linux_kernel/fs/mount.h
Miklos Szeredi 9f6c61f96f proc/mounts: add cursor
If mounts are deleted after a read(2) call on /proc/self/mounts (or its
kin), the subsequent read(2) could miss a mount that comes after the
deleted one in the list.  This is because the file position is interpreted
as the number mount entries from the start of the list.

E.g. first read gets entries #0 to #9; the seq file index will be 10.  Then
entry #5 is deleted, resulting in #10 becoming #9 and #11 becoming #10,
etc...  The next read will continue from entry #10, and #9 is missed.

Solve this by adding a cursor entry for each open instance.  Taking the
global namespace_sem for write seems excessive, since we are only dealing
with a per-namespace list.  Instead add a per-namespace spinlock and use
that together with namespace_sem taken for read to protect against
concurrent modification of the mount list.  This may reduce parallelism of
is_local_mountpoint(), but it's hardly a big contention point.  We could
also use RCU freeing of cursors to make traversal not need additional
locks, if that turns out to be neceesary.

Only move the cursor once for each read (cursor is not added on open) to
minimize cacheline invalidation.  When EOF is reached, the cursor is taken
off the list, in order to prevent an excessive number of cursors due to
inactive open file descriptors.

Reported-by: Karel Zak <kzak@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2020-05-14 16:44:24 +02:00

162 lines
4.2 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 {
atomic_t count;
struct ns_common ns;
struct mount * root;
/*
* Traversal and modification of .list is protected by either
* - taking namespace_sem for write, OR
* - taking namespace_sem for read AND taking .ns_lock.
*/
struct list_head list;
spinlock_t ns_lock;
struct user_namespace *user_ns;
struct ucounts *ucounts;
u64 seq; /* Sequence number to prevent loops */
wait_queue_head_t poll;
u64 event;
unsigned int mounts; /* # of mounts in the namespace */
unsigned int pending_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 */
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 */
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);
extern bool 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)
{
atomic_inc(&ns->count);
}
extern seqlock_t mount_lock;
static inline void lock_mount_hash(void)
{
write_seqlock(&mount_lock);
}
static inline void unlock_mount_hash(void)
{
write_sequnlock(&mount_lock);
}
struct proc_mounts {
struct mnt_namespace *ns;
struct path root;
int (*show)(struct seq_file *, struct vfsmount *);
struct mount cursor;
};
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;
}
extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);