rgrp.c

linux 内核源代码

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2007 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/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "lops.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "ops_file.h"
#include "util.h"
#include "log.h"
#include "inode.h"

#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)

/*
 * These routines are used by the resource group routines (rgrp.c)
 * to keep track of block allocation.  Each block is represented by two
 * bits.  So, each byte represents GFS2_NBBY (i.e. 4) blocks.
 *
 * 0 = Free
 * 1 = Used (not metadata)
 * 2 = Unlinked (still in use) inode
 * 3 = Used (metadata)
 */

static const char valid_change[16] = {
	        /* current */
	/* n */ 0, 1, 1, 1,
	/* e */ 1, 0, 0, 0,
	/* w */ 0, 0, 0, 1,
	        1, 0, 0, 0
};

static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
                        unsigned char old_state, unsigned char new_state);

/**
 * gfs2_setbit - Set a bit in the bitmaps
 * @buffer: the buffer that holds the bitmaps
 * @buflen: the length (in bytes) of the buffer
 * @block: the block to set
 * @new_state: the new state of the block
 *
 */

static void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
			unsigned int buflen, u32 block,
			unsigned char new_state)
{
	unsigned char *byte, *end, cur_state;
	unsigned int bit;

	byte = buffer + (block / GFS2_NBBY);
	bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
	end = buffer + buflen;

	gfs2_assert(rgd->rd_sbd, byte < end);

	cur_state = (*byte >> bit) & GFS2_BIT_MASK;

	if (valid_change[new_state * 4 + cur_state]) {
		*byte ^= cur_state << bit;
		*byte |= new_state << bit;
	} else
		gfs2_consist_rgrpd(rgd);
}

/**
 * gfs2_testbit - test a bit in the bitmaps
 * @buffer: the buffer that holds the bitmaps
 * @buflen: the length (in bytes) of the buffer
 * @block: the block to read
 *
 */

static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
				  unsigned int buflen, u32 block)
{
	unsigned char *byte, *end, cur_state;
	unsigned int bit;

	byte = buffer + (block / GFS2_NBBY);
	bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
	end = buffer + buflen;

	gfs2_assert(rgd->rd_sbd, byte < end);

	cur_state = (*byte >> bit) & GFS2_BIT_MASK;

	return cur_state;
}

/**
 * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing
 *       a block in a given allocation state.
 * @buffer: the buffer that holds the bitmaps
 * @buflen: the length (in bytes) of the buffer
 * @goal: start search at this block's bit-pair (within @buffer)
 * @old_state: GFS2_BLKST_XXX the state of the block we're looking for.
 *
 * Scope of @goal and returned block number is only within this bitmap buffer,
 * not entire rgrp or filesystem.  @buffer will be offset from the actual
 * beginning of a bitmap block buffer, skipping any header structures.
 *
 * Return: the block number (bitmap buffer scope) that was found
 */

static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
			    unsigned int buflen, u32 goal,
			    unsigned char old_state)
{
	unsigned char *byte, *end, alloc;
	u32 blk = goal;
	unsigned int bit;

	byte = buffer + (goal / GFS2_NBBY);
	bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE;
	end = buffer + buflen;
	alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0;

	while (byte < end) {
		/* If we're looking for a free block we can eliminate all
		   bitmap settings with 0x55, which represents four data
		   blocks in a row.  If we're looking for a data block, we can
		   eliminate 0x00 which corresponds to four free blocks. */
		if ((*byte & 0x55) == alloc) {
			blk += (8 - bit) >> 1;

			bit = 0;
			byte++;

			continue;
		}

		if (((*byte >> bit) & GFS2_BIT_MASK) == old_state)
			return blk;

		bit += GFS2_BIT_SIZE;
		if (bit >= 8) {
			bit = 0;
			byte++;
		}

		blk++;
	}

	return BFITNOENT;
}

/**
 * gfs2_bitcount - count the number of bits in a certain state
 * @buffer: the buffer that holds the bitmaps
 * @buflen: the length (in bytes) of the buffer
 * @state: the state of the block we're looking for
 *
 * Returns: The number of bits
 */

static u32 gfs2_bitcount(struct gfs2_rgrpd *rgd, unsigned char *buffer,
			      unsigned int buflen, unsigned char state)
{
	unsigned char *byte = buffer;
	unsigned char *end = buffer + buflen;
	unsigned char state1 = state << 2;
	unsigned char state2 = state << 4;
	unsigned char state3 = state << 6;
	u32 count = 0;

	for (; byte < end; byte++) {
		if (((*byte) & 0x03) == state)
			count++;
		if (((*byte) & 0x0C) == state1)
			count++;
		if (((*byte) & 0x30) == state2)
			count++;
		if (((*byte) & 0xC0) == state3)
			count++;
	}

	return count;
}

/**
 * gfs2_rgrp_verify - Verify that a resource group is consistent
 * @sdp: the filesystem
 * @rgd: the rgrp
 *
 */

void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_bitmap *bi = NULL;
	u32 length = rgd->rd_length;
	u32 count[4], tmp;
	int buf, x;

	memset(count, 0, 4 * sizeof(u32));

	/* Count # blocks in each of 4 possible allocation states */
	for (buf = 0; buf < length; buf++) {
		bi = rgd->rd_bits + buf;
		for (x = 0; x < 4; x++)
			count[x] += gfs2_bitcount(rgd,
						  bi->bi_bh->b_data +
						  bi->bi_offset,
						  bi->bi_len, x);
	}

	if (count[0] != rgd->rd_rg.rg_free) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "free data mismatch:  %u != %u\n",
			       count[0], rgd->rd_rg.rg_free);
		return;
	}

	tmp = rgd->rd_data -
		rgd->rd_rg.rg_free -
		rgd->rd_rg.rg_dinodes;
	if (count[1] + count[2] != tmp) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "used data mismatch:  %u != %u\n",
			       count[1], tmp);
		return;
	}

	if (count[3] != rgd->rd_rg.rg_dinodes) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "used metadata mismatch:  %u != %u\n",
			       count[3], rgd->rd_rg.rg_dinodes);
		return;
	}

	if (count[2] > count[3]) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "unlinked inodes > inodes:  %u\n",
			       count[2]);
		return;
	}

}

static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
{
	u64 first = rgd->rd_data0;
	u64 last = first + rgd->rd_data;
	return first <= block && block < last;
}

/**
 * gfs2_blk2rgrpd - Find resource group for a given data/meta block number
 * @sdp: The GFS2 superblock
 * @n: The data block number
 *
 * Returns: The resource group, or NULL if not found
 */

struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
{
	struct gfs2_rgrpd *rgd;

	spin_lock(&sdp->sd_rindex_spin);

	list_for_each_entry(rgd, &sdp->sd_rindex_mru_list, rd_list_mru) {
		if (rgrp_contains_block(rgd, blk)) {
			list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
			spin_unlock(&sdp->sd_rindex_spin);
			return rgd;
		}
	}

	spin_unlock(&sdp->sd_rindex_spin);

	return NULL;
}

/**
 * gfs2_rgrpd_get_first - get the first Resource Group in the filesystem
 * @sdp: The GFS2 superblock
 *
 * Returns: The first rgrp in the filesystem
 */

struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
{
	gfs2_assert(sdp, !list_empty(&sdp->sd_rindex_list));
	return list_entry(sdp->sd_rindex_list.next, struct gfs2_rgrpd, rd_list);
}

/**
 * gfs2_rgrpd_get_next - get the next RG
 * @rgd: A RG
 *
 * Returns: The next rgrp
 */

struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
{
	if (rgd->rd_list.next == &rgd->rd_sbd->sd_rindex_list)
		return NULL;
	return list_entry(rgd->rd_list.next, struct gfs2_rgrpd, rd_list);
}

static void clear_rgrpdi(struct gfs2_sbd *sdp)
{
	struct list_head *head;
	struct gfs2_rgrpd *rgd;
	struct gfs2_glock *gl;

	spin_lock(&sdp->sd_rindex_spin);
	sdp->sd_rindex_forward = NULL;
	head = &sdp->sd_rindex_recent_list;
	while (!list_empty(head)) {
		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_recent);
		list_del(&rgd->rd_recent);
	}
	spin_unlock(&sdp->sd_rindex_spin);

	head = &sdp->sd_rindex_list;
	while (!list_empty(head)) {
		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_list);
		gl = rgd->rd_gl;

		list_del(&rgd->rd_list);
		list_del(&rgd->rd_list_mru);

		if (gl) {
			gl->gl_object = NULL;
			gfs2_glock_put(gl);
		}

		kfree(rgd->rd_bits);
		kfree(rgd);
	}
}

void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
{
	mutex_lock(&sdp->sd_rindex_mutex);
	clear_rgrpdi(sdp);
	mutex_unlock(&sdp->sd_rindex_mutex);
}

static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd)
{
	printk(KERN_INFO "  ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
	printk(KERN_INFO "  ri_length = %u\n", rgd->rd_length);
	printk(KERN_INFO "  ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0);
	printk(KERN_INFO "  ri_data = %u\n", rgd->rd_data);
	printk(KERN_INFO "  ri_bitbytes = %u\n", rgd->rd_bitbytes);
}

/**
 * gfs2_compute_bitstructs - Compute the bitmap sizes
 * @rgd: The resource group descriptor
 *
 * Calculates bitmap descriptors, one for each block that contains bitmap data
 *
 * Returns: errno
 */

static int compute_bitstructs(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_bitmap *bi;
	u32 length = rgd->rd_length; /* # blocks in hdr & bitmap */
	u32 bytes_left, bytes;
	int x;

	if (!length)
		return -EINVAL;

	rgd->rd_bits = kcalloc(length, sizeof(struct gfs2_bitmap), GFP_NOFS);
	if (!rgd->rd_bits)
		return -ENOMEM;

	bytes_left = rgd->rd_bitbytes;

	for (x = 0; x < length; x++) {
		bi = rgd->rd_bits + x;

		/* small rgrp; bitmap stored completely in header block */
		if (length == 1) {
			bytes = bytes_left;
			bi->bi_offset = sizeof(struct gfs2_rgrp);
			bi->bi_start = 0;
			bi->bi_len = bytes;
		/* header block */
		} else if (x == 0) {
			bytes = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_rgrp);
			bi->bi_offset = sizeof(struct gfs2_rgrp);
			bi->bi_start = 0;
			bi->bi_len = bytes;
		/* last block */
		} else if (x + 1 == length) {
			bytes = bytes_left;
			bi->bi_offset = sizeof(struct gfs2_meta_header);
			bi->bi_start = rgd->rd_bitbytes - bytes_left;
			bi->bi_len = bytes;
		/* other blocks */
		} else {
			bytes = sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_meta_header);
			bi->bi_offset = sizeof(struct gfs2_meta_header);
			bi->bi_start = rgd->rd_bitbytes - bytes_left;
			bi->bi_len = bytes;
		}

		bytes_left -= bytes;
	}

	if (bytes_left) {
		gfs2_consist_rgrpd(rgd);
		return -EIO;
	}
	bi = rgd->rd_bits + (length - 1);
	if ((bi->bi_start + bi->bi_len) * GFS2_NBBY != rgd->rd_data) {
		if (gfs2_consist_rgrpd(rgd)) {
			gfs2_rindex_print(rgd);
			fs_err(sdp, "start=%u len=%u offset=%u\n",
			       bi->bi_start, bi->bi_len, bi->bi_offset);
		}
		return -EIO;
	}

	return 0;
}

/**
 * gfs2_ri_total - Total up the file system space, according to the rindex.
 *
 */
u64 gfs2_ri_total(struct gfs2_sbd *sdp)
{
	u64 total_data = 0;	
	struct inode *inode = sdp->sd_rindex;
	struct gfs2_inode *ip = GFS2_I(inode);
	char buf[sizeof(struct gfs2_rindex)];
	struct file_ra_state ra_state;
	int error, rgrps;

	mutex_lock(&sdp->sd_rindex_mutex);
	file_ra_state_init(&ra_state, inode->i_mapping);
	for (rgrps = 0;; rgrps++) {
		loff_t pos = rgrps * sizeof(struct gfs2_rindex);

		if (pos + sizeof(struct gfs2_rindex) >= ip->i_di.di_size)
			break;
		error = gfs2_internal_read(ip, &ra_state, buf, &pos,
					   sizeof(struct gfs2_rindex));
		if (error != sizeof(struct gfs2_rindex))
			break;
		total_data += be32_to_cpu(((struct gfs2_rindex *)buf)->ri_data);
	}
	mutex_unlock(&sdp->sd_rindex_mutex);
	return total_data;
}

static void gfs2_rindex_in(struct gfs2_rgrpd *rgd, const void *buf)
{
	const struct gfs2_rindex *str = buf;

	rgd->rd_addr = be64_to_cpu(str->ri_addr);
	rgd->rd_length = be32_to_cpu(str->ri_length);
	rgd->rd_data0 = be64_to_cpu(str->ri_data0);
	rgd->rd_data = be32_to_cpu(str->ri_data);
	rgd->rd_bitbytes = be32_to_cpu(str->ri_bitbytes);
}

/**
 * read_rindex_entry - Pull in a new resource index entry from the disk
 * @gl: The glock covering the rindex inode
 *
 * Returns: 0 on success, error code otherwise
 */

static int read_rindex_entry(struct gfs2_inode *ip,
			     struct file_ra_state *ra_state)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex);
	char buf[sizeof(struct gfs2_rindex)];
	int error;
	struct gfs2_rgrpd *rgd;

	error = gfs2_internal_read(ip, ra_state, buf, &pos,
				   sizeof(struct gfs2_rindex));
	if (!error)
		return 0;
	if (error != sizeof(struct gfs2_rindex)) {
		if (error > 0)
			error = -EIO;
		return error;
	}

	rgd = kzalloc(sizeof(struct gfs2_rgrpd), GFP_NOFS);
	error = -ENOMEM;
	if (!rgd)
		return error;

	mutex_init(&rgd->rd_mutex);
	lops_init_le(&rgd->rd_le, &gfs2_rg_lops);
	rgd->rd_sbd = sdp;

	list_add_tail(&rgd->rd_list, &sdp->sd_rindex_list);
	list_add_tail(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);

	gfs2_rindex_in(rgd, buf);
	error = compute_bitstructs(rgd);
	if (error)
		return error;

	error = gfs2_glock_get(sdp, rgd->rd_addr,
			       &gfs2_rgrp_glops, CREATE, &rgd->rd_gl);
	if (error)
		return error;

	rgd->rd_gl->gl_object = rgd;
	rgd->rd_rg_vn = rgd->rd_gl->gl_vn - 1;
	rgd->rd_flags |= GFS2_RDF_CHECK;
	return error;
}

/**
 * gfs2_ri_update - Pull in a new resource index from the disk
 * @ip: pointer to the rindex inode
 *
 * Returns: 0 on successful update, error code otherwise
 */

static int gfs2_ri_update(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct inode *inode = &ip->i_inode;
	struct file_ra_state ra_state;
	u64 rgrp_count = ip->i_di.di_size;
	int error;

	if (do_div(rgrp_count, sizeof(struct gfs2_rindex))) {
		gfs2_consist_inode(ip);
		return -EIO;
	}

	clear_rgrpdi(sdp);

	file_ra_state_init(&ra_state, inode->i_mapping);
	for (sdp->sd_rgrps = 0; sdp->sd_rgrps < rgrp_count; sdp->sd_rgrps++) {
		error = read_rindex_entry(ip, &ra_state);
		if (error) {
			clear_rgrpdi(sdp);
			return error;
		}