summaryrefslogtreecommitdiffstats
path: root/fs/namespace.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/namespace.c')
-rw-r--r--fs/namespace.c67
1 files changed, 37 insertions, 30 deletions
diff --git a/fs/namespace.c b/fs/namespace.c
index bfc5cff0e1..3ffae74652 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -39,10 +39,10 @@
/* Maximum number of mounts in a mount namespace */
static unsigned int sysctl_mount_max __read_mostly = 100000;
-static unsigned int m_hash_mask __read_mostly;
-static unsigned int m_hash_shift __read_mostly;
-static unsigned int mp_hash_mask __read_mostly;
-static unsigned int mp_hash_shift __read_mostly;
+static unsigned int m_hash_mask __ro_after_init;
+static unsigned int m_hash_shift __ro_after_init;
+static unsigned int mp_hash_mask __ro_after_init;
+static unsigned int mp_hash_shift __ro_after_init;
static __initdata unsigned long mhash_entries;
static int __init set_mhash_entries(char *str)
@@ -68,9 +68,9 @@ static u64 event;
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
-static struct hlist_head *mount_hashtable __read_mostly;
-static struct hlist_head *mountpoint_hashtable __read_mostly;
-static struct kmem_cache *mnt_cache __read_mostly;
+static struct hlist_head *mount_hashtable __ro_after_init;
+static struct hlist_head *mountpoint_hashtable __ro_after_init;
+static struct kmem_cache *mnt_cache __ro_after_init;
static DECLARE_RWSEM(namespace_sem);
static HLIST_HEAD(unmounted); /* protected by namespace_sem */
static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
@@ -86,7 +86,7 @@ struct mount_kattr {
};
/* /sys/fs */
-struct kobject *fs_kobj;
+struct kobject *fs_kobj __ro_after_init;
EXPORT_SYMBOL_GPL(fs_kobj);
/*
@@ -330,16 +330,16 @@ static int mnt_is_readonly(struct vfsmount *mnt)
* can determine when writes are able to occur to a filesystem.
*/
/**
- * __mnt_want_write - get write access to a mount without freeze protection
+ * mnt_get_write_access - get write access to a mount without freeze protection
* @m: the mount on which to take a write
*
* This tells the low-level filesystem that a write is about to be performed to
* it, and makes sure that writes are allowed (mnt it read-write) before
* returning success. This operation does not protect against filesystem being
- * frozen. When the write operation is finished, __mnt_drop_write() must be
+ * frozen. When the write operation is finished, mnt_put_write_access() must be
* called. This is effectively a refcount.
*/
-int __mnt_want_write(struct vfsmount *m)
+int mnt_get_write_access(struct vfsmount *m)
{
struct mount *mnt = real_mount(m);
int ret = 0;
@@ -386,6 +386,7 @@ int __mnt_want_write(struct vfsmount *m)
return ret;
}
+EXPORT_SYMBOL_GPL(mnt_get_write_access);
/**
* mnt_want_write - get write access to a mount
@@ -401,7 +402,7 @@ int mnt_want_write(struct vfsmount *m)
int ret;
sb_start_write(m->mnt_sb);
- ret = __mnt_want_write(m);
+ ret = mnt_get_write_access(m);
if (ret)
sb_end_write(m->mnt_sb);
return ret;
@@ -409,15 +410,15 @@ int mnt_want_write(struct vfsmount *m)
EXPORT_SYMBOL_GPL(mnt_want_write);
/**
- * __mnt_want_write_file - get write access to a file's mount
+ * mnt_get_write_access_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
- * This is like __mnt_want_write, but if the file is already open for writing it
+ * This is like mnt_get_write_access, but if @file is already open for write it
* skips incrementing mnt_writers (since the open file already has a reference)
* and instead only does the check for emergency r/o remounts. This must be
- * paired with __mnt_drop_write_file.
+ * paired with mnt_put_write_access_file.
*/
-int __mnt_want_write_file(struct file *file)
+int mnt_get_write_access_file(struct file *file)
{
if (file->f_mode & FMODE_WRITER) {
/*
@@ -428,7 +429,7 @@ int __mnt_want_write_file(struct file *file)
return -EROFS;
return 0;
}
- return __mnt_want_write(file->f_path.mnt);
+ return mnt_get_write_access(file->f_path.mnt);
}
/**
@@ -445,7 +446,7 @@ int mnt_want_write_file(struct file *file)
int ret;
sb_start_write(file_inode(file)->i_sb);
- ret = __mnt_want_write_file(file);
+ ret = mnt_get_write_access_file(file);
if (ret)
sb_end_write(file_inode(file)->i_sb);
return ret;
@@ -453,19 +454,20 @@ int mnt_want_write_file(struct file *file)
EXPORT_SYMBOL_GPL(mnt_want_write_file);
/**
- * __mnt_drop_write - give up write access to a mount
+ * mnt_put_write_access - give up write access to a mount
* @mnt: the mount on which to give up write access
*
* Tells the low-level filesystem that we are done
* performing writes to it. Must be matched with
- * __mnt_want_write() call above.
+ * mnt_get_write_access() call above.
*/
-void __mnt_drop_write(struct vfsmount *mnt)
+void mnt_put_write_access(struct vfsmount *mnt)
{
preempt_disable();
mnt_dec_writers(real_mount(mnt));
preempt_enable();
}
+EXPORT_SYMBOL_GPL(mnt_put_write_access);
/**
* mnt_drop_write - give up write access to a mount
@@ -477,20 +479,20 @@ void __mnt_drop_write(struct vfsmount *mnt)
*/
void mnt_drop_write(struct vfsmount *mnt)
{
- __mnt_drop_write(mnt);
+ mnt_put_write_access(mnt);
sb_end_write(mnt->mnt_sb);
}
EXPORT_SYMBOL_GPL(mnt_drop_write);
-void __mnt_drop_write_file(struct file *file)
+void mnt_put_write_access_file(struct file *file)
{
if (!(file->f_mode & FMODE_WRITER))
- __mnt_drop_write(file->f_path.mnt);
+ mnt_put_write_access(file->f_path.mnt);
}
void mnt_drop_write_file(struct file *file)
{
- __mnt_drop_write_file(file);
+ mnt_put_write_access_file(file);
sb_end_write(file_inode(file)->i_sb);
}
EXPORT_SYMBOL(mnt_drop_write_file);
@@ -1344,9 +1346,9 @@ void mntput(struct vfsmount *mnt)
{
if (mnt) {
struct mount *m = real_mount(mnt);
- /* avoid cacheline pingpong, hope gcc doesn't get "smart" */
+ /* avoid cacheline pingpong */
if (unlikely(m->mnt_expiry_mark))
- m->mnt_expiry_mark = 0;
+ WRITE_ONCE(m->mnt_expiry_mark, 0);
mntput_no_expire(m);
}
}
@@ -4470,10 +4472,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
/*
* If this is an attached mount make sure it's located in the callers
* mount namespace. If it's not don't let the caller interact with it.
- * If this is a detached mount make sure it has an anonymous mount
- * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE.
+ *
+ * If this mount doesn't have a parent it's most often simply a
+ * detached mount with an anonymous mount namespace. IOW, something
+ * that's simply not attached yet. But there are apparently also users
+ * that do change mount properties on the rootfs itself. That obviously
+ * neither has a parent nor is it a detached mount so we cannot
+ * unconditionally check for detached mounts.
*/
- if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns)))
+ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
goto out;
/*