tree-log.c 83.1 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
/*
 * Copyright (C) 2008 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * 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., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/sched.h>
#include "ctree.h"
#include "transaction.h"
#include "disk-io.h"
#include "locking.h"
#include "print-tree.h"
#include "compat.h"
26
#include "tree-log.h"
27 28 29 30 31 32 33 34 35 36

/* magic values for the inode_only field in btrfs_log_inode:
 *
 * LOG_INODE_ALL means to log everything
 * LOG_INODE_EXISTS means to log just enough to recreate the inode
 * during log replay
 */
#define LOG_INODE_ALL 0
#define LOG_INODE_EXISTS 1

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
/*
 * directory trouble cases
 *
 * 1) on rename or unlink, if the inode being unlinked isn't in the fsync
 * log, we must force a full commit before doing an fsync of the directory
 * where the unlink was done.
 * ---> record transid of last unlink/rename per directory
 *
 * mkdir foo/some_dir
 * normal commit
 * rename foo/some_dir foo2/some_dir
 * mkdir foo/some_dir
 * fsync foo/some_dir/some_file
 *
 * The fsync above will unlink the original some_dir without recording
 * it in its new location (foo2).  After a crash, some_dir will be gone
 * unless the fsync of some_file forces a full commit
 *
 * 2) we must log any new names for any file or dir that is in the fsync
 * log. ---> check inode while renaming/linking.
 *
 * 2a) we must log any new names for any file or dir during rename
 * when the directory they are being removed from was logged.
 * ---> check inode and old parent dir during rename
 *
 *  2a is actually the more important variant.  With the extra logging
 *  a crash might unlink the old name without recreating the new one
 *
 * 3) after a crash, we must go through any directories with a link count
 * of zero and redo the rm -rf
 *
 * mkdir f1/foo
 * normal commit
 * rm -rf f1/foo
 * fsync(f1)
 *
 * The directory f1 was fully removed from the FS, but fsync was never
 * called on f1, only its parent dir.  After a crash the rm -rf must
 * be replayed.  This must be able to recurse down the entire
 * directory tree.  The inode link count fixup code takes care of the
 * ugly details.
 */

80 81 82 83 84 85 86 87 88 89 90 91 92
/*
 * stages for the tree walking.  The first
 * stage (0) is to only pin down the blocks we find
 * the second stage (1) is to make sure that all the inodes
 * we find in the log are created in the subvolume.
 *
 * The last stage is to deal with directories and links and extents
 * and all the other fun semantics
 */
#define LOG_WALK_PIN_ONLY 0
#define LOG_WALK_REPLAY_INODES 1
#define LOG_WALK_REPLAY_ALL 2

93
static int btrfs_log_inode(struct btrfs_trans_handle *trans,
94 95
			     struct btrfs_root *root, struct inode *inode,
			     int inode_only);
96 97 98
static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root,
			     struct btrfs_path *path, u64 objectid);
99 100 101 102 103
static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
				       struct btrfs_root *root,
				       struct btrfs_root *log,
				       struct btrfs_path *path,
				       u64 dirid, int del_all);
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

/*
 * tree logging is a special write ahead log used to make sure that
 * fsyncs and O_SYNCs can happen without doing full tree commits.
 *
 * Full tree commits are expensive because they require commonly
 * modified blocks to be recowed, creating many dirty pages in the
 * extent tree an 4x-6x higher write load than ext3.
 *
 * Instead of doing a tree commit on every fsync, we use the
 * key ranges and transaction ids to find items for a given file or directory
 * that have changed in this transaction.  Those items are copied into
 * a special tree (one per subvolume root), that tree is written to disk
 * and then the fsync is considered complete.
 *
 * After a crash, items are copied out of the log-tree back into the
 * subvolume tree.  Any file data extents found are recorded in the extent
 * allocation tree, and the log-tree freed.
 *
 * The log tree is read three times, once to pin down all the extents it is
 * using in ram and once, once to create all the inodes logged in the tree
 * and once to do all the other items.
 */

/*
 * start a sub transaction and setup the log tree
 * this increments the log tree writer count to make the people
 * syncing the tree wait for us to finish
 */
static int start_log_trans(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root)
{
	int ret;
Y
Yan Zheng 已提交
137 138 139

	mutex_lock(&root->log_mutex);
	if (root->log_root) {
140 141 142 143 144 145 146
		if (!root->log_start_pid) {
			root->log_start_pid = current->pid;
			root->log_multiple_pids = false;
		} else if (root->log_start_pid != current->pid) {
			root->log_multiple_pids = true;
		}

Y
Yan Zheng 已提交
147 148 149 150 151
		root->log_batch++;
		atomic_inc(&root->log_writers);
		mutex_unlock(&root->log_mutex);
		return 0;
	}
152 153
	root->log_multiple_pids = false;
	root->log_start_pid = current->pid;
154 155 156 157 158 159 160 161 162 163
	mutex_lock(&root->fs_info->tree_log_mutex);
	if (!root->fs_info->log_root_tree) {
		ret = btrfs_init_log_root_tree(trans, root->fs_info);
		BUG_ON(ret);
	}
	if (!root->log_root) {
		ret = btrfs_add_log_tree(trans, root);
		BUG_ON(ret);
	}
	mutex_unlock(&root->fs_info->tree_log_mutex);
Y
Yan Zheng 已提交
164 165 166
	root->log_batch++;
	atomic_inc(&root->log_writers);
	mutex_unlock(&root->log_mutex);
167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182
	return 0;
}

/*
 * returns 0 if there was a log transaction running and we were able
 * to join, or returns -ENOENT if there were not transactions
 * in progress
 */
static int join_running_log_trans(struct btrfs_root *root)
{
	int ret = -ENOENT;

	smp_mb();
	if (!root->log_root)
		return -ENOENT;

Y
Yan Zheng 已提交
183
	mutex_lock(&root->log_mutex);
184 185
	if (root->log_root) {
		ret = 0;
Y
Yan Zheng 已提交
186
		atomic_inc(&root->log_writers);
187
	}
Y
Yan Zheng 已提交
188
	mutex_unlock(&root->log_mutex);
189 190 191
	return ret;
}

192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
/*
 * This either makes the current running log transaction wait
 * until you call btrfs_end_log_trans() or it makes any future
 * log transactions wait until you call btrfs_end_log_trans()
 */
int btrfs_pin_log_trans(struct btrfs_root *root)
{
	int ret = -ENOENT;

	mutex_lock(&root->log_mutex);
	atomic_inc(&root->log_writers);
	mutex_unlock(&root->log_mutex);
	return ret;
}

207 208 209 210
/*
 * indicate we're done making changes to the log tree
 * and wake up anyone waiting to do a sync
 */
211
int btrfs_end_log_trans(struct btrfs_root *root)
212
{
Y
Yan Zheng 已提交
213 214 215 216 217
	if (atomic_dec_and_test(&root->log_writers)) {
		smp_mb();
		if (waitqueue_active(&root->log_writer_wait))
			wake_up(&root->log_writer_wait);
	}
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
	return 0;
}


/*
 * the walk control struct is used to pass state down the chain when
 * processing the log tree.  The stage field tells us which part
 * of the log tree processing we are currently doing.  The others
 * are state fields used for that specific part
 */
struct walk_control {
	/* should we free the extent on disk when done?  This is used
	 * at transaction commit time while freeing a log tree
	 */
	int free;

	/* should we write out the extent buffer?  This is used
	 * while flushing the log tree to disk during a sync
	 */
	int write;

	/* should we wait for the extent buffer io to finish?  Also used
	 * while flushing the log tree to disk for a sync
	 */
	int wait;

	/* pin only walk, we record which extents on disk belong to the
	 * log trees
	 */
	int pin;

	/* what stage of the replay code we're currently in */
	int stage;

	/* the root we are currently replaying */
	struct btrfs_root *replay_dest;

	/* the trans handle for the current replay */
	struct btrfs_trans_handle *trans;

	/* the function that gets used to process blocks we find in the
	 * tree.  Note the extent_buffer might not be up to date when it is
	 * passed in, and it must be checked or read if you need the data
	 * inside it
	 */
	int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb,
			    struct walk_control *wc, u64 gen);
};

/*
 * process_func used to pin down extents, write them or wait on them
 */
static int process_one_buffer(struct btrfs_root *log,
			      struct extent_buffer *eb,
			      struct walk_control *wc, u64 gen)
{
J
Josef Bacik 已提交
274
	if (wc->pin)
275 276
		btrfs_pin_extent(log->fs_info->extent_root,
				 eb->start, eb->len, 0);
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

	if (btrfs_buffer_uptodate(eb, gen)) {
		if (wc->write)
			btrfs_write_tree_block(eb);
		if (wc->wait)
			btrfs_wait_tree_block_writeback(eb);
	}
	return 0;
}

/*
 * Item overwrite used by replay and tree logging.  eb, slot and key all refer
 * to the src data we are copying out.
 *
 * root is the tree we are copying into, and path is a scratch
 * path for use in this function (it should be released on entry and
 * will be released on exit).
 *
 * If the key is already in the destination tree the existing item is
 * overwritten.  If the existing item isn't big enough, it is extended.
 * If it is too large, it is truncated.
 *
 * If the key isn't in the destination yet, a new item is inserted.
 */
static noinline int overwrite_item(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct btrfs_path *path,
				   struct extent_buffer *eb, int slot,
				   struct btrfs_key *key)
{
	int ret;
	u32 item_size;
	u64 saved_i_size = 0;
	int save_old_i_size = 0;
	unsigned long src_ptr;
	unsigned long dst_ptr;
	int overwrite_root = 0;

	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
		overwrite_root = 1;

	item_size = btrfs_item_size_nr(eb, slot);
	src_ptr = btrfs_item_ptr_offset(eb, slot);

	/* look for the key in the destination tree */
	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
	if (ret == 0) {
		char *src_copy;
		char *dst_copy;
		u32 dst_size = btrfs_item_size_nr(path->nodes[0],
						  path->slots[0]);
		if (dst_size != item_size)
			goto insert;

		if (item_size == 0) {
			btrfs_release_path(root, path);
			return 0;
		}
		dst_copy = kmalloc(item_size, GFP_NOFS);
		src_copy = kmalloc(item_size, GFP_NOFS);

		read_extent_buffer(eb, src_copy, src_ptr, item_size);

		dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
		read_extent_buffer(path->nodes[0], dst_copy, dst_ptr,
				   item_size);
		ret = memcmp(dst_copy, src_copy, item_size);

		kfree(dst_copy);
		kfree(src_copy);
		/*
		 * they have the same contents, just return, this saves
		 * us from cowing blocks in the destination tree and doing
		 * extra writes that may not have been done by a previous
		 * sync
		 */
		if (ret == 0) {
			btrfs_release_path(root, path);
			return 0;
		}

	}
insert:
	btrfs_release_path(root, path);
	/* try to insert the key into the destination tree */
	ret = btrfs_insert_empty_item(trans, root, path,
				      key, item_size);

	/* make sure any existing item is the correct size */
	if (ret == -EEXIST) {
		u32 found_size;
		found_size = btrfs_item_size_nr(path->nodes[0],
						path->slots[0]);
		if (found_size > item_size) {
			btrfs_truncate_item(trans, root, path, item_size, 1);
		} else if (found_size < item_size) {
373 374
			ret = btrfs_extend_item(trans, root, path,
						item_size - found_size);
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
			BUG_ON(ret);
		}
	} else if (ret) {
		BUG();
	}
	dst_ptr = btrfs_item_ptr_offset(path->nodes[0],
					path->slots[0]);

	/* don't overwrite an existing inode if the generation number
	 * was logged as zero.  This is done when the tree logging code
	 * is just logging an inode to make sure it exists after recovery.
	 *
	 * Also, don't overwrite i_size on directories during replay.
	 * log replay inserts and removes directory items based on the
	 * state of the tree found in the subvolume, and i_size is modified
	 * as it goes
	 */
	if (key->type == BTRFS_INODE_ITEM_KEY && ret == -EEXIST) {
		struct btrfs_inode_item *src_item;
		struct btrfs_inode_item *dst_item;

		src_item = (struct btrfs_inode_item *)src_ptr;
		dst_item = (struct btrfs_inode_item *)dst_ptr;

		if (btrfs_inode_generation(eb, src_item) == 0)
			goto no_copy;

		if (overwrite_root &&
		    S_ISDIR(btrfs_inode_mode(eb, src_item)) &&
		    S_ISDIR(btrfs_inode_mode(path->nodes[0], dst_item))) {
			save_old_i_size = 1;
			saved_i_size = btrfs_inode_size(path->nodes[0],
							dst_item);
		}
	}

	copy_extent_buffer(path->nodes[0], eb, dst_ptr,
			   src_ptr, item_size);

	if (save_old_i_size) {
		struct btrfs_inode_item *dst_item;
		dst_item = (struct btrfs_inode_item *)dst_ptr;
		btrfs_set_inode_size(path->nodes[0], dst_item, saved_i_size);
	}

	/* make sure the generation is filled in */
	if (key->type == BTRFS_INODE_ITEM_KEY) {
		struct btrfs_inode_item *dst_item;
		dst_item = (struct btrfs_inode_item *)dst_ptr;
		if (btrfs_inode_generation(path->nodes[0], dst_item) == 0) {
			btrfs_set_inode_generation(path->nodes[0], dst_item,
						   trans->transid);
		}
	}
no_copy:
	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_release_path(root, path);
	return 0;
}

/*
 * simple helper to read an inode off the disk from a given root
 * This can only be called for subvolume roots and not for the log
 */
static noinline struct inode *read_one_inode(struct btrfs_root *root,
					     u64 objectid)
{
442
	struct btrfs_key key;
443 444
	struct inode *inode;

445 446 447 448 449 450 451
	key.objectid = objectid;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;
	inode = btrfs_iget(root->fs_info->sb, &key, root);
	if (IS_ERR(inode)) {
		inode = NULL;
	} else if (is_bad_inode(inode)) {
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
		iput(inode);
		inode = NULL;
	}
	return inode;
}

/* replays a single extent in 'eb' at 'slot' with 'key' into the
 * subvolume 'root'.  path is released on entry and should be released
 * on exit.
 *
 * extents in the log tree have not been allocated out of the extent
 * tree yet.  So, this completes the allocation, taking a reference
 * as required if the extent already exists or creating a new extent
 * if it isn't in the extent allocation tree yet.
 *
 * The extent is inserted into the file, dropping any existing extents
 * from the file that overlap the new one.
 */
static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_path *path,
				      struct extent_buffer *eb, int slot,
				      struct btrfs_key *key)
{
	int found_type;
	u64 mask = root->sectorsize - 1;
	u64 extent_end;
	u64 alloc_hint;
	u64 start = key->offset;
Y
Yan Zheng 已提交
481
	u64 saved_nbytes;
482 483 484 485 486 487 488 489
	struct btrfs_file_extent_item *item;
	struct inode *inode = NULL;
	unsigned long size;
	int ret = 0;

	item = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
	found_type = btrfs_file_extent_type(eb, item);

Y
Yan Zheng 已提交
490 491
	if (found_type == BTRFS_FILE_EXTENT_REG ||
	    found_type == BTRFS_FILE_EXTENT_PREALLOC)
492 493
		extent_end = start + btrfs_file_extent_num_bytes(eb, item);
	else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
C
Chris Mason 已提交
494
		size = btrfs_file_extent_inline_len(eb, item);
495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514
		extent_end = (start + size + mask) & ~mask;
	} else {
		ret = 0;
		goto out;
	}

	inode = read_one_inode(root, key->objectid);
	if (!inode) {
		ret = -EIO;
		goto out;
	}

	/*
	 * first check to see if we already have this extent in the
	 * file.  This must be done before the btrfs_drop_extents run
	 * so we don't try to drop this extent.
	 */
	ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
				       start, 0);

Y
Yan Zheng 已提交
515 516 517
	if (ret == 0 &&
	    (found_type == BTRFS_FILE_EXTENT_REG ||
	     found_type == BTRFS_FILE_EXTENT_PREALLOC)) {
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
		struct btrfs_file_extent_item cmp1;
		struct btrfs_file_extent_item cmp2;
		struct btrfs_file_extent_item *existing;
		struct extent_buffer *leaf;

		leaf = path->nodes[0];
		existing = btrfs_item_ptr(leaf, path->slots[0],
					  struct btrfs_file_extent_item);

		read_extent_buffer(eb, &cmp1, (unsigned long)item,
				   sizeof(cmp1));
		read_extent_buffer(leaf, &cmp2, (unsigned long)existing,
				   sizeof(cmp2));

		/*
		 * we already have a pointer to this exact extent,
		 * we don't have to do anything
		 */
		if (memcmp(&cmp1, &cmp2, sizeof(cmp1)) == 0) {
			btrfs_release_path(root, path);
			goto out;
		}
	}
	btrfs_release_path(root, path);

Y
Yan Zheng 已提交
543
	saved_nbytes = inode_get_bytes(inode);
544 545
	/* drop any overlapping extents */
	ret = btrfs_drop_extents(trans, root, inode,
C
Chris Mason 已提交
546
			 start, extent_end, extent_end, start, &alloc_hint, 1);
547 548
	BUG_ON(ret);

Y
Yan Zheng 已提交
549 550
	if (found_type == BTRFS_FILE_EXTENT_REG ||
	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
551
		u64 offset;
Y
Yan Zheng 已提交
552 553 554 555 556 557 558 559 560 561 562 563 564 565
		unsigned long dest_offset;
		struct btrfs_key ins;

		ret = btrfs_insert_empty_item(trans, root, path, key,
					      sizeof(*item));
		BUG_ON(ret);
		dest_offset = btrfs_item_ptr_offset(path->nodes[0],
						    path->slots[0]);
		copy_extent_buffer(path->nodes[0], eb, dest_offset,
				(unsigned long)item,  sizeof(*item));

		ins.objectid = btrfs_file_extent_disk_bytenr(eb, item);
		ins.offset = btrfs_file_extent_disk_num_bytes(eb, item);
		ins.type = BTRFS_EXTENT_ITEM_KEY;
566
		offset = key->offset - btrfs_file_extent_offset(eb, item);
Y
Yan Zheng 已提交
567 568 569 570 571 572 573 574 575 576 577 578 579 580

		if (ins.objectid > 0) {
			u64 csum_start;
			u64 csum_end;
			LIST_HEAD(ordered_sums);
			/*
			 * is this extent already allocated in the extent
			 * allocation tree?  If so, just add a reference
			 */
			ret = btrfs_lookup_extent(root, ins.objectid,
						ins.offset);
			if (ret == 0) {
				ret = btrfs_inc_extent_ref(trans, root,
						ins.objectid, ins.offset,
581 582
						0, root->root_key.objectid,
						key->objectid, offset);
Y
Yan Zheng 已提交
583 584 585 586 587
			} else {
				/*
				 * insert the extent pointer in the extent
				 * allocation tree
				 */
588 589 590
				ret = btrfs_alloc_logged_file_extent(trans,
						root, root->root_key.objectid,
						key->objectid, offset, &ins);
Y
Yan Zheng 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
				BUG_ON(ret);
			}
			btrfs_release_path(root, path);

			if (btrfs_file_extent_compression(eb, item)) {
				csum_start = ins.objectid;
				csum_end = csum_start + ins.offset;
			} else {
				csum_start = ins.objectid +
					btrfs_file_extent_offset(eb, item);
				csum_end = csum_start +
					btrfs_file_extent_num_bytes(eb, item);
			}

			ret = btrfs_lookup_csums_range(root->log_root,
						csum_start, csum_end - 1,
						&ordered_sums);
			BUG_ON(ret);
			while (!list_empty(&ordered_sums)) {
				struct btrfs_ordered_sum *sums;
				sums = list_entry(ordered_sums.next,
						struct btrfs_ordered_sum,
						list);
				ret = btrfs_csum_file_blocks(trans,
						root->fs_info->csum_root,
						sums);
				BUG_ON(ret);
				list_del(&sums->list);
				kfree(sums);
			}
		} else {
			btrfs_release_path(root, path);
		}
	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
		/* inline extents are easy, we just overwrite them */
		ret = overwrite_item(trans, root, path, eb, slot, key);
		BUG_ON(ret);
	}
629

Y
Yan Zheng 已提交
630
	inode_set_bytes(inode, saved_nbytes);
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
	btrfs_update_inode(trans, root, inode);
out:
	if (inode)
		iput(inode);
	return ret;
}

/*
 * when cleaning up conflicts between the directory names in the
 * subvolume, directory names in the log and directory names in the
 * inode back references, we may have to unlink inodes from directories.
 *
 * This is a helper function to do the unlink of a specific directory
 * item
 */
static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_path *path,
				      struct inode *dir,
				      struct btrfs_dir_item *di)
{
	struct inode *inode;
	char *name;
	int name_len;
	struct extent_buffer *leaf;
	struct btrfs_key location;
	int ret;

	leaf = path->nodes[0];

	btrfs_dir_item_key_to_cpu(leaf, di, &location);
	name_len = btrfs_dir_name_len(leaf, di);
	name = kmalloc(name_len, GFP_NOFS);
	read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len);
	btrfs_release_path(root, path);

	inode = read_one_inode(root, location.objectid);
	BUG_ON(!inode);

670 671
	ret = link_to_fixup_dir(trans, root, path, location.objectid);
	BUG_ON(ret);
672

673
	ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
674
	BUG_ON(ret);
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
	kfree(name);

	iput(inode);
	return ret;
}

/*
 * helper function to see if a given name and sequence number found
 * in an inode back reference are already in a directory and correctly
 * point to this inode
 */
static noinline int inode_in_dir(struct btrfs_root *root,
				 struct btrfs_path *path,
				 u64 dirid, u64 objectid, u64 index,
				 const char *name, int name_len)
{
	struct btrfs_dir_item *di;
	struct btrfs_key location;
	int match = 0;

	di = btrfs_lookup_dir_index_item(NULL, root, path, dirid,
					 index, name, name_len, 0);
	if (di && !IS_ERR(di)) {
		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
		if (location.objectid != objectid)
			goto out;
	} else
		goto out;
	btrfs_release_path(root, path);

	di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0);
	if (di && !IS_ERR(di)) {
		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
		if (location.objectid != objectid)
			goto out;
	} else
		goto out;
	match = 1;
out:
	btrfs_release_path(root, path);
	return match;
}

/*
 * helper function to check a log tree for a named back reference in
 * an inode.  This is used to decide if a back reference that is
 * found in the subvolume conflicts with what we find in the log.
 *
 * inode backreferences may have multiple refs in a single item,
 * during replay we process one reference at a time, and we don't
 * want to delete valid links to a file from the subvolume if that
 * link is also in the log.
 */
static noinline int backref_in_log(struct btrfs_root *log,
				   struct btrfs_key *key,
				   char *name, int namelen)
{
	struct btrfs_path *path;
	struct btrfs_inode_ref *ref;
	unsigned long ptr;
	unsigned long ptr_end;
	unsigned long name_ptr;
	int found_name_len;
	int item_size;
	int ret;
	int match = 0;

	path = btrfs_alloc_path();
	ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
	if (ret != 0)
		goto out;

	item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
	ptr_end = ptr + item_size;
	while (ptr < ptr_end) {
		ref = (struct btrfs_inode_ref *)ptr;
		found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
		if (found_name_len == namelen) {
			name_ptr = (unsigned long)(ref + 1);
			ret = memcmp_extent_buffer(path->nodes[0], name,
						   name_ptr, namelen);
			if (ret == 0) {
				match = 1;
				goto out;
			}
		}
		ptr = (unsigned long)(ref + 1) + found_name_len;
	}
out:
	btrfs_free_path(path);
	return match;
}


/*
 * replay one inode back reference item found in the log tree.
 * eb, slot and key refer to the buffer and key found in the log tree.
 * root is the destination we are replaying into, and path is for temp
 * use by this function.  (it should be released on return).
 */
static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
				  struct btrfs_root *root,
				  struct btrfs_root *log,
				  struct btrfs_path *path,
				  struct extent_buffer *eb, int slot,
				  struct btrfs_key *key)
{
	struct inode *dir;
	int ret;
	struct btrfs_key location;
	struct btrfs_inode_ref *ref;
	struct btrfs_dir_item *di;
	struct inode *inode;
	char *name;
	int namelen;
	unsigned long ref_ptr;
	unsigned long ref_end;

	location.objectid = key->objectid;
	location.type = BTRFS_INODE_ITEM_KEY;
	location.offset = 0;

	/*
	 * it is possible that we didn't log all the parent directories
	 * for a given inode.  If we don't find the dir, just don't
	 * copy the back ref in.  The link count fixup code will take
	 * care of the rest
	 */
	dir = read_one_inode(root, key->offset);
	if (!dir)
		return -ENOENT;

	inode = read_one_inode(root, key->objectid);
809
	BUG_ON(!inode);
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858

	ref_ptr = btrfs_item_ptr_offset(eb, slot);
	ref_end = ref_ptr + btrfs_item_size_nr(eb, slot);

again:
	ref = (struct btrfs_inode_ref *)ref_ptr;

	namelen = btrfs_inode_ref_name_len(eb, ref);
	name = kmalloc(namelen, GFP_NOFS);
	BUG_ON(!name);

	read_extent_buffer(eb, name, (unsigned long)(ref + 1), namelen);

	/* if we already have a perfect match, we're done */
	if (inode_in_dir(root, path, dir->i_ino, inode->i_ino,
			 btrfs_inode_ref_index(eb, ref),
			 name, namelen)) {
		goto out;
	}

	/*
	 * look for a conflicting back reference in the metadata.
	 * if we find one we have to unlink that name of the file
	 * before we add our new link.  Later on, we overwrite any
	 * existing back reference, and we don't want to create
	 * dangling pointers in the directory.
	 */
conflict_again:
	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
	if (ret == 0) {
		char *victim_name;
		int victim_name_len;
		struct btrfs_inode_ref *victim_ref;
		unsigned long ptr;
		unsigned long ptr_end;
		struct extent_buffer *leaf = path->nodes[0];

		/* are we trying to overwrite a back ref for the root directory
		 * if so, just jump out, we're done
		 */
		if (key->objectid == key->offset)
			goto out_nowrite;

		/* check all the names in this back reference to see
		 * if they are in the log.  if so, we allow them to stay
		 * otherwise they must be unlinked as a conflict
		 */
		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
		ptr_end = ptr + btrfs_item_size_nr(leaf, path->slots[0]);
C
Chris Mason 已提交
859
		while (ptr < ptr_end) {
860 861 862 863 864 865 866 867 868 869 870 871 872 873
			victim_ref = (struct btrfs_inode_ref *)ptr;
			victim_name_len = btrfs_inode_ref_name_len(leaf,
								   victim_ref);
			victim_name = kmalloc(victim_name_len, GFP_NOFS);
			BUG_ON(!victim_name);

			read_extent_buffer(leaf, victim_name,
					   (unsigned long)(victim_ref + 1),
					   victim_name_len);

			if (!backref_in_log(log, key, victim_name,
					    victim_name_len)) {
				btrfs_inc_nlink(inode);
				btrfs_release_path(root, path);
874

875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960
				ret = btrfs_unlink_inode(trans, root, dir,
							 inode, victim_name,
							 victim_name_len);
				kfree(victim_name);
				btrfs_release_path(root, path);
				goto conflict_again;
			}
			kfree(victim_name);
			ptr = (unsigned long)(victim_ref + 1) + victim_name_len;
		}
		BUG_ON(ret);
	}
	btrfs_release_path(root, path);

	/* look for a conflicting sequence number */
	di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
					 btrfs_inode_ref_index(eb, ref),
					 name, namelen, 0);
	if (di && !IS_ERR(di)) {
		ret = drop_one_dir_item(trans, root, path, dir, di);
		BUG_ON(ret);
	}
	btrfs_release_path(root, path);


	/* look for a conflicting name */
	di = btrfs_lookup_dir_item(trans, root, path, dir->i_ino,
				   name, namelen, 0);
	if (di && !IS_ERR(di)) {
		ret = drop_one_dir_item(trans, root, path, dir, di);
		BUG_ON(ret);
	}
	btrfs_release_path(root, path);

	/* insert our name */
	ret = btrfs_add_link(trans, dir, inode, name, namelen, 0,
			     btrfs_inode_ref_index(eb, ref));
	BUG_ON(ret);

	btrfs_update_inode(trans, root, inode);

out:
	ref_ptr = (unsigned long)(ref + 1) + namelen;
	kfree(name);
	if (ref_ptr < ref_end)
		goto again;

	/* finally write the back reference in the inode */
	ret = overwrite_item(trans, root, path, eb, slot, key);
	BUG_ON(ret);

out_nowrite:
	btrfs_release_path(root, path);
	iput(dir);
	iput(inode);
	return 0;
}

/*
 * There are a few corners where the link count of the file can't
 * be properly maintained during replay.  So, instead of adding
 * lots of complexity to the log code, we just scan the backrefs
 * for any file that has been through replay.
 *
 * The scan will update the link count on the inode to reflect the
 * number of back refs found.  If it goes down to zero, the iput
 * will free the inode.
 */
static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
					   struct btrfs_root *root,
					   struct inode *inode)
{
	struct btrfs_path *path;
	int ret;
	struct btrfs_key key;
	u64 nlink = 0;
	unsigned long ptr;
	unsigned long ptr_end;
	int name_len;

	key.objectid = inode->i_ino;
	key.type = BTRFS_INODE_REF_KEY;
	key.offset = (u64)-1;

	path = btrfs_alloc_path();

C
Chris Mason 已提交
961
	while (1) {
962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		if (ret < 0)
			break;
		if (ret > 0) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}
		btrfs_item_key_to_cpu(path->nodes[0], &key,
				      path->slots[0]);
		if (key.objectid != inode->i_ino ||
		    key.type != BTRFS_INODE_REF_KEY)
			break;
		ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
		ptr_end = ptr + btrfs_item_size_nr(path->nodes[0],
						   path->slots[0]);
C
Chris Mason 已提交
978
		while (ptr < ptr_end) {
979 980 981 982 983 984 985 986 987 988 989 990 991 992
			struct btrfs_inode_ref *ref;

			ref = (struct btrfs_inode_ref *)ptr;
			name_len = btrfs_inode_ref_name_len(path->nodes[0],
							    ref);
			ptr = (unsigned long)(ref + 1) + name_len;
			nlink++;
		}

		if (key.offset == 0)
			break;
		key.offset--;
		btrfs_release_path(root, path);
	}
993
	btrfs_release_path(root, path);
994 995 996 997
	if (nlink != inode->i_nlink) {
		inode->i_nlink = nlink;
		btrfs_update_inode(trans, root, inode);
	}
998
	BTRFS_I(inode)->index_cnt = (u64)-1;
999

1000 1001 1002 1003 1004 1005 1006
	if (inode->i_nlink == 0 && S_ISDIR(inode->i_mode)) {
		ret = replay_dir_deletes(trans, root, NULL, path,
					 inode->i_ino, 1);
		BUG_ON(ret);
	}
	btrfs_free_path(path);

1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020
	return 0;
}

static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
					    struct btrfs_root *root,
					    struct btrfs_path *path)
{
	int ret;
	struct btrfs_key key;
	struct inode *inode;

	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
	key.type = BTRFS_ORPHAN_ITEM_KEY;
	key.offset = (u64)-1;
C
Chris Mason 已提交
1021
	while (1) {
1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048
		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
		if (ret < 0)
			break;

		if (ret == 1) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}

		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid != BTRFS_TREE_LOG_FIXUP_OBJECTID ||
		    key.type != BTRFS_ORPHAN_ITEM_KEY)
			break;

		ret = btrfs_del_item(trans, root, path);
		BUG_ON(ret);

		btrfs_release_path(root, path);
		inode = read_one_inode(root, key.offset);
		BUG_ON(!inode);

		ret = fixup_inode_link_count(trans, root, inode);
		BUG_ON(ret);

		iput(inode);

1049 1050 1051 1052 1053 1054
		/*
		 * fixup on a directory may create new entries,
		 * make sure we always look for the highset possible
		 * offset
		 */
		key.offset = (u64)-1;
1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158
	}
	btrfs_release_path(root, path);
	return 0;
}


/*
 * record a given inode in the fixup dir so we can check its link
 * count when replay is done.  The link count is incremented here
 * so the inode won't go away until we check it
 */
static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_path *path,
				      u64 objectid)
{
	struct btrfs_key key;
	int ret = 0;
	struct inode *inode;

	inode = read_one_inode(root, objectid);
	BUG_ON(!inode);

	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
	key.offset = objectid;

	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);

	btrfs_release_path(root, path);
	if (ret == 0) {
		btrfs_inc_nlink(inode);
		btrfs_update_inode(trans, root, inode);
	} else if (ret == -EEXIST) {
		ret = 0;
	} else {
		BUG();
	}
	iput(inode);

	return ret;
}

/*
 * when replaying the log for a directory, we only insert names
 * for inodes that actually exist.  This means an fsync on a directory
 * does not implicitly fsync all the new files in it
 */
static noinline int insert_one_name(struct btrfs_trans_handle *trans,
				    struct btrfs_root *root,
				    struct btrfs_path *path,
				    u64 dirid, u64 index,
				    char *name, int name_len, u8 type,
				    struct btrfs_key *location)
{
	struct inode *inode;
	struct inode *dir;
	int ret;

	inode = read_one_inode(root, location->objectid);
	if (!inode)
		return -ENOENT;

	dir = read_one_inode(root, dirid);
	if (!dir) {
		iput(inode);
		return -EIO;
	}
	ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index);

	/* FIXME, put inode into FIXUP list */

	iput(inode);
	iput(dir);
	return ret;
}

/*
 * take a single entry in a log directory item and replay it into
 * the subvolume.
 *
 * if a conflicting item exists in the subdirectory already,
 * the inode it points to is unlinked and put into the link count
 * fix up tree.
 *
 * If a name from the log points to a file or directory that does
 * not exist in the FS, it is skipped.  fsyncs on directories
 * do not force down inodes inside that directory, just changes to the
 * names or unlinks in a directory.
 */
static noinline int replay_one_name(struct btrfs_trans_handle *trans,
				    struct btrfs_root *root,
				    struct btrfs_path *path,
				    struct extent_buffer *eb,
				    struct btrfs_dir_item *di,
				    struct btrfs_key *key)
{
	char *name;
	int name_len;
	struct btrfs_dir_item *dst_di;
	struct btrfs_key found_key;
	struct btrfs_key log_key;
	struct inode *dir;
	u8 log_type;
C
Chris Mason 已提交
1159
	int exists;
1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171
	int ret;

	dir = read_one_inode(root, key->objectid);
	BUG_ON(!dir);

	name_len = btrfs_dir_name_len(eb, di);
	name = kmalloc(name_len, GFP_NOFS);
	log_type = btrfs_dir_type(eb, di);
	read_extent_buffer(eb, name, (unsigned long)(di + 1),
		   name_len);

	btrfs_dir_item_key_to_cpu(eb, di, &log_key);
C
Chris Mason 已提交
1172 1173 1174 1175 1176 1177 1178
	exists = btrfs_lookup_inode(trans, root, path, &log_key, 0);
	if (exists == 0)
		exists = 1;
	else
		exists = 0;
	btrfs_release_path(root, path);

1179 1180 1181
	if (key->type == BTRFS_DIR_ITEM_KEY) {
		dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid,
				       name, name_len, 1);
C
Chris Mason 已提交
1182
	} else if (key->type == BTRFS_DIR_INDEX_KEY) {
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
		dst_di = btrfs_lookup_dir_index_item(trans, root, path,
						     key->objectid,
						     key->offset, name,
						     name_len, 1);
	} else {
		BUG();
	}
	if (!dst_di || IS_ERR(dst_di)) {
		/* we need a sequence number to insert, so we only
		 * do inserts for the BTRFS_DIR_INDEX_KEY types
		 */
		if (key->type != BTRFS_DIR_INDEX_KEY)
			goto out;
		goto insert;
	}

	btrfs_dir_item_key_to_cpu(path->nodes[0], dst_di, &found_key);
	/* the existing item matches the logged item */
	if (found_key.objectid == log_key.objectid &&
	    found_key.type == log_key.type &&
	    found_key.offset == log_key.offset &&
	    btrfs_dir_type(path->nodes[0], dst_di) == log_type) {
		goto out;
	}

	/*
	 * don't drop the conflicting directory entry if the inode
	 * for the new entry doesn't exist
	 */
C
Chris Mason 已提交
1212
	if (!exists)
1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
		goto out;

	ret = drop_one_dir_item(trans, root, path, dir, dst_di);
	BUG_ON(ret);

	if (key->type == BTRFS_DIR_INDEX_KEY)
		goto insert;
out:
	btrfs_release_path(root, path);
	kfree(name);
	iput(dir);
	return 0;

insert:
	btrfs_release_path(root, path);
	ret = insert_one_name(trans, root, path, key->objectid, key->offset,
			      name, name_len, log_type, &log_key);

S
Stoyan Gaydarov 已提交
1231
	BUG_ON(ret && ret != -ENOENT);
1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255
	goto out;
}

/*
 * find all the names in a directory item and reconcile them into
 * the subvolume.  Only BTRFS_DIR_ITEM_KEY types will have more than
 * one name in a directory item, but the same code gets used for
 * both directory index types
 */
static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
					struct btrfs_root *root,
					struct btrfs_path *path,
					struct extent_buffer *eb, int slot,
					struct btrfs_key *key)
{
	int ret;
	u32 item_size = btrfs_item_size_nr(eb, slot);
	struct btrfs_dir_item *di;
	int name_len;
	unsigned long ptr;
	unsigned long ptr_end;

	ptr = btrfs_item_ptr_offset(eb, slot);
	ptr_end = ptr + item_size;
C
Chris Mason 已提交
1256
	while (ptr < ptr_end) {
1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381
		di = (struct btrfs_dir_item *)ptr;
		name_len = btrfs_dir_name_len(eb, di);
		ret = replay_one_name(trans, root, path, eb, di, key);
		BUG_ON(ret);
		ptr = (unsigned long)(di + 1);
		ptr += name_len;
	}
	return 0;
}

/*
 * directory replay has two parts.  There are the standard directory
 * items in the log copied from the subvolume, and range items
 * created in the log while the subvolume was logged.
 *
 * The range items tell us which parts of the key space the log
 * is authoritative for.  During replay, if a key in the subvolume
 * directory is in a logged range item, but not actually in the log
 * that means it was deleted from the directory before the fsync
 * and should be removed.
 */
static noinline int find_dir_range(struct btrfs_root *root,
				   struct btrfs_path *path,
				   u64 dirid, int key_type,
				   u64 *start_ret, u64 *end_ret)
{
	struct btrfs_key key;
	u64 found_end;
	struct btrfs_dir_log_item *item;
	int ret;
	int nritems;

	if (*start_ret == (u64)-1)
		return 1;

	key.objectid = dirid;
	key.type = key_type;
	key.offset = *start_ret;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto out;
	if (ret > 0) {
		if (path->slots[0] == 0)
			goto out;
		path->slots[0]--;
	}
	if (ret != 0)
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	if (key.type != key_type || key.objectid != dirid) {
		ret = 1;
		goto next;
	}
	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_dir_log_item);
	found_end = btrfs_dir_log_end(path->nodes[0], item);

	if (*start_ret >= key.offset && *start_ret <= found_end) {
		ret = 0;
		*start_ret = key.offset;
		*end_ret = found_end;
		goto out;
	}
	ret = 1;
next:
	/* check the next slot in the tree to see if it is a valid item */
	nritems = btrfs_header_nritems(path->nodes[0]);
	if (path->slots[0] >= nritems) {
		ret = btrfs_next_leaf(root, path);
		if (ret)
			goto out;
	} else {
		path->slots[0]++;
	}

	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	if (key.type != key_type || key.objectid != dirid) {
		ret = 1;
		goto out;
	}
	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_dir_log_item);
	found_end = btrfs_dir_log_end(path->nodes[0], item);
	*start_ret = key.offset;
	*end_ret = found_end;
	ret = 0;
out:
	btrfs_release_path(root, path);
	return ret;
}

/*
 * this looks for a given directory item in the log.  If the directory
 * item is not in the log, the item is removed and the inode it points
 * to is unlinked
 */
static noinline int check_item_in_log(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_root *log,
				      struct btrfs_path *path,
				      struct btrfs_path *log_path,
				      struct inode *dir,
				      struct btrfs_key *dir_key)
{
	int ret;
	struct extent_buffer *eb;
	int slot;
	u32 item_size;
	struct btrfs_dir_item *di;
	struct btrfs_dir_item *log_di;
	int name_len;
	unsigned long ptr;
	unsigned long ptr_end;
	char *name;
	struct inode *inode;
	struct btrfs_key location;

again:
	eb = path->nodes[0];
	slot = path->slots[0];
	item_size = btrfs_item_size_nr(eb, slot);
	ptr = btrfs_item_ptr_offset(eb, slot);
	ptr_end = ptr + item_size;
C
Chris Mason 已提交
1382
	while (ptr < ptr_end) {
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392
		di = (struct btrfs_dir_item *)ptr;
		name_len = btrfs_dir_name_len(eb, di);
		name = kmalloc(name_len, GFP_NOFS);
		if (!name) {
			ret = -ENOMEM;
			goto out;
		}
		read_extent_buffer(eb, name, (unsigned long)(di + 1),
				  name_len);
		log_di = NULL;
1393
		if (log && dir_key->type == BTRFS_DIR_ITEM_KEY) {
1394 1395 1396
			log_di = btrfs_lookup_dir_item(trans, log, log_path,
						       dir_key->objectid,
						       name, name_len, 0);
1397
		} else if (log && dir_key->type == BTRFS_DIR_INDEX_KEY) {
1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457
			log_di = btrfs_lookup_dir_index_item(trans, log,
						     log_path,
						     dir_key->objectid,
						     dir_key->offset,
						     name, name_len, 0);
		}
		if (!log_di || IS_ERR(log_di)) {
			btrfs_dir_item_key_to_cpu(eb, di, &location);
			btrfs_release_path(root, path);
			btrfs_release_path(log, log_path);
			inode = read_one_inode(root, location.objectid);
			BUG_ON(!inode);

			ret = link_to_fixup_dir(trans, root,
						path, location.objectid);
			BUG_ON(ret);
			btrfs_inc_nlink(inode);
			ret = btrfs_unlink_inode(trans, root, dir, inode,
						 name, name_len);
			BUG_ON(ret);
			kfree(name);
			iput(inode);

			/* there might still be more names under this key
			 * check and repeat if required
			 */
			ret = btrfs_search_slot(NULL, root, dir_key, path,
						0, 0);
			if (ret == 0)
				goto again;
			ret = 0;
			goto out;
		}
		btrfs_release_path(log, log_path);
		kfree(name);

		ptr = (unsigned long)(di + 1);
		ptr += name_len;
	}
	ret = 0;
out:
	btrfs_release_path(root, path);
	btrfs_release_path(log, log_path);
	return ret;
}

/*
 * deletion replay happens before we copy any new directory items
 * out of the log or out of backreferences from inodes.  It
 * scans the log to find ranges of keys that log is authoritative for,
 * and then scans the directory to find items in those ranges that are
 * not present in the log.
 *
 * Anything we don't find in the log is unlinked and removed from the
 * directory.
 */
static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
				       struct btrfs_root *root,
				       struct btrfs_root *log,
				       struct btrfs_path *path,
1458
				       u64 dirid, int del_all)
1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486
{
	u64 range_start;
	u64 range_end;
	int key_type = BTRFS_DIR_LOG_ITEM_KEY;
	int ret = 0;
	struct btrfs_key dir_key;
	struct btrfs_key found_key;
	struct btrfs_path *log_path;
	struct inode *dir;

	dir_key.objectid = dirid;
	dir_key.type = BTRFS_DIR_ITEM_KEY;
	log_path = btrfs_alloc_path();
	if (!log_path)
		return -ENOMEM;

	dir = read_one_inode(root, dirid);
	/* it isn't an error if the inode isn't there, that can happen
	 * because we replay the deletes before we copy in the inode item
	 * from the log
	 */
	if (!dir) {
		btrfs_free_path(log_path);
		return 0;
	}
again:
	range_start = 0;
	range_end = 0;
C
Chris Mason 已提交
1487
	while (1) {
1488 1489 1490 1491 1492 1493 1494 1495
		if (del_all)
			range_end = (u64)-1;
		else {
			ret = find_dir_range(log, path, dirid, key_type,
					     &range_start, &range_end);
			if (ret != 0)
				break;
		}
1496 1497

		dir_key.offset = range_start;
C
Chris Mason 已提交
1498
		while (1) {
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520
			int nritems;
			ret = btrfs_search_slot(NULL, root, &dir_key, path,
						0, 0);
			if (ret < 0)
				goto out;

			nritems = btrfs_header_nritems(path->nodes[0]);
			if (path->slots[0] >= nritems) {
				ret = btrfs_next_leaf(root, path);
				if (ret)
					break;
			}
			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
					      path->slots[0]);
			if (found_key.objectid != dirid ||
			    found_key.type != dir_key.type)
				goto next_type;

			if (found_key.offset > range_end)
				break;

			ret = check_item_in_log(trans, root, log, path,
1521 1522
						log_path, dir,
						&found_key);
1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598
			BUG_ON(ret);
			if (found_key.offset == (u64)-1)
				break;
			dir_key.offset = found_key.offset + 1;
		}
		btrfs_release_path(root, path);
		if (range_end == (u64)-1)
			break;
		range_start = range_end + 1;
	}

next_type:
	ret = 0;
	if (key_type == BTRFS_DIR_LOG_ITEM_KEY) {
		key_type = BTRFS_DIR_LOG_INDEX_KEY;
		dir_key.type = BTRFS_DIR_INDEX_KEY;
		btrfs_release_path(root, path);
		goto again;
	}
out:
	btrfs_release_path(root, path);
	btrfs_free_path(log_path);
	iput(dir);
	return ret;
}

/*
 * the process_func used to replay items from the log tree.  This
 * gets called in two different stages.  The first stage just looks
 * for inodes and makes sure they are all copied into the subvolume.
 *
 * The second stage copies all the other item types from the log into
 * the subvolume.  The two stage approach is slower, but gets rid of
 * lots of complexity around inodes referencing other inodes that exist
 * only in the log (references come from either directory items or inode
 * back refs).
 */
static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
			     struct walk_control *wc, u64 gen)
{
	int nritems;
	struct btrfs_path *path;
	struct btrfs_root *root = wc->replay_dest;
	struct btrfs_key key;
	u32 item_size;
	int level;
	int i;
	int ret;

	btrfs_read_buffer(eb, gen);

	level = btrfs_header_level(eb);

	if (level != 0)
		return 0;

	path = btrfs_alloc_path();
	BUG_ON(!path);

	nritems = btrfs_header_nritems(eb);
	for (i = 0; i < nritems; i++) {
		btrfs_item_key_to_cpu(eb, &key, i);
		item_size = btrfs_item_size_nr(eb, i);

		/* inode keys are done during the first stage */
		if (key.type == BTRFS_INODE_ITEM_KEY &&
		    wc->stage == LOG_WALK_REPLAY_INODES) {
			struct inode *inode;
			struct btrfs_inode_item *inode_item;
			u32 mode;

			inode_item = btrfs_item_ptr(eb, i,
					    struct btrfs_inode_item);
			mode = btrfs_inode_mode(eb, inode_item);
			if (S_ISDIR(mode)) {
				ret = replay_dir_deletes(wc->trans,
1599
					 root, log, path, key.objectid, 0);
1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617
				BUG_ON(ret);
			}
			ret = overwrite_item(wc->trans, root, path,
					     eb, i, &key);
			BUG_ON(ret);

			/* for regular files, truncate away
			 * extents past the new EOF
			 */
			if (S_ISREG(mode)) {
				inode = read_one_inode(root,
						       key.objectid);
				BUG_ON(!inode);

				ret = btrfs_truncate_inode_items(wc->trans,
					root, inode, inode->i_size,
					BTRFS_EXTENT_DATA_KEY);
				BUG_ON(ret);
1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628

				/* if the nlink count is zero here, the iput
				 * will free the inode.  We bump it to make
				 * sure it doesn't get freed until the link
				 * count fixup is done
				 */
				if (inode->i_nlink == 0) {
					btrfs_inc_nlink(inode);
					btrfs_update_inode(wc->trans,
							   root, inode);
				}
1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661
				iput(inode);
			}
			ret = link_to_fixup_dir(wc->trans, root,
						path, key.objectid);
			BUG_ON(ret);
		}
		if (wc->stage < LOG_WALK_REPLAY_ALL)
			continue;

		/* these keys are simply copied */
		if (key.type == BTRFS_XATTR_ITEM_KEY) {
			ret = overwrite_item(wc->trans, root, path,
					     eb, i, &key);
			BUG_ON(ret);
		} else if (key.type == BTRFS_INODE_REF_KEY) {
			ret = add_inode_ref(wc->trans, root, log, path,
					    eb, i, &key);
			BUG_ON(ret && ret != -ENOENT);
		} else if (key.type == BTRFS_EXTENT_DATA_KEY) {
			ret = replay_one_extent(wc->trans, root, path,
						eb, i, &key);
			BUG_ON(ret);
		} else if (key.type == BTRFS_DIR_ITEM_KEY ||
			   key.type == BTRFS_DIR_INDEX_KEY) {
			ret = replay_one_dir_item(wc->trans, root, path,
						  eb, i, &key);
			BUG_ON(ret);
		}
	}
	btrfs_free_path(path);
	return 0;
}

C
Chris Mason 已提交
1662
static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
				   struct btrfs_root *root,
				   struct btrfs_path *path, int *level,
				   struct walk_control *wc)
{
	u64 root_owner;
	u64 root_gen;
	u64 bytenr;
	u64 ptr_gen;
	struct extent_buffer *next;
	struct extent_buffer *cur;
	struct extent_buffer *parent;
	u32 blocksize;
	int ret = 0;

	WARN_ON(*level < 0);
	WARN_ON(*level >= BTRFS_MAX_LEVEL);

C
Chris Mason 已提交
1680
	while (*level > 0) {
1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710
		WARN_ON(*level < 0);
		WARN_ON(*level >= BTRFS_MAX_LEVEL);
		cur = path->nodes[*level];

		if (btrfs_header_level(cur) != *level)
			WARN_ON(1);

		if (path->slots[*level] >=
		    btrfs_header_nritems(cur))
			break;

		bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
		ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
		blocksize = btrfs_level_size(root, *level - 1);

		parent = path->nodes[*level];
		root_owner = btrfs_header_owner(parent);
		root_gen = btrfs_header_generation(parent);

		next = btrfs_find_create_tree_block(root, bytenr, blocksize);

		wc->process_func(root, next, wc, ptr_gen);

		if (*level == 1) {
			path->slots[*level]++;
			if (wc->free) {
				btrfs_read_buffer(next, ptr_gen);

				btrfs_tree_lock(next);
				clean_tree_block(trans, root, next);
1711
				btrfs_set_lock_blocking(next);
1712 1713 1714 1715 1716
				btrfs_wait_tree_block_writeback(next);
				btrfs_tree_unlock(next);

				WARN_ON(root_owner !=
					BTRFS_TREE_LOG_OBJECTID);
1717 1718
				ret = btrfs_free_reserved_extent(root,
							 bytenr, blocksize);
1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736
				BUG_ON(ret);
			}
			free_extent_buffer(next);
			continue;
		}
		btrfs_read_buffer(next, ptr_gen);

		WARN_ON(*level <= 0);
		if (path->nodes[*level-1])
			free_extent_buffer(path->nodes[*level-1]);
		path->nodes[*level-1] = next;
		*level = btrfs_header_level(next);
		path->slots[*level] = 0;
		cond_resched();
	}
	WARN_ON(*level < 0);
	WARN_ON(*level >= BTRFS_MAX_LEVEL);

C
Chris Mason 已提交
1737
	if (path->nodes[*level] == root->node)
1738
		parent = path->nodes[*level];
C
Chris Mason 已提交
1739
	else
1740
		parent = path->nodes[*level + 1];
C
Chris Mason 已提交
1741

1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754
	bytenr = path->nodes[*level]->start;

	blocksize = btrfs_level_size(root, *level);
	root_owner = btrfs_header_owner(parent);
	root_gen = btrfs_header_generation(parent);

	wc->process_func(root, path->nodes[*level], wc,
			 btrfs_header_generation(path->nodes[*level]));

	if (wc->free) {
		next = path->nodes[*level];
		btrfs_tree_lock(next);
		clean_tree_block(trans, root, next);
1755
		btrfs_set_lock_blocking(next);
1756 1757 1758 1759
		btrfs_wait_tree_block_writeback(next);
		btrfs_tree_unlock(next);

		WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
1760
		ret = btrfs_free_reserved_extent(root, bytenr, blocksize);
1761 1762 1763 1764 1765 1766 1767 1768 1769 1770
		BUG_ON(ret);
	}
	free_extent_buffer(path->nodes[*level]);
	path->nodes[*level] = NULL;
	*level += 1;

	cond_resched();
	return 0;
}

C
Chris Mason 已提交
1771
static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
1772 1773 1774 1775 1776 1777 1778 1779 1780 1781
				 struct btrfs_root *root,
				 struct btrfs_path *path, int *level,
				 struct walk_control *wc)
{
	u64 root_owner;
	u64 root_gen;
	int i;
	int slot;
	int ret;

C
Chris Mason 已提交
1782
	for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) {
1783 1784 1785 1786 1787 1788 1789 1790 1791
		slot = path->slots[i];
		if (slot < btrfs_header_nritems(path->nodes[i]) - 1) {
			struct extent_buffer *node;
			node = path->nodes[i];
			path->slots[i]++;
			*level = i;
			WARN_ON(*level == 0);
			return 0;
		} else {
Z
Zheng Yan 已提交
1792 1793 1794 1795 1796 1797 1798 1799
			struct extent_buffer *parent;
			if (path->nodes[*level] == root->node)
				parent = path->nodes[*level];
			else
				parent = path->nodes[*level + 1];

			root_owner = btrfs_header_owner(parent);
			root_gen = btrfs_header_generation(parent);
1800 1801 1802 1803 1804 1805 1806 1807 1808
			wc->process_func(root, path->nodes[*level], wc,
				 btrfs_header_generation(path->nodes[*level]));
			if (wc->free) {
				struct extent_buffer *next;

				next = path->nodes[*level];

				btrfs_tree_lock(next);
				clean_tree_block(trans, root, next);
1809
				btrfs_set_lock_blocking(next);
1810 1811 1812 1813
				btrfs_wait_tree_block_writeback(next);
				btrfs_tree_unlock(next);

				WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
1814
				ret = btrfs_free_reserved_extent(root,
1815
						path->nodes[*level]->start,
1816
						path->nodes[*level]->len);
1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850
				BUG_ON(ret);
			}
			free_extent_buffer(path->nodes[*level]);
			path->nodes[*level] = NULL;
			*level = i + 1;
		}
	}
	return 1;
}

/*
 * drop the reference count on the tree rooted at 'snap'.  This traverses
 * the tree freeing any blocks that have a ref count of zero after being
 * decremented.
 */
static int walk_log_tree(struct btrfs_trans_handle *trans,
			 struct btrfs_root *log, struct walk_control *wc)
{
	int ret = 0;
	int wret;
	int level;
	struct btrfs_path *path;
	int i;
	int orig_level;

	path = btrfs_alloc_path();
	BUG_ON(!path);

	level = btrfs_header_level(log->node);
	orig_level = level;
	path->nodes[level] = log->node;
	extent_buffer_get(log->node);
	path->slots[level] = 0;

C
Chris Mason 已提交
1851
	while (1) {
1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875
		wret = walk_down_log_tree(trans, log, path, &level, wc);
		if (wret > 0)
			break;
		if (wret < 0)
			ret = wret;

		wret = walk_up_log_tree(trans, log, path, &level, wc);
		if (wret > 0)
			break;
		if (wret < 0)
			ret = wret;
	}

	/* was the root node processed? if not, catch it here */
	if (path->nodes[orig_level]) {
		wc->process_func(log, path->nodes[orig_level], wc,
			 btrfs_header_generation(path->nodes[orig_level]));
		if (wc->free) {
			struct extent_buffer *next;

			next = path->nodes[orig_level];

			btrfs_tree_lock(next);
			clean_tree_block(trans, log, next);
1876
			btrfs_set_lock_blocking(next);
1877 1878 1879 1880 1881
			btrfs_wait_tree_block_writeback(next);
			btrfs_tree_unlock(next);

			WARN_ON(log->root_key.objectid !=
				BTRFS_TREE_LOG_OBJECTID);
1882 1883
			ret = btrfs_free_reserved_extent(log, next->start,
							 next->len);
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897
			BUG_ON(ret);
		}
	}

	for (i = 0; i <= orig_level; i++) {
		if (path->nodes[i]) {
			free_extent_buffer(path->nodes[i]);
			path->nodes[i] = NULL;
		}
	}
	btrfs_free_path(path);
	return ret;
}

Y
Yan Zheng 已提交
1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917
/*
 * helper function to update the item for a given subvolumes log root
 * in the tree of log roots
 */
static int update_log_root(struct btrfs_trans_handle *trans,
			   struct btrfs_root *log)
{
	int ret;

	if (log->log_transid == 1) {
		/* insert root item on the first sync */
		ret = btrfs_insert_root(trans, log->fs_info->log_root_tree,
				&log->root_key, &log->root_item);
	} else {
		ret = btrfs_update_root(trans, log->fs_info->log_root_tree,
				&log->root_key, &log->root_item);
	}
	return ret;
}

1918 1919
static int wait_log_commit(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root, unsigned long transid)
1920 1921
{
	DEFINE_WAIT(wait);
Y
Yan Zheng 已提交
1922
	int index = transid % 2;
1923

Y
Yan Zheng 已提交
1924 1925 1926 1927 1928
	/*
	 * we only allow two pending log transactions at a time,
	 * so we know that if ours is more than 2 older than the
	 * current transaction, we're done
	 */
1929
	do {
Y
Yan Zheng 已提交
1930 1931 1932
		prepare_to_wait(&root->log_commit_wait[index],
				&wait, TASK_UNINTERRUPTIBLE);
		mutex_unlock(&root->log_mutex);
1933 1934 1935

		if (root->fs_info->last_trans_log_full_commit !=
		    trans->transid && root->log_transid < transid + 2 &&
Y
Yan Zheng 已提交
1936 1937
		    atomic_read(&root->log_commit[index]))
			schedule();
1938

Y
Yan Zheng 已提交
1939 1940 1941 1942 1943 1944 1945
		finish_wait(&root->log_commit_wait[index], &wait);
		mutex_lock(&root->log_mutex);
	} while (root->log_transid < transid + 2 &&
		 atomic_read(&root->log_commit[index]));
	return 0;
}

1946 1947
static int wait_for_writer(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root)
Y
Yan Zheng 已提交
1948 1949 1950 1951 1952 1953
{
	DEFINE_WAIT(wait);
	while (atomic_read(&root->log_writers)) {
		prepare_to_wait(&root->log_writer_wait,
				&wait, TASK_UNINTERRUPTIBLE);
		mutex_unlock(&root->log_mutex);
1954 1955
		if (root->fs_info->last_trans_log_full_commit !=
		    trans->transid && atomic_read(&root->log_writers))
1956
			schedule();
Y
Yan Zheng 已提交
1957 1958 1959
		mutex_lock(&root->log_mutex);
		finish_wait(&root->log_writer_wait, &wait);
	}
1960 1961 1962 1963 1964 1965
	return 0;
}

/*
 * btrfs_sync_log does sends a given tree log down to the disk and
 * updates the super blocks to record it.  When this call is done,
1966 1967 1968 1969 1970 1971 1972 1973
 * you know that any inodes previously logged are safely on disk only
 * if it returns 0.
 *
 * Any other return value means you need to call btrfs_commit_transaction.
 * Some of the edge cases for fsyncing directories that have had unlinks
 * or renames done in the past mean that sometimes the only safe
 * fsync is to commit the whole FS.  When btrfs_sync_log returns -EAGAIN,
 * that has happened.
1974 1975 1976 1977
 */
int btrfs_sync_log(struct btrfs_trans_handle *trans,
		   struct btrfs_root *root)
{
Y
Yan Zheng 已提交
1978 1979
	int index1;
	int index2;
1980 1981
	int ret;
	struct btrfs_root *log = root->log_root;
Y
Yan Zheng 已提交
1982
	struct btrfs_root *log_root_tree = root->fs_info->log_root_tree;
1983

Y
Yan Zheng 已提交
1984 1985 1986
	mutex_lock(&root->log_mutex);
	index1 = root->log_transid % 2;
	if (atomic_read(&root->log_commit[index1])) {
1987
		wait_log_commit(trans, root, root->log_transid);
Y
Yan Zheng 已提交
1988 1989
		mutex_unlock(&root->log_mutex);
		return 0;
1990
	}
Y
Yan Zheng 已提交
1991 1992 1993 1994
	atomic_set(&root->log_commit[index1], 1);

	/* wait for previous tree log sync to complete */
	if (atomic_read(&root->log_commit[(index1 + 1) % 2]))
1995
		wait_log_commit(trans, root, root->log_transid - 1);
1996

1997
	while (root->log_multiple_pids) {
Y
Yan Zheng 已提交
1998 1999
		unsigned long batch = root->log_batch;
		mutex_unlock(&root->log_mutex);
2000
		schedule_timeout_uninterruptible(1);
Y
Yan Zheng 已提交
2001
		mutex_lock(&root->log_mutex);
2002 2003

		wait_for_writer(trans, root);
Y
Yan Zheng 已提交
2004
		if (batch == root->log_batch)
2005 2006 2007
			break;
	}

2008 2009 2010 2011 2012 2013 2014
	/* bail out if we need to do a full commit */
	if (root->fs_info->last_trans_log_full_commit == trans->transid) {
		ret = -EAGAIN;
		mutex_unlock(&root->log_mutex);
		goto out;
	}

2015
	ret = btrfs_write_and_wait_marked_extents(log, &log->dirty_log_pages);
2016
	BUG_ON(ret);
Y
Yan Zheng 已提交
2017

2018
	btrfs_set_root_node(&log->root_item, log->node);
Y
Yan Zheng 已提交
2019 2020 2021 2022

	root->log_batch = 0;
	root->log_transid++;
	log->log_transid = root->log_transid;
2023
	root->log_start_pid = 0;
Y
Yan Zheng 已提交
2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048
	smp_mb();
	/*
	 * log tree has been flushed to disk, new modifications of
	 * the log will be written to new positions. so it's safe to
	 * allow log writers to go in.
	 */
	mutex_unlock(&root->log_mutex);

	mutex_lock(&log_root_tree->log_mutex);
	log_root_tree->log_batch++;
	atomic_inc(&log_root_tree->log_writers);
	mutex_unlock(&log_root_tree->log_mutex);

	ret = update_log_root(trans, log);
	BUG_ON(ret);

	mutex_lock(&log_root_tree->log_mutex);
	if (atomic_dec_and_test(&log_root_tree->log_writers)) {
		smp_mb();
		if (waitqueue_active(&log_root_tree->log_writer_wait))
			wake_up(&log_root_tree->log_writer_wait);
	}

	index2 = log_root_tree->log_transid % 2;
	if (atomic_read(&log_root_tree->log_commit[index2])) {
2049 2050
		wait_log_commit(trans, log_root_tree,
				log_root_tree->log_transid);
Y
Yan Zheng 已提交
2051 2052 2053 2054 2055
		mutex_unlock(&log_root_tree->log_mutex);
		goto out;
	}
	atomic_set(&log_root_tree->log_commit[index2], 1);

2056 2057 2058 2059 2060 2061
	if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2])) {
		wait_log_commit(trans, log_root_tree,
				log_root_tree->log_transid - 1);
	}

	wait_for_writer(trans, log_root_tree);
Y
Yan Zheng 已提交
2062

2063 2064 2065 2066 2067 2068 2069 2070 2071
	/*
	 * now that we've moved on to the tree of log tree roots,
	 * check the full commit flag again
	 */
	if (root->fs_info->last_trans_log_full_commit == trans->transid) {
		mutex_unlock(&log_root_tree->log_mutex);
		ret = -EAGAIN;
		goto out_wake_log_root;
	}
Y
Yan Zheng 已提交
2072 2073 2074

	ret = btrfs_write_and_wait_marked_extents(log_root_tree,
				&log_root_tree->dirty_log_pages);
2075 2076 2077
	BUG_ON(ret);

	btrfs_set_super_log_root(&root->fs_info->super_for_commit,
Y
Yan Zheng 已提交
2078
				log_root_tree->node->start);
2079
	btrfs_set_super_log_root_level(&root->fs_info->super_for_commit,
Y
Yan Zheng 已提交
2080
				btrfs_header_level(log_root_tree->node));
2081

Y
Yan Zheng 已提交
2082 2083
	log_root_tree->log_batch = 0;
	log_root_tree->log_transid++;
2084
	smp_mb();
Y
Yan Zheng 已提交
2085 2086 2087 2088 2089 2090 2091 2092 2093 2094

	mutex_unlock(&log_root_tree->log_mutex);

	/*
	 * nobody else is going to jump in and write the the ctree
	 * super here because the log_commit atomic below is protecting
	 * us.  We must be called with a transaction handle pinning
	 * the running transaction open, so a full commit can't hop
	 * in and cause problems either.
	 */
2095
	write_ctree_super(trans, root->fs_info->tree_root, 1);
2096
	ret = 0;
Y
Yan Zheng 已提交
2097

2098
out_wake_log_root:
Y
Yan Zheng 已提交
2099 2100 2101 2102
	atomic_set(&log_root_tree->log_commit[index2], 0);
	smp_mb();
	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
		wake_up(&log_root_tree->log_commit_wait[index2]);
2103
out:
Y
Yan Zheng 已提交
2104 2105 2106 2107
	atomic_set(&root->log_commit[index1], 0);
	smp_mb();
	if (waitqueue_active(&root->log_commit_wait[index1]))
		wake_up(&root->log_commit_wait[index1]);
2108 2109 2110
	return 0;
}

2111 2112
/*
 * free all the extents used by the tree log.  This should be called
2113 2114 2115 2116 2117 2118 2119
 * at commit time of the full transaction
 */
int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root)
{
	int ret;
	struct btrfs_root *log;
	struct key;
2120 2121
	u64 start;
	u64 end;
2122 2123 2124 2125 2126
	struct walk_control wc = {
		.free = 1,
		.process_func = process_one_buffer
	};

Y
Yan Zheng 已提交
2127
	if (!root->log_root || root->fs_info->log_root_recovering)
2128 2129 2130 2131 2132 2133
		return 0;

	log = root->log_root;
	ret = walk_log_tree(trans, log, &wc);
	BUG_ON(ret);

C
Chris Mason 已提交
2134
	while (1) {
2135 2136 2137 2138 2139 2140 2141 2142 2143
		ret = find_first_extent_bit(&log->dirty_log_pages,
				    0, &start, &end, EXTENT_DIRTY);
		if (ret)
			break;

		clear_extent_dirty(&log->dirty_log_pages,
				   start, end, GFP_NOFS);
	}

Y
Yan Zheng 已提交
2144 2145 2146 2147 2148
	if (log->log_transid > 0) {
		ret = btrfs_del_root(trans, root->fs_info->log_root_tree,
				     &log->root_key);
		BUG_ON(ret);
	}
2149
	root->log_root = NULL;
Y
Yan Zheng 已提交
2150 2151
	free_extent_buffer(log->node);
	kfree(log);
2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186
	return 0;
}

/*
 * If both a file and directory are logged, and unlinks or renames are
 * mixed in, we have a few interesting corners:
 *
 * create file X in dir Y
 * link file X to X.link in dir Y
 * fsync file X
 * unlink file X but leave X.link
 * fsync dir Y
 *
 * After a crash we would expect only X.link to exist.  But file X
 * didn't get fsync'd again so the log has back refs for X and X.link.
 *
 * We solve this by removing directory entries and inode backrefs from the
 * log when a file that was logged in the current transaction is
 * unlinked.  Any later fsync will include the updated log entries, and
 * we'll be able to reconstruct the proper directory items from backrefs.
 *
 * This optimizations allows us to avoid relogging the entire inode
 * or the entire directory.
 */
int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 const char *name, int name_len,
				 struct inode *dir, u64 index)
{
	struct btrfs_root *log;
	struct btrfs_dir_item *di;
	struct btrfs_path *path;
	int ret;
	int bytes_del = 0;

2187 2188 2189
	if (BTRFS_I(dir)->logged_trans < trans->transid)
		return 0;

2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245
	ret = join_running_log_trans(root);
	if (ret)
		return 0;

	mutex_lock(&BTRFS_I(dir)->log_mutex);

	log = root->log_root;
	path = btrfs_alloc_path();
	di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino,
				   name, name_len, -1);
	if (di && !IS_ERR(di)) {
		ret = btrfs_delete_one_dir_name(trans, log, path, di);
		bytes_del += name_len;
		BUG_ON(ret);
	}
	btrfs_release_path(log, path);
	di = btrfs_lookup_dir_index_item(trans, log, path, dir->i_ino,
					 index, name, name_len, -1);
	if (di && !IS_ERR(di)) {
		ret = btrfs_delete_one_dir_name(trans, log, path, di);
		bytes_del += name_len;
		BUG_ON(ret);
	}

	/* update the directory size in the log to reflect the names
	 * we have removed
	 */
	if (bytes_del) {
		struct btrfs_key key;

		key.objectid = dir->i_ino;
		key.offset = 0;
		key.type = BTRFS_INODE_ITEM_KEY;
		btrfs_release_path(log, path);

		ret = btrfs_search_slot(trans, log, &key, path, 0, 1);
		if (ret == 0) {
			struct btrfs_inode_item *item;
			u64 i_size;

			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
					      struct btrfs_inode_item);
			i_size = btrfs_inode_size(path->nodes[0], item);
			if (i_size > bytes_del)
				i_size -= bytes_del;
			else
				i_size = 0;
			btrfs_set_inode_size(path->nodes[0], item, i_size);
			btrfs_mark_buffer_dirty(path->nodes[0]);
		} else
			ret = 0;
		btrfs_release_path(log, path);
	}

	btrfs_free_path(path);
	mutex_unlock(&BTRFS_I(dir)->log_mutex);
2246
	btrfs_end_log_trans(root);
2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260

	return 0;
}

/* see comments for btrfs_del_dir_entries_in_log */
int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root,
			       const char *name, int name_len,
			       struct inode *inode, u64 dirid)
{
	struct btrfs_root *log;
	u64 index;
	int ret;

2261 2262 2263
	if (BTRFS_I(inode)->logged_trans < trans->transid)
		return 0;

2264 2265 2266 2267 2268 2269 2270 2271 2272
	ret = join_running_log_trans(root);
	if (ret)
		return 0;
	log = root->log_root;
	mutex_lock(&BTRFS_I(inode)->log_mutex);

	ret = btrfs_del_inode_ref(trans, log, name, name_len, inode->i_ino,
				  dirid, &index);
	mutex_unlock(&BTRFS_I(inode)->log_mutex);
2273
	btrfs_end_log_trans(root);
2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370

	return ret;
}

/*
 * creates a range item in the log for 'dirid'.  first_offset and
 * last_offset tell us which parts of the key space the log should
 * be considered authoritative for.
 */
static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
				       struct btrfs_root *log,
				       struct btrfs_path *path,
				       int key_type, u64 dirid,
				       u64 first_offset, u64 last_offset)
{
	int ret;
	struct btrfs_key key;
	struct btrfs_dir_log_item *item;

	key.objectid = dirid;
	key.offset = first_offset;
	if (key_type == BTRFS_DIR_ITEM_KEY)
		key.type = BTRFS_DIR_LOG_ITEM_KEY;
	else
		key.type = BTRFS_DIR_LOG_INDEX_KEY;
	ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item));
	BUG_ON(ret);

	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_dir_log_item);
	btrfs_set_dir_log_end(path->nodes[0], item, last_offset);
	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_release_path(log, path);
	return 0;
}

/*
 * log all the items included in the current transaction for a given
 * directory.  This also creates the range items in the log tree required
 * to replay anything deleted before the fsync
 */
static noinline int log_dir_items(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct inode *inode,
			  struct btrfs_path *path,
			  struct btrfs_path *dst_path, int key_type,
			  u64 min_offset, u64 *last_offset_ret)
{
	struct btrfs_key min_key;
	struct btrfs_key max_key;
	struct btrfs_root *log = root->log_root;
	struct extent_buffer *src;
	int ret;
	int i;
	int nritems;
	u64 first_offset = min_offset;
	u64 last_offset = (u64)-1;

	log = root->log_root;
	max_key.objectid = inode->i_ino;
	max_key.offset = (u64)-1;
	max_key.type = key_type;

	min_key.objectid = inode->i_ino;
	min_key.type = key_type;
	min_key.offset = min_offset;

	path->keep_locks = 1;

	ret = btrfs_search_forward(root, &min_key, &max_key,
				   path, 0, trans->transid);

	/*
	 * we didn't find anything from this transaction, see if there
	 * is anything at all
	 */
	if (ret != 0 || min_key.objectid != inode->i_ino ||
	    min_key.type != key_type) {
		min_key.objectid = inode->i_ino;
		min_key.type = key_type;
		min_key.offset = (u64)-1;
		btrfs_release_path(root, path);
		ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
		if (ret < 0) {
			btrfs_release_path(root, path);
			return ret;
		}
		ret = btrfs_previous_item(root, path, inode->i_ino, key_type);

		/* if ret == 0 there are items for this type,
		 * create a range to tell us the last key of this type.
		 * otherwise, there are no items in this directory after
		 * *min_offset, and we create a range to indicate that.
		 */
		if (ret == 0) {
			struct btrfs_key tmp;
			btrfs_item_key_to_cpu(path->nodes[0], &tmp,
					      path->slots[0]);
C
Chris Mason 已提交
2371
			if (key_type == tmp.type)
2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401
				first_offset = max(min_offset, tmp.offset) + 1;
		}
		goto done;
	}

	/* go backward to find any previous key */
	ret = btrfs_previous_item(root, path, inode->i_ino, key_type);
	if (ret == 0) {
		struct btrfs_key tmp;
		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
		if (key_type == tmp.type) {
			first_offset = tmp.offset;
			ret = overwrite_item(trans, log, dst_path,
					     path->nodes[0], path->slots[0],
					     &tmp);
		}
	}
	btrfs_release_path(root, path);

	/* find the first key from this transaction again */
	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
	if (ret != 0) {
		WARN_ON(1);
		goto done;
	}

	/*
	 * we have a block from this transaction, log every item in it
	 * from our directory
	 */
C
Chris Mason 已提交
2402
	while (1) {
2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478
		struct btrfs_key tmp;
		src = path->nodes[0];
		nritems = btrfs_header_nritems(src);
		for (i = path->slots[0]; i < nritems; i++) {
			btrfs_item_key_to_cpu(src, &min_key, i);

			if (min_key.objectid != inode->i_ino ||
			    min_key.type != key_type)
				goto done;
			ret = overwrite_item(trans, log, dst_path, src, i,
					     &min_key);
			BUG_ON(ret);
		}
		path->slots[0] = nritems;

		/*
		 * look ahead to the next item and see if it is also
		 * from this directory and from this transaction
		 */
		ret = btrfs_next_leaf(root, path);
		if (ret == 1) {
			last_offset = (u64)-1;
			goto done;
		}
		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
		if (tmp.objectid != inode->i_ino || tmp.type != key_type) {
			last_offset = (u64)-1;
			goto done;
		}
		if (btrfs_header_generation(path->nodes[0]) != trans->transid) {
			ret = overwrite_item(trans, log, dst_path,
					     path->nodes[0], path->slots[0],
					     &tmp);

			BUG_ON(ret);
			last_offset = tmp.offset;
			goto done;
		}
	}
done:
	*last_offset_ret = last_offset;
	btrfs_release_path(root, path);
	btrfs_release_path(log, dst_path);

	/* insert the log range keys to indicate where the log is valid */
	ret = insert_dir_log_key(trans, log, path, key_type, inode->i_ino,
				 first_offset, last_offset);
	BUG_ON(ret);
	return 0;
}

/*
 * logging directories is very similar to logging inodes, We find all the items
 * from the current transaction and write them to the log.
 *
 * The recovery code scans the directory in the subvolume, and if it finds a
 * key in the range logged that is not present in the log tree, then it means
 * that dir entry was unlinked during the transaction.
 *
 * In order for that scan to work, we must include one key smaller than
 * the smallest logged by this transaction and one key larger than the largest
 * key logged by this transaction.
 */
static noinline int log_directory_changes(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct inode *inode,
			  struct btrfs_path *path,
			  struct btrfs_path *dst_path)
{
	u64 min_key;
	u64 max_key;
	int ret;
	int key_type = BTRFS_DIR_ITEM_KEY;

again:
	min_key = 0;
	max_key = 0;
C
Chris Mason 已提交
2479
	while (1) {
2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514
		ret = log_dir_items(trans, root, inode, path,
				    dst_path, key_type, min_key,
				    &max_key);
		BUG_ON(ret);
		if (max_key == (u64)-1)
			break;
		min_key = max_key + 1;
	}

	if (key_type == BTRFS_DIR_ITEM_KEY) {
		key_type = BTRFS_DIR_INDEX_KEY;
		goto again;
	}
	return 0;
}

/*
 * a helper function to drop items from the log before we relog an
 * inode.  max_key_type indicates the highest item type to remove.
 * This cannot be run for file data extents because it does not
 * free the extents they point to.
 */
static int drop_objectid_items(struct btrfs_trans_handle *trans,
				  struct btrfs_root *log,
				  struct btrfs_path *path,
				  u64 objectid, int max_key_type)
{
	int ret;
	struct btrfs_key key;
	struct btrfs_key found_key;

	key.objectid = objectid;
	key.type = max_key_type;
	key.offset = (u64)-1;

C
Chris Mason 已提交
2515
	while (1) {
2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538
		ret = btrfs_search_slot(trans, log, &key, path, -1, 1);

		if (ret != 1)
			break;

		if (path->slots[0] == 0)
			break;

		path->slots[0]--;
		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
				      path->slots[0]);

		if (found_key.objectid != objectid)
			break;

		ret = btrfs_del_item(trans, log, path);
		BUG_ON(ret);
		btrfs_release_path(log, path);
	}
	btrfs_release_path(log, path);
	return 0;
}

2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553
static noinline int copy_items(struct btrfs_trans_handle *trans,
			       struct btrfs_root *log,
			       struct btrfs_path *dst_path,
			       struct extent_buffer *src,
			       int start_slot, int nr, int inode_only)
{
	unsigned long src_offset;
	unsigned long dst_offset;
	struct btrfs_file_extent_item *extent;
	struct btrfs_inode_item *inode_item;
	int ret;
	struct btrfs_key *ins_keys;
	u32 *ins_sizes;
	char *ins_data;
	int i;
2554 2555 2556
	struct list_head ordered_sums;

	INIT_LIST_HEAD(&ordered_sums);
2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570

	ins_data = kmalloc(nr * sizeof(struct btrfs_key) +
			   nr * sizeof(u32), GFP_NOFS);
	ins_sizes = (u32 *)ins_data;
	ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));

	for (i = 0; i < nr; i++) {
		ins_sizes[i] = btrfs_item_size_nr(src, i + start_slot);
		btrfs_item_key_to_cpu(src, ins_keys + i, i + start_slot);
	}
	ret = btrfs_insert_empty_items(trans, log, dst_path,
				       ins_keys, ins_sizes, nr);
	BUG_ON(ret);

2571
	for (i = 0; i < nr; i++, dst_path->slots[0]++) {
2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604
		dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0],
						   dst_path->slots[0]);

		src_offset = btrfs_item_ptr_offset(src, start_slot + i);

		copy_extent_buffer(dst_path->nodes[0], src, dst_offset,
				   src_offset, ins_sizes[i]);

		if (inode_only == LOG_INODE_EXISTS &&
		    ins_keys[i].type == BTRFS_INODE_ITEM_KEY) {
			inode_item = btrfs_item_ptr(dst_path->nodes[0],
						    dst_path->slots[0],
						    struct btrfs_inode_item);
			btrfs_set_inode_size(dst_path->nodes[0], inode_item, 0);

			/* set the generation to zero so the recover code
			 * can tell the difference between an logging
			 * just to say 'this inode exists' and a logging
			 * to say 'update this inode with these values'
			 */
			btrfs_set_inode_generation(dst_path->nodes[0],
						   inode_item, 0);
		}
		/* take a reference on file data extents so that truncates
		 * or deletes of this inode don't have to relog the inode
		 * again
		 */
		if (btrfs_key_type(ins_keys + i) == BTRFS_EXTENT_DATA_KEY) {
			int found_type;
			extent = btrfs_item_ptr(src, start_slot + i,
						struct btrfs_file_extent_item);

			found_type = btrfs_file_extent_type(src, extent);
Y
Yan Zheng 已提交
2605 2606
			if (found_type == BTRFS_FILE_EXTENT_REG ||
			    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618
				u64 ds, dl, cs, cl;
				ds = btrfs_file_extent_disk_bytenr(src,
								extent);
				/* ds == 0 is a hole */
				if (ds == 0)
					continue;

				dl = btrfs_file_extent_disk_num_bytes(src,
								extent);
				cs = btrfs_file_extent_offset(src, extent);
				cl = btrfs_file_extent_num_bytes(src,
								extent);;
2619 2620 2621 2622 2623
				if (btrfs_file_extent_compression(src,
								  extent)) {
					cs = 0;
					cl = dl;
				}
2624 2625 2626 2627 2628 2629

				ret = btrfs_lookup_csums_range(
						log->fs_info->csum_root,
						ds + cs, ds + cs + cl - 1,
						&ordered_sums);
				BUG_ON(ret);
2630 2631 2632 2633 2634 2635 2636
			}
		}
	}

	btrfs_mark_buffer_dirty(dst_path->nodes[0]);
	btrfs_release_path(log, dst_path);
	kfree(ins_data);
2637 2638 2639 2640 2641

	/*
	 * we have to do this after the loop above to avoid changing the
	 * log tree while trying to change the log tree.
	 */
C
Chris Mason 已提交
2642
	while (!list_empty(&ordered_sums)) {
2643 2644 2645 2646 2647 2648 2649 2650
		struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
						   struct btrfs_ordered_sum,
						   list);
		ret = btrfs_csum_file_blocks(trans, log, sums);
		BUG_ON(ret);
		list_del(&sums->list);
		kfree(sums);
	}
2651 2652 2653
	return 0;
}

2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667
/* log a single inode in the tree log.
 * At least one parent directory for this inode must exist in the tree
 * or be logged already.
 *
 * Any items from this inode changed by the current transaction are copied
 * to the log tree.  An extra reference is taken on any extents in this
 * file, allowing us to avoid a whole pile of corner cases around logging
 * blocks that have been removed from the tree.
 *
 * See LOG_INODE_ALL and related defines for a description of what inode_only
 * does.
 *
 * This handles both files and directories.
 */
2668
static int btrfs_log_inode(struct btrfs_trans_handle *trans,
2669 2670 2671 2672 2673 2674 2675 2676
			     struct btrfs_root *root, struct inode *inode,
			     int inode_only)
{
	struct btrfs_path *path;
	struct btrfs_path *dst_path;
	struct btrfs_key min_key;
	struct btrfs_key max_key;
	struct btrfs_root *log = root->log_root;
2677
	struct extent_buffer *src = NULL;
2678 2679
	u32 size;
	int ret;
2680
	int nritems;
2681 2682
	int ins_start_slot = 0;
	int ins_nr;
2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693

	log = root->log_root;

	path = btrfs_alloc_path();
	dst_path = btrfs_alloc_path();

	min_key.objectid = inode->i_ino;
	min_key.type = BTRFS_INODE_ITEM_KEY;
	min_key.offset = 0;

	max_key.objectid = inode->i_ino;
2694 2695 2696 2697 2698

	/* today the code can only do partial logging of directories */
	if (!S_ISDIR(inode->i_mode))
	    inode_only = LOG_INODE_ALL;

2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723
	if (inode_only == LOG_INODE_EXISTS || S_ISDIR(inode->i_mode))
		max_key.type = BTRFS_XATTR_ITEM_KEY;
	else
		max_key.type = (u8)-1;
	max_key.offset = (u64)-1;

	mutex_lock(&BTRFS_I(inode)->log_mutex);

	/*
	 * a brute force approach to making sure we get the most uptodate
	 * copies of everything.
	 */
	if (S_ISDIR(inode->i_mode)) {
		int max_key_type = BTRFS_DIR_LOG_INDEX_KEY;

		if (inode_only == LOG_INODE_EXISTS)
			max_key_type = BTRFS_XATTR_ITEM_KEY;
		ret = drop_objectid_items(trans, log, path,
					  inode->i_ino, max_key_type);
	} else {
		ret = btrfs_truncate_inode_items(trans, log, inode, 0, 0);
	}
	BUG_ON(ret);
	path->keep_locks = 1;

C
Chris Mason 已提交
2724
	while (1) {
2725
		ins_nr = 0;
2726 2727 2728 2729
		ret = btrfs_search_forward(root, &min_key, &max_key,
					   path, 0, trans->transid);
		if (ret != 0)
			break;
2730
again:
2731
		/* note, ins_nr might be > 0 here, cleanup outside the loop */
2732 2733 2734 2735
		if (min_key.objectid != inode->i_ino)
			break;
		if (min_key.type > max_key.type)
			break;
2736

2737 2738
		src = path->nodes[0];
		size = btrfs_item_size_nr(src, path->slots[0]);
2739 2740 2741 2742 2743 2744 2745
		if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
			ins_nr++;
			goto next_slot;
		} else if (!ins_nr) {
			ins_start_slot = path->slots[0];
			ins_nr = 1;
			goto next_slot;
2746 2747
		}

2748 2749 2750 2751 2752 2753
		ret = copy_items(trans, log, dst_path, src, ins_start_slot,
				 ins_nr, inode_only);
		BUG_ON(ret);
		ins_nr = 1;
		ins_start_slot = path->slots[0];
next_slot:
2754

2755 2756 2757 2758 2759 2760 2761
		nritems = btrfs_header_nritems(path->nodes[0]);
		path->slots[0]++;
		if (path->slots[0] < nritems) {
			btrfs_item_key_to_cpu(path->nodes[0], &min_key,
					      path->slots[0]);
			goto again;
		}
2762 2763 2764 2765 2766 2767 2768
		if (ins_nr) {
			ret = copy_items(trans, log, dst_path, src,
					 ins_start_slot,
					 ins_nr, inode_only);
			BUG_ON(ret);
			ins_nr = 0;
		}
2769 2770
		btrfs_release_path(root, path);

2771 2772 2773 2774 2775 2776 2777 2778 2779
		if (min_key.offset < (u64)-1)
			min_key.offset++;
		else if (min_key.type < (u8)-1)
			min_key.type++;
		else if (min_key.objectid < (u64)-1)
			min_key.objectid++;
		else
			break;
	}
2780 2781 2782 2783 2784 2785 2786 2787
	if (ins_nr) {
		ret = copy_items(trans, log, dst_path, src,
				 ins_start_slot,
				 ins_nr, inode_only);
		BUG_ON(ret);
		ins_nr = 0;
	}
	WARN_ON(ins_nr);
2788
	if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
2789 2790 2791 2792 2793
		btrfs_release_path(root, path);
		btrfs_release_path(log, dst_path);
		ret = log_directory_changes(trans, root, inode, path, dst_path);
		BUG_ON(ret);
	}
2794
	BTRFS_I(inode)->logged_trans = trans->transid;
2795 2796 2797 2798 2799 2800 2801
	mutex_unlock(&BTRFS_I(inode)->log_mutex);

	btrfs_free_path(path);
	btrfs_free_path(dst_path);
	return 0;
}

2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812
/*
 * follow the dentry parent pointers up the chain and see if any
 * of the directories in it require a full commit before they can
 * be logged.  Returns zero if nothing special needs to be done or 1 if
 * a full commit is required.
 */
static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
					       struct inode *inode,
					       struct dentry *parent,
					       struct super_block *sb,
					       u64 last_committed)
2813
{
2814 2815
	int ret = 0;
	struct btrfs_root *root;
2816

2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827
	/*
	 * for regular files, if its inode is already on disk, we don't
	 * have to worry about the parents at all.  This is because
	 * we can use the last_unlink_trans field to record renames
	 * and other fun in this file.
	 */
	if (S_ISREG(inode->i_mode) &&
	    BTRFS_I(inode)->generation <= last_committed &&
	    BTRFS_I(inode)->last_unlink_trans <= last_committed)
			goto out;

2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853
	if (!S_ISDIR(inode->i_mode)) {
		if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
			goto out;
		inode = parent->d_inode;
	}

	while (1) {
		BTRFS_I(inode)->logged_trans = trans->transid;
		smp_mb();

		if (BTRFS_I(inode)->last_unlink_trans > last_committed) {
			root = BTRFS_I(inode)->root;

			/*
			 * make sure any commits to the log are forced
			 * to be full commits
			 */
			root->fs_info->last_trans_log_full_commit =
				trans->transid;
			ret = 1;
			break;
		}

		if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
			break;

2854
		if (IS_ROOT(parent))
2855 2856 2857 2858 2859 2860 2861
			break;

		parent = parent->d_parent;
		inode = parent->d_inode;

	}
out:
2862 2863 2864 2865 2866 2867 2868 2869 2870
	return ret;
}

/*
 * helper function around btrfs_log_inode to make sure newly created
 * parent directories also end up in the log.  A minimal inode and backref
 * only logging is done of any parent directories that are older than
 * the last committed transaction
 */
2871 2872 2873
int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
		    struct btrfs_root *root, struct inode *inode,
		    struct dentry *parent, int exists_only)
2874
{
2875
	int inode_only = exists_only ? LOG_INODE_EXISTS : LOG_INODE_ALL;
2876
	struct super_block *sb;
2877 2878 2879 2880 2881
	int ret = 0;
	u64 last_committed = root->fs_info->last_trans_committed;

	sb = inode->i_sb;

S
Sage Weil 已提交
2882 2883 2884 2885 2886
	if (btrfs_test_opt(root, NOTREELOG)) {
		ret = 1;
		goto end_no_trans;
	}

2887 2888 2889 2890 2891 2892
	if (root->fs_info->last_trans_log_full_commit >
	    root->fs_info->last_trans_committed) {
		ret = 1;
		goto end_no_trans;
	}

2893 2894 2895 2896 2897 2898
	if (root != BTRFS_I(inode)->root ||
	    btrfs_root_refs(&root->root_item) == 0) {
		ret = 1;
		goto end_no_trans;
	}

2899 2900 2901 2902
	ret = check_parent_dirs_for_sync(trans, inode, parent,
					 sb, last_committed);
	if (ret)
		goto end_no_trans;
2903 2904 2905

	start_log_trans(trans, root);

2906 2907 2908
	ret = btrfs_log_inode(trans, root, inode, inode_only);
	BUG_ON(ret);

2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920
	/*
	 * for regular files, if its inode is already on disk, we don't
	 * have to worry about the parents at all.  This is because
	 * we can use the last_unlink_trans field to record renames
	 * and other fun in this file.
	 */
	if (S_ISREG(inode->i_mode) &&
	    BTRFS_I(inode)->generation <= last_committed &&
	    BTRFS_I(inode)->last_unlink_trans <= last_committed)
			goto no_parent;

	inode_only = LOG_INODE_EXISTS;
2921 2922
	while (1) {
		if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
2923 2924
			break;

2925
		inode = parent->d_inode;
2926 2927 2928
		if (root != BTRFS_I(inode)->root)
			break;

2929 2930 2931 2932 2933
		if (BTRFS_I(inode)->generation >
		    root->fs_info->last_trans_committed) {
			ret = btrfs_log_inode(trans, root, inode, inode_only);
			BUG_ON(ret);
		}
2934
		if (IS_ROOT(parent))
2935
			break;
2936 2937

		parent = parent->d_parent;
2938
	}
2939
no_parent:
2940 2941 2942 2943
	ret = 0;
	btrfs_end_log_trans(root);
end_no_trans:
	return ret;
2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954
}

/*
 * it is not safe to log dentry if the chunk root has added new
 * chunks.  This returns 0 if the dentry was logged, and 1 otherwise.
 * If this returns 1, you must commit the transaction to safely get your
 * data on disk.
 */
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct dentry *dentry)
{
2955 2956
	return btrfs_log_inode_parent(trans, root, dentry->d_inode,
				      dentry->d_parent, 0);
2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993
}

/*
 * should be called during mount to recover any replay any log trees
 * from the FS
 */
int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
{
	int ret;
	struct btrfs_path *path;
	struct btrfs_trans_handle *trans;
	struct btrfs_key key;
	struct btrfs_key found_key;
	struct btrfs_key tmp_key;
	struct btrfs_root *log;
	struct btrfs_fs_info *fs_info = log_root_tree->fs_info;
	struct walk_control wc = {
		.process_func = process_one_buffer,
		.stage = 0,
	};

	fs_info->log_root_recovering = 1;
	path = btrfs_alloc_path();
	BUG_ON(!path);

	trans = btrfs_start_transaction(fs_info->tree_root, 1);

	wc.trans = trans;
	wc.pin = 1;

	walk_log_tree(trans, log_root_tree, &wc);

again:
	key.objectid = BTRFS_TREE_LOG_OBJECTID;
	key.offset = (u64)-1;
	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);

C
Chris Mason 已提交
2994
	while (1) {
2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020
		ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);
		if (ret < 0)
			break;
		if (ret > 0) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}
		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
				      path->slots[0]);
		btrfs_release_path(log_root_tree, path);
		if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID)
			break;

		log = btrfs_read_fs_root_no_radix(log_root_tree,
						  &found_key);
		BUG_ON(!log);


		tmp_key.objectid = found_key.offset;
		tmp_key.type = BTRFS_ROOT_ITEM_KEY;
		tmp_key.offset = (u64)-1;

		wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key);
		BUG_ON(!wc.replay_dest);

Y
Yan Zheng 已提交
3021
		wc.replay_dest->log_root = log;
3022
		btrfs_record_root_in_trans(trans, wc.replay_dest);
3023 3024 3025 3026 3027 3028 3029 3030 3031 3032
		ret = walk_log_tree(trans, log, &wc);
		BUG_ON(ret);

		if (wc.stage == LOG_WALK_REPLAY_ALL) {
			ret = fixup_inode_link_counts(trans, wc.replay_dest,
						      path);
			BUG_ON(ret);
		}

		key.offset = found_key.offset - 1;
Y
Yan Zheng 已提交
3033
		wc.replay_dest->log_root = NULL;
3034
		free_extent_buffer(log->node);
3035
		free_extent_buffer(log->commit_root);
3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067
		kfree(log);

		if (found_key.offset == 0)
			break;
	}
	btrfs_release_path(log_root_tree, path);

	/* step one is to pin it all, step two is to replay just inodes */
	if (wc.pin) {
		wc.pin = 0;
		wc.process_func = replay_one_buffer;
		wc.stage = LOG_WALK_REPLAY_INODES;
		goto again;
	}
	/* step three is to replay everything */
	if (wc.stage < LOG_WALK_REPLAY_ALL) {
		wc.stage++;
		goto again;
	}

	btrfs_free_path(path);

	free_extent_buffer(log_root_tree->node);
	log_root_tree->log_root = NULL;
	fs_info->log_root_recovering = 0;

	/* step 4: commit the transaction, which also unpins the blocks */
	btrfs_commit_transaction(trans, fs_info->tree_root);

	kfree(log_root_tree);
	return 0;
}
3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080

/*
 * there are some corner cases where we want to force a full
 * commit instead of allowing a directory to be logged.
 *
 * They revolve around files there were unlinked from the directory, and
 * this function updates the parent directory so that a full commit is
 * properly done if it is fsync'd later after the unlinks are done.
 */
void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
			     struct inode *dir, struct inode *inode,
			     int for_rename)
{
3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093
	/*
	 * when we're logging a file, if it hasn't been renamed
	 * or unlinked, and its inode is fully committed on disk,
	 * we don't have to worry about walking up the directory chain
	 * to log its parents.
	 *
	 * So, we use the last_unlink_trans field to put this transid
	 * into the file.  When the file is logged we check it and
	 * don't log the parents if the file is fully on disk.
	 */
	if (S_ISREG(inode->i_mode))
		BTRFS_I(inode)->last_unlink_trans = trans->transid;

3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138
	/*
	 * if this directory was already logged any new
	 * names for this file/dir will get recorded
	 */
	smp_mb();
	if (BTRFS_I(dir)->logged_trans == trans->transid)
		return;

	/*
	 * if the inode we're about to unlink was logged,
	 * the log will be properly updated for any new names
	 */
	if (BTRFS_I(inode)->logged_trans == trans->transid)
		return;

	/*
	 * when renaming files across directories, if the directory
	 * there we're unlinking from gets fsync'd later on, there's
	 * no way to find the destination directory later and fsync it
	 * properly.  So, we have to be conservative and force commits
	 * so the new name gets discovered.
	 */
	if (for_rename)
		goto record;

	/* we can safely do the unlink without any special recording */
	return;

record:
	BTRFS_I(dir)->last_unlink_trans = trans->transid;
}

/*
 * Call this after adding a new name for a file and it will properly
 * update the log to reflect the new name.
 *
 * It will return zero if all goes well, and it will return 1 if a
 * full transaction commit is required.
 */
int btrfs_log_new_name(struct btrfs_trans_handle *trans,
			struct inode *inode, struct inode *old_dir,
			struct dentry *parent)
{
	struct btrfs_root * root = BTRFS_I(inode)->root;

3139 3140 3141 3142 3143 3144 3145
	/*
	 * this will force the logging code to walk the dentry chain
	 * up for the file
	 */
	if (S_ISREG(inode->i_mode))
		BTRFS_I(inode)->last_unlink_trans = trans->transid;

3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158
	/*
	 * if this inode hasn't been logged and directory we're renaming it
	 * from hasn't been logged, we don't need to log it
	 */
	if (BTRFS_I(inode)->logged_trans <=
	    root->fs_info->last_trans_committed &&
	    (!old_dir || BTRFS_I(old_dir)->logged_trans <=
		    root->fs_info->last_trans_committed))
		return 0;

	return btrfs_log_inode_parent(trans, root, inode, parent, 1);
}