inode.c 21.7 KB
Newer Older
R
Ryusuke Konishi 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26
/*
 * inode.c - NILFS inode operations.
 *
 * 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/mpage.h>
#include <linux/writeback.h>
27
#include <linux/uio.h>
R
Ryusuke Konishi 已提交
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50
#include "nilfs.h"
#include "segment.h"
#include "page.h"
#include "mdt.h"
#include "cpfile.h"
#include "ifile.h"


/**
 * nilfs_get_block() - get a file block on the filesystem (callback function)
 * @inode - inode struct of the target file
 * @blkoff - file block number
 * @bh_result - buffer head to be mapped on
 * @create - indicate whether allocating the block or not when it has not
 *      been allocated yet.
 *
 * This function does not issue actual read request of the specified data
 * block. It is done by VFS.
 */
int nilfs_get_block(struct inode *inode, sector_t blkoff,
		    struct buffer_head *bh_result, int create)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
51
	__u64 blknum = 0;
R
Ryusuke Konishi 已提交
52 53
	int err = 0, ret;
	struct inode *dat = nilfs_dat_inode(NILFS_I_NILFS(inode));
54
	unsigned maxblocks = bh_result->b_size >> inode->i_blkbits;
R
Ryusuke Konishi 已提交
55

56 57 58 59
	down_read(&NILFS_MDT(dat)->mi_sem);
	ret = nilfs_bmap_lookup_contig(ii->i_bmap, blkoff, &blknum, maxblocks);
	up_read(&NILFS_MDT(dat)->mi_sem);
	if (ret >= 0) {	/* found */
R
Ryusuke Konishi 已提交
60
		map_bh(bh_result, inode->i_sb, blknum);
61 62
		if (ret > 0)
			bh_result->b_size = (ret << inode->i_blkbits);
R
Ryusuke Konishi 已提交
63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
		goto out;
	}
	/* data block was not found */
	if (ret == -ENOENT && create) {
		struct nilfs_transaction_info ti;

		bh_result->b_blocknr = 0;
		err = nilfs_transaction_begin(inode->i_sb, &ti, 1);
		if (unlikely(err))
			goto out;
		err = nilfs_bmap_insert(ii->i_bmap, (unsigned long)blkoff,
					(unsigned long)bh_result);
		if (unlikely(err != 0)) {
			if (err == -EEXIST) {
				/*
				 * The get_block() function could be called
				 * from multiple callers for an inode.
				 * However, the page having this block must
				 * be locked in this case.
				 */
83
				printk(KERN_WARNING
R
Ryusuke Konishi 已提交
84 85 86 87 88 89
				       "nilfs_get_block: a race condition "
				       "while inserting a data block. "
				       "(inode number=%lu, file block "
				       "offset=%llu)\n",
				       inode->i_ino,
				       (unsigned long long)blkoff);
90
				err = 0;
R
Ryusuke Konishi 已提交
91 92 93 94 95 96
			} else if (err == -EINVAL) {
				nilfs_error(inode->i_sb, __func__,
					    "broken bmap (inode=%lu)\n",
					    inode->i_ino);
				err = -EIO;
			}
97
			nilfs_transaction_abort(inode->i_sb);
R
Ryusuke Konishi 已提交
98 99
			goto out;
		}
100
		nilfs_transaction_commit(inode->i_sb); /* never fails */
R
Ryusuke Konishi 已提交
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
		/* Error handling should be detailed */
		set_buffer_new(bh_result);
		map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed
						      to proper value */
	} else if (ret == -ENOENT) {
		/* not found is not error (e.g. hole); must return without
		   the mapped state flag. */
		;
	} else {
		err = ret;
	}

 out:
	return err;
}

/**
 * nilfs_readpage() - implement readpage() method of nilfs_aops {}
 * address_space_operations.
 * @file - file struct of the file to be read
 * @page - the page to be read
 */
static int nilfs_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, nilfs_get_block);
}

/**
 * nilfs_readpages() - implement readpages() method of nilfs_aops {}
 * address_space_operations.
 * @file - file struct of the file to be read
 * @mapping - address_space struct used for reading multiple pages
 * @pages - the pages to be read
 * @nr_pages - number of pages to be read
 */
static int nilfs_readpages(struct file *file, struct address_space *mapping,
			   struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
}

static int nilfs_writepages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
145 146 147 148 149 150 151 152
	struct inode *inode = mapping->host;
	int err = 0;

	if (wbc->sync_mode == WB_SYNC_ALL)
		err = nilfs_construct_dsync_segment(inode->i_sb, inode,
						    wbc->range_start,
						    wbc->range_end);
	return err;
R
Ryusuke Konishi 已提交
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
}

static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	int err;

	redirty_page_for_writepage(wbc, page);
	unlock_page(page);

	if (wbc->sync_mode == WB_SYNC_ALL) {
		err = nilfs_construct_segment(inode->i_sb);
		if (unlikely(err))
			return err;
	} else if (wbc->for_reclaim)
		nilfs_flush_segment(inode->i_sb, inode->i_ino);

	return 0;
}

static int nilfs_set_page_dirty(struct page *page)
{
	int ret = __set_page_dirty_buffers(page);

	if (ret) {
		struct inode *inode = page->mapping->host;
		struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
		unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);

		nilfs_set_file_dirty(sbi, inode, nr_dirty);
	}
	return ret;
}

static int nilfs_write_begin(struct file *file, struct address_space *mapping,
			     loff_t pos, unsigned len, unsigned flags,
			     struct page **pagep, void **fsdata)

{
	struct inode *inode = mapping->host;
	int err = nilfs_transaction_begin(inode->i_sb, NULL, 1);

	if (unlikely(err))
		return err;

	*pagep = NULL;
	err = block_write_begin(file, mapping, pos, len, flags, pagep,
				fsdata, nilfs_get_block);
	if (unlikely(err))
202
		nilfs_transaction_abort(inode->i_sb);
R
Ryusuke Konishi 已提交
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
	return err;
}

static int nilfs_write_end(struct file *file, struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied,
			   struct page *page, void *fsdata)
{
	struct inode *inode = mapping->host;
	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
	unsigned nr_dirty;
	int err;

	nr_dirty = nilfs_page_count_clean_buffers(page, start,
						  start + copied);
	copied = generic_write_end(file, mapping, pos, len, copied, page,
				   fsdata);
	nilfs_set_file_dirty(NILFS_SB(inode->i_sb), inode, nr_dirty);
220
	err = nilfs_transaction_commit(inode->i_sb);
R
Ryusuke Konishi 已提交
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
	return err ? : copied;
}

static ssize_t
nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
		loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	ssize_t size;

	if (rw == WRITE)
		return 0;

	/* Needs synchronization with the cleaner */
	size = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				  offset, nr_segs, nilfs_get_block, NULL);
	return size;
}

struct address_space_operations nilfs_aops = {
	.writepage		= nilfs_writepage,
	.readpage		= nilfs_readpage,
244
	.sync_page		= block_sync_page,
R
Ryusuke Konishi 已提交
245 246 247 248 249 250 251 252
	.writepages		= nilfs_writepages,
	.set_page_dirty		= nilfs_set_page_dirty,
	.readpages		= nilfs_readpages,
	.write_begin		= nilfs_write_begin,
	.write_end		= nilfs_write_end,
	/* .releasepage		= nilfs_releasepage, */
	.invalidatepage		= block_invalidatepage,
	.direct_IO		= nilfs_direct_IO,
253
	.is_partially_uptodate  = block_is_partially_uptodate,
R
Ryusuke Konishi 已提交
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
};

struct inode *nilfs_new_inode(struct inode *dir, int mode)
{
	struct super_block *sb = dir->i_sb;
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct inode *inode;
	struct nilfs_inode_info *ii;
	int err = -ENOMEM;
	ino_t ino;

	inode = new_inode(sb);
	if (unlikely(!inode))
		goto failed;

	mapping_set_gfp_mask(inode->i_mapping,
			     mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);

	ii = NILFS_I(inode);
	ii->i_state = 1 << NILFS_I_NEW;

	err = nilfs_ifile_create_inode(sbi->s_ifile, &ino, &ii->i_bh);
	if (unlikely(err))
		goto failed_ifile_create_inode;
	/* reference count of i_bh inherits from nilfs_mdt_read_block() */

	atomic_inc(&sbi->s_inodes_count);

	inode->i_uid = current_fsuid();
	if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current_fsgid();

	inode->i_mode = mode;
	inode->i_ino = ino;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;

	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
		err = nilfs_bmap_read(ii->i_bmap, NULL);
		if (err < 0)
			goto failed_bmap;

		set_bit(NILFS_I_BMAP, &ii->i_state);
		/* No lock is needed; iget() ensures it. */
	}

	ii->i_flags = NILFS_I(dir)->i_flags;
	if (S_ISLNK(mode))
		ii->i_flags &= ~(NILFS_IMMUTABLE_FL | NILFS_APPEND_FL);
	if (!S_ISDIR(mode))
		ii->i_flags &= ~NILFS_DIRSYNC_FL;

	/* ii->i_file_acl = 0; */
	/* ii->i_dir_acl = 0; */
	ii->i_dir_start_lookup = 0;
	ii->i_cno = 0;
	nilfs_set_inode_flags(inode);
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);
	insert_inode_hash(inode);

	err = nilfs_init_acl(inode, dir);
	if (unlikely(err))
		goto failed_acl; /* never occur. When supporting
				    nilfs_init_acl(), proper cancellation of
				    above jobs should be considered */

	mark_inode_dirty(inode);
	return inode;

 failed_acl:
 failed_bmap:
	inode->i_nlink = 0;
	iput(inode);  /* raw_inode will be deleted through
			 generic_delete_inode() */
	goto failed;

 failed_ifile_create_inode:
	make_bad_inode(inode);
	iput(inode);  /* if i_nlink == 1, generic_forget_inode() will be
			 called */
 failed:
	return ERR_PTR(err);
}

void nilfs_free_inode(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	struct nilfs_sb_info *sbi = NILFS_SB(sb);

	clear_inode(inode);
	/* XXX: check error code? Is there any thing I can do? */
	(void) nilfs_ifile_delete_inode(sbi->s_ifile, inode->i_ino);
	atomic_dec(&sbi->s_inodes_count);
}

void nilfs_set_inode_flags(struct inode *inode)
{
	unsigned int flags = NILFS_I(inode)->i_flags;

	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
			    S_DIRSYNC);
	if (flags & NILFS_SYNC_FL)
		inode->i_flags |= S_SYNC;
	if (flags & NILFS_APPEND_FL)
		inode->i_flags |= S_APPEND;
	if (flags & NILFS_IMMUTABLE_FL)
		inode->i_flags |= S_IMMUTABLE;
#ifndef NILFS_ATIME_DISABLE
	if (flags & NILFS_NOATIME_FL)
#endif
		inode->i_flags |= S_NOATIME;
	if (flags & NILFS_DIRSYNC_FL)
		inode->i_flags |= S_DIRSYNC;
	mapping_set_gfp_mask(inode->i_mapping,
			     mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
}

int nilfs_read_inode_common(struct inode *inode,
			    struct nilfs_inode *raw_inode)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	int err;

	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
	inode->i_uid = (uid_t)le32_to_cpu(raw_inode->i_uid);
	inode->i_gid = (gid_t)le32_to_cpu(raw_inode->i_gid);
	inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
	inode->i_size = le64_to_cpu(raw_inode->i_size);
	inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
	inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
	inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
390 391 392 393
	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
	if (inode->i_nlink == 0 && inode->i_mode == 0)
R
Ryusuke Konishi 已提交
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
		return -EINVAL; /* this inode is deleted */

	inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
	ii->i_flags = le32_to_cpu(raw_inode->i_flags);
#if 0
	ii->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
	ii->i_dir_acl = S_ISREG(inode->i_mode) ?
		0 : le32_to_cpu(raw_inode->i_dir_acl);
#endif
	ii->i_cno = 0;
	inode->i_generation = le32_to_cpu(raw_inode->i_generation);

	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode)) {
		err = nilfs_bmap_read(ii->i_bmap, raw_inode);
		if (err < 0)
			return err;
		set_bit(NILFS_I_BMAP, &ii->i_state);
		/* No lock is needed; iget() ensures it. */
	}
	return 0;
}

static int __nilfs_read_inode(struct super_block *sb, unsigned long ino,
			      struct inode *inode)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct inode *dat = nilfs_dat_inode(sbi->s_nilfs);
	struct buffer_head *bh;
	struct nilfs_inode *raw_inode;
	int err;

	down_read(&NILFS_MDT(dat)->mi_sem);	/* XXX */
	err = nilfs_ifile_get_inode_block(sbi->s_ifile, ino, &bh);
	if (unlikely(err))
		goto bad_inode;

	raw_inode = nilfs_ifile_map_inode(sbi->s_ifile, ino, bh);

	if (nilfs_read_inode_common(inode, raw_inode))
		goto failed_unmap;

	if (S_ISREG(inode->i_mode)) {
		inode->i_op = &nilfs_file_inode_operations;
		inode->i_fop = &nilfs_file_operations;
		inode->i_mapping->a_ops = &nilfs_aops;
	} else if (S_ISDIR(inode->i_mode)) {
		inode->i_op = &nilfs_dir_inode_operations;
		inode->i_fop = &nilfs_dir_operations;
		inode->i_mapping->a_ops = &nilfs_aops;
	} else if (S_ISLNK(inode->i_mode)) {
		inode->i_op = &nilfs_symlink_inode_operations;
		inode->i_mapping->a_ops = &nilfs_aops;
	} else {
		inode->i_op = &nilfs_special_inode_operations;
		init_special_inode(
			inode, inode->i_mode,
			new_decode_dev(le64_to_cpu(raw_inode->i_device_code)));
	}
	nilfs_ifile_unmap_inode(sbi->s_ifile, ino, bh);
	brelse(bh);
	up_read(&NILFS_MDT(dat)->mi_sem);	/* XXX */
	nilfs_set_inode_flags(inode);
	return 0;

 failed_unmap:
	nilfs_ifile_unmap_inode(sbi->s_ifile, ino, bh);
	brelse(bh);

 bad_inode:
	up_read(&NILFS_MDT(dat)->mi_sem);	/* XXX */
	return err;
}

struct inode *nilfs_iget(struct super_block *sb, unsigned long ino)
{
	struct inode *inode;
	int err;

	inode = iget_locked(sb, ino);
	if (unlikely(!inode))
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	err = __nilfs_read_inode(sb, ino, inode);
	if (unlikely(err)) {
		iget_failed(inode);
		return ERR_PTR(err);
	}
	unlock_new_inode(inode);
	return inode;
}

void nilfs_write_inode_common(struct inode *inode,
			      struct nilfs_inode *raw_inode, int has_bmap)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);

	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
	raw_inode->i_uid = cpu_to_le32(inode->i_uid);
	raw_inode->i_gid = cpu_to_le32(inode->i_gid);
	raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
	raw_inode->i_size = cpu_to_le64(inode->i_size);
	raw_inode->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
	raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
500 501
	raw_inode->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
	raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
R
Ryusuke Konishi 已提交
502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589
	raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);

	raw_inode->i_flags = cpu_to_le32(ii->i_flags);
	raw_inode->i_generation = cpu_to_le32(inode->i_generation);

	if (has_bmap)
		nilfs_bmap_write(ii->i_bmap, raw_inode);
	else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
		raw_inode->i_device_code =
			cpu_to_le64(new_encode_dev(inode->i_rdev));
	/* When extending inode, nilfs->ns_inode_size should be checked
	   for substitutions of appended fields */
}

void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
{
	ino_t ino = inode->i_ino;
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct super_block *sb = inode->i_sb;
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct nilfs_inode *raw_inode;

	raw_inode = nilfs_ifile_map_inode(sbi->s_ifile, ino, ibh);

	/* The buffer is guarded with lock_buffer() by the caller */
	if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
		memset(raw_inode, 0, NILFS_MDT(sbi->s_ifile)->mi_entry_size);
	set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);

	nilfs_write_inode_common(inode, raw_inode, 0);
		/* XXX: call with has_bmap = 0 is a workaround to avoid
		   deadlock of bmap. This delays update of i_bmap to just
		   before writing */
	nilfs_ifile_unmap_inode(sbi->s_ifile, ino, ibh);
}

#define NILFS_MAX_TRUNCATE_BLOCKS	16384  /* 64MB for 4KB block */

static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
				unsigned long from)
{
	unsigned long b;
	int ret;

	if (!test_bit(NILFS_I_BMAP, &ii->i_state))
		return;
 repeat:
	ret = nilfs_bmap_last_key(ii->i_bmap, &b);
	if (ret == -ENOENT)
		return;
	else if (ret < 0)
		goto failed;

	if (b < from)
		return;

	b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from);
	ret = nilfs_bmap_truncate(ii->i_bmap, b);
	nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb);
	if (!ret || (ret == -ENOMEM &&
		     nilfs_bmap_truncate(ii->i_bmap, b) == 0))
		goto repeat;

 failed:
	if (ret == -EINVAL)
		nilfs_error(ii->vfs_inode.i_sb, __func__,
			    "bmap is broken (ino=%lu)", ii->vfs_inode.i_ino);
	else
		nilfs_warning(ii->vfs_inode.i_sb, __func__,
			      "failed to truncate bmap (ino=%lu, err=%d)",
			      ii->vfs_inode.i_ino, ret);
}

void nilfs_truncate(struct inode *inode)
{
	unsigned long blkoff;
	unsigned int blocksize;
	struct nilfs_transaction_info ti;
	struct super_block *sb = inode->i_sb;
	struct nilfs_inode_info *ii = NILFS_I(inode);

	if (!test_bit(NILFS_I_BMAP, &ii->i_state))
		return;
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return;

	blocksize = sb->s_blocksize;
	blkoff = (inode->i_size + blocksize - 1) >> sb->s_blocksize_bits;
590
	nilfs_transaction_begin(sb, &ti, 0); /* never fails */
R
Ryusuke Konishi 已提交
591 592 593 594 595 596 597 598 599 600

	block_truncate_page(inode->i_mapping, inode->i_size, nilfs_get_block);

	nilfs_truncate_bmap(ii, blkoff);

	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	if (IS_SYNC(inode))
		nilfs_set_transaction_flag(NILFS_TI_SYNC);

	nilfs_set_file_dirty(NILFS_SB(sb), inode, 0);
601
	nilfs_transaction_commit(sb);
R
Ryusuke Konishi 已提交
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
	/* May construct a logical segment and may fail in sync mode.
	   But truncate has no return value. */
}

void nilfs_delete_inode(struct inode *inode)
{
	struct nilfs_transaction_info ti;
	struct super_block *sb = inode->i_sb;
	struct nilfs_inode_info *ii = NILFS_I(inode);

	if (unlikely(is_bad_inode(inode))) {
		if (inode->i_data.nrpages)
			truncate_inode_pages(&inode->i_data, 0);
		clear_inode(inode);
		return;
	}
618 619
	nilfs_transaction_begin(sb, &ti, 0); /* never fails */

R
Ryusuke Konishi 已提交
620 621 622 623 624 625 626 627
	if (inode->i_data.nrpages)
		truncate_inode_pages(&inode->i_data, 0);

	nilfs_truncate_bmap(ii, 0);
	nilfs_free_inode(inode);
	/* nilfs_free_inode() marks inode buffer dirty */
	if (IS_SYNC(inode))
		nilfs_set_transaction_flag(NILFS_TI_SYNC);
628
	nilfs_transaction_commit(sb);
R
Ryusuke Konishi 已提交
629 630 631 632 633 634 635 636 637
	/* May construct a logical segment and may fail in sync mode.
	   But delete_inode has no return value. */
}

int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
	struct nilfs_transaction_info ti;
	struct inode *inode = dentry->d_inode;
	struct super_block *sb = inode->i_sb;
638
	int err;
R
Ryusuke Konishi 已提交
639 640 641 642 643 644 645 646 647 648 649

	err = inode_change_ok(inode, iattr);
	if (err)
		return err;

	err = nilfs_transaction_begin(sb, &ti, 0);
	if (unlikely(err))
		return err;
	err = inode_setattr(inode, iattr);
	if (!err && (iattr->ia_valid & ATTR_MODE))
		err = nilfs_acl_chmod(inode);
650 651 652 653 654 655
	if (likely(!err))
		err = nilfs_transaction_commit(sb);
	else
		nilfs_transaction_abort(sb);

	return err;
R
Ryusuke Konishi 已提交
656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708
}

int nilfs_load_inode_block(struct nilfs_sb_info *sbi, struct inode *inode,
			   struct buffer_head **pbh)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	int err;

	spin_lock(&sbi->s_inode_lock);
	/* Caller of this function MUST lock s_inode_lock */
	if (ii->i_bh == NULL) {
		spin_unlock(&sbi->s_inode_lock);
		err = nilfs_ifile_get_inode_block(sbi->s_ifile, inode->i_ino,
						  pbh);
		if (unlikely(err))
			return err;
		spin_lock(&sbi->s_inode_lock);
		if (ii->i_bh == NULL)
			ii->i_bh = *pbh;
		else {
			brelse(*pbh);
			*pbh = ii->i_bh;
		}
	} else
		*pbh = ii->i_bh;

	get_bh(*pbh);
	spin_unlock(&sbi->s_inode_lock);
	return 0;
}

int nilfs_inode_dirty(struct inode *inode)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
	int ret = 0;

	if (!list_empty(&ii->i_dirty)) {
		spin_lock(&sbi->s_inode_lock);
		ret = test_bit(NILFS_I_DIRTY, &ii->i_state) ||
			test_bit(NILFS_I_BUSY, &ii->i_state);
		spin_unlock(&sbi->s_inode_lock);
	}
	return ret;
}

int nilfs_set_file_dirty(struct nilfs_sb_info *sbi, struct inode *inode,
			 unsigned nr_dirty)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);

	atomic_add(nr_dirty, &sbi->s_nilfs->ns_ndirtyblks);

R
Ryusuke Konishi 已提交
709
	if (test_and_set_bit(NILFS_I_DIRTY, &ii->i_state))
R
Ryusuke Konishi 已提交
710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
		return 0;

	spin_lock(&sbi->s_inode_lock);
	if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
	    !test_bit(NILFS_I_BUSY, &ii->i_state)) {
		/* Because this routine may race with nilfs_dispose_list(),
		   we have to check NILFS_I_QUEUED here, too. */
		if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) {
			/* This will happen when somebody is freeing
			   this inode. */
			nilfs_warning(sbi->s_super, __func__,
				      "cannot get inode (ino=%lu)\n",
				      inode->i_ino);
			spin_unlock(&sbi->s_inode_lock);
			return -EINVAL; /* NILFS_I_DIRTY may remain for
					   freeing inode */
		}
		list_del(&ii->i_dirty);
		list_add_tail(&ii->i_dirty, &sbi->s_dirty_files);
		set_bit(NILFS_I_QUEUED, &ii->i_state);
	}
	spin_unlock(&sbi->s_inode_lock);
	return 0;
}

int nilfs_mark_inode_dirty(struct inode *inode)
{
	struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
	struct buffer_head *ibh;
	int err;

	err = nilfs_load_inode_block(sbi, inode, &ibh);
	if (unlikely(err)) {
		nilfs_warning(inode->i_sb, __func__,
			      "failed to reget inode block.\n");
		return err;
	}
	lock_buffer(ibh);
	nilfs_update_inode(inode, ibh);
	unlock_buffer(ibh);
	nilfs_mdt_mark_buffer_dirty(ibh);
	nilfs_mdt_mark_dirty(sbi->s_ifile);
	brelse(ibh);
	return 0;
}

/**
 * nilfs_dirty_inode - reflect changes on given inode to an inode block.
 * @inode: inode of the file to be registered.
 *
 * nilfs_dirty_inode() loads a inode block containing the specified
 * @inode and copies data from a nilfs_inode to a corresponding inode
 * entry in the inode block. This operation is excluded from the segment
 * construction. This function can be called both as a single operation
 * and as a part of indivisible file operations.
 */
void nilfs_dirty_inode(struct inode *inode)
{
	struct nilfs_transaction_info ti;

	if (is_bad_inode(inode)) {
		nilfs_warning(inode->i_sb, __func__,
			      "tried to mark bad_inode dirty. ignored.\n");
		dump_stack();
		return;
	}
	nilfs_transaction_begin(inode->i_sb, &ti, 0);
R
Ryusuke Konishi 已提交
777
	nilfs_mark_inode_dirty(inode);
778
	nilfs_transaction_commit(inode->i_sb); /* never fails */
R
Ryusuke Konishi 已提交
779
}