Unevictable LRU Infrastructure

When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages.  Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.

Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan.  Based on a patch by Larry Woodman of Red Hat.  Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.

Kosaki Motohiro added the support for the memory controller unevictable
lru list.

Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.

The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.

A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable.  Subsequent patches will add the various
!evictable tests.  We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.

To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference.  If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list.  This way, we avoid "stranding" evictable pages on the
unevictable list.

[[email protected]: fix fallout from out-of-order merge]
[[email protected]: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[[email protected]: remove redundant mapping check]
[[email protected]: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[[email protected]: kill unnecessary lock_page() in vmscan.c]
[[email protected]: revert migration change of unevictable lru infrastructure]
[[email protected]: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[[email protected]: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <[email protected]>
Signed-off-by: Rik van Riel <[email protected]>
Signed-off-by: KOSAKI Motohiro <[email protected]>
Debugged-by: Benjamin Kidwell <[email protected]>
Signed-off-by: Daisuke Nishimura <[email protected]>
Signed-off-by: KAMEZAWA Hiroyuki <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/memcontrol.h

@@ -34,9 +34,9 @@ extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
+extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
-extern void mem_cgroup_move_lists(struct page *page, bool active);
 extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
 
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,

include/linux/mm_inline.h

@@ -91,11 +91,16 @@ del_page_from_lru(struct zone *zone, struct page *page)
 	enum lru_list l = LRU_BASE;
 
 	list_del(&page->lru);
-	if (PageActive(page)) {
-		__ClearPageActive(page);
-		l += LRU_ACTIVE;
+	if (PageUnevictable(page)) {
+		__ClearPageUnevictable(page);
+		l = LRU_UNEVICTABLE;
+	} else {
+		if (PageActive(page)) {
+			__ClearPageActive(page);
+			l += LRU_ACTIVE;
+		}
+		l += page_is_file_cache(page);
 	}
-	l += page_is_file_cache(page);
 	__dec_zone_state(zone, NR_LRU_BASE + l);
 }
 
@@ -110,9 +115,13 @@ static inline enum lru_list page_lru(struct page *page)
 {
 	enum lru_list lru = LRU_BASE;
 
-	if (PageActive(page))
-		lru += LRU_ACTIVE;
-	lru += page_is_file_cache(page);
+	if (PageUnevictable(page))
+		lru = LRU_UNEVICTABLE;
+	else {
+		if (PageActive(page))
+			lru += LRU_ACTIVE;
+		lru += page_is_file_cache(page);
+	}
 
 	return lru;
 }

include/linux/mmzone.h

@@ -86,6 +86,11 @@ enum zone_stat_item {
 	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
+#ifdef CONFIG_UNEVICTABLE_LRU
+	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+#else
+	NR_UNEVICTABLE = NR_ACTIVE_FILE, /* avoid compiler errors in dead code */
+#endif
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
@@ -128,10 +133,18 @@ enum lru_list {
 	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 };
+#ifdef CONFIG_UNEVICTABLE_LRU
+	LRU_UNEVICTABLE,
+#else
+	LRU_UNEVICTABLE = LRU_ACTIVE_FILE, /* avoid compiler errors in dead code */
+#endif
+	NR_LRU_LISTS
+};
 
 #define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
 
+#define for_each_evictable_lru(l) for (l = 0; l <= LRU_ACTIVE_FILE; l++)
+
 static inline int is_file_lru(enum lru_list l)
 {
 	return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE);
@@ -142,6 +155,15 @@ static inline int is_active_lru(enum lru_list l)
 	return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE);
 }
 
+static inline int is_unevictable_lru(enum lru_list l)
+{
+#ifdef CONFIG_UNEVICTABLE_LRU
+	return (l == LRU_UNEVICTABLE);
+#else
+	return 0;
+#endif
+}
+
 struct per_cpu_pages {
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */

include/linux/page-flags.h

@@ -94,6 +94,9 @@ enum pageflags {
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_buddy,		/* Page is free, on buddy lists */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
+#ifdef CONFIG_UNEVICTABLE_LRU
+	PG_unevictable,		/* Page is "unevictable"  */
+#endif
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 	PG_uncached,		/* Page has been mapped as uncached */
 #endif
@@ -182,6 +185,7 @@ PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
 PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
 PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
+	TESTCLEARFLAG(Active, active)
 __PAGEFLAG(Slab, slab)
 PAGEFLAG(Checked, checked)		/* Used by some filesystems */
 PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
@@ -225,6 +229,15 @@ PAGEFLAG(SwapCache, swapcache)
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
+	TESTCLEARFLAG(Unevictable, unevictable)
+#else
+PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable)
+	SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable)
+	__CLEARPAGEFLAG_NOOP(Unevictable)
+#endif
+
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 PAGEFLAG(Uncached, uncached)
 #else
@@ -340,9 +353,16 @@ static inline void __ClearPageTail(struct page *page)
 
 #endif /* !PAGEFLAGS_EXTENDED */
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+#define __PG_UNEVICTABLE (1 << PG_unevictable)
+#else
+#define __PG_UNEVICTABLE 0
+#endif
+
 #define PAGE_FLAGS	(1 << PG_lru   | 1 << PG_private   | 1 << PG_locked | \
 			 1 << PG_buddy | 1 << PG_writeback | \
-			 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active)
+			 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active | \
+			 __PG_UNEVICTABLE)
 
 /*
  * Flags checked in bad_page().  Pages on the free list should not have

include/linux/pagevec.h

@@ -101,7 +101,6 @@ 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))

include/linux/swap.h

@@ -180,6 +180,8 @@ extern int lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void swap_setup(void);
 
+extern void add_page_to_unevictable_list(struct page *page);
+
 /**
  * lru_cache_add: add a page to the page lists
  * @page: the page to add
@@ -228,6 +230,16 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 }
 #endif
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+extern int page_evictable(struct page *page, struct vm_area_struct *vma);
+#else
+static inline int page_evictable(struct page *page,
+						struct vm_area_struct *vma)
+{
+	return 1;
+}
+#endif
+
 extern int kswapd_run(int nid);
 
 #ifdef CONFIG_MMU

mm/Kconfig

@@ -209,5 +209,16 @@ config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
 
+config UNEVICTABLE_LRU
+	bool "Add LRU list to track non-evictable pages"
+	default y
+	depends on MMU
+	help
+	  Keeps unevictable pages off of the active and inactive pageout
+	  lists, so kswapd will not waste CPU time or have its balancing
+	  algorithms thrown off by scanning these pages.  Selecting this
+	  will use one page flag and increase the code size a little,
+	  say Y unless you know what you are doing.
+
 config MMU_NOTIFIER
 	bool

mm/internal.h

@@ -39,8 +39,15 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
+/*
+ * in mm/vmscan.c:
+ */
 extern int isolate_lru_page(struct page *page);
+extern void putback_lru_page(struct page *page);
 
+/*
+ * in mm/page_alloc.c
+ */
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
@@ -54,6 +61,25 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * unevictable_migrate_page() called only from migrate_page_copy() to
+ * migrate unevictable flag to new page.
+ * Note that the old page has been isolated from the LRU lists at this
+ * point so we don't need to worry about LRU statistics.
+ */
+static inline void unevictable_migrate_page(struct page *new, struct page *old)
+{
+	if (TestClearPageUnevictable(old))
+		SetPageUnevictable(new);
+}
+#else
+static inline void unevictable_migrate_page(struct page *new, struct page *old)
+{
+}
+#endif
+
+
 /*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
  * so all functions starting at paging_init should be marked __init

mm/memcontrol.c

@@ -160,9 +160,10 @@ struct page_cgroup {
 	struct mem_cgroup *mem_cgroup;
 	int flags;
 };
-#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 */
+#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 */
+#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8)	/* page is unevictableable */
 
 static int page_cgroup_nid(struct page_cgroup *pc)
 {
@@ -292,10 +293,14 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 {
 	int lru = LRU_BASE;
 
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
-	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
-		lru += LRU_FILE;
+	if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+		lru = LRU_UNEVICTABLE;
+	else {
+		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;
 
@@ -308,32 +313,46 @@ static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 {
 	int lru = LRU_BASE;
 
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
-	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
-		lru += LRU_FILE;
+	if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+		lru = LRU_UNEVICTABLE;
+	else {
+		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]);
 
 	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
 }
 
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
 {
 	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
-	int lru = LRU_FILE * !!file + !!from;
+	int active    = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int file      = pc->flags & PAGE_CGROUP_FLAG_FILE;
+	int unevictable = pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE;
+	enum lru_list from = unevictable ? LRU_UNEVICTABLE :
+				(LRU_FILE * !!file + !!active);
 
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	if (lru == from)
+		return;
 
-	if (active)
-		pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
-	else
+	MEM_CGROUP_ZSTAT(mz, from) -= 1;
+
+	if (is_unevictable_lru(lru)) {
 		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+		pc->flags |= PAGE_CGROUP_FLAG_UNEVICTABLE;
+	} else {
+		if (is_active_lru(lru))
+			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+		else
+			pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+		pc->flags &= ~PAGE_CGROUP_FLAG_UNEVICTABLE;
+	}
 
-	lru = LRU_FILE * !!file + !!active;
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_move(&pc->lru, &mz->lists[lru]);
 }
@@ -351,7 +370,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 /*
  * This routine assumes that the appropriate zone's lru lock is already held
  */
-void mem_cgroup_move_lists(struct page *page, bool active)
+void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup_per_zone *mz;
@@ -374,7 +393,7 @@ void mem_cgroup_move_lists(struct page *page, bool active)
 	if (pc) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_move_lists(pc, active);
+		__mem_cgroup_move_lists(pc, lru);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 	}
 	unlock_page_cgroup(page);
@@ -472,12 +491,10 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		/*
 		 * TODO: play better with lumpy reclaim, grabbing anything.
 		 */
-		if (PageActive(page) && !active) {
-			__mem_cgroup_move_lists(pc, true);
-			continue;
-		}
-		if (!PageActive(page) && active) {
-			__mem_cgroup_move_lists(pc, false);
+		if (PageUnevictable(page) ||
+		    (PageActive(page) && !active) ||
+		    (!PageActive(page) && active)) {
+			__mem_cgroup_move_lists(pc, page_lru(page));
 			continue;
 		}
 

mm/mempolicy.c

@@ -2202,7 +2202,7 @@ static void gather_stats(struct page *page, void *private, int pte_dirty)
 	if (PageSwapCache(page))
 		md->swapcache++;
 
-	if (PageActive(page))
+	if (PageActive(page) || PageUnevictable(page))
 		md->active++;
 
 	if (PageWriteback(page))