mirror of
https://github.com/torvalds/linux.git
synced 2024-11-27 14:41:39 +00:00
2eea9ce431
When adding a mount to a namespace insert it into an rbtree rooted in the mnt_namespace instead of a linear list. The mnt.mnt_list is still used to set up the mount tree and for propagation, but not after the mount has been added to a namespace. Hence mnt_list can live in union with rb_node. Use MNT_ONRB mount flag to validate that the mount is on the correct list. This allows removing the cursor used for reading /proc/$PID/mountinfo. The mnt_id_unique of the next mount can be used as an index into the seq file. Tested by inserting 100k bind mounts, unsharing the mount namespace, and unmounting. No performance regressions have been observed. For the last mount in the 100k list the statmount() call was more than 100x faster due to the mount ID lookup not having to do a linear search. This patch makes the overhead of mount ID lookup non-observable in this range. Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> Link: https://lore.kernel.org/r/20231025140205.3586473-3-mszeredi@redhat.com Reviewed-by: Ian Kent <raven@themaw.net> Signed-off-by: Christian Brauner <brauner@kernel.org>
155 lines
4.2 KiB
C
155 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 {
|
|
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;
|
|
} __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);
|