Re: [PATCH -mm v8 4/7] 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 <redacted>
---
 Documentation/vm/pagemap.txt |  6 ++++-
 fs/proc/page.c               | 53 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 6bfbc172cdb9..a9b7afc8fbc6 100644
--- 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

@@ -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

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 7eee2d8b97d9..70d23245dd43 100644
--- 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;
+