On 13.02.2018 15:16, David Hildenbrand wrote:
> On 09.02.2018 10:34, Janosch Frank wrote:
>> When changing guest pmds, we don't need to take care of the
>> corresponding host pmd. This means, we don't need to flush the host
>> TLB entries and we don't need to notify on all gmaps.
>>
>> Let's introduce a function, that exchanges a pmd and takes care of the
>> necessary flushing and notification.
>
> stale comment, notification is handled in a different patch.
>
>>
>> Signed-off-by: Janosch Frank <frankja@xxxxxxxxxxxxxxxxxx>
>> ---
[...]
> This fits into one line
Thanks!
Fixed for all of them.
>
>> + else
>> + __pmdp_csp(pmdp);
>> + *pmdp = new;
>> +}
>> +
>> static inline void thp_split_mm(struct mm_struct *mm)
>> {
>> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>>
>
> Apart from that, looks good to me. (although very similar to
> gmap_pmdp_idte_global - can we reuse gmap_pmdp_xchg() in
> gmap_pmdp_idte_global?)
Hrm, we'd need to disable notifications and do the split_free only for
the idte case. I'm not convinced that we gain a lot by doing that.
Attachment:
signature.asc
Description: OpenPGP digital signature
