![Jan Kara](/assets/img/avatar_default.png)
Currently notification marks are attached to object (inode or vfsmnt) by a hlist_head in the object. The list is also protected by a spinlock in the object. So while there is any mark attached to the list of marks, the object must be pinned in memory (and thus e.g. last iput() deleting inode cannot happen). Also for list iteration in fsnotify() to work, we must hold fsnotify_mark_srcu lock so that mark itself and mark->obj_list.next cannot get freed. Thus we are required to wait for response to fanotify events from userspace process with fsnotify_mark_srcu lock held. That causes issues when userspace process is buggy and does not reply to some event - basically the whole notification subsystem gets eventually stuck. So to be able to drop fsnotify_mark_srcu lock while waiting for response, we have to pin the mark in memory and make sure it stays in the object list (as removing the mark waiting for response could lead to lost notification events for groups later in the list). However we don't want inode reclaim to block on such mark as that would lead to system just locking up elsewhere. This commit is the first in the series that paves way towards solving these conflicting lifetime needs. Instead of anchoring the list of marks directly in the object, we anchor it in a dedicated structure (fsnotify_mark_connector) and just point to that structure from the object. The following commits will also add spinlock protecting the list and object pointer to the structure. Reviewed-by: Miklos Szeredi <mszeredi@redhat.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Jan Kara <jack@suse.cz>
147 lines
3.7 KiB
C
147 lines
3.7 KiB
C
#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;
|
|
struct list_head list;
|
|
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;
|
|
};
|
|
|
|
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 */
|
|
struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */
|
|
#ifdef CONFIG_FSNOTIFY
|
|
struct fsnotify_mark_connector *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 fs_pin mnt_umount;
|
|
struct dentry *mnt_ex_mountpoint;
|
|
};
|
|
|
|
#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 *);
|
|
void *cached_mount;
|
|
u64 cached_event;
|
|
loff_t cached_index;
|
|
};
|
|
|
|
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);
|
|
}
|