vmscan: split LRU lists into anon & file sets

Split the LRU lists in two, one set for pages that are backed by real file
systems ("file") and one for pages that are backed by memory and swap
("anon").  The latter includes tmpfs.

The advantage of doing this is that the VM will not have to scan over lots
of anonymous pages (which we generally do not want to swap out), just to
find the page cache pages that it should evict.

This patch has the infrastructure and a basic policy to balance how much
we scan the anon lists and how much we scan the file lists.  The big
policy changes are in separate patches.

[lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset]
[kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru]
[kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page]
[hugh@veritas.com: memcg swapbacked pages active]
[hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED]
[akpm@linux-foundation.org: fix /proc/vmstat units]
[nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration]
[kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo]
[kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 140 insertions, 31 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0a24d55..bee52ab 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -175,6 +175,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_READ_MAP:       Can be mapped for reading
  * BDI_CAP_WRITE_MAP:      Can be mapped for writing
  * BDI_CAP_EXEC_MAP:       Can be mapped for execution
+ *
+ * BDI_CAP_SWAP_BACKED:    Count shmem/tmpfs objects as swap-backed.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
@@ -184,6 +186,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_WRITE_MAP	0x00000020
 #define BDI_CAP_EXEC_MAP	0x00000040
 #define BDI_CAP_NO_ACCT_WB	0x00000080
+#define BDI_CAP_SWAP_BACKED	0x00000100
 
 #define BDI_CAP_VMFLAGS \
 	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
@@ -248,6 +251,11 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
 				      BDI_CAP_NO_WRITEBACK));
 }
 
+static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
+{
+	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
+}
+
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -258,4 +266,9 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping)
 	return bdi_cap_account_dirty(mapping->backing_dev_info);
 }
 
+static inline bool mapping_cap_swap_backed(struct address_space *mapping)
+{
+	return bdi_cap_swap_backed(mapping->backing_dev_info);
+}
+
 #endif		/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a6ac0d4..8d8f05c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -44,7 +44,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					unsigned long *scanned, int order,
 					int mode, struct zone *z,
 					struct mem_cgroup *mem_cont,
-					int active);
+					int active, int file);
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
 
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 96e9704..2eb5994 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -5,7 +5,7 @@
  * page_is_file_cache - should the page be on a file LRU or anon LRU?
  * @page: the page to test
  *
- * Returns !0 if @page is page cache page backed by a regular filesystem,
+ * Returns LRU_FILE if @page is page cache page backed by a regular filesystem,
  * or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed.
  * Used by functions that manipulate the LRU lists, to sort a page
  * onto the right LRU list.
@@ -20,7 +20,7 @@ static inline int page_is_file_cache(struct page *page)
 		return 0;
 
 	/* The page is page cache backed by a normal filesystem. */
-	return 1;
+	return LRU_FILE;
 }
 
 static inline void
@@ -38,39 +38,64 @@ del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l)
 }
 
 static inline void
-add_page_to_active_list(struct zone *zone, struct page *page)
+add_page_to_inactive_anon_list(struct zone *zone, struct page *page)
 {
-	add_page_to_lru_list(zone, page, LRU_ACTIVE);
+	add_page_to_lru_list(zone, page, LRU_INACTIVE_ANON);
 }
 
 static inline void
-add_page_to_inactive_list(struct zone *zone, struct page *page)
+add_page_to_active_anon_list(struct zone *zone, struct page *page)
 {
-	add_page_to_lru_list(zone, page, LRU_INACTIVE);
+	add_page_to_lru_list(zone, page, LRU_ACTIVE_ANON);
 }
 
 static inline void
-del_page_from_active_list(struct zone *zone, struct page *page)
+add_page_to_inactive_file_list(struct zone *zone, struct page *page)
 {
-	del_page_from_lru_list(zone, page, LRU_ACTIVE);
+	add_page_to_lru_list(zone, page, LRU_INACTIVE_FILE);
 }
 
 static inline void
-del_page_from_inactive_list(struct zone *zone, struct page *page)
+add_page_to_active_file_list(struct zone *zone, struct page *page)
 {
-	del_page_from_lru_list(zone, page, LRU_INACTIVE);
+	add_page_to_lru_list(zone, page, LRU_ACTIVE_FILE);
+}
+
+static inline void
+del_page_from_inactive_anon_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_INACTIVE_ANON);
+}
+
+static inline void
+del_page_from_active_anon_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_ACTIVE_ANON);
+}
+
+static inline void
+del_page_from_inactive_file_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
+}
+
+static inline void
+del_page_from_active_file_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
 }
 
 static inline void
 del_page_from_lru(struct zone *zone, struct page *page)
 {
-	enum lru_list l = LRU_INACTIVE;
+	enum lru_list l = LRU_BASE;
 
 	list_del(&page->lru);
 	if (PageActive(page)) {
 		__ClearPageActive(page);
-		l = LRU_ACTIVE;
+		l += LRU_ACTIVE;
 	}
+	l += page_is_file_cache(page);
 	__dec_zone_state(zone, NR_LRU_BASE + l);
 }
 
@@ -87,6 +112,7 @@ static inline enum lru_list page_lru(struct page *page)
 
 	if (PageActive(page))
 		lru += LRU_ACTIVE;
+	lru += page_is_file_cache(page);
 
 	return lru;
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 156e18f..59a4c8f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -82,21 +82,23 @@ enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
 	NR_LRU_BASE,
-	NR_INACTIVE = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
-	NR_ACTIVE,	/*  "     "     "   "       "         */
+	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
+	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
+	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
 	NR_FILE_PAGES,
 	NR_FILE_DIRTY,
 	NR_WRITEBACK,
-	/* Second 128 byte cacheline */
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
 	NR_VMSCAN_WRITE,
+	/* Second 128 byte cacheline */
 	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
 #ifdef CONFIG_NUMA
 	NUMA_HIT,		/* allocated in intended node */
@@ -108,17 +110,36 @@ enum zone_stat_item {
 #endif
 	NR_VM_ZONE_STAT_ITEMS };
 
+/*
+ * We do arithmetic on the LRU lists in various places in the code,
+ * so it is important to keep the active lists LRU_ACTIVE higher in
+ * the array than the corresponding inactive lists, and to keep
+ * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists.
+ *
+ * This has to be kept in sync with the statistics in zone_stat_item
+ * above and the descriptions in vmstat_text in mm/vmstat.c
+ */
+#define LRU_BASE 0
+#define LRU_ACTIVE 1
+#define LRU_FILE 2
+
 enum lru_list {
-	LRU_BASE,
-	LRU_INACTIVE=LRU_BASE,	/* must match order of NR_[IN]ACTIVE */
-	LRU_ACTIVE,		/*  "     "     "   "       "        */
+	LRU_INACTIVE_ANON = LRU_BASE,
+	LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
+	LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
+	LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
 	NR_LRU_LISTS };
 
 #define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
 
+static inline int is_file_lru(enum lru_list l)
+{
+	return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE);
+}
+
 static inline int is_active_lru(enum lru_list l)
 {
-	return (l == LRU_ACTIVE);
+	return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE);
 }
 
 struct per_cpu_pages {
@@ -269,6 +290,18 @@ struct zone {
 		struct list_head list;
 		unsigned long nr_scan;
 	} lru[NR_LRU_LISTS];
+
+	/*
+	 * The pageout code in vmscan.c keeps track of how many of the
+	 * mem/swap backed and file backed pages are refeferenced.
+	 * The higher the rotated/scanned ratio, the more valuable
+	 * that cache is.
+	 *
+	 * The anon LRU stats live in [0], file LRU stats in [1]
+	 */
+	unsigned long		recent_rotated[2];
+	unsigned long		recent_scanned[2];
+
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	unsigned long		flags;		   /* zone flags, see below */
 
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index fea3a98..5fc96a4 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -81,20 +81,37 @@ static inline void pagevec_free(struct pagevec *pvec)
 		__pagevec_free(pvec);
 }
 
-static inline void __pagevec_lru_add(struct pagevec *pvec)
+static inline void __pagevec_lru_add_anon(struct pagevec *pvec)
 {
-	____pagevec_lru_add(pvec, LRU_INACTIVE);
+	____pagevec_lru_add(pvec, LRU_INACTIVE_ANON);
 }
 
-static inline void __pagevec_lru_add_active(struct pagevec *pvec)
+static inline void __pagevec_lru_add_active_anon(struct pagevec *pvec)
 {
-	____pagevec_lru_add(pvec, LRU_ACTIVE);
+	____pagevec_lru_add(pvec, LRU_ACTIVE_ANON);
 }
 
-static inline void pagevec_lru_add(struct pagevec *pvec)
+static inline void __pagevec_lru_add_file(struct pagevec *pvec)
+{
+	____pagevec_lru_add(pvec, LRU_INACTIVE_FILE);
+}
+
+static inline void __pagevec_lru_add_active_file(struct pagevec *pvec)
+{
+	____pagevec_lru_add(pvec, LRU_ACTIVE_FILE);
+}
+
+
+static inline void pagevec_lru_add_file(struct pagevec *pvec)
+{
+	if (pagevec_count(pvec))
+		__pagevec_lru_add_file(pvec);
+}
+
+static inline void pagevec_lru_add_anon(struct pagevec *pvec)
 {
 	if (pagevec_count(pvec))
-		__pagevec_lru_add(pvec);
+		__pagevec_lru_add_anon(pvec);
 }
 
 #endif /* _LINUX_PAGEVEC_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 833be56..7d09d79 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -184,14 +184,24 @@ extern void swap_setup(void);
  * lru_cache_add: add a page to the page lists
  * @page: the page to add
  */
-static inline void lru_cache_add(struct page *page)
+static inline void lru_cache_add_anon(struct page *page)
 {
-	__lru_cache_add(page, LRU_INACTIVE);
+	__lru_cache_add(page, LRU_INACTIVE_ANON);
 }
 
-static inline void lru_cache_add_active(struct page *page)
+static inline void lru_cache_add_active_anon(struct page *page)
 {
-	__lru_cache_add(page, LRU_ACTIVE);
+	__lru_cache_add(page, LRU_ACTIVE_ANON);
+}
+
+static inline void lru_cache_add_file(struct page *page)
+{
+	__lru_cache_add(page, LRU_INACTIVE_FILE);
+}
+
+static inline void lru_cache_add_active_file(struct page *page)
+{
+	__lru_cache_add(page, LRU_ACTIVE_FILE);
 }
 
 /* linux/mm/vmscan.c */
@@ -199,7 +209,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask);
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
 							gfp_t gfp_mask);
-extern int __isolate_lru_page(struct page *page, int mode);
+extern int __isolate_lru_page(struct page *page, int mode, int file);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 58334d4..ff5179f 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -159,6 +159,16 @@ static inline unsigned long zone_page_state(struct zone *zone,
 	return x;
 }
 
+extern unsigned long global_lru_pages(void);
+
+static inline unsigned long zone_lru_pages(struct zone *zone)
+{
+	return (zone_page_state(zone, NR_ACTIVE_ANON)
+		+ zone_page_state(zone, NR_ACTIVE_FILE)
+		+ zone_page_state(zone, NR_INACTIVE_ANON)
+		+ zone_page_state(zone, NR_INACTIVE_FILE));
+}
+
 #ifdef CONFIG_NUMA
 /*
  * Determine the per node value of a stat item. This function