[PATCH v5 1/3] mm/compaction: enable compacting >0 order folios.

[Zi Yan]

From: Zi Yan <ziy@xxxxxxxxxx>

migrate_pages() supports >0 order folio migration and during compaction,
even if compaction_alloc() cannot provide >0 order free pages,
migrate_pages() can split the source page and try to migrate the base
pages from the split.  It can be a baseline and start point for adding
support for compacting >0 order folios.

Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
Suggested-by: Huang Ying <ying.huang@xxxxxxxxx>
Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Tested-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Tested-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Adam Manzanares <a.manzanares@xxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kemeng Shi <shikemeng@xxxxxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Luis Chamberlain <mcgrof@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Vishal Moola (Oracle) <vishal.moola@xxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Yin Fengwei <fengwei.yin@xxxxxxxxx>
---
 mm/compaction.c | 66 ++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 52 insertions(+), 14 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index cc801ce099b4..aa6aad805c4d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -816,6 +816,21 @@ static bool too_many_isolated(struct compact_control *cc)
 	return too_many;
 }
 
+/*
+ * 1. if the page order is larger than or equal to target_order (i.e.,
+ * cc->order and when it is not -1 for global compaction), skip it since
+ * target_order already indicates no free page with larger than target_order
+ * exists and later migrating it will most likely fail;
+ *
+ * 2. compacting > pageblock_order pages does not improve memory fragmentation,
+ * skip them;
+ */
+static bool skip_isolation_on_order(int order, int target_order)
+{
+	return (target_order != -1 && order >= target_order) ||
+		order >= pageblock_order;
+}
+
 /**
  * isolate_migratepages_block() - isolate all migrate-able pages within
  *				  a single pageblock
@@ -947,7 +962,22 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			valid_page = page;
 		}
 
-		if (PageHuge(page) && cc->alloc_contig) {
+		if (PageHuge(page)) {
+			/*
+			 * skip hugetlbfs if we are not compacting for pages
+			 * bigger than its order. THPs and other compound pages
+			 * are handled below.
+			 */
+			if (!cc->alloc_contig) {
+				const unsigned int order = compound_order(page);
+
+				if (order <= MAX_PAGE_ORDER) {
+					low_pfn += (1UL << order) - 1;
+					nr_scanned += (1UL << order) - 1;
+				}
+				goto isolate_fail;
+			}
+			/* for alloc_contig case */
 			if (locked) {
 				unlock_page_lruvec_irqrestore(locked, flags);
 				locked = NULL;
@@ -1008,21 +1038,24 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		}
 
 		/*
-		 * Regardless of being on LRU, compound pages such as THP and
-		 * hugetlbfs are not to be compacted unless we are attempting
-		 * an allocation much larger than the huge page size (eg CMA).
-		 * We can potentially save a lot of iterations if we skip them
-		 * at once. The check is racy, but we can consider only valid
-		 * values and the only danger is skipping too much.
+		 * Regardless of being on LRU, compound pages such as THP
+		 * (hugetlbfs is handled above) are not to be compacted unless
+		 * we are attempting an allocation larger than the compound
+		 * page size. We can potentially save a lot of iterations if we
+		 * skip them at once. The check is racy, but we can consider
+		 * only valid values and the only danger is skipping too much.
 		 */
 		if (PageCompound(page) && !cc->alloc_contig) {
 			const unsigned int order = compound_order(page);
 
-			if (likely(order <= MAX_PAGE_ORDER)) {
-				low_pfn += (1UL << order) - 1;
-				nr_scanned += (1UL << order) - 1;
+			/* Skip based on page order and compaction target order. */
+			if (skip_isolation_on_order(order, cc->order)) {
+				if (order <= MAX_PAGE_ORDER) {
+					low_pfn += (1UL << order) - 1;
+					nr_scanned += (1UL << order) - 1;
+				}
+				goto isolate_fail;
 			}
-			goto isolate_fail;
 		}
 
 		/*
@@ -1165,10 +1198,11 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			}
 
 			/*
-			 * folio become large since the non-locked check,
-			 * and it's on LRU.
+			 * Check LRU folio order under the lock
 			 */
-			if (unlikely(folio_test_large(folio) && !cc->alloc_contig)) {
+			if (unlikely(skip_isolation_on_order(folio_order(folio),
+							     cc->order) &&
+				     !cc->alloc_contig)) {
 				low_pfn += folio_nr_pages(folio) - 1;
 				nr_scanned += folio_nr_pages(folio) - 1;
 				folio_set_lru(folio);
@@ -1788,6 +1822,10 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 	struct compact_control *cc = (struct compact_control *)data;
 	struct folio *dst;
 
+	/* this makes migrate_pages() split the source page and retry */
+	if (folio_test_large(src) > 0)
+		return NULL;
+
 	if (list_empty(&cc->freepages)) {
 		isolate_freepages(cc);
 
-- 
2.43.0