path: root/fs/exportfs/expfs.c

/*
 * Copyright (C) Neil Brown 2002
 * Copyright (C) Christoph Hellwig 2007
 *
 * This file contains the code mapping from inodes to NFS file handles,
 * and for mapping back from file handles to dentries.
 *
 * For details on why we do all the strange and hairy things in here
 * take a look at Documentation/filesystems/nfs/Exporting.
 */
#include <linux/exportfs.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/sched.h>

#define dprintk(fmt, args...) do{}while(0)


static int get_name(const struct path *path, char *name, struct dentry *child);


static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir,
		char *name, struct dentry *child)
{
	const struct export_operations *nop = dir->d_sb->s_export_op;
	struct path path = {.mnt = mnt, .dentry = dir};

	if (nop->get_name)
		return nop->get_name(dir, name, child);
	else
		return get_name(&path, name, child);
}

/*
 * Check if the dentry or any of it's aliases is acceptable.
 */
static struct dentry *
find_acceptable_alias(struct dentry *result,
		int (*acceptable)(void *context, struct dentry *dentry),
		void *context)
{
	struct dentry *dentry, *toput = NULL;
	struct inode *inode;

	if (acceptable(context, result))
		return result;

	inode = result->d_inode;
	spin_lock(&inode->i_lock);
	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
		dget(dentry);
		spin_unlock(&inode->i_lock);
		if (toput)
			dput(toput);
		if (dentry != result && acceptable(context, dentry)) {
			dput(result);
			return dentry;
		}
		spin_lock(&inode->i_lock);
		toput = dentry;
	}
	spin_unlock(&inode->i_lock);

	if (toput)
		dput(toput);
	return NULL;
}

static bool dentry_connected(struct dentry *dentry)
{
	dget(dentry);
	while (dentry->d_flags & DCACHE_DISCONNECTED) {
		struct dentry *parent = dget_parent(dentry);

		dput(dentry);
		if (IS_ROOT(dentry)) {
			dput(parent);
			return false;
		}
		dentry = parent;
	}
	dput(dentry);
	return true;
}

static void clear_disconnected(struct dentry *dentry)
{
	dget(dentry);
	while (dentry->d_flags & DCACHE_DISCONNECTED) {
		struct dentry *parent = dget_parent(dentry);

		WARN_ON_ONCE(IS_ROOT(dentry));

		spin_lock(&dentry->d_lock);
		dentry->d_flags &= ~DCACHE_DISCONNECTED;
		spin_unlock(&dentry->d_lock);

		dput(dentry);
		dentry = parent;
	}
	dput(dentry);
}

/*
 * Reconnect a directory dentry with its parent.
 *
 * This can return a dentry, or NULL, or an error.
 *
 * In the first case the returned dentry is the parent of the given
 * dentry, and may itself need to be reconnected to its parent.
 *
 * In the NULL case, a concurrent VFS operation has either renamed or
 * removed this directory.  The concurrent operation has reconnected our
 * dentry, so we no longer need to.
 */
static struct dentry *reconnect_one(struct vfsmount *mnt,
		struct dentry *dentry, char *nbuf)
{
	struct dentry *parent;
	struct dentry *tmp;
	int err;

	parent = ERR_PTR(-EACCES);
	mutex_lock(&dentry->d_inode->i_mutex);
	if (mnt->mnt_sb->s_export_op->get_parent)
		parent = mnt->mnt_sb->s_export_op->get_parent(dentry);
	mutex_unlock(&dentry->d_inode->i_mutex);

	if (IS_ERR(parent)) {
		dprintk("%s: get_parent of %ld failed, err %d\n",
			__func__, dentry->d_inode->i_ino, PTR_ERR(parent));
		return parent;
	}

	dprintk("%s: find name of %lu in %lu\n", __func__,
		dentry->d_inode->i_ino, parent->d_inode->i_ino);
	err = exportfs_get_name(mnt, parent, nbuf, dentry);
	if (err == -ENOENT)
		goto out_reconnected;
	if (err)
		goto out_err;
	dprintk("%s: found name: %s\n", __func__, nbuf);
	mutex_lock(&parent->d_inode->i_mutex);
	tmp = lookup_one_len(nbuf, parent, strlen(nbuf));
	mutex_unlock(&parent->d_inode->i_mutex);
	if (IS_ERR(tmp)) {
		dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
		goto out_err;
	}
	if (tmp != dentry) {
		dput(tmp);
		goto out_reconnected;
	}
	dput(tmp);
	if (IS_ROOT(dentry)) {
		err = -ESTALE;
		goto out_err;
	}
	return parent;

out_err:
	dput(parent);
	return ERR_PTR(err);
out_reconnected:
	dput(parent);
	/*
	 * Someone must have renamed our entry into another parent, in
	 * which case it has been reconnected by the rename.
	 *
	 * Or someone removed it entirely, in which case filehandle
	 * lookup will succeed but the directory is now IS_DEAD and
	 * subsequent operations on it will fail.
	 *
	 * Alternatively, maybe there was no race at all, and the
	 * filesystem is just corrupt and gave us a parent that doesn't
	 * actually contain any entry pointing to this inode.  So,
	 * double check that this worked and return -ESTALE if not:
	 */
	if (!dentry_connected(dentry))
		return ERR_PTR(-ESTALE);
	return NULL;
}

/*
 * Make sure target_dir is fully connected to the dentry tree.
 *
 * On successful return, DCACHE_DISCONNECTED will be cleared on
 * target_dir, and target_dir->d_parent->...->d_parent will reach the
 * root of the filesystem.
 *
 * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected.
 * But the converse is not true: target_dir may have DCACHE_DISCONNECTED
 * set but already be connected.  In that case we'll verify the
 * connection to root and then clear the flag.
 *
 * Note that target_dir could be removed by a concurrent operation.  In
 * that case reconnect_path may still succeed with target_dir fully
 * connected, but further operations using the filehandle will fail when
 * necessary (due to S_DEAD being set on the directory).
 */
static int
reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf)
{
	struct dentry *dentry, *parent;

	dentry = dget(target_dir);

	while (dentry->d_flags & DCACHE_DISCONNECTED) {
		BUG_ON(dentry == mnt->mnt_sb->s_root);

		if (IS_ROOT(dentry))
			parent = reconnect_one(mnt, dentry, nbuf);
		else
			parent = dget_parent(dentry);

		if (!parent)
			break;
		dput(dentry);
		if (IS_ERR(parent))
			return PTR_ERR(parent);
		dentry = parent;
	}
	dput(dentry);
	clear_disconnected(target_dir);
	return 0;
}

struct getdents_callback {
	struct dir_context ctx;
	char *name;		/* name that was found. It already points to a
				   buffer NAME_MAX+1 is size */
	u64 ino;		/* the inum we are looking for */
	int found;		/* inode matched? */
	int sequence;		/* sequence counter */
};

/*
 * A rather strange filldir function to capture
 * the name matching the specified inode number.
 */
static int filldir_one(struct dir_context *ctx, const char *name, int len,
			loff_t pos, u64 ino, unsigned int d_type)
{
	struct getdents_callback *buf =
		container_of(ctx, struct getdents_callback, ctx);
	int result = 0;

	buf->sequence++;
	if (buf->ino == ino && len <= NAME_MAX) {
		memcpy(buf->name, name, len);
		buf->name