xfs_trans_buf.c 21.9 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
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_trans_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"

/*
 * Check to see if a buffer matching the given parameters is already
 * a part of the given transaction.
 */
STATIC struct xfs_buf *
xfs_trans_buf_item_match(
	struct xfs_trans	*tp,
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps)
{
	struct xfs_log_item_desc *lidp;
	struct xfs_buf_log_item	*blip;
	int			len = 0;
	int			i;

	for (i = 0; i < nmaps; i++)
		len += map[i].bm_len;

	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
		blip = (struct xfs_buf_log_item *)lidp->lid_item;
		if (blip->bli_item.li_type == XFS_LI_BUF &&
		    blip->bli_buf->b_target == target &&
		    XFS_BUF_ADDR(blip->bli_buf) == map[0].bm_bn &&
		    blip->bli_buf->b_length == len) {
			ASSERT(blip->bli_buf->b_map_count == nmaps);
			return blip->bli_buf;
		}
	}

	return NULL;
}

/*
 * Add the locked buffer to the transaction.
 *
 * The buffer must be locked, and it cannot be associated with any
 * transaction.
 *
 * If the buffer does not yet have a buf log item associated with it,
 * then allocate one for it.  Then add the buf item to the transaction.
 */
STATIC void
_xfs_trans_bjoin(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp,
	int			reset_recur)
{
	struct xfs_buf_log_item	*bip;

	ASSERT(bp->b_transp == NULL);

	/*
	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
	 * it doesn't have one yet, then allocate one and initialize it.
	 * The checks to see if one is there are in xfs_buf_item_init().
	 */
	xfs_buf_item_init(bp, tp->t_mountp);
	bip = bp->b_fspriv;
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
	if (reset_recur)
		bip->bli_recur = 0;

	/*
	 * Take a reference for this transaction on the buf item.
	 */
	atomic_inc(&bip->bli_refcount);

	/*
	 * Get a log_item_desc to point at the new item.
	 */
	xfs_trans_add_item(tp, &bip->bli_item);

	/*
	 * Initialize b_fsprivate2 so we can find it with incore_match()
	 * in xfs_trans_get_buf() and friends above.
	 */
	bp->b_transp = tp;

}

void
xfs_trans_bjoin(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp)
{
	_xfs_trans_bjoin(tp, bp, 0);
	trace_xfs_trans_bjoin(bp->b_fspriv);
}

/*
 * Get and lock the buffer for the caller if it is not already
 * locked within the given transaction.  If it is already locked
 * within the transaction, just increment its lock recursion count
 * and return a pointer to it.
 *
 * If the transaction pointer is NULL, make this just a normal
 * get_buf() call.
 */
struct xfs_buf *
xfs_trans_get_buf_map(
	struct xfs_trans	*tp,
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps,
	xfs_buf_flags_t		flags)
{
	xfs_buf_t		*bp;
	xfs_buf_log_item_t	*bip;

	if (!tp)
		return xfs_buf_get_map(target, map, nmaps, flags);

	/*
	 * If we find the buffer in the cache with this transaction
	 * pointer in its b_fsprivate2 field, then we know we already
	 * have it locked.  In this case we just increment the lock
	 * recursion count and return the buffer to the caller.
	 */
	bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
	if (bp != NULL) {
		ASSERT(xfs_buf_islocked(bp));
		if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
			xfs_buf_stale(bp);
			bp->b_flags |= XBF_DONE;
		}

		ASSERT(bp->b_transp == tp);
		bip = bp->b_fspriv;
		ASSERT(bip != NULL);
		ASSERT(atomic_read(&bip->bli_refcount) > 0);
		bip->bli_recur++;
		trace_xfs_trans_get_buf_recur(bip);
		return bp;
	}

	bp = xfs_buf_get_map(target, map, nmaps, flags);
	if (bp == NULL) {
		return NULL;
	}

	ASSERT(!bp->b_error);

	_xfs_trans_bjoin(tp, bp, 1);
	trace_xfs_trans_get_buf(bp->b_fspriv);
	return bp;
}

/*
 * Get and lock the superblock buffer of this file system for the
 * given transaction.
 *
 * We don't need to use incore_match() here, because the superblock
 * buffer is a private buffer which we keep a pointer to in the
 * mount structure.
 */
xfs_buf_t *
xfs_trans_getsb(xfs_trans_t	*tp,
		struct xfs_mount *mp,
		int		flags)
{
	xfs_buf_t		*bp;
	xfs_buf_log_item_t	*bip;

	/*
	 * Default to just trying to lock the superblock buffer
	 * if tp is NULL.
	 */
	if (tp == NULL)
		return xfs_getsb(mp, flags);

	/*
	 * If the superblock buffer already has this transaction
	 * pointer in its b_fsprivate2 field, then we know we already
	 * have it locked.  In this case we just increment the lock
	 * recursion count and return the buffer to the caller.
	 */
	bp = mp->m_sb_bp;
	if (bp->b_transp == tp) {
		bip = bp->b_fspriv;
		ASSERT(bip != NULL);
		ASSERT(atomic_read(&bip->bli_refcount) > 0);
		bip->bli_recur++;
		trace_xfs_trans_getsb_recur(bip);
		return bp;
	}

	bp = xfs_getsb(mp, flags);
	if (bp == NULL)
		return NULL;

	_xfs_trans_bjoin(tp, bp, 1);
	trace_xfs_trans_getsb(bp->b_fspriv);
	return bp;
}

/*
 * Get and lock the buffer for the caller if it is not already
 * locked within the given transaction.  If it has not yet been
 * read in, read it from disk. If it is already locked
 * within the transaction and already read in, just increment its
 * lock recursion count and return a pointer to it.
 *
 * If the transaction pointer is NULL, make this just a normal
 * read_buf() call.
 */
int
xfs_trans_read_buf_map(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps,
	xfs_buf_flags_t		flags,
	struct xfs_buf		**bpp,
	const struct xfs_buf_ops *ops)
{
	struct xfs_buf		*bp = NULL;
	struct xfs_buf_log_item	*bip;
	int			error;

	*bpp = NULL;
	/*
	 * If we find the buffer in the cache with this transaction
	 * pointer in its b_fsprivate2 field, then we know we already
	 * have it locked.  If it is already read in we just increment
	 * the lock recursion count and return the buffer to the caller.
	 * If the buffer is not yet read in, then we read it in, increment
	 * the lock recursion count, and return it to the caller.
	 */
	if (tp)
		bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
	if (bp) {
		ASSERT(xfs_buf_islocked(bp));
		ASSERT(bp->b_transp == tp);
		ASSERT(bp->b_fspriv != NULL);
		ASSERT(!bp->b_error);
		ASSERT(bp->b_flags & XBF_DONE);

		/*
		 * We never locked this buf ourselves, so we shouldn't
		 * brelse it either. Just get out.
		 */
		if (XFS_FORCED_SHUTDOWN(mp)) {
			trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
			return -EIO;
		}

		bip = bp->b_fspriv;
		bip->bli_recur++;

		ASSERT(atomic_read(&bip->bli_refcount) > 0);
		trace_xfs_trans_read_buf_recur(bip);
		*bpp = bp;
		return 0;
	}

	bp = xfs_buf_read_map(target, map, nmaps, flags, ops);
	if (!bp) {
		if (!(flags & XBF_TRYLOCK))
			return -ENOMEM;
		return tp ? 0 : -EAGAIN;
	}

	/*
	 * If we've had a read error, then the contents of the buffer are
	 * invalid and should not be used. To ensure that a followup read tries
	 * to pull the buffer from disk again, we clear the XBF_DONE flag and
	 * mark the buffer stale. This ensures that anyone who has a current
	 * reference to the buffer will interpret it's contents correctly and
	 * future cache lookups will also treat it as an empty, uninitialised
	 * buffer.
	 */
	if (bp->b_error) {
		error = bp->b_error;
		if (!XFS_FORCED_SHUTDOWN(mp))
			xfs_buf_ioerror_alert(bp, __func__);
		bp->b_flags &= ~XBF_DONE;
		xfs_buf_stale(bp);

		if (tp && (tp->t_flags & XFS_TRANS_DIRTY))
			xfs_force_shutdown(tp->t_mountp, SHUTDOWN_META_IO_ERROR);
		xfs_buf_relse(bp);

		/* bad CRC means corrupted metadata */
		if (error == -EFSBADCRC)
			error = -EFSCORRUPTED;
		return error;
	}

	if (XFS_FORCED_SHUTDOWN(mp)) {
		xfs_buf_relse(bp);
		trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
		return -EIO;
	}

	if (tp) {
		_xfs_trans_bjoin(tp, bp, 1);
		trace_xfs_trans_read_buf(bp->b_fspriv);
	}
	*bpp = bp;
	return 0;

}

/*
 * Release the buffer bp which was previously acquired with one of the
 * xfs_trans_... buffer allocation routines if the buffer has not
 * been modified within this transaction.  If the buffer is modified
 * within this transaction, do decrement the recursion count but do
 * not release the buffer even if the count goes to 0.  If the buffer is not
 * modified within the transaction, decrement the recursion count and
 * release the buffer if the recursion count goes to 0.
 *
 * If the buffer is to be released and it was not modified before
 * this transaction began, then free the buf_log_item associated with it.
 *
 * If the transaction pointer is NULL, make this just a normal
 * brelse() call.
 */
void
xfs_trans_brelse(xfs_trans_t	*tp,
		 xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;

	/*
	 * Default to a normal brelse() call if the tp is NULL.
	 */
	if (tp == NULL) {
		ASSERT(bp->b_transp == NULL);
		xfs_buf_relse(bp);
		return;
	}

	ASSERT(bp->b_transp == tp);
	bip = bp->b_fspriv;
	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	trace_xfs_trans_brelse(bip);

	/*
	 * If the release is just for a recursive lock,
	 * then decrement the count and return.
	 */
	if (bip->bli_recur > 0) {
		bip->bli_recur--;
		return;
	}

	/*
	 * If the buffer is dirty within this transaction, we can't
	 * release it until we commit.
	 */
	if (bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY)
		return;

	/*
	 * If the buffer has been invalidated, then we can't release
	 * it until the transaction commits to disk unless it is re-dirtied
	 * as part of this transaction.  This prevents us from pulling
	 * the item from the AIL before we should.
	 */
	if (bip->bli_flags & XFS_BLI_STALE)
		return;

	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));

	/*
	 * Free up the log item descriptor tracking the released item.
	 */
	xfs_trans_del_item(&bip->bli_item);

	/*
	 * Clear the hold flag in the buf log item if it is set.
	 * We wouldn't want the next user of the buffer to
	 * get confused.
	 */
	if (bip->bli_flags & XFS_BLI_HOLD) {
		bip->bli_flags &= ~XFS_BLI_HOLD;
	}

	/*
	 * Drop our reference to the buf log item.
	 */
	atomic_dec(&bip->bli_refcount);

	/*
	 * If the buf item is not tracking data in the log, then
	 * we must free it before releasing the buffer back to the
	 * free pool.  Before releasing the buffer to the free pool,
	 * clear the transaction pointer in b_fsprivate2 to dissolve
	 * its relation to this transaction.
	 */
	if (!xfs_buf_item_dirty(bip)) {
/***
		ASSERT(bp->b_pincount == 0);
***/
		ASSERT(atomic_read(&bip->bli_refcount) == 0);
		ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));
		ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF));
		xfs_buf_item_relse(bp);
	}

	bp->b_transp = NULL;
	xfs_buf_relse(bp);
}

/*
 * Mark the buffer as not needing to be unlocked when the buf item's
 * iop_unlock() routine is called.  The buffer must already be locked
 * and associated with the given transaction.
 */
/* ARGSUSED */
void
xfs_trans_bhold(xfs_trans_t	*tp,
		xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_HOLD;
	trace_xfs_trans_bhold(bip);
}

/*
 * Cancel the previous buffer hold request made on this buffer
 * for this transaction.
 */
void
xfs_trans_bhold_release(xfs_trans_t	*tp,
			xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	ASSERT(bip->bli_flags & XFS_BLI_HOLD);

	bip->bli_flags &= ~XFS_BLI_HOLD;
	trace_xfs_trans_bhold_release(bip);
}

/*
 * This is called to mark bytes first through last inclusive of the given
 * buffer as needing to be logged when the transaction is committed.
 * The buffer must already be associated with the given transaction.
 *
 * First and last are numbers relative to the beginning of this buffer,
 * so the first byte in the buffer is numbered 0 regardless of the
 * value of b_blkno.
 */
void
xfs_trans_log_buf(xfs_trans_t	*tp,
		  xfs_buf_t	*bp,
		  uint		first,
		  uint		last)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(first <= last && last < BBTOB(bp->b_length));
	ASSERT(bp->b_iodone == NULL ||
	       bp->b_iodone == xfs_buf_iodone_callbacks);

	/*
	 * Mark the buffer as needing to be written out eventually,
	 * and set its iodone function to remove the buffer's buf log
	 * item from the AIL and free it when the buffer is flushed
	 * to disk.  See xfs_buf_attach_iodone() for more details
	 * on li_cb and xfs_buf_iodone_callbacks().
	 * If we end up aborting this transaction, we trap this buffer
	 * inside the b_bdstrat callback so that this won't get written to
	 * disk.
	 */
	bp->b_flags |= XBF_DONE;

	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	bp->b_iodone = xfs_buf_iodone_callbacks;
	bip->bli_item.li_cb = xfs_buf_iodone;

	trace_xfs_trans_log_buf(bip);

	/*
	 * If we invalidated the buffer within this transaction, then
	 * cancel the invalidation now that we're dirtying the buffer
	 * again.  There are no races with the code in xfs_buf_item_unpin(),
	 * because we have a reference to the buffer this entire time.
	 */
	if (bip->bli_flags & XFS_BLI_STALE) {
		bip->bli_flags &= ~XFS_BLI_STALE;
		ASSERT(bp->b_flags & XBF_STALE);
		bp->b_flags &= ~XBF_STALE;
		bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
	}

	tp->t_flags |= XFS_TRANS_DIRTY;
	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;

	/*
	 * If we have an ordered buffer we are not logging any dirty range but
	 * it still needs to be marked dirty and that it has been logged.
	 */
	bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
	if (!(bip->bli_flags & XFS_BLI_ORDERED))
		xfs_buf_item_log(bip, first, last);
}


/*
 * Invalidate a buffer that is being used within a transaction.
 *
 * Typically this is because the blocks in the buffer are being freed, so we
 * need to prevent it from being written out when we're done.  Allowing it
 * to be written again might overwrite data in the free blocks if they are
 * reallocated to a file.
 *
 * We prevent the buffer from being written out by marking it stale.  We can't
 * get rid of the buf log item at this point because the buffer may still be
 * pinned by another transaction.  If that is the case, then we'll wait until
 * the buffer is committed to disk for the last time (we can tell by the ref
 * count) and free it in xfs_buf_item_unpin().  Until that happens we will
 * keep the buffer locked so that the buffer and buf log item are not reused.
 *
 * We also set the XFS_BLF_CANCEL flag in the buf log format structure and log
 * the buf item.  This will be used at recovery time to determine that copies
 * of the buffer in the log before this should not be replayed.
 *
 * We mark the item descriptor and the transaction dirty so that we'll hold
 * the buffer until after the commit.
 *
 * Since we're invalidating the buffer, we also clear the state about which
 * parts of the buffer have been logged.  We also clear the flag indicating
 * that this is an inode buffer since the data in the buffer will no longer
 * be valid.
 *
 * We set the stale bit in the buffer as well since we're getting rid of it.
 */
void
xfs_trans_binval(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;
	int			i;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	trace_xfs_trans_binval(bip);

	if (bip->bli_flags & XFS_BLI_STALE) {
		/*
		 * If the buffer is already invalidated, then
		 * just return.
		 */
		ASSERT(bp->b_flags & XBF_STALE);
		ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
		ASSERT(bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY);
		ASSERT(tp->t_flags & XFS_TRANS_DIRTY);
		return;
	}

	xfs_buf_stale(bp);

	bip->bli_flags |= XFS_BLI_STALE;
	bip->bli_flags &= ~(XFS_BLI_INODE_BUF | XFS_BLI_LOGGED | XFS_BLI_DIRTY);
	bip->__bli_format.blf_flags &= ~XFS_BLF_INODE_BUF;
	bip->__bli_format.blf_flags |= XFS_BLF_CANCEL;
	bip->__bli_format.blf_flags &= ~XFS_BLFT_MASK;
	for (i = 0; i < bip->bli_format_count; i++) {
		memset(bip->bli_formats[i].blf_data_map, 0,
		       (bip->bli_formats[i].blf_map_size * sizeof(uint)));
	}
	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
	tp->t_flags |= XFS_TRANS_DIRTY;
}

/*
 * This call is used to indicate that the buffer contains on-disk inodes which
 * must be handled specially during recovery.  They require special handling
 * because only the di_next_unlinked from the inodes in the buffer should be
 * recovered.  The rest of the data in the buffer is logged via the inodes
 * themselves.
 *
 * All we do is set the XFS_BLI_INODE_BUF flag in the items flags so it can be
 * transferred to the buffer's log format structure so that we'll know what to
 * do at recovery time.
 */
void
xfs_trans_inode_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_INODE_BUF;
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
}

/*
 * This call is used to indicate that the buffer is going to
 * be staled and was an inode buffer. This means it gets
 * special processing during unpin - where any inodes
 * associated with the buffer should be removed from ail.
 * There is also special processing during recovery,
 * any replay of the inodes in the buffer needs to be
 * prevented as the buffer may have been reused.
 */
void
xfs_trans_stale_inode_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_STALE_INODE;
	bip->bli_item.li_cb = xfs_buf_iodone;
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
}

/*
 * Mark the buffer as being one which contains newly allocated
 * inodes.  We need to make sure that even if this buffer is
 * relogged as an 'inode buf' we still recover all of the inode
 * images in the face of a crash.  This works in coordination with
 * xfs_buf_item_committed() to ensure that the buffer remains in the
 * AIL at its original location even after it has been relogged.
 */
/* ARGSUSED */
void
xfs_trans_inode_alloc_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF;
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
}

/*
 * Mark the buffer as ordered for this transaction. This means
 * that the contents of the buffer are not recorded in the transaction
 * but it is tracked in the AIL as though it was. This allows us
 * to record logical changes in transactions rather than the physical
 * changes we make to the buffer without changing writeback ordering
 * constraints of metadata buffers.
 */
void
xfs_trans_ordered_buf(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp)
{
	struct xfs_buf_log_item	*bip = bp->b_fspriv;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_ORDERED;
	trace_xfs_buf_item_ordered(bip);
}

/*
 * Set the type of the buffer for log recovery so that it can correctly identify
 * and hence attach the correct buffer ops to the buffer after replay.
 */
void
xfs_trans_buf_set_type(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp,
	enum xfs_blft		type)
{
	struct xfs_buf_log_item	*bip = bp->b_fspriv;

	if (!tp)
		return;

	ASSERT(bp->b_transp == tp);
	ASSERT(bip != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	xfs_blft_to_flags(&bip->__bli_format, type);
}

void
xfs_trans_buf_copy_type(
	struct xfs_buf		*dst_bp,
	struct xfs_buf		*src_bp)
{
	struct xfs_buf_log_item	*sbip = src_bp->b_fspriv;
	struct xfs_buf_log_item	*dbip = dst_bp->b_fspriv;
	enum xfs_blft		type;

	type = xfs_blft_from_flags(&sbip->__bli_format);
	xfs_blft_to_flags(&dbip->__bli_format, type);
}

/*
 * Similar to xfs_trans_inode_buf(), this marks the buffer as a cluster of
 * dquots. However, unlike in inode buffer recovery, dquot buffers get
 * recovered in their entirety. (Hence, no XFS_BLI_DQUOT_ALLOC_BUF flag).
 * The only thing that makes dquot buffers different from regular
 * buffers is that we must not replay dquot bufs when recovering
 * if a _corresponding_ quotaoff has happened. We also have to distinguish
 * between usr dquot bufs and grp dquot bufs, because usr and grp quotas
 * can be turned off independently.
 */
/* ARGSUSED */
void
xfs_trans_dquot_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp,
	uint		type)
{
	struct xfs_buf_log_item	*bip = bp->b_fspriv;

	ASSERT(type == XFS_BLF_UDQUOT_BUF ||
	       type == XFS_BLF_PDQUOT_BUF ||
	       type == XFS_BLF_GDQUOT_BUF);

	bip->__bli_format.blf_flags |= type;

	switch (type) {
	case XFS_BLF_UDQUOT_BUF:
		type = XFS_BLFT_UDQUOT_BUF;
		break;
	case XFS_BLF_PDQUOT_BUF:
		type = XFS_BLFT_PDQUOT_BUF;
		break;
	case XFS_BLF_GDQUOT_BUF:
		type = XFS_BLFT_GDQUOT_BUF;
		break;
	default:
		type = XFS_BLFT_UNKNOWN_BUF;
		break;
	}

	xfs_trans_buf_set_type(tp, bp, type);
}