lops.c 21.2 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879
/*
 * 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/mempool.h>
#include <linux/gfs2_ondisk.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/list_sort.h>

#include "gfs2.h"
#include "incore.h"
#include "inode.h"
#include "glock.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "recovery.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "trace_gfs2.h"

/**
 * gfs2_pin - Pin a buffer in memory
 * @sdp: The superblock
 * @bh: The buffer to be pinned
 *
 * The log lock must be held when calling this function
 */
void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	struct gfs2_bufdata *bd;

	BUG_ON(!current->journal_info);

	clear_buffer_dirty(bh);
	if (test_set_buffer_pinned(bh))
		gfs2_assert_withdraw(sdp, 0);
	if (!buffer_uptodate(bh))
		gfs2_io_error_bh(sdp, bh);
	bd = bh->b_private;
	/* If this buffer is in the AIL and it has already been written
	 * to in-place disk block, remove it from the AIL.
	 */
	spin_lock(&sdp->sd_ail_lock);
	if (bd->bd_tr)
		list_move(&bd->bd_ail_st_list, &bd->bd_tr->tr_ail2_list);
	spin_unlock(&sdp->sd_ail_lock);
	get_bh(bh);
	atomic_inc(&sdp->sd_log_pinned);
	trace_gfs2_pin(bd, 1);
}

static bool buffer_is_rgrp(const struct gfs2_bufdata *bd)
{
	return bd->bd_gl->gl_name.ln_type == LM_TYPE_RGRP;
}

static void maybe_release_space(struct gfs2_bufdata *bd)
{
	struct gfs2_glock *gl = bd->bd_gl;
	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct gfs2_rgrpd *rgd = gl->gl_object;
	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
	struct gfs2_bitmap *bi = rgd->rd_bits + index;

	if (bi->bi_clone == NULL)
		return;
	if (sdp->sd_args.ar_discard)
		gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL);
	memcpy(bi->bi_clone + bi->bi_offset,
	       bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
	clear_bit(GBF_FULL, &bi->bi_flags);
	rgd->rd_free_clone = rgd->rd_free;
	rgd->rd_extfail_pt = rgd->rd_free;
}

/**
 * gfs2_unpin - Unpin a buffer
 * @sdp: the filesystem the buffer belongs to
 * @bh: The buffer to unpin
 * @ai:
 * @flags: The inode dirty flags
 *
 */

static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
		       struct gfs2_trans *tr)
{
	struct gfs2_bufdata *bd = bh->b_private;

	BUG_ON(!buffer_uptodate(bh));
	BUG_ON(!buffer_pinned(bh));

	lock_buffer(bh);
	mark_buffer_dirty(bh);
	clear_buffer_pinned(bh);

	if (buffer_is_rgrp(bd))
		maybe_release_space(bd);

	spin_lock(&sdp->sd_ail_lock);
	if (bd->bd_tr) {
		list_del(&bd->bd_ail_st_list);
		brelse(bh);
	} else {
		struct gfs2_glock *gl = bd->bd_gl;
		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
		atomic_inc(&gl->gl_ail_count);
	}
	bd->bd_tr = tr;
	list_add(&bd->bd_ail_st_list, &tr->tr_ail1_list);
	spin_unlock(&sdp->sd_ail_lock);

	clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
	trace_gfs2_pin(bd, 0);
	unlock_buffer(bh);
	atomic_dec(&sdp->sd_log_pinned);
}

static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
{
	BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
	       (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;
	}
}

static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
{
	unsigned int lbn = sdp->sd_log_flush_head;
	struct gfs2_journal_extent *je;
	u64 block;

	list_for_each_entry(je, &sdp->sd_jdesc->extent_list, list) {
		if ((lbn >= je->lblock) && (lbn < (je->lblock + je->blocks))) {
			block = je->dblock + lbn - je->lblock;
			gfs2_log_incr_head(sdp);
			return block;
		}
	}

	return -1;
}

/**
 * gfs2_end_log_write_bh - end log write of pagecache data with buffers
 * @sdp: The superblock
 * @bvec: The bio_vec
 * @error: The i/o status
 *
 * This finds the relavent buffers and unlocks then and sets the
 * error flag according to the status of the i/o request. This is
 * used when the log is writing data which has an in-place version
 * that is pinned in the pagecache.
 */

static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
				  int error)
{
	struct buffer_head *bh, *next;
	struct page *page = bvec->bv_page;
	unsigned size;

	bh = page_buffers(page);
	size = bvec->bv_len;
	while (bh_offset(bh) < bvec->bv_offset)
		bh = bh->b_this_page;
	do {
		if (error)
			set_buffer_write_io_error(bh);
		unlock_buffer(bh);
		next = bh->b_this_page;
		size -= bh->b_size;
		brelse(bh);
		bh = next;
	} while(bh && size);
}

/**
 * gfs2_end_log_write - end of i/o to the log
 * @bio: The bio
 * @error: Status of i/o request
 *
 * Each bio_vec contains either data from the pagecache or data
 * relating to the log itself. Here we iterate over the bio_vec
 * array, processing both kinds of data.
 *
 */

static void gfs2_end_log_write(struct bio *bio)
{
	struct gfs2_sbd *sdp = bio->bi_private;
	struct bio_vec *bvec;
	struct page *page;
	int i;

	if (bio->bi_error) {
		sdp->sd_log_error = bio->bi_error;
		fs_err(sdp, "Error %d writing to log\n", bio->bi_error);
	}

	bio_for_each_segment_all(bvec, bio, i) {
		page = bvec->bv_page;
		if (page_has_buffers(page))
			gfs2_end_log_write_bh(sdp, bvec, bio->bi_error);
		else
			mempool_free(page, gfs2_page_pool);
	}

	bio_put(bio);
	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
		wake_up(&sdp->sd_log_flush_wait);
}

/**
 * gfs2_log_flush_bio - Submit any pending log bio
 * @sdp: The superblock
 * @rw: The rw flags
 *
 * Submit any pending part-built or full bio to the block device. If
 * there is no pending bio, then this is a no-op.
 */

void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
{
	if (sdp->sd_log_bio) {
		atomic_inc(&sdp->sd_log_in_flight);
		submit_bio(rw, sdp->sd_log_bio);
		sdp->sd_log_bio = NULL;
	}
}

/**
 * gfs2_log_alloc_bio - Allocate a new bio for log writing
 * @sdp: The superblock
 * @blkno: The next device block number we want to write to
 *
 * This should never be called when there is a cached bio in the
 * super block. When it returns, there will be a cached bio in the
 * super block which will have as many bio_vecs as the device is
 * happy to handle.
 *
 * Returns: Newly allocated bio
 */

static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
{
	struct super_block *sb = sdp->sd_vfs;
	struct bio *bio;

	BUG_ON(sdp->sd_log_bio);

	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
	bio->bi_bdev = sb->s_bdev;
	bio->bi_end_io = gfs2_end_log_write;
	bio->bi_private = sdp;

	sdp->sd_log_bio = bio;

	return bio;
}

/**
 * gfs2_log_get_bio - Get cached log bio, or allocate a new one
 * @sdp: The superblock
 * @blkno: The device block number we want to write to
 *
 * If there is a cached bio, then if the next block number is sequential
 * with the previous one, return it, otherwise flush the bio to the
 * device. If there is not a cached bio, or we just flushed it, then
 * allocate a new one.
 *
 * Returns: The bio to use for log writes
 */

static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno)
{
	struct bio *bio = sdp->sd_log_bio;
	u64 nblk;

	if (bio) {
		nblk = bio_end_sector(bio);
		nblk >>= sdp->sd_fsb2bb_shift;
		if (blkno == nblk)
			return bio;
		gfs2_log_flush_bio(sdp, WRITE);
	}

	return gfs2_log_alloc_bio(sdp, blkno);
}


/**
 * gfs2_log_write - write to log
 * @sdp: the filesystem
 * @page: the page to write
 * @size: the size of the data to write
 * @offset: the offset within the page 
 *
 * Try and add the page segment to the current bio. If that fails,
 * submit the current bio to the device and create a new one, and
 * then add the page segment to that.
 */

static void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
			   unsigned size, unsigned offset)
{
	u64 blkno = gfs2_log_bmap(sdp);
	struct bio *bio;
	int ret;

	bio = gfs2_log_get_bio(sdp, blkno);
	ret = bio_add_page(bio, page, size, offset);
	if (ret == 0) {
		gfs2_log_flush_bio(sdp, WRITE);
		bio = gfs2_log_alloc_bio(sdp, blkno);
		ret = bio_add_page(bio, page, size, offset);
		WARN_ON(ret == 0);
	}
}

/**
 * gfs2_log_write_bh - write a buffer's content to the log
 * @sdp: The super block
 * @bh: The buffer pointing to the in-place location
 * 
 * This writes the content of the buffer to the next available location
 * in the log. The buffer will be unlocked once the i/o to the log has
 * completed.
 */

static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh));
}

/**
 * gfs2_log_write_page - write one block stored in a page, into the log
 * @sdp: The superblock
 * @page: The struct page
 *
 * This writes the first block-sized part of the page into the log. Note
 * that the page must have been allocated from the gfs2_page_pool mempool
 * and that after this has been called, ownership has been transferred and
 * the page may be freed at any time.
 */

void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
{
	struct super_block *sb = sdp->sd_vfs;
	gfs2_log_write(sdp, page, sb->s_blocksize, 0);
}

static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type,
				      u32 ld_length, u32 ld_data1)
{
	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
	struct gfs2_log_descriptor *ld = page_address(page);
	clear_page(ld);
	ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
	ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
	ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
	ld->ld_type = cpu_to_be32(ld_type);
	ld->ld_length = cpu_to_be32(ld_length);
	ld->ld_data1 = cpu_to_be32(ld_data1);
	ld->ld_data2 = 0;
	return page;
}

static void gfs2_check_magic(struct buffer_head *bh)
{
	void *kaddr;
	__be32 *ptr;

	clear_buffer_escaped(bh);
	kaddr = kmap_atomic(bh->b_page);
	ptr = kaddr + bh_offset(bh);
	if (*ptr == cpu_to_be32(GFS2_MAGIC))
		set_buffer_escaped(bh);
	kunmap_atomic(kaddr);
}

static int blocknr_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct gfs2_bufdata *bda, *bdb;

	bda = list_entry(a, struct gfs2_bufdata, bd_list);
	bdb = list_entry(b, struct gfs2_bufdata, bd_list);

	if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
		return -1;
	if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
		return 1;
	return 0;
}

static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit,
				unsigned int total, struct list_head *blist,
				bool is_databuf)
{
	struct gfs2_log_descriptor *ld;
	struct gfs2_bufdata *bd1 = NULL, *bd2;
	struct page *page;
	unsigned int num;
	unsigned n;
	__be64 *ptr;

	gfs2_log_lock(sdp);
	list_sort(NULL, blist, blocknr_cmp);
	bd1 = bd2 = list_prepare_entry(bd1, blist, bd_list);
	while(total) {
		num = total;
		if (total > limit)
			num = limit;
		gfs2_log_unlock(sdp);
		page = gfs2_get_log_desc(sdp,
					 is_databuf ? GFS2_LOG_DESC_JDATA :
					 GFS2_LOG_DESC_METADATA, num + 1, num);
		ld = page_address(page);
		gfs2_log_lock(sdp);
		ptr = (__be64 *)(ld + 1);

		n = 0;
		list_for_each_entry_continue(bd1, blist, bd_list) {
			*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
			if (is_databuf) {
				gfs2_check_magic(bd1->bd_bh);
				*ptr++ = cpu_to_be64(buffer_escaped(bd1->bd_bh) ? 1 : 0);
			}
			if (++n >= num)
				break;
		}

		gfs2_log_unlock(sdp);
		gfs2_log_write_page(sdp, page);
		gfs2_log_lock(sdp);

		n = 0;
		list_for_each_entry_continue(bd2, blist, bd_list) {
			get_bh(bd2->bd_bh);
			gfs2_log_unlock(sdp);
			lock_buffer(bd2->bd_bh);

			if (buffer_escaped(bd2->bd_bh)) {
				void *kaddr;
				page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
				ptr = page_address(page);
				kaddr = kmap_atomic(bd2->bd_bh->b_page);
				memcpy(ptr, kaddr + bh_offset(bd2->bd_bh),
				       bd2->bd_bh->b_size);
				kunmap_atomic(kaddr);
				*(__be32 *)ptr = 0;
				clear_buffer_escaped(bd2->bd_bh);
				unlock_buffer(bd2->bd_bh);
				brelse(bd2->bd_bh);
				gfs2_log_write_page(sdp, page);
			} else {
				gfs2_log_write_bh(sdp, bd2->bd_bh);
			}
			gfs2_log_lock(sdp);
			if (++n >= num)
				break;
		}

		BUG_ON(total < num);
		total -= num;
	}
	gfs2_log_unlock(sdp);
}

static void buf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	unsigned int limit = buf_limit(sdp); /* 503 for 4k blocks */
	unsigned int nbuf;
	if (tr == NULL)
		return;
	nbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
	gfs2_before_commit(sdp, limit, nbuf, &tr->tr_buf, 0);
}

static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	struct list_head *head;
	struct gfs2_bufdata *bd;

	if (tr == NULL)
		return;

	head = &tr->tr_buf;
	while (!list_empty(head)) {
		bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
		list_del_init(&bd->bd_list);
		gfs2_unpin(sdp, bd->bd_bh, tr);
	}
}

static void buf_lo_before_scan(struct gfs2_jdesc *jd,
			       struct gfs2_log_header_host *head, int pass)
{
	if (pass != 0)
		return;

	jd->jd_found_blocks = 0;
	jd->jd_replayed_blocks = 0;
}

static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
				struct gfs2_log_descriptor *ld, __be64 *ptr,
				int pass)
{
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
	struct gfs2_glock *gl = ip->i_gl;
	unsigned int blks = be32_to_cpu(ld->ld_data1);
	struct buffer_head *bh_log, *bh_ip;
	u64 blkno;
	int error = 0;

	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_METADATA)
		return 0;

	gfs2_replay_incr_blk(sdp, &start);

	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
		blkno = be64_to_cpu(*ptr++);

		jd->jd_found_blocks++;

		if (gfs2_revoke_check(jd, blkno, start))
			continue;

		error = gfs2_replay_read_block(jd, start, &bh_log);
		if (error)
			return error;

		bh_ip = gfs2_meta_new(gl, blkno);
		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);

		if (gfs2_meta_check(sdp, bh_ip))
			error = -EIO;
		else
			mark_buffer_dirty(bh_ip);

		brelse(bh_log);
		brelse(bh_ip);

		if (error)
			break;

		jd->jd_replayed_blocks++;
	}

	return error;
}

/**
 * gfs2_meta_sync - Sync all buffers associated with a glock
 * @gl: The glock
 *
 */

static void gfs2_meta_sync(struct gfs2_glock *gl)
{
	struct address_space *mapping = gfs2_glock2aspace(gl);
	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	int error;

	if (mapping == NULL)
		mapping = &sdp->sd_aspace;

	filemap_fdatawrite(mapping);
	error = filemap_fdatawait(mapping);

	if (error)
		gfs2_io_error(gl->gl_name.ln_sbd);
}

static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);

	if (error) {
		gfs2_meta_sync(ip->i_gl);
		return;
	}
	if (pass != 1)
		return;

	gfs2_meta_sync(ip->i_gl);

	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
	        jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
}

static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	struct gfs2_meta_header *mh;
	unsigned int offset;
	struct list_head *head = &sdp->sd_log_le_revoke;
	struct gfs2_bufdata *bd;
	struct page *page;
	unsigned int length;

	gfs2_write_revokes(sdp);
	if (!sdp->sd_log_num_revoke)
		return;

	length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64));
	page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke);
	offset = sizeof(struct gfs2_log_descriptor);

	list_for_each_entry(bd, head, bd_list) {
		sdp->sd_log_num_revoke--;

		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {

			gfs2_log_write_page(sdp, page);
			page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
			mh = page_address(page);
			clear_page(mh);
			mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
			mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB);
			mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB);
			offset = sizeof(struct gfs2_meta_header);
		}

		*(__be64 *)(page_address(page) + offset) = cpu_to_be64(bd->bd_blkno);
		offset += sizeof(u64);
	}
	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);

	gfs2_log_write_page(sdp, page);
}

static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	struct list_head *head = &sdp->sd_log_le_revoke;
	struct gfs2_bufdata *bd;
	struct gfs2_glock *gl;

	while (!list_empty(head)) {
		bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
		list_del_init(&bd->bd_list);
		gl = bd->bd_gl;
		atomic_dec(&gl->gl_revokes);
		clear_bit(GLF_LFLUSH, &gl->gl_flags);
		kmem_cache_free(gfs2_bufdata_cachep, bd);
	}
}

static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
				  struct gfs2_log_header_host *head, int pass)
{
	if (pass != 0)
		return;

	jd->jd_found_revokes = 0;
	jd->jd_replay_tail = head->lh_tail;
}

static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
				   struct gfs2_log_descriptor *ld, __be64 *ptr,
				   int pass)
{
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
	unsigned int blks = be32_to_cpu(ld->ld_length);
	unsigned int revokes = be32_to_cpu(ld->ld_data1);
	struct buffer_head *bh;
	unsigned int offset;
	u64 blkno;
	int first = 1;
	int error;

	if (pass != 0 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_REVOKE)
		return 0;

	offset = sizeof(struct gfs2_log_descriptor);

	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
		error = gfs2_replay_read_block(jd, start, &bh);
		if (error)
			return error;

		if (!first)
			gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LB);

		while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
			blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));

			error = gfs2_revoke_add(jd, blkno, start);
			if (error < 0) {
				brelse(bh);
				return error;
			}
			else if (error)
				jd->jd_found_revokes++;

			if (!--revokes)
				break;
			offset += sizeof(u64);
		}

		brelse(bh);
		offset = sizeof(struct gfs2_meta_header);
		first = 0;
	}

	return 0;
}

static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);

	if (error) {
		gfs2_revoke_clean(jd);
		return;
	}
	if (pass != 1)
		return;

	fs_info(sdp, "jid=%u: Found %u revoke tags\n",
	        jd->jd_jid, jd->jd_found_revokes);

	gfs2_revoke_clean(jd);
}

/**
 * databuf_lo_before_commit - Scan the data buffers, writing as we go
 *
 */

static void databuf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	unsigned int limit = databuf_limit(sdp);
	unsigned int nbuf;
	if (tr == NULL)
		return;
	nbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
	gfs2_before_commit(sdp, limit, nbuf, &tr->tr_databuf, 1);
}

static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
				    struct gfs2_log_descriptor *ld,
				    __be64 *ptr, int pass)
{
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
	struct gfs2_glock *gl = ip->i_gl;
	unsigned int blks = be32_to_cpu(ld->ld_data1);
	struct buffer_head *bh_log, *bh_ip;
	u64 blkno;
	u64 esc;
	int error = 0;

	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_JDATA)
		return 0;

	gfs2_replay_incr_blk(sdp, &start);
	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
		blkno = be64_to_cpu(*ptr++);
		esc = be64_to_cpu(*ptr++);

		jd->jd_found_blocks++;

		if (gfs2_revoke_check(jd, blkno, start))
			continue;

		error = gfs2_replay_read_block(jd, start, &bh_log);
		if (error)
			return error;

		bh_ip = gfs2_meta_new(gl, blkno);
		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);

		/* Unescape */
		if (esc) {
			__be32 *eptr = (__be32 *)bh_ip->b_data;
			*eptr = cpu_to_be32(GFS2_MAGIC);
		}
		mark_buffer_dirty(bh_ip);

		brelse(bh_log);
		brelse(bh_ip);

		jd->jd_replayed_blocks++;
	}

	return error;
}

/* FIXME: sort out accounting for log blocks etc. */

static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);

	if (error) {
		gfs2_meta_sync(ip->i_gl);
		return;
	}
	if (pass != 1)
		return;

	/* data sync? */
	gfs2_meta_sync(ip->i_gl);

	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
		jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
}

static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
	struct list_head *head;
	struct gfs2_bufdata *bd;

	if (tr == NULL)
		return;

	head = &tr->tr_databuf;
	while (!list_empty(head)) {
		bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
		list_del_init(&bd->bd_list);
		gfs2_unpin(sdp, bd->bd_bh, tr);
	}
}


const struct gfs2_log_operations gfs2_buf_lops = {
	.lo_before_commit = buf_lo_before_commit,
	.lo_after_commit = buf_lo_after_commit,
	.lo_before_scan = buf_lo_before_scan,
	.lo_scan_elements = buf_lo_scan_elements,
	.lo_after_scan = buf_lo_after_scan,
	.lo_name = "buf",
};

const struct gfs2_log_operations gfs2_revoke_lops = {
	.lo_before_commit = revoke_lo_before_commit,
	.lo_after_commit = revoke_lo_after_commit,
	.lo_before_scan = revoke_lo_before_scan,
	.lo_scan_elements = revoke_lo_scan_elements,
	.lo_after_scan = revoke_lo_after_scan,
	.lo_name = "revoke",
};

const struct gfs2_log_operations gfs2_databuf_lops = {
	.lo_before_commit = databuf_lo_before_commit,
	.lo_after_commit = databuf_lo_after_commit,
	.lo_scan_elements = databuf_lo_scan_elements,
	.lo_after_scan = databuf_lo_after_scan,
	.lo_name = "databuf",
};

const struct gfs2_log_operations *gfs2_log_ops[] = {
	&gfs2_databuf_lops,
	&gfs2_buf_lops,
	&gfs2_revoke_lops,
	NULL,
};