linux/fs/mount.h
Linus Torvalds f608cabaed vfs-6.11.mount
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZpEHCgAKCRCRxhvAZXjc
 om+gAQCC4nJqJqs9bJZIItRtZ71GnxZQO3HVohhIlNM2KKh0VgEA47JhD0O0Srfb
 CleII4cQWqB32BfB/vMeff6hpNa7SA4=
 =7ltk
 -----END PGP SIGNATURE-----

Merge tag 'vfs-6.11.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs mount query updates from Christian Brauner:
 "This contains work to extend the abilities of listmount() and
  statmount() and various fixes and cleanups.

  Features:

   - Allow iterating through mounts via listmount() from newest to
     oldest. This makes it possible for mount(8) to keep iterating the
     mount table in reverse order so it gets newest mounts first.

   - Relax permissions on listmount() and statmount().

     It's not necessary to have capabilities in the initial namespace:
     it is sufficient to have capabilities in the owning namespace of
     the mount namespace we're located in to list unreachable mounts in
     that namespace.

   - Extend both listmount() and statmount() to list and stat mounts in
     foreign mount namespaces.

     Currently the only way to iterate over mount entries in mount
     namespaces that aren't in the caller's mount namespace is by
     crawling through /proc in order to find /proc/<pid>/mountinfo for
     the relevant mount namespace.

     This is both very clumsy and hugely inefficient. So extend struct
     mnt_id_req with a new member that allows to specify the mount
     namespace id of the mount namespace we want to look at.

     Luckily internally we already have most of the infrastructure for
     this so we just need to expose it to userspace. Give userspace a
     way to retrieve the id of a mount namespace via statmount() and
     through a new nsfs ioctl() on mount namespace file descriptor.

     This comes with appropriate selftests.

   - Expose mount options through statmount().

     Currently if userspace wants to get mount options for a mount and
     with statmount(), they still have to open /proc/<pid>/mountinfo to
     parse mount options. Simply the information through statmount()
     directly.

     Afterwards it's possible to only rely on statmount() and
     listmount() to retrieve all and more information than
     /proc/<pid>/mountinfo provides.

     This comes with appropriate selftests.

  Fixes:

   - Avoid copying to userspace under the namespace semaphore in
     listmount.

  Cleanups:

   - Simplify the error handling in listmount by relying on our newly
     added cleanup infrastructure.

   - Refuse invalid mount ids early for both listmount and statmount"

* tag 'vfs-6.11.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: reject invalid last mount id early
  fs: refuse mnt id requests with invalid ids early
  fs: find rootfs mount of the mount namespace
  fs: only copy to userspace on success in listmount()
  sefltests: extend the statmount test for mount options
  fs: use guard for namespace_sem in statmount()
  fs: export mount options via statmount()
  fs: rename show_mnt_opts -> show_vfsmnt_opts
  selftests: add a test for the foreign mnt ns extensions
  fs: add an ioctl to get the mnt ns id from nsfs
  fs: Allow statmount() in foreign mount namespace
  fs: Allow listmount() in foreign mount namespace
  fs: export the mount ns id via statmount
  fs: keep an index of current mount namespaces
  fs: relax permissions for statmount()
  listmount: allow listing in reverse order
  fs: relax permissions for listmount()
  fs: simplify error handling
  fs: don't copy to userspace under namespace semaphore
  path: add cleanup helper
2024-07-15 11:54:04 -07:00

158 lines
4.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/ns_common.h>
#include <linux/fs_pin.h>
struct mnt_namespace {
struct ns_common ns;
struct mount * root;
struct rb_root mounts; /* Protected by namespace_sem */
struct user_namespace *user_ns;
struct ucounts *ucounts;
u64 seq; /* Sequence number to prevent loops */
wait_queue_head_t poll;
u64 event;
unsigned int nr_mounts; /* # of mounts in the namespace */
unsigned int pending_mounts;
struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */
refcount_t passive; /* number references not pinning @mounts */
} __randomize_layout;
struct mnt_pcp {
int mnt_count;
int mnt_writers;
};
struct mountpoint {
struct hlist_node m_hash;
struct dentry *m_dentry;
struct hlist_head m_list;
int m_count;
};
struct mount {
struct hlist_node mnt_hash;
struct mount *mnt_parent;
struct dentry *mnt_mountpoint;
struct vfsmount mnt;
union {
struct rcu_head mnt_rcu;
struct llist_node mnt_llist;
};
#ifdef CONFIG_SMP
struct mnt_pcp __percpu *mnt_pcp;
#else
int mnt_count;
int mnt_writers;
#endif
struct list_head mnt_mounts; /* list of children, anchored here */
struct list_head mnt_child; /* and going through their mnt_child */
struct list_head mnt_instance; /* mount instance on sb->s_mounts */
const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */
union {
struct rb_node mnt_node; /* Under ns->mounts */
struct list_head mnt_list;
};
struct list_head mnt_expire; /* link in fs-specific expiry list */
struct list_head mnt_share; /* circular list of shared mounts */
struct list_head mnt_slave_list;/* list of slave mounts */
struct list_head mnt_slave; /* slave list entry */
struct mount *mnt_master; /* slave is on master->mnt_slave_list */
struct mnt_namespace *mnt_ns; /* containing namespace */
struct mountpoint *mnt_mp; /* where is it mounted */
union {
struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */
struct hlist_node mnt_umount;
};
struct list_head mnt_umounting; /* list entry for umount propagation */
#ifdef CONFIG_FSNOTIFY
struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
__u32 mnt_fsnotify_mask;
#endif
int mnt_id; /* mount identifier, reused */
u64 mnt_id_unique; /* mount ID unique until reboot */
int mnt_group_id; /* peer group identifier */
int mnt_expiry_mark; /* true if marked for expiry */
struct hlist_head mnt_pins;
struct hlist_head mnt_stuck_children;
} __randomize_layout;
#define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
static inline struct mount *real_mount(struct vfsmount *mnt)
{
return container_of(mnt, struct mount, mnt);
}
static inline int mnt_has_parent(struct mount *mnt)
{
return mnt != mnt->mnt_parent;
}
static inline int is_mounted(struct vfsmount *mnt)
{
/* neither detached nor internal? */
return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns);
}
extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
extern int __legitimize_mnt(struct vfsmount *, unsigned);
static inline bool __path_is_mountpoint(const struct path *path)
{
struct mount *m = __lookup_mnt(path->mnt, path->dentry);
return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT));
}
extern void __detach_mounts(struct dentry *dentry);
static inline void detach_mounts(struct dentry *dentry)
{
if (!d_mountpoint(dentry))
return;
__detach_mounts(dentry);
}
static inline void get_mnt_ns(struct mnt_namespace *ns)
{
refcount_inc(&ns->ns.count);
}
extern seqlock_t mount_lock;
struct proc_mounts {
struct mnt_namespace *ns;
struct path root;
int (*show)(struct seq_file *, struct vfsmount *);
};
extern const struct seq_operations mounts_op;
extern bool __is_local_mountpoint(struct dentry *dentry);
static inline bool is_local_mountpoint(struct dentry *dentry)
{
if (!d_mountpoint(dentry))
return false;
return __is_local_mountpoint(dentry);
}
static inline bool is_anon_ns(struct mnt_namespace *ns)
{
return ns->seq == 0;
}
static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
{
WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB));
mnt->mnt.mnt_flags &= ~MNT_ONRB;
rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts);
list_add_tail(&mnt->mnt_list, dt_list);
}
extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);
bool has_locked_children(struct mount *mnt, struct dentry *dentry);