the_nilfs.c 19.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27
/*
 * the_nilfs.c - the_nilfs shared structure.
 *
 * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
 *
 * 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 will 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 to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 *
 * Written by Ryusuke Konishi <ryusuke@osrg.net>
 *
 */

#include <linux/buffer_head.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
28
#include <linux/crc32.h>
29 30 31 32 33 34 35 36
#include "nilfs.h"
#include "segment.h"
#include "alloc.h"
#include "cpfile.h"
#include "sufile.h"
#include "dat.h"
#include "segbuf.h"

37 38 39 40

static LIST_HEAD(nilfs_objects);
static DEFINE_SPINLOCK(nilfs_lock);

41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60
void nilfs_set_last_segment(struct the_nilfs *nilfs,
			    sector_t start_blocknr, u64 seq, __u64 cno)
{
	spin_lock(&nilfs->ns_last_segment_lock);
	nilfs->ns_last_pseg = start_blocknr;
	nilfs->ns_last_seq = seq;
	nilfs->ns_last_cno = cno;
	spin_unlock(&nilfs->ns_last_segment_lock);
}

/**
 * alloc_nilfs - allocate the_nilfs structure
 * @bdev: block device to which the_nilfs is related
 *
 * alloc_nilfs() allocates memory for the_nilfs and
 * initializes its reference count and locks.
 *
 * Return Value: On success, pointer to the_nilfs is returned.
 * On error, NULL is returned.
 */
61
static struct the_nilfs *alloc_nilfs(struct block_device *bdev)
62 63 64 65 66 67 68 69 70 71 72
{
	struct the_nilfs *nilfs;

	nilfs = kzalloc(sizeof(*nilfs), GFP_KERNEL);
	if (!nilfs)
		return NULL;

	nilfs->ns_bdev = bdev;
	atomic_set(&nilfs->ns_count, 1);
	atomic_set(&nilfs->ns_ndirtyblks, 0);
	init_rwsem(&nilfs->ns_sem);
73
	init_rwsem(&nilfs->ns_super_sem);
74
	mutex_init(&nilfs->ns_mount_mutex);
75
	init_rwsem(&nilfs->ns_writer_sem);
76
	INIT_LIST_HEAD(&nilfs->ns_list);
77 78 79 80 81 82 83 84
	INIT_LIST_HEAD(&nilfs->ns_supers);
	spin_lock_init(&nilfs->ns_last_segment_lock);
	nilfs->ns_gc_inodes_h = NULL;
	init_rwsem(&nilfs->ns_segctor_sem);

	return nilfs;
}

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
/**
 * find_or_create_nilfs - find or create nilfs object
 * @bdev: block device to which the_nilfs is related
 *
 * find_nilfs() looks up an existent nilfs object created on the
 * device and gets the reference count of the object.  If no nilfs object
 * is found on the device, a new nilfs object is allocated.
 *
 * Return Value: On success, pointer to the nilfs object is returned.
 * On error, NULL is returned.
 */
struct the_nilfs *find_or_create_nilfs(struct block_device *bdev)
{
	struct the_nilfs *nilfs, *new = NULL;

 retry:
	spin_lock(&nilfs_lock);
	list_for_each_entry(nilfs, &nilfs_objects, ns_list) {
		if (nilfs->ns_bdev == bdev) {
			get_nilfs(nilfs);
			spin_unlock(&nilfs_lock);
			if (new)
				put_nilfs(new);
			return nilfs; /* existing object */
		}
	}
	if (new) {
		list_add_tail(&new->ns_list, &nilfs_objects);
		spin_unlock(&nilfs_lock);
		return new; /* new object */
	}
	spin_unlock(&nilfs_lock);

	new = alloc_nilfs(bdev);
	if (new)
		goto retry;
	return NULL; /* insufficient memory */
}

124 125 126 127 128 129 130 131 132
/**
 * put_nilfs - release a reference to the_nilfs
 * @nilfs: the_nilfs structure to be released
 *
 * put_nilfs() decrements a reference counter of the_nilfs.
 * If the reference count reaches zero, the_nilfs is freed.
 */
void put_nilfs(struct the_nilfs *nilfs)
{
133 134 135
	spin_lock(&nilfs_lock);
	if (!atomic_dec_and_test(&nilfs->ns_count)) {
		spin_unlock(&nilfs_lock);
136
		return;
137 138 139 140
	}
	list_del_init(&nilfs->ns_list);
	spin_unlock(&nilfs_lock);

141
	/*
142
	 * Increment of ns_count never occurs below because the caller
143 144 145
	 * of get_nilfs() holds at least one reference to the_nilfs.
	 * Thus its exclusion control is not required here.
	 */
146

147 148 149 150 151 152 153 154 155
	might_sleep();
	if (nilfs_loaded(nilfs)) {
		nilfs_mdt_destroy(nilfs->ns_sufile);
		nilfs_mdt_destroy(nilfs->ns_cpfile);
		nilfs_mdt_destroy(nilfs->ns_dat);
		nilfs_mdt_destroy(nilfs->ns_gc_dat);
	}
	if (nilfs_init(nilfs)) {
		nilfs_destroy_gccache(nilfs);
156 157
		brelse(nilfs->ns_sbh[0]);
		brelse(nilfs->ns_sbh[1]);
158 159 160 161 162 163 164 165 166
	}
	kfree(nilfs);
}

static int nilfs_load_super_root(struct the_nilfs *nilfs,
				 struct nilfs_sb_info *sbi, sector_t sr_block)
{
	struct buffer_head *bh_sr;
	struct nilfs_super_root *raw_sr;
167
	struct nilfs_super_block **sbp = nilfs->ns_sbp;
168 169 170 171 172 173 174 175 176
	unsigned dat_entry_size, segment_usage_size, checkpoint_size;
	unsigned inode_size;
	int err;

	err = nilfs_read_super_root_block(sbi->s_super, sr_block, &bh_sr, 1);
	if (unlikely(err))
		return err;

	down_read(&nilfs->ns_sem);
177 178 179
	dat_entry_size = le16_to_cpu(sbp[0]->s_dat_entry_size);
	checkpoint_size = le16_to_cpu(sbp[0]->s_checkpoint_size);
	segment_usage_size = le16_to_cpu(sbp[0]->s_segment_usage_size);
180 181 182 183 184
	up_read(&nilfs->ns_sem);

	inode_size = nilfs->ns_inode_size;

	err = -ENOMEM;
185
	nilfs->ns_dat = nilfs_dat_new(nilfs, dat_entry_size);
186 187 188
	if (unlikely(!nilfs->ns_dat))
		goto failed;

189
	nilfs->ns_gc_dat = nilfs_dat_new(nilfs, dat_entry_size);
190 191 192
	if (unlikely(!nilfs->ns_gc_dat))
		goto failed_dat;

193
	nilfs->ns_cpfile = nilfs_cpfile_new(nilfs, checkpoint_size);
194 195 196
	if (unlikely(!nilfs->ns_cpfile))
		goto failed_gc_dat;

197
	nilfs->ns_sufile = nilfs_sufile_new(nilfs, segment_usage_size);
198 199 200 201 202
	if (unlikely(!nilfs->ns_sufile))
		goto failed_cpfile;

	nilfs_mdt_set_shadow(nilfs->ns_dat, nilfs->ns_gc_dat);

203 204
	err = nilfs_dat_read(nilfs->ns_dat, (void *)bh_sr->b_data +
			     NILFS_SR_DAT_OFFSET(inode_size));
205 206 207
	if (unlikely(err))
		goto failed_sufile;

208 209
	err = nilfs_cpfile_read(nilfs->ns_cpfile, (void *)bh_sr->b_data +
				NILFS_SR_CPFILE_OFFSET(inode_size));
210 211 212
	if (unlikely(err))
		goto failed_sufile;

213 214
	err = nilfs_sufile_read(nilfs->ns_sufile, (void *)bh_sr->b_data +
				NILFS_SR_SUFILE_OFFSET(inode_size));
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
	if (unlikely(err))
		goto failed_sufile;

	raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
	nilfs->ns_nongc_ctime = le64_to_cpu(raw_sr->sr_nongc_ctime);

 failed:
	brelse(bh_sr);
	return err;

 failed_sufile:
	nilfs_mdt_destroy(nilfs->ns_sufile);

 failed_cpfile:
	nilfs_mdt_destroy(nilfs->ns_cpfile);

 failed_gc_dat:
	nilfs_mdt_destroy(nilfs->ns_gc_dat);

 failed_dat:
	nilfs_mdt_destroy(nilfs->ns_dat);
	goto failed;
}

static void nilfs_init_recovery_info(struct nilfs_recovery_info *ri)
{
	memset(ri, 0, sizeof(*ri));
	INIT_LIST_HEAD(&ri->ri_used_segments);
}

static void nilfs_clear_recovery_info(struct nilfs_recovery_info *ri)
{
	nilfs_dispose_segment_list(&ri->ri_used_segments);
}

/**
 * load_nilfs - load and recover the nilfs
 * @nilfs: the_nilfs structure to be released
 * @sbi: nilfs_sb_info used to recover past segment
 *
 * load_nilfs() searches and load the latest super root,
 * attaches the last segment, and does recovery if needed.
 * The caller must call this exclusively for simultaneous mounts.
 */
int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
{
	struct nilfs_recovery_info ri;
	unsigned int s_flags = sbi->s_super->s_flags;
	int really_read_only = bdev_read_only(nilfs->ns_bdev);
	unsigned valid_fs;
	int err = 0;

	nilfs_init_recovery_info(&ri);

	down_write(&nilfs->ns_sem);
	valid_fs = (nilfs->ns_mount_state & NILFS_VALID_FS);
	up_write(&nilfs->ns_sem);

	if (!valid_fs && (s_flags & MS_RDONLY)) {
		printk(KERN_INFO "NILFS: INFO: recovery "
		       "required for readonly filesystem.\n");
		if (really_read_only) {
			printk(KERN_ERR "NILFS: write access "
			       "unavailable, cannot proceed.\n");
			err = -EROFS;
			goto failed;
		}
		printk(KERN_INFO "NILFS: write access will "
		       "be enabled during recovery.\n");
		sbi->s_super->s_flags &= ~MS_RDONLY;
	}

	err = nilfs_search_super_root(nilfs, sbi, &ri);
	if (unlikely(err)) {
		printk(KERN_ERR "NILFS: error searching super root.\n");
		goto failed;
	}

	err = nilfs_load_super_root(nilfs, sbi, ri.ri_super_root);
	if (unlikely(err)) {
		printk(KERN_ERR "NILFS: error loading super root.\n");
		goto failed;
	}

	if (!valid_fs) {
		err = nilfs_recover_logical_segments(nilfs, sbi, &ri);
		if (unlikely(err)) {
			nilfs_mdt_destroy(nilfs->ns_cpfile);
			nilfs_mdt_destroy(nilfs->ns_sufile);
			nilfs_mdt_destroy(nilfs->ns_dat);
			goto failed;
		}
307 308
		if (ri.ri_need_recovery == NILFS_RECOVERY_SR_UPDATED)
			sbi->s_super->s_dirt = 1;
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
	}

	set_nilfs_loaded(nilfs);

 failed:
	nilfs_clear_recovery_info(&ri);
	sbi->s_super->s_flags = s_flags;
	return err;
}

static unsigned long long nilfs_max_size(unsigned int blkbits)
{
	unsigned int max_bits;
	unsigned long long res = MAX_LFS_FILESIZE; /* page cache limit */

	max_bits = blkbits + NILFS_BMAP_KEY_BIT; /* bmap size limit */
	if (max_bits < 64)
		res = min_t(unsigned long long, res, (1ULL << max_bits) - 1);
	return res;
}

330 331
static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
				   struct nilfs_super_block *sbp)
332 333 334 335 336 337 338 339 340 341
{
	if (le32_to_cpu(sbp->s_rev_level) != NILFS_CURRENT_REV) {
		printk(KERN_ERR "NILFS: revision mismatch "
		       "(superblock rev.=%d.%d, current rev.=%d.%d). "
		       "Please check the version of mkfs.nilfs.\n",
		       le32_to_cpu(sbp->s_rev_level),
		       le16_to_cpu(sbp->s_minor_rev_level),
		       NILFS_CURRENT_REV, NILFS_MINOR_REV);
		return -EINVAL;
	}
342 343 344 345
	nilfs->ns_sbsize = le16_to_cpu(sbp->s_bytes);
	if (nilfs->ns_sbsize > BLOCK_SIZE)
		return -EINVAL;

346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366
	nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
	nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);

	nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
	if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) {
		printk(KERN_ERR "NILFS: too short segment. \n");
		return -EINVAL;
	}

	nilfs->ns_first_data_block = le64_to_cpu(sbp->s_first_data_block);
	nilfs->ns_nsegments = le64_to_cpu(sbp->s_nsegments);
	nilfs->ns_r_segments_percentage =
		le32_to_cpu(sbp->s_r_segments_percentage);
	nilfs->ns_nrsvsegs =
		max_t(unsigned long, NILFS_MIN_NRSVSEGS,
		      DIV_ROUND_UP(nilfs->ns_nsegments *
				   nilfs->ns_r_segments_percentage, 100));
	nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed);
	return 0;
}

367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482
static int nilfs_valid_sb(struct nilfs_super_block *sbp)
{
	static unsigned char sum[4];
	const int sumoff = offsetof(struct nilfs_super_block, s_sum);
	size_t bytes;
	u32 crc;

	if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC)
		return 0;
	bytes = le16_to_cpu(sbp->s_bytes);
	if (bytes > BLOCK_SIZE)
		return 0;
	crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp,
		       sumoff);
	crc = crc32_le(crc, sum, 4);
	crc = crc32_le(crc, (unsigned char *)sbp + sumoff + 4,
		       bytes - sumoff - 4);
	return crc == le32_to_cpu(sbp->s_sum);
}

static int nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset)
{
	return offset < ((le64_to_cpu(sbp->s_nsegments) *
			  le32_to_cpu(sbp->s_blocks_per_segment)) <<
			 (le32_to_cpu(sbp->s_log_block_size) + 10));
}

static void nilfs_release_super_block(struct the_nilfs *nilfs)
{
	int i;

	for (i = 0; i < 2; i++) {
		if (nilfs->ns_sbp[i]) {
			brelse(nilfs->ns_sbh[i]);
			nilfs->ns_sbh[i] = NULL;
			nilfs->ns_sbp[i] = NULL;
		}
	}
}

void nilfs_fall_back_super_block(struct the_nilfs *nilfs)
{
	brelse(nilfs->ns_sbh[0]);
	nilfs->ns_sbh[0] = nilfs->ns_sbh[1];
	nilfs->ns_sbp[0] = nilfs->ns_sbp[1];
	nilfs->ns_sbh[1] = NULL;
	nilfs->ns_sbp[1] = NULL;
}

void nilfs_swap_super_block(struct the_nilfs *nilfs)
{
	struct buffer_head *tsbh = nilfs->ns_sbh[0];
	struct nilfs_super_block *tsbp = nilfs->ns_sbp[0];

	nilfs->ns_sbh[0] = nilfs->ns_sbh[1];
	nilfs->ns_sbp[0] = nilfs->ns_sbp[1];
	nilfs->ns_sbh[1] = tsbh;
	nilfs->ns_sbp[1] = tsbp;
}

static int nilfs_load_super_block(struct the_nilfs *nilfs,
				  struct super_block *sb, int blocksize,
				  struct nilfs_super_block **sbpp)
{
	struct nilfs_super_block **sbp = nilfs->ns_sbp;
	struct buffer_head **sbh = nilfs->ns_sbh;
	u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size);
	int valid[2], swp = 0;

	sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize,
					&sbh[0]);
	sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]);

	if (!sbp[0]) {
		if (!sbp[1]) {
			printk(KERN_ERR "NILFS: unable to read superblock\n");
			return -EIO;
		}
		printk(KERN_WARNING
		       "NILFS warning: unable to read primary superblock\n");
	} else if (!sbp[1])
		printk(KERN_WARNING
		       "NILFS warning: unable to read secondary superblock\n");

	valid[0] = nilfs_valid_sb(sbp[0]);
	valid[1] = nilfs_valid_sb(sbp[1]);
	swp = valid[1] &&
		(!valid[0] ||
		 le64_to_cpu(sbp[1]->s_wtime) > le64_to_cpu(sbp[0]->s_wtime));

	if (valid[swp] && nilfs_sb2_bad_offset(sbp[swp], sb2off)) {
		brelse(sbh[1]);
		sbh[1] = NULL;
		sbp[1] = NULL;
		swp = 0;
	}
	if (!valid[swp]) {
		nilfs_release_super_block(nilfs);
		printk(KERN_ERR "NILFS: Can't find nilfs on dev %s.\n",
		       sb->s_id);
		return -EINVAL;
	}

	if (swp) {
		printk(KERN_WARNING "NILFS warning: broken superblock. "
		       "using spare superblock.\n");
		nilfs_swap_super_block(nilfs);
	}

	nilfs->ns_sbwtime[0] = le64_to_cpu(sbp[0]->s_wtime);
	nilfs->ns_sbwtime[1] = valid[!swp] ? le64_to_cpu(sbp[1]->s_wtime) : 0;
	nilfs->ns_prot_seq = le64_to_cpu(sbp[valid[1] & !swp]->s_last_seq);
	*sbpp = sbp[0];
	return 0;
}

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
/**
 * init_nilfs - initialize a NILFS instance.
 * @nilfs: the_nilfs structure
 * @sbi: nilfs_sb_info
 * @sb: super block
 * @data: mount options
 *
 * init_nilfs() performs common initialization per block device (e.g.
 * reading the super block, getting disk layout information, initializing
 * shared fields in the_nilfs). It takes on some portion of the jobs
 * typically done by a fill_super() routine. This division arises from
 * the nature that multiple NILFS instances may be simultaneously
 * mounted on a device.
 * For multiple mounts on the same device, only the first mount
 * invokes these tasks.
 *
 * Return Value: On success, 0 is returned. On error, a negative error
 * code is returned.
 */
int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data)
{
	struct super_block *sb = sbi->s_super;
	struct nilfs_super_block *sbp;
	struct backing_dev_info *bdi;
	int blocksize;
508
	int err;
509 510 511 512

	down_write(&nilfs->ns_sem);
	if (nilfs_init(nilfs)) {
		/* Load values from existing the_nilfs */
513
		sbp = nilfs->ns_sbp[0];
514 515 516 517 518 519 520 521 522 523 524 525 526 527 528
		err = nilfs_store_magic_and_option(sb, sbp, data);
		if (err)
			goto out;

		blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size);
		if (sb->s_blocksize != blocksize &&
		    !sb_set_blocksize(sb, blocksize)) {
			printk(KERN_ERR "NILFS: blocksize %d unfit to device\n",
			       blocksize);
			err = -EINVAL;
		}
		sb->s_maxbytes = nilfs_max_size(sb->s_blocksize_bits);
		goto out;
	}

529 530 531
	blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
	if (!blocksize) {
		printk(KERN_ERR "NILFS: unable to set blocksize\n");
532 533 534
		err = -EINVAL;
		goto out;
	}
535 536 537 538
	err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp);
	if (err)
		goto out;

539 540 541 542 543 544
	err = nilfs_store_magic_and_option(sb, sbp, data);
	if (err)
		goto failed_sbh;

	blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size);
	if (sb->s_blocksize != blocksize) {
545
		int hw_blocksize = bdev_logical_block_size(sb->s_bdev);
546 547 548 549 550 551

		if (blocksize < hw_blocksize) {
			printk(KERN_ERR
			       "NILFS: blocksize %d too small for device "
			       "(sector-size = %d).\n",
			       blocksize, hw_blocksize);
552
			err = -EINVAL;
553 554 555 556 557 558 559
			goto failed_sbh;
		}
		nilfs_release_super_block(nilfs);
		sb_set_blocksize(sb, blocksize);

		err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp);
		if (err)
560 561 562 563 564 565
			goto out;
			/* not failed_sbh; sbh is released automatically
			   when reloading fails. */
	}
	nilfs->ns_blocksize_bits = sb->s_blocksize_bits;

566
	err = nilfs_store_disk_layout(nilfs, sbp);
567 568 569 570 571 572 573
	if (err)
		goto failed_sbh;

	sb->s_maxbytes = nilfs_max_size(sb->s_blocksize_bits);

	nilfs->ns_mount_state = le16_to_cpu(sbp->s_state);

574
	bdi = nilfs->ns_bdev->bd_inode->i_mapping->backing_dev_info;
575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606
	nilfs->ns_bdi = bdi ? : &default_backing_dev_info;

	/* Finding last segment */
	nilfs->ns_last_pseg = le64_to_cpu(sbp->s_last_pseg);
	nilfs->ns_last_cno = le64_to_cpu(sbp->s_last_cno);
	nilfs->ns_last_seq = le64_to_cpu(sbp->s_last_seq);

	nilfs->ns_seg_seq = nilfs->ns_last_seq;
	nilfs->ns_segnum =
		nilfs_get_segnum_of_block(nilfs, nilfs->ns_last_pseg);
	nilfs->ns_cno = nilfs->ns_last_cno + 1;
	if (nilfs->ns_segnum >= nilfs->ns_nsegments) {
		printk(KERN_ERR "NILFS invalid last segment number.\n");
		err = -EINVAL;
		goto failed_sbh;
	}
	/* Dummy values  */
	nilfs->ns_free_segments_count =
		nilfs->ns_nsegments - (nilfs->ns_segnum + 1);

	/* Initialize gcinode cache */
	err = nilfs_init_gccache(nilfs);
	if (err)
		goto failed_sbh;

	set_nilfs_init(nilfs);
	err = 0;
 out:
	up_write(&nilfs->ns_sem);
	return err;

 failed_sbh:
607
	nilfs_release_super_block(nilfs);
608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640
	goto out;
}

int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks)
{
	struct inode *dat = nilfs_dat_inode(nilfs);
	unsigned long ncleansegs;
	int err;

	down_read(&NILFS_MDT(dat)->mi_sem);	/* XXX */
	err = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile, &ncleansegs);
	up_read(&NILFS_MDT(dat)->mi_sem);	/* XXX */
	if (likely(!err))
		*nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment;
	return err;
}

int nilfs_near_disk_full(struct the_nilfs *nilfs)
{
	struct inode *sufile = nilfs->ns_sufile;
	unsigned long ncleansegs, nincsegs;
	int ret;

	ret = nilfs_sufile_get_ncleansegs(sufile, &ncleansegs);
	if (likely(!ret)) {
		nincsegs = atomic_read(&nilfs->ns_ndirtyblks) /
			nilfs->ns_blocks_per_segment + 1;
		if (ncleansegs <= nilfs->ns_nrsvsegs + nincsegs)
			ret++;
	}
	return ret;
}

641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
/**
 * nilfs_find_sbinfo - find existing nilfs_sb_info structure
 * @nilfs: nilfs object
 * @rw_mount: mount type (non-zero value for read/write mount)
 * @cno: checkpoint number (zero for read-only mount)
 *
 * nilfs_find_sbinfo() returns the nilfs_sb_info structure which
 * @rw_mount and @cno (in case of snapshots) matched.  If no instance
 * was found, NULL is returned.  Although the super block instance can
 * be unmounted after this function returns, the nilfs_sb_info struct
 * is kept on memory until nilfs_put_sbinfo() is called.
 */
struct nilfs_sb_info *nilfs_find_sbinfo(struct the_nilfs *nilfs,
					int rw_mount, __u64 cno)
{
	struct nilfs_sb_info *sbi;

658
	down_read(&nilfs->ns_super_sem);
659 660
	/*
	 * The SNAPSHOT flag and sb->s_flags are supposed to be
661
	 * protected with nilfs->ns_super_sem.
662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681
	 */
	sbi = nilfs->ns_current;
	if (rw_mount) {
		if (sbi && !(sbi->s_super->s_flags & MS_RDONLY))
			goto found; /* read/write mount */
		else
			goto out;
	} else if (cno == 0) {
		if (sbi && (sbi->s_super->s_flags & MS_RDONLY))
			goto found; /* read-only mount */
		else
			goto out;
	}

	list_for_each_entry(sbi, &nilfs->ns_supers, s_list) {
		if (nilfs_test_opt(sbi, SNAPSHOT) &&
		    sbi->s_snapshot_cno == cno)
			goto found; /* snapshot mount */
	}
 out:
682
	up_read(&nilfs->ns_super_sem);
683 684 685 686
	return NULL;

 found:
	atomic_inc(&sbi->s_count);
687
	up_read(&nilfs->ns_super_sem);
688 689 690
	return sbi;
}

691 692 693 694 695 696
int nilfs_checkpoint_is_mounted(struct the_nilfs *nilfs, __u64 cno,
				int snapshot_mount)
{
	struct nilfs_sb_info *sbi;
	int ret = 0;

697
	down_read(&nilfs->ns_super_sem);
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
	if (cno == 0 || cno > nilfs->ns_cno)
		goto out_unlock;

	list_for_each_entry(sbi, &nilfs->ns_supers, s_list) {
		if (sbi->s_snapshot_cno == cno &&
		    (!snapshot_mount || nilfs_test_opt(sbi, SNAPSHOT))) {
					/* exclude read-only mounts */
			ret++;
			break;
		}
	}
	/* for protecting recent checkpoints */
	if (cno >= nilfs_last_cno(nilfs))
		ret++;

 out_unlock:
714
	up_read(&nilfs->ns_super_sem);
715 716
	return ret;
}