log.c

linux 内核源代码

/*
 * 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/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/lm_interface.h>
#include <linux/delay.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "util.h"
#include "dir.h"

#define PULL 1

/**
 * gfs2_struct2blk - compute stuff
 * @sdp: the filesystem
 * @nstruct: the number of structures
 * @ssize: the size of the structures
 *
 * Compute the number of log descriptor blocks needed to hold a certain number
 * of structures of a certain size.
 *
 * Returns: the number of blocks needed (minimum is always 1)
 */

unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
			     unsigned int ssize)
{
	unsigned int blks;
	unsigned int first, second;

	blks = 1;
	first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;

	if (nstruct > first) {
		second = (sdp->sd_sb.sb_bsize -
			  sizeof(struct gfs2_meta_header)) / ssize;
		blks += DIV_ROUND_UP(nstruct - first, second);
	}

	return blks;
}

/**
 * gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
 * @mapping: The associated mapping (maybe NULL)
 * @bd: The gfs2_bufdata to remove
 *
 * The log lock _must_ be held when calling this function
 *
 */

void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd)
{
	bd->bd_ail = NULL;
	list_del_init(&bd->bd_ail_st_list);
	list_del_init(&bd->bd_ail_gl_list);
	atomic_dec(&bd->bd_gl->gl_ail_count);
	if (mapping)
		gfs2_meta_cache_flush(GFS2_I(mapping->host));
	brelse(bd->bd_bh);
}

/**
 * gfs2_ail1_start_one - Start I/O on a part of the AIL
 * @sdp: the filesystem
 * @tr: the part of the AIL
 *
 */

static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
	struct gfs2_bufdata *bd, *s;
	struct buffer_head *bh;
	int retry;

	BUG_ON(!spin_is_locked(&sdp->sd_log_lock));

	do {
		retry = 0;

		list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
						 bd_ail_st_list) {
			bh = bd->bd_bh;

			gfs2_assert(sdp, bd->bd_ail == ai);

			if (!buffer_busy(bh)) {
				if (!buffer_uptodate(bh))
					gfs2_io_error_bh(sdp, bh);
				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
				continue;
			}

			if (!buffer_dirty(bh))
				continue;

			list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);

			get_bh(bh);
			gfs2_log_unlock(sdp);
			lock_buffer(bh);
			if (test_clear_buffer_dirty(bh)) {
				bh->b_end_io = end_buffer_write_sync;
				submit_bh(WRITE, bh);
			} else {
				unlock_buffer(bh);
				brelse(bh);
			}
			gfs2_log_lock(sdp);

			retry = 1;
			break;
		}
	} while (retry);
}

/**
 * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
 * @sdp: the filesystem
 * @ai: the AIL entry
 *
 */

static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int flags)
{
	struct gfs2_bufdata *bd, *s;
	struct buffer_head *bh;

	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
					 bd_ail_st_list) {
		bh = bd->bd_bh;

		gfs2_assert(sdp, bd->bd_ail == ai);

		if (buffer_busy(bh)) {
			if (flags & DIO_ALL)
				continue;
			else
				break;
		}

		if (!buffer_uptodate(bh))
			gfs2_io_error_bh(sdp, bh);

		list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
	}

	return list_empty(&ai->ai_ail1_list);
}

static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
{
	struct list_head *head;
	u64 sync_gen;
	struct list_head *first;
	struct gfs2_ail *first_ai, *ai, *tmp;
	int done = 0;

	gfs2_log_lock(sdp);
	head = &sdp->sd_ail1_list;
	if (list_empty(head)) {
		gfs2_log_unlock(sdp);
		return;
	}
	sync_gen = sdp->sd_ail_sync_gen++;

	first = head->prev;
	first_ai = list_entry(first, struct gfs2_ail, ai_list);
	first_ai->ai_sync_gen = sync_gen;
	gfs2_ail1_start_one(sdp, first_ai); /* This may drop log lock */

	if (flags & DIO_ALL)
		first = NULL;

	while(!done) {
		if (first && (head->prev != first ||
			      gfs2_ail1_empty_one(sdp, first_ai, 0)))
			break;

		done = 1;
		list_for_each_entry_safe_reverse(ai, tmp, head, ai_list) {
			if (ai->ai_sync_gen >= sync_gen)
				continue;
			ai->ai_sync_gen = sync_gen;
			gfs2_ail1_start_one(sdp, ai); /* This may drop log lock */
			done = 0;
			break;
		}
	}

	gfs2_log_unlock(sdp);
}

int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags)
{
	struct gfs2_ail *ai, *s;
	int ret;

	gfs2_log_lock(sdp);

	list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
		if (gfs2_ail1_empty_one(sdp, ai, flags))
			list_move(&ai->ai_list, &sdp->sd_ail2_list);
		else if (!(flags & DIO_ALL))
			break;
	}

	ret = list_empty(&sdp->sd_ail1_list);

	gfs2_log_unlock(sdp);

	return ret;
}


/**
 * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
 * @sdp: the filesystem
 * @ai: the AIL entry
 *
 */

static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
	struct list_head *head = &ai->ai_ail2_list;
	struct gfs2_bufdata *bd;

	while (!list_empty(head)) {
		bd = list_entry(head->prev, struct gfs2_bufdata,
				bd_ail_st_list);
		gfs2_assert(sdp, bd->bd_ail == ai);
		gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd);
	}
}

static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
{
	struct gfs2_ail *ai, *safe;
	unsigned int old_tail = sdp->sd_log_tail;
	int wrap = (new_tail < old_tail);
	int a, b, rm;

	gfs2_log_lock(sdp);

	list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
		a = (old_tail <= ai->ai_first);
		b = (ai->ai_first < new_tail);
		rm = (wrap) ? (a || b) : (a && b);
		if (!rm)
			continue;

		gfs2_ail2_empty_one(sdp, ai);
		list_del(&ai->ai_list);
		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
		kfree(ai);
	}

	gfs2_log_unlock(sdp);
}

/**
 * gfs2_log_reserve - Make a log reservation
 * @sdp: The GFS2 superblock
 * @blks: The number of blocks to reserve
 *
 * Note that we never give out the last few blocks of the journal. Thats
 * due to the fact that there is a small number of header blocks
 * associated with each log flush. The exact number can't be known until
 * flush time, so we ensure that we have just enough free blocks at all
 * times to avoid running out during a log flush.
 *
 * Returns: errno
 */

int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
{
	unsigned int try = 0;
	unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize);

	if (gfs2_assert_warn(sdp, blks) ||
	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
		return -EINVAL;

	mutex_lock(&sdp->sd_log_reserve_mutex);
	gfs2_log_lock(sdp);
	while(sdp->sd_log_blks_free <= (blks + reserved_blks)) {
		gfs2_log_unlock(sdp);
		gfs2_ail1_empty(sdp, 0);
		gfs2_log_flush(sdp, NULL);

		if (try++)
			gfs2_ail1_start(sdp, 0);
		gfs2_log_lock(sdp);
	}
	sdp->sd_log_blks_free -= blks;
	gfs2_log_unlock(sdp);
	mutex_unlock(&sdp->sd_log_reserve_mutex);

	down_read(&sdp->sd_log_flush_lock);

	return 0;
}

/**
 * gfs2_log_release - Release a given number of log blocks
 * @sdp: The GFS2 superblock
 * @blks: The number of blocks
 *
 */

void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
{

	gfs2_log_lock(sdp);
	sdp->sd_log_blks_free += blks;
	gfs2_assert_withdraw(sdp,
			     sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
	gfs2_log_unlock(sdp);
	up_read(&sdp->sd_log_flush_lock);
}

static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
{
	struct inode *inode = sdp->sd_jdesc->jd_inode;
	int error;
	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };

	bh_map.b_size = 1 << inode->i_blkbits;
	error = gfs2_block_map(inode, lbn, 0, &bh_map);
	if (error || !bh_map.b_blocknr)
		printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error,
		       (unsigned long long)bh_map.b_blocknr, lbn);
	gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr);

	return bh_map.b_blocknr;
}

/**
 * log_distance - Compute distance between two journal blocks
 * @sdp: The GFS2 superblock
 * @newer: The most recent journal block of the pair
 * @older: The older journal block of the pair
 *
 *   Compute the distance (in the journal direction) between two
 *   blocks in the journal
 *
 * Returns: the distance in blocks
 */

static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
					unsigned int older)
{
	int dist;

	dist = newer - older;
	if (dist < 0)
		dist += sdp->sd_jdesc->jd_blocks;

	return dist;
}

/**
 * calc_reserved - Calculate the number of blocks to reserve when
 *                 refunding a transaction's unused buffers.
 * @sdp: The GFS2 superblock
 *
 * This is complex.  We need to reserve room for all our currently used
 * metadata buffers (e.g. normal file I/O rewriting file time stamps) and 
 * all our journaled data buffers for journaled files (e.g. files in the 
 * meta_fs like rindex, or files for which chattr +j was done.)
 * If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush
 * will count it as free space (sd_log_blks_free) and corruption will follow.
 *
 * We can have metadata bufs and jdata bufs in the same journal.  So each
 * type gets its own log header, for which we need to reserve a block.
 * In fact, each type has the potential for needing more than one header 
 * in cases where we have more buffers than will fit on a journal page.
 * Metadata journal entries take up half the space of journaled buffer entries.
 * Thus, metadata entries have buf_limit (502) and journaled buffers have
 * databuf_limit (251) before they cause a wrap around.
 *
 * Also, we need to reserve blocks for revoke journal entries and one for an
 * overall header for the lot.
 *
 * Returns: the number of blocks reserved
 */
static unsigned int calc_reserved(struct gfs2_sbd *sdp)
{
	unsigned int reserved = 0;
	unsigned int mbuf_limit, metabufhdrs_needed;
	unsigned int dbuf_limit, databufhdrs_needed;
	unsigned int revokes = 0;

	mbuf_limit = buf_limit(sdp);
	metabufhdrs_needed = (sdp->sd_log_commited_buf +
			      (mbuf_limit - 1)) / mbuf_limit;
	dbuf_limit = databuf_limit(sdp);
	databufhdrs_needed = (sdp->sd_log_commited_databuf +
			      (dbuf_limit - 1)) / dbuf_limit;

	if (sdp->sd_log_commited_revoke)
		revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
					  sizeof(u64));

	reserved = sdp->sd_log_commited_buf + metabufhdrs_needed +
		sdp->sd_log_commited_databuf + databufhdrs_needed +
		revokes;
	/* One for the overall header */
	if (reserved)
		reserved++;
	return reserved;
}

static unsigned int current_tail(struct gfs2_sbd *sdp)
{