xfs_rmap.c 36.9 KB
Newer Older
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
/*
 * Copyright (c) 2014 Red Hat, 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_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_btree.h"
#include "xfs_trans.h"
#include "xfs_alloc.h"
#include "xfs_rmap.h"
34
#include "xfs_rmap_btree.h"
35 36 37 38
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_error.h"
#include "xfs_extent_busy.h"
39 40
#include "xfs_bmap.h"
#include "xfs_inode.h"
41

D
Darrick J. Wong 已提交
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
/*
 * Lookup the first record less than or equal to [bno, len, owner, offset]
 * in the btree given by cur.
 */
int
xfs_rmap_lookup_le(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	uint64_t		owner,
	uint64_t		offset,
	unsigned int		flags,
	int			*stat)
{
	cur->bc_rec.r.rm_startblock = bno;
	cur->bc_rec.r.rm_blockcount = len;
	cur->bc_rec.r.rm_owner = owner;
	cur->bc_rec.r.rm_offset = offset;
	cur->bc_rec.r.rm_flags = flags;
	return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
}

/*
 * Lookup the record exactly matching [bno, len, owner, offset]
 * in the btree given by cur.
 */
int
xfs_rmap_lookup_eq(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	uint64_t		owner,
	uint64_t		offset,
	unsigned int		flags,
	int			*stat)
{
	cur->bc_rec.r.rm_startblock = bno;
	cur->bc_rec.r.rm_blockcount = len;
	cur->bc_rec.r.rm_owner = owner;
	cur->bc_rec.r.rm_offset = offset;
	cur->bc_rec.r.rm_flags = flags;
	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}

/*
 * Update the record referred to by cur to the value given
 * by [bno, len, owner, offset].
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int
xfs_rmap_update(
	struct xfs_btree_cur	*cur,
	struct xfs_rmap_irec	*irec)
{
	union xfs_btree_rec	rec;
97 98 99 100 101
	int			error;

	trace_xfs_rmap_update(cur->bc_mp, cur->bc_private.a.agno,
			irec->rm_startblock, irec->rm_blockcount,
			irec->rm_owner, irec->rm_offset, irec->rm_flags);
D
Darrick J. Wong 已提交
102 103 104 105 106 107

	rec.rmap.rm_startblock = cpu_to_be32(irec->rm_startblock);
	rec.rmap.rm_blockcount = cpu_to_be32(irec->rm_blockcount);
	rec.rmap.rm_owner = cpu_to_be64(irec->rm_owner);
	rec.rmap.rm_offset = cpu_to_be64(
			xfs_rmap_irec_offset_pack(irec));
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
	error = xfs_btree_update(cur, &rec);
	if (error)
		trace_xfs_rmap_update_error(cur->bc_mp,
				cur->bc_private.a.agno, error, _RET_IP_);
	return error;
}

int
xfs_rmap_insert(
	struct xfs_btree_cur	*rcur,
	xfs_agblock_t		agbno,
	xfs_extlen_t		len,
	uint64_t		owner,
	uint64_t		offset,
	unsigned int		flags)
{
	int			i;
	int			error;

	trace_xfs_rmap_insert(rcur->bc_mp, rcur->bc_private.a.agno, agbno,
			len, owner, offset, flags);

	error = xfs_rmap_lookup_eq(rcur, agbno, len, owner, offset, flags, &i);
	if (error)
		goto done;
	XFS_WANT_CORRUPTED_GOTO(rcur->bc_mp, i == 0, done);

	rcur->bc_rec.r.rm_startblock = agbno;
	rcur->bc_rec.r.rm_blockcount = len;
	rcur->bc_rec.r.rm_owner = owner;
	rcur->bc_rec.r.rm_offset = offset;
	rcur->bc_rec.r.rm_flags = flags;
	error = xfs_btree_insert(rcur, &i);
	if (error)
		goto done;
	XFS_WANT_CORRUPTED_GOTO(rcur->bc_mp, i == 1, done);
done:
	if (error)
		trace_xfs_rmap_insert_error(rcur->bc_mp,
				rcur->bc_private.a.agno, error, _RET_IP_);
	return error;
D
Darrick J. Wong 已提交
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
}

static int
xfs_rmap_btrec_to_irec(
	union xfs_btree_rec	*rec,
	struct xfs_rmap_irec	*irec)
{
	irec->rm_flags = 0;
	irec->rm_startblock = be32_to_cpu(rec->rmap.rm_startblock);
	irec->rm_blockcount = be32_to_cpu(rec->rmap.rm_blockcount);
	irec->rm_owner = be64_to_cpu(rec->rmap.rm_owner);
	return xfs_rmap_irec_offset_unpack(be64_to_cpu(rec->rmap.rm_offset),
			irec);
}

/*
 * Get the data from the pointed-to record.
 */
int
xfs_rmap_get_rec(
	struct xfs_btree_cur	*cur,
	struct xfs_rmap_irec	*irec,
	int			*stat)
{
	union xfs_btree_rec	*rec;
	int			error;

	error = xfs_btree_get_rec(cur, &rec, stat);
	if (error || !*stat)
		return error;

	return xfs_rmap_btrec_to_irec(rec, irec);
}

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
/*
 * Find the extent in the rmap btree and remove it.
 *
 * The record we find should always be an exact match for the extent that we're
 * looking for, since we insert them into the btree without modification.
 *
 * Special Case #1: when growing the filesystem, we "free" an extent when
 * growing the last AG. This extent is new space and so it is not tracked as
 * used space in the btree. The growfs code will pass in an owner of
 * XFS_RMAP_OWN_NULL to indicate that it expected that there is no owner of this
 * extent. We verify that - the extent lookup result in a record that does not
 * overlap.
 *
 * Special Case #2: EFIs do not record the owner of the extent, so when
 * recovering EFIs from the log we pass in XFS_RMAP_OWN_UNKNOWN to tell the rmap
 * btree to ignore the owner (i.e. wildcard match) so we don't trigger
 * corruption checks during log recovery.
 */
STATIC int
xfs_rmap_unmap(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	bool			unwritten,
	struct xfs_owner_info	*oinfo)
{
	struct xfs_mount	*mp = cur->bc_mp;
	struct xfs_rmap_irec	ltrec;
	uint64_t		ltoff;
	int			error = 0;
	int			i;
	uint64_t		owner;
	uint64_t		offset;
	unsigned int		flags;
	bool			ignore_off;

	xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
	ignore_off = XFS_RMAP_NON_INODE_OWNER(owner) ||
			(flags & XFS_RMAP_BMBT_BLOCK);
	if (unwritten)
		flags |= XFS_RMAP_UNWRITTEN;
	trace_xfs_rmap_unmap(mp, cur->bc_private.a.agno, bno, len,
			unwritten, oinfo);

	/*
	 * We should always have a left record because there's a static record
	 * for the AG headers at rm_startblock == 0 created by mkfs/growfs that
	 * will not ever be removed from the tree.
	 */
	error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, flags, &i);
	if (error)
		goto out_error;
	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error);

	error = xfs_rmap_get_rec(cur, &ltrec, &i);
	if (error)
		goto out_error;
	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error);
	trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
			cur->bc_private.a.agno, ltrec.rm_startblock,
			ltrec.rm_blockcount, ltrec.rm_owner,
			ltrec.rm_offset, ltrec.rm_flags);
	ltoff = ltrec.rm_offset;

	/*
	 * For growfs, the incoming extent must be beyond the left record we
	 * just found as it is new space and won't be used by anyone. This is
	 * just a corruption check as we don't actually do anything with this
	 * extent.  Note that we need to use >= instead of > because it might
	 * be the case that the "left" extent goes all the way to EOFS.
	 */
	if (owner == XFS_RMAP_OWN_NULL) {
		XFS_WANT_CORRUPTED_GOTO(mp, bno >= ltrec.rm_startblock +
						ltrec.rm_blockcount, out_error);
		goto out_done;
	}

	/* Make sure the unwritten flag matches. */
	XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) ==
			(ltrec.rm_flags & XFS_RMAP_UNWRITTEN), out_error);

	/* Make sure the extent we found covers the entire freeing range. */
	XFS_WANT_CORRUPTED_GOTO(mp, ltrec.rm_startblock <= bno &&
		ltrec.rm_startblock + ltrec.rm_blockcount >=
		bno + len, out_error);

	/* Make sure the owner matches what we expect to find in the tree. */
	XFS_WANT_CORRUPTED_GOTO(mp, owner == ltrec.rm_owner ||
				    XFS_RMAP_NON_INODE_OWNER(owner), out_error);

	/* Check the offset, if necessary. */
	if (!XFS_RMAP_NON_INODE_OWNER(owner)) {
		if (flags & XFS_RMAP_BMBT_BLOCK) {
			XFS_WANT_CORRUPTED_GOTO(mp,
					ltrec.rm_flags & XFS_RMAP_BMBT_BLOCK,
					out_error);
		} else {
			XFS_WANT_CORRUPTED_GOTO(mp,
					ltrec.rm_offset <= offset, out_error);
			XFS_WANT_CORRUPTED_GOTO(mp,
					ltoff + ltrec.rm_blockcount >= offset + len,
					out_error);
		}
	}

	if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) {
		/* exact match, simply remove the record from rmap tree */
		trace_xfs_rmap_delete(mp, cur->bc_private.a.agno,
				ltrec.rm_startblock, ltrec.rm_blockcount,
				ltrec.rm_owner, ltrec.rm_offset,
				ltrec.rm_flags);
		error = xfs_btree_delete(cur, &i);
		if (error)
			goto out_error;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error);
	} else if (ltrec.rm_startblock == bno) {
		/*
		 * overlap left hand side of extent: move the start, trim the
		 * length and update the current record.
		 *
		 *       ltbno                ltlen
		 * Orig:    |oooooooooooooooooooo|
		 * Freeing: |fffffffff|
		 * Result:            |rrrrrrrrrr|
		 *         bno       len
		 */
		ltrec.rm_startblock += len;
		ltrec.rm_blockcount -= len;
		if (!ignore_off)
			ltrec.rm_offset += len;
		error = xfs_rmap_update(cur, &ltrec);
		if (error)
			goto out_error;
	} else if (ltrec.rm_startblock + ltrec.rm_blockcount == bno + len) {
		/*
		 * overlap right hand side of extent: trim the length and update
		 * the current record.
		 *
		 *       ltbno                ltlen
		 * Orig:    |oooooooooooooooooooo|
		 * Freeing:            |fffffffff|
		 * Result:  |rrrrrrrrrr|
		 *                    bno       len
		 */
		ltrec.rm_blockcount -= len;
		error = xfs_rmap_update(cur, &ltrec);
		if (error)
			goto out_error;
	} else {

		/*
		 * overlap middle of extent: trim the length of the existing
		 * record to the length of the new left-extent size, increment
		 * the insertion position so we can insert a new record
		 * containing the remaining right-extent space.
		 *
		 *       ltbno                ltlen
		 * Orig:    |oooooooooooooooooooo|
		 * Freeing:       |fffffffff|
		 * Result:  |rrrrr|         |rrrr|
		 *               bno       len
		 */
		xfs_extlen_t	orig_len = ltrec.rm_blockcount;

		ltrec.rm_blockcount = bno - ltrec.rm_startblock;
		error = xfs_rmap_update(cur, &ltrec);
		if (error)
			goto out_error;

		error = xfs_btree_increment(cur, 0, &i);
		if (error)
			goto out_error;

		cur->bc_rec.r.rm_startblock = bno + len;
		cur->bc_rec.r.rm_blockcount = orig_len - len -
						     ltrec.rm_blockcount;
		cur->bc_rec.r.rm_owner = ltrec.rm_owner;
		if (ignore_off)
			cur->bc_rec.r.rm_offset = 0;
		else
			cur->bc_rec.r.rm_offset = offset + len;
		cur->bc_rec.r.rm_flags = flags;
		trace_xfs_rmap_insert(mp, cur->bc_private.a.agno,
				cur->bc_rec.r.rm_startblock,
				cur->bc_rec.r.rm_blockcount,
				cur->bc_rec.r.rm_owner,
				cur->bc_rec.r.rm_offset,
				cur->bc_rec.r.rm_flags);
		error = xfs_btree_insert(cur, &i);
		if (error)
			goto out_error;
	}

out_done:
	trace_xfs_rmap_unmap_done(mp, cur->bc_private.a.agno, bno, len,
			unwritten, oinfo);
out_error:
	if (error)
		trace_xfs_rmap_unmap_error(mp, cur->bc_private.a.agno,
				error, _RET_IP_);
	return error;
}

/*
 * Remove a reference to an extent in the rmap btree.
 */
389 390 391 392 393 394 395 396 397 398
int
xfs_rmap_free(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	struct xfs_owner_info	*oinfo)
{
	struct xfs_mount	*mp = tp->t_mountp;
399 400
	struct xfs_btree_cur	*cur;
	int			error;
401 402 403 404

	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return 0;

405 406 407 408
	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);

	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
	if (error)
409
		goto out_error;
410 411

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
412 413 414
	return 0;

out_error:
415
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
416 417 418
	return error;
}

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
/*
 * A mergeable rmap must have the same owner and the same values for
 * the unwritten, attr_fork, and bmbt flags.  The startblock and
 * offset are checked separately.
 */
static bool
xfs_rmap_is_mergeable(
	struct xfs_rmap_irec	*irec,
	uint64_t		owner,
	unsigned int		flags)
{
	if (irec->rm_owner == XFS_RMAP_OWN_NULL)
		return false;
	if (irec->rm_owner != owner)
		return false;
	if ((flags & XFS_RMAP_UNWRITTEN) ^
	    (irec->rm_flags & XFS_RMAP_UNWRITTEN))
		return false;
	if ((flags & XFS_RMAP_ATTR_FORK) ^
	    (irec->rm_flags & XFS_RMAP_ATTR_FORK))
		return false;
	if ((flags & XFS_RMAP_BMBT_BLOCK) ^
	    (irec->rm_flags & XFS_RMAP_BMBT_BLOCK))
		return false;
	return true;
}

/*
 * When we allocate a new block, the first thing we do is add a reference to
 * the extent in the rmap btree. This takes the form of a [agbno, length,
 * owner, offset] record.  Flags are encoded in the high bits of the offset
 * field.
 */
STATIC int
xfs_rmap_map(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	bool			unwritten,
	struct xfs_owner_info	*oinfo)
{
	struct xfs_mount	*mp = cur->bc_mp;
	struct xfs_rmap_irec	ltrec;
	struct xfs_rmap_irec	gtrec;
	int			have_gt;
	int			have_lt;
	int			error = 0;
	int			i;
	uint64_t		owner;
	uint64_t		offset;
	unsigned int		flags = 0;
	bool			ignore_off;

	xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
	ASSERT(owner != 0);
	ignore_off = XFS_RMAP_NON_INODE_OWNER(owner) ||
			(flags & XFS_RMAP_BMBT_BLOCK);
	if (unwritten)
		flags |= XFS_RMAP_UNWRITTEN;
	trace_xfs_rmap_map(mp, cur->bc_private.a.agno, bno, len,
			unwritten, oinfo);

	/*
	 * For the initial lookup, look for an exact match or the left-adjacent
	 * record for our insertion point. This will also give us the record for
	 * start block contiguity tests.
	 */
	error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, flags,
			&have_lt);
	if (error)
		goto out_error;
	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);

	error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
	if (error)
		goto out_error;
	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
	trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
			cur->bc_private.a.agno, ltrec.rm_startblock,
			ltrec.rm_blockcount, ltrec.rm_owner,
			ltrec.rm_offset, ltrec.rm_flags);

	if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
		have_lt = 0;

	XFS_WANT_CORRUPTED_GOTO(mp,
		have_lt == 0 ||
		ltrec.rm_startblock + ltrec.rm_blockcount <= bno, out_error);

	/*
	 * Increment the cursor to see if we have a right-adjacent record to our
	 * insertion point. This will give us the record for end block
	 * contiguity tests.
	 */
	error = xfs_btree_increment(cur, 0, &have_gt);
	if (error)
		goto out_error;
	if (have_gt) {
		error = xfs_rmap_get_rec(cur, &gtrec, &have_gt);
		if (error)
			goto out_error;
		XFS_WANT_CORRUPTED_GOTO(mp, have_gt == 1, out_error);
		XFS_WANT_CORRUPTED_GOTO(mp, bno + len <= gtrec.rm_startblock,
					out_error);
		trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp,
			cur->bc_private.a.agno, gtrec.rm_startblock,
			gtrec.rm_blockcount, gtrec.rm_owner,
			gtrec.rm_offset, gtrec.rm_flags);
		if (!xfs_rmap_is_mergeable(&gtrec, owner, flags))
			have_gt = 0;
	}

	/*
	 * Note: cursor currently points one record to the right of ltrec, even
	 * if there is no record in the tree to the right.
	 */
	if (have_lt &&
	    ltrec.rm_startblock + ltrec.rm_blockcount == bno &&
	    (ignore_off || ltrec.rm_offset + ltrec.rm_blockcount == offset)) {
		/*
		 * left edge contiguous, merge into left record.
		 *
		 *       ltbno     ltlen
		 * orig:   |ooooooooo|
		 * adding:           |aaaaaaaaa|
		 * result: |rrrrrrrrrrrrrrrrrrr|
		 *                  bno       len
		 */
		ltrec.rm_blockcount += len;
		if (have_gt &&
		    bno + len == gtrec.rm_startblock &&
		    (ignore_off || offset + len == gtrec.rm_offset) &&
		    (unsigned long)ltrec.rm_blockcount + len +
				gtrec.rm_blockcount <= XFS_RMAP_LEN_MAX) {
			/*
			 * right edge also contiguous, delete right record
			 * and merge into left record.
			 *
			 *       ltbno     ltlen    gtbno     gtlen
			 * orig:   |ooooooooo|         |ooooooooo|
			 * adding:           |aaaaaaaaa|
			 * result: |rrrrrrrrrrrrrrrrrrrrrrrrrrrrr|
			 */
			ltrec.rm_blockcount += gtrec.rm_blockcount;
			trace_xfs_rmap_delete(mp, cur->bc_private.a.agno,
					gtrec.rm_startblock,
					gtrec.rm_blockcount,
					gtrec.rm_owner,
					gtrec.rm_offset,
					gtrec.rm_flags);
			error = xfs_btree_delete(cur, &i);
			if (error)
				goto out_error;
			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error);
		}

		/* point the cursor back to the left record and update */
		error = xfs_btree_decrement(cur, 0, &have_gt);
		if (error)
			goto out_error;
		error = xfs_rmap_update(cur, &ltrec);
		if (error)
			goto out_error;
	} else if (have_gt &&
		   bno + len == gtrec.rm_startblock &&
		   (ignore_off || offset + len == gtrec.rm_offset)) {
		/*
		 * right edge contiguous, merge into right record.
		 *
		 *                 gtbno     gtlen
		 * Orig:             |ooooooooo|
		 * adding: |aaaaaaaaa|
		 * Result: |rrrrrrrrrrrrrrrrrrr|
		 *        bno       len
		 */
		gtrec.rm_startblock = bno;
		gtrec.rm_blockcount += len;
		if (!ignore_off)
			gtrec.rm_offset = offset;
		error = xfs_rmap_update(cur, &gtrec);
		if (error)
			goto out_error;
	} else {
		/*
		 * no contiguous edge with identical owner, insert
		 * new record at current cursor position.
		 */
		cur->bc_rec.r.rm_startblock = bno;
		cur->bc_rec.r.rm_blockcount = len;
		cur->bc_rec.r.rm_owner = owner;
		cur->bc_rec.r.rm_offset = offset;
		cur->bc_rec.r.rm_flags = flags;
		trace_xfs_rmap_insert(mp, cur->bc_private.a.agno, bno, len,
			owner, offset, flags);
		error = xfs_btree_insert(cur, &i);
		if (error)
			goto out_error;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error);
	}

	trace_xfs_rmap_map_done(mp, cur->bc_private.a.agno, bno, len,
			unwritten, oinfo);
out_error:
	if (error)
		trace_xfs_rmap_map_error(mp, cur->bc_private.a.agno,
				error, _RET_IP_);
	return error;
}

/*
 * Add a reference to an extent in the rmap btree.
 */
631 632 633 634 635 636 637 638 639 640
int
xfs_rmap_alloc(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	struct xfs_owner_info	*oinfo)
{
	struct xfs_mount	*mp = tp->t_mountp;
641 642
	struct xfs_btree_cur	*cur;
	int			error;
643 644 645 646

	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return 0;

647 648 649
	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
	error = xfs_rmap_map(cur, bno, len, false, oinfo);
	if (error)
650
		goto out_error;
651 652

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
653 654 655
	return 0;

out_error:
656
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
657 658
	return error;
}
659

660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
#define RMAP_LEFT_CONTIG	(1 << 0)
#define RMAP_RIGHT_CONTIG	(1 << 1)
#define RMAP_LEFT_FILLING	(1 << 2)
#define RMAP_RIGHT_FILLING	(1 << 3)
#define RMAP_LEFT_VALID		(1 << 6)
#define RMAP_RIGHT_VALID	(1 << 7)

#define LEFT		r[0]
#define RIGHT		r[1]
#define PREV		r[2]
#define NEW		r[3]

/*
 * Convert an unwritten extent to a real extent or vice versa.
 * Does not handle overlapping extents.
 */
STATIC int
xfs_rmap_convert(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	bool			unwritten,
	struct xfs_owner_info	*oinfo)
{
	struct xfs_mount	*mp = cur->bc_mp;
	struct xfs_rmap_irec	r[4];	/* neighbor extent entries */
					/* left is 0, right is 1, prev is 2 */
					/* new is 3 */
	uint64_t		owner;
	uint64_t		offset;
	uint64_t		new_endoff;
	unsigned int		oldext;
	unsigned int		newext;
	unsigned int		flags = 0;
	int			i;
	int			state = 0;
	int			error;

	xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
	ASSERT(!(XFS_RMAP_NON_INODE_OWNER(owner) ||
			(flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))));
	oldext = unwritten ? XFS_RMAP_UNWRITTEN : 0;
	new_endoff = offset + len;
	trace_xfs_rmap_convert(mp, cur->bc_private.a.agno, bno, len,
			unwritten, oinfo);

	/*
	 * For the initial lookup, look for an exact match or the left-adjacent
	 * record for our insertion point. This will also give us the record for
	 * start block contiguity tests.
	 */
	error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, oldext, &i);
	if (error)
		goto done;
	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);

	error = xfs_rmap_get_rec(cur, &PREV, &i);
	if (error)
		goto done;
	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
	trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
			cur->bc_private.a.agno, PREV.rm_startblock,
			PREV.rm_blockcount, PREV.rm_owner,
			PREV.rm_offset, PREV.rm_flags);

	ASSERT(PREV.rm_offset <= offset);
	ASSERT(PREV.rm_offset + PREV.rm_blockcount >= new_endoff);
	ASSERT((PREV.rm_flags & XFS_RMAP_UNWRITTEN) == oldext);
	newext = ~oldext & XFS_RMAP_UNWRITTEN;

	/*
	 * Set flags determining what part of the previous oldext allocation
	 * extent is being replaced by a newext allocation.
	 */
	if (PREV.rm_offset == offset)
		state |= RMAP_LEFT_FILLING;
	if (PREV.rm_offset + PREV.rm_blockcount == new_endoff)
		state |= RMAP_RIGHT_FILLING;

	/*
	 * Decrement the cursor to see if we have a left-adjacent record to our
	 * insertion point. This will give us the record for end block
	 * contiguity tests.
	 */
	error = xfs_btree_decrement(cur, 0, &i);
	if (error)
		goto done;
	if (i) {
		state |= RMAP_LEFT_VALID;
		error = xfs_rmap_get_rec(cur, &LEFT, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		XFS_WANT_CORRUPTED_GOTO(mp,
				LEFT.rm_startblock + LEFT.rm_blockcount <= bno,
				done);
		trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp,
				cur->bc_private.a.agno, LEFT.rm_startblock,
				LEFT.rm_blockcount, LEFT.rm_owner,
				LEFT.rm_offset, LEFT.rm_flags);
		if (LEFT.rm_startblock + LEFT.rm_blockcount == bno &&
		    LEFT.rm_offset + LEFT.rm_blockcount == offset &&
		    xfs_rmap_is_mergeable(&LEFT, owner, newext))
			state |= RMAP_LEFT_CONTIG;
	}

	/*
	 * Increment the cursor to see if we have a right-adjacent record to our
	 * insertion point. This will give us the record for end block
	 * contiguity tests.
	 */
	error = xfs_btree_increment(cur, 0, &i);
	if (error)
		goto done;
	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
	error = xfs_btree_increment(cur, 0, &i);
	if (error)
		goto done;
	if (i) {
		state |= RMAP_RIGHT_VALID;
		error = xfs_rmap_get_rec(cur, &RIGHT, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		XFS_WANT_CORRUPTED_GOTO(mp, bno + len <= RIGHT.rm_startblock,
					done);
		trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp,
				cur->bc_private.a.agno, RIGHT.rm_startblock,
				RIGHT.rm_blockcount, RIGHT.rm_owner,
				RIGHT.rm_offset, RIGHT.rm_flags);
		if (bno + len == RIGHT.rm_startblock &&
		    offset + len == RIGHT.rm_offset &&
		    xfs_rmap_is_mergeable(&RIGHT, owner, newext))
			state |= RMAP_RIGHT_CONTIG;
	}

	/* check that left + prev + right is not too long */
	if ((state & (RMAP_LEFT_FILLING | RMAP_LEFT_CONTIG |
			 RMAP_RIGHT_FILLING | RMAP_RIGHT_CONTIG)) ==
	    (RMAP_LEFT_FILLING | RMAP_LEFT_CONTIG |
	     RMAP_RIGHT_FILLING | RMAP_RIGHT_CONTIG) &&
	    (unsigned long)LEFT.rm_blockcount + len +
	     RIGHT.rm_blockcount > XFS_RMAP_LEN_MAX)
		state &= ~RMAP_RIGHT_CONTIG;

	trace_xfs_rmap_convert_state(mp, cur->bc_private.a.agno, state,
			_RET_IP_);

	/* reset the cursor back to PREV */
	error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, oldext, &i);
	if (error)
		goto done;
	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);

	/*
	 * Switch out based on the FILLING and CONTIG state bits.
	 */
	switch (state & (RMAP_LEFT_FILLING | RMAP_LEFT_CONTIG |
			 RMAP_RIGHT_FILLING | RMAP_RIGHT_CONTIG)) {
	case RMAP_LEFT_FILLING | RMAP_LEFT_CONTIG |
	     RMAP_RIGHT_FILLING | RMAP_RIGHT_CONTIG:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * The left and right neighbors are both contiguous with new.
		 */
		error = xfs_btree_increment(cur, 0, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		trace_xfs_rmap_delete(mp, cur->bc_private.a.agno,
				RIGHT.rm_startblock, RIGHT.rm_blockcount,
				RIGHT.rm_owner, RIGHT.rm_offset,
				RIGHT.rm_flags);
		error = xfs_btree_delete(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		error = xfs_btree_decrement(cur, 0, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		trace_xfs_rmap_delete(mp, cur->bc_private.a.agno,
				PREV.rm_startblock, PREV.rm_blockcount,
				PREV.rm_owner, PREV.rm_offset,
				PREV.rm_flags);
		error = xfs_btree_delete(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		error = xfs_btree_decrement(cur, 0, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		NEW = LEFT;
		NEW.rm_blockcount += PREV.rm_blockcount + RIGHT.rm_blockcount;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		break;

	case RMAP_LEFT_FILLING | RMAP_RIGHT_FILLING | RMAP_LEFT_CONTIG:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * The left neighbor is contiguous, the right is not.
		 */
		trace_xfs_rmap_delete(mp, cur->bc_private.a.agno,
				PREV.rm_startblock, PREV.rm_blockcount,
				PREV.rm_owner, PREV.rm_offset,
				PREV.rm_flags);
		error = xfs_btree_delete(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		error = xfs_btree_decrement(cur, 0, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		NEW = LEFT;
		NEW.rm_blockcount += PREV.rm_blockcount;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		break;

	case RMAP_LEFT_FILLING | RMAP_RIGHT_FILLING | RMAP_RIGHT_CONTIG:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * The right neighbor is contiguous, the left is not.
		 */
		error = xfs_btree_increment(cur, 0, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		trace_xfs_rmap_delete(mp, cur->bc_private.a.agno,
				RIGHT.rm_startblock, RIGHT.rm_blockcount,
				RIGHT.rm_owner, RIGHT.rm_offset,
				RIGHT.rm_flags);
		error = xfs_btree_delete(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		error = xfs_btree_decrement(cur, 0, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		NEW = PREV;
		NEW.rm_blockcount = len + RIGHT.rm_blockcount;
		NEW.rm_flags = newext;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		break;

	case RMAP_LEFT_FILLING | RMAP_RIGHT_FILLING:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * Neither the left nor right neighbors are contiguous with
		 * the new one.
		 */
		NEW = PREV;
		NEW.rm_flags = newext;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		break;

	case RMAP_LEFT_FILLING | RMAP_LEFT_CONTIG:
		/*
		 * Setting the first part of a previous oldext extent to newext.
		 * The left neighbor is contiguous.
		 */
		NEW = PREV;
		NEW.rm_offset += len;
		NEW.rm_startblock += len;
		NEW.rm_blockcount -= len;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		error = xfs_btree_decrement(cur, 0, &i);
		if (error)
			goto done;
		NEW = LEFT;
		NEW.rm_blockcount += len;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		break;

	case RMAP_LEFT_FILLING:
		/*
		 * Setting the first part of a previous oldext extent to newext.
		 * The left neighbor is not contiguous.
		 */
		NEW = PREV;
		NEW.rm_startblock += len;
		NEW.rm_offset += len;
		NEW.rm_blockcount -= len;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		NEW.rm_startblock = bno;
		NEW.rm_owner = owner;
		NEW.rm_offset = offset;
		NEW.rm_blockcount = len;
		NEW.rm_flags = newext;
		cur->bc_rec.r = NEW;
		trace_xfs_rmap_insert(mp, cur->bc_private.a.agno, bno,
				len, owner, offset, newext);
		error = xfs_btree_insert(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		break;

	case RMAP_RIGHT_FILLING | RMAP_RIGHT_CONTIG:
		/*
		 * Setting the last part of a previous oldext extent to newext.
		 * The right neighbor is contiguous with the new allocation.
		 */
		NEW = PREV;
		NEW.rm_blockcount -= len;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		error = xfs_btree_increment(cur, 0, &i);
		if (error)
			goto done;
		NEW = RIGHT;
		NEW.rm_offset = offset;
		NEW.rm_startblock = bno;
		NEW.rm_blockcount += len;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		break;

	case RMAP_RIGHT_FILLING:
		/*
		 * Setting the last part of a previous oldext extent to newext.
		 * The right neighbor is not contiguous.
		 */
		NEW = PREV;
		NEW.rm_blockcount -= len;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		error = xfs_rmap_lookup_eq(cur, bno, len, owner, offset,
				oldext, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
		NEW.rm_startblock = bno;
		NEW.rm_owner = owner;
		NEW.rm_offset = offset;
		NEW.rm_blockcount = len;
		NEW.rm_flags = newext;
		cur->bc_rec.r = NEW;
		trace_xfs_rmap_insert(mp, cur->bc_private.a.agno, bno,
				len, owner, offset, newext);
		error = xfs_btree_insert(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		break;

	case 0:
		/*
		 * Setting the middle part of a previous oldext extent to
		 * newext.  Contiguity is impossible here.
		 * One extent becomes three extents.
		 */
		/* new right extent - oldext */
		NEW.rm_startblock = bno + len;
		NEW.rm_owner = owner;
		NEW.rm_offset = new_endoff;
		NEW.rm_blockcount = PREV.rm_offset + PREV.rm_blockcount -
				new_endoff;
		NEW.rm_flags = PREV.rm_flags;
		error = xfs_rmap_update(cur, &NEW);
		if (error)
			goto done;
		/* new left extent - oldext */
		NEW = PREV;
		NEW.rm_blockcount = offset - PREV.rm_offset;
		cur->bc_rec.r = NEW;
		trace_xfs_rmap_insert(mp, cur->bc_private.a.agno,
				NEW.rm_startblock, NEW.rm_blockcount,
				NEW.rm_owner, NEW.rm_offset,
				NEW.rm_flags);
		error = xfs_btree_insert(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		/*
		 * Reset the cursor to the position of the new extent
		 * we are about to insert as we can't trust it after
		 * the previous insert.
		 */
		error = xfs_rmap_lookup_eq(cur, bno, len, owner, offset,
				oldext, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
		/* new middle extent - newext */
		cur->bc_rec.r.rm_flags &= ~XFS_RMAP_UNWRITTEN;
		cur->bc_rec.r.rm_flags |= newext;
		trace_xfs_rmap_insert(mp, cur->bc_private.a.agno, bno, len,
				owner, offset, newext);
		error = xfs_btree_insert(cur, &i);
		if (error)
			goto done;
		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
		break;

	case RMAP_LEFT_FILLING | RMAP_LEFT_CONTIG | RMAP_RIGHT_CONTIG:
	case RMAP_RIGHT_FILLING | RMAP_LEFT_CONTIG | RMAP_RIGHT_CONTIG:
	case RMAP_LEFT_FILLING | RMAP_RIGHT_CONTIG:
	case RMAP_RIGHT_FILLING | RMAP_LEFT_CONTIG:
	case RMAP_LEFT_CONTIG | RMAP_RIGHT_CONTIG:
	case RMAP_LEFT_CONTIG:
	case RMAP_RIGHT_CONTIG:
		/*
		 * These cases are all impossible.
		 */
		ASSERT(0);
	}

	trace_xfs_rmap_convert_done(mp, cur->bc_private.a.agno, bno, len,
			unwritten, oinfo);
done:
	if (error)
		trace_xfs_rmap_convert_error(cur->bc_mp,
				cur->bc_private.a.agno, error, _RET_IP_);
	return error;
}

#undef	NEW
#undef	LEFT
#undef	RIGHT
#undef	PREV

1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142
struct xfs_rmap_query_range_info {
	xfs_rmap_query_range_fn	fn;
	void				*priv;
};

/* Format btree record and pass to our callback. */
STATIC int
xfs_rmap_query_range_helper(
	struct xfs_btree_cur	*cur,
	union xfs_btree_rec	*rec,
	void			*priv)
{
	struct xfs_rmap_query_range_info	*query = priv;
	struct xfs_rmap_irec			irec;
	int					error;

	error = xfs_rmap_btrec_to_irec(rec, &irec);
	if (error)
		return error;
	return query->fn(cur, &irec, query->priv);
}

/* Find all rmaps between two keys. */
int
xfs_rmap_query_range(
	struct xfs_btree_cur		*cur,
	struct xfs_rmap_irec		*low_rec,
	struct xfs_rmap_irec		*high_rec,
	xfs_rmap_query_range_fn	fn,
	void				*priv)
{
	union xfs_btree_irec		low_brec;
	union xfs_btree_irec		high_brec;
	struct xfs_rmap_query_range_info	query;

	low_brec.r = *low_rec;
	high_brec.r = *high_rec;
	query.priv = priv;
	query.fn = fn;
	return xfs_btree_query_range(cur, &low_brec, &high_brec,
			xfs_rmap_query_range_helper, &query);
}
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265

/* Clean up after calling xfs_rmap_finish_one. */
void
xfs_rmap_finish_one_cleanup(
	struct xfs_trans	*tp,
	struct xfs_btree_cur	*rcur,
	int			error)
{
	struct xfs_buf		*agbp;

	if (rcur == NULL)
		return;
	agbp = rcur->bc_private.a.agbp;
	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
	if (error)
		xfs_trans_brelse(tp, agbp);
}

/*
 * Process one of the deferred rmap operations.  We pass back the
 * btree cursor to maintain our lock on the rmapbt between calls.
 * This saves time and eliminates a buffer deadlock between the
 * superblock and the AGF because we'll always grab them in the same
 * order.
 */
int
xfs_rmap_finish_one(
	struct xfs_trans		*tp,
	enum xfs_rmap_intent_type	type,
	__uint64_t			owner,
	int				whichfork,
	xfs_fileoff_t			startoff,
	xfs_fsblock_t			startblock,
	xfs_filblks_t			blockcount,
	xfs_exntst_t			state,
	struct xfs_btree_cur		**pcur)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_btree_cur		*rcur;
	struct xfs_buf			*agbp = NULL;
	int				error = 0;
	xfs_agnumber_t			agno;
	struct xfs_owner_info		oinfo;
	xfs_agblock_t			bno;
	bool				unwritten;

	agno = XFS_FSB_TO_AGNO(mp, startblock);
	ASSERT(agno != NULLAGNUMBER);
	bno = XFS_FSB_TO_AGBNO(mp, startblock);

	trace_xfs_rmap_deferred(mp, agno, type, bno, owner, whichfork,
			startoff, blockcount, state);

	if (XFS_TEST_ERROR(false, mp,
			XFS_ERRTAG_RMAP_FINISH_ONE,
			XFS_RANDOM_RMAP_FINISH_ONE))
		return -EIO;

	/*
	 * If we haven't gotten a cursor or the cursor AG doesn't match
	 * the startblock, get one now.
	 */
	rcur = *pcur;
	if (rcur != NULL && rcur->bc_private.a.agno != agno) {
		xfs_rmap_finish_one_cleanup(tp, rcur, 0);
		rcur = NULL;
		*pcur = NULL;
	}
	if (rcur == NULL) {
		/*
		 * Refresh the freelist before we start changing the
		 * rmapbt, because a shape change could cause us to
		 * allocate blocks.
		 */
		error = xfs_free_extent_fix_freelist(tp, agno, &agbp);
		if (error)
			return error;
		if (!agbp)
			return -EFSCORRUPTED;

		rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
		if (!rcur) {
			error = -ENOMEM;
			goto out_cur;
		}
	}
	*pcur = rcur;

	xfs_rmap_ino_owner(&oinfo, owner, whichfork, startoff);
	unwritten = state == XFS_EXT_UNWRITTEN;
	bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, startblock);

	switch (type) {
	case XFS_RMAP_ALLOC:
	case XFS_RMAP_MAP:
		error = xfs_rmap_map(rcur, bno, blockcount, unwritten, &oinfo);
		break;
	case XFS_RMAP_FREE:
	case XFS_RMAP_UNMAP:
		error = xfs_rmap_unmap(rcur, bno, blockcount, unwritten,
				&oinfo);
		break;
	case XFS_RMAP_CONVERT:
		error = xfs_rmap_convert(rcur, bno, blockcount, !unwritten,
				&oinfo);
		break;
	default:
		ASSERT(0);
		error = -EFSCORRUPTED;
	}
	return error;

out_cur:
	xfs_trans_brelse(tp, agbp);

	return error;
}

/*
 * Don't defer an rmap if we aren't an rmap filesystem.
 */
static bool
xfs_rmap_update_is_needed(
D
Darrick J. Wong 已提交
1266 1267
	struct xfs_mount	*mp,
	int			whichfork)
1268
{
D
Darrick J. Wong 已提交
1269
	return xfs_sb_version_hasrmapbt(&mp->m_sb) && whichfork != XFS_COW_FORK;
1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314
}

/*
 * Record a rmap intent; the list is kept sorted first by AG and then by
 * increasing age.
 */
static int
__xfs_rmap_add(
	struct xfs_mount		*mp,
	struct xfs_defer_ops		*dfops,
	enum xfs_rmap_intent_type	type,
	__uint64_t			owner,
	int				whichfork,
	struct xfs_bmbt_irec		*bmap)
{
	struct xfs_rmap_intent	*ri;

	trace_xfs_rmap_defer(mp, XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
			type,
			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
			owner, whichfork,
			bmap->br_startoff,
			bmap->br_blockcount,
			bmap->br_state);

	ri = kmem_alloc(sizeof(struct xfs_rmap_intent), KM_SLEEP | KM_NOFS);
	INIT_LIST_HEAD(&ri->ri_list);
	ri->ri_type = type;
	ri->ri_owner = owner;
	ri->ri_whichfork = whichfork;
	ri->ri_bmap = *bmap;

	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
	return 0;
}

/* Map an extent into a file. */
int
xfs_rmap_map_extent(
	struct xfs_mount	*mp,
	struct xfs_defer_ops	*dfops,
	struct xfs_inode	*ip,
	int			whichfork,
	struct xfs_bmbt_irec	*PREV)
{
D
Darrick J. Wong 已提交
1315
	if (!xfs_rmap_update_is_needed(mp, whichfork))
1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
		return 0;

	return __xfs_rmap_add(mp, dfops, XFS_RMAP_MAP, ip->i_ino,
			whichfork, PREV);
}

/* Unmap an extent out of a file. */
int
xfs_rmap_unmap_extent(
	struct xfs_mount	*mp,
	struct xfs_defer_ops	*dfops,
	struct xfs_inode	*ip,
	int			whichfork,
	struct xfs_bmbt_irec	*PREV)
{
D
Darrick J. Wong 已提交
1331
	if (!xfs_rmap_update_is_needed(mp, whichfork))
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346
		return 0;

	return __xfs_rmap_add(mp, dfops, XFS_RMAP_UNMAP, ip->i_ino,
			whichfork, PREV);
}

/* Convert a data fork extent from unwritten to real or vice versa. */
int
xfs_rmap_convert_extent(
	struct xfs_mount	*mp,
	struct xfs_defer_ops	*dfops,
	struct xfs_inode	*ip,
	int			whichfork,
	struct xfs_bmbt_irec	*PREV)
{
D
Darrick J. Wong 已提交
1347
	if (!xfs_rmap_update_is_needed(mp, whichfork))
1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365
		return 0;

	return __xfs_rmap_add(mp, dfops, XFS_RMAP_CONVERT, ip->i_ino,
			whichfork, PREV);
}

/* Schedule the creation of an rmap for non-file data. */
int
xfs_rmap_alloc_extent(
	struct xfs_mount	*mp,
	struct xfs_defer_ops	*dfops,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	__uint64_t		owner)
{
	struct xfs_bmbt_irec	bmap;

D
Darrick J. Wong 已提交
1366
	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389
		return 0;

	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
	bmap.br_blockcount = len;
	bmap.br_startoff = 0;
	bmap.br_state = XFS_EXT_NORM;

	return __xfs_rmap_add(mp, dfops, XFS_RMAP_ALLOC, owner,
			XFS_DATA_FORK, &bmap);
}

/* Schedule the deletion of an rmap for non-file data. */
int
xfs_rmap_free_extent(
	struct xfs_mount	*mp,
	struct xfs_defer_ops	*dfops,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	__uint64_t		owner)
{
	struct xfs_bmbt_irec	bmap;

D
Darrick J. Wong 已提交
1390
	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
1391 1392 1393 1394 1395 1396 1397 1398 1399 1400
		return 0;

	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
	bmap.br_blockcount = len;
	bmap.br_startoff = 0;
	bmap.br_state = XFS_EXT_NORM;

	return __xfs_rmap_add(mp, dfops, XFS_RMAP_FREE, owner,
			XFS_DATA_FORK, &bmap);
}