Re: [PATCH v7 2/8] x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range

[Alex Shi <alex.shi@intel.com>]

On 05/24/2012 05:44 PM, Jan Beulich wrote:

>>>> On 24.05.12 at 10:55, Alex Shi <alex.shi@intel.com> wrote:
>> On 05/24/2012 04:12 PM, Jan Beulich wrote:
>>
>>>>>> On 24.05.12 at 08:41, Alex Shi <alex.shi@intel.com> wrote:
>>>> So, the following change should be more safe for PV?
>>>>
>>>> -       if (va == TLB_FLUSH_ALL) {
>>>> -               args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
>>>> -       } else {
>>>> -               args->op.cmd = MMUEXT_INVLPG_MULTI;
>>>> -               args->op.arg1.linear_addr = va;
>>>> -       }
>>>> +       args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
>>>
>>> This would be safe ...
>>>
>>>> +       if (start != TLB_FLUSH_ALL)
>>>> +               args->op.arg1.linear_addr = start;
>>>
>>> ... and then this superfluous, but it'd result in an unconditional
>>> full TLB flush. When start and end (or perhaps end-1, assuming
>>> end is not inclusive) are on the same page, MMUEXT_INVLPG_MULTI
>>> should be used; MMUEXT_TLB_FLUSH_MULTI might need to be
>>> used in all other cases, unless you want to split multi-page, non-
>>> global invalidations into multiple MMUEXT_INVLPG_MULTI-s (which
>>> would appear to be what the whole patch aims at).
>>
>>
>>         args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
>> -       if (start != TLB_FLUSH_ALL)
>> +       if (start != TLB_FLUSH_ALL && (end - start) < PAGE_SIZE) {
> 
> Assuming 'end' is not inclusive (you didn't clarify that),
> 
>        if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
> 
> (and only if 'start' is guaranteed to be page aligned).


I still a idiot for xen and a newbie for kernel. :)
AFAIK, if system just flush one page, it won't set end there. But anyway
using '<=' has no problem.

> 
>> +               args->op.cmd = MMUEXT_INVLPG_MULTI;
>>                 args->op.arg1.linear_addr = start;
>> +       }
>>
>> So, above it correct code for xen?
>> As to the xen optimisation of flush range, it is may better to be done
>> in a separate patch.
> 
> Agreed.


Thanks for all comments!

> 
> Jan
>