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

/*
 *  linux/fs/namespace.c
 *
 * (C) Copyright Al Viro 2000, 2001
 *	Released under GPL v2.
 *
 * Based on code from fs/super.c, copyright Linus Torvalds and others.
 * Heavily rewritten.
 */

#include <linux/config.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/acct.h>
#include <linux/module.h>
#include <linux/devfs_fs_kernel.h>

#include <asm/uaccess.h>

#include <linux/seq_file.h>

struct vfsmount *do_kern_mount(char *type, int flags, char *name, void *data);
int do_remount_sb(struct super_block *sb, int flags, void * data);
void kill_super(struct super_block *sb);

static struct list_head *mount_hashtable;
static int hash_mask, hash_bits;
static kmem_cache_t *mnt_cache; 

static LIST_HEAD(vfsmntlist);
static DECLARE_MUTEX(mount_sem);

/* Will be static */
struct vfsmount *root_vfsmnt;

static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
{
	unsigned long tmp = ((unsigned long) mnt / L1_CACHE_BYTES);
	tmp += ((unsigned long) dentry / L1_CACHE_BYTES);
	tmp = tmp + (tmp >> hash_bits);
	return tmp & hash_mask;
}

struct vfsmount *alloc_vfsmnt(void)
{
	struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL); 
	if (mnt) {
		memset(mnt, 0, sizeof(struct vfsmount));
		atomic_set(&mnt->mnt_count,1);
		INIT_LIST_HEAD(&mnt->mnt_hash);
		INIT_LIST_HEAD(&mnt->mnt_child);
		INIT_LIST_HEAD(&mnt->mnt_mounts);
		INIT_LIST_HEAD(&mnt->mnt_list);
	}
	return mnt;
}

void free_vfsmnt(struct vfsmount *mnt)
{
	if (mnt->mnt_devname)
		kfree(mnt->mnt_devname);
	kmem_cache_free(mnt_cache, mnt);
}

void set_devname(struct vfsmount *mnt, const char *name)
{
	if (name) {
		int size = strlen(name)+1;
		char * newname = kmalloc(size, GFP_KERNEL);
		if (newname) {
			memcpy(newname, name, size);
			mnt->mnt_devname = newname;
		}
	}
}

struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
	struct list_head * head = mount_hashtable + hash(mnt, dentry);
	struct list_head * tmp = head;
	struct vfsmount *p;

	for (;;) {
		tmp = tmp->next;
		p = NULL;
		if (tmp == head)
			break;
		p = list_entry(tmp, struct vfsmount, mnt_hash);
		if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry)
			break;
	}
	return p;
}

static int check_mnt(struct vfsmount *mnt)
{
	spin_lock(&dcache_lock);
	while (mnt->mnt_parent != mnt)
		mnt = mnt->mnt_parent;
	spin_unlock(&dcache_lock);
	return mnt == root_vfsmnt;
}

static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd)
{
	old_nd->dentry = mnt->mnt_mountpoint;
	old_nd->mnt = mnt->mnt_parent;
	mnt->mnt_parent = mnt;
	mnt->mnt_mountpoint = mnt->mnt_root;
	list_del_init(&mnt->mnt_child);
	list_del_init(&mnt->mnt_hash);
	old_nd->dentry->d_mounted--;
}

static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd)
{
	mnt->mnt_parent = mntget(nd->mnt);
	mnt->mnt_mountpoint = dget(nd->dentry);
	list_add(&mnt->mnt_hash, mount_hashtable+hash(nd->mnt, nd->dentry));
	list_add(&mnt->mnt_child, &nd->mnt->mnt_mounts);
	nd->dentry->d_mounted++;
}

static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root)
{
	struct list_head *next = p->mnt_mounts.next;
	if (next == &p->mnt_mounts) {
		while (1) {
			if (p == root)
				return NULL;
			next = p->mnt_child.next;
			if (next != &p->mnt_parent->mnt_mounts)
				break;
			p = p->mnt_parent;
		}
	}
	return list_entry(next, struct vfsmount, mnt_child);
}

static struct vfsmount *
clone_mnt(struct vfsmount *old, struct dentry *root)
{
	struct super_block *sb = old->mnt_sb;
	struct vfsmount *mnt = alloc_vfsmnt();

	if (mnt) {
		mnt->mnt_flags = old->mnt_flags;
		set_devname(mnt, old->mnt_devname);
		atomic_inc(&sb->s_active);
		mnt->mnt_sb = sb;
		mnt->mnt_root = dget(root);
		mnt->mnt_mountpoint = mnt->mnt_root;
		mnt->mnt_parent = mnt;
	}
	return mnt;
}

void __mntput(struct vfsmount *mnt)
{
	struct super_block *sb = mnt->mnt_sb;
	dput(mnt->mnt_root);
	free_vfsmnt(mnt);
	kill_super(sb);
}

/* iterator */
static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct list_head *p;
	loff_t n = *pos;

	down(&mount_sem);
	list_for_each(p, &vfsmntlist)
		if (!n--)
			return list_entry(p, struct vfsmount, mnt_list);
	return NULL;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct list_head *p = ((struct vfsmount *)v)->mnt_list.next;
	(*pos)++;
	return p==&vfsmntlist ? NULL : list_entry(p, struct vfsmount, mnt_list);
}

static void m_stop(struct seq_file *m, void *v)
{
	up(&mount_sem);
}

static inline void mangle(struct seq_file *m, const char *s)
{
	seq_escape(m, s, " \t\n\\");
}

static int show_vfsmnt(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = v;
	int err = 0;
	static struct proc_fs_info {
		int flag;
		char *str;
	} fs_info[] = {
		{ MS_SYNCHRONOUS, ",sync" },
		{ MS_MANDLOCK, ",mand" },
		{ MS_NOATIME, ",noatime" },
		{ MS_NODIRATIME, ",nodiratime" },
		{ 0, NULL }
	};
	static struct proc_fs_info mnt_info[] = {
		{ MNT_NOSUID, ",nosuid" },
		{ MNT_NODEV, ",nodev" },
		{ MNT_NOEXEC, ",noexec" },
		{ 0, NULL }
	};
	struct proc_fs_info *fs_infop;
	char *path_buf, *path;

	path_buf = (char *) __get_free_page(GFP_KERNEL);
	if (!path_buf)
		return -ENOMEM;
	path = d_path(mnt->mnt_root, mnt, path_buf, PAGE_SIZE);

	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
	seq_putc(m, ' ');
	mangle(m, path);
	free_page((unsigned long) path_buf);
	seq_putc(m, ' ');
	mangle(m, mnt->mnt_sb->s_type->name);
	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_sb->s_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	if (mnt->mnt_sb->s_op->show_options)
		err = mnt->mnt_sb->s_op->show_options(m, mnt);
	seq_puts(m, " 0 0\n");
	return err;
}

struct seq_operations mounts_op = {
	start:	m_start,
	next:	m_next,
	stop:	m_stop,
	show:	show_vfsmnt
};

/*
 * Doesn't take quota and stuff into account. IOW, in some cases it will
 * give false negatives. The main reason why it's here is that we need
 * a non-destructive way to look for easily umountable filesystems.
 */
int may_umount(struct vfsmount *mnt)
{
	if (atomic_read(&mnt->mnt_count) > 2)
		return -EBUSY;
	return 0;
}

void umount_tree(struct vfsmount *mnt)
{
	struct vfsmount *p;
	LIST_HEAD(kill);

	for (p = mnt; p; p = next_mnt(p, mnt)) {
		list_del(&p->mnt_list);
		list_add(&p->mnt_list, &kill);
	}

	while (!list_empty(&kill)) {
		mnt = list_entry(kill.next, struct vfsmount, mnt_list);
		list_del_init(&mnt->mnt_list);
		if (mnt->mnt_parent == mnt) {
			spin_unlock(&dcache_lock);
		} else {
			struct nameidata old_nd;
			detach_mnt(mnt, &old_nd);
			spin_unlock(&dcache_lock);
			path_release(&old_nd);
		}
		mntput(mnt);
		spin_lock(&dcache_lock);
	}
}

static int do_umount(struct vfsmount *mnt, int flags)
{
	struct super_block * sb = mnt->mnt_sb;
	int retval = 0;

	/*
	 * If we may have to abort operations to get out of this
	 * mount, and they will themselves hold resources we must
	 * allow the fs to do things. In the Unix tradition of
	 * 'Gee thats tricky lets do it in userspace' the umount_begin
	 * might fail to complete on the first run through as other tasks
	 * must return, and the like. Thats for the mount program to worry
	 * about for the moment.
	 */

	lock_kernel();
	if( (flags&MNT_FORCE) && sb->s_op->umount_begin)
		sb->s_op->umount_begin(sb);
	unlock_kernel();

	/*
	 * No sense to grab the lock for this test, but test itself looks
	 * somewhat bogus. Suggestions for better replacement?
	 * Ho-hum... In principle, we might treat that as umount + switch
	 * to rootfs. GC would eventually take care of the old vfsmount.
	 * Actually it makes sense, especially if rootfs would contain a
	 * /reboot - static binary that would close all descriptors and
	 * call reboot(9). Then init(8) could umount root and exec /reboot.
	 */
	if (mnt == current->fs->rootmnt && !(flags & MNT_DETACH)) {
		/*
		 * Special case for "unmounting" root ...
		 * we just try to remount it readonly.
		 */
		down_write(&sb->s_umount);
		if (!(sb->s_flags & MS_RDONLY)) {
			lock_kernel();
			retval = do_remount_sb(sb, MS_RDONLY, 0);
			unlock_kernel();
		}
		up_write(&sb->s_umount);
		return retval;
	}

	down(&mount_sem);
	spin_lock(&dcache_lock);

	if (atomic_read(&sb->s_active) == 1) {
		/* last instance - try to be smart */
		spin_unlock(&dcache_lock);
		lock_kernel();
		DQUOT_OFF(sb);
		acct_auto_close(sb->s_dev);
		unlock_kernel();
		spin_lock(&dcache_lock);
	}
	retval = -EBUSY;
	if (atomic_read(&mnt->mnt_count) == 2 || flags & MNT_DETACH) {
		if (!list_empty(&mnt->mnt_list))
			umount_tree(mnt);
		retval = 0;
	}
	spin_unlock(&dcache_lock);
	up(&mount_sem);
	return retval;
}

/*
 * Now umount can handle mount points as well as block devices.
 * This is important for filesystems which use unnamed block devices.
 *
 * We now support a flag for forced unmount like the other 'big iron'
 * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
 */

asmlinkage long sys_umount(char * name, int flags)
{
	struct nameidata nd;
	char *kname;
	int retval;

	kname = getname(name);
	retval = PTR_ERR(kname);
	if (IS_ERR(kname))
		goto out;
	retval = 0;
	if (path_init(kname, LOOKUP_POSITIVE|LOOKUP_FOLLOW, &nd))
		retval = path_walk(kname, &nd);
	putname(kname);
	if (retval)
		goto out;
	retval = -EINVAL;
	if (nd.dentry != nd.mnt->mnt_root)
		goto dput_and_out;
	if (!check_mnt(nd.mnt))
		goto dput_and_out;

	retval = -EPERM;
	if (!capable(CAP_SYS_ADMIN))
		goto dput_and_out;

	retval = do_umount(nd.mnt, flags);
dput_and_out:
	path_release(&nd);
out:
	return retval;
}

/*
 *	The 2.0 compatible umount. No flags. 
 */
 
asmlinkage long sys_oldumount(char * name)
{
	return sys_umount(name,0);
}

static int mount_is_safe(struct nameidata *nd)
{
	if (capable(CAP_SYS_ADMIN))
		return 0;
	return -EPERM;
#ifdef notyet
	if (S_ISLNK(nd->dentry->d_inode->i_mode))
		return -EPERM;
	if (nd->dentry->d_inode->i_mode & S_ISVTX) {
		if (current->uid != nd->dentry->d_inode->i_uid)
			return -EPERM;
	}
	if (permission(nd->dentry->d_inode, MAY_WRITE))
		return -EPERM;
	return 0;
#endif
}

static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry)
{
	struct vfsmount *p, *next, *q, *res;
	struct nameidata nd;

	p = mnt;
	res = nd.mnt = q = clone_mnt(p, dentry);
	if (!q)
		goto Enomem;
	q->mnt_parent = q;
	q->mnt_mountpoint = p->mnt_mountpoint;

	while ( (next = next_mnt(p, mnt)) != NULL) {
		while (p != next->mnt_parent) {
			p = p->mnt_parent;
			q = q->mnt_parent;
		}
		p = next;
		nd.mnt = q;
		nd.dentry = p->mnt_mountpoint;
		q = clone_mnt(p, p->mnt_root);
		if (!q)
			goto Enomem;
		spin_lock(&dcache_lock);
		list_add_tail(&q->mnt_list, &res->mnt_list);
		attach_mnt(q, &nd);
		spin_unlock(&dcache_lock);
	}
	return res;
Enomem:
	if (res) {
		spin_lock(&dcache_lock);
		umount_tree(res);
		spin_unlock(&dcache_lock);
	}
	return NULL;
}

/* Will become static */
int graft_tree(struct vfsmount *mnt, struct nameidata *nd)
{
	int err;
	if (mnt->mnt_sb->s_flags & MS_NOUSER)
		return -EINVAL;

	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
		return -ENOTDIR;

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

	spin_lock(&dcache_lock);
	if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) {
		struct list_head head;
		attach_mnt(mnt, nd);
		list_add_tail(&head, &mnt->mnt_list);
		list_splice(&head, vfsmntlist.prev);
		mntget(mnt);
		err = 0;
	}
	spin_unlock(&dcache_lock);
out_unlock:
	up(&nd->dentry->d_inode->i_zombie);
	return err;
}

/*
 * do loopback mount.
 */
static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
{
	struct nameidata old_nd;
	struct vfsmount *mnt = NULL;
	int err = mount_is_safe(nd);
	if (err)
		return err;
	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);
	err = -EINVAL;
	if (check_mnt(nd->mnt) && (!recurse || check_mnt(old_nd.mnt))) {
		err = -ENOMEM;
		if (recurse)
			mnt = copy_tree(old_nd.mnt, old_nd.dentry);
		else
			mnt = clone_mnt(old_nd.mnt, old_nd.dentry);
	}

	if (mnt) {
		err = graft_tree(mnt, nd);
		if (err) {
			spin_lock(&dcache_lock);
			umount_tree(mnt);
			spin_unlock(&dcache_lock);
		} else
			mntput(mnt);
	}

	up(&mount_sem);
	path_release(&old_nd);
	return err;
}

/*
 * change filesystem flags. dir should be a physical root of filesystem.
 * If you've mounted a non-root directory somewhere and want to do remount
 * on it - tough luck.
 */

static int do_remount(struct nameidata *nd,int flags,int mnt_flags,void *data)
{
	int err;
	struct super_block * sb = nd->mnt->mnt_sb;

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

	if (!check_mnt(nd->mnt))
		return -EINVAL;

	if (nd->dentry != nd->mnt->mnt_root)
		return -EINVAL;

	down_write(&sb->s_umount);
	err = do_remount_sb(sb, flags, data);
	if (!err)
		nd->mnt->mnt_flags=mnt_flags;