mm: introduce idle page tracking

Knowing the portion of memory that is not used by a certain application or
memory cgroup (idle memory) can be useful for partitioning the system
efficiently, e.g.  by setting memory cgroup limits appropriately.
Currently, the only means to estimate the amount of idle memory provided
by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the
access bit for all pages mapped to a particular process by writing 1 to
clear_refs, wait for some time, and then count smaps:Referenced.  However,
this method has two serious shortcomings:

 - it does not count unmapped file pages
 - it affects the reclaimer logic

To overcome these drawbacks, this patch introduces two new page flags,
Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap.
A page's Idle flag can only be set from userspace by setting bit in
/sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page,
and it is cleared whenever the page is accessed either through page tables
(it is cleared in page_referenced() in this case) or using the read(2)
system call (mark_page_accessed()). Thus by setting the Idle flag for
pages of a particular workload, which can be found e.g.  by reading
/proc/PID/pagemap, waiting for some time to let the workload access its
working set, and then reading the bitmap file, one can estimate the amount
of pages that are not used by the workload.

The Young page flag is used to avoid interference with the memory
reclaimer.  A page's Young flag is set whenever the Access bit of a page
table entry pointing to the page is cleared by writing to the bitmap file.
If page_referenced() is called on a Young page, it will add 1 to its
return value, therefore concealing the fact that the Access bit was
cleared.

Note, since there is no room for extra page flags on 32 bit, this feature
uses extended page flags when compiled on 32 bit.

[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: kpageidle requires an MMU]
[akpm@linux-foundation.org: decouple from page-flags rework]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

9 files changed, 278 insertions, 2 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 3a4070f5ab79..6413d027c0b2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -649,6 +649,18 @@ config DEFERRED_STRUCT_PAGE_INIT
 	  processes running early in the lifetime of the systemm until kswapd
 	  finishes the initialisation.
 
+config IDLE_PAGE_TRACKING
+	bool "Enable idle page tracking"
+	depends on SYSFS && MMU
+	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/idle_page_tracking.txt for more details.
+
 config ZONE_DEVICE
 	bool "Device memory (pmem, etc...) hotplug support" if EXPERT
 	default !ZONE_DMA
diff --git a/mm/Makefile b/mm/Makefile
index b424d5e5b6ff..56f8eed73f1a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -79,3 +79,4 @@ obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
 obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
 obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
 obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
+obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
diff --git a/mm/debug.c b/mm/debug.c
index 76089ddf99ea..6c1b3ea61bfd 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -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,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b16279cbd91d..4b06b8db9df2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -25,6 +25,7 @@
 #include <linux/migrate.h>
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/page_idle.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -1757,6 +1758,11 @@ 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
@@ -2262,7 +2268,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 
 		/* If there is no mapped pte young don't collapse the page */
-		if (pte_young(pteval) || PageReferenced(page) ||
+		if (pte_young(pteval) ||
+		    page_is_young(page) || PageReferenced(page) ||
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = true;
 	}
@@ -2693,7 +2700,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 */
 		if (page_count(page) != 1 + !!PageSwapCache(page))
 			goto out_unmap;
-		if (pte_young(pteval) || PageReferenced(page) ||
+		if (pte_young(pteval) ||
+		    page_is_young(page) || PageReferenced(page) ||
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = true;
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index 02ce25df16c2..c3cb566af3e2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -37,6 +37,7 @@
 #include <linux/gfp.h>
 #include <linux/balloon_compaction.h>
 #include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
 
 #include <asm/tlbflush.h>
 
@@ -524,6 +525,11 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 			__set_page_dirty_nobuffers(newpage);
  	}
 
+	if (page_is_young(page))
+		set_page_young(newpage);
+	if (page_is_idle(page))
+		set_page_idle(newpage);
+
 	/*
 	 * Copy NUMA information to the new page, to prevent over-eager
 	 * future migrations of this same page.
diff --git a/mm/page_ext.c b/mm/page_ext.c
index d86fd2f5353f..292ca7b8debd 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -6,6 +6,7 @@
 #include <linux/vmalloc.h>
 #include <linux/kmemleak.h>
 #include <linux/page_owner.h>
+#include <linux/page_idle.h>
 
 /*
  * struct page extension
@@ -59,6 +60,9 @@ 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;
diff --git a/mm/page_idle.c b/mm/page_idle.c
new file mode 100644
index 000000000000..d5dd79041484
--- /dev/null
+++ b/mm/page_idle.c
@@ -0,0 +1,232 @@
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_ext.h>
+#include <linux/page_idle.h>
+
+#define BITMAP_CHUNK_SIZE	sizeof(u64)
+#define BITMAP_CHUNK_BITS	(BITMAP_CHUNK_SIZE * BITS_PER_BYTE)
+
+/*
+ * 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 *page_idle_get_page(unsigned long pfn)
+{
+	struct page *page;
+	struct zone *zone;
+
+	if (!pfn_valid(pfn))
+		return NULL;
+
+	page = pfn_to_page(pfn);
+	if (!page || !PageLRU(page) ||
+	    !get_page_unless_zero(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 page_idle_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_clear_young_notify(vma, addr, pmd);
+			spin_unlock(ptl);
+		}
+	} else {
+		pte = page_check_address(page, mm, addr, &ptl, 0);
+		if (pte) {
+			referenced = ptep_clear_young_notify(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 page_idle_clear_pte_refs(struct page *page)
+{
+	/*
+	 * Since rwc.arg is unused, rwc is effectively immutable, so we
+	 * can make it static const to save some cycles and stack.
+	 */
+	static const struct rmap_walk_control rwc = {
+		.rmap_one = page_idle_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, (struct rmap_walk_control *)&rwc);
+
+	if (need_lock)
+		unlock_page(page);
+}
+
+static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
+				     struct bin_attribute *attr, char *buf,
+				     loff_t pos, size_t count)
+{
+	u64 *out = (u64 *)buf;
+	struct page *page;
+	unsigned long pfn, end_pfn;
+	int bit;
+
+	if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
+		return -EINVAL;
+
+	pfn = pos * 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, BITMAP_CHUNK_BITS);
+
+	for (; pfn < end_pfn; pfn++) {
+		bit = pfn % BITMAP_CHUNK_BITS;
+		if (!bit)
+			*out = 0ULL;
+		page = page_idle_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.
+				 */
+				page_idle_clear_pte_refs(page);
+				if (page_is_idle(page))
+					*out |= 1ULL << bit;
+			}
+			put_page(page);
+		}
+		if (bit == BITMAP_CHUNK_BITS - 1)
+			out++;
+		cond_resched();
+	}
+	return (char *)out - buf;
+}
+
+static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
+				      struct bin_attribute *attr, char *buf,
+				      loff_t pos, size_t count)
+{
+	const u64 *in = (u64 *)buf;
+	struct page *page;
+	unsigned long pfn, end_pfn;
+	int bit;
+
+	if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
+		return -EINVAL;
+
+	pfn = pos * 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, BITMAP_CHUNK_BITS);
+
+	for (; pfn < end_pfn; pfn++) {
+		bit = pfn % BITMAP_CHUNK_BITS;
+		if ((*in >> bit) & 1) {
+			page = page_idle_get_page(pfn);
+			if (page) {
+				page_idle_clear_pte_refs(page);
+				set_page_idle(page);
+				put_page(page);
+			}
+		}
+		if (bit == BITMAP_CHUNK_BITS - 1)
+			in++;
+		cond_resched();
+	}
+	return (char *)in - buf;
+}
+
+static struct bin_attribute page_idle_bitmap_attr =
+		__BIN_ATTR(bitmap, S_IRUSR | S_IWUSR,
+			   page_idle_bitmap_read, page_idle_bitmap_write, 0);
+
+static struct bin_attribute *page_idle_bin_attrs[] = {
+	&page_idle_bitmap_attr,
+	NULL,
+};
+
+static struct attribute_group page_idle_attr_group = {
+	.bin_attrs = page_idle_bin_attrs,
+	.name = "page_idle",
+};
+
+#ifndef CONFIG_64BIT
+static bool need_page_idle(void)
+{
+	return true;
+}
+struct page_ext_operations page_idle_ops = {
+	.need = need_page_idle,
+};
+#endif
+
+static int __init page_idle_init(void)
+{
+	int err;
+
+	err = sysfs_create_group(mm_kobj, &page_idle_attr_group);
+	if (err) {
+		pr_err("page_idle: register sysfs failed\n");
+		return err;
+	}
+	return 0;
+}
+subsys_initcall(page_idle_init);
diff --git a/mm/rmap.c b/mm/rmap.c
index 0db38e7d0a72..f5b5c1f3dcd7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -59,6 +59,7 @@
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
 #include <linux/backing-dev.h>
+#include <linux/page_idle.h>
 
 #include <asm/tlbflush.h>
 
@@ -886,6 +887,11 @@ 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;
diff --git a/mm/swap.c b/mm/swap.c
index a3a0a2f1f7c3..983f692a47fd 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/uio.h>
 #include <linux/hugetlb.h>
+#include <linux/page_idle.h>
 
 #include "internal.h"
 
@@ -622,6 +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);