From e3fec5f8eb291df4e78374ed5f8dfebc25bd3066 Mon Sep 17 00:00:00 2001
From: Saied Kazemi <saied@google.com>
Date: Mon, 9 Feb 2015 14:07:40 +0300
Subject: [PATCH] Ignore mnt_id value for AUFS file descriptors.

Starting with version 3.15, the kernel provides a mnt_id field in
/proc/<pid>/fdinfo/<fd>.  However, the value provided by the kernel for
AUFS file descriptors obtained by opening a file in /proc/<pid>/map_files
is incorrect.

Below is an example for a Docker container running Nginx.  The mntid
program below mimics CRIU by opening a file in /proc/1/map_files and
using the descriptor to obtain its mnt_id.  As shown below, mnt_id is
set to 22 by the kernel but it does not exist in the mount namespace of
the container.  Therefore, CRIU fails with the error:

	"Unable to look up the 22 mount"

In the global namespace, 22 is the root of AUFS (/var/lib/docker/aufs).

This patch sets the mnt_id of these AUFS descriptors to -1, mimicing
pre-3.15 kernel behavior.

	$ docker ps
	CONTAINER ID        IMAGE                    ...
	3850a63ee857        nginx-streaming:latest   ...
	$ docker exec -it 38 bash -i
	root@3850a63ee857:/# ps -e
	  PID TTY          TIME CMD
	    1 ?        00:00:00 nginx
	    7 ?        00:00:00 nginx
	   31 ?        00:00:00 bash
	   46 ?        00:00:00 ps
	root@3850a63ee857:/# ./mntid 1
	open("/proc/1/map_files/400000-4b8000") = 3
	cat /proc/49/fdinfo/3
	pos:	0
	flags:	0100000
	mnt_id:	22
	root@3850a63ee857:/# awk '{print $1 " " $2}' /proc/1/mountinfo
	87 58
	103 87
	104 87
	105 104
	106 104
	107 104
	108 87
	109 87
	110 87
	111 87
	root@3850a63ee857:/# exit
	$ grep 22 /proc/self/mountinfo
	22 21 8:1 /var/lib/docker/aufs /var/lib/docker/aufs ...
	44 22 0:35 / /var/lib/docker/aufs/mnt/<ID> ...
	$

Signed-off-by: Saied Kazemi <saied@google.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
 proc_parse.c  | 10 +++++++++-
 sysfs_parse.c |  5 ++++-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/proc_parse.c b/proc_parse.c
index 297914246..c8034c1cd 100644
--- a/proc_parse.c
+++ b/proc_parse.c
@@ -543,7 +543,15 @@ int parse_smaps(pid_t pid, struct vm_area_list *vma_area_list)
 					vma_area->e->status |= VMA_FILE_SHARED;
 			}
 
-			if (get_fd_mntid(vma_area->vm_file_fd, &vma_area->mnt_id))
+			/*
+			 * We cannot use the mnt_id value provided by the kernel
+			 * for vm_file_fd if it is an AUFS file (the value is
+			 * wrong).  In such a case, fixup_aufs_vma_fd() has set
+			 * mnt_id to -1 to mimic pre-3.15 kernels that didn't
+			 * have mnt_id.
+			 */
+			if (vma_area->mnt_id != -1 &&
+			    get_fd_mntid(vma_area->vm_file_fd, &vma_area->mnt_id))
 				return -1;
 		} else {
 			/*
diff --git a/sysfs_parse.c b/sysfs_parse.c
index c5881d05d..93b527d8d 100644
--- a/sysfs_parse.c
+++ b/sysfs_parse.c
@@ -262,7 +262,8 @@ err:
 
 /*
  * AUFS support to compensate for the kernel bug
- * exposing branch pathnames in map_files.
+ * exposing branch pathnames in map_files and providing
+ * a wrong mnt_id value in /proc/<pid>/fdinfo/<fd>.
  *
  * If the link points inside a branch, save the
  * relative pathname from the root of the mount
@@ -304,6 +305,8 @@ int fixup_aufs_vma_fd(struct vma_area *vma)
 		return -1;
 	}
 
+	/* tell parse_smap() not to call get_fd_mntid() */
+	vma->mnt_id = -1;
 	return len;
 }