mm/rmap: add fast-path for small folios when adding/removing/duplicating

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.

Link: https://lkml.kernel.org/r/20240409192301.907377-4-david@redhat.comSigned-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Richard Chang <richardycc@google.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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);

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: