log.c

linux 内核源代码

	struct gfs2_ail *ai;
	unsigned int tail;

	gfs2_log_lock(sdp);

	if (list_empty(&sdp->sd_ail1_list)) {
		tail = sdp->sd_log_head;
	} else {
		ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
		tail = ai->ai_first;
	}

	gfs2_log_unlock(sdp);

	return tail;
}

void gfs2_log_incr_head(struct gfs2_sbd *sdp)
{
	if (sdp->sd_log_flush_head == sdp->sd_log_tail)
		BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);

	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
		sdp->sd_log_flush_head = 0;
		sdp->sd_log_flush_wrapped = 1;
	}
}

/**
 * gfs2_log_write_endio - End of I/O for a log buffer
 * @bh: The buffer head
 * @uptodate: I/O Status
 *
 */

static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
{
	struct gfs2_sbd *sdp = bh->b_private;
	bh->b_private = NULL;

	end_buffer_write_sync(bh, uptodate);
	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
		wake_up(&sdp->sd_log_flush_wait);
}

/**
 * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
 * @sdp: The GFS2 superblock
 *
 * Returns: the buffer_head
 */

struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
{
	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
	struct buffer_head *bh;

	bh = sb_getblk(sdp->sd_vfs, blkno);
	lock_buffer(bh);
	memset(bh->b_data, 0, bh->b_size);
	set_buffer_uptodate(bh);
	clear_buffer_dirty(bh);
	gfs2_log_incr_head(sdp);
	atomic_inc(&sdp->sd_log_in_flight);
	bh->b_private = sdp;
	bh->b_end_io = gfs2_log_write_endio;

	return bh;
}

/**
 * gfs2_fake_write_endio - 
 * @bh: The buffer head
 * @uptodate: The I/O Status
 *
 */

static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
{
	struct buffer_head *real_bh = bh->b_private;
	struct gfs2_bufdata *bd = real_bh->b_private;
	struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;

	end_buffer_write_sync(bh, uptodate);
	free_buffer_head(bh);
	unlock_buffer(real_bh);
	brelse(real_bh);
	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
		wake_up(&sdp->sd_log_flush_wait);
}

/**
 * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
 * @sdp: the filesystem
 * @data: the data the buffer_head should point to
 *
 * Returns: the log buffer descriptor
 */

struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
				      struct buffer_head *real)
{
	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
	struct buffer_head *bh;

	bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
	atomic_set(&bh->b_count, 1);
	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
	set_bh_page(bh, real->b_page, bh_offset(real));
	bh->b_blocknr = blkno;
	bh->b_size = sdp->sd_sb.sb_bsize;
	bh->b_bdev = sdp->sd_vfs->s_bdev;
	bh->b_private = real;
	bh->b_end_io = gfs2_fake_write_endio;

	gfs2_log_incr_head(sdp);
	atomic_inc(&sdp->sd_log_in_flight);

	return bh;
}

static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
{
	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);

	ail2_empty(sdp, new_tail);

	gfs2_log_lock(sdp);
	sdp->sd_log_blks_free += dist;
	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
	gfs2_log_unlock(sdp);

	sdp->sd_log_tail = new_tail;
}

/**
 * log_write_header - Get and initialize a journal header buffer
 * @sdp: The GFS2 superblock
 *
 * Returns: the initialized log buffer descriptor
 */

static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
{
	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
	struct buffer_head *bh;
	struct gfs2_log_header *lh;
	unsigned int tail;
	u32 hash;

	bh = sb_getblk(sdp->sd_vfs, blkno);
	lock_buffer(bh);
	memset(bh->b_data, 0, bh->b_size);
	set_buffer_uptodate(bh);
	clear_buffer_dirty(bh);
	unlock_buffer(bh);

	gfs2_ail1_empty(sdp, 0);
	tail = current_tail(sdp);

	lh = (struct gfs2_log_header *)bh->b_data;
	memset(lh, 0, sizeof(struct gfs2_log_header));
	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
	lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
	lh->lh_flags = cpu_to_be32(flags);
	lh->lh_tail = cpu_to_be32(tail);
	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
	lh->lh_hash = cpu_to_be32(hash);

	set_buffer_dirty(bh);
	if (sync_dirty_buffer(bh))
		gfs2_io_error_bh(sdp, bh);
	brelse(bh);

	if (sdp->sd_log_tail != tail)
		log_pull_tail(sdp, tail);
	else
		gfs2_assert_withdraw(sdp, !pull);

	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
	gfs2_log_incr_head(sdp);
}

static void log_flush_commit(struct gfs2_sbd *sdp)
{
	DEFINE_WAIT(wait);

	if (atomic_read(&sdp->sd_log_in_flight)) {
		do {
			prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
					TASK_UNINTERRUPTIBLE);
			if (atomic_read(&sdp->sd_log_in_flight))
				io_schedule();
		} while(atomic_read(&sdp->sd_log_in_flight));
		finish_wait(&sdp->sd_log_flush_wait, &wait);
	}

	log_write_header(sdp, 0, 0);
}

static void gfs2_ordered_write(struct gfs2_sbd *sdp)
{
	struct gfs2_bufdata *bd;
	struct buffer_head *bh;
	LIST_HEAD(written);

	gfs2_log_lock(sdp);
	while (!list_empty(&sdp->sd_log_le_ordered)) {
		bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
		list_move(&bd->bd_le.le_list, &written);
		bh = bd->bd_bh;
		if (!buffer_dirty(bh))
			continue;
		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);
	}
	list_splice(&written, &sdp->sd_log_le_ordered);
	gfs2_log_unlock(sdp);
}

static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
{
	struct gfs2_bufdata *bd;
	struct buffer_head *bh;

	gfs2_log_lock(sdp);
	while (!list_empty(&sdp->sd_log_le_ordered)) {
		bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list);
		bh = bd->bd_bh;
		if (buffer_locked(bh)) {
			get_bh(bh);
			gfs2_log_unlock(sdp);
			wait_on_buffer(bh);
			brelse(bh);
			gfs2_log_lock(sdp);
			continue;
		}
		list_del_init(&bd->bd_le.le_list);
	}
	gfs2_log_unlock(sdp);
}

/**
 * gfs2_log_flush - flush incore transaction(s)
 * @sdp: the filesystem
 * @gl: The glock structure to flush.  If NULL, flush the whole incore log
 *
 */

void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
{
	struct gfs2_ail *ai;

	down_write(&sdp->sd_log_flush_lock);

	if (gl) {
		gfs2_log_lock(sdp);
		if (list_empty(&gl->gl_le.le_list)) {
			gfs2_log_unlock(sdp);
			up_write(&sdp->sd_log_flush_lock);
			return;
		}
		gfs2_log_unlock(sdp);
	}

	ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
	INIT_LIST_HEAD(&ai->ai_ail1_list);
	INIT_LIST_HEAD(&ai->ai_ail2_list);

	if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
		printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
		       sdp->sd_log_commited_buf);
		gfs2_assert_withdraw(sdp, 0);
	}
	if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) {
		printk(KERN_INFO "GFS2: log databuf %u %u\n",
		       sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf);
		gfs2_assert_withdraw(sdp, 0);
	}
	gfs2_assert_withdraw(sdp,
			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);

	sdp->sd_log_flush_head = sdp->sd_log_head;
	sdp->sd_log_flush_wrapped = 0;
	ai->ai_first = sdp->sd_log_flush_head;

	gfs2_ordered_write(sdp);
	lops_before_commit(sdp);
	gfs2_ordered_wait(sdp);

	if (sdp->sd_log_head != sdp->sd_log_flush_head)
		log_flush_commit(sdp);
	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
		gfs2_log_lock(sdp);
		sdp->sd_log_blks_free--; /* Adjust for unreserved buffer */
		gfs2_log_unlock(sdp);
		log_write_header(sdp, 0, PULL);
	}
	lops_after_commit(sdp, ai);

	gfs2_log_lock(sdp);
	sdp->sd_log_head = sdp->sd_log_flush_head;
	sdp->sd_log_blks_reserved = 0;
	sdp->sd_log_commited_buf = 0;
	sdp->sd_log_commited_databuf = 0;
	sdp->sd_log_commited_revoke = 0;

	if (!list_empty(&ai->ai_ail1_list)) {
		list_add(&ai->ai_list, &sdp->sd_ail1_list);
		ai = NULL;
	}
	gfs2_log_unlock(sdp);

	sdp->sd_vfs->s_dirt = 0;
	up_write(&sdp->sd_log_flush_lock);

	kfree(ai);
}

static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	unsigned int reserved;
	unsigned int old;

	gfs2_log_lock(sdp);

	sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
	sdp->sd_log_commited_databuf += tr->tr_num_databuf_new -
		tr->tr_num_databuf_rm;
	gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) ||
			     (((int)sdp->sd_log_commited_databuf) >= 0));
	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
	gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0);
	reserved = calc_reserved(sdp);
	old = sdp->sd_log_blks_free;
	sdp->sd_log_blks_free += tr->tr_reserved -
				 (reserved - sdp->sd_log_blks_reserved);

	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old);
	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <=
			     sdp->sd_jdesc->jd_blocks);

	sdp->sd_log_blks_reserved = reserved;

	gfs2_log_unlock(sdp);
}

/**
 * gfs2_log_commit - Commit a transaction to the log
 * @sdp: the filesystem
 * @tr: the transaction
 *
 * Returns: errno
 */

void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	log_refund(sdp, tr);
	lops_incore_commit(sdp, tr);

	sdp->sd_vfs->s_dirt = 1;
	up_read(&sdp->sd_log_flush_lock);

	gfs2_log_lock(sdp);
	if (sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks))
		wake_up_process(sdp->sd_logd_process);
	gfs2_log_unlock(sdp);
}

/**
 * gfs2_log_shutdown - write a shutdown header into a journal
 * @sdp: the filesystem
 *
 */

void gfs2_log_shutdown(struct gfs2_sbd *sdp)
{
	down_write(&sdp->sd_log_flush_lock);

	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_gl);
	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf);
	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));

	sdp->sd_log_flush_head = sdp->sd_log_head;
	sdp->sd_log_flush_wrapped = 0;

	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT,
			 (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL);

	gfs2_assert_warn(sdp, sdp->sd_log_blks_free == sdp->sd_jdesc->jd_blocks);
	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));

	sdp->sd_log_head = sdp->sd_log_flush_head;
	sdp->sd_log_tail = sdp->sd_log_head;

	up_write(&sdp->sd_log_flush_lock);
}


/**
 * gfs2_meta_syncfs - sync all the buffers in a filesystem
 * @sdp: the filesystem
 *
 */

void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
{
	gfs2_log_flush(sdp, NULL);
	for (;;) {
		gfs2_ail1_start(sdp, DIO_ALL);
		if (gfs2_ail1_empty(sdp, DIO_ALL))
			break;
		msleep(10);
	}
}