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: NRik van Riel <riel@redhat.com>
Signed-off-by: NLee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NDaisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/base/node.c

@@ -61,34 +61,44 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 	si_meminfo_node(&i, nid);
 
 	n = sprintf(buf, "\n"
-		       "Node %d MemTotal:     %8lu kB\n"
-		       "Node %d MemFree:      %8lu kB\n"
-		       "Node %d MemUsed:      %8lu kB\n"
-		       "Node %d Active:       %8lu kB\n"
-		       "Node %d Inactive:     %8lu kB\n"
+		       "Node %d MemTotal:       %8lu kB\n"
+		       "Node %d MemFree:        %8lu kB\n"
+		       "Node %d MemUsed:        %8lu kB\n"
+		       "Node %d Active:         %8lu kB\n"
+		       "Node %d Inactive:       %8lu kB\n"
+		       "Node %d Active(anon):   %8lu kB\n"
+		       "Node %d Inactive(anon): %8lu kB\n"
+		       "Node %d Active(file):   %8lu kB\n"
+		       "Node %d Inactive(file): %8lu kB\n"
 #ifdef CONFIG_HIGHMEM
-		       "Node %d HighTotal:    %8lu kB\n"
-		       "Node %d HighFree:     %8lu kB\n"
-		       "Node %d LowTotal:     %8lu kB\n"
-		       "Node %d LowFree:      %8lu kB\n"
+		       "Node %d HighTotal:      %8lu kB\n"
+		       "Node %d HighFree:       %8lu kB\n"
+		       "Node %d LowTotal:       %8lu kB\n"
+		       "Node %d LowFree:        %8lu kB\n"
 #endif
-		       "Node %d Dirty:        %8lu kB\n"
-		       "Node %d Writeback:    %8lu kB\n"
-		       "Node %d FilePages:    %8lu kB\n"
-		       "Node %d Mapped:       %8lu kB\n"
-		       "Node %d AnonPages:    %8lu kB\n"
-		       "Node %d PageTables:   %8lu kB\n"
-		       "Node %d NFS_Unstable: %8lu kB\n"
-		       "Node %d Bounce:       %8lu kB\n"
-		       "Node %d WritebackTmp: %8lu kB\n"
-		       "Node %d Slab:         %8lu kB\n"
-		       "Node %d SReclaimable: %8lu kB\n"
-		       "Node %d SUnreclaim:   %8lu kB\n",
+		       "Node %d Dirty:          %8lu kB\n"
+		       "Node %d Writeback:      %8lu kB\n"
+		       "Node %d FilePages:      %8lu kB\n"
+		       "Node %d Mapped:         %8lu kB\n"
+		       "Node %d AnonPages:      %8lu kB\n"
+		       "Node %d PageTables:     %8lu kB\n"
+		       "Node %d NFS_Unstable:   %8lu kB\n"
+		       "Node %d Bounce:         %8lu kB\n"
+		       "Node %d WritebackTmp:   %8lu kB\n"
+		       "Node %d Slab:           %8lu kB\n"
+		       "Node %d SReclaimable:   %8lu kB\n"
+		       "Node %d SUnreclaim:     %8lu kB\n",
 		       nid, K(i.totalram),
 		       nid, K(i.freeram),
 		       nid, K(i.totalram - i.freeram),
-		       nid, K(node_page_state(nid, NR_ACTIVE)),
-		       nid, K(node_page_state(nid, NR_INACTIVE)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_ANON) +
+				node_page_state(nid, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_ANON) +
+				node_page_state(nid, NR_INACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_ANON)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_ANON)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
 #ifdef CONFIG_HIGHMEM
 		       nid, K(i.totalhigh),
 		       nid, K(i.freehigh),

fs/cifs/file.c

@@ -1791,7 +1791,7 @@ static void cifs_copy_cache_pages(struct address_space *mapping,
 		SetPageUptodate(page);
 		unlock_page(page);
 		if (!pagevec_add(plru_pvec, page))
-			__pagevec_lru_add(plru_pvec);
+			__pagevec_lru_add_file(plru_pvec);
 		data += PAGE_CACHE_SIZE;
 	}
 	return;
@@ -1925,7 +1925,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		bytes_read = 0;
 	}
 
-	pagevec_lru_add(&lru_pvec);
+	pagevec_lru_add_file(&lru_pvec);
 
 /* need to free smb_read_data buf before exit */
 	if (smb_read_data) {

fs/nfs/dir.c

@@ -1517,7 +1517,7 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 	if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
 							GFP_KERNEL)) {
 		pagevec_add(&lru_pvec, page);
-		pagevec_lru_add(&lru_pvec);
+		pagevec_lru_add_file(&lru_pvec);
 		SetPageUptodate(page);
 		unlock_page(page);
 	} else

fs/ntfs/file.c

@@ -439,7 +439,7 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
 			pages[nr] = *cached_page;
 			page_cache_get(*cached_page);
 			if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
-				__pagevec_lru_add(lru_pvec);
+				__pagevec_lru_add_file(lru_pvec);
 			*cached_page = NULL;
 		}
 		index++;
@@ -2084,7 +2084,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 						OSYNC_METADATA|OSYNC_DATA);
 		}
   	}
-	pagevec_lru_add(&lru_pvec);
+	pagevec_lru_add_file(&lru_pvec);
 	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
 			written ? "written" : "status", (unsigned long)written,
 			(long)status);

fs/proc/proc_misc.c

@@ -136,6 +136,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 	unsigned long allowed;
 	struct vmalloc_info vmi;
 	long cached;
+	unsigned long pages[NR_LRU_LISTS];
+	int lru;
 
 /*
  * display in kilobytes.
@@ -154,51 +156,62 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 
 	get_vmalloc_info(&vmi);
 
+	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+		pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
 	/*
 	 * Tagged format, for easy grepping and expansion.
 	 */
 	len = sprintf(page,
-		"MemTotal:     %8lu kB\n"
-		"MemFree:      %8lu kB\n"
-		"Buffers:      %8lu kB\n"
-		"Cached:       %8lu kB\n"
-		"SwapCached:   %8lu kB\n"
-		"Active:       %8lu kB\n"
-		"Inactive:     %8lu kB\n"
+		"MemTotal:       %8lu kB\n"
+		"MemFree:        %8lu kB\n"
+		"Buffers:        %8lu kB\n"
+		"Cached:         %8lu kB\n"
+		"SwapCached:     %8lu kB\n"
+		"Active:         %8lu kB\n"
+		"Inactive:       %8lu kB\n"
+		"Active(anon):   %8lu kB\n"
+		"Inactive(anon): %8lu kB\n"
+		"Active(file):   %8lu kB\n"
+		"Inactive(file): %8lu kB\n"
 #ifdef CONFIG_HIGHMEM
-		"HighTotal:    %8lu kB\n"
-		"HighFree:     %8lu kB\n"
-		"LowTotal:     %8lu kB\n"
-		"LowFree:      %8lu kB\n"
+		"HighTotal:      %8lu kB\n"
+		"HighFree:       %8lu kB\n"
+		"LowTotal:       %8lu kB\n"
+		"LowFree:        %8lu kB\n"
 #endif
-		"SwapTotal:    %8lu kB\n"
-		"SwapFree:     %8lu kB\n"
-		"Dirty:        %8lu kB\n"
-		"Writeback:    %8lu kB\n"
-		"AnonPages:    %8lu kB\n"
-		"Mapped:       %8lu kB\n"
-		"Slab:         %8lu kB\n"
-		"SReclaimable: %8lu kB\n"
-		"SUnreclaim:   %8lu kB\n"
-		"PageTables:   %8lu kB\n"
+		"SwapTotal:      %8lu kB\n"
+		"SwapFree:       %8lu kB\n"
+		"Dirty:          %8lu kB\n"
+		"Writeback:      %8lu kB\n"
+		"AnonPages:      %8lu kB\n"
+		"Mapped:         %8lu kB\n"
+		"Slab:           %8lu kB\n"
+		"SReclaimable:   %8lu kB\n"
+		"SUnreclaim:     %8lu kB\n"
+		"PageTables:     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
-		"Quicklists:   %8lu kB\n"
+		"Quicklists:     %8lu kB\n"
 #endif
-		"NFS_Unstable: %8lu kB\n"
-		"Bounce:       %8lu kB\n"
-		"WritebackTmp: %8lu kB\n"
-		"CommitLimit:  %8lu kB\n"
-		"Committed_AS: %8lu kB\n"
-		"VmallocTotal: %8lu kB\n"
-		"VmallocUsed:  %8lu kB\n"
-		"VmallocChunk: %8lu kB\n",
+		"NFS_Unstable:   %8lu kB\n"
+		"Bounce:         %8lu kB\n"
+		"WritebackTmp:   %8lu kB\n"
+		"CommitLimit:    %8lu kB\n"
+		"Committed_AS:   %8lu kB\n"
+		"VmallocTotal:   %8lu kB\n"
+		"VmallocUsed:    %8lu kB\n"
+		"VmallocChunk:   %8lu kB\n",
 		K(i.totalram),
 		K(i.freeram),
 		K(i.bufferram),
 		K(cached),
 		K(total_swapcache_pages),
-		K(global_page_state(NR_ACTIVE)),
-		K(global_page_state(NR_INACTIVE)),
+		K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+		K(pages[LRU_ACTIVE_ANON]),
+		K(pages[LRU_INACTIVE_ANON]),
+		K(pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_FILE]),
 #ifdef CONFIG_HIGHMEM
 		K(i.totalhigh),
 		K(i.freehigh),

fs/ramfs/file-nommu.c

@@ -112,12 +112,12 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 			goto add_error;
 
 		if (!pagevec_add(&lru_pvec, page))
-			__pagevec_lru_add(&lru_pvec);
+			__pagevec_lru_add_file(&lru_pvec);
 
 		unlock_page(page);
 	}
 
-	pagevec_lru_add(&lru_pvec);
+	pagevec_lru_add_file(&lru_pvec);
 	return 0;
 
  fsize_exceeded:

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 */

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);
 

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;
 }

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 */
 

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 */

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);

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

mm/filemap.c

@@ -33,6 +33,7 @@
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
+#include <linux/mm_inline.h> /* for page_is_file_cache() */
 #include "internal.h"
 
 /*
@@ -492,9 +493,24 @@ EXPORT_SYMBOL(add_to_page_cache_locked);
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t offset, gfp_t gfp_mask)
 {
-	int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
-	if (ret == 0)
-		lru_cache_add(page);
+	int ret;
+
+	/*
+	 * Splice_read and readahead add shmem/tmpfs pages into the page cache
+	 * before shmem_readpage has a chance to mark them as SwapBacked: they
+	 * need to go on the active_anon lru below, and mem_cgroup_cache_charge
+	 * (called in add_to_page_cache) needs to know where they're going too.
+	 */
+	if (mapping_cap_swap_backed(mapping))
+		SetPageSwapBacked(page);
+
+	ret = add_to_page_cache(page, mapping, offset, gfp_mask);
+	if (ret == 0) {
+		if (page_is_file_cache(page))
+			lru_cache_add_file(page);
+		else
+			lru_cache_add_active_anon(page);
+	}
 	return ret;
 }
 

mm/hugetlb.c

@@ -1459,11 +1459,11 @@ int hugetlb_report_meminfo(char *buf)
 {
 	struct hstate *h = &default_hstate;
 	return sprintf(buf,
-			"HugePages_Total: %5lu\n"
-			"HugePages_Free:  %5lu\n"
-			"HugePages_Rsvd:  %5lu\n"
-			"HugePages_Surp:  %5lu\n"
-			"Hugepagesize:    %5lu kB\n",
+			"HugePages_Total:   %5lu\n"
+			"HugePages_Free:    %5lu\n"
+			"HugePages_Rsvd:    %5lu\n"
+			"HugePages_Surp:    %5lu\n"
+			"Hugepagesize:   %8lu kB\n",
 			h->nr_huge_pages,
 			h->free_huge_pages,
 			h->resv_huge_pages,

mm/memcontrol.c

@@ -162,6 +162,7 @@ struct page_cgroup {
 };
 #define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
 #define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE	(0x4)	/* page is file system backed */
 
 static int page_cgroup_nid(struct page_cgroup *pc)
 {
@@ -177,6 +178,7 @@ enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
 	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
+	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
 };
 
 /*
@@ -288,8 +290,12 @@ static void unlock_page_cgroup(struct page *page)
 static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 			struct page_cgroup *pc)
 {
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	int lru = !!from;
+	int lru = LRU_BASE;
+
+	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+		lru += LRU_ACTIVE;
+	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+		lru += LRU_FILE;
 
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
@@ -300,10 +306,12 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 				struct page_cgroup *pc)
 {
-	int lru = LRU_INACTIVE;
+	int lru = LRU_BASE;
 
 	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
 		lru += LRU_ACTIVE;
+	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+		lru += LRU_FILE;
 
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_add(&pc->lru, &mz->lists[lru]);
@@ -314,10 +322,9 @@ static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 {
 	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int lru = LRU_INACTIVE;
-
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
+	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
+	int lru = LRU_FILE * !!file + !!from;
 
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
@@ -326,7 +333,7 @@ static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 	else
 		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
 
-	lru = !!active;
+	lru = LRU_FILE * !!file + !!active;
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_move(&pc->lru, &mz->lists[lru]);
 }
@@ -390,21 +397,6 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
 	return (int)((rss * 100L) / total);
 }
 
-/*
- * This function is called from vmscan.c. In page reclaiming loop. balance
- * between active and inactive list is calculated. For memory controller
- * page reclaiming, we should use using mem_cgroup's imbalance rather than
- * zone's global lru imbalance.
- */
-long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
-{
-	unsigned long active, inactive;
-	/* active and inactive are the number of pages. 'long' is ok.*/
-	active = mem_cgroup_get_all_zonestat(mem, LRU_ACTIVE);
-	inactive = mem_cgroup_get_all_zonestat(mem, LRU_INACTIVE);
-	return (long) (active / (inactive + 1));
-}
-
 /*
  * prev_priority control...this will be used in memory reclaim path.
  */
@@ -450,7 +442,7 @@ 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)
 {
 	unsigned long nr_taken = 0;
 	struct page *page;
@@ -461,7 +453,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int nid = z->zone_pgdat->node_id;
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
-	int lru = !!active;
+	int lru = LRU_FILE * !!file + !!active;
 
 	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
@@ -477,6 +469,9 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		if (unlikely(!PageLRU(page)))
 			continue;
 
+		/*
+		 * TODO: play better with lumpy reclaim, grabbing anything.
+		 */
 		if (PageActive(page) && !active) {
 			__mem_cgroup_move_lists(pc, true);
 			continue;
@@ -489,7 +484,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		scan++;
 		list_move(&pc->lru, &pc_list);
 
-		if (__isolate_lru_page(page, mode) == 0) {
+		if (__isolate_lru_page(page, mode, file) == 0) {
 			list_move(&page->lru, dst);
 			nr_taken++;
 		}
@@ -575,10 +570,16 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	 * If a page is accounted as a page cache, insert to inactive list.
 	 * If anon, insert to active list.
 	 */
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
 		pc->flags = PAGE_CGROUP_FLAG_CACHE;
-	else
+		if (page_is_file_cache(page))
+			pc->flags |= PAGE_CGROUP_FLAG_FILE;
+		else
+			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+	} else if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
 		pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
+	else /* MEM_CGROUP_CHARGE_TYPE_SHMEM */
+		pc->flags = PAGE_CGROUP_FLAG_CACHE | PAGE_CGROUP_FLAG_ACTIVE;
 
 	lock_page_cgroup(page);
 	if (unlikely(page_get_page_cgroup(page))) {
@@ -737,8 +738,12 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 	if (pc) {
 		mem = pc->mem_cgroup;
 		css_get(&mem->css);
-		if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
-			ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+		if (pc->flags & PAGE_CGROUP_FLAG_CACHE) {
+			if (page_is_file_cache(page))
+				ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+			else
+				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+		}
 	}
 	unlock_page_cgroup(page);
 	if (mem) {
@@ -982,14 +987,21 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	}
 	/* showing # of active pages */
 	{
-		unsigned long active, inactive;
-
-		inactive = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_INACTIVE);
-		active = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_ACTIVE);
-		cb->fill(cb, "active", (active) * PAGE_SIZE);
-		cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
+		unsigned long active_anon, inactive_anon;
+		unsigned long active_file, inactive_file;
+
+		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_INACTIVE_ANON);
+		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_ACTIVE_ANON);
+		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_INACTIVE_FILE);
+		active_file = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_ACTIVE_FILE);
+		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
+		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
+		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
+		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
 	}
 	return 0;
 }

mm/memory.c

@@ -1889,7 +1889,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		set_pte_at(mm, address, page_table, entry);
 		update_mmu_cache(vma, address, entry);
 		SetPageSwapBacked(new_page);
-		lru_cache_add_active(new_page);
+		lru_cache_add_active_anon(new_page);
 		page_add_new_anon_rmap(new_page, vma, address);
 
 		if (old_page) {
@@ -2384,7 +2384,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto release;
 	inc_mm_counter(mm, anon_rss);
 	SetPageSwapBacked(page);
-	lru_cache_add_active(page);
+	lru_cache_add_active_anon(page);
 	page_add_new_anon_rmap(page, vma, address);
 	set_pte_at(mm, address, page_table, entry);
 
@@ -2526,7 +2526,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (anon) {
                         inc_mm_counter(mm, anon_rss);
 			SetPageSwapBacked(page);
-                        lru_cache_add_active(page);
+                        lru_cache_add_active_anon(page);
                         page_add_new_anon_rmap(page, vma, address);
 		} else {
 			inc_mm_counter(mm, file_rss);

mm/page-writeback.c

@@ -329,9 +329,7 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 		struct zone *z =
 			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
 
-		x += zone_page_state(z, NR_FREE_PAGES)
-			+ zone_page_state(z, NR_INACTIVE)
-			+ zone_page_state(z, NR_ACTIVE);
+		x += zone_page_state(z, NR_FREE_PAGES) + zone_lru_pages(z);
 	}
 	/*
 	 * Make sure that the number of highmem pages is never larger
@@ -355,9 +353,7 @@ unsigned long determine_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES)
-		+ global_page_state(NR_INACTIVE)
-		+ global_page_state(NR_ACTIVE);
+	x = global_page_state(NR_FREE_PAGES) + global_lru_pages();
 
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);

mm/page_alloc.c

@@ -1864,10 +1864,13 @@ void show_free_areas(void)
 		}
 	}
 
-	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu\n"
+	printk("Active_anon:%lu active_file:%lu inactive_anon%lu\n"
+		" inactive_file:%lu dirty:%lu writeback:%lu unstable:%lu\n"
 		" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
-		global_page_state(NR_ACTIVE),
-		global_page_state(NR_INACTIVE),
+		global_page_state(NR_ACTIVE_ANON),
+		global_page_state(NR_ACTIVE_FILE),
+		global_page_state(NR_INACTIVE_ANON),
+		global_page_state(NR_INACTIVE_FILE),
 		global_page_state(NR_FILE_DIRTY),
 		global_page_state(NR_WRITEBACK),
 		global_page_state(NR_UNSTABLE_NFS),
@@ -1890,8 +1893,10 @@ void show_free_areas(void)
 			" min:%lukB"
 			" low:%lukB"
 			" high:%lukB"
-			" active:%lukB"
-			" inactive:%lukB"
+			" active_anon:%lukB"
+			" inactive_anon:%lukB"
+			" active_file:%lukB"
+			" inactive_file:%lukB"
 			" present:%lukB"
 			" pages_scanned:%lu"
 			" all_unreclaimable? %s"
@@ -1901,8 +1906,10 @@ void show_free_areas(void)
 			K(zone->pages_min),
 			K(zone->pages_low),
 			K(zone->pages_high),
-			K(zone_page_state(zone, NR_ACTIVE)),
-			K(zone_page_state(zone, NR_INACTIVE)),
+			K(zone_page_state(zone, NR_ACTIVE_ANON)),
+			K(zone_page_state(zone, NR_INACTIVE_ANON)),
+			K(zone_page_state(zone, NR_ACTIVE_FILE)),
+			K(zone_page_state(zone, NR_INACTIVE_FILE)),
 			K(zone->present_pages),
 			zone->pages_scanned,
 			(zone_is_all_unreclaimable(zone) ? "yes" : "no")
@@ -3472,6 +3479,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			INIT_LIST_HEAD(&zone->lru[l].list);
 			zone->lru[l].nr_scan = 0;
 		}
+		zone->recent_rotated[0] = 0;
+		zone->recent_rotated[1] = 0;
+		zone->recent_scanned[0] = 0;
+		zone->recent_scanned[1] = 0;
 		zap_zone_vm_stats(zone);
 		zone->flags = 0;
 		if (!size)

mm/readahead.c

@@ -229,7 +229,7 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
  */
 unsigned long max_sane_readahead(unsigned long nr)
 {
-	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE)
+	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
 		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
 }
 

mm/shmem.c

@@ -199,7 +199,7 @@ static struct vm_operations_struct shmem_vm_ops;
 
 static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 	.unplug_io_fn	= default_unplug_io_fn,
 };
 

mm/swap.c

@@ -116,7 +116,8 @@ static void pagevec_move_tail(struct pagevec *pvec)
 			spin_lock(&zone->lru_lock);
 		}
 		if (PageLRU(page) && !PageActive(page)) {
-			list_move_tail(&page->lru, &zone->lru[LRU_INACTIVE].list);
+			int lru = page_is_file_cache(page);
+			list_move_tail(&page->lru, &zone->lru[lru].list);
 			pgmoved++;
 		}
 	}
@@ -157,11 +158,18 @@ void activate_page(struct page *page)
 
 	spin_lock_irq(&zone->lru_lock);
 	if (PageLRU(page) && !PageActive(page)) {
-		del_page_from_inactive_list(zone, page);
+		int file = page_is_file_cache(page);
+		int lru = LRU_BASE + file;
+		del_page_from_lru_list(zone, page, lru);
+
 		SetPageActive(page);
-		add_page_to_active_list(zone, page);
+		lru += LRU_ACTIVE;
+		add_page_to_lru_list(zone, page, lru);
 		__count_vm_event(PGACTIVATE);
 		mem_cgroup_move_lists(page, true);
+
+		zone->recent_rotated[!!file]++;
+		zone->recent_scanned[!!file]++;
 	}
 	spin_unlock_irq(&zone->lru_lock);
 }

mm/swap_state.c

@@ -33,7 +33,7 @@ static const struct address_space_operations swap_aops = {
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 	.unplug_io_fn	= swap_unplug_io_fn,
 };
 
@@ -310,7 +310,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			/*
 			 * Initiate read into locked page and return.
 			 */
-			lru_cache_add_active(new_page);
+			lru_cache_add_active_anon(new_page);
 			swap_readpage(NULL, new_page);
 			return new_page;
 		}

mm/vmstat.c

@@ -619,8 +619,10 @@ const struct seq_operations pagetypeinfo_op = {
 static const char * const vmstat_text[] = {
 	/* Zoned VM counters */
 	"nr_free_pages",
-	"nr_inactive",
-	"nr_active",
+	"nr_inactive_anon",
+	"nr_active_anon",
+	"nr_inactive_file",
+	"nr_active_file",
 	"nr_anon_pages",
 	"nr_mapped",
 	"nr_file_pages",
@@ -688,7 +690,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        min      %lu"
 		   "\n        low      %lu"
 		   "\n        high     %lu"
-		   "\n        scanned  %lu (a: %lu i: %lu)"
+		   "\n        scanned  %lu (aa: %lu ia: %lu af: %lu if: %lu)"
 		   "\n        spanned  %lu"
 		   "\n        present  %lu",
 		   zone_page_state(zone, NR_FREE_PAGES),
@@ -696,8 +698,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   zone->pages_low,
 		   zone->pages_high,
 		   zone->pages_scanned,
-		   zone->lru[LRU_ACTIVE].nr_scan,
-		   zone->lru[LRU_INACTIVE].nr_scan,
+		   zone->lru[LRU_ACTIVE_ANON].nr_scan,
+		   zone->lru[LRU_INACTIVE_ANON].nr_scan,
+		   zone->lru[LRU_ACTIVE_FILE].nr_scan,
+		   zone->lru[LRU_INACTIVE_FILE].nr_scan,
 		   zone->spanned_pages,
 		   zone->present_pages);