Re: [v7 11/16] mm/migrate_device: add THP splitting during migration

[Zi Yan <ziy@nvidia.com>]

On 19 Oct 2025, at 18:49, Balbir Singh wrote:

> On 10/19/25 19:19, Wei Yang wrote:
>> On Wed, Oct 01, 2025 at 04:57:02PM +1000, Balbir Singh wrote:
>> [...]
>>> static int __folio_split(struct folio *folio, unsigned int new_order,
>>> 		struct page *split_at, struct page *lock_at,
>>> -		struct list_head *list, bool uniform_split)
>>> +		struct list_head *list, bool uniform_split, bool unmapped)
>>> {
>>> 	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
>>> 	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
>>> @@ -3765,13 +3757,15 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
>>> 		 * is taken to serialise against parallel split or collapse
>>> 		 * operations.
>>> 		 */
>>> -		anon_vma = folio_get_anon_vma(folio);
>>> -		if (!anon_vma) {
>>> -			ret = -EBUSY;
>>> -			goto out;
>>> +		if (!unmapped) {
>>> +			anon_vma = folio_get_anon_vma(folio);
>>> +			if (!anon_vma) {
>>> +				ret = -EBUSY;
>>> +				goto out;
>>> +			}
>>> +			anon_vma_lock_write(anon_vma);
>>> 		}
>>> 		mapping = NULL;
>>> -		anon_vma_lock_write(anon_vma);
>>> 	} else {
>>> 		unsigned int min_order;
>>> 		gfp_t gfp;
>>> @@ -3838,7 +3832,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
>>> 		goto out_unlock;
>>> 	}
>>>
>>> -	unmap_folio(folio);
>>> +	if (!unmapped)
>>> +		unmap_folio(folio);
>>>
>>> 	/* block interrupt reentry in xa_lock and spinlock */
>>> 	local_irq_disable();
>>> @@ -3925,10 +3920,13 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
>>>
>>> 			next = folio_next(new_folio);
>>>
>>> +			zone_device_private_split_cb(folio, new_folio);
>>> +
>>> 			expected_refs = folio_expected_ref_count(new_folio) + 1;
>>> 			folio_ref_unfreeze(new_folio, expected_refs);
>>>
>>> -			lru_add_split_folio(folio, new_folio, lruvec, list);
>>> +			if (!unmapped)
>>> +				lru_add_split_folio(folio, new_folio, lruvec, list);
>>>
>>> 			/*
>>> 			 * Anonymous folio with swap cache.
>>> @@ -3959,6 +3957,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
>>> 			__filemap_remove_folio(new_folio, NULL);
>>> 			folio_put_refs(new_folio, nr_pages);
>>> 		}
>>> +
>>> +		zone_device_private_split_cb(folio, NULL);
>>> 		/*
>>> 		 * Unfreeze @folio only after all page cache entries, which
>>> 		 * used to point to it, have been updated with new folios.
>>> @@ -3982,6 +3982,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
>>>
>>> 	local_irq_enable();
>>>
>>> +	if (unmapped)
>>> +		return ret;
>>
>> As the comment of __folio_split() and __split_huge_page_to_list_to_order()
>> mentioned:
>>
>>   * The large folio must be locked
>>   * After splitting, the after-split folio containing @lock_at remains locked
>>
>> But here we seems to change the prerequisites.
>>
>> Hmm.. I am not sure this is correct.
>>
>
> The code is correct, but you are right in that the documentation needs to be updated.
> When "unmapped", we do want to leave the folios locked after the split.

Sigh, this "unmapped" code needs so many special branches and a different locking
requirement. It should be a separate function to avoid confusions.

--
Best Regards,
Yan, Zi