[PATCH 2/3] mm: free zapped tail pages when splitting isolated thp

[Yu Zhao]

If a tail page has only two references left, one inherited from the
isolation of its head and the other from lru_add_page_tail() which we
are about to drop, it means this tail page was concurrently zapped.
Then we can safely free it and save page reclaim or migration the
trouble of trying it.

Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Tested-by: Shuang Zhai <zhais@xxxxxxxxxx>
---
 include/linux/vm_event_item.h |  1 +
 mm/huge_memory.c              | 28 ++++++++++++++++++++++++++++
 mm/vmstat.c                   |  1 +
 3 files changed, 30 insertions(+)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index ae0dd1948c2b..829eeac84094 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -99,6 +99,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 		THP_SPLIT_PUD,
 #endif
+		THP_SPLIT_FREE,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 		THP_SWPOUT,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d8b655856e79..5120478bca41 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2432,6 +2432,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	struct address_space *swap_cache = NULL;
 	unsigned long offset = 0;
 	unsigned int nr = thp_nr_pages(head);
+	LIST_HEAD(pages_to_free);
+	int nr_pages_to_free = 0;
 	int i;
 
 	VM_BUG_ON_PAGE(list && PageLRU(head), head);
@@ -2506,6 +2508,25 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 			continue;
 		unlock_page(subpage);
 
+		/*
+		 * If a tail page has only two references left, one inherited
+		 * from the isolation of its head and the other from
+		 * lru_add_page_tail() which we are about to drop, it means this
+		 * tail page was concurrently zapped. Then we can safely free it
+		 * and save page reclaim or migration the trouble of trying it.
+		 */
+		if (list && page_ref_freeze(subpage, 2)) {
+			VM_BUG_ON_PAGE(PageLRU(subpage), subpage);
+			VM_BUG_ON_PAGE(PageCompound(subpage), subpage);
+			VM_BUG_ON_PAGE(page_mapped(subpage), subpage);
+
+			ClearPageActive(subpage);
+			ClearPageUnevictable(subpage);
+			list_move(&subpage->lru, &pages_to_free);
+			nr_pages_to_free++;
+			continue;
+		}
+
 		/*
 		 * Subpages may be freed if there wasn't any mapping
 		 * like if add_to_swap() is running on a lru page that
@@ -2515,6 +2536,13 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		 */
 		put_page(subpage);
 	}
+
+	if (!nr_pages_to_free)
+		return;
+
+	mem_cgroup_uncharge_list(&pages_to_free);
+	free_unref_page_list(&pages_to_free);
+	count_vm_events(THP_SPLIT_FREE, nr_pages_to_free);
 }
 
 int total_mapcount(struct page *page)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b0534e068166..f486e5d98d96 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1300,6 +1300,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 	"thp_split_pud",
 #endif
+	"thp_split_free",
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 	"thp_swpout",
-- 
2.32.0.554.ge1b32706d8-goog