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 <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>

diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 3cd38438242aef330a6b2e67e82dfe52ee63f7b2..ce294b0aace49297a188b1419c412b5669312a96 100644 (file)
--- a/Documentation/vm/pagemap.txt
+++ b/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

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 7eee2d8b97d9786b7c05ca1078d477c4db6af5e1..70d23245dd43942d6c3e7691f5f07ba8aa7deaaf 100644 (file)
--- a/fs/proc/page.c
+++ b/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);