btree.c 13.8 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 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
/*
 * Copyright (C) 2017 Oracle.  All Rights Reserved.
 *
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 *
 * 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; either version 2
 * of the License, or (at your option) any later version.
 *
 * 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_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_btree.h"
#include "xfs_bit.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"

/* btree scrubbing */

/*
 * Check for btree operation errors.  See the section about handling
 * operational errors in common.c.
 */
bool
xfs_scrub_btree_process_error(
	struct xfs_scrub_context	*sc,
	struct xfs_btree_cur		*cur,
	int				level,
	int				*error)
{
	if (*error == 0)
		return true;

	switch (*error) {
	case -EDEADLOCK:
		/* Used to restart an op with deadlock avoidance. */
		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
		break;
	case -EFSBADCRC:
	case -EFSCORRUPTED:
		/* Note the badness but don't abort. */
		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
		*error = 0;
		/* fall through */
	default:
		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
			trace_xfs_scrub_ifork_btree_op_error(sc, cur, level,
					*error, __return_address);
		else
			trace_xfs_scrub_btree_op_error(sc, cur, level,
					*error, __return_address);
		break;
	}
	return false;
}

/* Record btree block corruption. */
void
xfs_scrub_btree_set_corrupt(
	struct xfs_scrub_context	*sc,
	struct xfs_btree_cur		*cur,
	int				level)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;

	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
		trace_xfs_scrub_ifork_btree_error(sc, cur, level,
				__return_address);
	else
		trace_xfs_scrub_btree_error(sc, cur, level,
				__return_address);
}

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
/*
 * Make sure this record is in order and doesn't stray outside of the parent
 * keys.
 */
STATIC void
xfs_scrub_btree_rec(
	struct xfs_scrub_btree	*bs)
{
	struct xfs_btree_cur	*cur = bs->cur;
	union xfs_btree_rec	*rec;
	union xfs_btree_key	key;
	union xfs_btree_key	hkey;
	union xfs_btree_key	*keyp;
	struct xfs_btree_block	*block;
	struct xfs_btree_block	*keyblock;
	struct xfs_buf		*bp;

	block = xfs_btree_get_block(cur, 0, &bp);
	rec = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);

	trace_xfs_scrub_btree_rec(bs->sc, cur, 0);

	/* If this isn't the first record, are they in order? */
	if (!bs->firstrec && !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
		xfs_scrub_btree_set_corrupt(bs->sc, cur, 0);
	bs->firstrec = false;
	memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len);

	if (cur->bc_nlevels == 1)
		return;

	/* Is this at least as large as the parent low key? */
	cur->bc_ops->init_key_from_rec(&key, rec);
	keyblock = xfs_btree_get_block(cur, 1, &bp);
	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[1], keyblock);
	if (cur->bc_ops->diff_two_keys(cur, &key, keyp) < 0)
		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Is this no larger than the parent high key? */
	cur->bc_ops->init_high_key_from_rec(&hkey, rec);
	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[1], keyblock);
	if (cur->bc_ops->diff_two_keys(cur, keyp, &hkey) < 0)
		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
}

/*
 * Make sure this key is in order and doesn't stray outside of the parent
 * keys.
 */
STATIC void
xfs_scrub_btree_key(
	struct xfs_scrub_btree	*bs,
	int			level)
{
	struct xfs_btree_cur	*cur = bs->cur;
	union xfs_btree_key	*key;
	union xfs_btree_key	*keyp;
	struct xfs_btree_block	*block;
	struct xfs_btree_block	*keyblock;
	struct xfs_buf		*bp;

	block = xfs_btree_get_block(cur, level, &bp);
	key = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);

	trace_xfs_scrub_btree_key(bs->sc, cur, level);

	/* If this isn't the first key, are they in order? */
	if (!bs->firstkey[level] &&
	    !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level], key))
		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
	bs->firstkey[level] = false;
	memcpy(&bs->lastkey[level], key, cur->bc_ops->key_len);

	if (level + 1 >= cur->bc_nlevels)
		return;

	/* Is this at least as large as the parent low key? */
	keyblock = xfs_btree_get_block(cur, level + 1, &bp);
	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
	if (cur->bc_ops->diff_two_keys(cur, key, keyp) < 0)
		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Is this no larger than the parent high key? */
	key = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
	if (cur->bc_ops->diff_two_keys(cur, keyp, key) < 0)
		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
}

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
/*
 * Check a btree pointer.  Returns true if it's ok to use this pointer.
 * Callers do not need to set the corrupt flag.
 */
static bool
xfs_scrub_btree_ptr_ok(
	struct xfs_scrub_btree		*bs,
	int				level,
	union xfs_btree_ptr		*ptr)
{
	bool				res;

	/* A btree rooted in an inode has no block pointer to the root. */
	if ((bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
	    level == bs->cur->bc_nlevels)
		return true;

	/* Otherwise, check the pointers. */
	if (bs->cur->bc_flags & XFS_BTREE_LONG_PTRS)
		res = xfs_btree_check_lptr(bs->cur, be64_to_cpu(ptr->l), level);
	else
		res = xfs_btree_check_sptr(bs->cur, be32_to_cpu(ptr->s), level);
	if (!res)
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);

	return res;
}

/* Check that a btree block's sibling matches what we expect it. */
STATIC int
xfs_scrub_btree_block_check_sibling(
	struct xfs_scrub_btree		*bs,
	int				level,
	int				direction,
	union xfs_btree_ptr		*sibling)
{
	struct xfs_btree_cur		*cur = bs->cur;
	struct xfs_btree_block		*pblock;
	struct xfs_buf			*pbp;
	struct xfs_btree_cur		*ncur = NULL;
	union xfs_btree_ptr		*pp;
	int				success;
	int				error;

	error = xfs_btree_dup_cursor(cur, &ncur);
	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error) ||
	    !ncur)
		return error;

	/*
	 * If the pointer is null, we shouldn't be able to move the upper
	 * level pointer anywhere.
	 */
	if (xfs_btree_ptr_is_null(cur, sibling)) {
		if (direction > 0)
			error = xfs_btree_increment(ncur, level + 1, &success);
		else
			error = xfs_btree_decrement(ncur, level + 1, &success);
		if (error == 0 && success)
			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
		error = 0;
		goto out;
	}

	/* Increment upper level pointer. */
	if (direction > 0)
		error = xfs_btree_increment(ncur, level + 1, &success);
	else
		error = xfs_btree_decrement(ncur, level + 1, &success);
	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error))
		goto out;
	if (!success) {
		xfs_scrub_btree_set_corrupt(bs->sc, cur, level + 1);
		goto out;
	}

	/* Compare upper level pointer to sibling pointer. */
	pblock = xfs_btree_get_block(ncur, level + 1, &pbp);
	pp = xfs_btree_ptr_addr(ncur, ncur->bc_ptrs[level + 1], pblock);
	if (!xfs_scrub_btree_ptr_ok(bs, level + 1, pp))
		goto out;

	if (xfs_btree_diff_two_ptrs(cur, pp, sibling))
		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
out:
	xfs_btree_del_cursor(ncur, XFS_BTREE_ERROR);
	return error;
}

/* Check the siblings of a btree block. */
STATIC int
xfs_scrub_btree_block_check_siblings(
	struct xfs_scrub_btree		*bs,
	struct xfs_btree_block		*block)
{
	struct xfs_btree_cur		*cur = bs->cur;
	union xfs_btree_ptr		leftsib;
	union xfs_btree_ptr		rightsib;
	int				level;
	int				error = 0;

	xfs_btree_get_sibling(cur, block, &leftsib, XFS_BB_LEFTSIB);
	xfs_btree_get_sibling(cur, block, &rightsib, XFS_BB_RIGHTSIB);
	level = xfs_btree_get_level(block);

	/* Root block should never have siblings. */
	if (level == cur->bc_nlevels - 1) {
		if (!xfs_btree_ptr_is_null(cur, &leftsib) ||
		    !xfs_btree_ptr_is_null(cur, &rightsib))
			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
		goto out;
	}

	/*
	 * Does the left & right sibling pointers match the adjacent
	 * parent level pointers?
	 * (These function absorbs error codes for us.)
	 */
	error = xfs_scrub_btree_block_check_sibling(bs, level, -1, &leftsib);
	if (error)
		return error;
	error = xfs_scrub_btree_block_check_sibling(bs, level, 1, &rightsib);
	if (error)
		return error;
out:
	return error;
}

/*
 * Grab and scrub a btree block given a btree pointer.  Returns block
 * and buffer pointers (if applicable) if they're ok to use.
 */
STATIC int
xfs_scrub_btree_get_block(
	struct xfs_scrub_btree		*bs,
	int				level,
	union xfs_btree_ptr		*pp,
	struct xfs_btree_block		**pblock,
	struct xfs_buf			**pbp)
{
	void				*failed_at;
	int				error;

	*pblock = NULL;
	*pbp = NULL;

	error = xfs_btree_lookup_get_block(bs->cur, level, pp, pblock);
	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, level, &error) ||
338
	    !*pblock)
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
		return error;

	xfs_btree_get_block(bs->cur, level, pbp);
	if (bs->cur->bc_flags & XFS_BTREE_LONG_PTRS)
		failed_at = __xfs_btree_check_lblock(bs->cur, *pblock,
				level, *pbp);
	else
		failed_at = __xfs_btree_check_sblock(bs->cur, *pblock,
				 level, *pbp);
	if (failed_at) {
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
		return 0;
	}

	/*
	 * Check the block's siblings; this function absorbs error codes
	 * for us.
	 */
	return xfs_scrub_btree_block_check_siblings(bs, *pblock);
}

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
/*
 * Check that the low and high keys of this block match the keys stored
 * in the parent block.
 */
STATIC void
xfs_scrub_btree_block_keys(
	struct xfs_scrub_btree		*bs,
	int				level,
	struct xfs_btree_block		*block)
{
	union xfs_btree_key		block_keys;
	struct xfs_btree_cur		*cur = bs->cur;
	union xfs_btree_key		*high_bk;
	union xfs_btree_key		*parent_keys;
	union xfs_btree_key		*high_pk;
	struct xfs_btree_block		*parent_block;
	struct xfs_buf			*bp;

	if (level >= cur->bc_nlevels - 1)
		return;

	/* Calculate the keys for this block. */
	xfs_btree_get_keys(cur, block, &block_keys);

	/* Obtain the parent's copy of the keys for this block. */
	parent_block = xfs_btree_get_block(cur, level + 1, &bp);
	parent_keys = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1],
			parent_block);

	if (cur->bc_ops->diff_two_keys(cur, &block_keys, parent_keys) != 0)
		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Get high keys */
	high_bk = xfs_btree_high_key_from_key(cur, &block_keys);
	high_pk = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1],
			parent_block);

	if (cur->bc_ops->diff_two_keys(cur, high_bk, high_pk) != 0)
		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
}

404 405 406
/*
 * Visit all nodes and leaves of a btree.  Check that all pointers and
 * records are in order, that the keys reflect the records, and use a callback
407
 * so that the caller can verify individual records.
408 409 410 411 412 413 414 415 416
 */
int
xfs_scrub_btree(
	struct xfs_scrub_context	*sc,
	struct xfs_btree_cur		*cur,
	xfs_scrub_btree_rec_fn		scrub_fn,
	struct xfs_owner_info		*oinfo,
	void				*private)
{
417
	struct xfs_scrub_btree		bs = { NULL };
418 419
	union xfs_btree_ptr		ptr;
	union xfs_btree_ptr		*pp;
420
	union xfs_btree_rec		*recp;
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
	struct xfs_btree_block		*block;
	int				level;
	struct xfs_buf			*bp;
	int				i;
	int				error = 0;

	/* Initialize scrub state */
	bs.cur = cur;
	bs.scrub_rec = scrub_fn;
	bs.oinfo = oinfo;
	bs.firstrec = true;
	bs.private = private;
	bs.sc = sc;
	for (i = 0; i < XFS_BTREE_MAXLEVELS; i++)
		bs.firstkey[i] = true;
	INIT_LIST_HEAD(&bs.to_check);

	/* Don't try to check a tree with a height we can't handle. */
	if (cur->bc_nlevels > XFS_BTREE_MAXLEVELS) {
		xfs_scrub_btree_set_corrupt(sc, cur, 0);
		goto out;
	}

	/*
	 * Load the root of the btree.  The helper function absorbs
	 * error codes for us.
	 */
	level = cur->bc_nlevels - 1;
	cur->bc_ops->init_ptr_from_cur(cur, &ptr);
	if (!xfs_scrub_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
		goto out;
	error = xfs_scrub_btree_get_block(&bs, level, &ptr, &block, &bp);
	if (error || !block)
		goto out;

	cur->bc_ptrs[level] = 1;

	while (level < cur->bc_nlevels) {
		block = xfs_btree_get_block(cur, level, &bp);

		if (level == 0) {
			/* End of leaf, pop back towards the root. */
			if (cur->bc_ptrs[level] >
			    be16_to_cpu(block->bb_numrecs)) {
465
				xfs_scrub_btree_block_keys(&bs, level, block);
466 467 468 469 470 471
				if (level < cur->bc_nlevels - 1)
					cur->bc_ptrs[level + 1]++;
				level++;
				continue;
			}

472 473 474 475 476 477 478 479 480 481
			/* Records in order for scrub? */
			xfs_scrub_btree_rec(&bs);

			/* Call out to the record checker. */
			recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
			error = bs.scrub_rec(&bs, recp);
			if (error)
				break;
			if (xfs_scrub_should_terminate(sc, &error) ||
			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
482 483 484 485 486 487 488 489
				break;

			cur->bc_ptrs[level]++;
			continue;
		}

		/* End of node, pop back towards the root. */
		if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
490
			xfs_scrub_btree_block_keys(&bs, level, block);
491 492 493 494 495 496
			if (level < cur->bc_nlevels - 1)
				cur->bc_ptrs[level + 1]++;
			level++;
			continue;
		}

497 498 499
		/* Keys in order for scrub? */
		xfs_scrub_btree_key(&bs, level);

500 501 502 503 504 505 506 507 508 509 510 511 512
		/* Drill another level deeper. */
		pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
		if (!xfs_scrub_btree_ptr_ok(&bs, level, pp)) {
			cur->bc_ptrs[level]++;
			continue;
		}
		level--;
		error = xfs_scrub_btree_get_block(&bs, level, pp, &block, &bp);
		if (error || !block)
			goto out;

		cur->bc_ptrs[level] = 1;
	}
513

514
out:
515 516
	return error;
}