dir.c 21.2 KB
Newer Older
J
Joern Engel 已提交
1 2 3 4 5 6 7 8
/*
 * fs/logfs/dir.c	- directory-related code
 *
 * As should be obvious for Linux kernel code, license is GPLv2
 *
 * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
 */
#include "logfs.h"
9
#include <linux/slab.h>
J
Joern Engel 已提交
10 11 12 13 14

/*
 * Atomic dir operations
 *
 * Directory operations are by default not atomic.  Dentries and Inodes are
A
Anand Gadiyar 已提交
15
 * created/removed/altered in separate operations.  Therefore we need to do
J
Joern Engel 已提交
16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94
 * a small amount of journaling.
 *
 * Create, link, mkdir, mknod and symlink all share the same function to do
 * the work: __logfs_create.  This function works in two atomic steps:
 * 1. allocate inode (remember in journal)
 * 2. allocate dentry (clear journal)
 *
 * As we can only get interrupted between the two, when the inode we just
 * created is simply stored in the anchor.  On next mount, if we were
 * interrupted, we delete the inode.  From a users point of view the
 * operation never happened.
 *
 * Unlink and rmdir also share the same function: unlink.  Again, this
 * function works in two atomic steps
 * 1. remove dentry (remember inode in journal)
 * 2. unlink inode (clear journal)
 *
 * And again, on the next mount, if we were interrupted, we delete the inode.
 * From a users point of view the operation succeeded.
 *
 * Rename is the real pain to deal with, harder than all the other methods
 * combined.  Depending on the circumstances we can run into three cases.
 * A "target rename" where the target dentry already existed, a "local
 * rename" where both parent directories are identical or a "cross-directory
 * rename" in the remaining case.
 *
 * Local rename is atomic, as the old dentry is simply rewritten with a new
 * name.
 *
 * Cross-directory rename works in two steps, similar to __logfs_create and
 * logfs_unlink:
 * 1. Write new dentry (remember old dentry in journal)
 * 2. Remove old dentry (clear journal)
 *
 * Here we remember a dentry instead of an inode.  On next mount, if we were
 * interrupted, we delete the dentry.  From a users point of view, the
 * operation succeeded.
 *
 * Target rename works in three atomic steps:
 * 1. Attach old inode to new dentry (remember old dentry and new inode)
 * 2. Remove old dentry (still remember the new inode)
 * 3. Remove victim inode
 *
 * Here we remember both an inode an a dentry.  If we get interrupted
 * between steps 1 and 2, we delete both the dentry and the inode.  If
 * we get interrupted between steps 2 and 3, we delete just the inode.
 * In either case, the remaining objects are deleted on next mount.  From
 * a users point of view, the operation succeeded.
 */

static int write_dir(struct inode *dir, struct logfs_disk_dentry *dd,
		loff_t pos)
{
	return logfs_inode_write(dir, dd, sizeof(*dd), pos, WF_LOCK, NULL);
}

static int write_inode(struct inode *inode)
{
	return __logfs_write_inode(inode, WF_LOCK);
}

static s64 dir_seek_data(struct inode *inode, s64 pos)
{
	s64 new_pos = logfs_seek_data(inode, pos);

	return max(pos, new_pos - 1);
}

static int beyond_eof(struct inode *inode, loff_t bix)
{
	loff_t pos = bix << inode->i_sb->s_blocksize_bits;
	return pos >= i_size_read(inode);
}

/*
 * Prime value was chosen to be roughly 256 + 26.  r5 hash uses 11,
 * so short names (len <= 9) don't even occupy the complete 32bit name
 * space.  A prime >256 ensures short names quickly spread the 32bit
 * name space.  Add about 26 for the estimated amount of information
L
Lucas De Marchi 已提交
95
 * of each character and pick a prime nearby, preferably a bit-sparse
J
Joern Engel 已提交
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
 * one.
 */
static u32 hash_32(const char *s, int len, u32 seed)
{
	u32 hash = seed;
	int i;

	for (i = 0; i < len; i++)
		hash = hash * 293 + s[i];
	return hash;
}

/*
 * We have to satisfy several conflicting requirements here.  Small
 * directories should stay fairly compact and not require too many
 * indirect blocks.  The number of possible locations for a given hash
 * should be small to make lookup() fast.  And we should try hard not
 * to overflow the 32bit name space or nfs and 32bit host systems will
 * be unhappy.
 *
 * So we use the following scheme.  First we reduce the hash to 0..15
 * and try a direct block.  If that is occupied we reduce the hash to
 * 16..255 and try an indirect block.  Same for 2x and 3x indirect
 * blocks.  Lastly we reduce the hash to 0x800_0000 .. 0xffff_ffff,
 * but use buckets containing eight entries instead of a single one.
 *
 * Using 16 entries should allow for a reasonable amount of hash
 * collisions, so the 32bit name space can be packed fairly tight
 * before overflowing.  Oh and currently we don't overflow but return
 * and error.
 *
 * How likely are collisions?  Doing the appropriate math is beyond me
 * and the Bronstein textbook.  But running a test program to brute
 * force collisions for a couple of days showed that on average the
 * first collision occurs after 598M entries, with 290M being the
 * smallest result.  Obviously 21 entries could already cause a
 * collision if all entries are carefully chosen.
 */
static pgoff_t hash_index(u32 hash, int round)
{
136 137 138 139 140
	u32 i0_blocks = I0_BLOCKS;
	u32 i1_blocks = I1_BLOCKS;
	u32 i2_blocks = I2_BLOCKS;
	u32 i3_blocks = I3_BLOCKS;

J
Joern Engel 已提交
141 142
	switch (round) {
	case 0:
143
		return hash % i0_blocks;
J
Joern Engel 已提交
144
	case 1:
145
		return i0_blocks + hash % (i1_blocks - i0_blocks);
J
Joern Engel 已提交
146
	case 2:
147
		return i1_blocks + hash % (i2_blocks - i1_blocks);
J
Joern Engel 已提交
148
	case 3:
149
		return i2_blocks + hash % (i3_blocks - i2_blocks);
J
Joern Engel 已提交
150
	case 4 ... 19:
151
		return i3_blocks + 16 * (hash % (((1<<31) - i3_blocks) / 16))
J
Joern Engel 已提交
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
			+ round - 4;
	}
	BUG();
}

static struct page *logfs_get_dd_page(struct inode *dir, struct dentry *dentry)
{
	struct qstr *name = &dentry->d_name;
	struct page *page;
	struct logfs_disk_dentry *dd;
	u32 hash = hash_32(name->name, name->len, 0);
	pgoff_t index;
	int round;

	if (name->len > LOGFS_MAX_NAMELEN)
		return ERR_PTR(-ENAMETOOLONG);

	for (round = 0; round < 20; round++) {
		index = hash_index(hash, round);

		if (beyond_eof(dir, index))
			return NULL;
		if (!logfs_exist_block(dir, index))
			continue;
		page = read_cache_page(dir->i_mapping, index,
				(filler_t *)logfs_readpage, NULL);
		if (IS_ERR(page))
			return page;
		dd = kmap_atomic(page, KM_USER0);
		BUG_ON(dd->namelen == 0);

		if (name->len != be16_to_cpu(dd->namelen) ||
				memcmp(name->name, dd->name, name->len)) {
			kunmap_atomic(dd, KM_USER0);
			page_cache_release(page);
			continue;
		}

		kunmap_atomic(dd, KM_USER0);
		return page;
	}
	return NULL;
}

static int logfs_remove_inode(struct inode *inode)
{
	int ret;

	inode->i_nlink--;
	ret = write_inode(inode);
	LOGFS_BUG_ON(ret, inode->i_sb);
	return ret;
}

static void abort_transaction(struct inode *inode, struct logfs_transaction *ta)
{
	if (logfs_inode(inode)->li_block)
		logfs_inode(inode)->li_block->ta = NULL;
	kfree(ta);
}

static int logfs_unlink(struct inode *dir, struct dentry *dentry)
{
	struct logfs_super *super = logfs_super(dir->i_sb);
	struct inode *inode = dentry->d_inode;
	struct logfs_transaction *ta;
	struct page *page;
	pgoff_t index;
	int ret;

	ta = kzalloc(sizeof(*ta), GFP_KERNEL);
	if (!ta)
		return -ENOMEM;

	ta->state = UNLINK_1;
	ta->ino = inode->i_ino;

	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;

	page = logfs_get_dd_page(dir, dentry);
232 233
	if (!page) {
		kfree(ta);
J
Joern Engel 已提交
234
		return -ENOENT;
235 236 237
	}
	if (IS_ERR(page)) {
		kfree(ta);
J
Joern Engel 已提交
238
		return PTR_ERR(page);
239
	}
J
Joern Engel 已提交
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
	index = page->index;
	page_cache_release(page);

	mutex_lock(&super->s_dirop_mutex);
	logfs_add_transaction(dir, ta);

	ret = logfs_delete(dir, index, NULL);
	if (!ret)
		ret = write_inode(dir);

	if (ret) {
		abort_transaction(dir, ta);
		printk(KERN_ERR"LOGFS: unable to delete inode\n");
		goto out;
	}

	ta->state = UNLINK_2;
	logfs_add_transaction(inode, ta);
	ret = logfs_remove_inode(inode);
out:
	mutex_unlock(&super->s_dirop_mutex);
	return ret;
}

static inline int logfs_empty_dir(struct inode *dir)
{
	u64 data;

	data = logfs_seek_data(dir, 0) << dir->i_sb->s_blocksize_bits;
	return data >= i_size_read(dir);
}

static int logfs_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

276 277
	dentry_unhash(dentry);

J
Joern Engel 已提交
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
	if (!logfs_empty_dir(inode))
		return -ENOTEMPTY;

	return logfs_unlink(dir, dentry);
}

/* FIXME: readdir currently has it's own dir_walk code.  I don't see a good
 * way to combine the two copies */
#define IMPLICIT_NODES 2
static int __logfs_readdir(struct file *file, void *buf, filldir_t filldir)
{
	struct inode *dir = file->f_dentry->d_inode;
	loff_t pos = file->f_pos - IMPLICIT_NODES;
	struct page *page;
	struct logfs_disk_dentry *dd;
	int full;

	BUG_ON(pos < 0);
	for (;; pos++) {
		if (beyond_eof(dir, pos))
			break;
		if (!logfs_exist_block(dir, pos)) {
			/* deleted dentry */
			pos = dir_seek_data(dir, pos);
			continue;
		}
		page = read_cache_page(dir->i_mapping, pos,
				(filler_t *)logfs_readpage, NULL);
		if (IS_ERR(page))
			return PTR_ERR(page);
308
		dd = kmap(page);
J
Joern Engel 已提交
309 310 311 312
		BUG_ON(dd->namelen == 0);

		full = filldir(buf, (char *)dd->name, be16_to_cpu(dd->namelen),
				pos, be64_to_cpu(dd->ino), dd->type);
313
		kunmap(page);
J
Joern Engel 已提交
314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438
		page_cache_release(page);
		if (full)
			break;
	}

	file->f_pos = pos + IMPLICIT_NODES;
	return 0;
}

static int logfs_readdir(struct file *file, void *buf, filldir_t filldir)
{
	struct inode *inode = file->f_dentry->d_inode;
	ino_t pino = parent_ino(file->f_dentry);
	int err;

	if (file->f_pos < 0)
		return -EINVAL;

	if (file->f_pos == 0) {
		if (filldir(buf, ".", 1, 1, inode->i_ino, DT_DIR) < 0)
			return 0;
		file->f_pos++;
	}
	if (file->f_pos == 1) {
		if (filldir(buf, "..", 2, 2, pino, DT_DIR) < 0)
			return 0;
		file->f_pos++;
	}

	err = __logfs_readdir(file, buf, filldir);
	return err;
}

static void logfs_set_name(struct logfs_disk_dentry *dd, struct qstr *name)
{
	dd->namelen = cpu_to_be16(name->len);
	memcpy(dd->name, name->name, name->len);
}

static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry,
		struct nameidata *nd)
{
	struct page *page;
	struct logfs_disk_dentry *dd;
	pgoff_t index;
	u64 ino = 0;
	struct inode *inode;

	page = logfs_get_dd_page(dir, dentry);
	if (IS_ERR(page))
		return ERR_CAST(page);
	if (!page) {
		d_add(dentry, NULL);
		return NULL;
	}
	index = page->index;
	dd = kmap_atomic(page, KM_USER0);
	ino = be64_to_cpu(dd->ino);
	kunmap_atomic(dd, KM_USER0);
	page_cache_release(page);

	inode = logfs_iget(dir->i_sb, ino);
	if (IS_ERR(inode)) {
		printk(KERN_ERR"LogFS: Cannot read inode #%llx for dentry (%lx, %lx)n",
				ino, dir->i_ino, index);
		return ERR_CAST(inode);
	}
	return d_splice_alias(inode, dentry);
}

static void grow_dir(struct inode *dir, loff_t index)
{
	index = (index + 1) << dir->i_sb->s_blocksize_bits;
	if (i_size_read(dir) < index)
		i_size_write(dir, index);
}

static int logfs_write_dir(struct inode *dir, struct dentry *dentry,
		struct inode *inode)
{
	struct page *page;
	struct logfs_disk_dentry *dd;
	u32 hash = hash_32(dentry->d_name.name, dentry->d_name.len, 0);
	pgoff_t index;
	int round, err;

	for (round = 0; round < 20; round++) {
		index = hash_index(hash, round);

		if (logfs_exist_block(dir, index))
			continue;
		page = find_or_create_page(dir->i_mapping, index, GFP_KERNEL);
		if (!page)
			return -ENOMEM;

		dd = kmap_atomic(page, KM_USER0);
		memset(dd, 0, sizeof(*dd));
		dd->ino = cpu_to_be64(inode->i_ino);
		dd->type = logfs_type(inode);
		logfs_set_name(dd, &dentry->d_name);
		kunmap_atomic(dd, KM_USER0);

		err = logfs_write_buf(dir, page, WF_LOCK);
		unlock_page(page);
		page_cache_release(page);
		if (!err)
			grow_dir(dir, index);
		return err;
	}
	/* FIXME: Is there a better return value?  In most cases neither
	 * the filesystem nor the directory are full.  But we have had
	 * too many collisions for this particular hash and no fallback.
	 */
	return -ENOSPC;
}

static int __logfs_create(struct inode *dir, struct dentry *dentry,
		struct inode *inode, const char *dest, long destlen)
{
	struct logfs_super *super = logfs_super(dir->i_sb);
	struct logfs_inode *li = logfs_inode(inode);
	struct logfs_transaction *ta;
	int ret;

	ta = kzalloc(sizeof(*ta), GFP_KERNEL);
A
Al Viro 已提交
439 440 441
	if (!ta) {
		inode->i_nlink--;
		iput(inode);
J
Joern Engel 已提交
442
		return -ENOMEM;
A
Al Viro 已提交
443
	}
J
Joern Engel 已提交
444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559

	ta->state = CREATE_1;
	ta->ino = inode->i_ino;
	mutex_lock(&super->s_dirop_mutex);
	logfs_add_transaction(inode, ta);

	if (dest) {
		/* symlink */
		ret = logfs_inode_write(inode, dest, destlen, 0, WF_LOCK, NULL);
		if (!ret)
			ret = write_inode(inode);
	} else {
		/* creat/mkdir/mknod */
		ret = write_inode(inode);
	}
	if (ret) {
		abort_transaction(inode, ta);
		li->li_flags |= LOGFS_IF_STILLBORN;
		/* FIXME: truncate symlink */
		inode->i_nlink--;
		iput(inode);
		goto out;
	}

	ta->state = CREATE_2;
	logfs_add_transaction(dir, ta);
	ret = logfs_write_dir(dir, dentry, inode);
	/* sync directory */
	if (!ret)
		ret = write_inode(dir);

	if (ret) {
		logfs_del_transaction(dir, ta);
		ta->state = CREATE_2;
		logfs_add_transaction(inode, ta);
		logfs_remove_inode(inode);
		iput(inode);
		goto out;
	}
	d_instantiate(dentry, inode);
out:
	mutex_unlock(&super->s_dirop_mutex);
	return ret;
}

static int logfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct inode *inode;

	/*
	 * FIXME: why do we have to fill in S_IFDIR, while the mode is
	 * correct for mknod, creat, etc.?  Smells like the vfs *should*
	 * do it for us but for some reason fails to do so.
	 */
	inode = logfs_new_inode(dir, S_IFDIR | mode);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	inode->i_op = &logfs_dir_iops;
	inode->i_fop = &logfs_dir_fops;

	return __logfs_create(dir, dentry, inode, NULL, 0);
}

static int logfs_create(struct inode *dir, struct dentry *dentry, int mode,
		struct nameidata *nd)
{
	struct inode *inode;

	inode = logfs_new_inode(dir, mode);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	inode->i_op = &logfs_reg_iops;
	inode->i_fop = &logfs_reg_fops;
	inode->i_mapping->a_ops = &logfs_reg_aops;

	return __logfs_create(dir, dentry, inode, NULL, 0);
}

static int logfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
		dev_t rdev)
{
	struct inode *inode;

	if (dentry->d_name.len > LOGFS_MAX_NAMELEN)
		return -ENAMETOOLONG;

	inode = logfs_new_inode(dir, mode);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	init_special_inode(inode, mode, rdev);

	return __logfs_create(dir, dentry, inode, NULL, 0);
}

static int logfs_symlink(struct inode *dir, struct dentry *dentry,
		const char *target)
{
	struct inode *inode;
	size_t destlen = strlen(target) + 1;

	if (destlen > dir->i_sb->s_blocksize)
		return -ENAMETOOLONG;

	inode = logfs_new_inode(dir, S_IFLNK | 0777);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	inode->i_op = &logfs_symlink_iops;
	inode->i_mapping->a_ops = &logfs_reg_aops;

	return __logfs_create(dir, dentry, inode, target, destlen);
}

560
static int logfs_permission(struct inode *inode, int mask, unsigned int flags)
J
Joern Engel 已提交
561
{
562 563 564
	if (flags & IPERM_FLAG_RCU)
		return -ECHILD;
	return generic_permission(inode, mask, flags, NULL);
J
Joern Engel 已提交
565 566 567 568 569 570 571 572 573 574 575
}

static int logfs_link(struct dentry *old_dentry, struct inode *dir,
		struct dentry *dentry)
{
	struct inode *inode = old_dentry->d_inode;

	if (inode->i_nlink >= LOGFS_LINK_MAX)
		return -EMLINK;

	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
A
Al Viro 已提交
576
	ihold(inode);
J
Joern Engel 已提交
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
	inode->i_nlink++;
	mark_inode_dirty_sync(inode);

	return __logfs_create(dir, dentry, inode, NULL, 0);
}

static int logfs_get_dd(struct inode *dir, struct dentry *dentry,
		struct logfs_disk_dentry *dd, loff_t *pos)
{
	struct page *page;
	void *map;

	page = logfs_get_dd_page(dir, dentry);
	if (IS_ERR(page))
		return PTR_ERR(page);
	*pos = page->index;
	map = kmap_atomic(page, KM_USER0);
	memcpy(dd, map, sizeof(*dd));
	kunmap_atomic(map, KM_USER0);
	page_cache_release(page);
	return 0;
}

static int logfs_delete_dd(struct inode *dir, loff_t pos)
{
	/*
	 * Getting called with pos somewhere beyond eof is either a goofup
	 * within this file or means someone maliciously edited the
	 * (crc-protected) journal.
	 */
	BUG_ON(beyond_eof(dir, pos));
	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	log_dir(" Delete dentry (%lx, %llx)\n", dir->i_ino, pos);
	return logfs_delete(dir, pos, NULL);
}

/*
 * Cross-directory rename, target does not exist.  Just a little nasty.
 * Create a new dentry in the target dir, then remove the old dentry,
 * all the while taking care to remember our operation in the journal.
 */
static int logfs_rename_cross(struct inode *old_dir, struct dentry *old_dentry,
			      struct inode *new_dir, struct dentry *new_dentry)
{
	struct logfs_super *super = logfs_super(old_dir->i_sb);
	struct logfs_disk_dentry dd;
	struct logfs_transaction *ta;
	loff_t pos;
	int err;

627 628 629
	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
		dentry_unhash(new_dentry);

J
Joern Engel 已提交
630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833
	/* 1. locate source dd */
	err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
	if (err)
		return err;

	ta = kzalloc(sizeof(*ta), GFP_KERNEL);
	if (!ta)
		return -ENOMEM;

	ta->state = CROSS_RENAME_1;
	ta->dir = old_dir->i_ino;
	ta->pos = pos;

	/* 2. write target dd */
	mutex_lock(&super->s_dirop_mutex);
	logfs_add_transaction(new_dir, ta);
	err = logfs_write_dir(new_dir, new_dentry, old_dentry->d_inode);
	if (!err)
		err = write_inode(new_dir);

	if (err) {
		super->s_rename_dir = 0;
		super->s_rename_pos = 0;
		abort_transaction(new_dir, ta);
		goto out;
	}

	/* 3. remove source dd */
	ta->state = CROSS_RENAME_2;
	logfs_add_transaction(old_dir, ta);
	err = logfs_delete_dd(old_dir, pos);
	if (!err)
		err = write_inode(old_dir);
	LOGFS_BUG_ON(err, old_dir->i_sb);
out:
	mutex_unlock(&super->s_dirop_mutex);
	return err;
}

static int logfs_replace_inode(struct inode *dir, struct dentry *dentry,
		struct logfs_disk_dentry *dd, struct inode *inode)
{
	loff_t pos;
	int err;

	err = logfs_get_dd(dir, dentry, dd, &pos);
	if (err)
		return err;
	dd->ino = cpu_to_be64(inode->i_ino);
	dd->type = logfs_type(inode);

	err = write_dir(dir, dd, pos);
	if (err)
		return err;
	log_dir("Replace dentry (%lx, %llx) %s -> %llx\n", dir->i_ino, pos,
			dd->name, be64_to_cpu(dd->ino));
	return write_inode(dir);
}

/* Target dentry exists - the worst case.  We need to attach the source
 * inode to the target dentry, then remove the orphaned target inode and
 * source dentry.
 */
static int logfs_rename_target(struct inode *old_dir, struct dentry *old_dentry,
			       struct inode *new_dir, struct dentry *new_dentry)
{
	struct logfs_super *super = logfs_super(old_dir->i_sb);
	struct inode *old_inode = old_dentry->d_inode;
	struct inode *new_inode = new_dentry->d_inode;
	int isdir = S_ISDIR(old_inode->i_mode);
	struct logfs_disk_dentry dd;
	struct logfs_transaction *ta;
	loff_t pos;
	int err;

	BUG_ON(isdir != S_ISDIR(new_inode->i_mode));
	if (isdir) {
		if (!logfs_empty_dir(new_inode))
			return -ENOTEMPTY;
	}

	/* 1. locate source dd */
	err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
	if (err)
		return err;

	ta = kzalloc(sizeof(*ta), GFP_KERNEL);
	if (!ta)
		return -ENOMEM;

	ta->state = TARGET_RENAME_1;
	ta->dir = old_dir->i_ino;
	ta->pos = pos;
	ta->ino = new_inode->i_ino;

	/* 2. attach source inode to target dd */
	mutex_lock(&super->s_dirop_mutex);
	logfs_add_transaction(new_dir, ta);
	err = logfs_replace_inode(new_dir, new_dentry, &dd, old_inode);
	if (err) {
		super->s_rename_dir = 0;
		super->s_rename_pos = 0;
		super->s_victim_ino = 0;
		abort_transaction(new_dir, ta);
		goto out;
	}

	/* 3. remove source dd */
	ta->state = TARGET_RENAME_2;
	logfs_add_transaction(old_dir, ta);
	err = logfs_delete_dd(old_dir, pos);
	if (!err)
		err = write_inode(old_dir);
	LOGFS_BUG_ON(err, old_dir->i_sb);

	/* 4. remove target inode */
	ta->state = TARGET_RENAME_3;
	logfs_add_transaction(new_inode, ta);
	err = logfs_remove_inode(new_inode);

out:
	mutex_unlock(&super->s_dirop_mutex);
	return err;
}

static int logfs_rename(struct inode *old_dir, struct dentry *old_dentry,
			struct inode *new_dir, struct dentry *new_dentry)
{
	if (new_dentry->d_inode)
		return logfs_rename_target(old_dir, old_dentry,
					   new_dir, new_dentry);
	return logfs_rename_cross(old_dir, old_dentry, new_dir, new_dentry);
}

/* No locking done here, as this is called before .get_sb() returns. */
int logfs_replay_journal(struct super_block *sb)
{
	struct logfs_super *super = logfs_super(sb);
	struct inode *inode;
	u64 ino, pos;
	int err;

	if (super->s_victim_ino) {
		/* delete victim inode */
		ino = super->s_victim_ino;
		printk(KERN_INFO"LogFS: delete unmapped inode #%llx\n", ino);
		inode = logfs_iget(sb, ino);
		if (IS_ERR(inode))
			goto fail;

		LOGFS_BUG_ON(i_size_read(inode) > 0, sb);
		super->s_victim_ino = 0;
		err = logfs_remove_inode(inode);
		iput(inode);
		if (err) {
			super->s_victim_ino = ino;
			goto fail;
		}
	}
	if (super->s_rename_dir) {
		/* delete old dd from rename */
		ino = super->s_rename_dir;
		pos = super->s_rename_pos;
		printk(KERN_INFO"LogFS: delete unbacked dentry (%llx, %llx)\n",
				ino, pos);
		inode = logfs_iget(sb, ino);
		if (IS_ERR(inode))
			goto fail;

		super->s_rename_dir = 0;
		super->s_rename_pos = 0;
		err = logfs_delete_dd(inode, pos);
		iput(inode);
		if (err) {
			super->s_rename_dir = ino;
			super->s_rename_pos = pos;
			goto fail;
		}
	}
	return 0;
fail:
	LOGFS_BUG(sb);
	return -EIO;
}

const struct inode_operations logfs_symlink_iops = {
	.readlink	= generic_readlink,
	.follow_link	= page_follow_link_light,
};

const struct inode_operations logfs_dir_iops = {
	.create		= logfs_create,
	.link		= logfs_link,
	.lookup		= logfs_lookup,
	.mkdir		= logfs_mkdir,
	.mknod		= logfs_mknod,
	.rename		= logfs_rename,
	.rmdir		= logfs_rmdir,
	.permission	= logfs_permission,
	.symlink	= logfs_symlink,
	.unlink		= logfs_unlink,
};
const struct file_operations logfs_dir_fops = {
	.fsync		= logfs_fsync,
A
Arnd Bergmann 已提交
834
	.unlocked_ioctl	= logfs_ioctl,
J
Joern Engel 已提交
835 836
	.readdir	= logfs_readdir,
	.read		= generic_read_dir,
837
	.llseek		= default_llseek,
J
Joern Engel 已提交
838
};