inode.c

		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
		spin_unlock(&inode->i_lock);
	}
	if ((attr->ia_valid & ATTR_SIZE) != 0) {
		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
		inode->i_size = attr->ia_size;
		vmtruncate(inode, attr->ia_size);
	}
}

static int nfs_wait_schedule(void *word)
{
	if (signal_pending(current))
		return -ERESTARTSYS;
	schedule();
	return 0;
}

/*
 * Wait for the inode to get unlocked.
 */
static int nfs_wait_on_inode(struct inode *inode)
{
	struct rpc_clnt	*clnt = NFS_CLIENT(inode);
	struct nfs_inode *nfsi = NFS_I(inode);
	sigset_t oldmask;
	int error;

	rpc_clnt_sigmask(clnt, &oldmask);
	error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
					nfs_wait_schedule, TASK_INTERRUPTIBLE);
	rpc_clnt_sigunmask(clnt, &oldmask);

	return error;
}

static void nfs_wake_up_inode(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
	smp_mb__after_clear_bit();
	wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
}

int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
	int err;

	/* Flush out writes to the server in order to update c/mtime */
	nfs_sync_inode_wait(inode, 0, 0, FLUSH_NOCOMMIT);

	/*
	 * We may force a getattr if the user cares about atime.
	 *
	 * Note that we only have to check the vfsmount flags here:
	 *  - NFS always sets S_NOATIME by so checking it would give a
	 *    bogus result
	 *  - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
	 *    no point in checking those.
	 */
 	if ((mnt->mnt_flags & MNT_NOATIME) ||
 	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
		need_atime = 0;

	if (need_atime)
		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
	else
		err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!err)
		generic_fillattr(inode, stat);
	return err;
}

static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
{
	struct nfs_open_context *ctx;

	ctx = (struct nfs_open_context *)kmalloc(sizeof(*ctx), GFP_KERNEL);
	if (ctx != NULL) {
		atomic_set(&ctx->count, 1);
		ctx->dentry = dget(dentry);
		ctx->vfsmnt = mntget(mnt);
		ctx->cred = get_rpccred(cred);
		ctx->state = NULL;
		ctx->lockowner = current->files;
		ctx->error = 0;
		ctx->dir_cookie = 0;
	}
	return ctx;
}

struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
	if (ctx != NULL)
		atomic_inc(&ctx->count);
	return ctx;
}

void put_nfs_open_context(struct nfs_open_context *ctx)
{
	if (atomic_dec_and_test(&ctx->count)) {
		if (!list_empty(&ctx->list)) {
			struct inode *inode = ctx->dentry->d_inode;
			spin_lock(&inode->i_lock);
			list_del(&ctx->list);
			spin_unlock(&inode->i_lock);
		}
		if (ctx->state != NULL)
			nfs4_close_state(ctx->state, ctx->mode);
		if (ctx->cred != NULL)
			put_rpccred(ctx->cred);
		dput(ctx->dentry);
		mntput(ctx->vfsmnt);
		kfree(ctx);
	}
}

/*
 * Ensure that mmap has a recent RPC credential for use when writing out
 * shared pages
 */
static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct nfs_inode *nfsi = NFS_I(inode);

	filp->private_data = get_nfs_open_context(ctx);
	spin_lock(&inode->i_lock);
	list_add(&ctx->list, &nfsi->open_files);
	spin_unlock(&inode->i_lock);
}

/*
 * Given an inode, search for an open context with the desired characteristics
 */
struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_open_context *pos, *ctx = NULL;

	spin_lock(&inode->i_lock);
	list_for_each_entry(pos, &nfsi->open_files, list) {
		if (cred != NULL && pos->cred != cred)
			continue;
		if ((pos->mode & mode) == mode) {
			ctx = get_nfs_open_context(pos);
			break;
		}
	}
	spin_unlock(&inode->i_lock);
	return ctx;
}

static void nfs_file_clear_open_context(struct file *filp)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct nfs_open_context *ctx = (struct nfs_open_context *)filp->private_data;

	if (ctx) {
		filp->private_data = NULL;
		spin_lock(&inode->i_lock);
		list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
		spin_unlock(&inode->i_lock);
		put_nfs_open_context(ctx);
	}
}

/*
 * These allocate and release file read/write context information.
 */
int nfs_open(struct inode *inode, struct file *filp)
{
	struct nfs_open_context *ctx;
	struct rpc_cred *cred;

	cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
	if (IS_ERR(cred))
		return PTR_ERR(cred);
	ctx = alloc_nfs_open_context(filp->f_vfsmnt, filp->f_dentry, cred);
	put_rpccred(cred);
	if (ctx == NULL)
		return -ENOMEM;
	ctx->mode = filp->f_mode;
	nfs_file_set_open_context(filp, ctx);
	put_nfs_open_context(ctx);
	return 0;
}

int nfs_release(struct inode *inode, struct file *filp)
{
	nfs_file_clear_open_context(filp);
	return 0;
}

/*
 * This function is called whenever some part of NFS notices that
 * the cached attributes have to be refreshed.
 */
int
__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
	int		 status = -ESTALE;
	struct nfs_fattr fattr;
	struct nfs_inode *nfsi = NFS_I(inode);

	dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
		inode->i_sb->s_id, (long long)NFS_FILEID(inode));

	nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
	lock_kernel();
	if (!inode || is_bad_inode(inode))
 		goto out_nowait;
	if (NFS_STALE(inode))
 		goto out_nowait;

	status = nfs_wait_on_inode(inode);
	if (status < 0)
		goto out;
	if (NFS_STALE(inode)) {
		status = -ESTALE;
		/* Do we trust the cached ESTALE? */
		if (NFS_ATTRTIMEO(inode) != 0) {
			if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME)) {
				/* no */
			} else
				goto out;
		}
	}

	status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
	if (status != 0) {
		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
			 inode->i_sb->s_id,
			 (long long)NFS_FILEID(inode), status);
		if (status == -ESTALE) {
			nfs_zap_caches(inode);
			if (!S_ISDIR(inode->i_mode))
				set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
		}
		goto out;
	}

	spin_lock(&inode->i_lock);
	status = nfs_update_inode(inode, &fattr);
	if (status) {
		spin_unlock(&inode->i_lock);
		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
			 inode->i_sb->s_id,
			 (long long)NFS_FILEID(inode), status);
		goto out;
	}
	spin_unlock(&inode->i_lock);

	if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
		nfs_zap_acl_cache(inode);

	dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n",
		inode->i_sb->s_id,
		(long long)NFS_FILEID(inode));

 out:
	nfs_wake_up_inode(inode);

 out_nowait:
	unlock_kernel();
	return status;
}

int nfs_attribute_timeout(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	if (nfs_have_delegation(inode, FMODE_READ))
		return 0;
	return time_after(jiffies, nfsi->read_cache_jiffies+nfsi->attrtimeo);
}

/**
 * nfs_revalidate_inode - Revalidate the inode attributes
 * @server - pointer to nfs_server struct
 * @inode - pointer to inode struct
 *
 * Updates inode attribute information by retrieving the data from the server.
 */
int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
	if (!(NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATTR)
			&& !nfs_attribute_timeout(inode))
		return NFS_STALE(inode) ? -ESTALE : 0;
	return __nfs_revalidate_inode(server, inode);
}

/**
 * nfs_revalidate_mapping - Revalidate the pagecache
 * @inode - pointer to host inode
 * @mapping - pointer to mapping
 */
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int ret = 0;

	if (NFS_STALE(inode))
		ret = -ESTALE;
	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
			|| nfs_attribute_timeout(inode))
		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);

	if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
		nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
		if (S_ISREG(inode->i_mode))
			nfs_sync_mapping(mapping);
		invalidate_inode_pages2(mapping);

		spin_lock(&inode->i_lock);
		nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
		if (S_ISDIR(inode->i_mode)) {
			memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
			/* This ensures we revalidate child dentries */
			nfsi->cache_change_attribute = jiffies;
		}
		spin_unlock(&inode->i_lock);

		dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
				inode->i_sb->s_id,
				(long long)NFS_FILEID(inode));
	}
	return ret;
}

/**
 * nfs_begin_data_update
 * @inode - pointer to inode
 * Declare that a set of operations will update file data on the server
 */
void nfs_begin_data_update(struct inode *inode)
{
	atomic_inc(&NFS_I(inode)->data_updates);
}

/**
 * nfs_end_data_update
 * @inode - pointer to inode
 * Declare end of the operations that will update file data
 * This will mark the inode as immediately needing revalidation
 * of its attribute cache.
 */
void nfs_end_data_update(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	if (!nfs_have_delegation(inode, FMODE_READ)) {
		/* Directories and symlinks: invalidate page cache */
		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
			spin_lock(&inode->i_lock);
			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
			spin_unlock(&inode->i_lock);
		}
	}
	nfsi->cache_change_attribute = jiffies;
	atomic_dec(&nfsi->data_updates);
}

static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	/* If we have atomic WCC data, we may update some attributes */
	if ((fattr->valid & NFS_ATTR_WCC) != 0) {
		if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
			memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
			nfsi->cache_change_attribute = jiffies;
		}
		if (timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
			memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
			nfsi->cache_change_attribute = jiffies;
		}
		if (inode->i_size == fattr->pre_size && nfsi->npages == 0) {
			inode->i_size = fattr->size;
			nfsi->cache_change_attribute = jiffies;
		}
	}
}

/**
 * nfs_check_inode_attributes - verify consistency of the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * Verifies the attribute cache. If we have just changed the attributes,
 * so that fattr carries weak cache consistency data, then it may
 * also update the ctime/mtime/change_attribute.
 */
static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	loff_t cur_size, new_isize;
	int data_unstable;


	/* Has the inode gone and changed behind our back? */
	if (nfsi->fileid != fattr->fileid
			|| (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
		return -EIO;
	}

	/* Are we in the process of updating data on the server? */
	data_unstable = nfs_caches_unstable(inode);

	/* Do atomic weak cache consistency updates */
	nfs_wcc_update_inode(inode, fattr);

	if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
			nfsi->change_attr != fattr->change_attr)
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;

	/* Verify a few of the more important attributes */
	if (!timespec_equal(&inode->i_mtime, &fattr->mtime))
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;

	cur_size = i_size_read(inode);
 	new_isize = nfs_size_to_loff_t(fattr->size);
	if (cur_size != new_isize && nfsi->npages == 0)
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;

	/* Have any file permissions changed? */
	if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)
			|| inode->i_uid != fattr->uid
			|| inode->i_gid != fattr->gid)
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;

	/* Has the link count changed? */
	if (inode->i_nlink != fattr->nlink)
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR;

	if (!timespec_equal(&inode->i_atime, &fattr->atime))
		nfsi->cache_validity |= NFS_INO_INVALID_ATIME;

	nfsi->read_cache_jiffies = fattr->time_start;
	return 0;
}

/**
 * nfs_refresh_inode - try to update the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * Check that an RPC call that returned attributes has not overlapped with
 * other recent updates of the inode metadata, then decide whether it is
 * safe to do a full update of the inode attributes, or whether just to
 * call nfs_check_inode_attributes.
 */
int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int status;

	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
		return 0;
	spin_lock(&inode->i_lock);
	if (time_after(fattr->time_start, nfsi->last_updated))
		status = nfs_update_inode(inode, fattr);
	else
		status = nfs_check_inode_attributes(inode, fattr);

	spin_unlock(&inode->i_lock);
	return status;
}

/**
 * nfs_post_op_update_inode - try to update the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * After an operation that has changed the inode metadata, mark the
 * attribute cache as being invalid, then try to update it.
 */
int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int status = 0;

	spin_lock(&inode->i_lock);
	if (unlikely((fattr->valid & NFS_ATTR_FATTR) == 0)) {
		nfsi->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
		goto out;
	}
	status = nfs_update_inode(inode, fattr);
out:
	spin_unlock(&inode->i_lock);
	return status;
}

/*
 * Many nfs protocol calls return the new file attributes after
 * an operation.  Here we update the inode to reflect the state
 * of the server's inode.
 *
 * This is a bit tricky because we have to make sure all dirty pages
 * have been sent off to the server before calling invalidate_inode_pages.
 * To make sure no other process adds more write requests while we try
 * our best to flush them, we make them sleep during the attribute refresh.
 *
 * A very similar scenario holds for the dir cache.
 */
static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_server *server;
	struct nfs_inode *nfsi = NFS_I(inode);
	loff_t cur_isize, new_isize;
	unsigned int	invalid = 0;
	int data_stable;

	dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
			__FUNCTION__, inode->i_sb->s_id, inode->i_ino,
			atomic_read(&inode->i_count), fattr->valid);

	if (nfsi->fileid != fattr->fileid)
		goto out_fileid;

	/*
	 * Make sure the inode's type hasn't changed.
	 */
	if ((inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
		goto out_changed;

	server = NFS_SERVER(inode);
	/* Update the fsid if and only if this is the root directory */
	if (inode == inode->i_sb->s_root->d_inode
			&& !nfs_fsid_equal(&server->fsid, &fattr->fsid))
		server->fsid = fattr->fsid;

	/*
	 * Update the read time so we don't revalidate too often.
	 */
	nfsi->read_cache_jiffies = fattr->time_start;
	nfsi->last_updated = jiffies;

	/* Are we racing with known updates of the metadata on the server? */
	data_stable = nfs_verify_change_attribute(inode, fattr->time_start);
	if (data_stable)
		nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATIME);

	/* Do atomic weak cache consistency updates */
	nfs_wcc_update_inode(inode, fattr);

	/* Check if our cached file size is stale */
 	new_isize = nfs_size_to_loff_t(fattr->size);
	cur_isize = i_size_read(inode);
	if (new_isize != cur_isize) {
		/* Do we perhaps have any outstanding writes? */
		if (nfsi->npages == 0) {
			/* No, but did we race with nfs_end_data_update()? */
			if (data_stable) {
				inode->i_size = new_isize;
				invalid |= NFS_INO_INVALID_DATA;
			}
			invalid |= NFS_INO_INVALID_ATTR;
		} else if (new_isize > cur_isize) {
			inode->i_size = new_isize;
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
		}
		nfsi->cache_change_attribute = jiffies;
		dprintk("NFS: isize change on server for file %s/%ld\n",
				inode->i_sb->s_id, inode->i_ino);
	}

	/* Check if the mtime agrees */
	if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
		dprintk("NFS: mtime change on server for file %s/%ld\n",
				inode->i_sb->s_id, inode->i_ino);
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
		nfsi->cache_change_attribute = jiffies;
	}

	/* If ctime has changed we should definitely clear access+acl caches */
	if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
		invalid |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
		nfsi->cache_change_attribute = jiffies;
	}
	memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));

	if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO) ||
	    inode->i_uid != fattr->uid ||
	    inode->i_gid != fattr->gid)
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;

	inode->i_mode = fattr->mode;
	inode->i_nlink = fattr->nlink;
	inode->i_uid = fattr->uid;
	inode->i_gid = fattr->gid;

	if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
		/*
		 * report the blocks in 512byte units
		 */
		inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
		inode->i_blksize = inode->i_sb->s_blocksize;
 	} else {
 		inode->i_blocks = fattr->du.nfs2.blocks;
 		inode->i_blksize = fattr->du.nfs2.blocksize;
 	}

	if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
			nfsi->change_attr != fattr->change_attr) {
		dprintk("NFS: change_attr change on server for file %s/%ld\n",
				inode->i_sb->s_id, inode->i_ino);
		nfsi->change_attr = fattr->change_attr;
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
		nfsi->cache_change_attribute = jiffies;
	}

	/* Update attrtimeo value if we're out of the unstable period */
	if (invalid & NFS_INO_INVALID_ATTR) {
		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
		nfsi->attrtimeo_timestamp = jiffies;
	} else if (time_after(jiffies, nfsi->attrtimeo_timestamp+nfsi->attrtimeo)) {
		if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
			nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
		nfsi->attrtimeo_timestamp = jiffies;
	}
	/* Don't invalidate the data if we were to blame */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
				|| S_ISLNK(inode->i_mode)))
		invalid &= ~NFS_INO_INVALID_DATA;
	if (data_stable)
		invalid &= ~(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME|NFS_INO_REVAL_PAGECACHE);
	if (!nfs_have_delegation(inode, FMODE_READ))
		nfsi->cache_validity |= invalid;

	return 0;
 out_changed:
	/*
	 * Big trouble! The inode has become a different object.
	 */
#ifdef NFS_PARANOIA
	printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
			__FUNCTION__, inode->i_ino, inode->i_mode, fattr->mode);
#endif
 out_err:
	/*
	 * No need to worry about unhashing the dentry, as the
	 * lookup validation will know that the inode is bad.
	 * (But we fall through to invalidate the caches.)
	 */
	nfs_invalidate_inode(inode);
	return -ESTALE;

 out_fileid:
	printk(KERN_ERR "NFS: server %s error: fileid changed\n"
		"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
		NFS_SERVER(inode)->hostname, inode->i_sb->s_id,
		(long long)nfsi->fileid, (long long)fattr->fileid);
	goto out_err;
}

/*
 * File system information
 */

/*
 * nfs_path - reconstruct the path given an arbitrary dentry
 * @base - arbitrary string to prepend to the path
 * @dentry - pointer to dentry
 * @buffer - result buffer
 * @buflen - length of buffer
 *
 * Helper function for constructing the path from the
 * root dentry to an arbitrary hashed dentry.
 *
 * This is mainly for use in figuring out the path on the
 * server side when automounting on top of an existing partition.
 */
static char *nfs_path(const char *base, const struct dentry *dentry,
		      char *buffer, ssize_t buflen)
{
	char *end = buffer+buflen;
	int namelen;

	*--end = '\0';
	buflen--;
	spin_lock(&dcache_lock);
	while (!IS_ROOT(dentry)) {
		namelen = dentry->d_name.len;
		buflen -= namelen + 1;
		if (buflen < 0)
			goto Elong;
		end -= namelen;
		memcpy(end, dentry->d_name.name, namelen);
		*--end = '/';
		dentry = dentry->d_parent;
	}
	spin_unlock(&dcache_lock);
	namelen = strlen(base);
	/* Strip off excess slashes in base string */
	while (namelen > 0 && base[namelen - 1] == '/')
		namelen--;
	buflen -= namelen;
	if (buflen < 0)
		goto Elong;
	end -= namelen;
	memcpy(end, base, namelen);
	return end;
Elong:
	return ERR_PTR(-ENAMETOOLONG);
}

struct nfs_clone_mount {
	const struct super_block *sb;
	const struct dentry *dentry;
	struct nfs_fh *fh;
	struct nfs_fattr *fattr;
	char *hostname;
	char *mnt_path;
	struct sockaddr_in *addr;
	rpc_authflavor_t authflavor;
};

static struct super_block *nfs_clone_generic_sb(struct nfs_clone_mount *data,
		struct super_block *(*fill_sb)(struct nfs_server *, struct nfs_clone_mount *),
		struct nfs_server *(*fill_server)(struct super_block *, struct nfs_clone_mount *))
{
	struct nfs_server *server;
	struct nfs_server *parent = NFS_SB(data->sb);
	struct super_block *sb = ERR_PTR(-EINVAL);
	void *err = ERR_PTR(-ENOMEM);
	char *hostname;
	int len;

	server = kmalloc(sizeof(struct nfs_server), GFP_KERNEL);
	if (server == NULL)
		goto out_err;
	memcpy(server, parent, sizeof(*server));
	hostname = (data->hostname != NULL) ? data->hostname : parent->hostname;
	len = strlen(hostname) + 1;
	server->hostname = kmalloc(len, GFP_KERNEL);
	if (server->hostname == NULL)
		goto free_server;
	memcpy(server->hostname, hostname, len);
	if (rpciod_up() != 0)
		goto free_hostname;

	sb = fill_sb(server, data);
	if (IS_ERR((err = sb)) || sb->s_root)
		goto kill_rpciod;

	server = fill_server(sb, data);
	if (IS_ERR((err = server)))
		goto out_deactivate;
	return sb;
out_deactivate:
	up_write(&sb->s_umount);
	deactivate_super(sb);
	return (struct super_block *)err;
kill_rpciod:
	rpciod_down();
free_hostname:
	kfree(server->hostname);
free_server:
	kfree(server);
out_err:
	return (struct super_block *)err;
}

static int nfs_set_super(struct super_block *s, void *data)
{
	s->s_fs_info = data;
	return set_anon_super(s, data);
}
 
static int nfs_compare_super(struct super_block *sb, void *data)
{
	struct nfs_server *server = data;
	struct nfs_server *old = NFS_SB(sb);

	if (old->addr.sin_addr.s_addr != server->addr.sin_addr.s_addr)
		return 0;
	if (old->addr.sin_port != server->addr.sin_port)
		return 0;
	return !nfs_compare_fh(&old->fh, &server->fh);
}

static struct super_block *nfs_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data)
{
	int error;
	struct nfs_server *server = NULL;
	struct super_block *s;
	struct nfs_fh *root;
	struct nfs_mount_data *data = raw_data;

	s = ERR_PTR(-EINVAL);
	if (data == NULL) {
		dprintk("%s: missing data argument\n", __FUNCTION__);
		goto out_err;
	}
	if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) {
		dprintk("%s: bad mount version\n", __FUNCTION__);
		goto out_err;
	}
	switch (data->version) {
		case 1:
			data->namlen = 0;
		case 2:
			data->bsize  = 0;
		case 3:
			if (data->flags & NFS_MOUNT_VER3) {
				dprintk("%s: mount structure version %d does not support NFSv3\n",
						__FUNCTION__,
						data->version);
				goto out_err;
			}
			data->root.size = NFS2_FHSIZE;
			memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
		case 4:
			if (data->flags & NFS_MOUNT_SECFLAVOUR) {
				dprintk("%s: mount structure version %d does not support strong security\n",
						__FUNCTION__,
						data->version);
				goto out_err;
			}
		case 5:
			memset(data->context, 0, sizeof(data->context));
	}
#ifndef CONFIG_NFS_V3
	/* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */
	s = ERR_PTR(-EPROTONOSUPPORT);
	if (data->flags & NFS_MOUNT_VER3) {
		dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__);
		goto out_err;
	}
#endif /* CONFIG_NFS_V3 */

	s = ERR_PTR(-ENOMEM);
	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
	if (!server)
		goto out_err;
	/* Zero out the NFS state stuff */
	init_nfsv4_state(server);
	server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);

	root = &server->fh;
	if (data->flags & NFS_MOUNT_VER3)
		root->size = data->root.size;
	else
		root->size = NFS2_FHSIZE;
	s = ERR_PTR(-EINVAL);
	if (root->size > sizeof(root->data)) {
		dprintk("%s: invalid root filehandle\n", __FUNCTION__);
		goto out_err;
	}
	memcpy(root->data, data->root.data, root->size);

	/* We now require that the mount process passes the remote address */
	memcpy(&server->addr, &data->addr, sizeof(server->addr));
	if (server->addr.sin_addr.s_addr == INADDR_ANY) {
		dprintk("%s: mount program didn't pass remote address!\n",
				__FUNCTION__);
		goto out_err;
	}

	/* Fire up rpciod if not yet running */
	s = ERR_PTR(rpciod_up());
	if (IS_ERR(s)) {
		dprintk("%s: couldn't start rpciod! Error = %ld\n",
				__FUNCTION__, PTR_ERR(s));
		goto out_err;
	}

	s = sget(fs_type, nfs_compare_super, nfs_set_super, server);
	if (IS_ERR(s) || s->s_root)
		goto out_rpciod_down;

	s->s_flags = flags;

	error = nfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
	if (error) {
		up_write(&s->s_umount);
		deactivate_super(s);
		return ERR_PTR(error);
	}
	s->s_flags |= MS_ACTIVE;
	return s;
out_rpciod_down:
	rpciod_down();
out_err:
	kfree(server);
	return s;
}

static void nfs_kill_super(struct super_block *s)
{
	struct nfs_server *server = NFS_SB(s);

	kill_anon_super(s);

	if (!IS_ERR(server->client))
		rpc_shutdown_client(server->client);
	if (!IS_ERR(server->client_sys))
		rpc_shutdown_client(server->client_sys);
	if (!IS_ERR(server->client_acl))
		rpc_shutdown_client(server->client_acl);

	if (!(server->flags & NFS_MOUNT_NONLM))
		lockd_down();	/* release rpc.lockd */

	rpciod_down();		/* release rpciod */

	nfs_free_iostats(server->io_stats);
	kfree(server->hostname);
	kfree(server);
	nfs_release_automount_timer();
}

static struct file_system_type nfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs",
	.get_sb		= nfs_get_sb,
	.kill_sb	= nfs_kill_super,
	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

static struct super_block *nfs_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
{
	struct super_block *sb;

	server->fsid = data->fattr->fsid;
	nfs_copy_fh(&server->fh, data->fh);
	sb = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
	if (!IS_ERR(sb) && sb->s_root == NULL && !(server->flags & NFS_MOUNT_NONLM))
		lockd_up();
	return sb;
}

static struct nfs_server *nfs_clone_server(struct super_block *sb, struct nfs_clone_mount *data)
{
	struct nfs_server *server = NFS_SB(sb);
	struct nfs_server *parent = NFS_SB(data->sb);
	struct inode *root_inode;
	struct nfs_fsinfo fsinfo;
	void *err = ERR_PTR(-ENOMEM);

	sb->s_op = data->sb->s_op;
	sb->s_blocksize = data->sb->s_blocksize;
	sb->s_blocksize_bits = data->sb->s_blocksize_bits;
	sb->s_maxbytes = data->sb->s_maxbytes;

	server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
	server->io_stats = nfs_alloc_iostats();
	if (server->io_stats == NULL)
		goto out;

	server->client = rpc_clone_client(parent->client);
	if (IS_ERR((err = server->client)))
		goto out;

	if (!IS_ERR(parent->client_sys)) {
		server->client_sys = rpc_clone_client(parent->client_sys);
		if (IS_ERR((err = server->client_sys)))
			goto out;
	}
	if (!IS_ERR(parent->client_acl)) {
		server->client_acl = rpc_clone_client(parent->client_acl);
		if (IS_ERR((err = server->client_acl)))
			goto out;
	}
	root_inode = nfs_fhget(sb, data->fh, data->fattr);
	if (!root_inode)
		goto out;
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root)
		goto out_put_root;
	fsinfo.fattr = data->fattr;
	if (NFS_PROTO(root_inode)->fsinfo(server, data->fh, &fsinfo) == 0)
		nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);
	sb->s_root->d_op = server->rpc_ops->dentry_ops;
	sb->s_flags |= MS_ACTIVE;
	return server;
out_put_root:
	iput(root_inode);
out:
	return err;
}

static struct super_block *nfs_clone_nfs_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data)
{
	struct nfs_clone_mount *data = raw_data;
	return nfs_clone_generic_sb(data, nfs_clone_sb, nfs_clone_server);
}

static struct file_system_type clone_nfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs",