idle memory tracking

@@ -116,6 +116,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+extern unsigned long page_cgroup_ino(struct page *page);
 
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,

@@ -631,6 +631,29 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 	return &memcg->css;
 }
 
+/**
+ * page_cgroup_ino - return inode number of the memcg a page is charged to
+ * @page: the page
+ *
+ * Look up the closest online ancestor of the memory cgroup @page is charged to
+ * and return its inode number or 0 if @page is not charged to any cgroup. It
+ * is safe to call this function without holding a reference to @page.
+ */
+unsigned long page_cgroup_ino(struct page *page)
+{
+	struct mem_cgroup *memcg;
+	unsigned long ino = 0;
+
+	rcu_read_lock();
+	memcg = READ_ONCE(page->mem_cgroup);
+	while (memcg && !(memcg->css.flags & CSS_ONLINE))
+		memcg = parent_mem_cgroup(memcg);
+	if (memcg)
+		ino = cgroup_ino(memcg->css.cgroup);
+	rcu_read_unlock();
+	return ino;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {

@@ -94,7 +94,6 @@ bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 			      struct mem_cgroup *root);
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 
-extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);

@@ -259,11 +258,6 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 	return &zone->lruvec;
 }
 
-static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
-{
-	return NULL;
-}
-
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 		struct mem_cgroup *memcg)
 {

@@ -2378,40 +2378,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 	css_put_many(&memcg->css, nr_pages);
 }
 
-/*
- * try_get_mem_cgroup_from_page - look up page's memcg association
- * @page: the page
- *
- * Look up, get a css reference, and return the memcg that owns @page.
- *
- * The page must be locked to prevent racing with swap-in and page
- * cache charges.  If coming from an unlocked page table, the caller
- * must ensure the page is on the LRU or this can race with charging.
- */
-struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
-{
-	struct mem_cgroup *memcg;
-	unsigned short id;
-	swp_entry_t ent;
-
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-
-	memcg = page->mem_cgroup;
-	if (memcg) {
-		if (!css_tryget_online(&memcg->css))
-			memcg = NULL;
-	} else if (PageSwapCache(page)) {
-		ent.val = page_private(page);
-		id = lookup_swap_cgroup_id(ent);
-		rcu_read_lock();
-		memcg = mem_cgroup_from_id(id);
-		if (memcg && !css_tryget_online(&memcg->css))
-			memcg = NULL;
-		rcu_read_unlock();
-	}
-	return memcg;
-}
-
 static void lock_page_lru(struct page *page, int *isolated)
 {
 	struct zone *zone = page_zone(page);

@@ -5628,8 +5594,20 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		 * the page lock, which serializes swap cache removal, which
 		 * in turn serializes uncharging.
 		 */
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		if (page->mem_cgroup)
 			goto out;
+
+		if (do_swap_account) {
+			swp_entry_t ent = { .val = page_private(page), };
+			unsigned short id = lookup_swap_cgroup_id(ent);
+
+			rcu_read_lock();
+			memcg = mem_cgroup_from_id(id);
+			if (memcg && !css_tryget_online(&memcg->css))
+				memcg = NULL;
+			rcu_read_unlock();
+		}
 	}
 
 	if (PageTransHuge(page)) {

@@ -5637,8 +5615,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 	}
 
-	if (do_swap_account && PageSwapCache(page))
-		memcg = try_get_mem_cgroup_from_page(page);
 	if (!memcg)
 		memcg = get_mem_cgroup_from_mm(mm);
 

@@ -5,7 +5,7 @@ pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
 userspace programs to examine the page tables and related information by
 reading files in /proc.
 
-There are three components to pagemap:
+There are four components to pagemap:
 
  * /proc/pid/pagemap.  This file lets a userspace process find out which
    physical frame each virtual page is mapped to.  It contains one 64-bit

@@ -65,6 +65,10 @@ There are three components to pagemap:
     23. BALLOON
     24. ZERO_PAGE
 
+ * /proc/kpagecgroup.  This file contains a 64-bit inode number of the
+   memory cgroup each page is charged to, indexed by PFN. Only available when
+   CONFIG_MEMCG is set.
+
 Short descriptions to the page flags:
 
  0. LOCKED

@@ -9,6 +9,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
 #include <linux/kernel-page-flags.h>
 #include <asm/uaccess.h>
 #include "internal.h"

@@ -225,10 +226,62 @@ static const struct file_operations proc_kpageflags_operations = {
 	.read = kpageflags_read,
 };
 
+#ifdef CONFIG_MEMCG
+static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	u64 __user *out = (u64 __user *)buf;
+	struct page *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 ino;
+
+	pfn = src / KPMSIZE;
+	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+
+	while (count > 0) {
+		if (pfn_valid(pfn))
+			ppage = pfn_to_page(pfn);
+		else
+			ppage = NULL;
+
+		if (ppage)
+			ino = page_cgroup_ino(ppage);
+		else
+			ino = 0;
+
+		if (put_user(ino, out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+static const struct file_operations proc_kpagecgroup_operations = {
+	.llseek = mem_lseek,
+	.read = kpagecgroup_read,
+};
+#endif /* CONFIG_MEMCG */
+
 static int __init proc_page_init(void)
 {
 	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
 	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
+#ifdef CONFIG_MEMCG
+	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
+#endif
 	return 0;
 }
 fs_initcall(proc_page_init);

@@ -5,7 +5,7 @@ pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
 userspace programs to examine the page tables and related information by
 reading files in /proc.
 
-There are four components to pagemap:
+There are five components to pagemap:
 
  * /proc/pid/pagemap.  This file lets a userspace process find out which
    physical frame each virtual page is mapped to.  It contains one 64-bit

@@ -69,6 +69,16 @@ There are four components to pagemap:
    memory cgroup each page is charged to, indexed by PFN. Only available when
    CONFIG_MEMCG is set.
 
+ * /proc/kpageidle.  This file implements a bitmap where each bit corresponds
+   to a page, indexed by PFN. When the bit is set, the corresponding page is
+   idle. A page is considered idle if it has not been accessed since it was
+   marked idle. To mark a page idle one should set the bit corresponding to the
+   page by writing to the file. A value written to the file is OR-ed with the
+   current bitmap value. Only user memory pages can be marked idle, for other
+   page types input is silently ignored. Writing to this file beyond max PFN
+   results in the ENXIO error. Only available when CONFIG_IDLE_PAGE_TRACKING is
+   set.
+
 Short descriptions to the page flags:
 
  0. LOCKED

@@ -5,6 +5,7 @@
 #include <linux/ksm.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
+#include <linux/rmap.h>
 #include <linux/huge_mm.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>

@@ -16,6 +17,7 @@
 
 #define KPMSIZE sizeof(u64)
 #define KPMMASK (KPMSIZE - 1)
+#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
 
 /* /proc/kpagecount - an array exposing page counts
  *

@@ -275,6 +277,222 @@ static const struct file_operations proc_kpagecgroup_operations = {
 };
 #endif /* CONFIG_MEMCG */
 
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+/*
+ * Idle page tracking only considers user memory pages, for other types of
+ * pages the idle flag is always unset and an attempt to set it is silently
+ * ignored.
+ *
+ * We treat a page as a user memory page if it is on an LRU list, because it is
+ * always safe to pass such a page to rmap_walk(), which is essential for idle
+ * page tracking. With such an indicator of user pages we can skip isolated
+ * pages, but since there are not usually many of them, it will hardly affect
+ * the overall result.
+ *
+ * This function tries to get a user memory page by pfn as described above.
+ */
+static struct page *kpageidle_get_page(unsigned long pfn)
+{
+	struct page *page;
+	struct zone *zone;
+
+	if (!pfn_valid(pfn))
+		return NULL;
+
+	page = pfn_to_page(pfn);
+	if (!page || PageTail(page) || !PageLRU(page) ||
+	    !get_page_unless_zero(page))
+		return NULL;
+
+	if (unlikely(PageTail(page))) {
+		put_page(page);
+		return NULL;
+	}
+
+	zone = page_zone(page);
+	spin_lock_irq(&zone->lru_lock);
+	if (unlikely(!PageLRU(page))) {
+		put_page(page);
+		page = NULL;
+	}
+	spin_unlock_irq(&zone->lru_lock);
+	return page;
+}
+
+static int kpageidle_clear_pte_refs_one(struct page *page,
+					struct vm_area_struct *vma,
+					unsigned long addr, void *arg)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
+	pmd_t *pmd;
+	pte_t *pte;
+	bool referenced = false;
+
+	if (unlikely(PageTransHuge(page))) {
+		pmd = page_check_address_pmd(page, mm, addr,
+					     PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+		if (pmd) {
+			referenced = pmdp_test_and_clear_young(vma, addr, pmd);
+			spin_unlock(ptl);
+		}
+	} else {
+		pte = page_check_address(page, mm, addr, &ptl, 0);
+		if (pte) {
+			referenced = ptep_test_and_clear_young(vma, addr, pte);
+			pte_unmap_unlock(pte, ptl);
+		}
+	}
+	if (referenced) {
+		clear_page_idle(page);
+		/*
+		 * We cleared the referenced bit in a mapping to this page. To
+		 * avoid interference with page reclaim, mark it young so that
+		 * page_referenced() will return > 0.
+		 */
+		set_page_young(page);
+	}
+	return SWAP_AGAIN;
+}
+
+static void kpageidle_clear_pte_refs(struct page *page)
+{
+	struct rmap_walk_control rwc = {
+		.rmap_one = kpageidle_clear_pte_refs_one,
+		.anon_lock = page_lock_anon_vma_read,
+	};
+	bool need_lock;
+
+	if (!page_mapped(page) ||
+	    !page_rmapping(page))
+		return;
+
+	need_lock = !PageAnon(page) || PageKsm(page);
+	if (need_lock && !trylock_page(page))
+		return;
+
+	rmap_walk(page, &rwc);
+
+	if (need_lock)
+		unlock_page(page);
+}
+
+static ssize_t kpageidle_read(struct file *file, char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	u64 __user *out = (u64 __user *)buf;
+	struct page *page;
+	unsigned long pfn, end_pfn;
+	ssize_t ret = 0;
+	u64 idle_bitmap = 0;
+	int bit;
+
+	if (*ppos & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+
+	pfn = *ppos * BITS_PER_BYTE;
+	if (pfn >= max_pfn)
+		return 0;
+
+	end_pfn = pfn + count * BITS_PER_BYTE;
+	if (end_pfn > max_pfn)
+		end_pfn = ALIGN(max_pfn, KPMBITS);
+
+	for (; pfn < end_pfn; pfn++) {
+		bit = pfn % KPMBITS;
+		page = kpageidle_get_page(pfn);
+		if (page) {
+			if (page_is_idle(page)) {
+				/*
+				 * The page might have been referenced via a
+				 * pte, in which case it is not idle. Clear
+				 * refs and recheck.
+				 */
+				kpageidle_clear_pte_refs(page);
+				if (page_is_idle(page))
+					idle_bitmap |= 1ULL << bit;
+			}
+			put_page(page);
+		}
+		if (bit == KPMBITS - 1) {
+			if (put_user(idle_bitmap, out)) {
+				ret = -EFAULT;
+				break;
+			}
+			idle_bitmap = 0;
+			out++;
+		}
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+static ssize_t kpageidle_write(struct file *file, const char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	const u64 __user *in = (const u64 __user *)buf;
+	struct page *page;
+	unsigned long pfn, end_pfn;
+	ssize_t ret = 0;
+	u64 idle_bitmap = 0;
+	int bit;
+
+	if (*ppos & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+
+	pfn = *ppos * BITS_PER_BYTE;
+	if (pfn >= max_pfn)
+		return -ENXIO;
+
+	end_pfn = pfn + count * BITS_PER_BYTE;
+	if (end_pfn > max_pfn)
+		end_pfn = ALIGN(max_pfn, KPMBITS);
+
+	for (; pfn < end_pfn; pfn++) {
+		bit = pfn % KPMBITS;
+		if (bit == 0) {
+			if (get_user(idle_bitmap, in)) {
+				ret = -EFAULT;
+				break;
+			}
+			in++;
+		}
+		if (idle_bitmap >> bit & 1) {
+			page = kpageidle_get_page(pfn);
+			if (page) {
+				kpageidle_clear_pte_refs(page);
+				set_page_idle(page);
+				put_page(page);
+			}
+		}
+	}
+
+	*ppos += (const char __user *)in - buf;
+	if (!ret)
+		ret = (const char __user *)in - buf;
+	return ret;
+}
+
+static const struct file_operations proc_kpageidle_operations = {
+	.llseek = mem_lseek,
+	.read = kpageidle_read,
+	.write = kpageidle_write,
+};
+
+#ifndef CONFIG_64BIT
+static bool need_page_idle(void)
+{
+	return true;
+}
+struct page_ext_operations page_idle_ops = {
+	.need = need_page_idle,
+};
+#endif
+#endif /* CONFIG_IDLE_PAGE_TRACKING */
+
 static int __init proc_page_init(void)
 {
 	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);

@@ -282,6 +500,10 @@ static int __init proc_page_init(void)
 #ifdef CONFIG_MEMCG
 	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
 #endif
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+	proc_create("kpageidle", S_IRUSR | S_IWUSR, NULL,
+		    &proc_kpageidle_operations);
+#endif
 	return 0;
 }
 fs_initcall(proc_page_init);

@@ -458,7 +458,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 
 	mss->resident += size;
 	/* Accumulate the size in pages that have been accessed. */
-	if (young || PageReferenced(page))
+	if (young || page_is_young(page) || PageReferenced(page))
 		mss->referenced += size;
 	mapcount = page_mapcount(page);
 	if (mapcount >= 2) {

@@ -810,6 +810,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 
 		/* Clear accessed and referenced bits. */
 		pmdp_test_and_clear_young(vma, addr, pmd);
+		test_and_clear_page_young(page);
 		ClearPageReferenced(page);
 out:
 		spin_unlock(ptl);

@@ -837,6 +838,7 @@ out:
 
 		/* Clear accessed and referenced bits. */
 		ptep_test_and_clear_young(vma, addr, pte);
+		test_and_clear_page_young(page);
 		ClearPageReferenced(page);
 	}
 	pte_unmap_unlock(pte - 1, ptl);

@@ -2205,5 +2205,103 @@ void __init setup_nr_node_ids(void);
 static inline void setup_nr_node_ids(void) {}
 #endif
 
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+#ifdef CONFIG_64BIT
+static inline bool page_is_young(struct page *page)
+{
+	return PageYoung(page);
+}
+
+static inline void set_page_young(struct page *page)
+{
+	SetPageYoung(page);
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return TestClearPageYoung(page);
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return PageIdle(page);
+}
+
+static inline void set_page_idle(struct page *page)
+{
+	SetPageIdle(page);
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+	ClearPageIdle(page);
+}
+#else /* !CONFIG_64BIT */
+/*
+ * If there is not enough space to store Idle and Young bits in page flags, use
+ * page ext flags instead.
+ */
+extern struct page_ext_operations page_idle_ops;
+
+static inline bool page_is_young(struct page *page)
+{
+	return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+}
+
+static inline void set_page_young(struct page *page)
+{
+	set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return test_and_clear_bit(PAGE_EXT_YOUNG,
+				  &lookup_page_ext(page)->flags);
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+
+static inline void set_page_idle(struct page *page)
+{
+	set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+	clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+#endif /* CONFIG_64BIT */
+#else /* !CONFIG_IDLE_PAGE_TRACKING */
+static inline bool page_is_young(struct page *page)
+{
+	return false;
+}
+
+static inline void set_page_young(struct page *page)
+{
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return false;
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return false;
+}
+
+static inline void set_page_idle(struct page *page)
+{
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+}
+#endif /* CONFIG_IDLE_PAGE_TRACKING */
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

@@ -109,6 +109,10 @@ enum pageflags {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	PG_compound_lock,
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+	PG_young,
+	PG_idle,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */

@@ -363,6 +367,13 @@ PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+TESTPAGEFLAG(Young, young, PF_ANY)
+SETPAGEFLAG(Young, young, PF_ANY)
+TESTCLEARFLAG(Young, young, PF_ANY)
+PAGEFLAG(Idle, idle, PF_ANY)
+#endif
+
 /*
  * On an anonymous page mapped into a user virtual memory area,
  * page->mapping points to its anon_vma, not to a struct address_space;

@@ -26,6 +26,10 @@ enum page_ext_flags {
 	PAGE_EXT_DEBUG_POISON,		/* Page is poisoned */
 	PAGE_EXT_DEBUG_GUARD,
 	PAGE_EXT_OWNER,
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+	PAGE_EXT_YOUNG,
+	PAGE_EXT_IDLE,
+#endif
 };
 
 /*

@@ -654,3 +654,15 @@ config DEFERRED_STRUCT_PAGE_INIT
 	  when kswapd starts. This has a potential performance impact on
 	  processes running early in the lifetime of the systemm until kswapd
 	  finishes the initialisation.
+
+config IDLE_PAGE_TRACKING
+	bool "Enable idle page tracking"
+	select PROC_PAGE_MONITOR
+	select PAGE_EXTENSION if !64BIT
+	help
+	  This feature allows to estimate the amount of user pages that have
+	  not been touched during a given period of time. This information can
+	  be useful to tune memory cgroup limits and/or for job placement
+	  within a compute cluster.
+
+	  See Documentation/vm/pagemap.txt for more details.

@@ -48,6 +48,10 @@ static const struct trace_print_flags pageflag_names[] = {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	{1UL << PG_compound_lock,	"compound_lock"	},
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+	{1UL << PG_young,		"young"		},
+	{1UL << PG_idle,		"idle"		},
+#endif
 };
 
 static void dump_flags(unsigned long flags,

@@ -1754,6 +1754,11 @@ static void __split_huge_page_refcount(struct page *page,
 		/* clear PageTail before overwriting first_page */
 		smp_wmb();
 
+		if (page_is_young(page))
+			set_page_young(page_tail);
+		if (page_is_idle(page))
+			set_page_idle(page_tail);
+
 		/*
 		 * __split_huge_page_splitting() already set the
 		 * splitting bit in all pmd that could map this

@@ -59,6 +59,9 @@ static struct page_ext_operations *page_ext_ops[] = {
 #ifdef CONFIG_PAGE_OWNER
 	&page_owner_ops,
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+	&page_idle_ops,
+#endif
 };
 
 static unsigned long total_usage;

@@ -798,6 +798,11 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pte_unmap_unlock(pte, ptl);
 	}
 
+	if (referenced)
+		clear_page_idle(page);
+	if (test_and_clear_page_young(page))
+		referenced++;
+
 	if (referenced) {
 		pra->referenced++;
 		pra->vm_flags |= vma->vm_flags;

@@ -623,6 +623,8 @@ void mark_page_accessed(struct page *page)
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
 	}
+	if (page_is_idle(page))
+		clear_page_idle(page);
 }
 EXPORT_SYMBOL(mark_page_accessed);
 

@@ -64,6 +64,7 @@ There are five components to pagemap:
     22. THP
     23. BALLOON
     24. ZERO_PAGE
+    25. IDLE
 
  * /proc/kpagecgroup.  This file contains a 64-bit inode number of the
    memory cgroup each page is charged to, indexed by PFN. Only available when

@@ -124,6 +125,11 @@ Short descriptions to the page flags:
 24. ZERO_PAGE
     zero page for pfn_zero or huge_zero page
 
+25. IDLE
+    page has not been accessed since it was marked idle (see /proc/kpageidle)
+    Note that this flag may be stale in case the page was accessed via a PTE.
+    To make sure the flag is up-to-date one has to read /proc/kpageidle first.
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data

@@ -149,6 +149,9 @@ u64 stable_page_flags(struct page *page)
 	if (PageBalloon(page))
 		u |= 1 << KPF_BALLOON;
 
+	if (page_is_idle(page))
+		u |= 1 << KPF_IDLE;
+
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);

@@ -33,6 +33,7 @@
 #define KPF_THP			22
 #define KPF_BALLOON		23
 #define KPF_ZERO_PAGE		24
+#define KPF_IDLE		25
 
 
 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */

@@ -45,12 +45,9 @@ static int hwpoison_inject(void *data, u64 val)
 	/*
 	 * do a racy check with elevated page count, to make sure PG_hwpoison
 	 * will only be set for the targeted owner (or on a free page).
-	 * We temporarily take page lock for try_get_mem_cgroup_from_page().
 	 * memory_failure() will redo the check reliably inside page lock.
 	 */
-	lock_page(hpage);
 	err = hwpoison_filter(hpage);
-	unlock_page(hpage);
 	if (err)
 		goto put_out;
 

@@ -126,7 +123,7 @@ static int pfn_inject_init(void)
 	if (!dentry)
 		goto fail;
 
-#ifdef CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
 	dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
 				    hwpoison_dir, &hwpoison_filter_memcg);
 	if (!dentry)

@@ -130,27 +130,15 @@ static int hwpoison_filter_flags(struct page *p)
  * can only guarantee that the page either belongs to the memcg tasks, or is
  * a freed page.
  */
-#ifdef	CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
 u64 hwpoison_filter_memcg;
 EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
 static int hwpoison_filter_task(struct page *p)
 {
-	struct mem_cgroup *mem;
-	struct cgroup_subsys_state *css;
-	unsigned long ino;
-
 	if (!hwpoison_filter_memcg)
 		return 0;
 
-	mem = try_get_mem_cgroup_from_page(p);
-	if (!mem)
-		return -EINVAL;
-
-	css = mem_cgroup_css(mem);
-	ino = cgroup_ino(css->cgroup);
-	css_put(css);
-
-	if (ino != hwpoison_filter_memcg)
+	if (page_cgroup_ino(p) != hwpoison_filter_memcg)
 		return -EINVAL;
 
 	return 0;