super.c 26.4 KB
Newer Older
J
Jaegeuk Kim 已提交
1
/*
J
Jaegeuk Kim 已提交
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
 * fs/f2fs/super.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/statfs.h>
#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
21
#include <linux/proc_fs.h>
J
Jaegeuk Kim 已提交
22 23
#include <linux/random.h>
#include <linux/exportfs.h>
24
#include <linux/blkdev.h>
J
Jaegeuk Kim 已提交
25
#include <linux/f2fs_fs.h>
26
#include <linux/sysfs.h>
J
Jaegeuk Kim 已提交
27 28 29

#include "f2fs.h"
#include "node.h"
30
#include "segment.h"
J
Jaegeuk Kim 已提交
31
#include "xattr.h"
32
#include "gc.h"
J
Jaegeuk Kim 已提交
33

34 35 36
#define CREATE_TRACE_POINTS
#include <trace/events/f2fs.h>

37
static struct proc_dir_entry *f2fs_proc_root;
J
Jaegeuk Kim 已提交
38
static struct kmem_cache *f2fs_inode_cachep;
39
static struct kset *f2fs_kset;
J
Jaegeuk Kim 已提交
40 41

enum {
42
	Opt_gc_background,
J
Jaegeuk Kim 已提交
43 44 45
	Opt_disable_roll_forward,
	Opt_discard,
	Opt_noheap,
46
	Opt_user_xattr,
J
Jaegeuk Kim 已提交
47
	Opt_nouser_xattr,
48
	Opt_acl,
J
Jaegeuk Kim 已提交
49 50 51
	Opt_noacl,
	Opt_active_logs,
	Opt_disable_ext_identify,
J
Jaegeuk Kim 已提交
52
	Opt_inline_xattr,
J
Jaegeuk Kim 已提交
53 54 55 56
	Opt_err,
};

static match_table_t f2fs_tokens = {
57
	{Opt_gc_background, "background_gc=%s"},
J
Jaegeuk Kim 已提交
58 59 60
	{Opt_disable_roll_forward, "disable_roll_forward"},
	{Opt_discard, "discard"},
	{Opt_noheap, "no_heap"},
61
	{Opt_user_xattr, "user_xattr"},
J
Jaegeuk Kim 已提交
62
	{Opt_nouser_xattr, "nouser_xattr"},
63
	{Opt_acl, "acl"},
J
Jaegeuk Kim 已提交
64 65 66
	{Opt_noacl, "noacl"},
	{Opt_active_logs, "active_logs=%u"},
	{Opt_disable_ext_identify, "disable_ext_identify"},
J
Jaegeuk Kim 已提交
67
	{Opt_inline_xattr, "inline_xattr"},
J
Jaegeuk Kim 已提交
68 69 70
	{Opt_err, NULL},
};

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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
/* Sysfs support for f2fs */
struct f2fs_attr {
	struct attribute attr;
	ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
	ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
			 const char *, size_t);
	int offset;
};

static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
			struct f2fs_sb_info *sbi, char *buf)
{
	struct f2fs_gc_kthread *gc_kth = sbi->gc_thread;
	unsigned int *ui;

	if (!gc_kth)
		return -EINVAL;

	ui = (unsigned int *)(((char *)gc_kth) + a->offset);

	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
}

static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
			struct f2fs_sb_info *sbi,
			const char *buf, size_t count)
{
	struct f2fs_gc_kthread *gc_kth = sbi->gc_thread;
	unsigned long t;
	unsigned int *ui;
	ssize_t ret;

	if (!gc_kth)
		return -EINVAL;

	ui = (unsigned int *)(((char *)gc_kth) + a->offset);

	ret = kstrtoul(skip_spaces(buf), 0, &t);
	if (ret < 0)
		return ret;
	*ui = t;
	return count;
}

static ssize_t f2fs_attr_show(struct kobject *kobj,
				struct attribute *attr, char *buf)
{
	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
								s_kobj);
	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);

	return a->show ? a->show(a, sbi, buf) : 0;
}

static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
						const char *buf, size_t len)
{
	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
									s_kobj);
	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);

	return a->store ? a->store(a, sbi, buf, len) : 0;
}

static void f2fs_sb_release(struct kobject *kobj)
{
	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
								s_kobj);
	complete(&sbi->s_kobj_unregister);
}

#define F2FS_ATTR_OFFSET(_name, _mode, _show, _store, _elname) \
static struct f2fs_attr f2fs_attr_##_name = {			\
	.attr = {.name = __stringify(_name), .mode = _mode },	\
	.show	= _show,					\
	.store	= _store,					\
	.offset = offsetof(struct f2fs_gc_kthread, _elname),	\
}

#define F2FS_RW_ATTR(name, elname)	\
	F2FS_ATTR_OFFSET(name, 0644, f2fs_sbi_show, f2fs_sbi_store, elname)

F2FS_RW_ATTR(gc_min_sleep_time, min_sleep_time);
F2FS_RW_ATTR(gc_max_sleep_time, max_sleep_time);
F2FS_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time);
156
F2FS_RW_ATTR(gc_idle, gc_idle);
157 158 159 160 161 162

#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
	ATTR_LIST(gc_min_sleep_time),
	ATTR_LIST(gc_max_sleep_time),
	ATTR_LIST(gc_no_gc_sleep_time),
163
	ATTR_LIST(gc_idle),
164 165 166 167 168 169 170 171 172 173 174 175 176 177
	NULL,
};

static const struct sysfs_ops f2fs_attr_ops = {
	.show	= f2fs_attr_show,
	.store	= f2fs_attr_store,
};

static struct kobj_type f2fs_ktype = {
	.default_attrs	= f2fs_attrs,
	.sysfs_ops	= &f2fs_attr_ops,
	.release	= f2fs_sb_release,
};

178 179 180 181 182 183 184 185 186 187 188 189
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
	va_end(args);
}

J
Jaegeuk Kim 已提交
190 191 192 193 194 195 196
static void init_once(void *foo)
{
	struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;

	inode_init_once(&fi->vfs_inode);
}

197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
static int parse_options(struct super_block *sb, char *options)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	substring_t args[MAX_OPT_ARGS];
	char *p, *name;
	int arg = 0;

	if (!options)
		return 0;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;
		/*
		 * Initialize args struct so we know whether arg was
		 * found; some options take optional arguments.
		 */
		args[0].to = args[0].from = NULL;
		token = match_token(p, f2fs_tokens, args);

		switch (token) {
		case Opt_gc_background:
			name = match_strdup(&args[0]);

			if (!name)
				return -ENOMEM;
			if (!strncmp(name, "on", 2))
				set_opt(sbi, BG_GC);
			else if (!strncmp(name, "off", 3))
				clear_opt(sbi, BG_GC);
			else {
				kfree(name);
				return -EINVAL;
			}
			kfree(name);
			break;
		case Opt_disable_roll_forward:
			set_opt(sbi, DISABLE_ROLL_FORWARD);
			break;
		case Opt_discard:
			set_opt(sbi, DISCARD);
			break;
		case Opt_noheap:
			set_opt(sbi, NOHEAP);
			break;
#ifdef CONFIG_F2FS_FS_XATTR
244 245 246
		case Opt_user_xattr:
			set_opt(sbi, XATTR_USER);
			break;
247 248 249
		case Opt_nouser_xattr:
			clear_opt(sbi, XATTR_USER);
			break;
J
Jaegeuk Kim 已提交
250 251 252
		case Opt_inline_xattr:
			set_opt(sbi, INLINE_XATTR);
			break;
253
#else
254 255 256 257
		case Opt_user_xattr:
			f2fs_msg(sb, KERN_INFO,
				"user_xattr options not supported");
			break;
258 259 260 261
		case Opt_nouser_xattr:
			f2fs_msg(sb, KERN_INFO,
				"nouser_xattr options not supported");
			break;
J
Jaegeuk Kim 已提交
262 263 264 265
		case Opt_inline_xattr:
			f2fs_msg(sb, KERN_INFO,
				"inline_xattr options not supported");
			break;
266 267
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
268 269 270
		case Opt_acl:
			set_opt(sbi, POSIX_ACL);
			break;
271 272 273 274
		case Opt_noacl:
			clear_opt(sbi, POSIX_ACL);
			break;
#else
275 276 277
		case Opt_acl:
			f2fs_msg(sb, KERN_INFO, "acl options not supported");
			break;
278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
		case Opt_noacl:
			f2fs_msg(sb, KERN_INFO, "noacl options not supported");
			break;
#endif
		case Opt_active_logs:
			if (args->from && match_int(args, &arg))
				return -EINVAL;
			if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
				return -EINVAL;
			sbi->active_logs = arg;
			break;
		case Opt_disable_ext_identify:
			set_opt(sbi, DISABLE_EXT_IDENTIFY);
			break;
		default:
			f2fs_msg(sb, KERN_ERR,
				"Unrecognized mount option \"%s\" or missing value",
				p);
			return -EINVAL;
		}
	}
	return 0;
}

J
Jaegeuk Kim 已提交
302 303 304 305 306 307 308 309 310 311
static struct inode *f2fs_alloc_inode(struct super_block *sb)
{
	struct f2fs_inode_info *fi;

	fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_NOFS | __GFP_ZERO);
	if (!fi)
		return NULL;

	init_once((void *) fi);

M
Masanari Iida 已提交
312
	/* Initialize f2fs-specific inode info */
J
Jaegeuk Kim 已提交
313 314 315 316 317 318 319 320
	fi->vfs_inode.i_version = 1;
	atomic_set(&fi->dirty_dents, 0);
	fi->i_current_depth = 1;
	fi->i_advise = 0;
	rwlock_init(&fi->ext.ext_lock);

	set_inode_flag(fi, FI_NEW_INODE);

J
Jaegeuk Kim 已提交
321 322 323
	if (test_opt(F2FS_SB(sb), INLINE_XATTR))
		set_inode_flag(fi, FI_INLINE_XATTR);

J
Jaegeuk Kim 已提交
324 325 326
	return &fi->vfs_inode;
}

327 328 329 330 331 332 333 334 335 336 337 338 339 340
static int f2fs_drop_inode(struct inode *inode)
{
	/*
	 * This is to avoid a deadlock condition like below.
	 * writeback_single_inode(inode)
	 *  - f2fs_write_data_page
	 *    - f2fs_gc -> iput -> evict
	 *       - inode_wait_for_writeback(inode)
	 */
	if (!inode_unhashed(inode) && inode->i_state & I_SYNC)
		return 0;
	return generic_drop_inode(inode);
}

341 342 343 344 345 346 347 348 349 350
/*
 * f2fs_dirty_inode() is called from __mark_inode_dirty()
 *
 * We should call set_dirty_inode to write the dirty inode through write_inode.
 */
static void f2fs_dirty_inode(struct inode *inode, int flags)
{
	set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
}

J
Jaegeuk Kim 已提交
351 352 353 354 355 356
static void f2fs_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode));
}

357
static void f2fs_destroy_inode(struct inode *inode)
J
Jaegeuk Kim 已提交
358 359 360 361 362 363 364 365
{
	call_rcu(&inode->i_rcu, f2fs_i_callback);
}

static void f2fs_put_super(struct super_block *sb)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);

366 367 368 369
	if (sbi->s_proc) {
		remove_proc_entry("segment_info", sbi->s_proc);
		remove_proc_entry(sb->s_id, f2fs_proc_root);
	}
370
	kobject_del(&sbi->s_kobj);
371

J
Jaegeuk Kim 已提交
372 373 374
	f2fs_destroy_stats(sbi);
	stop_gc_thread(sbi);

J
Jaegeuk Kim 已提交
375 376 377
	/* We don't need to do checkpoint when it's clean */
	if (sbi->s_dirty && get_pages(sbi, F2FS_DIRTY_NODES))
		write_checkpoint(sbi, true);
J
Jaegeuk Kim 已提交
378 379 380 381 382 383 384 385 386

	iput(sbi->node_inode);
	iput(sbi->meta_inode);

	/* destroy f2fs internal modules */
	destroy_node_manager(sbi);
	destroy_segment_manager(sbi);

	kfree(sbi->ckpt);
387 388
	kobject_put(&sbi->s_kobj);
	wait_for_completion(&sbi->s_kobj_unregister);
J
Jaegeuk Kim 已提交
389 390 391 392 393 394 395 396 397 398

	sb->s_fs_info = NULL;
	brelse(sbi->raw_super_buf);
	kfree(sbi);
}

int f2fs_sync_fs(struct super_block *sb, int sync)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);

399 400
	trace_f2fs_sync_fs(sb, sync);

J
Jaegeuk Kim 已提交
401 402 403
	if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES))
		return 0;

404 405
	if (sync) {
		mutex_lock(&sbi->gc_mutex);
406
		write_checkpoint(sbi, false);
407 408
		mutex_unlock(&sbi->gc_mutex);
	} else {
409
		f2fs_balance_fs(sbi);
410
	}
J
Jaegeuk Kim 已提交
411

412
	return 0;
J
Jaegeuk Kim 已提交
413 414
}

415 416 417 418
static int f2fs_freeze(struct super_block *sb)
{
	int err;

J
Jaegeuk Kim 已提交
419
	if (f2fs_readonly(sb))
420 421 422 423 424 425 426 427 428 429 430
		return 0;

	err = f2fs_sync_fs(sb, 1);
	return err;
}

static int f2fs_unfreeze(struct super_block *sb)
{
	return 0;
}

J
Jaegeuk Kim 已提交
431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
	block_t total_count, user_block_count, start_count, ovp_count;

	total_count = le64_to_cpu(sbi->raw_super->block_count);
	user_block_count = sbi->user_block_count;
	start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
	buf->f_type = F2FS_SUPER_MAGIC;
	buf->f_bsize = sbi->blocksize;

	buf->f_blocks = total_count - start_count;
	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
	buf->f_bavail = user_block_count - valid_user_blocks(sbi);

449 450
	buf->f_files = sbi->total_node_count;
	buf->f_ffree = sbi->total_node_count - valid_inode_count(sbi);
J
Jaegeuk Kim 已提交
451

452
	buf->f_namelen = F2FS_NAME_LEN;
J
Jaegeuk Kim 已提交
453 454 455 456 457 458 459 460 461 462
	buf->f_fsid.val[0] = (u32)id;
	buf->f_fsid.val[1] = (u32)(id >> 32);

	return 0;
}

static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);

463 464
	if (!(root->d_sb->s_flags & MS_RDONLY) && test_opt(sbi, BG_GC))
		seq_printf(seq, ",background_gc=%s", "on");
J
Jaegeuk Kim 已提交
465
	else
466
		seq_printf(seq, ",background_gc=%s", "off");
J
Jaegeuk Kim 已提交
467 468 469 470 471 472 473 474 475 476 477
	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
		seq_puts(seq, ",disable_roll_forward");
	if (test_opt(sbi, DISCARD))
		seq_puts(seq, ",discard");
	if (test_opt(sbi, NOHEAP))
		seq_puts(seq, ",no_heap_alloc");
#ifdef CONFIG_F2FS_FS_XATTR
	if (test_opt(sbi, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	else
		seq_puts(seq, ",nouser_xattr");
J
Jaegeuk Kim 已提交
478 479
	if (test_opt(sbi, INLINE_XATTR))
		seq_puts(seq, ",inline_xattr");
J
Jaegeuk Kim 已提交
480 481 482 483 484 485 486 487
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
	if (test_opt(sbi, POSIX_ACL))
		seq_puts(seq, ",acl");
	else
		seq_puts(seq, ",noacl");
#endif
	if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
488
		seq_puts(seq, ",disable_ext_identify");
J
Jaegeuk Kim 已提交
489 490 491 492 493 494

	seq_printf(seq, ",active_logs=%u", sbi->active_logs);

	return 0;
}

495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524
static int segment_info_seq_show(struct seq_file *seq, void *offset)
{
	struct super_block *sb = seq->private;
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	unsigned int total_segs = le32_to_cpu(sbi->raw_super->segment_count_main);
	int i;

	for (i = 0; i < total_segs; i++) {
		seq_printf(seq, "%u", get_valid_blocks(sbi, i, 1));
		if (i != 0 && (i % 10) == 0)
			seq_puts(seq, "\n");
		else
			seq_puts(seq, " ");
	}
	return 0;
}

static int segment_info_open_fs(struct inode *inode, struct file *file)
{
	return single_open(file, segment_info_seq_show, PDE_DATA(inode));
}

static const struct file_operations f2fs_seq_segment_info_fops = {
	.owner = THIS_MODULE,
	.open = segment_info_open_fs,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	struct f2fs_mount_info org_mount_opt;
	int err, active_logs;

	/*
	 * Save the old mount options in case we
	 * need to restore them.
	 */
	org_mount_opt = sbi->mount_opt;
	active_logs = sbi->active_logs;

	/* parse mount options */
	err = parse_options(sb, data);
	if (err)
		goto restore_opts;

	/*
	 * Previous and new state of filesystem is RO,
	 * so no point in checking GC conditions.
	 */
	if ((sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY))
		goto skip;

	/*
	 * We stop the GC thread if FS is mounted as RO
	 * or if background_gc = off is passed in mount
	 * option. Also sync the filesystem.
	 */
	if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
		if (sbi->gc_thread) {
			stop_gc_thread(sbi);
			f2fs_sync_fs(sb, 1);
		}
	} else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
		err = start_gc_thread(sbi);
		if (err)
			goto restore_opts;
	}
skip:
	/* Update the POSIXACL Flag */
	 sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
	return 0;

restore_opts:
	sbi->mount_opt = org_mount_opt;
	sbi->active_logs = active_logs;
	return err;
}

J
Jaegeuk Kim 已提交
577 578
static struct super_operations f2fs_sops = {
	.alloc_inode	= f2fs_alloc_inode,
579
	.drop_inode	= f2fs_drop_inode,
J
Jaegeuk Kim 已提交
580 581
	.destroy_inode	= f2fs_destroy_inode,
	.write_inode	= f2fs_write_inode,
582
	.dirty_inode	= f2fs_dirty_inode,
J
Jaegeuk Kim 已提交
583 584 585 586
	.show_options	= f2fs_show_options,
	.evict_inode	= f2fs_evict_inode,
	.put_super	= f2fs_put_super,
	.sync_fs	= f2fs_sync_fs,
587 588
	.freeze_fs	= f2fs_freeze,
	.unfreeze_fs	= f2fs_unfreeze,
J
Jaegeuk Kim 已提交
589
	.statfs		= f2fs_statfs,
590
	.remount_fs	= f2fs_remount,
J
Jaegeuk Kim 已提交
591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639
};

static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
		u64 ino, u32 generation)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	struct inode *inode;

	if (ino < F2FS_ROOT_INO(sbi))
		return ERR_PTR(-ESTALE);

	/*
	 * f2fs_iget isn't quite right if the inode is currently unallocated!
	 * However f2fs_iget currently does appropriate checks to handle stale
	 * inodes so everything is OK.
	 */
	inode = f2fs_iget(sb, ino);
	if (IS_ERR(inode))
		return ERR_CAST(inode);
	if (generation && inode->i_generation != generation) {
		/* we didn't find the right inode.. */
		iput(inode);
		return ERR_PTR(-ESTALE);
	}
	return inode;
}

static struct dentry *f2fs_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
				    f2fs_nfs_get_inode);
}

static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
				    f2fs_nfs_get_inode);
}

static const struct export_operations f2fs_export_ops = {
	.fh_to_dentry = f2fs_fh_to_dentry,
	.fh_to_parent = f2fs_fh_to_parent,
	.get_parent = f2fs_get_parent,
};

static loff_t max_file_size(unsigned bits)
{
640
	loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
J
Jaegeuk Kim 已提交
641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
	loff_t leaf_count = ADDRS_PER_BLOCK;

	/* two direct node blocks */
	result += (leaf_count * 2);

	/* two indirect node blocks */
	leaf_count *= NIDS_PER_BLOCK;
	result += (leaf_count * 2);

	/* one double indirect node block */
	leaf_count *= NIDS_PER_BLOCK;
	result += leaf_count;

	result <<= bits;
	return result;
}

658 659
static int sanity_check_raw_super(struct super_block *sb,
			struct f2fs_super_block *raw_super)
J
Jaegeuk Kim 已提交
660 661 662
{
	unsigned int blocksize;

663 664 665 666
	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
		f2fs_msg(sb, KERN_INFO,
			"Magic Mismatch, valid(0x%x) - read(0x%x)",
			F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
J
Jaegeuk Kim 已提交
667
		return 1;
668
	}
J
Jaegeuk Kim 已提交
669

670 671 672
	/* Currently, support only 4KB page cache size */
	if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
		f2fs_msg(sb, KERN_INFO,
673
			"Invalid page_cache_size (%lu), supports only 4KB\n",
674 675 676 677
			PAGE_CACHE_SIZE);
		return 1;
	}

J
Jaegeuk Kim 已提交
678 679
	/* Currently, support only 4KB block size */
	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
680
	if (blocksize != F2FS_BLKSIZE) {
681 682 683
		f2fs_msg(sb, KERN_INFO,
			"Invalid blocksize (%u), supports only 4KB\n",
			blocksize);
J
Jaegeuk Kim 已提交
684
		return 1;
685
	}
686

J
Jaegeuk Kim 已提交
687
	if (le32_to_cpu(raw_super->log_sectorsize) !=
688 689
					F2FS_LOG_SECTOR_SIZE) {
		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
J
Jaegeuk Kim 已提交
690
		return 1;
691
	}
J
Jaegeuk Kim 已提交
692
	if (le32_to_cpu(raw_super->log_sectors_per_block) !=
693 694
					F2FS_LOG_SECTORS_PER_BLOCK) {
		f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
J
Jaegeuk Kim 已提交
695
		return 1;
696
	}
J
Jaegeuk Kim 已提交
697 698 699
	return 0;
}

700
static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
J
Jaegeuk Kim 已提交
701 702
{
	unsigned int total, fsmeta;
703 704
	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
J
Jaegeuk Kim 已提交
705 706 707 708 709 710 711 712 713 714

	total = le32_to_cpu(raw_super->segment_count);
	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
	fsmeta += le32_to_cpu(raw_super->segment_count_sit);
	fsmeta += le32_to_cpu(raw_super->segment_count_nat);
	fsmeta += le32_to_cpu(ckpt->rsvd_segment_count);
	fsmeta += le32_to_cpu(raw_super->segment_count_ssa);

	if (fsmeta >= total)
		return 1;
715 716 717 718 719

	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
		return 1;
	}
J
Jaegeuk Kim 已提交
720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
	return 0;
}

static void init_sb_info(struct f2fs_sb_info *sbi)
{
	struct f2fs_super_block *raw_super = sbi->raw_super;
	int i;

	sbi->log_sectors_per_block =
		le32_to_cpu(raw_super->log_sectors_per_block);
	sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize);
	sbi->blocksize = 1 << sbi->log_blocksize;
	sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
	sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg;
	sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
	sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
	sbi->total_sections = le32_to_cpu(raw_super->section_count);
	sbi->total_node_count =
		(le32_to_cpu(raw_super->segment_count_nat) / 2)
			* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
	sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
	sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
	sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
743
	sbi->cur_victim_sec = NULL_SECNO;
J
Jaegeuk Kim 已提交
744 745 746 747 748

	for (i = 0; i < NR_COUNT_TYPE; i++)
		atomic_set(&sbi->nr_pages[i], 0);
}

749 750 751 752 753 754 755 756 757 758 759
static int validate_superblock(struct super_block *sb,
		struct f2fs_super_block **raw_super,
		struct buffer_head **raw_super_buf, sector_t block)
{
	const char *super = (block == 0 ? "first" : "second");

	/* read f2fs raw super block */
	*raw_super_buf = sb_bread(sb, block);
	if (!*raw_super_buf) {
		f2fs_msg(sb, KERN_ERR, "unable to read %s superblock",
				super);
760
		return -EIO;
761 762 763 764 765 766 767 768 769 770 771
	}

	*raw_super = (struct f2fs_super_block *)
		((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);

	/* sanity checking of raw super */
	if (!sanity_check_raw_super(sb, *raw_super))
		return 0;

	f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem "
				"in %s superblock", super);
772
	return -EINVAL;
773 774
}

J
Jaegeuk Kim 已提交
775 776 777 778 779 780 781 782 783 784 785 786 787
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct f2fs_sb_info *sbi;
	struct f2fs_super_block *raw_super;
	struct buffer_head *raw_super_buf;
	struct inode *root;
	long err = -EINVAL;

	/* allocate memory for f2fs-specific super block info */
	sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

788
	/* set a block size */
789 790
	if (!sb_set_blocksize(sb, F2FS_BLKSIZE)) {
		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
J
Jaegeuk Kim 已提交
791
		goto free_sbi;
792
	}
J
Jaegeuk Kim 已提交
793

794 795
	err = validate_superblock(sb, &raw_super, &raw_super_buf, 0);
	if (err) {
796
		brelse(raw_super_buf);
797 798 799
		/* check secondary superblock when primary failed */
		err = validate_superblock(sb, &raw_super, &raw_super_buf, 1);
		if (err)
800
			goto free_sb_buf;
J
Jaegeuk Kim 已提交
801
	}
802
	sb->s_fs_info = sbi;
J
Jaegeuk Kim 已提交
803 804 805 806 807 808 809 810 811 812 813 814
	/* init some FS parameters */
	sbi->active_logs = NR_CURSEG_TYPE;

	set_opt(sbi, BG_GC);

#ifdef CONFIG_F2FS_FS_XATTR
	set_opt(sbi, XATTR_USER);
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
	set_opt(sbi, POSIX_ACL);
#endif
	/* parse mount options */
815
	err = parse_options(sb, (char *)data);
816
	if (err)
J
Jaegeuk Kim 已提交
817 818
		goto free_sb_buf;

819
	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
J
Jaegeuk Kim 已提交
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
	sb->s_max_links = F2FS_LINK_MAX;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));

	sb->s_op = &f2fs_sops;
	sb->s_xattr = f2fs_xattr_handlers;
	sb->s_export_op = &f2fs_export_ops;
	sb->s_magic = F2FS_SUPER_MAGIC;
	sb->s_time_gran = 1;
	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));

	/* init f2fs-specific super block info */
	sbi->sb = sb;
	sbi->raw_super = raw_super;
	sbi->raw_super_buf = raw_super_buf;
	mutex_init(&sbi->gc_mutex);
	mutex_init(&sbi->writepages);
	mutex_init(&sbi->cp_mutex);
839
	mutex_init(&sbi->node_write);
J
Jaegeuk Kim 已提交
840 841 842
	sbi->por_doing = 0;
	spin_lock_init(&sbi->stat_lock);
	init_rwsem(&sbi->bio_sem);
843
	init_rwsem(&sbi->cp_rwsem);
J
Jaegeuk Kim 已提交
844 845 846 847 848
	init_sb_info(sbi);

	/* get an inode for meta space */
	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
	if (IS_ERR(sbi->meta_inode)) {
849
		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
J
Jaegeuk Kim 已提交
850 851 852 853 854
		err = PTR_ERR(sbi->meta_inode);
		goto free_sb_buf;
	}

	err = get_valid_checkpoint(sbi);
855 856
	if (err) {
		f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
J
Jaegeuk Kim 已提交
857
		goto free_meta_inode;
858
	}
J
Jaegeuk Kim 已提交
859 860 861

	/* sanity checking of checkpoint */
	err = -EINVAL;
862
	if (sanity_check_ckpt(sbi)) {
863
		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
J
Jaegeuk Kim 已提交
864
		goto free_cp;
865
	}
J
Jaegeuk Kim 已提交
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882

	sbi->total_valid_node_count =
				le32_to_cpu(sbi->ckpt->valid_node_count);
	sbi->total_valid_inode_count =
				le32_to_cpu(sbi->ckpt->valid_inode_count);
	sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
	sbi->total_valid_block_count =
				le64_to_cpu(sbi->ckpt->valid_block_count);
	sbi->last_valid_block_count = sbi->total_valid_block_count;
	sbi->alloc_valid_block_count = 0;
	INIT_LIST_HEAD(&sbi->dir_inode_list);
	spin_lock_init(&sbi->dir_inode_lock);

	init_orphan_info(sbi);

	/* setup f2fs internal modules */
	err = build_segment_manager(sbi);
883 884 885
	if (err) {
		f2fs_msg(sb, KERN_ERR,
			"Failed to initialize F2FS segment manager");
J
Jaegeuk Kim 已提交
886
		goto free_sm;
887
	}
J
Jaegeuk Kim 已提交
888
	err = build_node_manager(sbi);
889 890 891
	if (err) {
		f2fs_msg(sb, KERN_ERR,
			"Failed to initialize F2FS node manager");
J
Jaegeuk Kim 已提交
892
		goto free_nm;
893
	}
J
Jaegeuk Kim 已提交
894 895 896 897 898 899

	build_gc_manager(sbi);

	/* get an inode for node space */
	sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
	if (IS_ERR(sbi->node_inode)) {
900
		f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
J
Jaegeuk Kim 已提交
901 902 903 904 905 906
		err = PTR_ERR(sbi->node_inode);
		goto free_nm;
	}

	/* if there are nt orphan nodes free them */
	err = -EINVAL;
907
	if (recover_orphan_inodes(sbi))
J
Jaegeuk Kim 已提交
908 909 910 911 912
		goto free_node_inode;

	/* read root inode and dentry */
	root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
	if (IS_ERR(root)) {
913
		f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
J
Jaegeuk Kim 已提交
914 915 916 917 918 919 920 921 922 923 924 925 926
		err = PTR_ERR(root);
		goto free_node_inode;
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size)
		goto free_root_inode;

	sb->s_root = d_make_root(root); /* allocate root dentry */
	if (!sb->s_root) {
		err = -ENOMEM;
		goto free_root_inode;
	}

	/* recover fsynced data */
927 928
	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
		err = recover_fsync_data(sbi);
929 930 931
		if (err)
			f2fs_msg(sb, KERN_ERR,
				"Cannot recover all fsync data errno=%ld", err);
932
	}
J
Jaegeuk Kim 已提交
933

934 935 936 937 938 939 940 941 942 943
	/*
	 * If filesystem is not mounted as read-only then
	 * do start the gc_thread.
	 */
	if (!(sb->s_flags & MS_RDONLY)) {
		/* After POR, we can run background GC thread.*/
		err = start_gc_thread(sbi);
		if (err)
			goto fail;
	}
J
Jaegeuk Kim 已提交
944 945 946 947 948

	err = f2fs_build_stats(sbi);
	if (err)
		goto fail;

949 950 951 952 953 954 955
	if (f2fs_proc_root)
		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);

	if (sbi->s_proc)
		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
				 &f2fs_seq_segment_info_fops, sb);

956 957 958 959 960 961 962 963
	if (test_opt(sbi, DISCARD)) {
		struct request_queue *q = bdev_get_queue(sb->s_bdev);
		if (!blk_queue_discard(q))
			f2fs_msg(sb, KERN_WARNING,
					"mounting with \"discard\" option, but "
					"the device does not support discard");
	}

964 965 966 967 968 969 970
	sbi->s_kobj.kset = f2fs_kset;
	init_completion(&sbi->s_kobj_unregister);
	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
							"%s", sb->s_id);
	if (err)
		goto fail;

J
Jaegeuk Kim 已提交
971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007
	return 0;
fail:
	stop_gc_thread(sbi);
free_root_inode:
	dput(sb->s_root);
	sb->s_root = NULL;
free_node_inode:
	iput(sbi->node_inode);
free_nm:
	destroy_node_manager(sbi);
free_sm:
	destroy_segment_manager(sbi);
free_cp:
	kfree(sbi->ckpt);
free_meta_inode:
	make_bad_inode(sbi->meta_inode);
	iput(sbi->meta_inode);
free_sb_buf:
	brelse(raw_super_buf);
free_sbi:
	kfree(sbi);
	return err;
}

static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
			const char *dev_name, void *data)
{
	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
}

static struct file_system_type f2fs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "f2fs",
	.mount		= f2fs_mount,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};
1008
MODULE_ALIAS_FS("f2fs");
J
Jaegeuk Kim 已提交
1009

1010
static int __init init_inodecache(void)
J
Jaegeuk Kim 已提交
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
{
	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
			sizeof(struct f2fs_inode_info), NULL);
	if (f2fs_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(f2fs_inode_cachep);
}

static int __init init_f2fs_fs(void)
{
	int err;

	err = init_inodecache();
	if (err)
		goto fail;
	err = create_node_manager_caches();
	if (err)
1038
		goto free_inodecache;
J
Jaegeuk Kim 已提交
1039 1040
	err = create_gc_caches();
	if (err)
1041
		goto free_node_manager_caches;
J
Jaegeuk Kim 已提交
1042 1043
	err = create_checkpoint_caches();
	if (err)
1044
		goto free_gc_caches;
1045
	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
1046 1047
	if (!f2fs_kset) {
		err = -ENOMEM;
1048
		goto free_checkpoint_caches;
1049
	}
1050 1051
	err = register_filesystem(&f2fs_fs_type);
	if (err)
1052
		goto free_kset;
1053
	f2fs_create_root_stats();
1054
	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066
	return 0;

free_kset:
	kset_unregister(f2fs_kset);
free_checkpoint_caches:
	destroy_checkpoint_caches();
free_gc_caches:
	destroy_gc_caches();
free_node_manager_caches:
	destroy_node_manager_caches();
free_inodecache:
	destroy_inodecache();
J
Jaegeuk Kim 已提交
1067 1068 1069 1070 1071 1072
fail:
	return err;
}

static void __exit exit_f2fs_fs(void)
{
1073
	remove_proc_entry("fs/f2fs", NULL);
1074
	f2fs_destroy_root_stats();
J
Jaegeuk Kim 已提交
1075 1076 1077 1078 1079
	unregister_filesystem(&f2fs_fs_type);
	destroy_checkpoint_caches();
	destroy_gc_caches();
	destroy_node_manager_caches();
	destroy_inodecache();
1080
	kset_unregister(f2fs_kset);
J
Jaegeuk Kim 已提交
1081 1082 1083 1084 1085 1086 1087 1088
}

module_init(init_f2fs_fs)
module_exit(exit_f2fs_fs)

MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");