namespace.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

	up_write(&sb->s_umount);
	return err;
}

static int do_move_mount(struct nameidata *nd, char *old_name)
{
	struct nameidata old_nd, parent_nd;
	struct vfsmount *p;
	int err = 0;
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!old_name || !*old_name)
		return -EINVAL;
	if (path_init(old_name, LOOKUP_POSITIVE|LOOKUP_FOLLOW, &old_nd))
		err = path_walk(old_name, &old_nd);
	if (err)
		return err;

	down(&mount_sem);
	while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
		;
	err = -EINVAL;
	if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
		goto out;

	err = -ENOENT;
	down(&nd->dentry->d_inode->i_zombie);
	if (IS_DEADDIR(nd->dentry->d_inode))
		goto out1;

	spin_lock(&dcache_lock);
	if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry))
		goto out2;

	err = -EINVAL;
	if (old_nd.dentry != old_nd.mnt->mnt_root)
		goto out2;

	if (old_nd.mnt == old_nd.mnt->mnt_parent)
		goto out2;

	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
	      S_ISDIR(old_nd.dentry->d_inode->i_mode))
		goto out2;

	err = -ELOOP;
	for (p = nd->mnt; p->mnt_parent!=p; p = p->mnt_parent)
		if (p == old_nd.mnt)
			goto out2;
	err = 0;

	detach_mnt(old_nd.mnt, &parent_nd);
	attach_mnt(old_nd.mnt, nd);
out2:
	spin_unlock(&dcache_lock);
out1:
	up(&nd->dentry->d_inode->i_zombie);
out:
	up(&mount_sem);
	if (!err)
		path_release(&parent_nd);
	path_release(&old_nd);
	return err;
}

static int do_add_mount(struct nameidata *nd, char *type, int flags,
			int mnt_flags, char *name, void *data)
{
	struct vfsmount *mnt = do_kern_mount(type, flags, name, data);
	int err = PTR_ERR(mnt);

	if (IS_ERR(mnt))
		goto out;

	down(&mount_sem);
	/* Something was mounted here while we slept */
	while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
		;
	err = -EINVAL;
	if (!check_mnt(nd->mnt))
		goto unlock;

	/* Refuse the same filesystem on the same mount point */
	err = -EBUSY;
	if (nd->mnt->mnt_sb == mnt->mnt_sb && nd->mnt->mnt_root == nd->dentry)
		goto unlock;

	mnt->mnt_flags = mnt_flags;
	err = graft_tree(mnt, nd);
unlock:
	up(&mount_sem);
	mntput(mnt);
out:
	return err;
}

static int copy_mount_options (const void *data, unsigned long *where)
{
	int i;
	unsigned long page;
	unsigned long size;
	
	*where = 0;
	if (!data)
		return 0;

	if (!(page = __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	/* We only care that *some* data at the address the user
	 * gave us is valid.  Just in case, we'll zero
	 * the remainder of the page.
	 */
	/* copy_from_user cannot cross TASK_SIZE ! */
	size = TASK_SIZE - (unsigned long)data;
	if (size > PAGE_SIZE)
		size = PAGE_SIZE;

	i = size - copy_from_user((void *)page, data, size);
	if (!i) {
		free_page(page); 
		return -EFAULT;
	}
	if (i != PAGE_SIZE)
		memset((char *)page + i, 0, PAGE_SIZE - i);
	*where = page;
	return 0;
}

/*
 * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
 * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
 *
 * data is a (void *) that can point to any structure up to
 * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
 * information (or be NULL).
 *
 * Pre-0.97 versions of mount() didn't have a flags word.
 * When the flags word was introduced its top half was required
 * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9.
 * Therefore, if this magic number is present, it carries no information
 * and must be discarded.
 */
long do_mount(char * dev_name, char * dir_name, char *type_page,
		  unsigned long flags, void *data_page)
{
	struct nameidata nd;
	int retval = 0;
	int mnt_flags = 0;

	/* Discard magic */
	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
		flags &= ~MS_MGC_MSK;

	/* Basic sanity checks */

	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
		return -EINVAL;
	if (dev_name && !memchr(dev_name, 0, PAGE_SIZE))
		return -EINVAL;

	/* Separate the per-mountpoint flags */
	if (flags & MS_NOSUID)
		mnt_flags |= MNT_NOSUID;
	if (flags & MS_NODEV)
		mnt_flags |= MNT_NODEV;
	if (flags & MS_NOEXEC)
		mnt_flags |= MNT_NOEXEC;
	flags &= ~(MS_NOSUID|MS_NOEXEC|MS_NODEV);

	/* ... and get the mountpoint */
	if (path_init(dir_name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, &nd))
		retval = path_walk(dir_name, &nd);
	if (retval)
		return retval;

	if (flags & MS_REMOUNT)
		retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags,
				    data_page);
	else if (flags & MS_BIND)
		retval = do_loopback(&nd, dev_name, flags & MS_REC);
	else if (flags & MS_MOVE)
		retval = do_move_mount(&nd, dev_name);
	else
		retval = do_add_mount(&nd, type_page, flags, mnt_flags,
				      dev_name, data_page);
	path_release(&nd);
	return retval;
}

asmlinkage long sys_mount(char * dev_name, char * dir_name, char * type,
			  unsigned long flags, void * data)
{
	int retval;
	unsigned long data_page;
	unsigned long type_page;
	unsigned long dev_page;
	char *dir_page;

	retval = copy_mount_options (type, &type_page);
	if (retval < 0)
		return retval;

	dir_page = getname(dir_name);
	retval = PTR_ERR(dir_page);
	if (IS_ERR(dir_page))
		goto out1;

	retval = copy_mount_options (dev_name, &dev_page);
	if (retval < 0)
		goto out2;

	retval = copy_mount_options (data, &data_page);
	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:
	free_page(dev_page);
out2:
	putname(dir_page);
out1:
	free_page(type_page);
	return retval;
}

static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd)
{
	struct task_struct *p;
	struct fs_struct *fs;

	read_lock(&tasklist_lock);
	for_each_task(p) {
		task_lock(p);
		fs = p->fs;
		if (fs) {
			atomic_inc(&fs->count);
			task_unlock(p);
			if (fs->root==old_nd->dentry&&fs->rootmnt==old_nd->mnt)
				set_fs_root(fs, new_nd->mnt, new_nd->dentry);
			if (fs->pwd==old_nd->dentry&&fs->pwdmnt==old_nd->mnt)
				set_fs_pwd(fs, new_nd->mnt, new_nd->dentry);
			put_fs_struct(fs);
		} else
			task_unlock(p);
	}
	read_unlock(&tasklist_lock);
}

/*
 * Moves the current root to put_root, and sets root/cwd of all processes
 * which had them on the old root to new_root.
 *
 * Note:
 *  - we don't move root/cwd if they are not at the root (reason: if something
 *    cared enough to change them, it's probably wrong to force them elsewhere)
 *  - it's okay to pick a root that isn't the root of a file system, e.g.
 *    /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
 *    though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
 *    first.
 */

asmlinkage long sys_pivot_root(const char *new_root, const char *put_old)
{
	struct vfsmount *tmp;
	struct nameidata new_nd, old_nd, parent_nd, root_parent, user_nd;
	char *name;
	int error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	lock_kernel();

	name = getname(new_root);
	error = PTR_ERR(name);
	if (IS_ERR(name))
		goto out0;
	error = 0;
	if (path_init(name, LOOKUP_POSITIVE|LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &new_nd))
		error = path_walk(name, &new_nd);
	putname(name);
	if (error)
		goto out0;
	error = -EINVAL;
	if (!check_mnt(new_nd.mnt))
		goto out1;

	name = getname(put_old);
	error = PTR_ERR(name);
	if (IS_ERR(name))
		goto out1;
	error = 0;
	if (path_init(name, LOOKUP_POSITIVE|LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &old_nd))
		error = path_walk(name, &old_nd);
	putname(name);
	if (error)
		goto out1;

	read_lock(&current->fs->lock);
	user_nd.mnt = mntget(current->fs->rootmnt);
	user_nd.dentry = dget(current->fs->root);
	read_unlock(&current->fs->lock);
	down(&mount_sem);
	down(&old_nd.dentry->d_inode->i_zombie);
	error = -EINVAL;
	if (!check_mnt(user_nd.mnt))
		goto out2;
	error = -ENOENT;
	if (IS_DEADDIR(new_nd.dentry->d_inode))
		goto out2;
	if (d_unhashed(new_nd.dentry) && !IS_ROOT(new_nd.dentry))
		goto out2;
	if (d_unhashed(old_nd.dentry) && !IS_ROOT(old_nd.dentry))
		goto out2;
	error = -EBUSY;
	if (new_nd.mnt == user_nd.mnt || old_nd.mnt == user_nd.mnt)
		goto out2; /* loop */
	error = -EINVAL;
	if (user_nd.mnt->mnt_root != user_nd.dentry)
		goto out2;
	if (new_nd.mnt->mnt_root != new_nd.dentry)
		goto out2; /* not a mountpoint */
	tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */
	spin_lock(&dcache_lock);
	if (tmp != new_nd.mnt) {
		for (;;) {
			if (tmp->mnt_parent == tmp)
				goto out3;
			if (tmp->mnt_parent == new_nd.mnt)
				break;
			tmp = tmp->mnt_parent;
		}
		if (!is_subdir(tmp->mnt_mountpoint, new_nd.dentry))
			goto out3;
	} else if (!is_subdir(old_nd.dentry, new_nd.dentry))
		goto out3;
	detach_mnt(new_nd.mnt, &parent_nd);
	detach_mnt(user_nd.mnt, &root_parent);
	attach_mnt(user_nd.mnt, &old_nd);
	attach_mnt(new_nd.mnt, &root_parent);
	spin_unlock(&dcache_lock);
	chroot_fs_refs(&user_nd, &new_nd);
	error = 0;
	path_release(&root_parent);
	path_release(&parent_nd);
out2:
	up(&old_nd.dentry->d_inode->i_zombie);
	up(&mount_sem);
	path_release(&user_nd);
	path_release(&old_nd);
out1:
	path_release(&new_nd);
out0:
	unlock_kernel();
	return error;
out3:
	spin_unlock(&dcache_lock);
	goto out2;
}

/*
 * Absolutely minimal fake fs - only empty root directory and nothing else.
 * In 2.5 we'll use ramfs or tmpfs, but for now it's all we need - just
 * something to go with root vfsmount.
 */
static struct dentry *rootfs_lookup(struct inode *dir, struct dentry *dentry)
{
	d_add(dentry, NULL);
	return NULL;
}
static struct file_operations rootfs_dir_operations = {
	read:		generic_read_dir,
	readdir:	dcache_readdir,
};
static struct inode_operations rootfs_dir_inode_operations = {
	lookup:		rootfs_lookup,
};
static struct super_block *rootfs_read_super(struct super_block * sb, void * data, int silent)
{
	struct inode * inode;
	struct dentry * root;
	static struct super_operations s_ops = {};
	sb->s_op = &s_ops;
	inode = new_inode(sb);
	if (!inode)
		return NULL;
	inode->i_mode = S_IFDIR|0555;
	inode->i_uid = inode->i_gid = 0;
	inode->i_op = &rootfs_dir_inode_operations;
	inode->i_fop = &rootfs_dir_operations;
	root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		return NULL;
	}
	sb->s_root = root;
	return sb;
}
static DECLARE_FSTYPE(root_fs_type, "rootfs", rootfs_read_super, FS_NOMOUNT);

static void __init init_mount_tree(void)
{
	register_filesystem(&root_fs_type);
	root_vfsmnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
	if (IS_ERR(root_vfsmnt))
		panic("can't allocate root vfsmount");
}

void __init mnt_init(unsigned long mempages)
{
	struct list_head *d;
	unsigned long order;
	unsigned int nr_hash;
	int i;

	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount),
					0, SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!mnt_cache)
		panic("Cannot create vfsmount cache");

	mempages >>= (16 - PAGE_SHIFT);
	mempages *= sizeof(struct list_head);
	for (order = 0; ((1UL << order) << PAGE_SHIFT) < mempages; order++)
		;

	do {
		mount_hashtable = (struct list_head *)
			__get_free_pages(GFP_ATOMIC, order);
	} while (mount_hashtable == NULL && --order >= 0);

	if (!mount_hashtable)
		panic("Failed to allocate mount hash table\n");

	/*
	 * Find the power-of-two list-heads that can fit into the allocation..
	 * We don't guarantee that "sizeof(struct list_head)" is necessarily
	 * a power-of-two.
	 */
	nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct list_head);
	hash_bits = 0;
	do {
		hash_bits++;
	} while ((nr_hash >> hash_bits) != 0);
	hash_bits--;

	/*
	 * Re-calculate the actual number of entries and the mask
	 * from the number of bits we can fit.
	 */
	nr_hash = 1UL << hash_bits;
	hash_mask = nr_hash-1;

	printk("Mount-cache hash table entries: %d (order: %ld, %ld bytes)\n",
			nr_hash, order, (PAGE_SIZE << order));

	/* And initialize the newly allocated array */
	d = mount_hashtable;
	i = nr_hash;
	do {
		INIT_LIST_HEAD(d);
		d++;
		i--;
	} while (i);
	init_mount_tree();
}

#ifdef CONFIG_BLK_DEV_INITRD

int __init change_root(kdev_t new_root_dev,const char *put_old)
{
	struct vfsmount *old_rootmnt;
	struct nameidata devfs_nd, nd;
	struct nameidata parent_nd;
	char *new_devname = kmalloc(strlen("/dev/root.old")+1, GFP_KERNEL);
	int error = 0;

	if (new_devname)
		strcpy(new_devname, "/dev/root.old");

	read_lock(&current->fs->lock);
	old_rootmnt = mntget(current->fs->rootmnt);
	read_unlock(&current->fs->lock);
	/*  First unmount devfs if mounted  */
	if (path_init("/dev", LOOKUP_FOLLOW|LOOKUP_POSITIVE, &devfs_nd))
		error = path_walk("/dev", &devfs_nd);
	if (!error) {
		if (devfs_nd.mnt->mnt_sb->s_magic == DEVFS_SUPER_MAGIC &&
		    devfs_nd.dentry == devfs_nd.mnt->mnt_root) {
			do_umount(devfs_nd.mnt, 0);
		}
		path_release(&devfs_nd);
	}
	spin_lock(&dcache_lock);
	detach_mnt(old_rootmnt, &parent_nd);
	spin_unlock(&dcache_lock);
	ROOT_DEV = new_root_dev;
	mount_root();
#if 1
	shrink_dcache();
	printk("change_root: old root has d_count=%d\n", 
	       atomic_read(&old_rootmnt->mnt_root->d_count));
#endif
	mount_devfs_fs ();
	/*
	 * Get the new mount directory
	 */
	error = 0;
	if (path_init(put_old, LOOKUP_FOLLOW|LOOKUP_POSITIVE|LOOKUP_DIRECTORY, &nd))
		error = path_walk(put_old, &nd);
	if (error) {
		int blivet;
		struct block_device *ramdisk = old_rootmnt->mnt_sb->s_bdev;

		atomic_inc(&ramdisk->bd_count);
		blivet = blkdev_get(ramdisk, FMODE_READ, 0, BDEV_FS);
		printk(KERN_NOTICE "Trying to unmount old root ... ");
		if (!blivet) {
			spin_lock(&dcache_lock);
			list_del_init(&old_rootmnt->mnt_list);
 			spin_unlock(&dcache_lock);
 			mntput(old_rootmnt);
			mntput(old_rootmnt);
			blivet = ioctl_by_bdev(ramdisk, BLKFLSBUF, 0);
			path_release(&parent_nd);
			blkdev_put(ramdisk, BDEV_FS);
		}
		if (blivet) {
			printk(KERN_ERR "error %d\n", blivet);
		} else {
			printk("okay\n");
			error = 0;
		}			
		kfree(new_devname);
		return error;
	}

	spin_lock(&dcache_lock);
	attach_mnt(old_rootmnt, &nd);
	if (new_devname) {
		if (old_rootmnt->mnt_devname)
			kfree(old_rootmnt->mnt_devname);
		old_rootmnt->mnt_devname = new_devname;
	}
	spin_unlock(&dcache_lock);

	/* put the old stuff */
	path_release(&parent_nd);
	mntput(old_rootmnt);
	path_release(&nd);
	return 0;
}

#endif