[PATCH v5 2/5] mm: changes to split_huge_page() to free zero filled tail pages

[<alexlzhu@fb.com>]

From: Alexander Zhu <alexlzhu@fb.com>

Currently, when /sys/kernel/mm/transparent_hugepage/enabled=always is set
there are a large number of transparent hugepages that are almost entirely
zero filled.  This is mentioned in a number of previous patchsets
including:
https://lore.kernel.org/all/20210731063938.1391602-1-yuzhao@google.com/
https://lore.kernel.org/all/
1635422215-99394-1-git-send-email-ningzhang@linux.alibaba.com/

Currently, split_huge_page() does not have a way to identify zero filled
pages within the THP. Thus these zero pages get remapped and continue to
create memory waste. In this patch, we identify and free tail pages that
are zero filled in split_huge_page(). In this way, we avoid mapping these
pages back into page table entries and can free up unused memory within
THPs. This is based off the previously mentioned patchset by Yu Zhao.
However, we chose to free anonymous zero tail pages whenever they are
encountered instead of only on reclaim or migration.

Signed-off-by: Alexander Zhu <alexlzhu@fb.com>
---
v4 to v5
-split out split_huge_page changes into three different patches. One for zapping zero pages, one for not remapping zero pages, and one for self tests.

 include/linux/vm_event_item.h |  3 +++
 mm/huge_memory.c              | 37 +++++++++++++++++++++++++++++++++++
 mm/vmstat.c                   |  3 +++
 3 files changed, 43 insertions(+)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 3518dba1e02f..3618b10ddec9 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -111,6 +111,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 		THP_SPLIT_PUD,
 #endif
+		THP_SPLIT_FREE,
+		THP_SPLIT_UNMAP,
+		THP_SPLIT_REMAP_READONLY_ZERO_PAGE,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 		THP_SWPOUT,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1cc4a5f4791e..363218e8a22a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2496,6 +2496,8 @@ 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;
 
 	/* complete memcg works before add pages to LRU */
@@ -2572,6 +2574,34 @@ 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;
+		}
+
+		/*
+		 * If a tail page has only one reference left, it will be freed
+		 * by the call to free_page_and_swap_cache below. Since zero
+		 * subpages are no longer remapped, there will only be one
+		 * reference left in cases outside of reclaim or migration.
+		 */
+		if (page_ref_count(subpage) == 1)
+			nr_pages_to_free++;
+
 		/*
 		 * Subpages may be freed if there wasn't any mapping
 		 * like if add_to_swap() is running on a lru page that
@@ -2581,6 +2611,13 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		 */
 		free_page_and_swap_cache(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);
 }
 
 /* Racy check whether the huge page can be split */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b2371d745e00..3d802eb6754d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1359,6 +1359,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 	"thp_split_pud",
 #endif
+	"thp_split_free",
+	"thp_split_unmap",
+	"thp_split_remap_readonly_zero_page",
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 	"thp_swpout",
-- 
2.30.2