0
0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-12-22 02:24:57 +08:00
linux/fs/pnode.h

60 lines
2.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* linux/fs/pnode.h
*
* (C) Copyright IBM Corporation 2005.
*/
#ifndef _LINUX_PNODE_H
#define _LINUX_PNODE_H
#include <linux/list.h>
#include "mount.h"
#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 18:10:10 +08:00
#define IS_MNT_NEW(m) (!(m)->mnt_ns || is_anon_ns((m)->mnt_ns))
#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 22:35:45 +08:00
#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)
#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
#define CL_EXPIRE 0x01
#define CL_SLAVE 0x02
#define CL_COPY_UNBINDABLE 0x04
#define CL_MAKE_SHARED 0x08
#define CL_PRIVATE 0x10
#define CL_SHARED_TO_SLAVE 0x20
#define CL_COPY_MNT_NS_FILE 0x40
#define CL_COPY_ALL (CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
static inline void set_mnt_shared(struct mount *mnt)
{
mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
mnt->mnt.mnt_flags |= MNT_SHARED;
}
void change_mnt_propagation(struct mount *, int);
int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
struct hlist_head *);
int propagate_umount(struct list_head *);
int propagate_mount_busy(struct mount *, int);
void propagate_mount_unlock(struct mount *);
void mnt_release_group_id(struct mount *);
int get_dominating_id(struct mount *mnt, const struct path *root);
int mnt_get_count(struct mount *mnt);
void mnt_set_mountpoint(struct mount *, struct mountpoint *,
struct mount *);
mnt: Tuck mounts under others instead of creating shadow/side mounts. Ever since mount propagation was introduced in cases where a mount in propagated to parent mount mountpoint pair that is already in use the code has placed the new mount behind the old mount in the mount hash table. This implementation detail is problematic as it allows creating arbitrary length mount hash chains. Furthermore it invalidates the constraint maintained elsewhere in the mount code that a parent mount and a mountpoint pair will have exactly one mount upon them. Making it hard to deal with and to talk about this special case in the mount code. Modify mount propagation to notice when there is already a mount at the parent mount and mountpoint where a new mount is propagating to and place that preexisting mount on top of the new mount. Modify unmount propagation to notice when a mount that is being unmounted has another mount on top of it (and no other children), and to replace the unmounted mount with the mount on top of it. Move the MNT_UMUONT test from __lookup_mnt_last into __propagate_umount as that is the only call of __lookup_mnt_last where MNT_UMOUNT may be set on any mount visible in the mount hash table. These modifications allow: - __lookup_mnt_last to be removed. - attach_shadows to be renamed __attach_mnt and its shadow handling to be removed. - commit_tree to be simplified - copy_tree to be simplified The result is an easier to understand tree of mounts that does not allow creation of arbitrary length hash chains in the mount hash table. The result is also a very slight userspace visible difference in semantics. The following two cases now behave identically, where before order mattered: case 1: (explicit user action) B is a slave of A mount something on A/a , it will propagate to B/a and than mount something on B/a case 2: (tucked mount) B is a slave of A mount something on B/a and than mount something on A/a Histroically umount A/a would fail in case 1 and succeed in case 2. Now umount A/a succeeds in both configurations. This very small change in semantics appears if anything to be a bug fix to me and my survey of userspace leads me to believe that no programs will notice or care of this subtle semantic change. v2: Updated to mnt_change_mountpoint to not call dput or mntput and instead to decrement the counts directly. It is guaranteed that there will be other references when mnt_change_mountpoint is called so this is safe. v3: Moved put_mountpoint under mount_lock in attach_recursive_mnt As the locking in fs/namespace.c changed between v2 and v3. v4: Reworked the logic in propagate_mount_busy and __propagate_umount that detects when a mount completely covers another mount. v5: Removed unnecessary tests whose result is alwasy true in find_topper and attach_recursive_mnt. v6: Document the user space visible semantic difference. Cc: stable@vger.kernel.org Fixes: b90fa9ae8f51 ("[PATCH] shared mount handling: bind and rbind") Tested-by: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2017-01-20 13:28:35 +08:00
void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
struct mount *mnt);
struct mount *copy_tree(struct mount *, struct dentry *, int);
bool is_path_reachable(struct mount *, struct dentry *,
const struct path *root);
mnt: Add a per mount namespace limit on the number of mounts CAI Qian <caiqian@redhat.com> pointed out that the semantics of shared subtrees make it possible to create an exponentially increasing number of mounts in a mount namespace. mkdir /tmp/1 /tmp/2 mount --make-rshared / for i in $(seq 1 20) ; do mount --bind /tmp/1 /tmp/2 ; done Will create create 2^20 or 1048576 mounts, which is a practical problem as some people have managed to hit this by accident. As such CVE-2016-6213 was assigned. Ian Kent <raven@themaw.net> described the situation for autofs users as follows: > The number of mounts for direct mount maps is usually not very large because of > the way they are implemented, large direct mount maps can have performance > problems. There can be anywhere from a few (likely case a few hundred) to less > than 10000, plus mounts that have been triggered and not yet expired. > > Indirect mounts have one autofs mount at the root plus the number of mounts that > have been triggered and not yet expired. > > The number of autofs indirect map entries can range from a few to the common > case of several thousand and in rare cases up to between 30000 and 50000. I've > not heard of people with maps larger than 50000 entries. > > The larger the number of map entries the greater the possibility for a large > number of active mounts so it's not hard to expect cases of a 1000 or somewhat > more active mounts. So I am setting the default number of mounts allowed per mount namespace at 100,000. This is more than enough for any use case I know of, but small enough to quickly stop an exponential increase in mounts. Which should be perfect to catch misconfigurations and malfunctioning programs. For anyone who needs a higher limit this can be changed by writing to the new /proc/sys/fs/mount-max sysctl. Tested-by: CAI Qian <caiqian@redhat.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2016-09-28 13:27:17 +08:00
int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
fs: allow to mount beneath top mount Various distributions are adding or are in the process of adding support for system extensions and in the future configuration extensions through various tools. A more detailed explanation on system and configuration extensions can be found on the manpage which is listed below at [1]. System extension images may – dynamically at runtime — extend the /usr/ and /opt/ directory hierarchies with additional files. This is particularly useful on immutable system images where a /usr/ and/or /opt/ hierarchy residing on a read-only file system shall be extended temporarily at runtime without making any persistent modifications. When one or more system extension images are activated, their /usr/ and /opt/ hierarchies are combined via overlayfs with the same hierarchies of the host OS, and the host /usr/ and /opt/ overmounted with it ("merging"). When they are deactivated, the mount point is disassembled — again revealing the unmodified original host version of the hierarchy ("unmerging"). Merging thus makes the extension's resources suddenly appear below the /usr/ and /opt/ hierarchies as if they were included in the base OS image itself. Unmerging makes them disappear again, leaving in place only the files that were shipped with the base OS image itself. System configuration images are similar but operate on directories containing system or service configuration. On nearly all modern distributions mount propagation plays a crucial role and the rootfs of the OS is a shared mount in a peer group (usually with peer group id 1): TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID / / ext4 shared:1 29 1 On such systems all services and containers run in a separate mount namespace and are pivot_root()ed into their rootfs. A separate mount namespace is almost always used as it is the minimal isolation mechanism services have. But usually they are even much more isolated up to the point where they almost become indistinguishable from containers. Mount propagation again plays a crucial role here. The rootfs of all these services is a slave mount to the peer group of the host rootfs. This is done so the service will receive mount propagation events from the host when certain files or directories are updated. In addition, the rootfs of each service, container, and sandbox is also a shared mount in its separate peer group: TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID / / ext4 shared:24 master:1 71 47 For people not too familiar with mount propagation, the master:1 means that this is a slave mount to peer group 1. Which as one can see is the host rootfs as indicated by shared:1 above. The shared:24 indicates that the service rootfs is a shared mount in a separate peer group with peer group id 24. A service may run other services. Such nested services will also have a rootfs mount that is a slave to the peer group of the outer service rootfs mount. For containers things are just slighly different. A container's rootfs isn't a slave to the service's or host rootfs' peer group. The rootfs mount of a container is simply a shared mount in its own peer group: TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID /home/ubuntu/debian-tree / ext4 shared:99 61 60 So whereas services are isolated OS components a container is treated like a separate world and mount propagation into it is restricted to a single well known mount that is a slave to the peer group of the shared mount /run on the host: TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID /propagate/debian-tree /run/host/incoming tmpfs master:5 71 68 Here, the master:5 indicates that this mount is a slave to the peer group with peer group id 5. This allows to propagate mounts into the container and served as a workaround for not being able to insert mounts into mount namespaces directly. But the new mount api does support inserting mounts directly. For the interested reader the blogpost in [2] might be worth reading where I explain the old and the new approach to inserting mounts into mount namespaces. Containers of course, can themselves be run as services. They often run full systems themselves which means they again run services and containers with the exact same propagation settings explained above. The whole system is designed so that it can be easily updated, including all services in various fine-grained ways without having to enter every single service's mount namespace which would be prohibitively expensive. The mount propagation layout has been carefully chosen so it is possible to propagate updates for system extensions and configurations from the host into all services. The simplest model to update the whole system is to mount on top of /usr, /opt, or /etc on the host. The new mount on /usr, /opt, or /etc will then propagate into every service. This works cleanly the first time. However, when the system is updated multiple times it becomes necessary to unmount the first update on /opt, /usr, /etc and then propagate the new update. But this means, there's an interval where the old base system is accessible. This has to be avoided to protect against downgrade attacks. The vfs already exposes a mechanism to userspace whereby mounts can be mounted beneath an existing mount. Such mounts are internally referred to as "tucked". The patch series exposes the ability to mount beneath a top mount through the new MOVE_MOUNT_BENEATH flag for the move_mount() system call. This allows userspace to seamlessly upgrade mounts. After this series the only thing that will have changed is that mounting beneath an existing mount can be done explicitly instead of just implicitly. Today, there are two scenarios where a mount can be mounted beneath an existing mount instead of on top of it: (1) When a service or container is started in a new mount namespace and pivot_root()s into its new rootfs. The way this is done is by mounting the new rootfs beneath the old rootfs: fd_newroot = open("/var/lib/machines/fedora", ...); fd_oldroot = open("/", ...); fchdir(fd_newroot); pivot_root(".", "."); After the pivot_root(".", ".") call the new rootfs is mounted beneath the old rootfs which can then be unmounted to reveal the underlying mount: fchdir(fd_oldroot); umount2(".", MNT_DETACH); Since pivot_root() moves the caller into a new rootfs no mounts must be propagated out of the new rootfs as a consequence of the pivot_root() call. Thus, the mounts cannot be shared. (2) When a mount is propagated to a mount that already has another mount mounted on the same dentry. The easiest example for this is to create a new mount namespace. The following commands will create a mount namespace where the rootfs mount / will be a slave to the peer group of the host rootfs / mount's peer group. IOW, it will receive propagation from the host: mount --make-shared / unshare --mount --propagation=slave Now a new mount on the /mnt dentry in that mount namespace is created. (As it can be confusing it should be spelled out that the tmpfs mount on the /mnt dentry that was just created doesn't propagate back to the host because the rootfs mount / of the mount namespace isn't a peer of the host rootfs.): mount -t tmpfs tmpfs /mnt TARGET SOURCE FSTYPE PROPAGATION └─/mnt tmpfs tmpfs Now another terminal in the host mount namespace can observe that the mount indeed hasn't propagated back to into the host mount namespace. A new mount can now be created on top of the /mnt dentry with the rootfs mount / as its parent: mount --bind /opt /mnt TARGET SOURCE FSTYPE PROPAGATION └─/mnt /dev/sda2[/opt] ext4 shared:1 The mount namespace that was created earlier can now observe that the bind mount created on the host has propagated into it: TARGET SOURCE FSTYPE PROPAGATION └─/mnt /dev/sda2[/opt] ext4 master:1 └─/mnt tmpfs tmpfs But instead of having been mounted on top of the tmpfs mount at the /mnt dentry the /opt mount has been mounted on top of the rootfs mount at the /mnt dentry. And the tmpfs mount has been remounted on top of the propagated /opt mount at the /opt dentry. So in other words, the propagated mount has been mounted beneath the preexisting mount in that mount namespace. Mount namespaces make this easy to illustrate but it's also easy to mount beneath an existing mount in the same mount namespace (The following example assumes a shared rootfs mount / with peer group id 1): mount --bind /opt /opt TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION └─/opt /dev/sda2[/opt] ext4 188 29 shared:1 If another mount is mounted on top of the /opt mount at the /opt dentry: mount --bind /tmp /opt The following clunky mount tree will result: TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION └─/opt /dev/sda2[/tmp] ext4 405 29 shared:1 └─/opt /dev/sda2[/opt] ext4 188 405 shared:1 └─/opt /dev/sda2[/tmp] ext4 404 188 shared:1 The /tmp mount is mounted beneath the /opt mount and another copy is mounted on top of the /opt mount. This happens because the rootfs / and the /opt mount are shared mounts in the same peer group. When the new /tmp mount is supposed to be mounted at the /opt dentry then the /tmp mount first propagates to the root mount at the /opt dentry. But there already is the /opt mount mounted at the /opt dentry. So the old /opt mount at the /opt dentry will be mounted on top of the new /tmp mount at the /tmp dentry, i.e. @opt->mnt_parent is @tmp and @opt->mnt_mountpoint is /tmp (Note that @opt->mnt_root is /opt which is what shows up as /opt under SOURCE). So again, a mount will be mounted beneath a preexisting mount. (Fwiw, a few iterations of mount --bind /opt /opt in a loop on a shared rootfs is a good example of what could be referred to as mount explosion.) The main point is that such mounts allows userspace to umount a top mount and reveal an underlying mount. So for example, umounting the tmpfs mount on /mnt that was created in example (1) using mount namespaces reveals the /opt mount which was mounted beneath it. In (2) where a mount was mounted beneath the top mount in the same mount namespace unmounting the top mount would unmount both the top mount and the mount beneath. In the process the original mount would be remounted on top of the rootfs mount / at the /opt dentry again. This again, is a result of mount propagation only this time it's umount propagation. However, this can be avoided by simply making the parent mount / of the @opt mount a private or slave mount. Then the top mount and the original mount can be unmounted to reveal the mount beneath. These two examples are fairly arcane and are merely added to make it clear how mount propagation has effects on current and future features. More common use-cases will just be things like: mount -t btrfs /dev/sdA /mnt mount -t xfs /dev/sdB --beneath /mnt umount /mnt after which we'll have updated from a btrfs filesystem to a xfs filesystem without ever revealing the underlying mountpoint. The crux is that the proposed mechanism already exists and that it is so powerful as to cover cases where mounts are supposed to be updated with new versions. Crucially, it offers an important flexibility. Namely that updates to a system may either be forced or can be delayed and the umount of the top mount be left to a service if it is a cooperative one. This adds a new flag to move_mount() that allows to explicitly move a beneath the top mount adhering to the following semantics: * Mounts cannot be mounted beneath the rootfs. This restriction encompasses the rootfs but also chroots via chroot() and pivot_root(). To mount a mount beneath the rootfs or a chroot, pivot_root() can be used as illustrated above. * The source mount must be a private mount to force the kernel to allocate a new, unused peer group id. This isn't a required restriction but a voluntary one. It avoids repeating a semantical quirk that already exists today. If bind mounts which already have a peer group id are inserted into mount trees that have the same peer group id this can cause a lot of mount propagation events to be generated (For example, consider running mount --bind /opt /opt in a loop where the parent mount is a shared mount.). * Avoid getting rid of the top mount in the kernel. Cooperative services need to be able to unmount the top mount themselves. This also avoids a good deal of additional complexity. The umount would have to be propagated which would be another rather expensive operation. So namespace_lock() and lock_mount_hash() would potentially have to be held for a long time for both a mount and umount propagation. That should be avoided. * The path to mount beneath must be mounted and attached. * The top mount and its parent must be in the caller's mount namespace and the caller must be able to mount in that mount namespace. * The caller must be able to unmount the top mount to prove that they could reveal the underlying mount. * The propagation tree is calculated based on the destination mount's parent mount and the destination mount's mountpoint on the parent mount. Of course, if the parent of the destination mount and the destination mount are shared mounts in the same peer group and the mountpoint of the new mount to be mounted is a subdir of their ->mnt_root then both will receive a mount of /opt. That's probably easier to understand with an example. Assuming a standard shared rootfs /: mount --bind /opt /opt mount --bind /tmp /opt will cause the same mount tree as: mount --bind /opt /opt mount --beneath /tmp /opt because both / and /opt are shared mounts/peers in the same peer group and the /opt dentry is a subdirectory of both the parent's and the child's ->mnt_root. If a mount tree like that is created it almost always is an accident or abuse of mount propagation. Realistically what most people probably mean in this scenarios is: mount --bind /opt /opt mount --make-private /opt mount --make-shared /opt This forces the allocation of a new separate peer group for the /opt mount. Aferwards a mount --bind or mount --beneath actually makes sense as the / and /opt mount belong to different peer groups. Before that it's likely just confusion about what the user wanted to achieve. * Refuse MOVE_MOUNT_BENEATH if: (1) the @mnt_from has been overmounted in between path resolution and acquiring @namespace_sem when locking @mnt_to. This avoids the proliferation of shadow mounts. (2) if @to_mnt is moved to a different mountpoint while acquiring @namespace_sem to lock @to_mnt. (3) if @to_mnt is unmounted while acquiring @namespace_sem to lock @to_mnt. (4) if the parent of the target mount propagates to the target mount at the same mountpoint. This would mean mounting @mnt_from on @mnt_to->mnt_parent and then propagating a copy @c of @mnt_from onto @mnt_to. This defeats the whole purpose of mounting @mnt_from beneath @mnt_to. (5) if the parent mount @mnt_to->mnt_parent propagates to @mnt_from at the same mountpoint. If @mnt_to->mnt_parent propagates to @mnt_from this would mean propagating a copy @c of @mnt_from on top of @mnt_from. Afterwards @mnt_from would be mounted on top of @mnt_to->mnt_parent and @mnt_to would be unmounted from @mnt->mnt_parent and remounted on @mnt_from. But since @c is already mounted on @mnt_from, @mnt_to would ultimately be remounted on top of @c. Afterwards, @mnt_from would be covered by a copy @c of @mnt_from and @c would be covered by @mnt_from itself. This defeats the whole purpose of mounting @mnt_from beneath @mnt_to. Cases (1) to (3) are required as they deal with races that would cause bugs or unexpected behavior for users. Cases (4) and (5) refuse semantical quirks that would not be a bug but would cause weird mount trees to be created. While they can already be created via other means (mount --bind /opt /opt x n) there's no reason to repeat past mistakes in new features. Link: https://man7.org/linux/man-pages/man8/systemd-sysext.8.html [1] Link: https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html [2] Link: https://github.com/flatcar/sysext-bakery Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_1 Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_2 Link: https://github.com/systemd/systemd/pull/26013 Reviewed-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org> Message-Id: <20230202-fs-move-mount-replace-v4-4-98f3d80d7eaa@kernel.org> Signed-off-by: Christian Brauner <brauner@kernel.org>
2023-05-03 19:18:42 +08:00
bool propagation_would_overmount(const struct mount *from,
const struct mount *to,
const struct mountpoint *mp);
#endif /* _LINUX_PNODE_H */