path: root/fs/gfs2/bmap.c

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "log.h"
#include "super.h"
#include "trans.h"
#include "dir.h"
#include "util.h"
#include "trace_gfs2.h"

/* This doesn't need to be that large as max 64 bit pointers in a 4k
 * block is 512, so __u16 is fine for that. It saves stack space to
 * keep it small.
 */
struct metapath {
	struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT];
	__u16 mp_list[GFS2_MAX_META_HEIGHT];
};

struct strip_mine {
	int sm_first;
	unsigned int sm_height;
};

/**
 * gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
 * @ip: the inode
 * @dibh: the dinode buffer
 * @block: the block number that was allocated
 * @page: The (optional) page. This is looked up if @page is NULL
 *
 * Returns: errno
 */

static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
			       u64 block, struct page *page)
{
	struct inode *inode = &ip->i_inode;
	struct buffer_head *bh;
	int release = 0;

	if (!page || page->index) {
		page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
		if (!page)
			return -ENOMEM;
		release = 1;
	}

	if (!PageUptodate(page)) {
		void *kaddr = kmap(page);
		u64 dsize = i_size_read(inode);
 
		if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
			dsize = dibh->b_size - sizeof(struct gfs2_dinode);

		memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
		memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
		kunmap(page);

		SetPageUptodate(page);
	}

	if (!page_has_buffers(page))
		create_empty_buffers(page, 1 << inode->i_blkbits,
				     (1 << BH_Uptodate));

	bh = page_buffers(page);

	if (!buffer_mapped(bh))
		map_bh(bh, inode->i_sb, block);

	set_buffer_uptodate(bh);
	if (!gfs2_is_jdata(ip))
		mark_buffer_dirty(bh);
	if (!gfs2_is_writeback(ip))
		gfs2_trans_add_data(ip->i_gl, bh);

	if (release) {
		unlock_page(page);
		page_cache_release(page);
	}

	return 0;
}

/**
 * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
 * @ip: The GFS2 inode to unstuff
 * @page: The (optional) page. This is looked up if the @page is NULL
 *
 * This routine unstuffs a dinode and returns it to a "normal" state such
 * that the height can be grown in the traditional way.
 *
 * Returns: errno
 */

int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
{
	struct buffer_head *bh, *dibh;
	struct gfs2_dinode *di;
	u64 block = 0;
	int isdir = gfs2_is_dir(ip);
	int error;

	down_write(&ip->i_rw_mutex);

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto out;

	if (i_size_read(&ip->i_inode)) {
		/* Get a free block, fill it with the stuffed data,
		   and write it out to disk */

		unsigned int n = 1;
		error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL);
		if (error)
			goto out_brelse;
		if (isdir) {
			gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
			error = gfs2_dir_get_new_buffer(ip, block, &bh);
			if (error)
				goto out_brelse;
			gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header),
					      dibh, sizeof(struct gfs2_dinode));
			brelse(bh);
		} else {
			error = gfs2_unstuffer_page(ip, dibh, block, page);
			if (error)
				goto out_brelse;
		}
	}

	/*  Set up the pointer to the new block  */

	gfs2_trans_add_meta(ip->i_gl, dibh);
	di = (struct gfs2_dinode *)dibh->b_data;
	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));

	if (i_size_read(&ip->i_inode)) {
		*(__be64 *)(di + 1) = cpu_to_be64(block);
		gfs2_add_inode_blocks(&ip->i_inode, 1);
		di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
	}

	ip->i_height = 1;
	di->di_height = cpu_to_be16(1);

out_brelse:
	brelse(dibh);
out:
	up_write(&ip->i_rw_mutex);
	return error;
}


/**
 * find_metapath - Find path through the metadata tree
 * @sdp: The superblock
 * @mp: The metapath to return the result in
 * @block: The disk block to look up
 * @height: The pre-calculated height of the metadata tree
 *
 *   This routine returns a struct metapath structure that defines a path
 *   through the metadata of inode "ip" to get to block "block".
 *
 *   Example:
 *   Given:  "ip" is a height 3 file, "offset" is 101342453, and this is a
 *   filesystem with a blocksize of 4096.
 *
 *   find_metapath() would return a struct metapath structure set to:
 *   mp_offset = 101342453, mp_height = 3, mp_list[0] = 0, mp_list[1] = 48,
 *   and mp_list[2] = 165.
 *
 *   That means that in order to get to the block containing the byte at
 *   offset 101342453, we would load the indirect block pointed to by pointer
 *   0 in the dinode.  We would then load the indirect block pointed to by
 *   pointer 48 in that indirect block.  We would then load the data block
 *   pointed to by pointer 165 in that indirect block.
 *
 *             ----------------------------------------
 *             | Dinode |                             |
 *             |        |                            4|
 *             |        |0 1 2 3 4 5                 9|
 *             |        |                            6|
 *             ----------------------------------------
 *                       |
 *                       |
 *                       V
 *             ----------------------------------------
 *             | Indirect Block                       |
 *             |                                     5|
 *             |            4 4 4 4 4 5 5            1|
 *             |0           5 6 7 8 9 0 1            2|
 *             ----------------------------------------
 *                                |
 *                                |
 *                                V
 *             ----------------------------------------
 *             | Indirect Block                       |
 *             |                         1 1 1 1 1   5|
 *             |                         6 6 6 6 6   1|
 *             |0                        3 4 5 6 7   2|
 *             ----------------------------------------
 *                                           |
 *                                           |
 *                                           V
 *             ----------------------------------------
 *             | Data block containing offset         |
 *             |            101342453                 |
 *             |                                      |
 *             |                                      |
 *             ----------------------------------------
 *
 */

static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
			  struct metapath *mp, unsigned int height)
{
	unsigned int i;

	for (i = height; i--;)
		mp->mp_list[i] = do_div(block, sdp->sd_inptrs);

}

static inline unsigned int metapath_branch_start(const struct metapath *mp)
{
	if (mp->mp_list[0] == 0)
		return 2;
	return 1;
}

/**
 * metapointer - Return pointer to start of metadata in a buffer
 * @height: The metadata height (0 = dinode)
 * @mp: The metapath
 *
 * Return a pointer to the block number of the next height of the metadata
 * tree given a buffer containing the pointer to the current height of the
 * metadata tree.
 */

static inline __be64 *metapointer(unsigned int height, const struct metapath *mp)
{
	struct buffer_head *bh = mp->mp_bh[height];
	unsigned int head_size = (height > 0) ?
		sizeof(struct gfs2_meta_header) : sizeof(struct gfs2_dinode);
	return ((__be64 *)(bh->b_data + head_size)) + mp->mp_list[height];
}

static void gfs2_metapath_ra(struct gfs2_glock *gl,
			     const struct buffer_head *bh, const __be64 *pos)
{
	struct buffer_head *rabh;
	const __be64 *endp = (const __be64 *)(bh->b_data + bh->b_size);
	const __be64 *t;

	for (t = pos; t < endp; t++) {
		if (!*t)
			continue;

		rabh = gfs2_getbuf(gl, be64_to_cpu(*t), CREATE);
		if (trylock_buffer(rabh)) {
			if (!buffer_uptodate(rabh)) {
				rabh->b_end_io = end_buffer_read_sync;
				submit_bh(READA | REQ_META, rabh);
				continue;
			}
			unlock_buffer(rabh);
		}
		brelse(rabh);
	}
}

/**
 * lookup_metapath - Walk the metadata tree to a specific point
 * @ip: The inode
 * @mp: The metapath
 *
 * Assumes that the inode's buffer has already been looked up and
 * hooked onto mp->mp_bh[0] and that the metapath has been initialised
 * by find_metapath().
 *
 * If this function encounters part of the tree which has