proc: add kpagecgroup file

/proc/kpagecgroup contains a 64-bit inode number of the memory cgroup each
page is charged to, indexed by PFN.  Having this information is useful for
estimating a cgroup working set size.

The file is present if CONFIG_PROC_PAGE_MONITOR && CONFIG_MEMCG.

Signed-off-by: Vladimir Davydov <[email protected]>
Reviewed-by: Andres Lagar-Cavilla <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Raghavendra K T <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Greg Thelen <[email protected]>
Cc: Michel Lespinasse <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Pavel Emelyanov <[email protected]>
Cc: Cyrill Gorcunov <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Vladimir Davydov

Documentation/vm/pagemap.txt

@@ -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
@@ -71,6 +71,10 @@ 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

fs/proc/page.c

@@ -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);