On 2022/6/24 16:03, Muchun Song wrote:
> On Fri, Jun 24, 2022 at 10:25:48AM +0800, Miaohe Lin wrote:
>> On 2022/6/24 7:51, Naoya Horiguchi wrote:
>>> From: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
>>>
>>> I found a weird state of 1GB hugepage pool, caused by the following
>>> procedure:
>>>
>>> - run a process reserving all free 1GB hugepages,
>>> - shrink free 1GB hugepage pool to zero (i.e. writing 0 to
>>> /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages), then
>>> - kill the reserving process.
>>>
>>> , then all the hugepages are free *and* surplus at the same time.
>>>
>>> $ cat /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages
>>> 3
>>> $ cat /sys/kernel/mm/hugepages/hugepages-1048576kB/free_hugepages
>>> 3
>>> $ cat /sys/kernel/mm/hugepages/hugepages-1048576kB/resv_hugepages
>>> 0
>>> $ cat /sys/kernel/mm/hugepages/hugepages-1048576kB/surplus_hugepages
>>> 3
>>>
>>> This state is resolved by reserving and allocating the pages then
>>> freeing them again, so this seems not to result in serious problem.
>>> But it's a little surprizing (shrinking pool suddenly fails).
>>>
>>> This behavior is caused by hstate_is_gigantic() check in
>>> return_unused_surplus_pages(). This was introduced so long ago in 2008
>>> by commit aa888a74977a ("hugetlb: support larger than MAX_ORDER"), and
>>> it seems to me that this check is no longer unnecessary. Let's remove it.
>>
>> s/unnecessary/necessary/
>>
>>>
>>> Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
>>> ---
>>> mm/hugetlb.c | 4 ----
>>> 1 file changed, 4 deletions(-)
>>>
>>> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
>>> index a57e1be41401..c538278170a2 100644
>>> --- a/mm/hugetlb.c
>>> +++ b/mm/hugetlb.c
>>> @@ -2432,10 +2432,6 @@ static void return_unused_surplus_pages(struct hstate *h,
>>> /* Uncommit the reservation */
>>> h->resv_huge_pages -= unused_resv_pages;
>>>
>>> - /* Cannot return gigantic pages currently */
>>> - if (hstate_is_gigantic(h))
>>> - goto out;
>>> -
>>
>> IIUC it might be better to do the below check:
>> /*
>> * Cannot return gigantic pages currently if runtime gigantic page
>> * allocation is not supported.
>> */
>> if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
>> goto out;
>>
>
> The change looks good to me. However, the comments above is unnecessary
> since gigantic_page_runtime_supported() is straightforward.
Agree. The comments can be removed.
>
> Thanks.
Thanks for reviewing.
>
>> But I might be miss something.
>>
>> Thanks.
>>
>>> /*
>>> * Part (or even all) of the reservation could have been backed
>>> * by pre-allocated pages. Only free surplus pages.
>>>
>>
>>
> .
>
