#include <linux/seq_file.h>
#include <linux/mnt_namespace.h>
#include <linux/namei.h>
+#include <linux/nsproxy.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/ramfs.h>
static int event;
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
+static int mnt_id_start = 0;
+static int mnt_group_start = 1;
static struct list_head *mount_hashtable __read_mostly;
static struct kmem_cache *mnt_cache __read_mostly;
retry:
ida_pre_get(&mnt_id_ida, GFP_KERNEL);
spin_lock(&vfsmount_lock);
- res = ida_get_new(&mnt_id_ida, &mnt->mnt_id);
+ res = ida_get_new_above(&mnt_id_ida, mnt_id_start, &mnt->mnt_id);
+ if (!res)
+ mnt_id_start = mnt->mnt_id + 1;
spin_unlock(&vfsmount_lock);
if (res == -EAGAIN)
goto retry;
static void mnt_free_id(struct vfsmount *mnt)
{
+ int id = mnt->mnt_id;
spin_lock(&vfsmount_lock);
- ida_remove(&mnt_id_ida, mnt->mnt_id);
+ ida_remove(&mnt_id_ida, id);
+ if (mnt_id_start > id)
+ mnt_id_start = id;
spin_unlock(&vfsmount_lock);
}
*/
static int mnt_alloc_group_id(struct vfsmount *mnt)
{
+ int res;
+
if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL))
return -ENOMEM;
- return ida_get_new_above(&mnt_group_ida, 1, &mnt->mnt_group_id);
+ res = ida_get_new_above(&mnt_group_ida,
+ mnt_group_start,
+ &mnt->mnt_group_id);
+ if (!res)
+ mnt_group_start = mnt->mnt_group_id + 1;
+
+ return res;
}
/*
*/
void mnt_release_group_id(struct vfsmount *mnt)
{
- ida_remove(&mnt_group_ida, mnt->mnt_group_id);
+ int id = mnt->mnt_group_id;
+ ida_remove(&mnt_group_ida, id);
+ if (mnt_group_start > id)
+ mnt_group_start = id;
mnt->mnt_group_id = 0;
}
EXPORT_SYMBOL_GPL(mnt_want_write);
/**
+ * mnt_clone_write - get write access to a mount
+ * @mnt: the mount on which to take a write
+ *
+ * This is effectively like mnt_want_write, except
+ * it must only be used to take an extra write reference
+ * on a mountpoint that we already know has a write reference
+ * on it. This allows some optimisation.
+ *
+ * After finished, mnt_drop_write must be called as usual to
+ * drop the reference.
+ */
+int mnt_clone_write(struct vfsmount *mnt)
+{
+ /* superblock may be r/o */
+ if (__mnt_is_readonly(mnt))
+ return -EROFS;
+ preempt_disable();
+ inc_mnt_writers(mnt);
+ preempt_enable();
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mnt_clone_write);
+
+/**
+ * mnt_want_write_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 it takes a file and can
+ * do some optimisations if the file is open for write already
+ */
+int mnt_want_write_file(struct file *file)
+{
+ struct inode *inode = file->f_dentry->d_inode;
+ if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
+ return mnt_want_write(file->f_path.mnt);
+ else
+ return mnt_clone_write(file->f_path.mnt);
+}
+EXPORT_SYMBOL_GPL(mnt_want_write_file);
+
+/**
* mnt_drop_write - give up write access to a mount
* @mnt: the mount on which to give up write access
*
* we just try to remount it readonly.
*/
down_write(&sb->s_umount);
- if (!(sb->s_flags & MS_RDONLY)) {
- lock_kernel();
+ if (!(sb->s_flags & MS_RDONLY))
retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
- unlock_kernel();
- }
up_write(&sb->s_umount);
return retval;
}
goto out_unlock;
err = -ENOENT;
- if (IS_ROOT(path->dentry) || !d_unhashed(path->dentry))
+ if (!d_unlinked(path->dentry))
err = attach_recursive_mnt(mnt, path, NULL);
out_unlock:
mutex_unlock(&path->dentry->d_inode->i_mutex);
if (IS_DEADDIR(path->dentry->d_inode))
goto out1;
- if (!IS_ROOT(path->dentry) && d_unhashed(path->dentry))
+ if (d_unlinked(path->dentry))
goto out1;
err = -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ lock_kernel();
mnt = do_kern_mount(type, flags, name, data);
+ unlock_kernel();
if (IS_ERR(mnt))
return PTR_ERR(mnt);
return retval;
}
+static struct mnt_namespace *alloc_mnt_ns(void)
+{
+ struct mnt_namespace *new_ns;
+
+ new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
+ if (!new_ns)
+ return ERR_PTR(-ENOMEM);
+ atomic_set(&new_ns->count, 1);
+ new_ns->root = NULL;
+ INIT_LIST_HEAD(&new_ns->list);
+ init_waitqueue_head(&new_ns->poll);
+ new_ns->event = 0;
+ return new_ns;
+}
+
/*
* Allocate a new namespace structure and populate it with contents
* copied from the namespace of the passed in task structure.
struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
struct vfsmount *p, *q;
- new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
- if (!new_ns)
- return ERR_PTR(-ENOMEM);
-
- atomic_set(&new_ns->count, 1);
- INIT_LIST_HEAD(&new_ns->list);
- init_waitqueue_head(&new_ns->poll);
- new_ns->event = 0;
+ new_ns = alloc_mnt_ns();
+ if (IS_ERR(new_ns))
+ return new_ns;
down_write(&namespace_sem);
/* First pass: copy the tree topology */
return new_ns;
}
+/**
+ * create_mnt_ns - creates a private namespace and adds a root filesystem
+ * @mnt: pointer to the new root filesystem mountpoint
+ */
+struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
+{
+ struct mnt_namespace *new_ns;
+
+ new_ns = alloc_mnt_ns();
+ if (!IS_ERR(new_ns)) {
+ mnt->mnt_ns = new_ns;
+ new_ns->root = mnt;
+ list_add(&new_ns->list, &new_ns->root->mnt_list);
+ }
+ return new_ns;
+}
+EXPORT_SYMBOL(create_mnt_ns);
+
SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
char __user *, type, unsigned long, flags, void __user *, data)
{
if (retval < 0)
goto out3;
- lock_kernel();
retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
flags, (void *)data_page);
- unlock_kernel();
free_page(data_page);
out3:
error = -ENOENT;
if (IS_DEADDIR(new.dentry->d_inode))
goto out2;
- if (d_unhashed(new.dentry) && !IS_ROOT(new.dentry))
+ if (d_unlinked(new.dentry))
goto out2;
- if (d_unhashed(old.dentry) && !IS_ROOT(old.dentry))
+ if (d_unlinked(old.dentry))
goto out2;
error = -EBUSY;
if (new.mnt == root.mnt ||
mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
if (IS_ERR(mnt))
panic("Can't create rootfs");
- ns = kmalloc(sizeof(*ns), GFP_KERNEL);
- if (!ns)
+ ns = create_mnt_ns(mnt);
+ if (IS_ERR(ns))
panic("Can't allocate initial namespace");
- atomic_set(&ns->count, 1);
- INIT_LIST_HEAD(&ns->list);
- init_waitqueue_head(&ns->poll);
- ns->event = 0;
- list_add(&mnt->mnt_list, &ns->list);
- ns->root = mnt;
- mnt->mnt_ns = ns;
init_task.nsproxy->mnt_ns = ns;
get_mnt_ns(ns);
init_mount_tree();
}
-void __put_mnt_ns(struct mnt_namespace *ns)
+void put_mnt_ns(struct mnt_namespace *ns)
{
- struct vfsmount *root = ns->root;
+ struct vfsmount *root;
LIST_HEAD(umount_list);
+
+ if (!atomic_dec_and_lock(&ns->count, &vfsmount_lock))
+ return;
+ root = ns->root;
ns->root = NULL;
spin_unlock(&vfsmount_lock);
down_write(&namespace_sem);
release_mounts(&umount_list);
kfree(ns);
}
+EXPORT_SYMBOL(put_mnt_ns);