[RFC v2 3/3] proc: add kpageidle file

@@ -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 +69,21 @@ 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.  For each page this file contains a 64-bit number, which
+   equals 1 if the page is idle or 0 otherwise. The file is indexed by PFN. To
+   set or clear a page's Idle flag, one can write 1 or 0 respectively to this
+   file at the offset corresponding to the page. It is only possible to modify
+   the Idle flag for user pages (pages that are on an LRU list, to be more
+   exact). For other page types, the input is silently ignored. Writing to this
+   file beyond max PFN results in the ENXIO error.
+
+   A page's Idle flag is automatically cleared whenever the page is accessed
+   (via a page table entry or using the read(2) system call). This makes this
+   file useful for tracking a workload's working set, i.e. the set of pages
+   that are actively used by the workload.
+
+   The file is only available when CONFIG_IDLE_PAGE_TRACKING is set.
+
 Short descriptions to the page flags:
 
  0. LOCKED

@@ -275,6 +275,151 @@ static const struct file_operations proc_kpagecgroup_operations = {
 };
 #endif /* CONFIG_MEMCG */
 
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+static struct page *kpageidle_get_page(struct page *page)
+{
+	if (!page || page_count(page) == 0 || !PageLRU(page))
+		return NULL;
+	if (!get_page_unless_zero(page))
+		return NULL;
+	if (unlikely(!PageLRU(page))) {
+		put_page(page);
+		return NULL;
+	}
+	return page;
+}
+
+static void kpageidle_clear_refs(struct page *page)
+{
+	unsigned long dummy;
+
+	if (page_referenced(page, 0, NULL, &dummy, NULL))
+		SetPageYoung(page);
+}
+
+static u64 kpageidle_read_page_state(struct page *page)
+{
+	u64 state = 0;
+
+	page = kpageidle_get_page(page);
+	if (!page)
+		return 0;
+	if (PageIdle(page)) {
+		kpageidle_clear_refs(page);
+		if (PageIdle(page))
+			state = 1;
+	}
+	put_page(page);
+	return state;
+}
+
+static int kpageidle_write_page_state(struct page *page, u64 state)
+{
+	if (state != 0 && state != 1)
+		return -EINVAL;
+	page = kpageidle_get_page(page);
+	if (!page)
+		return 0;
+	if (state && !PageIdle(page)) {
+		kpageidle_clear_refs(page);
+		SetPageIdle(page);
+	} else if (!state && PageIdle(page))
+		ClearPageIdle(page);
+	put_page(page);
+	return 0;
+}
+
+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 *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 val;
+
+	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;
+
+		val = kpageidle_read_page_state(ppage);
+
+		if (put_user(val, out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+	}
+
+	*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 = (u64 __user *)buf;
+	struct page *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 val;
+
+	pfn = src / KPMSIZE;
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+
+	while (count > 0) {
+		if (pfn >= max_pfn) {
+			if ((char __user *)in == buf)
+				ret = -ENXIO;
+			break;
+		}
+		if (pfn_valid(pfn))
+			ppage = pfn_to_page(pfn);
+		else
+			ppage = NULL;
+
+		if (get_user(val, in)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		ret = kpageidle_write_page_state(ppage, val);
+		if (ret)
+			break;
+
+		pfn++;
+		in++;
+		count -= KPMSIZE;
+	}
+
+	*ppos += (char __user *)in - buf;
+	if (!ret)
+		ret = (char __user *)in - buf;
+	return ret;
+}
+
+static const struct file_operations proc_kpageidle_operations = {
+	.llseek = mem_lseek,
+	.read = kpageidle_read,
+	.write = kpageidle_write,
+};
+#endif /* CONFIG_IDLE_PAGE_TRACKING */
+
 static int __init proc_page_init(void)
 {
 	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);

@@ -282,6 +427,10 @@ 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 || PageYoung(page) || PageReferenced(page))
 		mss->referenced += size;
 	mapcount = page_mapcount(page);
 	if (mapcount >= 2) {

@@ -808,6 +808,7 @@ 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);
+		ClearPageYoung(page);
 		ClearPageReferenced(page);
 out:
 		spin_unlock(ptl);

@@ -835,6 +836,7 @@ out:
 
 		/* Clear accessed and referenced bits. */
 		ptep_test_and_clear_young(vma, addr, pte);
+		ClearPageYoung(page);
 		ClearPageReferenced(page);
 	}
 	pte_unmap_unlock(pte - 1, ptl);

@@ -109,6 +109,10 @@ enum pageflags {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	PG_compound_lock,
 #endif
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+	PG_young,
+	PG_idle,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */

@@ -363,6 +367,14 @@ PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+PAGEFLAG(Young, young, PF_HEAD)
+PAGEFLAG(Idle, idle, PF_HEAD)
+#else
+PAGEFLAG_FALSE(Young)
+PAGEFLAG_FALSE(Idle)
+#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;

@@ -635,3 +635,15 @@ config MAX_STACK_SIZE_MB
 	  changed to a smaller value in which case that is used.
 
 	  A sane initial value is 80 MB.
+
+config IDLE_PAGE_TRACKING
+	bool "Enable idle page tracking"
+	depends on 64BIT
+	select PROC_PAGE_MONITOR
+	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
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+	{1UL << PG_young,		"young"		},
+	{1UL << PG_idle,		"idle"		},
+#endif
 };
 
 static void dump_flags(unsigned long flags,

@@ -799,6 +799,13 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 	if (referenced) {
 		pra->referenced++;
 		pra->vm_flags |= vma->vm_flags;
+		if (PageIdle(page))
+			ClearPageIdle(page);
+	}
+
+	if (PageYoung(page)) {
+		ClearPageYoung(page);
+		pra->referenced++;
 	}
 
 	if (dirty)

@@ -624,6 +624,8 @@ void mark_page_accessed(struct page *page)
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
 	}
+	if (PageIdle(page))
+		ClearPageIdle(page);
 }
 EXPORT_SYMBOL(mark_page_accessed);