[PATCH v1 03/18] mm/rmap: add fast-path for small folios when adding/removing/duplicating

[David Hildenbrand]

Let's add a fast-path for small folios to all relevant rmap functions.
Note that only RMAP_LEVEL_PTE applies.

This is a preparation for tracking the mapcount of large folios in a
single value.

Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
 include/linux/rmap.h | 13 +++++++++++++
 mm/rmap.c            | 26 ++++++++++++++++----------
 2 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 9549d78928bb..327f1ca5a487 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -322,6 +322,11 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio,
 
 	switch (level) {
 	case RMAP_LEVEL_PTE:
+		if (!folio_test_large(folio)) {
+			atomic_inc(&page->_mapcount);
+			break;
+		}
+
 		do {
 			atomic_inc(&page->_mapcount);
 		} while (page++, --nr_pages > 0);
@@ -405,6 +410,14 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
 				if (PageAnonExclusive(page + i))
 					return -EBUSY;
 		}
+
+		if (!folio_test_large(folio)) {
+			if (PageAnonExclusive(page))
+				ClearPageAnonExclusive(page);
+			atomic_inc(&page->_mapcount);
+			break;
+		}
+
 		do {
 			if (PageAnonExclusive(page))
 				ClearPageAnonExclusive(page);
diff --git a/mm/rmap.c b/mm/rmap.c
index 56b313aa2ebf..4bde6d60db6c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1172,15 +1172,18 @@ static __always_inline unsigned int __folio_add_rmap(struct folio *folio,
 
 	switch (level) {
 	case RMAP_LEVEL_PTE:
+		if (!folio_test_large(folio)) {
+			nr = atomic_inc_and_test(&page->_mapcount);
+			break;
+		}
+
 		do {
 			first = atomic_inc_and_test(&page->_mapcount);
-			if (first && folio_test_large(folio)) {
+			if (first) {
 				first = atomic_inc_return_relaxed(mapped);
-				first = (first < ENTIRELY_MAPPED);
+				if (first < ENTIRELY_MAPPED)
+					nr++;
 			}
-
-			if (first)
-				nr++;
 		} while (page++, --nr_pages > 0);
 		break;
 	case RMAP_LEVEL_PMD:
@@ -1514,15 +1517,18 @@ static __always_inline void __folio_remove_rmap(struct folio *folio,
 
 	switch (level) {
 	case RMAP_LEVEL_PTE:
+		if (!folio_test_large(folio)) {
+			nr = atomic_add_negative(-1, &page->_mapcount);
+			break;
+		}
+
 		do {
 			last = atomic_add_negative(-1, &page->_mapcount);
-			if (last && folio_test_large(folio)) {
+			if (last) {
 				last = atomic_dec_return_relaxed(mapped);
-				last = (last < ENTIRELY_MAPPED);
+				if (last < ENTIRELY_MAPPED)
+					nr++;
 			}
-
-			if (last)
-				nr++;
 		} while (page++, --nr_pages > 0);
 		break;
 	case RMAP_LEVEL_PMD:
-- 
2.44.0