diff mbox series

[v2,3/6] mm/huge_memory: add buddy allocator like folio_split()

Message ID 20241101150357.1752726-4-ziy@nvidia.com (mailing list archive)
State New
Headers show
Series Buddy allocator like folio split | expand

Commit Message

Zi Yan Nov. 1, 2024, 3:03 p.m. UTC
folio_split() splits a large folio in the same way as buddy allocator
splits a large free page for allocation. The purpose is to minimize the
number of folios after the split. For example, if user wants to free the
3rd subpage in a order-9 folio, folio_split() will split the order-9 folio
as:
O-0, O-0, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-8 if it is anon
O-1,      O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache
Since anon folio does not support order-1 yet.

It generates fewer folios than existing page split approach, which splits
the order-9 to 512 order-0 folios.

folio_split() and existing split_huge_page_to_list_to_order() share
the folio unmapping and remapping code in __folio_split() and the common
backend split code in __folio_split_without_mapping() using
uniform_split variable to distinguish their operations.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/huge_memory.c | 56 +++++++++++++++++++++++++++++++++++-------------
 1 file changed, 41 insertions(+), 15 deletions(-)
diff mbox series

Patch

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 63ca870ca3fb..4f227d246ac5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3706,11 +3706,10 @@  static int __folio_split_without_mapping(struct folio *folio, int new_order,
 }
 
 static int __folio_split(struct folio *folio, unsigned int new_order,
-		struct page *page, struct list_head *list)
+		struct page *page, struct list_head *list, bool uniform_split)
 {
 	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
-	/* reset xarray order to new order after split */
-	XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order);
+	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
 	bool is_anon = folio_test_anon(folio);
 	struct address_space *mapping = NULL;
 	struct anon_vma *anon_vma = NULL;
@@ -3731,9 +3730,10 @@  static int __folio_split(struct folio *folio, unsigned int new_order,
 			VM_WARN_ONCE(1, "Cannot split to order-1 folio");
 			return -EINVAL;
 		}
-	} else if (new_order) {
+	} else {
 		/* Split shmem folio to non-zero order not supported */
-		if (shmem_mapping(folio->mapping)) {
+		if ((!uniform_split || new_order) &&
+		    shmem_mapping(folio->mapping)) {
 			VM_WARN_ONCE(1,
 				"Cannot split shmem folio to non-0 order");
 			return -EINVAL;
@@ -3744,7 +3744,7 @@  static int __folio_split(struct folio *folio, unsigned int new_order,
 		 * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping
 		 * does not actually support large folios properly.
 		 */
-		if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+		if (new_order && IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
 		    !mapping_large_folio_support(folio->mapping)) {
 			VM_WARN_ONCE(1,
 				"Cannot split file folio to non-0 order");
@@ -3753,7 +3753,7 @@  static int __folio_split(struct folio *folio, unsigned int new_order,
 	}
 
 	/* Only swapping a whole PMD-mapped folio is supported */
-	if (folio_test_swapcache(folio) && new_order)
+	if (folio_test_swapcache(folio) && (!uniform_split || new_order))
 		return -EINVAL;
 
 	is_hzp = is_huge_zero_folio(folio);
@@ -3810,10 +3810,13 @@  static int __folio_split(struct folio *folio, unsigned int new_order,
 			goto out;
 		}
 
-		xas_split_alloc(&xas, folio, folio_order(folio), gfp);
-		if (xas_error(&xas)) {
-			ret = xas_error(&xas);
-			goto out;
+		if (uniform_split) {
+			xas_set_order(&xas, folio->index, new_order);
+			xas_split_alloc(&xas, folio, folio_order(folio), gfp);
+			if (xas_error(&xas)) {
+				ret = xas_error(&xas);
+				goto out;
+			}
 		}
 
 		anon_vma = NULL;
@@ -3878,7 +3881,6 @@  static int __folio_split(struct folio *folio, unsigned int new_order,
 		if (mapping) {
 			int nr = folio_nr_pages(folio);
 
-			xas_split(&xas, folio, folio_order(folio));
 			if (folio_test_pmd_mappable(folio) &&
 			    new_order < HPAGE_PMD_ORDER) {
 				if (folio_test_swapbacked(folio)) {
@@ -3896,8 +3898,8 @@  static int __folio_split(struct folio *folio, unsigned int new_order,
 			mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
 			mod_mthp_stat(new_order, MTHP_STAT_NR_ANON, 1 << (order - new_order));
 		}
-		__split_huge_page(page, list, end, new_order);
-		ret = 0;
+		ret = __folio_split_without_mapping(page_folio(page), new_order,
+				page, list, end, &xas, mapping, uniform_split);
 	} else {
 		spin_unlock(&ds_queue->split_queue_lock);
 fail:
@@ -3975,7 +3977,31 @@  int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 {
 	struct folio *folio = page_folio(page);
 
-	return __folio_split(folio, new_order, page, list);
+	return __folio_split(folio, new_order, page, list, true);
+}
+
+/*
+ * folio_split: split a folio at offset_in_new_order to a new_order folio
+ * @folio: folio to split
+ * @new_order: the order of the new folio
+ * @page: a page within the new folio
+ *
+ * return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be
+ * split but not to @new_order, the caller needs to check)
+ *
+ * Split a folio at offset_in_new_order to a new_order folio, leave the
+ * remaining subpages of the original folio as large as possible. For example,
+ * split an order-9 folio at its third order-3 subpages to an order-3 folio.
+ * There are 2^6=64 order-3 subpages in an order-9 folio and the result will be
+ * a set of folios with different order and the new folio is in bracket:
+ * [order-4, {order-3}, order-3, order-5, order-6, order-7, order-8].
+ *
+ * After split, folio is left locked for caller.
+ */
+int folio_split(struct folio *folio, unsigned int new_order,
+		struct page *page, struct list_head *list)
+{
+	return __folio_split(folio, new_order, page, list, false);
 }
 
 int min_order_for_split(struct folio *folio)