xfs_sb.c 36.2 KB
Newer Older
D
Dave Chinner 已提交
1
// SPDX-License-Identifier: GPL-2.0
2 3 4 5 6 7
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
8
#include "xfs_shared.h"
9
#include "xfs_format.h"
10 11
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
12 13 14
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
15
#include "xfs_defer.h"
16 17 18 19 20 21
#include "xfs_inode.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
22
#include "xfs_trans.h"
23
#include "xfs_buf_item.h"
24 25 26
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
27
#include "xfs_log.h"
28
#include "xfs_rmap_btree.h"
29 30
#include "xfs_bmap.h"
#include "xfs_refcount_btree.h"
31 32
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
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

/*
 * Physical superblock buffer manipulations. Shared with libxfs in userspace.
 */

/*
 * Reference counting access wrappers to the perag structures.
 * Because we never free per-ag structures, the only thing we
 * have to protect against changes is the tree structure itself.
 */
struct xfs_perag *
xfs_perag_get(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno)
{
	struct xfs_perag	*pag;
	int			ref = 0;

	rcu_read_lock();
	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
	if (pag) {
		ASSERT(atomic_read(&pag->pag_ref) >= 0);
		ref = atomic_inc_return(&pag->pag_ref);
	}
	rcu_read_unlock();
	trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
	return pag;
}

/*
 * search from @first to find the next perag with the given tag set.
 */
struct xfs_perag *
xfs_perag_get_tag(
	struct xfs_mount	*mp,
	xfs_agnumber_t		first,
	int			tag)
{
	struct xfs_perag	*pag;
	int			found;
	int			ref;

	rcu_read_lock();
	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
					(void **)&pag, first, 1, tag);
	if (found <= 0) {
		rcu_read_unlock();
		return NULL;
	}
	ref = atomic_inc_return(&pag->pag_ref);
	rcu_read_unlock();
	trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_);
	return pag;
}

void
xfs_perag_put(
	struct xfs_perag	*pag)
{
	int	ref;

	ASSERT(atomic_read(&pag->pag_ref) > 0);
	ref = atomic_dec_return(&pag->pag_ref);
	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
}

99
/* Check all the superblock fields we care about when reading one in. */
100
STATIC int
101 102 103
xfs_validate_sb_read(
	struct xfs_mount	*mp,
	struct xfs_sb		*sbp)
104
{
105 106
	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
		return 0;
107 108

	/*
109 110
	 * Version 5 superblock feature mask validation. Reject combinations
	 * the kernel cannot support up front before checking anything else.
111
	 */
112 113
	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
		xfs_warn(mp,
114
"Superblock has unknown compatible features (0x%x) enabled.",
115 116
			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
		xfs_warn(mp,
117
"Using a more recent kernel is recommended.");
118
	}
119

120 121
	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
		xfs_alert(mp,
122
"Superblock has unknown read-only compatible features (0x%x) enabled.",
123 124 125 126
			(sbp->sb_features_ro_compat &
					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
			xfs_warn(mp,
127
"Attempted to mount read-only compatible filesystem read-write.");
128
			xfs_warn(mp,
129
"Filesystem can only be safely mounted read only.");
130

D
Dave Chinner 已提交
131
			return -EINVAL;
132
		}
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
	}
	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
		xfs_warn(mp,
"Superblock has unknown incompatible features (0x%x) enabled.",
			(sbp->sb_features_incompat &
					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
		xfs_warn(mp,
"Filesystem cannot be safely mounted by this kernel.");
		return -EINVAL;
	}

	return 0;
}

/* Check all the superblock fields we care about when writing one out. */
STATIC int
xfs_validate_sb_write(
	struct xfs_mount	*mp,
151
	struct xfs_buf		*bp,
152 153
	struct xfs_sb		*sbp)
{
154 155 156 157
	/*
	 * Carry out additional sb summary counter sanity checks when we write
	 * the superblock.  We skip this in the read validator because there
	 * could be newer superblocks in the log and if the values are garbage
158
	 * even after replay we'll recalculate them at the end of log mount.
159 160 161 162
	 *
	 * mkfs has traditionally written zeroed counters to inprogress and
	 * secondary superblocks, so allow this usage to continue because
	 * we never read counters from such superblocks.
163
	 */
164 165 166 167
	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && !sbp->sb_inprogress &&
	    (sbp->sb_fdblocks > sbp->sb_dblocks ||
	     !xfs_verify_icount(mp, sbp->sb_icount) ||
	     sbp->sb_ifree > sbp->sb_icount)) {
168 169 170 171
		xfs_warn(mp, "SB summary counter sanity check failed");
		return -EFSCORRUPTED;
	}

172 173 174
	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
		return 0;

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
	/*
	 * Version 5 superblock feature mask validation. Reject combinations
	 * the kernel cannot support since we checked for unsupported bits in
	 * the read verifier, which means that memory is corrupt.
	 */
	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
		xfs_warn(mp,
"Corruption detected in superblock compatible features (0x%x)!",
			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
		return -EFSCORRUPTED;
	}

	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
		xfs_alert(mp,
"Corruption detected in superblock read-only compatible features (0x%x)!",
			(sbp->sb_features_ro_compat &
					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
		return -EFSCORRUPTED;
	}
	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
		xfs_warn(mp,
"Corruption detected in superblock incompatible features (0x%x)!",
			(sbp->sb_features_incompat &
					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
		return -EFSCORRUPTED;
	}
	if (xfs_sb_has_incompat_log_feature(sbp,
			XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)) {
		xfs_warn(mp,
"Corruption detected in superblock incompatible log features (0x%x)!",
			(sbp->sb_features_log_incompat &
					XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN));
		return -EFSCORRUPTED;
	}
209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227

	/*
	 * We can't read verify the sb LSN because the read verifier is called
	 * before the log is allocated and processed. We know the log is set up
	 * before write verifier calls, so check it here.
	 */
	if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
		return -EFSCORRUPTED;

	return 0;
}

/* Check the validity of the SB. */
STATIC int
xfs_validate_sb_common(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct xfs_sb		*sbp)
{
228
	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
229 230 231
	uint32_t		agcount = 0;
	uint32_t		rem;

232
	if (!xfs_verify_magic(bp, dsb->sb_magicnum)) {
233 234 235 236 237 238 239
		xfs_warn(mp, "bad magic number");
		return -EWRONGFS;
	}

	if (!xfs_sb_good_version(sbp)) {
		xfs_warn(mp, "bad version");
		return -EWRONGFS;
240 241 242 243 244
	}

	if (xfs_sb_version_has_pquotino(sbp)) {
		if (sbp->sb_qflags & (XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD)) {
			xfs_notice(mp,
245
			   "Version 5 of Super block has XFS_OQUOTA bits.");
D
Dave Chinner 已提交
246
			return -EFSCORRUPTED;
247 248 249 250
		}
	} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
				XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
			xfs_notice(mp,
251
"Superblock earlier than Version 5 has XFS_[PQ]UOTA_{ENFD|CHKD} bits.");
D
Dave Chinner 已提交
252
			return -EFSCORRUPTED;
253 254
	}

255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272
	/*
	 * Full inode chunks must be aligned to inode chunk size when
	 * sparse inodes are enabled to support the sparse chunk
	 * allocation algorithm and prevent overlapping inode records.
	 */
	if (xfs_sb_version_hassparseinodes(sbp)) {
		uint32_t	align;

		align = XFS_INODES_PER_CHUNK * sbp->sb_inodesize
				>> sbp->sb_blocklog;
		if (sbp->sb_inoalignmt != align) {
			xfs_warn(mp,
"Inode block alignment (%u) must match chunk size (%u) for sparse inodes.",
				 sbp->sb_inoalignmt, align);
			return -EINVAL;
		}
	}

273 274 275 276 277
	if (unlikely(
	    sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
		xfs_warn(mp,
		"filesystem is marked as having an external log; "
		"specify logdev on the mount command line.");
D
Dave Chinner 已提交
278
		return -EINVAL;
279 280 281 282 283 284 285
	}

	if (unlikely(
	    sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
		xfs_warn(mp,
		"filesystem is marked as having an internal log; "
		"do not specify logdev on the mount command line.");
D
Dave Chinner 已提交
286
		return -EINVAL;
287 288
	}

289 290 291 292 293 294 295
	/* Compute agcount for this number of dblocks and agblocks */
	if (sbp->sb_agblocks) {
		agcount = div_u64_rem(sbp->sb_dblocks, sbp->sb_agblocks, &rem);
		if (rem)
			agcount++;
	}

296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
	/*
	 * More sanity checking.  Most of these were stolen directly from
	 * xfs_repair.
	 */
	if (unlikely(
	    sbp->sb_agcount <= 0					||
	    sbp->sb_sectsize < XFS_MIN_SECTORSIZE			||
	    sbp->sb_sectsize > XFS_MAX_SECTORSIZE			||
	    sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG			||
	    sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG			||
	    sbp->sb_sectsize != (1 << sbp->sb_sectlog)			||
	    sbp->sb_blocksize < XFS_MIN_BLOCKSIZE			||
	    sbp->sb_blocksize > XFS_MAX_BLOCKSIZE			||
	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
312
	    sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
313 314 315 316 317
	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
	    sbp->sb_inodesize != (1 << sbp->sb_inodelog)		||
318
	    sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE			||
319
	    sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
320 321 322 323
	    XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES	||
	    XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES	||
	    sbp->sb_agblklog != xfs_highbit32(sbp->sb_agblocks - 1) + 1	||
	    agcount == 0 || agcount != sbp->sb_agcount			||
324 325 326 327 328 329
	    (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog)	||
	    (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)	||
	    (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)	||
	    (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */)	||
	    sbp->sb_dblocks == 0					||
	    sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp)			||
330 331
	    sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp)			||
	    sbp->sb_shared_vn != 0)) {
332
		xfs_notice(mp, "SB sanity check failed");
D
Dave Chinner 已提交
333
		return -EFSCORRUPTED;
334 335
	}

336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351
	if (sbp->sb_unit) {
		if (!xfs_sb_version_hasdalign(sbp) ||
		    sbp->sb_unit > sbp->sb_width ||
		    (sbp->sb_width % sbp->sb_unit) != 0) {
			xfs_notice(mp, "SB stripe unit sanity check failed");
			return -EFSCORRUPTED;
		}
	} else if (xfs_sb_version_hasdalign(sbp)) {
		xfs_notice(mp, "SB stripe alignment sanity check failed");
		return -EFSCORRUPTED;
	} else if (sbp->sb_width) {
		xfs_notice(mp, "SB stripe width sanity check failed");
		return -EFSCORRUPTED;
	}


352 353 354 355
	if (xfs_sb_version_hascrc(&mp->m_sb) &&
	    sbp->sb_blocksize < XFS_MIN_CRC_BLOCKSIZE) {
		xfs_notice(mp, "v5 SB sanity check failed");
		return -EFSCORRUPTED;
356 357 358 359 360 361 362 363 364 365
	}

	/*
	 * Until this is fixed only page-sized or smaller data blocks work.
	 */
	if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
		xfs_warn(mp,
		"File system with blocksize %d bytes. "
		"Only pagesize (%ld) or less will currently work.",
				sbp->sb_blocksize, PAGE_SIZE);
D
Dave Chinner 已提交
366
		return -ENOSYS;
367 368 369 370 371 372 373 374 375 376 377 378 379 380
	}

	/*
	 * Currently only very few inode sizes are supported.
	 */
	switch (sbp->sb_inodesize) {
	case 256:
	case 512:
	case 1024:
	case 2048:
		break;
	default:
		xfs_warn(mp, "inode size of %d bytes not supported",
				sbp->sb_inodesize);
D
Dave Chinner 已提交
381
		return -ENOSYS;
382 383 384 385 386 387
	}

	if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
	    xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
		xfs_warn(mp,
		"file system too large to be mounted on this system.");
D
Dave Chinner 已提交
388
		return -EFBIG;
389 390
	}

391 392 393 394 395 396
	/*
	 * Don't touch the filesystem if a user tool thinks it owns the primary
	 * superblock.  mkfs doesn't clear the flag from secondary supers, so
	 * we don't check them at all.
	 */
	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && sbp->sb_inprogress) {
397
		xfs_warn(mp, "Offline file system operation in progress!");
D
Dave Chinner 已提交
398
		return -EFSCORRUPTED;
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
	}
	return 0;
}

void
xfs_sb_quota_from_disk(struct xfs_sb *sbp)
{
	/*
	 * older mkfs doesn't initialize quota inodes to NULLFSINO. This
	 * leads to in-core values having two different values for a quota
	 * inode to be invalid: 0 and NULLFSINO. Change it to a single value
	 * NULLFSINO.
	 *
	 * Note that this change affect only the in-core values. These
	 * values are not written back to disk unless any quota information
	 * is written to the disk. Even in that case, sb_pquotino field is
	 * not written to disk unless the superblock supports pquotino.
	 */
	if (sbp->sb_uquotino == 0)
		sbp->sb_uquotino = NULLFSINO;
	if (sbp->sb_gquotino == 0)
		sbp->sb_gquotino = NULLFSINO;
	if (sbp->sb_pquotino == 0)
		sbp->sb_pquotino = NULLFSINO;

	/*
	 * We need to do these manipilations only if we are working
	 * with an older version of on-disk superblock.
	 */
	if (xfs_sb_version_has_pquotino(sbp))
		return;

	if (sbp->sb_qflags & XFS_OQUOTA_ENFD)
		sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ?
					XFS_PQUOTA_ENFD : XFS_GQUOTA_ENFD;
	if (sbp->sb_qflags & XFS_OQUOTA_CHKD)
		sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ?
					XFS_PQUOTA_CHKD : XFS_GQUOTA_CHKD;
	sbp->sb_qflags &= ~(XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD);

439 440
	if (sbp->sb_qflags & XFS_PQUOTA_ACCT &&
	    sbp->sb_gquotino != NULLFSINO)  {
441 442 443 444 445
		/*
		 * In older version of superblock, on-disk superblock only
		 * has sb_gquotino, and in-core superblock has both sb_gquotino
		 * and sb_pquotino. But, only one of them is supported at any
		 * point of time. So, if PQUOTA is set in disk superblock,
446 447 448
		 * copy over sb_gquotino to sb_pquotino.  The NULLFSINO test
		 * above is to make sure we don't do this twice and wipe them
		 * both out!
449 450 451 452 453 454
		 */
		sbp->sb_pquotino = sbp->sb_gquotino;
		sbp->sb_gquotino = NULLFSINO;
	}
}

455 456
static void
__xfs_sb_from_disk(
457
	struct xfs_sb	*to,
458 459
	xfs_dsb_t	*from,
	bool		convert_xquota)
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
{
	to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
	to->sb_blocksize = be32_to_cpu(from->sb_blocksize);
	to->sb_dblocks = be64_to_cpu(from->sb_dblocks);
	to->sb_rblocks = be64_to_cpu(from->sb_rblocks);
	to->sb_rextents = be64_to_cpu(from->sb_rextents);
	memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
	to->sb_logstart = be64_to_cpu(from->sb_logstart);
	to->sb_rootino = be64_to_cpu(from->sb_rootino);
	to->sb_rbmino = be64_to_cpu(from->sb_rbmino);
	to->sb_rsumino = be64_to_cpu(from->sb_rsumino);
	to->sb_rextsize = be32_to_cpu(from->sb_rextsize);
	to->sb_agblocks = be32_to_cpu(from->sb_agblocks);
	to->sb_agcount = be32_to_cpu(from->sb_agcount);
	to->sb_rbmblocks = be32_to_cpu(from->sb_rbmblocks);
	to->sb_logblocks = be32_to_cpu(from->sb_logblocks);
	to->sb_versionnum = be16_to_cpu(from->sb_versionnum);
	to->sb_sectsize = be16_to_cpu(from->sb_sectsize);
	to->sb_inodesize = be16_to_cpu(from->sb_inodesize);
	to->sb_inopblock = be16_to_cpu(from->sb_inopblock);
	memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
	to->sb_blocklog = from->sb_blocklog;
	to->sb_sectlog = from->sb_sectlog;
	to->sb_inodelog = from->sb_inodelog;
	to->sb_inopblog = from->sb_inopblog;
	to->sb_agblklog = from->sb_agblklog;
	to->sb_rextslog = from->sb_rextslog;
	to->sb_inprogress = from->sb_inprogress;
	to->sb_imax_pct = from->sb_imax_pct;
	to->sb_icount = be64_to_cpu(from->sb_icount);
	to->sb_ifree = be64_to_cpu(from->sb_ifree);
	to->sb_fdblocks = be64_to_cpu(from->sb_fdblocks);
	to->sb_frextents = be64_to_cpu(from->sb_frextents);
	to->sb_uquotino = be64_to_cpu(from->sb_uquotino);
	to->sb_gquotino = be64_to_cpu(from->sb_gquotino);
	to->sb_qflags = be16_to_cpu(from->sb_qflags);
	to->sb_flags = from->sb_flags;
	to->sb_shared_vn = from->sb_shared_vn;
	to->sb_inoalignmt = be32_to_cpu(from->sb_inoalignmt);
	to->sb_unit = be32_to_cpu(from->sb_unit);
	to->sb_width = be32_to_cpu(from->sb_width);
	to->sb_dirblklog = from->sb_dirblklog;
	to->sb_logsectlog = from->sb_logsectlog;
	to->sb_logsectsize = be16_to_cpu(from->sb_logsectsize);
	to->sb_logsunit = be32_to_cpu(from->sb_logsunit);
	to->sb_features2 = be32_to_cpu(from->sb_features2);
	to->sb_bad_features2 = be32_to_cpu(from->sb_bad_features2);
	to->sb_features_compat = be32_to_cpu(from->sb_features_compat);
	to->sb_features_ro_compat = be32_to_cpu(from->sb_features_ro_compat);
	to->sb_features_incompat = be32_to_cpu(from->sb_features_incompat);
	to->sb_features_log_incompat =
				be32_to_cpu(from->sb_features_log_incompat);
512 513
	/* crc is only used on disk, not in memory; just init to 0 here. */
	to->sb_crc = 0;
514
	to->sb_spino_align = be32_to_cpu(from->sb_spino_align);
515 516
	to->sb_pquotino = be64_to_cpu(from->sb_pquotino);
	to->sb_lsn = be64_to_cpu(from->sb_lsn);
517 518 519 520 521 522 523 524
	/*
	 * sb_meta_uuid is only on disk if it differs from sb_uuid and the
	 * feature flag is set; if not set we keep it only in memory.
	 */
	if (xfs_sb_version_hasmetauuid(to))
		uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
	else
		uuid_copy(&to->sb_meta_uuid, &from->sb_uuid);
525 526 527 528 529 530 531 532 533 534 535
	/* Convert on-disk flags to in-memory flags? */
	if (convert_xquota)
		xfs_sb_quota_from_disk(to);
}

void
xfs_sb_from_disk(
	struct xfs_sb	*to,
	xfs_dsb_t	*from)
{
	__xfs_sb_from_disk(to, from, true);
536 537
}

538
static void
539
xfs_sb_quota_to_disk(
540 541
	struct xfs_dsb	*to,
	struct xfs_sb	*from)
542
{
543
	uint16_t	qflags = from->sb_qflags;
544

545 546 547 548 549 550 551 552
	to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
	if (xfs_sb_version_has_pquotino(from)) {
		to->sb_qflags = cpu_to_be16(from->sb_qflags);
		to->sb_gquotino = cpu_to_be64(from->sb_gquotino);
		to->sb_pquotino = cpu_to_be64(from->sb_pquotino);
		return;
	}

553
	/*
554 555 556
	 * The in-core version of sb_qflags do not have XFS_OQUOTA_*
	 * flags, whereas the on-disk version does.  So, convert incore
	 * XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags.
557
	 */
558 559
	qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD |
			XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD);
560

561 562 563 564 565 566 567
	if (from->sb_qflags &
			(XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD))
		qflags |= XFS_OQUOTA_ENFD;
	if (from->sb_qflags &
			(XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD))
		qflags |= XFS_OQUOTA_CHKD;
	to->sb_qflags = cpu_to_be16(qflags);
568 569

	/*
570 571 572 573
	 * GQUOTINO and PQUOTINO cannot be used together in versions
	 * of superblock that do not have pquotino. from->sb_flags
	 * tells us which quota is active and should be copied to
	 * disk. If neither are active, we should NULL the inode.
574
	 *
575 576
	 * In all cases, the separate pquotino must remain 0 because it
	 * it beyond the "end" of the valid non-pquotino superblock.
577
	 */
578
	if (from->sb_qflags & XFS_GQUOTA_ACCT)
579
		to->sb_gquotino = cpu_to_be64(from->sb_gquotino);
580
	else if (from->sb_qflags & XFS_PQUOTA_ACCT)
581
		to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
582 583 584 585 586 587 588 589 590 591 592
	else {
		/*
		 * We can't rely on just the fields being logged to tell us
		 * that it is safe to write NULLFSINO - we should only do that
		 * if quotas are not actually enabled. Hence only write
		 * NULLFSINO if both in-core quota inodes are NULL.
		 */
		if (from->sb_gquotino == NULLFSINO &&
		    from->sb_pquotino == NULLFSINO)
			to->sb_gquotino = cpu_to_be64(NULLFSINO);
	}
593

594
	to->sb_pquotino = 0;
595 596 597 598
}

void
xfs_sb_to_disk(
599 600
	struct xfs_dsb	*to,
	struct xfs_sb	*from)
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
	xfs_sb_quota_to_disk(to, from);

	to->sb_magicnum = cpu_to_be32(from->sb_magicnum);
	to->sb_blocksize = cpu_to_be32(from->sb_blocksize);
	to->sb_dblocks = cpu_to_be64(from->sb_dblocks);
	to->sb_rblocks = cpu_to_be64(from->sb_rblocks);
	to->sb_rextents = cpu_to_be64(from->sb_rextents);
	memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
	to->sb_logstart = cpu_to_be64(from->sb_logstart);
	to->sb_rootino = cpu_to_be64(from->sb_rootino);
	to->sb_rbmino = cpu_to_be64(from->sb_rbmino);
	to->sb_rsumino = cpu_to_be64(from->sb_rsumino);
	to->sb_rextsize = cpu_to_be32(from->sb_rextsize);
	to->sb_agblocks = cpu_to_be32(from->sb_agblocks);
	to->sb_agcount = cpu_to_be32(from->sb_agcount);
	to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks);
	to->sb_logblocks = cpu_to_be32(from->sb_logblocks);
	to->sb_versionnum = cpu_to_be16(from->sb_versionnum);
	to->sb_sectsize = cpu_to_be16(from->sb_sectsize);
	to->sb_inodesize = cpu_to_be16(from->sb_inodesize);
	to->sb_inopblock = cpu_to_be16(from->sb_inopblock);
	memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
	to->sb_blocklog = from->sb_blocklog;
	to->sb_sectlog = from->sb_sectlog;
	to->sb_inodelog = from->sb_inodelog;
	to->sb_inopblog = from->sb_inopblog;
	to->sb_agblklog = from->sb_agblklog;
	to->sb_rextslog = from->sb_rextslog;
	to->sb_inprogress = from->sb_inprogress;
	to->sb_imax_pct = from->sb_imax_pct;
	to->sb_icount = cpu_to_be64(from->sb_icount);
	to->sb_ifree = cpu_to_be64(from->sb_ifree);
	to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks);
	to->sb_frextents = cpu_to_be64(from->sb_frextents);
636

637 638 639 640 641 642 643 644 645
	to->sb_flags = from->sb_flags;
	to->sb_shared_vn = from->sb_shared_vn;
	to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt);
	to->sb_unit = cpu_to_be32(from->sb_unit);
	to->sb_width = cpu_to_be32(from->sb_width);
	to->sb_dirblklog = from->sb_dirblklog;
	to->sb_logsectlog = from->sb_logsectlog;
	to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize);
	to->sb_logsunit = cpu_to_be32(from->sb_logsunit);
646 647 648 649 650 651 652

	/*
	 * We need to ensure that bad_features2 always matches features2.
	 * Hence we enforce that here rather than having to remember to do it
	 * everywhere else that updates features2.
	 */
	from->sb_bad_features2 = from->sb_features2;
653 654 655 656 657 658 659 660 661 662 663
	to->sb_features2 = cpu_to_be32(from->sb_features2);
	to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2);

	if (xfs_sb_version_hascrc(from)) {
		to->sb_features_compat = cpu_to_be32(from->sb_features_compat);
		to->sb_features_ro_compat =
				cpu_to_be32(from->sb_features_ro_compat);
		to->sb_features_incompat =
				cpu_to_be32(from->sb_features_incompat);
		to->sb_features_log_incompat =
				cpu_to_be32(from->sb_features_log_incompat);
664
		to->sb_spino_align = cpu_to_be32(from->sb_spino_align);
665
		to->sb_lsn = cpu_to_be64(from->sb_lsn);
666 667
		if (xfs_sb_version_hasmetauuid(from))
			uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
668 669 670 671 672 673 674 675 676
	}
}

/*
 * If the superblock has the CRC feature bit set or the CRC field is non-null,
 * check that the CRC is valid.  We check the CRC field is non-null because a
 * single bit error could clear the feature bit and unused parts of the
 * superblock are supposed to be zero. Hence a non-null crc field indicates that
 * we've potentially lost a feature bit and we should check it anyway.
677 678 679 680 681
 *
 * However, past bugs (i.e. in growfs) left non-zeroed regions beyond the
 * last field in V4 secondary superblocks.  So for secondary superblocks,
 * we are more forgiving, and ignore CRC failures if the primary doesn't
 * indicate that the fs version is V5.
682 683 684
 */
static void
xfs_sb_read_verify(
685
	struct xfs_buf		*bp)
686
{
687 688 689 690
	struct xfs_sb		sb;
	struct xfs_mount	*mp = bp->b_target->bt_mount;
	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
	int			error;
691 692 693 694 695 696 697 698 699 700

	/*
	 * open code the version check to avoid needing to convert the entire
	 * superblock from disk order just to check the version number
	 */
	if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC) &&
	    (((be16_to_cpu(dsb->sb_versionnum) & XFS_SB_VERSION_NUMBITS) ==
						XFS_SB_VERSION_5) ||
	     dsb->sb_crc != 0)) {

701
		if (!xfs_buf_verify_cksum(bp, XFS_SB_CRC_OFF)) {
702
			/* Only fail bad secondaries on a known V5 filesystem */
703
			if (bp->b_bn == XFS_SB_DADDR ||
704
			    xfs_sb_version_hascrc(&mp->m_sb)) {
D
Dave Chinner 已提交
705
				error = -EFSBADCRC;
706 707
				goto out_error;
			}
708 709
		}
	}
710 711 712 713 714 715 716 717 718 719

	/*
	 * Check all the superblock fields.  Don't byteswap the xquota flags
	 * because _verify_common checks the on-disk values.
	 */
	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
	error = xfs_validate_sb_common(mp, bp, &sb);
	if (error)
		goto out_error;
	error = xfs_validate_sb_read(mp, &sb);
720 721

out_error:
722
	if (error == -EFSCORRUPTED || error == -EFSBADCRC)
723
		xfs_verifier_error(bp, error, __this_address);
724
	else if (error)
725 726 727 728 729 730
		xfs_buf_ioerror(bp, error);
}

/*
 * We may be probed for a filesystem match, so we may not want to emit
 * messages when the superblock buffer is not actually an XFS superblock.
731
 * If we find an XFS superblock, then run a normal, noisy mount because we are
732 733 734 735 736 737 738 739 740 741 742 743 744 745
 * really going to mount it and want to know about errors.
 */
static void
xfs_sb_quiet_read_verify(
	struct xfs_buf	*bp)
{
	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);

	if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
		/* XFS filesystem, verify noisily! */
		xfs_sb_read_verify(bp);
		return;
	}
	/* quietly fail */
D
Dave Chinner 已提交
746
	xfs_buf_ioerror(bp, -EWRONGFS);
747 748 749 750 751 752
}

static void
xfs_sb_write_verify(
	struct xfs_buf		*bp)
{
753
	struct xfs_sb		sb;
754
	struct xfs_mount	*mp = bp->b_target->bt_mount;
C
Carlos Maiolino 已提交
755
	struct xfs_buf_log_item	*bip = bp->b_log_item;
756 757
	int			error;

758 759 760 761 762 763 764 765
	/*
	 * Check all the superblock fields.  Don't byteswap the xquota flags
	 * because _verify_common checks the on-disk values.
	 */
	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
	error = xfs_validate_sb_common(mp, bp, &sb);
	if (error)
		goto out_error;
766
	error = xfs_validate_sb_write(mp, bp, &sb);
767 768
	if (error)
		goto out_error;
769 770 771 772 773 774 775

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

	if (bip)
		XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);

776
	xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
777 778 779 780
	return;

out_error:
	xfs_verifier_error(bp, error, __this_address);
781 782 783
}

const struct xfs_buf_ops xfs_sb_buf_ops = {
784
	.name = "xfs_sb",
785
	.magic = { cpu_to_be32(XFS_SB_MAGIC), cpu_to_be32(XFS_SB_MAGIC) },
786 787 788 789 790
	.verify_read = xfs_sb_read_verify,
	.verify_write = xfs_sb_write_verify,
};

const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
791
	.name = "xfs_sb_quiet",
792
	.magic = { cpu_to_be32(XFS_SB_MAGIC), cpu_to_be32(XFS_SB_MAGIC) },
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
	.verify_read = xfs_sb_quiet_read_verify,
	.verify_write = xfs_sb_write_verify,
};

/*
 * xfs_mount_common
 *
 * Mount initialization code establishing various mount
 * fields from the superblock associated with the given
 * mount structure
 */
void
xfs_sb_mount_common(
	struct xfs_mount *mp,
	struct xfs_sb	*sbp)
{
	mp->m_agfrotor = mp->m_agirotor = 0;
	mp->m_maxagi = mp->m_sb.sb_agcount;
	mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
	mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
	mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
	mp->m_blockmask = sbp->sb_blocksize - 1;
	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
	mp->m_blockwmask = mp->m_blockwsize - 1;

	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1);
	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0);
	mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2;
	mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2;

	mp->m_inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1);
	mp->m_inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0);
	mp->m_inobt_mnr[0] = mp->m_inobt_mxr[0] / 2;
	mp->m_inobt_mnr[1] = mp->m_inobt_mxr[1] / 2;

	mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1);
	mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0);
	mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2;
	mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2;

835 836
	mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(sbp->sb_blocksize, 1);
	mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(sbp->sb_blocksize, 0);
837 838 839
	mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2;
	mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2;

840 841
	mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(sbp->sb_blocksize, true);
	mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(sbp->sb_blocksize, false);
842 843 844
	mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2;
	mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2;

845
	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
D
Dave Chinner 已提交
846
	mp->m_ialloc_inos = max_t(uint16_t, XFS_INODES_PER_CHUNK,
847 848
					sbp->sb_inopblock);
	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
849 850 851 852 853

	if (sbp->sb_spino_align)
		mp->m_ialloc_min_blks = sbp->sb_spino_align;
	else
		mp->m_ialloc_min_blks = mp->m_ialloc_blks;
854 855
	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
	mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp);
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878
}

/*
 * xfs_initialize_perag_data
 *
 * Read in each per-ag structure so we can count up the number of
 * allocated inodes, free inodes and used filesystem blocks as this
 * information is no longer persistent in the superblock. Once we have
 * this information, write it into the in-core superblock structure.
 */
int
xfs_initialize_perag_data(
	struct xfs_mount *mp,
	xfs_agnumber_t	agcount)
{
	xfs_agnumber_t	index;
	xfs_perag_t	*pag;
	xfs_sb_t	*sbp = &mp->m_sb;
	uint64_t	ifree = 0;
	uint64_t	ialloc = 0;
	uint64_t	bfree = 0;
	uint64_t	bfreelst = 0;
	uint64_t	btree = 0;
879
	uint64_t	fdblocks;
880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
	int		error;

	for (index = 0; index < agcount; index++) {
		/*
		 * read the agf, then the agi. This gets us
		 * all the information we need and populates the
		 * per-ag structures for us.
		 */
		error = xfs_alloc_pagf_init(mp, NULL, index, 0);
		if (error)
			return error;

		error = xfs_ialloc_pagi_init(mp, NULL, index);
		if (error)
			return error;
		pag = xfs_perag_get(mp, index);
		ifree += pag->pagi_freecount;
		ialloc += pag->pagi_count;
		bfree += pag->pagf_freeblks;
		bfreelst += pag->pagf_flcount;
		btree += pag->pagf_btreeblks;
		xfs_perag_put(pag);
	}
903 904 905 906 907 908 909 910 911 912 913 914 915
	fdblocks = bfree + bfreelst + btree;

	/*
	 * If the new summary counts are obviously incorrect, fail the
	 * mount operation because that implies the AGFs are also corrupt.
	 * Clear BAD_SUMMARY so that we don't unmount with a dirty log, which
	 * will prevent xfs_repair from fixing anything.
	 */
	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
		error = -EFSCORRUPTED;
		goto out;
	}
D
Dave Chinner 已提交
916 917

	/* Overwrite incore superblock counters with just-read data */
918 919 920
	spin_lock(&mp->m_sb_lock);
	sbp->sb_ifree = ifree;
	sbp->sb_icount = ialloc;
921
	sbp->sb_fdblocks = fdblocks;
922 923
	spin_unlock(&mp->m_sb_lock);

D
Dave Chinner 已提交
924
	xfs_reinit_percpu_counters(mp);
925 926 927
out:
	mp->m_flags &= ~XFS_MOUNT_BAD_SUMMARY;
	return error;
928 929 930
}

/*
931 932 933 934
 * xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock
 * into the superblock buffer to be logged.  It does not provide the higher
 * level of locking that is needed to protect the in-core superblock from
 * concurrent access.
935 936
 */
void
937
xfs_log_sb(
938
	struct xfs_trans	*tp)
939
{
940 941
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_buf		*bp = xfs_trans_getsb(tp, mp, 0);
942

943
	mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
944
	mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
945
	mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
946

947
	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
948
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
949
	xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb));
950
}
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970

/*
 * xfs_sync_sb
 *
 * Sync the superblock to disk.
 *
 * Note that the caller is responsible for checking the frozen state of the
 * filesystem. This procedure uses the non-blocking transaction allocator and
 * thus will allow modifications to a frozen fs. This is required because this
 * code can be called during the process of freezing where use of the high-level
 * allocator would deadlock.
 */
int
xfs_sync_sb(
	struct xfs_mount	*mp,
	bool			wait)
{
	struct xfs_trans	*tp;
	int			error;

971 972 973
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0,
			XFS_TRANS_NO_WRITECOUNT, &tp);
	if (error)
974 975 976 977 978
		return error;

	xfs_log_sb(tp);
	if (wait)
		xfs_trans_set_sync(tp);
979
	return xfs_trans_commit(tp);
980
}
981

D
Dave Chinner 已提交
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
/*
 * Update all the secondary superblocks to match the new state of the primary.
 * Because we are completely overwriting all the existing fields in the
 * secondary superblock buffers, there is no need to read them in from disk.
 * Just get a new buffer, stamp it and write it.
 *
 * The sb buffers need to be cached here so that we serialise against other
 * operations that access the secondary superblocks, but we don't want to keep
 * them in memory once it is written so we mark it as a one-shot buffer.
 */
int
xfs_update_secondary_sbs(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	int			saved_error = 0;
	int			error = 0;
	LIST_HEAD		(buffer_list);

	/* update secondary superblocks. */
	for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) {
		struct xfs_buf		*bp;

		bp = xfs_buf_get(mp->m_ddev_targp,
				 XFS_AG_DADDR(mp, agno, XFS_SB_DADDR),
				 XFS_FSS_TO_BB(mp, 1), 0);
		/*
		 * If we get an error reading or writing alternate superblocks,
		 * continue.  xfs_repair chooses the "best" superblock based
		 * on most matches; if we break early, we'll leave more
		 * superblocks un-updated than updated, and xfs_repair may
		 * pick them over the properly-updated primary.
		 */
		if (!bp) {
			xfs_warn(mp,
		"error allocating secondary superblock for ag %d",
				agno);
			if (!saved_error)
				saved_error = -ENOMEM;
			continue;
		}

		bp->b_ops = &xfs_sb_buf_ops;
		xfs_buf_oneshot(bp);
		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
		xfs_buf_delwri_queue(bp, &buffer_list);
		xfs_buf_relse(bp);

		/* don't hold too many buffers at once */
		if (agno % 16)
			continue;

		error = xfs_buf_delwri_submit(&buffer_list);
		if (error) {
			xfs_warn(mp,
		"write error %d updating a secondary superblock near ag %d",
				error, agno);
			if (!saved_error)
				saved_error = error;
			continue;
		}
	}
	error = xfs_buf_delwri_submit(&buffer_list);
	if (error) {
		xfs_warn(mp,
		"write error %d updating a secondary superblock near ag %d",
			error, agno);
	}

	return saved_error ? saved_error : error;
}

1055 1056 1057 1058 1059 1060 1061 1062 1063
/*
 * Same behavior as xfs_sync_sb, except that it is always synchronous and it
 * also writes the superblock buffer to disk sector 0 immediately.
 */
int
xfs_sync_sb_buf(
	struct xfs_mount	*mp)
{
	struct xfs_trans	*tp;
1064
	struct xfs_buf		*bp;
1065 1066 1067 1068 1069 1070
	int			error;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
	if (error)
		return error;

1071
	bp = xfs_trans_getsb(tp, mp, 0);
1072
	xfs_log_sb(tp);
1073
	xfs_trans_bhold(tp, bp);
1074 1075 1076 1077 1078 1079 1080
	xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp);
	if (error)
		goto out;
	/*
	 * write out the sb buffer to get the changes to disk
	 */
1081
	error = xfs_bwrite(bp);
1082
out:
1083
	xfs_buf_relse(bp);
1084 1085 1086
	return error;
}

1087 1088
int
xfs_fs_geometry(
1089 1090 1091
	struct xfs_sb		*sbp,
	struct xfs_fsop_geom	*geo,
	int			struct_version)
1092
{
1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
	memset(geo, 0, sizeof(struct xfs_fsop_geom));

	geo->blocksize = sbp->sb_blocksize;
	geo->rtextsize = sbp->sb_rextsize;
	geo->agblocks = sbp->sb_agblocks;
	geo->agcount = sbp->sb_agcount;
	geo->logblocks = sbp->sb_logblocks;
	geo->sectsize = sbp->sb_sectsize;
	geo->inodesize = sbp->sb_inodesize;
	geo->imaxpct = sbp->sb_imax_pct;
	geo->datablocks = sbp->sb_dblocks;
	geo->rtblocks = sbp->sb_rblocks;
	geo->rtextents = sbp->sb_rextents;
	geo->logstart = sbp->sb_logstart;
	BUILD_BUG_ON(sizeof(geo->uuid) != sizeof(sbp->sb_uuid));
	memcpy(geo->uuid, &sbp->sb_uuid, sizeof(sbp->sb_uuid));

	if (struct_version < 2)
		return 0;

	geo->sunit = sbp->sb_unit;
	geo->swidth = sbp->sb_width;

	if (struct_version < 3)
		return 0;

	geo->version = XFS_FSOP_GEOM_VERSION;
	geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK |
1121 1122
		     XFS_FSOP_GEOM_FLAGS_DIRV2 |
		     XFS_FSOP_GEOM_FLAGS_EXTFLG;
1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159
	if (xfs_sb_version_hasattr(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR;
	if (xfs_sb_version_hasquota(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_QUOTA;
	if (xfs_sb_version_hasalign(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_IALIGN;
	if (xfs_sb_version_hasdalign(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_DALIGN;
	if (xfs_sb_version_hassector(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR;
	if (xfs_sb_version_hasasciici(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_DIRV2CI;
	if (xfs_sb_version_haslazysbcount(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_LAZYSB;
	if (xfs_sb_version_hasattr2(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR2;
	if (xfs_sb_version_hasprojid32bit(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_PROJID32;
	if (xfs_sb_version_hascrc(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_V5SB;
	if (xfs_sb_version_hasftype(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_FTYPE;
	if (xfs_sb_version_hasfinobt(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_FINOBT;
	if (xfs_sb_version_hassparseinodes(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_SPINODES;
	if (xfs_sb_version_hasrmapbt(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_RMAPBT;
	if (xfs_sb_version_hasreflink(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_REFLINK;
	if (xfs_sb_version_hassector(sbp))
		geo->logsectsize = sbp->sb_logsectsize;
	else
		geo->logsectsize = BBSIZE;
	geo->rtsectsize = sbp->sb_blocksize;
	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);

1160
	if (struct_version < 4)
1161 1162 1163 1164 1165 1166
		return 0;

	if (xfs_sb_version_haslogv2(sbp))
		geo->flags |= XFS_FSOP_GEOM_FLAGS_LOGV2;

	geo->logsunit = sbp->sb_logsunit;
1167 1168 1169

	return 0;
}
1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191

/* Read a secondary superblock. */
int
xfs_sb_read_secondary(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	struct xfs_buf		**bpp)
{
	struct xfs_buf		*bp;
	int			error;

	ASSERT(agno != 0 && agno != NULLAGNUMBER);
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
	if (error)
		return error;
	xfs_buf_set_ref(bp, XFS_SSB_REF);
	*bpp = bp;
	return 0;
}
D
Darrick J. Wong 已提交
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213

/* Get an uninitialised secondary superblock buffer. */
int
xfs_sb_get_secondary(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	struct xfs_buf		**bpp)
{
	struct xfs_buf		*bp;

	ASSERT(agno != 0 && agno != NULLAGNUMBER);
	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
			XFS_FSS_TO_BB(mp, 1), 0);
	if (!bp)
		return -ENOMEM;
	bp->b_ops = &xfs_sb_buf_ops;
	xfs_buf_oneshot(bp);
	*bpp = bp;
	return 0;
}