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>

2 files changed, 13 insertions, 4 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ee1c244a62a1..528454c2caa9 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 b5b12c71a2af..1701ce4be746 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;
 }