From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Subject: Re: [PATCH] fs/pnode.c: treat zero mnt_group_id-s as unequal
To: Al Viro <viro@ZenIV.linux.org.uk>
References: <20160216194527.9291.54622.stgit@maxim-thinkpad>
 <20160216195423.GC17997@ZenIV.linux.org.uk>
CC: <linux-fsdevel@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<devel@openvz.org>
From: Maxim Patlasov <mpatlasov@virtuozzo.com>
Message-ID: <56C41C34.900@virtuozzo.com>
Date: Tue, 16 Feb 2016 23:07:32 -0800
MIME-Version: 1.0
In-Reply-To: <20160216195423.GC17997@ZenIV.linux.org.uk>
Content-Type: multipart/mixed;
	boundary="------------040505080001020009000103"
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

--------------040505080001020009000103
Content-Type: text/plain; charset="windows-1252"; format=flowed
Content-Transfer-Encoding: 7bit

On 02/16/2016 11:54 AM, Al Viro wrote:
> On Tue, Feb 16, 2016 at 11:45:33AM -0800, Maxim Patlasov wrote:
>> propagate_one(m) calculates "type" argument for copy_tree() like this:
>>
>>>     if (m->mnt_group_id == last_dest->mnt_group_id) {
>>>         type = CL_MAKE_SHARED;
>>>     } else {
>>>         type = CL_SLAVE;
>>>         if (IS_MNT_SHARED(m))
>>>            type |= CL_MAKE_SHARED;
>>>    }
>> The "type" argument then governs clone_mnt() behavior with respect to flags
>> and mnt_master of new mount. When we iterate through a slave group, it is
>> possible that both current "m" and "last_dest" are not shared (although,
>> both are slaves, i.e. have non-NULL mnt_master-s). Then the comparison
>> above erroneously makes new mount shared and sets its mnt_master to
>> last_source->mnt_master. The patch fixes the problem by handling zero
>> mnt_group_id-s as though they are unequal.
>>
>> The similar problem exists in the implementation of "else" clause above
>> when we have to ascend upward in the master/slave tree by calling:
>>
>>>     last_source = last_source->mnt_master;
>>>     last_dest = last_source->mnt_parent;
>> proper number of times. The last step is governed by
>> "n->mnt_group_id != last_dest->mnt_group_id" condition that may lie if
>> both are zero. The patch fixes this case in the same way as the former one.
> Mind putting together a reproducer?

There are two files attached: reproducer1.c and reproducer2.c. The 
former demonstrates the problem before applying the patch. The latter 
demonstrates why the first hunk of the patch is not enough.

[root@f22ml ~]# reproducer1
main pid = 1496
monitor pid = 1497
child pid = 1498
grand-child pid = 1499

[root@f22ml ~]# grep "child" /proc/1496/mountinfo
243 144 0:37 /child /tmp/child rw shared:93 - tmpfs tmpfs rw,seclabel
[root@f22ml ~]# grep "child" /proc/1498/mountinfo
244 208 0:37 /child /tmp/child rw shared:127 master:93 - tmpfs tmpfs 
rw,seclabel
[root@f22ml ~]# grep "child" /proc/1499/mountinfo
245 240 0:37 /child /tmp/child rw master:127 - tmpfs tmpfs rw,seclabel
[root@f22ml ~]# grep "child" /proc/1497/mountinfo
246 176 0:37 /child /tmp/child rw shared:128 master:127 - tmpfs tmpfs 
rw,seclabel

while expected info for 1497 would be:
246 176 0:37 /child /tmp/child rw master:93 - tmpfs tmpfs rw,seclabel

Now, assuming that only the first hunk of the patch is applied:

 > -    if (m->mnt_group_id == last_dest->mnt_group_id) {
 > +    if (m->mnt_group_id && m->mnt_group_id == last_dest->mnt_group_id) {

[root@f22ml ~]# reproducer2
main pid = 1506
monitor pid = 1507
child pid = 1508
grand-child pid = 1509

[root@f22ml ~]# grep "child" /proc/1506/mountinfo
243 144 0:37 /child /tmp/child rw shared:93 - tmpfs tmpfs rw,seclabel
[root@f22ml ~]# grep "child" /proc/1508/mountinfo
244 208 0:37 /child /tmp/child rw shared:93 - tmpfs tmpfs rw,seclabel
[root@f22ml ~]# grep "child" /proc/1509/mountinfo
245 240 0:37 /child /tmp/child rw master:93 - tmpfs tmpfs rw,seclabel
[root@f22ml ~]# grep "child" /proc/1507/mountinfo
246 176 0:37 /child /tmp/child rw master:0 - tmpfs tmpfs rw,seclabel

while expected info for 1507 would be:
246 176 0:37 /child /tmp/child rw master:93 - tmpfs tmpfs rw,seclabel

Thanks,
Maxim

--------------040505080001020009000103
Content-Type: text/x-csrc; name="reproducer1.c"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="reproducer1.c"

#define _GNU_SOURCE
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <errno.h>
#include <sys/mount.h>
#include <sys/syscall.h>
#include <sched.h>

int main()
{
	const char *child  = "/tmp/child";
	int ret;

	printf("main pid = %d\n", getpid());	

	/* make our own private playground ... */
	ret = unshare(CLONE_NEWNS);
	if (ret) {
		perror("unshare");
		exit(1);
	}

	ret = mount("none", "/", NULL, MS_REC|MS_PRIVATE, NULL);
	if (ret) {
		perror("mount");
		exit(1);
	}

	ret = mount("none", "/", NULL, MS_REC|MS_SHARED, NULL);
	if (ret) {
		perror("mount2");
		exit(1);
	}

	/* fork monitor ... */
	ret = fork();
	if (ret < 0) {
		perror("fork");
		exit(1);
	} else if (!ret) {
		printf("monitor pid = %d\n", getpid());

		ret = unshare(CLONE_NEWNS);
		if (ret) {
			perror("unshare in monitor");
			exit(1);
		}

		ret = mount("none", "/", NULL, MS_REC|MS_SHARED, NULL);
		if (ret) {
			perror("mount in monitor");
			exit(1);
		}

		ret = mount("none", "/", NULL, MS_REC|MS_SLAVE, NULL);
		if (ret) {
			perror("mount2 in monitor");
			exit(1);
		}

		sleep(-1);
	}

	/* wait monitor to setup */
	sleep(1);


	/* fork child ... */	
	ret = fork();
	if (ret < 0) {
		perror("fork");
		exit(1);
	} else if (!ret) {
		printf("child pid = %d\n", getpid());

		ret = unshare(CLONE_NEWNS);
		if (ret) {
			perror("unshare in child");
			exit(1);
		}

		ret = mount("none", "/", NULL, MS_REC|MS_SLAVE, NULL);
		if (ret) {
			perror("mount in child");
			exit(1);
		}
		ret = mount(NULL, "/", NULL, MS_REC|MS_SHARED, NULL);
		if (ret) {
			perror("mount2 in child");
			exit(1);
		}

		if (!fork()) { /* grand-child */
			printf("grand-child pid = %d\n", getpid());
			ret = unshare(CLONE_NEWNS);
			if (ret) {
				perror("unshare in grand-child");
				exit(1);
			}

			ret = mount("none", "/", NULL, MS_REC|MS_SHARED, NULL);
			if (ret) {
				perror("mount in grand-child");
				exit(1);
			}

			ret = mount("none", "/", NULL, MS_REC|MS_SLAVE, NULL);
			if (ret) {
				perror("mount2 in grand-child");
				exit(1);
			}

			sleep(-1);
		}

		sleep(-1);
	}

	/* wait child and grand-child to setup */
	sleep(1);
	
	ret = mkdir(child, 0755);
	if (ret &&  errno != EEXIST) {
		perror("mkdir");
		exit(1);
	}

	/* let "child" mount slip to everyone' namespaces ... */
	ret = mount(child, child, NULL, MS_BIND, NULL);
	if (ret) {
		perror("bind mount");
		exit(1);
	}

	sleep(-1);
}


--------------040505080001020009000103
Content-Type: text/x-csrc; name="reproducer2.c"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="reproducer2.c"

#define _GNU_SOURCE
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <errno.h>
#include <sys/mount.h>
#include <sys/syscall.h>
#include <sched.h>

int main()
{
	const char *child  = "/tmp/child";
	int ret;

	printf("main pid = %d\n", getpid());	

	/* make our own private playground ... */
	ret = unshare(CLONE_NEWNS);
	if (ret) {
		perror("unshare");
		exit(1);
	}

	ret = mount("none", "/", NULL, MS_REC|MS_PRIVATE, NULL);
	if (ret) {
		perror("mount");
		exit(1);
	}

	ret = mount("none", "/", NULL, MS_REC|MS_SHARED, NULL);
	if (ret) {
		perror("mount2");
		exit(1);
	}

	/* fork monitor ... */
	ret = fork();
	if (ret < 0) {
		perror("fork");
		exit(1);
	} else if (!ret) {
		printf("monitor pid = %d\n", getpid());

		ret = unshare(CLONE_NEWNS);
		if (ret) {
			perror("unshare in monitor");
			exit(1);
		}

		ret = mount("none", "/", NULL, MS_REC|MS_SHARED, NULL);
		if (ret) {
			perror("mount in monitor");
			exit(1);
		}

		ret = mount("none", "/", NULL, MS_REC|MS_SLAVE, NULL);
		if (ret) {
			perror("mount2 in monitor");
			exit(1);
		}

		sleep(-1);
	}

	/* wait monitor to setup */
	sleep(1);


	/* fork child ... */	
	ret = fork();
	if (ret < 0) {
		perror("fork");
		exit(1);
	} else if (!ret) {
		printf("child pid = %d\n", getpid());

		ret = unshare(CLONE_NEWNS);
		if (ret) {
			perror("unshare in child");
			exit(1);
		}

		if (!fork()) { /* grand-child */
			printf("grand-child pid = %d\n", getpid());
			ret = unshare(CLONE_NEWNS);
			if (ret) {
				perror("unshare in grand-child");
				exit(1);
			}

			ret = mount("none", "/", NULL, MS_REC|MS_SHARED, NULL);
			if (ret) {
				perror("mount in grand-child");
				exit(1);
			}

			ret = mount("none", "/", NULL, MS_REC|MS_SLAVE, NULL);
			if (ret) {
				perror("mount2 in grand-child");
				exit(1);
			}

			sleep(-1);
		}

		sleep(-1);
	}

	/* wait child and grand-child to setup */
	sleep(1);
	
	ret = mkdir(child, 0755);
	if (ret &&  errno != EEXIST) {
		perror("mkdir");
		exit(1);
	}

	/* let "child" mount slip to everyone' namespaces ... */
	ret = mount(child, child, NULL, MS_BIND, NULL);
	if (ret) {
		perror("bind mount");
		exit(1);
	}

	sleep(-1);
}


--------------040505080001020009000103--