lkml.org 
[lkml]   [2023]   [Aug]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH 0/2] don't use mapcount() to check large folio sharing
From
On 02.08.23 14:40, Ryan Roberts wrote:
> On 02/08/2023 13:35, Yin, Fengwei wrote:
>>
>>
>> On 8/2/2023 6:27 PM, Ryan Roberts wrote:
>>> On 28/07/2023 17:13, Yin Fengwei wrote:
>>>> In madvise_cold_or_pageout_pte_range() and madvise_free_pte_range(),
>>>> folio_mapcount() is used to check whether the folio is shared. But it's
>>>> not correct as folio_mapcount() returns total mapcount of large folio.
>>>>
>>>> Use folio_estimated_sharers() here as the estimated number is enough.
>>>>
>>>> Yin Fengwei (2):
>>>> madvise: don't use mapcount() against large folio for sharing check
>>>> madvise: don't use mapcount() against large folio for sharing check
>>>>
>>>> mm/huge_memory.c | 2 +-
>>>> mm/madvise.c | 6 +++---
>>>> 2 files changed, 4 insertions(+), 4 deletions(-)
>>>>
>>>
>>> As a set of fixes, I agree this is definitely an improvement, so:
>>>
>>> Reviewed-By: Ryan Roberts
>> Thanks.
>>
>>>
>>>
>>> But I have a couple of comments around further improvements;
>>>
>>> Once we have the scheme that David is working on to be able to provide precise
>>> exclusive vs shared info, we will probably want to move to that. Although that
>>> scheme will need access to the mm_struct of a process known to be mapping the
>>> folio. We have that info, but its not passed to folio_estimated_sharers() so we
>>> can't just reimplement folio_estimated_sharers() - we will need to rework these
>>> call sites again.
>> Yes. This could be extra work. Maybe should delay till David's work is done.
>
> What you have is definitely an improvement over what was there before. And is
> probably the best we can do without David's scheme. So I wouldn't delay this.
> Just pointing out that we will be able to make it even better later on (if
> David's stuff goes in).

Agreed, we just should be careful and clearly spell out the implications
and that this is eventually also not what we 100% want.

That MADV_PAGEOUT now fails on a PTE-mapped THP -- as can be seen when
executing the cow selftest where MADV_PAGEOUT will essentially fail --
is certainly undesired and should be fixed IMHO.

--
Cheers,

David / dhildenb

\
 
 \ /
  Last update: 2023-08-02 14:47    [W:0.095 / U:2.152 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site