mm: page cache: store only head pages in i_pages

Transparent Huge Pages are currently stored in i_pages as pointers to
consecutive subpages.  This patch changes that to storing consecutive
pointers to the head page in preparation for storing huge pages more
efficiently in i_pages.

Large parts of this are "inspired" by Kirill's patch
https://lore.kernel.org/lkml/20170126115819.58875-2-kirill.shutemov@linux.intel.com/

Kirill and Huang Ying contributed several fixes.

[willy@infradead.org: use compound_nr, squish uninit-var warning]
Link: http://lkml.kernel.org/r/20190731210400.7419-1-willy@infradead.org
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Acked-by: Jan Kara <jack@suse.cz>
Reviewed-by: Kirill Shutemov <kirill@shutemov.name>
Reviewed-by: Song Liu <songliubraving@fb.com>
Tested-by: Song Liu <songliubraving@fb.com>
Tested-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Tested-by: Qian Cai <cai@lca.pw>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 20 insertions, 2 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index de1f15969e27..483b07b2d6ae 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2497,6 +2497,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	struct page *head = compound_head(page);
 	pg_data_t *pgdat = page_pgdat(head);
 	struct lruvec *lruvec;
+	struct address_space *swap_cache = NULL;
+	unsigned long offset = 0;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, pgdat);
@@ -2504,6 +2506,14 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
+	if (PageAnon(head) && PageSwapCache(head)) {
+		swp_entry_t entry = { .val = page_private(head) };
+
+		offset = swp_offset(entry);
+		swap_cache = swap_address_space(entry);
+		xa_lock(&swap_cache->i_pages);
+	}
+
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */
@@ -2513,6 +2523,12 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 			if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
 				shmem_uncharge(head->mapping->host, 1);
 			put_page(head + i);
+		} else if (!PageAnon(page)) {
+			__xa_store(&head->mapping->i_pages, head[i].index,
+					head + i, 0);
+		} else if (swap_cache) {
+			__xa_store(&swap_cache->i_pages, offset + i,
+					head + i, 0);
 		}
 	}
 
@@ -2523,10 +2539,12 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* See comment in __split_huge_page_tail() */
 	if (PageAnon(head)) {
 		/* Additional pin to swap cache */
-		if (PageSwapCache(head))
+		if (PageSwapCache(head)) {
 			page_ref_add(head, 2);
-		else
+			xa_unlock(&swap_cache->i_pages);
+		} else {
 			page_ref_inc(head);
+		}
 	} else {
 		/* Additional pin to page cache */
 		page_ref_add(head, 2);