ops_fstype.c 35.3 KB
Newer Older
D
David Teigland 已提交
1 2
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
3
 * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
D
David Teigland 已提交
4 5 6
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
7
 * of the GNU General Public License version 2.
D
David Teigland 已提交
8 9 10 11 12 13 14 15 16
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/kthread.h>
17 18
#include <linux/namei.h>
#include <linux/mount.h>
19
#include <linux/gfs2_ondisk.h>
20
#include <linux/slow-work.h>
21
#include <linux/quotaops.h>
D
David Teigland 已提交
22 23

#include "gfs2.h"
24
#include "incore.h"
B
Bob Peterson 已提交
25
#include "bmap.h"
D
David Teigland 已提交
26 27 28 29 30 31 32
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "sys.h"
33
#include "util.h"
34
#include "log.h"
35
#include "quota.h"
36
#include "dir.h"
S
Steven Whitehouse 已提交
37
#include "trace_gfs2.h"
D
David Teigland 已提交
38 39 40 41

#define DO 0
#define UNDO 1

S
Steven Whitehouse 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
static const u32 gfs2_old_fs_formats[] = {
        0
};

static const u32 gfs2_old_multihost_formats[] = {
        0
};

/**
 * gfs2_tune_init - Fill a gfs2_tune structure with default values
 * @gt: tune
 *
 */

static void gfs2_tune_init(struct gfs2_tune *gt)
{
	spin_lock_init(&gt->gt_spin);

	gt->gt_incore_log_blocks = 1024;
	gt->gt_logd_secs = 1;
	gt->gt_quota_simul_sync = 64;
	gt->gt_quota_warn_period = 10;
	gt->gt_quota_scale_num = 1;
	gt->gt_quota_scale_den = 1;
	gt->gt_new_files_jdata = 0;
	gt->gt_max_readahead = 1 << 18;
	gt->gt_stall_secs = 600;
	gt->gt_complain_secs = 10;
}

D
David Teigland 已提交
72 73 74 75
static struct gfs2_sbd *init_sbd(struct super_block *sb)
{
	struct gfs2_sbd *sdp;

76
	sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
D
David Teigland 已提交
77 78 79
	if (!sdp)
		return NULL;

80
	sb->s_fs_info = sdp;
D
David Teigland 已提交
81 82 83 84
	sdp->sd_vfs = sb;

	gfs2_tune_init(&sdp->sd_tune);

85 86
	init_waitqueue_head(&sdp->sd_glock_wait);
	atomic_set(&sdp->sd_glock_disposal, 0);
D
David Teigland 已提交
87 88 89
	spin_lock_init(&sdp->sd_statfs_spin);

	spin_lock_init(&sdp->sd_rindex_spin);
90
	mutex_init(&sdp->sd_rindex_mutex);
D
David Teigland 已提交
91 92 93 94 95
	INIT_LIST_HEAD(&sdp->sd_rindex_list);
	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);

	INIT_LIST_HEAD(&sdp->sd_jindex_list);
	spin_lock_init(&sdp->sd_jindex_spin);
96
	mutex_init(&sdp->sd_jindex_mutex);
D
David Teigland 已提交
97 98

	INIT_LIST_HEAD(&sdp->sd_quota_list);
99
	mutex_init(&sdp->sd_quota_mutex);
100
	init_waitqueue_head(&sdp->sd_quota_wait);
101 102
	INIT_LIST_HEAD(&sdp->sd_trunc_list);
	spin_lock_init(&sdp->sd_trunc_lock);
D
David Teigland 已提交
103 104 105 106 107 108 109

	spin_lock_init(&sdp->sd_log_lock);

	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
110
	INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
D
David Teigland 已提交
111

112
	mutex_init(&sdp->sd_log_reserve_mutex);
D
David Teigland 已提交
113 114 115
	INIT_LIST_HEAD(&sdp->sd_ail1_list);
	INIT_LIST_HEAD(&sdp->sd_ail2_list);

116
	init_rwsem(&sdp->sd_log_flush_lock);
117 118
	atomic_set(&sdp->sd_log_in_flight, 0);
	init_waitqueue_head(&sdp->sd_log_flush_wait);
D
David Teigland 已提交
119 120 121

	INIT_LIST_HEAD(&sdp->sd_revoke_list);

122
	mutex_init(&sdp->sd_freeze_lock);
D
David Teigland 已提交
123 124 125 126 127

	return sdp;
}


S
Steven Whitehouse 已提交
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
/**
 * gfs2_check_sb - Check superblock
 * @sdp: the filesystem
 * @sb: The superblock
 * @silent: Don't print a message if the check fails
 *
 * Checks the version code of the FS is one that we understand how to
 * read and that the sizes of the various on-disk structures have not
 * changed.
 */

static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
{
	unsigned int x;

	if (sb->sb_magic != GFS2_MAGIC ||
	    sb->sb_type != GFS2_METATYPE_SB) {
		if (!silent)
			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
		return -EINVAL;
	}

	/*  If format numbers match exactly, we're done.  */

	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
		return 0;

	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
		for (x = 0; gfs2_old_fs_formats[x]; x++)
			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
				break;

		if (!gfs2_old_fs_formats[x]) {
			printk(KERN_WARNING
			       "GFS2: code version (%u, %u) is incompatible "
			       "with ondisk format (%u, %u)\n",
			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
			       sb->sb_fs_format, sb->sb_multihost_format);
			printk(KERN_WARNING
			       "GFS2: I don't know how to upgrade this FS\n");
			return -EINVAL;
		}
	}

	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
		for (x = 0; gfs2_old_multihost_formats[x]; x++)
			if (gfs2_old_multihost_formats[x] ==
			    sb->sb_multihost_format)
				break;

		if (!gfs2_old_multihost_formats[x]) {
			printk(KERN_WARNING
			       "GFS2: code version (%u, %u) is incompatible "
			       "with ondisk format (%u, %u)\n",
			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
			       sb->sb_fs_format, sb->sb_multihost_format);
			printk(KERN_WARNING
			       "GFS2: I don't know how to upgrade this FS\n");
			return -EINVAL;
		}
	}

	if (!sdp->sd_args.ar_upgrade) {
		printk(KERN_WARNING
		       "GFS2: code version (%u, %u) is incompatible "
		       "with ondisk format (%u, %u)\n",
		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
		       sb->sb_fs_format, sb->sb_multihost_format);
		printk(KERN_INFO
		       "GFS2: Use the \"upgrade\" mount option to upgrade "
		       "the FS\n");
		printk(KERN_INFO "GFS2: See the manual for more details\n");
		return -EINVAL;
	}

	return 0;
}

static void end_bio_io_page(struct bio *bio, int error)
{
	struct page *page = bio->bi_private;

	if (!error)
		SetPageUptodate(page);
	else
		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
	unlock_page(page);
}

static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
{
	const struct gfs2_sb *str = buf;

	sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
	sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
	sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
	sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
	sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
	sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
	sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);

	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
236
	memcpy(sb->sb_uuid, str->sb_uuid, 16);
S
Steven Whitehouse 已提交
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
}

/**
 * gfs2_read_super - Read the gfs2 super block from disk
 * @sdp: The GFS2 super block
 * @sector: The location of the super block
 * @error: The error code to return
 *
 * This uses the bio functions to read the super block from disk
 * because we want to be 100% sure that we never read cached data.
 * A super block is read twice only during each GFS2 mount and is
 * never written to by the filesystem. The first time its read no
 * locks are held, and the only details which are looked at are those
 * relating to the locking protocol. Once locking is up and working,
 * the sb is read again under the lock to establish the location of
 * the master directory (contains pointers to journals etc) and the
 * root directory.
 *
 * Returns: 0 on success or error
 */

static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
{
	struct super_block *sb = sdp->sd_vfs;
	struct gfs2_sb *p;
	struct page *page;
	struct bio *bio;

	page = alloc_page(GFP_NOFS);
	if (unlikely(!page))
		return -ENOBUFS;

	ClearPageUptodate(page);
	ClearPageDirty(page);
	lock_page(page);

	bio = bio_alloc(GFP_NOFS, 1);
	bio->bi_sector = sector * (sb->s_blocksize >> 9);
	bio->bi_bdev = sb->s_bdev;
	bio_add_page(bio, page, PAGE_SIZE, 0);

	bio->bi_end_io = end_bio_io_page;
	bio->bi_private = page;
	submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
	wait_on_page_locked(page);
	bio_put(bio);
	if (!PageUptodate(page)) {
		__free_page(page);
		return -EIO;
	}
	p = kmap(page);
	gfs2_sb_in(&sdp->sd_sb, p);
	kunmap(page);
	__free_page(page);
	return 0;
}
S
Steven Whitehouse 已提交
293

S
Steven Whitehouse 已提交
294 295 296 297 298 299 300
/**
 * gfs2_read_sb - Read super block
 * @sdp: The GFS2 superblock
 * @silent: Don't print message if mount fails
 *
 */

S
Steven Whitehouse 已提交
301
static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
S
Steven Whitehouse 已提交
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
{
	u32 hash_blocks, ind_blocks, leaf_blocks;
	u32 tmp_blocks;
	unsigned int x;
	int error;

	error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
	if (error) {
		if (!silent)
			fs_err(sdp, "can't read superblock\n");
		return error;
	}

	error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
	if (error)
		return error;

	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
			       GFS2_BASIC_BLOCK_SHIFT;
	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
			  sizeof(struct gfs2_dinode)) / sizeof(u64);
	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_meta_header)) /
			        sizeof(struct gfs2_quota_change);

	/* Compute maximum reservation required to add a entry to a directory */

	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
			     sdp->sd_jbsize);

	ind_blocks = 0;
	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
		ind_blocks += tmp_blocks;
	}

	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;

	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;

	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_dinode);
	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
	for (x = 2;; x++) {
		u64 space, d;
		u32 m;

		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
		d = space;
		m = do_div(d, sdp->sd_inptrs);

		if (d != sdp->sd_heightsize[x - 1] || m)
			break;
		sdp->sd_heightsize[x] = space;
	}
	sdp->sd_max_height = x;
	sdp->sd_heightsize[x] = ~0;
	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);

	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
				 sizeof(struct gfs2_dinode);
	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
	for (x = 2;; x++) {
		u64 space, d;
		u32 m;

		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
		d = space;
		m = do_div(d, sdp->sd_inptrs);

		if (d != sdp->sd_jheightsize[x - 1] || m)
			break;
		sdp->sd_jheightsize[x] = space;
	}
	sdp->sd_max_jheight = x;
	sdp->sd_jheightsize[x] = ~0;
	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);

	return 0;
}

D
David Teigland 已提交
390 391 392 393 394 395 396 397 398 399 400
static int init_names(struct gfs2_sbd *sdp, int silent)
{
	char *proto, *table;
	int error = 0;

	proto = sdp->sd_args.ar_lockproto;
	table = sdp->sd_args.ar_locktable;

	/*  Try to autodetect  */

	if (!proto[0] || !table[0]) {
401 402 403
		error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
		if (error)
			return error;
404 405

		error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
D
David Teigland 已提交
406 407 408 409
		if (error)
			goto out;

		if (!proto[0])
410
			proto = sdp->sd_sb.sb_lockproto;
D
David Teigland 已提交
411
		if (!table[0])
412
			table = sdp->sd_sb.sb_locktable;
D
David Teigland 已提交
413 414 415 416 417
	}

	if (!table[0])
		table = sdp->sd_vfs->s_id;

418 419
	strlcpy(sdp->sd_proto_name, proto, GFS2_FSNAME_LEN);
	strlcpy(sdp->sd_table_name, table, GFS2_FSNAME_LEN);
D
David Teigland 已提交
420

421 422
	table = sdp->sd_table_name;
	while ((table = strchr(table, '/')))
423 424
		*table = '_';

425
out:
D
David Teigland 已提交
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
	return error;
}

static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
			int undo)
{
	int error = 0;

	if (undo)
		goto fail_trans;

	error = gfs2_glock_nq_num(sdp,
				  GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
				  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
				  mount_gh);
	if (error) {
		fs_err(sdp, "can't acquire mount glock: %d\n", error);
		goto fail;
	}

	error = gfs2_glock_nq_num(sdp,
				  GFS2_LIVE_LOCK, &gfs2_nondisk_glops,
				  LM_ST_SHARED,
449
				  LM_FLAG_NOEXP | GL_EXACT,
D
David Teigland 已提交
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
				  &sdp->sd_live_gh);
	if (error) {
		fs_err(sdp, "can't acquire live glock: %d\n", error);
		goto fail_mount;
	}

	error = gfs2_glock_get(sdp, GFS2_RENAME_LOCK, &gfs2_nondisk_glops,
			       CREATE, &sdp->sd_rename_gl);
	if (error) {
		fs_err(sdp, "can't create rename glock: %d\n", error);
		goto fail_live;
	}

	error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
			       CREATE, &sdp->sd_trans_gl);
	if (error) {
		fs_err(sdp, "can't create transaction glock: %d\n", error);
		goto fail_rename;
	}

	return 0;

472
fail_trans:
D
David Teigland 已提交
473
	gfs2_glock_put(sdp->sd_trans_gl);
474
fail_rename:
D
David Teigland 已提交
475
	gfs2_glock_put(sdp->sd_rename_gl);
476
fail_live:
D
David Teigland 已提交
477
	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
478
fail_mount:
D
David Teigland 已提交
479
	gfs2_glock_dq_uninit(mount_gh);
480
fail:
D
David Teigland 已提交
481 482 483
	return error;
}

S
Steven Whitehouse 已提交
484 485
static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
			    u64 no_addr, const char *name)
486
{
S
Steven Whitehouse 已提交
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct dentry *dentry;
	struct inode *inode;

	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
	if (IS_ERR(inode)) {
		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
		return PTR_ERR(inode);
	}
	dentry = d_alloc_root(inode);
	if (!dentry) {
		fs_err(sdp, "can't alloc %s dentry\n", name);
		iput(inode);
		return -ENOMEM;
	}
	dentry->d_op = &gfs2_dops;
	*dptr = dentry;
	return 0;
505 506
}

S
Steven Whitehouse 已提交
507
static int init_sb(struct gfs2_sbd *sdp, int silent)
D
David Teigland 已提交
508 509 510
{
	struct super_block *sb = sdp->sd_vfs;
	struct gfs2_holder sb_gh;
511
	u64 no_addr;
S
Steven Whitehouse 已提交
512
	int ret;
D
David Teigland 已提交
513

S
Steven Whitehouse 已提交
514 515 516 517 518
	ret = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
				LM_ST_SHARED, 0, &sb_gh);
	if (ret) {
		fs_err(sdp, "can't acquire superblock glock: %d\n", ret);
		return ret;
D
David Teigland 已提交
519
	}
520

S
Steven Whitehouse 已提交
521
	ret = gfs2_read_sb(sdp, silent);
S
Steven Whitehouse 已提交
522 523
	if (ret) {
		fs_err(sdp, "can't read superblock: %d\n", ret);
D
David Teigland 已提交
524 525 526 527
		goto out;
	}

	/* Set up the buffer cache and SB for real */
528
	if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) {
S
Steven Whitehouse 已提交
529
		ret = -EINVAL;
D
David Teigland 已提交
530 531
		fs_err(sdp, "FS block size (%u) is too small for device "
		       "block size (%u)\n",
532
		       sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev));
D
David Teigland 已提交
533 534 535
		goto out;
	}
	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
S
Steven Whitehouse 已提交
536
		ret = -EINVAL;
D
David Teigland 已提交
537 538 539 540 541 542 543
		fs_err(sdp, "FS block size (%u) is too big for machine "
		       "page size (%u)\n",
		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
		goto out;
	}
	sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);

544
	/* Get the root inode */
545
	no_addr = sdp->sd_sb.sb_root_dir.no_addr;
S
Steven Whitehouse 已提交
546 547
	ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
	if (ret)
548
		goto out;
D
David Teigland 已提交
549

S
Steven Whitehouse 已提交
550 551 552 553 554 555 556 557
	/* Get the master inode */
	no_addr = sdp->sd_sb.sb_master_dir.no_addr;
	ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
	if (ret) {
		dput(sdp->sd_root_dir);
		goto out;
	}
	sb->s_root = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
558
out:
D
David Teigland 已提交
559
	gfs2_glock_dq_uninit(&sb_gh);
S
Steven Whitehouse 已提交
560
	return ret;
D
David Teigland 已提交
561 562
}

B
Bob Peterson 已提交
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
/**
 * map_journal_extents - create a reusable "extent" mapping from all logical
 * blocks to all physical blocks for the given journal.  This will save
 * us time when writing journal blocks.  Most journals will have only one
 * extent that maps all their logical blocks.  That's because gfs2.mkfs
 * arranges the journal blocks sequentially to maximize performance.
 * So the extent would map the first block for the entire file length.
 * However, gfs2_jadd can happen while file activity is happening, so
 * those journals may not be sequential.  Less likely is the case where
 * the users created their own journals by mounting the metafs and
 * laying it out.  But it's still possible.  These journals might have
 * several extents.
 *
 * TODO: This should be done in bigger chunks rather than one block at a time,
 *       but since it's only done at mount time, I'm not worried about the
 *       time it takes.
 */
static int map_journal_extents(struct gfs2_sbd *sdp)
{
	struct gfs2_jdesc *jd = sdp->sd_jdesc;
	unsigned int lb;
	u64 db, prev_db; /* logical block, disk block, prev disk block */
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_journal_extent *jext = NULL;
	struct buffer_head bh;
	int rc = 0;

	prev_db = 0;

592
	for (lb = 0; lb < ip->i_disksize >> sdp->sd_sb.sb_bsize_shift; lb++) {
B
Bob Peterson 已提交
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
		bh.b_state = 0;
		bh.b_blocknr = 0;
		bh.b_size = 1 << ip->i_inode.i_blkbits;
		rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
		db = bh.b_blocknr;
		if (rc || !db) {
			printk(KERN_INFO "GFS2 journal mapping error %d: lb="
			       "%u db=%llu\n", rc, lb, (unsigned long long)db);
			break;
		}
		if (!prev_db || db != prev_db + 1) {
			jext = kzalloc(sizeof(struct gfs2_journal_extent),
				       GFP_KERNEL);
			if (!jext) {
				printk(KERN_INFO "GFS2 error: out of memory "
				       "mapping journal extents.\n");
				rc = -ENOMEM;
				break;
			}
			jext->dblock = db;
			jext->lblock = lb;
			jext->blocks = 1;
			list_add_tail(&jext->extent_list, &jd->extent_list);
		} else {
			jext->blocks++;
		}
		prev_db = db;
	}
	return rc;
}

624
static void gfs2_others_may_mount(struct gfs2_sbd *sdp)
625
{
626 627 628 629 630
	char *message = "FIRSTMOUNT=Done";
	char *envp[] = { message, NULL };
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	ls->ls_first_done = 1;
	kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
631 632
}

633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677
/**
 * gfs2_jindex_hold - Grab a lock on the jindex
 * @sdp: The GFS2 superblock
 * @ji_gh: the holder for the jindex glock
 *
 * Returns: errno
 */

static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
{
	struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
	struct qstr name;
	char buf[20];
	struct gfs2_jdesc *jd;
	int error;

	name.name = buf;

	mutex_lock(&sdp->sd_jindex_mutex);

	for (;;) {
		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, ji_gh);
		if (error)
			break;

		name.len = sprintf(buf, "journal%u", sdp->sd_journals);
		name.hash = gfs2_disk_hash(name.name, name.len);

		error = gfs2_dir_check(sdp->sd_jindex, &name, NULL);
		if (error == -ENOENT) {
			error = 0;
			break;
		}

		gfs2_glock_dq_uninit(ji_gh);

		if (error)
			break;

		error = -ENOMEM;
		jd = kzalloc(sizeof(struct gfs2_jdesc), GFP_KERNEL);
		if (!jd)
			break;

		INIT_LIST_HEAD(&jd->extent_list);
678
		slow_work_init(&jd->jd_work, &gfs2_recover_ops);
679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699
		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
			if (!jd->jd_inode)
				error = -ENOENT;
			else
				error = PTR_ERR(jd->jd_inode);
			kfree(jd);
			break;
		}

		spin_lock(&sdp->sd_jindex_spin);
		jd->jd_jid = sdp->sd_journals++;
		list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
		spin_unlock(&sdp->sd_jindex_spin);
	}

	mutex_unlock(&sdp->sd_jindex_mutex);

	return error;
}

D
David Teigland 已提交
700 701
static int init_journal(struct gfs2_sbd *sdp, int undo)
{
S
Steven Whitehouse 已提交
702
	struct inode *master = sdp->sd_master_dir->d_inode;
D
David Teigland 已提交
703
	struct gfs2_holder ji_gh;
704
	struct gfs2_inode *ip;
D
David Teigland 已提交
705 706 707 708 709
	int jindex = 1;
	int error = 0;

	if (undo) {
		jindex = 0;
710
		goto fail_jinode_gh;
D
David Teigland 已提交
711 712
	}

S
Steven Whitehouse 已提交
713
	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
714
	if (IS_ERR(sdp->sd_jindex)) {
D
David Teigland 已提交
715
		fs_err(sdp, "can't lookup journal index: %d\n", error);
716
		return PTR_ERR(sdp->sd_jindex);
D
David Teigland 已提交
717
	}
718
	ip = GFS2_I(sdp->sd_jindex);
D
David Teigland 已提交
719 720 721 722 723 724 725 726 727

	/* Load in the journal index special file */

	error = gfs2_jindex_hold(sdp, &ji_gh);
	if (error) {
		fs_err(sdp, "can't read journal index: %d\n", error);
		goto fail;
	}

A
Abhijith Das 已提交
728
	error = -EUSERS;
D
David Teigland 已提交
729 730
	if (!gfs2_jindex_size(sdp)) {
		fs_err(sdp, "no journals!\n");
731
		goto fail_jindex;
D
David Teigland 已提交
732 733 734 735
	}

	if (sdp->sd_args.ar_spectator) {
		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
736
		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
D
David Teigland 已提交
737 738 739 740 741 742 743 744 745 746 747
	} else {
		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
			fs_err(sdp, "can't mount journal #%u\n",
			       sdp->sd_lockstruct.ls_jid);
			fs_err(sdp, "there are only %u journals (0 - %u)\n",
			       gfs2_jindex_size(sdp),
			       gfs2_jindex_size(sdp) - 1);
			goto fail_jindex;
		}
		sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);

748
		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
D
David Teigland 已提交
749 750 751 752 753 754 755 756
					  &gfs2_journal_glops,
					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
					  &sdp->sd_journal_gh);
		if (error) {
			fs_err(sdp, "can't acquire journal glock: %d\n", error);
			goto fail_jindex;
		}

757 758
		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
759
					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
D
David Teigland 已提交
760 761 762 763 764 765 766 767 768 769 770 771 772
					   &sdp->sd_jinode_gh);
		if (error) {
			fs_err(sdp, "can't acquire journal inode glock: %d\n",
			       error);
			goto fail_journal_gh;
		}

		error = gfs2_jdesc_check(sdp->sd_jdesc);
		if (error) {
			fs_err(sdp, "my journal (%u) is bad: %d\n",
			       sdp->sd_jdesc->jd_jid, error);
			goto fail_jinode_gh;
		}
773
		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
B
Bob Peterson 已提交
774 775 776

		/* Map the extents for this journal's blocks */
		map_journal_extents(sdp);
D
David Teigland 已提交
777
	}
S
Steven Whitehouse 已提交
778
	trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free));
D
David Teigland 已提交
779 780 781 782

	if (sdp->sd_lockstruct.ls_first) {
		unsigned int x;
		for (x = 0; x < sdp->sd_journals; x++) {
D
David Teigland 已提交
783
			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
D
David Teigland 已提交
784 785 786 787 788 789 790
			if (error) {
				fs_err(sdp, "error recovering journal %u: %d\n",
				       x, error);
				goto fail_jinode_gh;
			}
		}

791
		gfs2_others_may_mount(sdp);
D
David Teigland 已提交
792
	} else if (!sdp->sd_args.ar_spectator) {
D
David Teigland 已提交
793
		error = gfs2_recover_journal(sdp->sd_jdesc);
D
David Teigland 已提交
794 795 796 797 798 799 800 801 802 803 804 805
		if (error) {
			fs_err(sdp, "error recovering my journal: %d\n", error);
			goto fail_jinode_gh;
		}
	}

	set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
	gfs2_glock_dq_uninit(&ji_gh);
	jindex = 0;

	return 0;

806
fail_jinode_gh:
D
David Teigland 已提交
807 808
	if (!sdp->sd_args.ar_spectator)
		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
809
fail_journal_gh:
D
David Teigland 已提交
810 811
	if (!sdp->sd_args.ar_spectator)
		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
812
fail_jindex:
D
David Teigland 已提交
813 814 815
	gfs2_jindex_free(sdp);
	if (jindex)
		gfs2_glock_dq_uninit(&ji_gh);
816
fail:
817
	iput(sdp->sd_jindex);
D
David Teigland 已提交
818 819 820 821 822 823 824
	return error;
}


static int init_inodes(struct gfs2_sbd *sdp, int undo)
{
	int error = 0;
825
	struct gfs2_inode *ip;
S
Steven Whitehouse 已提交
826
	struct inode *master = sdp->sd_master_dir->d_inode;
D
David Teigland 已提交
827 828

	if (undo)
829 830 831 832
		goto fail_qinode;

	error = init_journal(sdp, undo);
	if (error)
S
Steven Whitehouse 已提交
833
		goto fail;
D
David Teigland 已提交
834 835

	/* Read in the master statfs inode */
S
Steven Whitehouse 已提交
836
	sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
837 838
	if (IS_ERR(sdp->sd_statfs_inode)) {
		error = PTR_ERR(sdp->sd_statfs_inode);
D
David Teigland 已提交
839
		fs_err(sdp, "can't read in statfs inode: %d\n", error);
840
		goto fail_journal;
D
David Teigland 已提交
841 842 843
	}

	/* Read in the resource index inode */
S
Steven Whitehouse 已提交
844
	sdp->sd_rindex = gfs2_lookup_simple(master, "rindex");
845 846
	if (IS_ERR(sdp->sd_rindex)) {
		error = PTR_ERR(sdp->sd_rindex);
D
David Teigland 已提交
847 848 849
		fs_err(sdp, "can't get resource index inode: %d\n", error);
		goto fail_statfs;
	}
850
	ip = GFS2_I(sdp->sd_rindex);
851
	sdp->sd_rindex_uptodate = 0;
D
David Teigland 已提交
852 853

	/* Read in the quota inode */
S
Steven Whitehouse 已提交
854
	sdp->sd_quota_inode = gfs2_lookup_simple(master, "quota");
855 856
	if (IS_ERR(sdp->sd_quota_inode)) {
		error = PTR_ERR(sdp->sd_quota_inode);
D
David Teigland 已提交
857 858 859 860 861
		fs_err(sdp, "can't get quota file inode: %d\n", error);
		goto fail_rindex;
	}
	return 0;

862 863 864
fail_qinode:
	iput(sdp->sd_quota_inode);
fail_rindex:
D
David Teigland 已提交
865
	gfs2_clear_rgrpd(sdp);
866 867 868 869 870 871
	iput(sdp->sd_rindex);
fail_statfs:
	iput(sdp->sd_statfs_inode);
fail_journal:
	init_journal(sdp, UNDO);
fail:
D
David Teigland 已提交
872 873 874 875 876
	return error;
}

static int init_per_node(struct gfs2_sbd *sdp, int undo)
{
877
	struct inode *pn = NULL;
D
David Teigland 已提交
878 879
	char buf[30];
	int error = 0;
880
	struct gfs2_inode *ip;
S
Steven Whitehouse 已提交
881
	struct inode *master = sdp->sd_master_dir->d_inode;
D
David Teigland 已提交
882 883 884 885 886 887 888

	if (sdp->sd_args.ar_spectator)
		return 0;

	if (undo)
		goto fail_qc_gh;

S
Steven Whitehouse 已提交
889
	pn = gfs2_lookup_simple(master, "per_node");
890 891
	if (IS_ERR(pn)) {
		error = PTR_ERR(pn);
D
David Teigland 已提交
892 893 894 895 896
		fs_err(sdp, "can't find per_node directory: %d\n", error);
		return error;
	}

	sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
897 898 899
	sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
	if (IS_ERR(sdp->sd_sc_inode)) {
		error = PTR_ERR(sdp->sd_sc_inode);
D
David Teigland 已提交
900
		fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
901
		goto fail;
D
David Teigland 已提交
902 903 904
	}

	sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
905 906 907
	sdp->sd_qc_inode = gfs2_lookup_simple(pn, buf);
	if (IS_ERR(sdp->sd_qc_inode)) {
		error = PTR_ERR(sdp->sd_qc_inode);
D
David Teigland 已提交
908 909 910 911
		fs_err(sdp, "can't find local \"qc\" file: %d\n", error);
		goto fail_ut_i;
	}

912
	iput(pn);
D
David Teigland 已提交
913 914
	pn = NULL;

915
	ip = GFS2_I(sdp->sd_sc_inode);
916
	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
D
David Teigland 已提交
917 918 919
				   &sdp->sd_sc_gh);
	if (error) {
		fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
920
		goto fail_qc_i;
D
David Teigland 已提交
921 922
	}

923
	ip = GFS2_I(sdp->sd_qc_inode);
924
	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
D
David Teigland 已提交
925 926 927 928 929 930 931 932
				   &sdp->sd_qc_gh);
	if (error) {
		fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
		goto fail_ut_gh;
	}

	return 0;

933
fail_qc_gh:
D
David Teigland 已提交
934
	gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
935
fail_ut_gh:
D
David Teigland 已提交
936
	gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
937
fail_qc_i:
938
	iput(sdp->sd_qc_inode);
939
fail_ut_i:
940
	iput(sdp->sd_sc_inode);
941
fail:
D
David Teigland 已提交
942
	if (pn)
943
		iput(pn);
D
David Teigland 已提交
944 945 946 947 948 949 950 951 952
	return error;
}

static int init_threads(struct gfs2_sbd *sdp, int undo)
{
	struct task_struct *p;
	int error = 0;

	if (undo)
953
		goto fail_quotad;
D
David Teigland 已提交
954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975

	sdp->sd_log_flush_time = jiffies;

	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
	error = IS_ERR(p);
	if (error) {
		fs_err(sdp, "can't start logd thread: %d\n", error);
		return error;
	}
	sdp->sd_logd_process = p;

	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
	error = IS_ERR(p);
	if (error) {
		fs_err(sdp, "can't start quotad thread: %d\n", error);
		goto fail;
	}
	sdp->sd_quotad_process = p;

	return 0;


976
fail_quotad:
D
David Teigland 已提交
977
	kthread_stop(sdp->sd_quotad_process);
978
fail:
D
David Teigland 已提交
979 980 981
	kthread_stop(sdp->sd_logd_process);
	return error;
}
982

983 984 985 986 987
static const match_table_t nolock_tokens = {
	{ Opt_jid, "jid=%d\n", },
	{ Opt_err, NULL },
};

988 989 990 991 992 993 994 995
static void nolock_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	kmem_cache_free(cachep, gl);
	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
		wake_up(&sdp->sd_glock_wait);
}

996 997
static const struct lm_lockops nolock_ops = {
	.lm_proto_name = "lock_nolock",
998
	.lm_put_lock = nolock_put_lock,
999 1000 1001
	.lm_tokens = &nolock_tokens,
};

1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
/**
 * gfs2_lm_mount - mount a locking protocol
 * @sdp: the filesystem
 * @args: mount arguements
 * @silent: if 1, don't complain if the FS isn't a GFS2 fs
 *
 * Returns: errno
 */

static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
{
1013 1014 1015 1016 1017 1018 1019 1020
	const struct lm_lockops *lm;
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	struct gfs2_args *args = &sdp->sd_args;
	const char *proto = sdp->sd_proto_name;
	const char *table = sdp->sd_table_name;
	const char *fsname;
	char *o, *options;
	int ret;
1021

1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
	if (!strcmp("lock_nolock", proto)) {
		lm = &nolock_ops;
		sdp->sd_args.ar_localflocks = 1;
		sdp->sd_args.ar_localcaching = 1;
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
	} else if (!strcmp("lock_dlm", proto)) {
		lm = &gfs2_dlm_ops;
#endif
	} else {
		printk(KERN_INFO "GFS2: can't find protocol %s\n", proto);
		return -ENOENT;
	}
1034 1035 1036

	fs_info(sdp, "Trying to join cluster \"%s\", \"%s\"\n", proto, table);

1037 1038
	ls->ls_ops = lm;
	ls->ls_first = 1;
1039

1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
	for (options = args->ar_hostdata; (o = strsep(&options, ":")); ) {
		substring_t tmp[MAX_OPT_ARGS];
		int token, option;

		if (!o || !*o)
			continue;

		token = match_token(o, *lm->lm_tokens, tmp);
		switch (token) {
		case Opt_jid:
			ret = match_int(&tmp[0], &option);
			if (ret || option < 0) 
				goto hostdata_error;
			ls->ls_jid = option;
			break;
		case Opt_id:
1056
			/* Obsolete, but left for backward compat purposes */
1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075
			break;
		case Opt_first:
			ret = match_int(&tmp[0], &option);
			if (ret || (option != 0 && option != 1))
				goto hostdata_error;
			ls->ls_first = option;
			break;
		case Opt_nodir:
			ret = match_int(&tmp[0], &option);
			if (ret || (option != 0 && option != 1))
				goto hostdata_error;
			ls->ls_nodir = option;
			break;
		case Opt_err:
		default:
hostdata_error:
			fs_info(sdp, "unknown hostdata (%s)\n", o);
			return -EINVAL;
		}
1076 1077 1078 1079 1080 1081 1082 1083
	}

	if (sdp->sd_args.ar_spectator)
		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.s", table);
	else
		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", table,
			 sdp->sd_lockstruct.ls_jid);

1084 1085 1086 1087 1088 1089
	fsname = strchr(table, ':');
	if (fsname)
		fsname++;
	if (lm->lm_mount == NULL) {
		fs_info(sdp, "Now mounting FS...\n");
		return 0;
1090
	}
1091 1092 1093 1094
	ret = lm->lm_mount(sdp, fsname);
	if (ret == 0)
		fs_info(sdp, "Joined cluster. Now mounting FS...\n");
	return ret;
1095 1096 1097 1098
}

void gfs2_lm_unmount(struct gfs2_sbd *sdp)
{
1099 1100 1101 1102
	const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
	    lm->lm_unmount)
		lm->lm_unmount(sdp);
1103
}
D
David Teigland 已提交
1104

1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115
void gfs2_online_uevent(struct gfs2_sbd *sdp)
{
	struct super_block *sb = sdp->sd_vfs;
	char ro[20];
	char spectator[20];
	char *envp[] = { ro, spectator, NULL };
	sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
	sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);
	kobject_uevent_env(&sdp->sd_kobj, KOBJ_ONLINE, envp);
}

D
David Teigland 已提交
1116 1117 1118 1119 1120 1121 1122 1123 1124
/**
 * fill_super - Read in superblock
 * @sb: The VFS superblock
 * @data: Mount options
 * @silent: Don't complain if it's not a GFS2 filesystem
 *
 * Returns: errno
 */

1125
static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent)
D
David Teigland 已提交
1126 1127 1128 1129 1130 1131 1132
{
	struct gfs2_sbd *sdp;
	struct gfs2_holder mount_gh;
	int error;

	sdp = init_sbd(sb);
	if (!sdp) {
1133
		printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n");
D
David Teigland 已提交
1134 1135
		return -ENOMEM;
	}
1136
	sdp->sd_args = *args;
D
David Teigland 已提交
1137

1138
	if (sdp->sd_args.ar_spectator) {
1139
                sb->s_flags |= MS_RDONLY;
1140 1141
		set_bit(SDF_NORECOVERY, &sdp->sd_flags);
	}
1142 1143
	if (sdp->sd_args.ar_posix_acl)
		sb->s_flags |= MS_POSIXACL;
1144 1145
	if (sdp->sd_args.ar_nobarrier)
		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
1146

1147 1148 1149
	sb->s_magic = GFS2_MAGIC;
	sb->s_op = &gfs2_super_ops;
	sb->s_export_op = &gfs2_export_ops;
1150
	sb->s_xattr = gfs2_xattr_handlers;
1151 1152
	sb->s_qcop = &gfs2_quotactl_ops;
	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
1153 1154
	sb->s_time_gran = 1;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
1155 1156 1157 1158 1159 1160 1161 1162

	/* Set up the buffer cache and fill in some fake block size values
	   to allow us to read-in the on-disk superblock. */
	sdp->sd_sb.sb_bsize = sb_min_blocksize(sb, GFS2_BASIC_BLOCK);
	sdp->sd_sb.sb_bsize_shift = sb->s_blocksize_bits;
	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
                               GFS2_BASIC_BLOCK_SHIFT;
	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
D
David Teigland 已提交
1163

1164
	sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit;
1165 1166 1167 1168 1169 1170 1171 1172 1173
	sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum;
	if (sdp->sd_args.ar_statfs_quantum) {
		sdp->sd_tune.gt_statfs_slow = 0;
		sdp->sd_tune.gt_statfs_quantum = sdp->sd_args.ar_statfs_quantum;
	}
	else {
		sdp->sd_tune.gt_statfs_slow = 1;
		sdp->sd_tune.gt_statfs_quantum = 30;
	}
1174

D
David Teigland 已提交
1175 1176 1177 1178
	error = init_names(sdp, silent);
	if (error)
		goto fail;

1179 1180
	gfs2_create_debugfs_file(sdp);

D
David Teigland 已提交
1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
	error = gfs2_sys_fs_add(sdp);
	if (error)
		goto fail;

	error = gfs2_lm_mount(sdp, silent);
	if (error)
		goto fail_sys;

	error = init_locking(sdp, &mount_gh, DO);
	if (error)
		goto fail_lm;

S
Steven Whitehouse 已提交
1193
	error = init_sb(sdp, silent);
D
David Teigland 已提交
1194 1195 1196 1197 1198
	if (error)
		goto fail_locking;

	error = init_inodes(sdp, DO);
	if (error)
1199
		goto fail_sb;
D
David Teigland 已提交
1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223

	error = init_per_node(sdp, DO);
	if (error)
		goto fail_inodes;

	error = gfs2_statfs_init(sdp);
	if (error) {
		fs_err(sdp, "can't initialize statfs subsystem: %d\n", error);
		goto fail_per_node;
	}

	error = init_threads(sdp, DO);
	if (error)
		goto fail_per_node;

	if (!(sb->s_flags & MS_RDONLY)) {
		error = gfs2_make_fs_rw(sdp);
		if (error) {
			fs_err(sdp, "can't make FS RW: %d\n", error);
			goto fail_threads;
		}
	}

	gfs2_glock_dq_uninit(&mount_gh);
1224
	gfs2_online_uevent(sdp);
D
David Teigland 已提交
1225 1226
	return 0;

1227
fail_threads:
D
David Teigland 已提交
1228
	init_threads(sdp, UNDO);
1229
fail_per_node:
D
David Teigland 已提交
1230
	init_per_node(sdp, UNDO);
1231
fail_inodes:
D
David Teigland 已提交
1232
	init_inodes(sdp, UNDO);
1233
fail_sb:
S
Steven Whitehouse 已提交
1234 1235 1236 1237
	if (sdp->sd_root_dir)
		dput(sdp->sd_root_dir);
	if (sdp->sd_master_dir)
		dput(sdp->sd_master_dir);
1238 1239
	if (sb->s_root)
		dput(sb->s_root);
S
Steven Whitehouse 已提交
1240
	sb->s_root = NULL;
1241
fail_locking:
D
David Teigland 已提交
1242
	init_locking(sdp, &mount_gh, UNDO);
1243
fail_lm:
1244
	gfs2_gl_hash_clear(sdp);
D
David Teigland 已提交
1245 1246 1247
	gfs2_lm_unmount(sdp);
	while (invalidate_inodes(sb))
		yield();
1248
fail_sys:
D
David Teigland 已提交
1249
	gfs2_sys_fs_del(sdp);
1250
fail:
R
Robert Peterson 已提交
1251
	gfs2_delete_debugfs_file(sdp);
S
Steven Whitehouse 已提交
1252
	kfree(sdp);
1253
	sb->s_fs_info = NULL;
D
David Teigland 已提交
1254 1255 1256
	return error;
}

1257
static int set_gfs2_super(struct super_block *s, void *data)
D
David Teigland 已提交
1258
{
1259 1260 1261 1262 1263 1264 1265 1266 1267
	s->s_bdev = data;
	s->s_dev = s->s_bdev->bd_dev;

	/*
	 * We set the bdi here to the queue backing, file systems can
	 * overwrite this in ->fill_super()
	 */
	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
	return 0;
1268 1269
}

1270
static int test_gfs2_super(struct super_block *s, void *ptr)
1271 1272 1273 1274 1275
{
	struct block_device *bdev = ptr;
	return (bdev == s->s_bdev);
}

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 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
/**
 * gfs2_get_sb - Get the GFS2 superblock
 * @fs_type: The GFS2 filesystem type
 * @flags: Mount flags
 * @dev_name: The name of the device
 * @data: The mount arguments
 * @mnt: The vfsmnt for this mount
 *
 * Q. Why not use get_sb_bdev() ?
 * A. We need to select one of two root directories to mount, independent
 *    of whether this is the initial, or subsequent, mount of this sb
 *
 * Returns: 0 or -ve on error
 */

static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
		       const char *dev_name, void *data, struct vfsmount *mnt)
{
	struct block_device *bdev;
	struct super_block *s;
	fmode_t mode = FMODE_READ;
	int error;
	struct gfs2_args args;
	struct gfs2_sbd *sdp;

	if (!(flags & MS_RDONLY))
		mode |= FMODE_WRITE;

	bdev = open_bdev_exclusive(dev_name, mode, fs_type);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);

	/*
	 * once the super is inserted into the list by sget, s_umount
	 * will protect the lockfs code from trying to start a snapshot
	 * while we are mounting
	 */
	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (bdev->bd_fsfreeze_count > 0) {
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		error = -EBUSY;
		goto error_bdev;
	}
	s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev);
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	error = PTR_ERR(s);
	if (IS_ERR(s))
		goto error_bdev;

	memset(&args, 0, sizeof(args));
	args.ar_quota = GFS2_QUOTA_DEFAULT;
	args.ar_data = GFS2_DATA_DEFAULT;
	args.ar_commit = 60;
1329 1330
	args.ar_statfs_quantum = 30;
	args.ar_quota_quantum = 60;
1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377
	args.ar_errors = GFS2_ERRORS_DEFAULT;

	error = gfs2_mount_args(&args, data);
	if (error) {
		printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
		if (s->s_root)
			goto error_super;
		deactivate_locked_super(s);
		return error;
	}

	if (s->s_root) {
		error = -EBUSY;
		if ((flags ^ s->s_flags) & MS_RDONLY)
			goto error_super;
		close_bdev_exclusive(bdev, mode);
	} else {
		char b[BDEVNAME_SIZE];

		s->s_flags = flags;
		s->s_mode = mode;
		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
		sb_set_blocksize(s, block_size(bdev));
		error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0);
		if (error) {
			deactivate_locked_super(s);
			return error;
		}
		s->s_flags |= MS_ACTIVE;
		bdev->bd_super = s;
	}

	sdp = s->s_fs_info;
	mnt->mnt_sb = s;
	if (args.ar_meta)
		mnt->mnt_root = dget(sdp->sd_master_dir);
	else
		mnt->mnt_root = dget(sdp->sd_root_dir);
	return 0;

error_super:
	deactivate_locked_super(s);
error_bdev:
	close_bdev_exclusive(bdev, mode);
	return error;
}

1378 1379 1380 1381 1382
static int set_meta_super(struct super_block *s, void *ptr)
{
	return -EINVAL;
}

1383 1384
static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
			    const char *dev_name, void *data, struct vfsmount *mnt)
1385
{
1386
	struct super_block *s;
1387
	struct gfs2_sbd *sdp;
A
Al Viro 已提交
1388
	struct path path;
1389
	int error;
1390

A
Al Viro 已提交
1391
	error = kern_path(dev_name, LOOKUP_FOLLOW, &path);
1392
	if (error) {
S
Steven Whitehouse 已提交
1393 1394
		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
		       dev_name, error);
1395
		return error;
1396
	}
1397
	s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super,
1398
		 path.dentry->d_inode->i_sb->s_bdev);
A
Al Viro 已提交
1399
	path_put(&path);
1400
	if (IS_ERR(s)) {
1401
		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
1402
		return PTR_ERR(s);
1403
	}
1404 1405 1406 1407
	if ((flags ^ s->s_flags) & MS_RDONLY) {
		deactivate_locked_super(s);
		return -EBUSY;
	}
1408 1409
	sdp = s->s_fs_info;
	mnt->mnt_sb = s;
S
Steven Whitehouse 已提交
1410 1411
	mnt->mnt_root = dget(sdp->sd_master_dir);
	return 0;
D
David Teigland 已提交
1412 1413
}

1414
static void gfs2_kill_sb(struct super_block *sb)
1415 1416
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
1417 1418 1419 1420

	if (sdp == NULL) {
		kill_block_super(sb);
		return;
1421
	}
1422 1423 1424 1425 1426 1427

	gfs2_meta_syncfs(sdp);
	dput(sdp->sd_root_dir);
	dput(sdp->sd_master_dir);
	sdp->sd_root_dir = NULL;
	sdp->sd_master_dir = NULL;
1428
	shrink_dcache_sb(sb);
S
Steven Whitehouse 已提交
1429
	kill_block_super(sb);
1430 1431
	gfs2_delete_debugfs_file(sdp);
	kfree(sdp);
1432 1433
}

D
David Teigland 已提交
1434 1435 1436 1437
struct file_system_type gfs2_fs_type = {
	.name = "gfs2",
	.fs_flags = FS_REQUIRES_DEV,
	.get_sb = gfs2_get_sb,
1438 1439 1440 1441 1442 1443 1444
	.kill_sb = gfs2_kill_sb,
	.owner = THIS_MODULE,
};

struct file_system_type gfs2meta_fs_type = {
	.name = "gfs2meta",
	.fs_flags = FS_REQUIRES_DEV,
1445
	.get_sb = gfs2_get_sb_meta,
D
David Teigland 已提交
1446 1447 1448
	.owner = THIS_MODULE,
};