[PATCH v9 4/8] mm/huge_memory: add buddy allocator like (non-uniform) folio_split()

[Zi Yan <ziy@nvidia.com>]

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,
since anon folio does not support order-1 yet.
-----------------------------------------------------------------
|   |   |   |   |     |   |       |                             |
|O-0|O-0|O-0|O-0| O-2 |...|  O-7  |             O-8             |
|   |   |   |   |     |   |       |                             |
-----------------------------------------------------------------

O-1,      O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache
---------------------------------------------------------------
|     |   |   |     |   |       |                             |
| O-1 |O-0|O-0| O-2 |...|  O-7  |             O-8             |
|     |   |   |     |   |       |                             |
---------------------------------------------------------------

It generates fewer folios (i.e., 11 or 10) than existing page split
approach, which splits the order-9 to 512 order-0 folios.  It also reduces
the number of new xa_node needed during a pagecache folio split from 8 to
1, potentially decreasing the folio split failure rate due to memory
constraints.

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 __split_unmapped_folio() using uniform_split
variable to distinguish their operations.

uniform_split_supported() and non_uniform_split_supported() are added to
factor out check code and will be used outside __folio_split() in the
following commit.

Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Kairui Song <kasong@tencent.com>
---
 mm/huge_memory.c | 160 ++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 123 insertions(+), 37 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4c79f54566d4..0e45937c0d91 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3847,12 +3847,85 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 	return ret;
 }
 
+static bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
+		bool warns)
+{
+	if (folio_test_anon(folio)) {
+		/* order-1 is not supported for anonymous THP. */
+		VM_WARN_ONCE(warns && new_order == 1,
+				"Cannot split to order-1 folio");
+		return new_order != 1;
+	} else if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+	    !mapping_large_folio_support(folio->mapping)) {
+		/*
+		 * No split if the file system does not support large folio.
+		 * Note that we might still have THPs in such mappings due to
+		 * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping
+		 * does not actually support large folios properly.
+		 */
+		VM_WARN_ONCE(warns,
+			"Cannot split file folio to non-0 order");
+		return false;
+	}
+
+	/* Only swapping a whole PMD-mapped folio is supported */
+	if (folio_test_swapcache(folio)) {
+		VM_WARN_ONCE(warns,
+			"Cannot split swapcache folio to non-0 order");
+		return false;
+	}
+
+	return true;
+}
+
+/* See comments in non_uniform_split_supported() */
+static bool uniform_split_supported(struct folio *folio, unsigned int new_order,
+		bool warns)
+{
+	if (folio_test_anon(folio)) {
+		VM_WARN_ONCE(warns && new_order == 1,
+				"Cannot split to order-1 folio");
+		return new_order != 1;
+	} else  if (new_order) {
+		if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+		    !mapping_large_folio_support(folio->mapping)) {
+			VM_WARN_ONCE(warns,
+				"Cannot split file folio to non-0 order");
+			return false;
+		}
+	}
+
+	if (new_order && folio_test_swapcache(folio)) {
+		VM_WARN_ONCE(warns,
+			"Cannot split swapcache folio to non-0 order");
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * __folio_split: split a folio at @split_at to a @new_order folio
+ * @folio: folio to split
+ * @new_order: the order of the new folio
+ * @split_at: a page within the new folio
+ * @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)
+ *
+ * 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
+ * preparing @folio for __split_unmapped_folio().
+ *
+ * return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be
+ * split but not to @new_order, the caller needs to check)
+ */
 static int __folio_split(struct folio *folio, unsigned int new_order,
-		struct page *page, struct list_head *list)
+		struct page *split_at, struct page *lock_at,
+		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;
@@ -3864,32 +3937,17 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
+	if (folio != page_folio(split_at) || folio != page_folio(lock_at))
+		return -EINVAL;
+
 	if (new_order >= folio_order(folio))
 		return -EINVAL;
 
-	if (is_anon) {
-		/* order-1 is not supported for anonymous THP. */
-		if (new_order == 1) {
-			VM_WARN_ONCE(1, "Cannot split to order-1 folio");
-			return -EINVAL;
-		}
-	} else if (new_order) {
-		/*
-		 * No split if the file system does not support large folio.
-		 * Note that we might still have THPs in such mappings due to
-		 * 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) &&
-		    !mapping_large_folio_support(folio->mapping)) {
-			VM_WARN_ONCE(1,
-				"Cannot split file folio to non-0 order");
-			return -EINVAL;
-		}
-	}
+	if (uniform_split && !uniform_split_supported(folio, new_order, true))
+		return -EINVAL;
 
-	/* Only swapping a whole PMD-mapped folio is supported */
-	if (folio_test_swapcache(folio) && new_order)
+	if (!uniform_split &&
+	    !non_uniform_split_supported(folio, new_order, true))
 		return -EINVAL;
 
 	is_hzp = is_huge_zero_folio(folio);
@@ -3946,10 +4004,13 @@ 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;
@@ -4014,7 +4075,6 @@ 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)) {
@@ -4028,12 +4088,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 			}
 		}
 
-		if (is_anon) {
-			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 = __split_unmapped_folio(folio, new_order,
+				split_at, lock_at, list, end, &xas, mapping,
+				uniform_split);
 	} else {
 		spin_unlock(&ds_queue->split_queue_lock);
 fail:
@@ -4111,7 +4168,36 @@ 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, &folio->page, page, list, true);
+}
+
+/*
+ * folio_split: split a folio at @split_at to a @new_order folio
+ * @folio: folio to split
+ * @new_order: the order of the new folio
+ * @split_at: 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)
+ *
+ * It has the same prerequisites and returns as
+ * split_huge_page_to_list_to_order().
+ *
+ * Split a folio at @split_at to a new_order folio, leave the
+ * remaining subpages of the original folio as large as possible. For example,
+ * in the case of splitting an order-9 folio at its third order-3 subpages to
+ * an order-3 folio, there are 2^(9-3)=64 order-3 subpages in the order-9 folio.
+ * After the split, there will be a group of folios with different orders and
+ * the new folio containing @split_at is marked in bracket:
+ * [order-4, {order-3}, order-3, order-5, order-6, order-7, order-8].
+ *
+ * After split, folio is left locked for caller.
+ */
+static 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);
 }
 
 int min_order_for_split(struct folio *folio)
-- 
2.47.2