Re: [PATCH v2] mm: thp: support "THPeligible" semantics for mTHP with anonymous shmem

["Bang Li" <libang.li@antgroup.com>]

Hi Baolin,

On 2024/7/2 14:14, Baolin Wang wrote:
> 
> 
> On 2024/7/2 10:34, Bang Li wrote:
>> After the commit 7fb1b252afb5 ("mm: shmem: add mTHP support for
>> anonymous shmem"), we can configure different policies through
>> the multi-size THP sysfs interface for anonymous shmem. But
>> currently "THPeligible" indicates only whether the mapping is
>> eligible for allocating THP-pages as well as the THP is PMD
>> mappable or not for anonymous shmem, we need to support semantics
>> for mTHP with anonymous shmem similar to those for mTHP with
>> anonymous memory.
>>
>> Signed-off-by: Bang Li <libang.li@antgroup.com>
>> ---
>> Changes since v1 [1]:
>>   - Put anonymous shmem mthp related logic into
>>     thp_vma_allowable_orders() (per David)
>>
>> [1] 
>> https://lore.kernel.org/linux-mm/20240628104926.34209-1-libang.li@antgroup.com/
>> ---
>>   include/linux/huge_mm.h | 11 +++++++++++
>>   mm/huge_memory.c        | 13 +++++++++----
>>   mm/shmem.c              |  9 +--------
>>   3 files changed, 21 insertions(+), 12 deletions(-)
>>
>> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
>> index 212cca384d7e..f87136f38aa1 100644
>> --- a/include/linux/huge_mm.h
>> +++ b/include/linux/huge_mm.h
>> @@ -267,6 +267,10 @@ unsigned long thp_vma_allowable_orders(struct 
>> vm_area_struct *vma,
>>       return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, 
>> orders);
>>   }
>> +unsigned long shmem_allowable_huge_orders(struct inode *inode,
>> +                struct vm_area_struct *vma, pgoff_t index,
>> +                bool global_huge);
>> +
>>   struct thpsize {
>>       struct kobject kobj;
>>       struct list_head node;
>> @@ -460,6 +464,13 @@ static inline unsigned long 
>> thp_vma_allowable_orders(struct vm_area_struct *vma,
>>       return 0;
>>   }
>> +static inline unsigned long shmem_allowable_huge_orders(struct inode 
>> *inode,
>> +                struct vm_area_struct *vma, pgoff_t index,
>> +                bool global_huge)
>> +{
>> +    return 0;
>> +}
> 
> This function should be placed in the ‘shmem_fs.h’ header file, just 
> like shmem_is_huge().

Looks more reasonable，thank you for your review.

Thanks,
Bang