On Mon, Jan 20, 2020 at 08:22:37AM +0100, Michal Hocko wrote:
>On Sat 18-01-20 15:36:06, David Rientjes wrote:
>> On Sat, 18 Jan 2020, Andrew Morton wrote:
>>
>> > On Sat, 18 Jan 2020 07:38:36 +0800 Wei Yang <richardw.yang@xxxxxxxxxxxxxxx> wrote:
>> >
>> > > If compound is true, this means it is a PMD mapped THP. Which implies
>> > > the page is not linked to any defer list. So the first code chunk will
>> > > not be executed.
>> > >
>> > > Also with this reason, it would not be proper to add this page to a
>> > > defer list. So the second code chunk is not correct.
>> > >
>> > > Based on this, we should remove the defer list related code.
>> > >
>> > > Fixes: 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware")
>> > >
>> > > Signed-off-by: Wei Yang <richardw.yang@xxxxxxxxxxxxxxx>
>> > > Suggested-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
>> > > Cc: <stable@xxxxxxxxxxxxxxx> [5.4+]
>> >
>> > This patch is identical to "mm: thp: grab the lock before manipulating
>> > defer list", which is rather confusing. Please let people know when
>> > this sort of thing is done.
>> >
>> > The earlier changelog mentioned a possible race condition. This
>> > changelog does not. In fact this changelog fails to provide any
>> > description of any userspace-visible runtime effects of the bug.
>> > Please send along such a description for inclusion, as always.
>> >
>>
>> The locking concern that Wei was originally looking at is no longer an
>> issue because we determined that the code in question could simply be
>> removed.
>>
>> I think the following can be added to the changelog:
>>
>> ----->o-----
>>
>> When migrating memcg charges of thp memory, there are two possibilities:
>>
>> (1) The underlying compound page is mapped by a pmd and thus does is not
>> on a deferred split queue (it's mapped), or
>>
>> (2) The compound page is not mapped by a pmd and is awaiting split on a
>> deferred split queue.
>>
>> The current charge migration implementation does *not* migrate charges for
>> thp memory on the deferred split queue, it only migrates charges for pages
>> that are mapped by a pmd.
>>
>> Thus, to migrate charges, the underlying compound page cannot be on a
>> deferred split queue; no list manipulation needs to be done in
>> mem_cgroup_move_account().
>>
>> With the current code, the underlying compound page is moved to the
>> deferred split queue of the memcg its memory is not charged to, so
>> susbequent reclaim will consider these pages for the wrong memcg. Remove
>> the deferred split queue handling in mem_cgroup_move_account() entirely.
>
>I believe this still doesn't describe the underlying problem to the full
>extent. What happens with the page on the deferred list when it
>shouldn't be there in fact? Unless I am missing something deferred_split_scan
>will simply split that huge page. Which is a bit unfortunate but nothing
>really critical. This should be mentioned in the changelog.
>
Per my understanding, if we do the split when it is not necessary, we
probably have a lower performance due to tlb miss. For others, I don't see the
impact.
>With that clarified, feel free to add
>
>Acked-by: Michal Hocko <mhocko@xxxxxxxx>
>
>--
>Michal Hocko
>SUSE Labs
--
Wei Yang
Help you, Help me
