Re: [PATCH v5 2/6] mm: remap unused subpages to shared zeropage when splitting isolated thp

[Zi Yan <ziy@nvidia.com>]

[-- Attachment #1: Type: text/plain, Size: 4891 bytes --]

On 23 Oct 2024, at 12:50, Usama Arif wrote:

> On 23/10/2024 17:21, Zi Yan wrote:
>> On 30 Aug 2024, at 6:03, Usama Arif wrote:
>>
>>> From: Yu Zhao <yuzhao@google.com>
>>>
>>> Here being unused means containing only zeros and inaccessible to
>>> userspace. When splitting an isolated thp under reclaim or migration,
>>> the unused subpages can be mapped to the shared zeropage, hence saving
>>> memory. This is particularly helpful when the internal
>>> fragmentation of a thp is high, i.e. it has many untouched subpages.
>>>
>>> This is also a prerequisite for THP low utilization shrinker which will
>>> be introduced in later patches, where underutilized THPs are split, and
>>> the zero-filled pages are freed saving memory.
>>>
>>> Signed-off-by: Yu Zhao <yuzhao@google.com>
>>> Tested-by: Shuang Zhai <zhais@google.com>
>>> Signed-off-by: Usama Arif <usamaarif642@gmail.com>
>>> ---
>>>  include/linux/rmap.h |  7 ++++-
>>>  mm/huge_memory.c     |  8 ++---
>>>  mm/migrate.c         | 72 ++++++++++++++++++++++++++++++++++++++------
>>>  mm/migrate_device.c  |  4 +--
>>>  4 files changed, 75 insertions(+), 16 deletions(-)
>>>
>>> diff --git a/include/linux/rmap.h b/include/linux/rmap.h
>>> index 91b5935e8485..d5e93e44322e 100644
>>> --- a/include/linux/rmap.h
>>> +++ b/include/linux/rmap.h
>>> @@ -745,7 +745,12 @@ int folio_mkclean(struct folio *);
>>>  int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
>>>  		      struct vm_area_struct *vma);
>>>
>>> -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);
>>> +enum rmp_flags {
>>> +	RMP_LOCKED		= 1 << 0,
>>> +	RMP_USE_SHARED_ZEROPAGE	= 1 << 1,
>>> +};
>>> +
>>> +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags);
>>>
>>>  /*
>>>   * rmap_walk_control: To control rmap traversing for specific needs
>>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>>> index 0c48806ccb9a..af60684e7c70 100644
>>> --- a/mm/huge_memory.c
>>> +++ b/mm/huge_memory.c
>>> @@ -3020,7 +3020,7 @@ bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
>>>  	return false;
>>>  }
>>>
>>> -static void remap_page(struct folio *folio, unsigned long nr)
>>> +static void remap_page(struct folio *folio, unsigned long nr, int flags)
>>>  {
>>>  	int i = 0;
>>>
>>> @@ -3028,7 +3028,7 @@ static void remap_page(struct folio *folio, unsigned long nr)
>>>  	if (!folio_test_anon(folio))
>>>  		return;
>>>  	for (;;) {
>>> -		remove_migration_ptes(folio, folio, true);
>>> +		remove_migration_ptes(folio, folio, RMP_LOCKED | flags);
>>>  		i += folio_nr_pages(folio);
>>>  		if (i >= nr)
>>>  			break;
>>> @@ -3240,7 +3240,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>>>
>>>  	if (nr_dropped)
>>>  		shmem_uncharge(folio->mapping->host, nr_dropped);
>>> -	remap_page(folio, nr);
>>> +	remap_page(folio, nr, PageAnon(head) ? RMP_USE_SHARED_ZEROPAGE : 0);
>>>
>>>  	/*
>>>  	 * set page to its compound_head when split to non order-0 pages, so
>>> @@ -3542,7 +3542,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
>>>  		if (mapping)
>>>  			xas_unlock(&xas);
>>>  		local_irq_enable();
>>> -		remap_page(folio, folio_nr_pages(folio));
>>> +		remap_page(folio, folio_nr_pages(folio), 0);
>>>  		ret = -EAGAIN;
>>>  	}
>>>
>>> diff --git a/mm/migrate.c b/mm/migrate.c
>>> index 6f9c62c746be..d039863e014b 100644
>>> --- a/mm/migrate.c
>>> +++ b/mm/migrate.c
>>> @@ -204,13 +204,57 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
>>>  	return true;
>>>  }
>>>
>>> +static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
>>> +					  struct folio *folio,
>>> +					  unsigned long idx)
>>> +{
>>> +	struct page *page = folio_page(folio, idx);
>>> +	bool contains_data;
>>> +	pte_t newpte;
>>> +	void *addr;
>>> +
>>> +	VM_BUG_ON_PAGE(PageCompound(page), page);
>>
>> This should be:
>>
>> diff --git a/mm/migrate.c b/mm/migrate.c
>> index e950fd62607f..7ffdbe078aa7 100644
>> --- a/mm/migrate.c
>> +++ b/mm/migrate.c
>> @@ -206,7 +206,8 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
>>         pte_t newpte;
>>         void *addr;
>>
>> -       VM_BUG_ON_PAGE(PageCompound(page), page);
>> +       if (PageCompound(page))
>> +               return false;
>>         VM_BUG_ON_PAGE(!PageAnon(page), page);
>>         VM_BUG_ON_PAGE(!PageLocked(page), page);
>>         VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page);
>>
>> Otherwise, splitting anonymous large folios to non order-0 ones just
>> triggers this BUG_ON.
>>
>
> That makes sense, would you like to send the fix?
>
> Adding Yu Zhao to "To" incase he has any objections.
>
Sure, will do.

Best Regards,
Yan, Zi

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 854 bytes --]