[Devel] [PATCH RHEL7 COMMIT] ms/memcg/proc: add kpagecgroup file

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-123.1.2-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-123.1.2.vz7.5.1
------>
commit 3e48c113a59f801934292fc89e6915b1d8a341a7
Author: Vladimir Davydov <vdavydov at parallels.com>
Date:   Tue May 19 08:23:48 2015 +0400

    ms/memcg/proc: add kpagecgroup file
    
    Patchset description: idle memory tracking
    
    This patch set backports
    
      https://lkml.org/lkml/2015/5/12/449
    
    which is required by vcmmd.
    
    It is not yet clear if the original patch set will be accepted upstream
    as is, there still may be changes. However, I hope the user API will be
    preserved. If it is not, we will have to fix this in our kernel too.
    
    https://jira.sw.ru/browse/PSBM-32460
    
    Vladimir Davydov (3):
      memcg: add page_cgroup_ino helper
      proc: add kpagecgroup file
      proc: add kpageidle file
    
    ===================================================
    This patch description:
    
    /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 at parallels.com>
---
 Documentation/vm/pagemap.txt |  6 ++++-
 fs/proc/Kconfig              |  5 +++--
 fs/proc/page.c               | 53 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 61 insertions(+), 3 deletions(-)

diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index fd7c3cf..e37cff9 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
@@ -63,6 +63,10 @@ There are three components to pagemap:
     21. KSM
     22. THP
 
+ * /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/Kconfig b/fs/proc/Kconfig
index 15af622..e8ed22d 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -65,5 +65,6 @@ config PROC_PAGE_MONITOR
  	help
 	  Various /proc files exist to monitor process memory utilization:
 	  /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
-	  /proc/kpagecount, and /proc/kpageflags. Disabling these
-          interfaces will reduce the size of the kernel by approximately 4kb.
+	  /proc/kpagecount, /proc/kpageflags, and /proc/kpagecgroup.
+	  Disabling these interfaces will reduce the size of the kernel
+	  by approximately 4kb.
diff --git a/fs/proc/page.c b/fs/proc/page.c
index cab84b6..c9cbed3 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -8,6 +8,7 @@
 #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"
@@ -213,10 +214,62 @@ 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;
 }
 module_init(proc_page_init);