inode.c 19.5 KB
Newer Older
D
Darrick J. Wong 已提交
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
/*
 * 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_icache.h"
#include "xfs_inode_buf.h"
#include "xfs_inode_fork.h"
#include "xfs_ialloc.h"
#include "xfs_da_format.h"
#include "xfs_reflink.h"
39
#include "xfs_rmap.h"
40 41
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
D
Darrick J. Wong 已提交
42 43 44
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
45
#include "scrub/btree.h"
D
Darrick J. Wong 已提交
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
#include "scrub/trace.h"

/*
 * Grab total control of the inode metadata.  It doesn't matter here if
 * the file data is still changing; exclusive access to the metadata is
 * the goal.
 */
int
xfs_scrub_setup_inode(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip)
{
	struct xfs_mount		*mp = sc->mp;
	int				error;

	/*
	 * Try to get the inode.  If the verifiers fail, we try again
	 * in raw mode.
	 */
	error = xfs_scrub_get_inode(sc, ip);
	switch (error) {
	case 0:
		break;
	case -EFSCORRUPTED:
	case -EFSBADCRC:
71
		return xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
D
Darrick J. Wong 已提交
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
	default:
		return error;
	}

	/* Got the inode, lock it and we're ready to go. */
	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
	xfs_ilock(sc->ip, sc->ilock_flags);
	error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
	if (error)
		goto out;
	sc->ilock_flags |= XFS_ILOCK_EXCL;
	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);

out:
	/* scrub teardown will unlock and release the inode for us */
	return error;
}

/* Inode core */

/*
 * Validate di_extsize hint.
 *
 * The rules are documented at xfs_ioctl_setattr_check_extsize().
 * These functions must be kept in sync with each other.
 */
STATIC void
xfs_scrub_inode_extsize(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp,
	struct xfs_dinode		*dip,
	xfs_ino_t			ino,
	uint16_t			mode,
	uint16_t			flags)
{
	struct xfs_mount		*mp = sc->mp;
	bool				rt_flag;
	bool				hint_flag;
	bool				inherit_flag;
	uint32_t			extsize;
	uint32_t			extsize_bytes;
	uint32_t			blocksize_bytes;

	rt_flag = (flags & XFS_DIFLAG_REALTIME);
	hint_flag = (flags & XFS_DIFLAG_EXTSIZE);
	inherit_flag = (flags & XFS_DIFLAG_EXTSZINHERIT);
	extsize = be32_to_cpu(dip->di_extsize);
	extsize_bytes = XFS_FSB_TO_B(sc->mp, extsize);

	if (rt_flag)
		blocksize_bytes = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
	else
		blocksize_bytes = mp->m_sb.sb_blocksize;

	if ((hint_flag || inherit_flag) && !(S_ISDIR(mode) || S_ISREG(mode)))
		goto bad;

	if (hint_flag && !S_ISREG(mode))
		goto bad;

	if (inherit_flag && !S_ISDIR(mode))
		goto bad;

	if ((hint_flag || inherit_flag) && extsize == 0)
		goto bad;

	if (!(hint_flag || inherit_flag) && extsize != 0)
		goto bad;

	if (extsize_bytes % blocksize_bytes)
		goto bad;

	if (extsize > MAXEXTLEN)
		goto bad;

	if (!rt_flag && extsize > mp->m_sb.sb_agblocks / 2)
		goto bad;

	return;
bad:
	xfs_scrub_ino_set_corrupt(sc, ino, bp);
}

/*
 * Validate di_cowextsize hint.
 *
 * The rules are documented at xfs_ioctl_setattr_check_cowextsize().
 * These functions must be kept in sync with each other.
 */
STATIC void
xfs_scrub_inode_cowextsize(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp,
	struct xfs_dinode		*dip,
	xfs_ino_t			ino,
	uint16_t			mode,
	uint16_t			flags,
	uint64_t			flags2)
{
	struct xfs_mount		*mp = sc->mp;
	bool				rt_flag;
	bool				hint_flag;
	uint32_t			extsize;
	uint32_t			extsize_bytes;

	rt_flag = (flags & XFS_DIFLAG_REALTIME);
	hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE);
	extsize = be32_to_cpu(dip->di_cowextsize);
	extsize_bytes = XFS_FSB_TO_B(sc->mp, extsize);

	if (hint_flag && !xfs_sb_version_hasreflink(&mp->m_sb))
		goto bad;

	if (hint_flag && !(S_ISDIR(mode) || S_ISREG(mode)))
		goto bad;

	if (hint_flag && extsize == 0)
		goto bad;

	if (!hint_flag && extsize != 0)
		goto bad;

	if (hint_flag && rt_flag)
		goto bad;

	if (extsize_bytes % mp->m_sb.sb_blocksize)
		goto bad;

	if (extsize > MAXEXTLEN)
		goto bad;

	if (extsize > mp->m_sb.sb_agblocks / 2)
		goto bad;

	return;
bad:
	xfs_scrub_ino_set_corrupt(sc, ino, bp);
}

/* Make sure the di_flags make sense for the inode. */
STATIC void
xfs_scrub_inode_flags(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp,
	struct xfs_dinode		*dip,
	xfs_ino_t			ino,
	uint16_t			mode,
	uint16_t			flags)
{
	struct xfs_mount		*mp = sc->mp;

	if (flags & ~XFS_DIFLAG_ANY)
		goto bad;

	/* rt flags require rt device */
	if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) &&
	    !mp->m_rtdev_targp)
		goto bad;

	/* new rt bitmap flag only valid for rbmino */
	if ((flags & XFS_DIFLAG_NEWRTBM) && ino != mp->m_sb.sb_rbmino)
		goto bad;

	/* directory-only flags */
	if ((flags & (XFS_DIFLAG_RTINHERIT |
		     XFS_DIFLAG_EXTSZINHERIT |
		     XFS_DIFLAG_PROJINHERIT |
		     XFS_DIFLAG_NOSYMLINKS)) &&
	    !S_ISDIR(mode))
		goto bad;

	/* file-only flags */
	if ((flags & (XFS_DIFLAG_REALTIME | FS_XFLAG_EXTSIZE)) &&
	    !S_ISREG(mode))
		goto bad;

	/* filestreams and rt make no sense */
	if ((flags & XFS_DIFLAG_FILESTREAM) && (flags & XFS_DIFLAG_REALTIME))
		goto bad;

	return;
bad:
	xfs_scrub_ino_set_corrupt(sc, ino, bp);
}

/* Make sure the di_flags2 make sense for the inode. */
STATIC void
xfs_scrub_inode_flags2(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp,
	struct xfs_dinode		*dip,
	xfs_ino_t			ino,
	uint16_t			mode,
	uint16_t			flags,
	uint64_t			flags2)
{
	struct xfs_mount		*mp = sc->mp;

	if (flags2 & ~XFS_DIFLAG2_ANY)
		goto bad;

	/* reflink flag requires reflink feature */
	if ((flags2 & XFS_DIFLAG2_REFLINK) &&
	    !xfs_sb_version_hasreflink(&mp->m_sb))
		goto bad;

	/* cowextsize flag is checked w.r.t. mode separately */

	/* file/dir-only flags */
	if ((flags2 & XFS_DIFLAG2_DAX) && !(S_ISREG(mode) || S_ISDIR(mode)))
		goto bad;

	/* file-only flags */
	if ((flags2 & XFS_DIFLAG2_REFLINK) && !S_ISREG(mode))
		goto bad;

	/* realtime and reflink make no sense, currently */
	if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK))
		goto bad;

	/* dax and reflink make no sense, currently */
	if ((flags2 & XFS_DIFLAG2_DAX) && (flags2 & XFS_DIFLAG2_REFLINK))
		goto bad;

	return;
bad:
	xfs_scrub_ino_set_corrupt(sc, ino, bp);
}

/* Scrub all the ondisk inode fields. */
STATIC void
xfs_scrub_dinode(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp,
	struct xfs_dinode		*dip,
	xfs_ino_t			ino)
{
	struct xfs_mount		*mp = sc->mp;
	size_t				fork_recs;
	unsigned long long		isize;
	uint64_t			flags2;
	uint32_t			nextents;
	uint16_t			flags;
	uint16_t			mode;

	flags = be16_to_cpu(dip->di_flags);
	if (dip->di_version >= 3)
		flags2 = be64_to_cpu(dip->di_flags2);
	else
		flags2 = 0;

	/* di_mode */
	mode = be16_to_cpu(dip->di_mode);
D
Darrick J. Wong 已提交
325 326 327 328 329 330 331 332 333 334 335
	switch (mode & S_IFMT) {
	case S_IFLNK:
	case S_IFREG:
	case S_IFDIR:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFIFO:
	case S_IFSOCK:
		/* mode is recognized */
		break;
	default:
D
Darrick J. Wong 已提交
336
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
D
Darrick J. Wong 已提交
337 338
		break;
	}
D
Darrick J. Wong 已提交
339 340 341 342 343 344 345 346

	/* v1/v2 fields */
	switch (dip->di_version) {
	case 1:
		/*
		 * We autoconvert v1 inodes into v2 inodes on writeout,
		 * so just mark this inode for preening.
		 */
347
		xfs_scrub_ino_set_preen(sc, ino, bp);
D
Darrick J. Wong 已提交
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
		break;
	case 2:
	case 3:
		if (dip->di_onlink != 0)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);

		if (dip->di_mode == 0 && sc->ip)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);

		if (dip->di_projid_hi != 0 &&
		    !xfs_sb_version_hasprojid32bit(&mp->m_sb))
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	default:
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
		return;
	}

	/*
	 * di_uid/di_gid -- -1 isn't invalid, but there's no way that
	 * userspace could have created that.
	 */
	if (dip->di_uid == cpu_to_be32(-1U) ||
	    dip->di_gid == cpu_to_be32(-1U))
372
		xfs_scrub_ino_set_warning(sc, ino, bp);
D
Darrick J. Wong 已提交
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

	/* di_format */
	switch (dip->di_format) {
	case XFS_DINODE_FMT_DEV:
		if (!S_ISCHR(mode) && !S_ISBLK(mode) &&
		    !S_ISFIFO(mode) && !S_ISSOCK(mode))
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	case XFS_DINODE_FMT_LOCAL:
		if (!S_ISDIR(mode) && !S_ISLNK(mode))
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	case XFS_DINODE_FMT_EXTENTS:
		if (!S_ISREG(mode) && !S_ISDIR(mode) && !S_ISLNK(mode))
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	case XFS_DINODE_FMT_BTREE:
		if (!S_ISREG(mode) && !S_ISDIR(mode))
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	case XFS_DINODE_FMT_UUID:
	default:
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	}

D
Darrick J. Wong 已提交
399 400 401 402 403 404 405 406
	/* di_[amc]time.nsec */
	if (be32_to_cpu(dip->di_atime.t_nsec) >= NSEC_PER_SEC)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
	if (be32_to_cpu(dip->di_mtime.t_nsec) >= NSEC_PER_SEC)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
	if (be32_to_cpu(dip->di_ctime.t_nsec) >= NSEC_PER_SEC)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

D
Darrick J. Wong 已提交
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
	/*
	 * di_size.  xfs_dinode_verify checks for things that screw up
	 * the VFS such as the upper bit being set and zero-length
	 * symlinks/directories, but we can do more here.
	 */
	isize = be64_to_cpu(dip->di_size);
	if (isize & (1ULL << 63))
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

	/* Devices, fifos, and sockets must have zero size */
	if (!S_ISDIR(mode) && !S_ISREG(mode) && !S_ISLNK(mode) && isize != 0)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

	/* Directories can't be larger than the data section size (32G) */
	if (S_ISDIR(mode) && (isize == 0 || isize >= XFS_DIR2_SPACE_SIZE))
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

	/* Symlinks can't be larger than SYMLINK_MAXLEN */
	if (S_ISLNK(mode) && (isize == 0 || isize >= XFS_SYMLINK_MAXLEN))
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

	/*
	 * Warn if the running kernel can't handle the kinds of offsets
	 * needed to deal with the file size.  In other words, if the
	 * pagecache can't cache all the blocks in this file due to
	 * overly large offsets, flag the inode for admin review.
	 */
	if (isize >= mp->m_super->s_maxbytes)
435
		xfs_scrub_ino_set_warning(sc, ino, bp);
D
Darrick J. Wong 已提交
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

	/* di_nblocks */
	if (flags2 & XFS_DIFLAG2_REFLINK) {
		; /* nblocks can exceed dblocks */
	} else if (flags & XFS_DIFLAG_REALTIME) {
		/*
		 * nblocks is the sum of data extents (in the rtdev),
		 * attr extents (in the datadev), and both forks' bmbt
		 * blocks (in the datadev).  This clumsy check is the
		 * best we can do without cross-referencing with the
		 * inode forks.
		 */
		if (be64_to_cpu(dip->di_nblocks) >=
		    mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
	} else {
		if (be64_to_cpu(dip->di_nblocks) >= mp->m_sb.sb_dblocks)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
	}

	xfs_scrub_inode_flags(sc, bp, dip, ino, mode, flags);

	xfs_scrub_inode_extsize(sc, bp, dip, ino, mode, flags);

	/* di_nextents */
	nextents = be32_to_cpu(dip->di_nextents);
	fork_recs =  XFS_DFORK_DSIZE(dip, mp) / sizeof(struct xfs_bmbt_rec);
	switch (dip->di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		if (nextents > fork_recs)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	case XFS_DINODE_FMT_BTREE:
		if (nextents <= fork_recs)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	default:
		if (nextents != 0)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	}

	/* di_forkoff */
	if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
	if (dip->di_anextents != 0 && dip->di_forkoff == 0)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
	if (dip->di_forkoff == 0 && dip->di_aformat != XFS_DINODE_FMT_EXTENTS)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

	/* di_aformat */
	if (dip->di_aformat != XFS_DINODE_FMT_LOCAL &&
	    dip->di_aformat != XFS_DINODE_FMT_EXTENTS &&
	    dip->di_aformat != XFS_DINODE_FMT_BTREE)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);

	/* di_anextents */
	nextents = be16_to_cpu(dip->di_anextents);
	fork_recs =  XFS_DFORK_ASIZE(dip, mp) / sizeof(struct xfs_bmbt_rec);
	switch (dip->di_aformat) {
	case XFS_DINODE_FMT_EXTENTS:
		if (nextents > fork_recs)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	case XFS_DINODE_FMT_BTREE:
		if (nextents <= fork_recs)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
		break;
	default:
		if (nextents != 0)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
	}

	if (dip->di_version >= 3) {
D
Darrick J. Wong 已提交
510 511
		if (be32_to_cpu(dip->di_crtime.t_nsec) >= NSEC_PER_SEC)
			xfs_scrub_ino_set_corrupt(sc, ino, bp);
D
Darrick J. Wong 已提交
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
		xfs_scrub_inode_flags2(sc, bp, dip, ino, mode, flags, flags2);
		xfs_scrub_inode_cowextsize(sc, bp, dip, ino, mode, flags,
				flags2);
	}
}

/* Map and read a raw inode. */
STATIC int
xfs_scrub_inode_map_raw(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino,
	struct xfs_buf			**bpp,
	struct xfs_dinode		**dipp)
{
	struct xfs_imap			imap;
	struct xfs_mount		*mp = sc->mp;
	struct xfs_buf			*bp = NULL;
	struct xfs_dinode		*dip;
	int				error;

	error = xfs_imap(mp, sc->tp, ino, &imap, XFS_IGET_UNTRUSTED);
	if (error == -EINVAL) {
		/*
		 * Inode could have gotten deleted out from under us;
		 * just forget about it.
		 */
		error = -ENOENT;
		goto out;
	}
	if (!xfs_scrub_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
			XFS_INO_TO_AGBNO(mp, ino), &error))
		goto out;

	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
			imap.im_blkno, imap.im_len, XBF_UNMAPPED, &bp,
			NULL);
	if (!xfs_scrub_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
			XFS_INO_TO_AGBNO(mp, ino), &error))
		goto out;

	/*
	 * Is this really an inode?  We disabled verifiers in the above
	 * xfs_trans_read_buf call because the inode buffer verifier
	 * fails on /any/ inode record in the inode cluster with a bad
	 * magic or version number, not just the one that we're
	 * checking.  Therefore, grab the buffer unconditionally, attach
	 * the inode verifiers by hand, and run the inode verifier only
	 * on the one inode we want.
	 */
	bp->b_ops = &xfs_inode_buf_ops;
	dip = xfs_buf_offset(bp, imap.im_boffset);
563
	if (xfs_dinode_verify(mp, ino, dip) != NULL ||
D
Darrick J. Wong 已提交
564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583
	    !xfs_dinode_good_version(mp, dip->di_version)) {
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
		goto out_buf;
	}

	/* ...and is it the one we asked for? */
	if (be32_to_cpu(dip->di_gen) != sc->sm->sm_gen) {
		error = -ENOENT;
		goto out_buf;
	}

	*dipp = dip;
	*bpp = bp;
out:
	return error;
out_buf:
	xfs_trans_brelse(sc->tp, bp);
	return error;
}

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
/*
 * Make sure the finobt doesn't think this inode is free.
 * We don't have to check the inobt ourselves because we got the inode via
 * IGET_UNTRUSTED, which checks the inobt for us.
 */
static void
xfs_scrub_inode_xref_finobt(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino)
{
	struct xfs_inobt_rec_incore	rec;
	xfs_agino_t			agino;
	int				has_record;
	int				error;

	if (!sc->sa.fino_cur)
		return;

	agino = XFS_INO_TO_AGINO(sc->mp, ino);

	/*
	 * Try to get the finobt record.  If we can't get it, then we're
	 * in good shape.
	 */
	error = xfs_inobt_lookup(sc->sa.fino_cur, agino, XFS_LOOKUP_LE,
			&has_record);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
	    !has_record)
		return;

	error = xfs_inobt_get_rec(sc->sa.fino_cur, &rec, &has_record);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
	    !has_record)
		return;

	/*
	 * Otherwise, make sure this record either doesn't cover this inode,
	 * or that it does but it's marked present.
	 */
	if (rec.ir_startino > agino ||
	    rec.ir_startino + XFS_INODES_PER_CHUNK <= agino)
		return;

	if (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
}

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
/* Cross reference the inode fields with the forks. */
STATIC void
xfs_scrub_inode_xref_bmap(
	struct xfs_scrub_context	*sc,
	struct xfs_dinode		*dip)
{
	xfs_extnum_t			nextents;
	xfs_filblks_t			count;
	xfs_filblks_t			acount;
	int				error;

	/* Walk all the extents to check nextents/naextents/nblocks. */
	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
			&nextents, &count);
	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
		return;
	if (nextents < be32_to_cpu(dip->di_nextents))
		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino, NULL);

	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
			&nextents, &acount);
	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
		return;
	if (nextents != be16_to_cpu(dip->di_anextents))
		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino, NULL);

	/* Check nblocks against the inode. */
	if (count + acount != be64_to_cpu(dip->di_nblocks))
		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino, NULL);
}

662 663 664 665 666 667 668
/* Cross-reference with the other btrees. */
STATIC void
xfs_scrub_inode_xref(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino,
	struct xfs_dinode		*dip)
{
669
	struct xfs_owner_info		oinfo;
670 671 672 673
	xfs_agnumber_t			agno;
	xfs_agblock_t			agbno;
	int				error;

674 675
	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
		return;
676 677 678 679 680 681 682 683 684

	agno = XFS_INO_TO_AGNO(sc->mp, ino);
	agbno = XFS_INO_TO_AGBNO(sc->mp, ino);

	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
		return;

	xfs_scrub_xref_is_used_space(sc, agbno, 1);
685
	xfs_scrub_inode_xref_finobt(sc, ino);
686 687
	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
688
	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
689
	xfs_scrub_inode_xref_bmap(sc, dip);
690 691

	xfs_scrub_ag_free(sc, &sc->sa);
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
/*
 * If the reflink iflag disagrees with a scan for shared data fork extents,
 * either flag an error (shared extents w/ no flag) or a preen (flag set w/o
 * any shared extents).  We already checked for reflink iflag set on a non
 * reflink filesystem.
 */
static void
xfs_scrub_inode_check_reflink_iflag(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino,
	struct xfs_buf			*bp)
{
	struct xfs_mount		*mp = sc->mp;
	bool				has_shared;
	int				error;

	if (!xfs_sb_version_hasreflink(&mp->m_sb))
		return;

	error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
			&has_shared);
	if (!xfs_scrub_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
			XFS_INO_TO_AGBNO(mp, ino), &error))
		return;
	if (xfs_is_reflink_inode(sc->ip) && !has_shared)
		xfs_scrub_ino_set_preen(sc, ino, bp);
	else if (!xfs_is_reflink_inode(sc->ip) && has_shared)
		xfs_scrub_ino_set_corrupt(sc, ino, bp);
}

D
Darrick J. Wong 已提交
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
/* Scrub an inode. */
int
xfs_scrub_inode(
	struct xfs_scrub_context	*sc)
{
	struct xfs_dinode		di;
	struct xfs_buf			*bp = NULL;
	struct xfs_dinode		*dip;
	xfs_ino_t			ino;
	int				error = 0;

	/* Did we get the in-core inode, or are we doing this manually? */
	if (sc->ip) {
		ino = sc->ip->i_ino;
		xfs_inode_to_disk(sc->ip, &di, 0);
		dip = &di;
	} else {
		/* Map & read inode. */
		ino = sc->sm->sm_ino;
		error = xfs_scrub_inode_map_raw(sc, ino, &bp, &dip);
		if (error || !bp)
			goto out;
	}

	xfs_scrub_dinode(sc, bp, dip, ino);
	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
		goto out;

	/* Now let's do the things that require a live inode. */
	if (!sc->ip)
		goto out;

	/*
757 758 759
	 * Look for discrepancies between file's data blocks and the reflink
	 * iflag.  We already checked the iflag against the file mode when
	 * we scrubbed the dinode.
D
Darrick J. Wong 已提交
760
	 */
761 762
	if (S_ISREG(VFS_I(sc->ip)->i_mode))
		xfs_scrub_inode_check_reflink_iflag(sc, ino, bp);
D
Darrick J. Wong 已提交
763

764
	xfs_scrub_inode_xref(sc, ino, dip);
D
Darrick J. Wong 已提交
765 766 767 768 769
out:
	if (bp)
		xfs_trans_brelse(sc->tp, bp);
	return error;
}