dir.c

ocfs1.2.7 源码

/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * dir.c
 *
 * Creates, reads, walks and deletes directory-nodes
 *
 * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
 *
 *  Portions of this code from linux/fs/ext3/dir.c
 *
 *  Copyright (C) 1992, 1993, 1994, 1995
 *  Remy Card ([e-mail])
 *  Laboratoire MASI - Institut Blaise pascal
 *  Universite Pierre et Marie Curie (Paris VI)
 *
 *   from
 *
 *   linux/fs/minix/dir.c
 *
 *   Copyright (C) 1991, 1992 Linux Torvalds
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>

#define MLOG_MASK_PREFIX ML_NAMEI
#include <cluster/masklog.h>

#include "ocfs2.h"

#include "alloc.h"
#include "dir.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "file.h"
#include "inode.h"
#include "journal.h"
#include "namei.h"
#include "suballoc.h"
#include "uptodate.h"

#include "buffer_head_io.h"

static unsigned char ocfs2_filetype_table[] = {
	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};

static int ocfs2_extend_dir(struct ocfs2_super *osb,
			    struct inode *dir,
			    struct buffer_head *parent_fe_bh,
			    struct buffer_head **new_de_bh);
/*
 * ocfs2_readdir()
 *
 */
int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
	int error = 0;
	unsigned long offset, blk;
	int i, num, stored;
	struct buffer_head * bh, * tmp;
	struct ocfs2_dir_entry * de;
	int err;
	struct inode *inode = filp->f_dentry->d_inode;
	struct super_block * sb = inode->i_sb;
	int have_disk_lock = 0;

	mlog_entry("dirino=%"MLFu64"\n", OCFS2_I(inode)->ip_blkno);

	stored = 0;
	bh = NULL;

	error = ocfs2_meta_lock(inode, NULL, NULL, 0);
	if (error < 0) {
		if (error != -ENOENT)
			mlog_errno(error);
		/* we haven't got any yet, so propagate the error. */
		stored = error;
		goto bail;
	}
	have_disk_lock = 1;

	offset = filp->f_pos & (sb->s_blocksize - 1);

	while (!error && !stored && filp->f_pos < i_size_read(inode)) {
		blk = (filp->f_pos) >> sb->s_blocksize_bits;
		bh = ocfs2_bread(inode, blk, &err, 0);
		if (!bh) {
			mlog(ML_ERROR, "directory #%"MLFu64" contains a hole "
				       "at offset %lld\n",
			     OCFS2_I(inode)->ip_blkno,
			     filp->f_pos);
			filp->f_pos += sb->s_blocksize - offset;
			continue;
		}

		/*
		 * Do the readahead (8k)
		 */
		if (!offset) {
			for (i = 16 >> (sb->s_blocksize_bits - 9), num = 0;
			     i > 0; i--) {
				tmp = ocfs2_bread(inode, ++blk, &err, 1);
				if (tmp)
					brelse(tmp);
			}
		}

revalidate:
		/* If the dir block has changed since the last call to
		 * readdir(2), then we might be pointing to an invalid
		 * dirent right now.  Scan from the start of the block
		 * to make sure. */
		if (filp->f_version != inode->i_version) {
			for (i = 0; i < sb->s_blocksize && i < offset; ) {
				de = (struct ocfs2_dir_entry *) (bh->b_data + i);
				/* It's too expensive to do a full
				 * dirent test each time round this
				 * loop, but we do have to test at
				 * least that it is non-zero.  A
				 * failure will be detected in the
				 * dirent test below. */
				if (le16_to_cpu(de->rec_len) <
				    OCFS2_DIR_REC_LEN(1))
					break;
				i += le16_to_cpu(de->rec_len);
			}
			offset = i;
			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
				| offset;
			filp->f_version = inode->i_version;
		}

		while (!error && filp->f_pos < i_size_read(inode)
		       && offset < sb->s_blocksize) {
			de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
			if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
				/* On error, skip the f_pos to the
				   next block. */
				filp->f_pos = (filp->f_pos |
					       (sb->s_blocksize - 1)) + 1;
				brelse(bh);
				goto bail;
			}
			offset += le16_to_cpu(de->rec_len);
			if (le64_to_cpu(de->inode)) {
				/* We might block in the next section
				 * if the data destination is
				 * currently swapped out.  So, use a
				 * version stamp to detect whether or
				 * not the directory has been modified
				 * during the copy operation.
				 */
				unsigned long version = filp->f_version;
				unsigned char d_type = DT_UNKNOWN;

				if (de->file_type < OCFS2_FT_MAX)
					d_type = ocfs2_filetype_table[de->file_type];
				error = filldir(dirent, de->name,
						de->name_len,
						filp->f_pos,
						ino_from_blkno(sb, le64_to_cpu(de->inode)),
						d_type);
				if (error)
					break;
				if (version != filp->f_version)
					goto revalidate;
				stored ++;
			}
			filp->f_pos += le16_to_cpu(de->rec_len);
		}
		offset = 0;
		brelse(bh);
	}

	stored = 0;
bail:
	if (have_disk_lock)
		ocfs2_meta_unlock(inode, 0);

	mlog_exit(stored);

	return stored;
}

/*
 * NOTE: this should always be called with parent dir i_mutex taken.
 */
int ocfs2_find_files_on_disk(const char *name,
			     int namelen,
			     u64 *blkno,
			     struct inode *inode,
			     struct buffer_head **dirent_bh,
			     struct ocfs2_dir_entry **dirent)
{
	int status = -ENOENT;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	mlog_entry("(osb=%p, parent=%"MLFu64", name='%.*s', blkno=%p, "
		   "inode=%p)\n",
		   osb, OCFS2_I(inode)->ip_blkno, namelen, name, blkno, inode);

	*dirent_bh = ocfs2_find_entry(name, namelen, inode, dirent);
	if (!*dirent_bh || !*dirent) {
		status = -ENOENT;
		goto leave;
	}

	*blkno = le64_to_cpu((*dirent)->inode);

	status = 0;
leave:
	if (status < 0) {
		*dirent = NULL;
		if (*dirent_bh) {
			brelse(*dirent_bh);
			*dirent_bh = NULL;
		}
	}

	mlog_exit(status);
	return status;
}

/* Check for a name within a directory.
 *
 * Return 0 if the name does not exist
 * Return -EEXIST if the directory contains the name
 *
 * Callers should have i_mutex + a cluster lock on dir
 */
int ocfs2_check_dir_for_entry(struct inode *dir,
			      const char *name,
			      int namelen)
{
	int ret;
	struct buffer_head *dirent_bh = NULL;
	struct ocfs2_dir_entry *dirent = NULL;

	mlog_entry("dir %"MLFu64", name '%.*s'\n", OCFS2_I(dir)->ip_blkno,
		   namelen, name);

	ret = -EEXIST;
	dirent_bh = ocfs2_find_entry(name, namelen, dir, &dirent);
	if (dirent_bh)
		goto bail;

	ret = 0;
bail:
	if (dirent_bh)
		brelse(dirent_bh);

	mlog_exit(ret);
	return ret;
}

/*
 * routine to check that the specified directory is empty (for rmdir)
 */
int ocfs2_empty_dir(struct inode *inode)
{
	unsigned long offset;
	struct buffer_head * bh;
	struct ocfs2_dir_entry * de, * de1;
	struct super_block * sb;
	int err;

	sb = inode->i_sb;
	if ((i_size_read(inode) <
	     (OCFS2_DIR_REC_LEN(1) + OCFS2_DIR_REC_LEN(2))) ||
	    !(bh = ocfs2_bread(inode, 0, &err, 0))) {
	    	mlog(ML_ERROR, "bad directory (dir #%"MLFu64") - "
			       "no data block\n",
		     OCFS2_I(inode)->ip_blkno);
		return 1;
	}

	de = (struct ocfs2_dir_entry *) bh->b_data;
	de1 = (struct ocfs2_dir_entry *)
			((char *)de + le16_to_cpu(de->rec_len));
	if ((le64_to_cpu(de->inode) != OCFS2_I(inode)->ip_blkno) ||
			!le64_to_cpu(de1->inode) ||
			strcmp(".", de->name) ||
			strcmp("..", de1->name)) {
	    	mlog(ML_ERROR, "bad directory (dir #%"MLFu64") - "
			       "no `.' or `..'\n",
		     OCFS2_I(inode)->ip_blkno);
		brelse(bh);
		return 1;
	}
	offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len);
	de = (struct ocfs2_dir_entry *)((char *)de1 + le16_to_cpu(de1->rec_len));
	while (offset < i_size_read(inode) ) {
		if (!bh || (void *)de >= (void *)(bh->b_data + sb->s_blocksize)) {