mm: thp: add split tail pages to shrink page list in page reclaim

In page reclaim, huge page is split.  split_huge_page() adds tail pages
to LRU list.  Since we are reclaiming a huge page, it's better we
reclaim all subpages of the huge page instead of just the head page.
This patch adds split tail pages to shrink page list so the tail pages
can be reclaimed soon.

Before this patch, run a swap workload:
  thp_fault_alloc 3492
  thp_fault_fallback 608
  thp_collapse_alloc 6
  thp_collapse_alloc_failed 0
  thp_split 916

With this patch:
  thp_fault_alloc 4085
  thp_fault_fallback 16
  thp_collapse_alloc 90
  thp_collapse_alloc_failed 0
  thp_split 1272

fallback allocation is reduced a lot.

[akpm@linux-foundation.org: fix CONFIG_SWAP=n build]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 39 insertions, 16 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ee1c244a..528454c 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -99,7 +99,11 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 extern int handle_pte_fault(struct mm_struct *mm,
 			    struct vm_area_struct *vma, unsigned long address,
 			    pte_t *pte, pmd_t *pmd, unsigned int flags);
-extern int split_huge_page(struct page *page);
+extern int split_huge_page_to_list(struct page *page, struct list_head *list);
+static inline int split_huge_page(struct page *page)
+{
+	return split_huge_page_to_list(page, NULL);
+}
 extern void __split_huge_page_pmd(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmd);
 #define split_huge_page_pmd(__vma, __address, __pmd)			\
@@ -186,6 +190,11 @@ extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vm
 #define transparent_hugepage_enabled(__vma) 0
 
 #define transparent_hugepage_flags 0UL
+static inline int
+split_huge_page_to_list(struct page *page, struct list_head *list)
+{
+	return 0;
+}
 static inline int split_huge_page(struct page *page)
 {
 	return 0;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b5b12c7..1701ce4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -236,7 +236,7 @@ extern unsigned long nr_free_pagecache_pages(void);
 extern void __lru_cache_add(struct page *, enum lru_list lru);
 extern void lru_cache_add_lru(struct page *, enum lru_list lru);
 extern void lru_add_page_tail(struct page *page, struct page *page_tail,
-			      struct lruvec *lruvec);
+			 struct lruvec *lruvec, struct list_head *head);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
@@ -346,7 +346,7 @@ extern struct address_space swapper_spaces[];
 #define swap_address_space(entry) (&swapper_spaces[swp_type(entry)])
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
-extern int add_to_swap(struct page *);
+extern int add_to_swap(struct page *, struct list_head *list);
 extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
 extern int __add_to_swap_cache(struct page *page, swp_entry_t entry);
 extern void __delete_from_swap_cache(struct page *);
@@ -465,7 +465,7 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp)
 	return NULL;
 }
 
-static inline int add_to_swap(struct page *page)
+static inline int add_to_swap(struct page *page, struct list_head *list)
 {
 	return 0;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 45eaae0..2ed1a16 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1559,7 +1559,8 @@ static int __split_huge_page_splitting(struct page *page,
 	return ret;
 }
 
-static void __split_huge_page_refcount(struct page *page)
+static void __split_huge_page_refcount(struct page *page,
+				       struct list_head *list)
 {
 	int i;
 	struct zone *zone = page_zone(page);
@@ -1645,7 +1646,7 @@ static void __split_huge_page_refcount(struct page *page)
 		BUG_ON(!PageDirty(page_tail));
 		BUG_ON(!PageSwapBacked(page_tail));
 
-		lru_add_page_tail(page, page_tail, lruvec);
+		lru_add_page_tail(page, page_tail, lruvec, list);
 	}
 	atomic_sub(tail_count, &page->_count);
 	BUG_ON(atomic_read(&page->_count) <= 0);
@@ -1752,7 +1753,8 @@ static int __split_huge_page_map(struct page *page,
 
 /* must be called with anon_vma->root->rwsem held */
 static void __split_huge_page(struct page *page,
-			      struct anon_vma *anon_vma)
+			      struct anon_vma *anon_vma,
+			      struct list_head *list)
 {
 	int mapcount, mapcount2;
 	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -1783,7 +1785,7 @@ static void __split_huge_page(struct page *page,
 		       mapcount, page_mapcount(page));
 	BUG_ON(mapcount != page_mapcount(page));
 
-	__split_huge_page_refcount(page);
+	__split_huge_page_refcount(page, list);
 
 	mapcount2 = 0;
 	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
@@ -1798,7 +1800,14 @@ static void __split_huge_page(struct page *page,
 	BUG_ON(mapcount != mapcount2);
 }
 
-int split_huge_page(struct page *page)
+/*
+ * Split a hugepage into normal pages. This doesn't change the position of head
+ * page. If @list is null, tail pages will be added to LRU list, otherwise, to
+ * @list. Both head page and tail pages will inherit mapping, flags, and so on
+ * from the hugepage.
+ * Return 0 if the hugepage is split successfully otherwise return 1.
+ */
+int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct anon_vma *anon_vma;
 	int ret = 1;
@@ -1823,7 +1832,7 @@ int split_huge_page(struct page *page)
 		goto out_unlock;
 
 	BUG_ON(!PageSwapBacked(page));
-	__split_huge_page(page, anon_vma);
+	__split_huge_page(page, anon_vma, list);
 	count_vm_event(THP_SPLIT);
 
 	BUG_ON(PageCompound(page));
diff --git a/mm/swap.c b/mm/swap.c
index 8a529a0..acd40bf 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -737,7 +737,7 @@ EXPORT_SYMBOL(__pagevec_release);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /* used by __split_huge_page_refcount() */
 void lru_add_page_tail(struct page *page, struct page *page_tail,
-		       struct lruvec *lruvec)
+		       struct lruvec *lruvec, struct list_head *list)
 {
 	int uninitialized_var(active);
 	enum lru_list lru;
@@ -749,7 +749,8 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 	VM_BUG_ON(NR_CPUS != 1 &&
 		  !spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
 
-	SetPageLRU(page_tail);
+	if (!list)
+		SetPageLRU(page_tail);
 
 	if (page_evictable(page_tail)) {
 		if (PageActive(page)) {
@@ -767,7 +768,11 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 
 	if (likely(PageLRU(page)))
 		list_add_tail(&page_tail->lru, &page->lru);
-	else {
+	else if (list) {
+		/* page reclaim is reclaiming a huge page */
+		get_page(page_tail);
+		list_add_tail(&page_tail->lru, list);
+	} else {
 		struct list_head *list_head;
 		/*
 		 * Head page has not yet been counted, as an hpage,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index fe43fd5..b3d40dc 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -160,7 +160,7 @@ void __delete_from_swap_cache(struct page *page)
  * Allocate swap space for the page and add the page to the
  * swap cache.  Caller needs to hold the page lock. 
  */
-int add_to_swap(struct page *page)
+int add_to_swap(struct page *page, struct list_head *list)
 {
 	swp_entry_t entry;
 	int err;
@@ -173,7 +173,7 @@ int add_to_swap(struct page *page)
 		return 0;
 
 	if (unlikely(PageTransHuge(page)))
-		if (unlikely(split_huge_page(page))) {
+		if (unlikely(split_huge_page_to_list(page, list))) {
 			swapcache_free(entry, NULL);
 			return 0;
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e53e495..fa6a853 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -781,7 +781,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (PageAnon(page) && !PageSwapCache(page)) {
 			if (!(sc->gfp_mask & __GFP_IO))
 				goto keep_locked;
-			if (!add_to_swap(page))
+			if (!add_to_swap(page, page_list))
 				goto activate_locked;
 			may_enter_fs = 1;
 		}