,
>>> it avoids flushing pcpus which have subsequently switched away from
>>> pg_owner context.  It also avoids all playing with v->dirty_cpu.
>> That would look to be correct, but I'm not sure it would be an improvement:
>> While it may avoid flushing some CPUs, it may then do extra flushes on
>> others (which another vCPU of the domain has been switched to). Plus it
>> would flush even those CPUs where pv_destroy_ldt() has returned false,
>> as long as the function returned true at least once.
> Ping?

I'm not sure it is worth trying to optimise this code.  I've got a patch
for 4.12 to leave it compiled out by default.

Therefore, Acked-by: Andrew Cooper <andrew.cooper3@citrix.com> on the
original patch.

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel