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

[Balbir Singh <balbirs@nvidia.com>]

On 10/20/25 09:59, Zi Yan wrote:
> 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.
> 

Yep, I have a patch for it, I am also waiting on Matthew's feedback, FYI, here is
a WIP patch that can be applied on top of the series

---
 include/linux/huge_mm.h |   5 +-
 mm/huge_memory.c        | 137 ++++++++++++++++++++++++++++++++++------
 mm/migrate_device.c     |   3 +-
 3 files changed, 120 insertions(+), 25 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c4a811958cda..86e1cefaf391 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -366,7 +366,8 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
 
 bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins);
 int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
-		unsigned int new_order, bool unmapped);
+		unsigned int new_order);
+int split_unmapped_folio_to_order(struct folio *folio, unsigned int new_order);
 int min_order_for_split(struct folio *folio);
 int split_folio_to_list(struct folio *folio, struct list_head *list);
 bool uniform_split_supported(struct folio *folio, unsigned int new_order,
@@ -379,7 +380,7 @@ int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
 static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order)
 {
-	return __split_huge_page_to_list_to_order(page, list, new_order, false);
+	return __split_huge_page_to_list_to_order(page, list, new_order);
 }
 
 /*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8c82a0ac6e69..e20cbf68d037 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3711,7 +3711,6 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order,
  * @lock_at: a page within @folio to be left locked to caller
  * @list: after-split folios will be put on it if non NULL
  * @uniform_split: perform uniform split or not (non-uniform split)
- * @unmapped: The pages are already unmapped, they are migration entries.
  *
  * It calls __split_unmapped_folio() to perform uniform and non-uniform split.
  * It is in charge of checking whether the split is supported or not and
@@ -3727,7 +3726,7 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order,
  */
 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, bool unmapped)
+		struct list_head *list, bool uniform_split)
 {
 	struct deferred_split *ds_queue;
 	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
@@ -3777,14 +3776,12 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		 * is taken to serialise against parallel split or collapse
 		 * operations.
 		 */
-		if (!unmapped) {
-			anon_vma = folio_get_anon_vma(folio);
-			if (!anon_vma) {
-				ret = -EBUSY;
-				goto out;
-			}
-			anon_vma_lock_write(anon_vma);
+		anon_vma = folio_get_anon_vma(folio);
+		if (!anon_vma) {
+			ret = -EBUSY;
+			goto out;
 		}
+		anon_vma_lock_write(anon_vma);
 		mapping = NULL;
 	} else {
 		unsigned int min_order;
@@ -3852,8 +3849,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		goto out_unlock;
 	}
 
-	if (!unmapped)
-		unmap_folio(folio);
+	unmap_folio(folio);
 
 	/* block interrupt reentry in xa_lock and spinlock */
 	local_irq_disable();
@@ -3954,8 +3950,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 			expected_refs = folio_expected_ref_count(new_folio) + 1;
 			folio_ref_unfreeze(new_folio, expected_refs);
 
-			if (!unmapped)
-				lru_add_split_folio(folio, new_folio, lruvec, list);
+			lru_add_split_folio(folio, new_folio, lruvec, list);
 
 			/*
 			 * Anonymous folio with swap cache.
@@ -4011,9 +4006,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 	local_irq_enable();
 
-	if (unmapped)
-		return ret;
-
 	if (nr_shmem_dropped)
 		shmem_uncharge(mapping->host, nr_shmem_dropped);
 
@@ -4057,6 +4049,111 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	return ret;
 }
 
+/*
+ * This function is a helper for splitting folios that have already been unmapped.
+ * The use case is that the device or the CPU can refuse to migrate THP pages in
+ * the middle of migration, due to allocation issues on either side
+ *
+ * The high level code is copied from __folio_split, since the pages are anonymous
+ * and are already isolated from the LRU, the code has been simplified to not
+ * burden __folio_split with unmapped sprinkled into the code.
+ *
+ * None of the split folios are unlocked
+ */
+int split_unmapped_folio_to_order(struct folio *folio, unsigned int new_order)
+{
+	int extra_pins;
+	int ret = 0;
+	struct folio *new_folio, *next;
+	struct folio *end_folio = folio_next(folio);
+	struct deferred_split *ds_queue;
+	int old_order = folio_order(folio);
+
+	VM_WARN_ON_FOLIO(folio_mapped(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio);
+
+	if (!can_split_folio(folio, 1, &extra_pins)) {
+		ret = -EAGAIN;
+		goto err;
+	}
+
+	local_irq_disable();
+	/* Prevent deferred_split_scan() touching ->_refcount */
+	ds_queue = folio_split_queue_lock(folio);
+	if (folio_ref_freeze(folio, 1 + extra_pins)) {
+		int expected_refs;
+		struct swap_cluster_info *ci = NULL;
+
+		if (old_order > 1) {
+			if (!list_empty(&folio->_deferred_list)) {
+				ds_queue->split_queue_len--;
+				/*
+				 * Reinitialize page_deferred_list after
+				 * removing the page from the split_queue,
+				 * otherwise a subsequent split will see list
+				 * corruption when checking the
+				 * page_deferred_list.
+				 */
+				list_del_init(&folio->_deferred_list);
+			}
+			if (folio_test_partially_mapped(folio)) {
+				folio_clear_partially_mapped(folio);
+				mod_mthp_stat(old_order,
+					MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
+			}
+			/*
+			 * Reinitialize page_deferred_list after removing the
+			 * page from the split_queue, otherwise a subsequent
+			 * split will see list corruption when checking the
+			 * page_deferred_list.
+			 */
+			list_del_init(&folio->_deferred_list);
+		}
+		split_queue_unlock(ds_queue);
+
+		if (folio_test_swapcache(folio))
+			ci = swap_cluster_get_and_lock(folio);
+
+		ret = __split_unmapped_folio(folio, new_order, &folio->page,
+					     NULL, NULL, true);
+
+		/*
+		 * Unfreeze after-split folios
+		 */
+		for (new_folio = folio_next(folio); new_folio != end_folio;
+		     new_folio = next) {
+			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);
+			if (ci)
+				__swap_cache_replace_folio(ci, folio, new_folio);
+		}
+
+		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.
+		 * Otherwise, a parallel folio_try_get() can grab @folio
+		 * and its caller can see stale page cache entries.
+		 */
+		expected_refs = folio_expected_ref_count(folio) + 1;
+		folio_ref_unfreeze(folio, expected_refs);
+
+		if (ci)
+			swap_cluster_unlock(ci);
+	} else {
+		split_queue_unlock(ds_queue);
+		ret = -EAGAIN;
+	}
+	local_irq_enable();
+err:
+	return ret;
+}
+
 /*
  * This function splits a large folio into smaller folios of order @new_order.
  * @page can point to any page of the large folio to split. The split operation
@@ -4105,12 +4202,11 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
  * with the folio. Splitting to order 0 is compatible with all folios.
  */
 int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
-				     unsigned int new_order, bool unmapped)
+				     unsigned int new_order)
 {
 	struct folio *folio = page_folio(page);
 
-	return __folio_split(folio, new_order, &folio->page, page, list, true,
-				unmapped);
+	return __folio_split(folio, new_order, &folio->page, page, list, true);
 }
 
 /*
@@ -4138,8 +4234,7 @@ int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list
 int folio_split(struct folio *folio, unsigned int new_order,
 		struct page *split_at, struct list_head *list)
 {
-	return __folio_split(folio, new_order, split_at, &folio->page, list,
-			false, false);
+	return __folio_split(folio, new_order, split_at, &folio->page, list, false);
 }
 
 int min_order_for_split(struct folio *folio)
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index c869b272e85a..23515f3ffc35 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -918,8 +918,7 @@ static int migrate_vma_split_unmapped_folio(struct migrate_vma *migrate,
 
 	folio_get(folio);
 	split_huge_pmd_address(migrate->vma, addr, true);
-	ret = __split_huge_page_to_list_to_order(folio_page(folio, 0), NULL,
-							0, true);
+	ret = split_unmapped_folio_to_order(folio, 0);
 	if (ret)
 		return ret;
 	migrate->src[idx] &= ~MIGRATE_PFN_COMPOUND;
-- 
2.51.0