2019-05-28 20:10:12 +03:00
/* SPDX-License-Identifier: GPL-2.0-only */
2005-11-08 01:19:07 +03:00
/*
* linux / fs / pnode . h
*
* ( C ) Copyright IBM Corporation 2005.
*/
# ifndef _LINUX_PNODE_H
# define _LINUX_PNODE_H
# include <linux/list.h>
2011-11-24 04:26:23 +04:00
# include "mount.h"
2005-11-08 01:19:33 +03:00
2011-11-25 10:05:37 +04:00
# define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
# define IS_MNT_SLAVE(m) ((m)->mnt_master)
mount: fix mounting of detached mounts onto targets that reside on shared mounts
Creating a series of detached mounts, attaching them to the filesystem,
and unmounting them can be used to trigger an integer overflow in
ns->mounts causing the kernel to block any new mounts in count_mounts()
and returning ENOSPC because it falsely assumes that the maximum number
of mounts in the mount namespace has been reached, i.e. it thinks it
can't fit the new mounts into the mount namespace anymore.
Depending on the number of mounts in your system, this can be reproduced
on any kernel that supportes open_tree() and move_mount() by compiling
and running the following program:
/* SPDX-License-Identifier: LGPL-2.1+ */
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <getopt.h>
#include <limits.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mount.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <unistd.h>
/* open_tree() */
#ifndef OPEN_TREE_CLONE
#define OPEN_TREE_CLONE 1
#endif
#ifndef OPEN_TREE_CLOEXEC
#define OPEN_TREE_CLOEXEC O_CLOEXEC
#endif
#ifndef __NR_open_tree
#if defined __alpha__
#define __NR_open_tree 538
#elif defined _MIPS_SIM
#if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
#define __NR_open_tree 4428
#endif
#if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
#define __NR_open_tree 6428
#endif
#if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
#define __NR_open_tree 5428
#endif
#elif defined __ia64__
#define __NR_open_tree (428 + 1024)
#else
#define __NR_open_tree 428
#endif
#endif
/* move_mount() */
#ifndef MOVE_MOUNT_F_EMPTY_PATH
#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
#endif
#ifndef __NR_move_mount
#if defined __alpha__
#define __NR_move_mount 539
#elif defined _MIPS_SIM
#if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
#define __NR_move_mount 4429
#endif
#if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
#define __NR_move_mount 6429
#endif
#if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
#define __NR_move_mount 5429
#endif
#elif defined __ia64__
#define __NR_move_mount (428 + 1024)
#else
#define __NR_move_mount 429
#endif
#endif
static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
{
return syscall(__NR_open_tree, dfd, filename, flags);
}
static inline int sys_move_mount(int from_dfd, const char *from_pathname, int to_dfd,
const char *to_pathname, unsigned int flags)
{
return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags);
}
static bool is_shared_mountpoint(const char *path)
{
bool shared = false;
FILE *f = NULL;
char *line = NULL;
int i;
size_t len = 0;
f = fopen("/proc/self/mountinfo", "re");
if (!f)
return 0;
while (getline(&line, &len, f) > 0) {
char *slider1, *slider2;
for (slider1 = line, i = 0; slider1 && i < 4; i++)
slider1 = strchr(slider1 + 1, ' ');
if (!slider1)
continue;
slider2 = strchr(slider1 + 1, ' ');
if (!slider2)
continue;
*slider2 = '\0';
if (strcmp(slider1 + 1, path) == 0) {
/* This is the path. Is it shared? */
slider1 = strchr(slider2 + 1, ' ');
if (slider1 && strstr(slider1, "shared:")) {
shared = true;
break;
}
}
}
fclose(f);
free(line);
return shared;
}
static void usage(void)
{
const char *text = "mount-new [--recursive] <base-dir>\n";
fprintf(stderr, "%s", text);
_exit(EXIT_SUCCESS);
}
#define exit_usage(format, ...) \
({ \
fprintf(stderr, format "\n", ##__VA_ARGS__); \
usage(); \
})
#define exit_log(format, ...) \
({ \
fprintf(stderr, format "\n", ##__VA_ARGS__); \
exit(EXIT_FAILURE); \
})
static const struct option longopts[] = {
{"help", no_argument, 0, 'a'},
{ NULL, no_argument, 0, 0 },
};
int main(int argc, char *argv[])
{
int exit_code = EXIT_SUCCESS, index = 0;
int dfd, fd_tree, new_argc, ret;
char *base_dir;
char *const *new_argv;
char target[PATH_MAX];
while ((ret = getopt_long_only(argc, argv, "", longopts, &index)) != -1) {
switch (ret) {
case 'a':
/* fallthrough */
default:
usage();
}
}
new_argv = &argv[optind];
new_argc = argc - optind;
if (new_argc < 1)
exit_usage("Missing base directory\n");
base_dir = new_argv[0];
if (*base_dir != '/')
exit_log("Please specify an absolute path");
/* Ensure that target is a shared mountpoint. */
if (!is_shared_mountpoint(base_dir))
exit_log("Please ensure that \"%s\" is a shared mountpoint", base_dir);
dfd = open(base_dir, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
if (dfd < 0)
exit_log("%m - Failed to open base directory \"%s\"", base_dir);
ret = mkdirat(dfd, "detached-move-mount", 0755);
if (ret < 0)
exit_log("%m - Failed to create required temporary directories");
ret = snprintf(target, sizeof(target), "%s/detached-move-mount", base_dir);
if (ret < 0 || (size_t)ret >= sizeof(target))
exit_log("%m - Failed to assemble target path");
/*
* Having a mount table with 10000 mounts is already quite excessive
* and shoult account even for weird test systems.
*/
for (size_t i = 0; i < 10000; i++) {
fd_tree = sys_open_tree(dfd, "detached-move-mount",
OPEN_TREE_CLONE |
OPEN_TREE_CLOEXEC |
AT_EMPTY_PATH);
if (fd_tree < 0) {
fprintf(stderr, "%m - Failed to open %d(detached-move-mount)", dfd);
exit_code = EXIT_FAILURE;
break;
}
ret = sys_move_mount(fd_tree, "", dfd, "detached-move-mount", MOVE_MOUNT_F_EMPTY_PATH);
if (ret < 0) {
if (errno == ENOSPC)
fprintf(stderr, "%m - Buggy mount counting");
else
fprintf(stderr, "%m - Failed to attach mount to %d(detached-move-mount)", dfd);
exit_code = EXIT_FAILURE;
break;
}
close(fd_tree);
ret = umount2(target, MNT_DETACH);
if (ret < 0) {
fprintf(stderr, "%m - Failed to unmount %s", target);
exit_code = EXIT_FAILURE;
break;
}
}
(void)unlinkat(dfd, "detached-move-mount", AT_REMOVEDIR);
close(dfd);
exit(exit_code);
}
and wait for the kernel to refuse any new mounts by returning ENOSPC.
How many iterations are needed depends on the number of mounts in your
system. Assuming you have something like 50 mounts on a standard system
it should be almost instantaneous.
The root cause of this is that detached mounts aren't handled correctly
when source and target mount are identical and reside on a shared mount
causing a broken mount tree where the detached source itself is
propagated which propagation prevents for regular bind-mounts and new
mounts. This ultimately leads to a miscalculation of the number of
mounts in the mount namespace.
Detached mounts created via
open_tree(fd, path, OPEN_TREE_CLONE)
are essentially like an unattached new mount, or an unattached
bind-mount. They can then later on be attached to the filesystem via
move_mount() which calls into attach_recursive_mount(). Part of
attaching it to the filesystem is making sure that mounts get correctly
propagated in case the destination mountpoint is MS_SHARED, i.e. is a
shared mountpoint. This is done by calling into propagate_mnt() which
walks the list of peers calling propagate_one() on each mount in this
list making sure it receives the propagation event.
The propagate_one() functions thereby skips both new mounts and bind
mounts to not propagate them "into themselves". Both are identified by
checking whether the mount is already attached to any mount namespace in
mnt->mnt_ns. The is what the IS_MNT_NEW() helper is responsible for.
However, detached mounts have an anonymous mount namespace attached to
them stashed in mnt->mnt_ns which means that IS_MNT_NEW() doesn't
realize they need to be skipped causing the mount to propagate "into
itself" breaking the mount table and causing a disconnect between the
number of mounts recorded as being beneath or reachable from the target
mountpoint and the number of mounts actually recorded/counted in
ns->mounts ultimately causing an overflow which in turn prevents any new
mounts via the ENOSPC issue.
So teach propagation to handle detached mounts by making it aware of
them. I've been tracking this issue down for the last couple of days and
then verifying that the fix is correct by
unmounting everything in my current mount table leaving only /proc and
/sys mounted and running the reproducer above overnight verifying the
number of mounts counted in ns->mounts. With this fix the counts are
correct and the ENOSPC issue can't be reproduced.
This change will only have an effect on mounts created with the new
mount API since detached mounts cannot be created with the old mount API
so regressions are extremely unlikely.
Link: https://lore.kernel.org/r/20210306101010.243666-1-christian.brauner@ubuntu.com
Fixes: 2db154b3ea8e ("vfs: syscall: Add move_mount(2) to move mounts around")
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: <stable@vger.kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-03-06 13:10:10 +03:00
# define IS_MNT_NEW(m) (!(m)->mnt_ns || is_anon_ns((m)->mnt_ns))
2011-11-25 10:05:37 +04:00
# define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
# define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
smarter propagate_mnt()
The current mainline has copies propagated to *all* nodes, then
tears down the copies we made for nodes that do not contain
counterparts of the desired mountpoint. That sets the right
propagation graph for the copies (at teardown time we move
the slaves of removed node to a surviving peer or directly
to master), but we end up paying a fairly steep price in
useless allocations. It's fairly easy to create a situation
where N calls of mount(2) create exactly N bindings, with
O(N^2) vfsmounts allocated and freed in process.
Fortunately, it is possible to avoid those allocations/freeings.
The trick is to create copies in the right order and find which
one would've eventually become a master with the current algorithm.
It turns out to be possible in O(nodes getting propagation) time
and with no extra allocations at all.
One part is that we need to make sure that eventual master will be
created before its slaves, so we need to walk the propagation
tree in a different order - by peer groups. And iterate through
the peers before dealing with the next group.
Another thing is finding the (earlier) copy that will be a master
of one we are about to create; to do that we are (temporary) marking
the masters of mountpoints we are attaching the copies to.
Either we are in a peer of the last mountpoint we'd dealt with,
or we have the following situation: we are attaching to mountpoint M,
the last copy S_0 had been attached to M_0 and there are sequences
S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i},
S_{i} mounted on M{i} and we need to create a slave of the first S_{k}
such that M is getting propagation from M_{k}. It means that the master
of M_{k} will be among the sequence of masters of M. On the
other hand, the nearest marked node in that sequence will either
be the master of M_{k} or the master of M_{k-1} (the latter -
in the case if M_{k-1} is a slave of something M gets propagation
from, but in a wrong peer group).
So we go through the sequence of masters of M until we find
a marked one (P). Let N be the one before it. Then we go through
the sequence of masters of S_0 until we find one (say, S) mounted
on a node D that has P as master and check if D is a peer of N.
If it is, S will be the master of new copy, if not - the master of S
will be.
That's it for the hard part; the rest is fairly simple. Iterator
is in next_group(), handling of one prospective mountpoint is
propagate_one().
It seems to survive all tests and gives a noticably better performance
than the current mainline for setups that are seriously using shared
subtrees.
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-02-27 18:35:45 +04:00
# define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
# define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
# define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
2015-01-05 22:38:04 +03:00
# define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
2005-11-08 01:19:33 +03:00
2005-11-08 01:19:50 +03:00
# define CL_EXPIRE 0x01
2005-11-08 01:20:48 +03:00
# define CL_SLAVE 0x02
2013-03-30 12:35:18 +04:00
# define CL_COPY_UNBINDABLE 0x04
2005-11-08 01:19:50 +03:00
# define CL_MAKE_SHARED 0x08
2010-01-16 21:28:47 +03:00
# define CL_PRIVATE 0x10
2012-08-01 00:13:04 +04:00
# define CL_SHARED_TO_SLAVE 0x20
2019-01-30 21:15:45 +03:00
# define CL_COPY_MNT_NS_FILE 0x40
2013-03-30 12:35:18 +04:00
# define CL_COPY_ALL (CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
2005-11-08 01:19:50 +03:00
2011-11-25 05:43:10 +04:00
static inline void set_mnt_shared ( struct mount * mnt )
2005-11-08 01:19:50 +03:00
{
2011-11-25 05:43:10 +04:00
mnt - > mnt . mnt_flags & = ~ MNT_SHARED_MASK ;
mnt - > mnt . mnt_flags | = MNT_SHARED ;
2005-11-08 01:19:50 +03:00
}
2011-11-25 05:43:10 +04:00
void change_mnt_propagation ( struct mount * , int ) ;
2013-03-15 18:53:28 +04:00
int propagate_mnt ( struct mount * , struct mountpoint * , struct mount * ,
2014-03-21 05:10:51 +04:00
struct hlist_head * ) ;
2014-12-18 22:10:48 +03:00
int propagate_umount ( struct list_head * ) ;
2011-11-25 06:35:16 +04:00
int propagate_mount_busy ( struct mount * , int ) ;
2015-01-03 14:39:35 +03:00
void propagate_mount_unlock ( struct mount * ) ;
2011-11-25 04:54:23 +04:00
void mnt_release_group_id ( struct mount * ) ;
2011-11-25 08:35:54 +04:00
int get_dominating_id ( struct mount * mnt , const struct path * root ) ;
2020-11-01 07:40:21 +03:00
int mnt_get_count ( struct mount * mnt ) ;
2013-03-15 18:53:28 +04:00
void mnt_set_mountpoint ( struct mount * , struct mountpoint * ,
2011-11-25 06:28:22 +04:00
struct mount * ) ;
2017-01-20 08:28:35 +03:00
void mnt_change_mountpoint ( struct mount * parent , struct mountpoint * mp ,
struct mount * mnt ) ;
2011-11-25 06:24:27 +04:00
struct mount * copy_tree ( struct mount * , struct dentry * , int ) ;
2011-11-25 07:00:28 +04:00
bool is_path_reachable ( struct mount * , struct dentry * ,
2011-11-24 04:34:49 +04:00
const struct path * root ) ;
2016-09-28 08:27:17 +03:00
int count_mounts ( struct mnt_namespace * ns , struct mount * mnt ) ;
2005-11-08 01:19:07 +03:00
# endif /* _LINUX_PNODE_H */
