inline.c 49.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 * Copyright (c) 2012 Taobao.
 * Written by Tao Ma <boyu.mt@taobao.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of version 2.1 of the GNU Lesser General Public License
 * 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.
 */
14 15 16

#include <linux/fiemap.h>

17 18 19
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
20
#include "truncate.h"
21 22 23

#define EXT4_XATTR_SYSTEM_DATA	"data"
#define EXT4_MIN_INLINE_DATA_SIZE	((sizeof(__le32) * EXT4_N_BLOCKS))
24 25
#define EXT4_INLINE_DOTDOT_OFFSET	2
#define EXT4_INLINE_DOTDOT_SIZE		4
26

27
static int ext4_get_inline_size(struct inode *inode)
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
{
	if (EXT4_I(inode)->i_inline_off)
		return EXT4_I(inode)->i_inline_size;

	return 0;
}

static int get_max_inline_xattr_value_size(struct inode *inode,
					   struct ext4_iloc *iloc)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_entry *entry;
	struct ext4_inode *raw_inode;
	int free, min_offs;

	min_offs = EXT4_SB(inode->i_sb)->s_inode_size -
			EXT4_GOOD_OLD_INODE_SIZE -
			EXT4_I(inode)->i_extra_isize -
			sizeof(struct ext4_xattr_ibody_header);

	/*
	 * We need to subtract another sizeof(__u32) since an in-inode xattr
	 * needs an empty 4 bytes to indicate the gap between the xattr entry
	 * and the name/value pair.
	 */
	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
		return EXT4_XATTR_SIZE(min_offs -
			EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)) -
			EXT4_XATTR_ROUND - sizeof(__u32));

	raw_inode = ext4_raw_inode(iloc);
	header = IHDR(inode, raw_inode);
	entry = IFIRST(header);

	/* Compute min_offs. */
	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
		if (!entry->e_value_block && entry->e_value_size) {
			size_t offs = le16_to_cpu(entry->e_value_offs);
			if (offs < min_offs)
				min_offs = offs;
		}
	}
	free = min_offs -
		((void *)entry - (void *)IFIRST(header)) - sizeof(__u32);

	if (EXT4_I(inode)->i_inline_off) {
		entry = (struct ext4_xattr_entry *)
			((void *)raw_inode + EXT4_I(inode)->i_inline_off);

77
		free += EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size));
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
		goto out;
	}

	free -= EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA));

	if (free > EXT4_XATTR_ROUND)
		free = EXT4_XATTR_SIZE(free - EXT4_XATTR_ROUND);
	else
		free = 0;

out:
	return free;
}

/*
 * Get the maximum size we now can store in an inode.
 * If we can't find the space for a xattr entry, don't use the space
 * of the extents since we have no space to indicate the inline data.
 */
int ext4_get_max_inline_size(struct inode *inode)
{
	int error, max_inline_size;
	struct ext4_iloc iloc;

	if (EXT4_I(inode)->i_extra_isize == 0)
		return 0;

	error = ext4_get_inode_loc(inode, &iloc);
	if (error) {
		ext4_error_inode(inode, __func__, __LINE__, 0,
				 "can't get inode location %lu",
				 inode->i_ino);
		return 0;
	}

	down_read(&EXT4_I(inode)->xattr_sem);
	max_inline_size = get_max_inline_xattr_value_size(inode, &iloc);
	up_read(&EXT4_I(inode)->xattr_sem);

	brelse(iloc.bh);

	if (!max_inline_size)
		return 0;

	return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE;
}

/*
 * this function does not take xattr_sem, which is OK because it is
 * currently only used in a code path coming form ext4_iget, before
 * the new inode has been unlocked
 */
int ext4_find_inline_data_nolock(struct inode *inode)
{
	struct ext4_xattr_ibody_find is = {
		.s = { .not_found = -ENODATA, },
	};
	struct ext4_xattr_info i = {
		.name_index = EXT4_XATTR_INDEX_SYSTEM,
		.name = EXT4_XATTR_SYSTEM_DATA,
	};
	int error;

	if (EXT4_I(inode)->i_extra_isize == 0)
		return 0;

	error = ext4_get_inode_loc(inode, &is.iloc);
	if (error)
		return error;

	error = ext4_xattr_ibody_find(inode, &i, &is);
	if (error)
		goto out;

	if (!is.s.not_found) {
		EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
					(void *)ext4_raw_inode(&is.iloc));
		EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
				le32_to_cpu(is.s.here->e_value_size);
		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
	}
out:
	brelse(is.iloc.bh);
	return error;
}

static int ext4_read_inline_data(struct inode *inode, void *buffer,
				 unsigned int len,
				 struct ext4_iloc *iloc)
{
	struct ext4_xattr_entry *entry;
	struct ext4_xattr_ibody_header *header;
	int cp_len = 0;
	struct ext4_inode *raw_inode;

	if (!len)
		return 0;

	BUG_ON(len > EXT4_I(inode)->i_inline_size);

	cp_len = len < EXT4_MIN_INLINE_DATA_SIZE ?
			len : EXT4_MIN_INLINE_DATA_SIZE;

	raw_inode = ext4_raw_inode(iloc);
	memcpy(buffer, (void *)(raw_inode->i_block), cp_len);

	len -= cp_len;
	buffer += cp_len;

	if (!len)
		goto out;

	header = IHDR(inode, raw_inode);
	entry = (struct ext4_xattr_entry *)((void *)raw_inode +
					    EXT4_I(inode)->i_inline_off);
	len = min_t(unsigned int, len,
		    (unsigned int)le32_to_cpu(entry->e_value_size));

	memcpy(buffer,
	       (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs), len);
	cp_len += len;

out:
	return cp_len;
}

/*
 * write the buffer to the inline inode.
 * If 'create' is set, we don't need to do the extra copy in the xattr
207 208
 * value since it is already handled by ext4_xattr_ibody_inline_set.
 * That saves us one memcpy.
209
 */
210 211
static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
				   void *buffer, loff_t pos, unsigned int len)
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
{
	struct ext4_xattr_entry *entry;
	struct ext4_xattr_ibody_header *header;
	struct ext4_inode *raw_inode;
	int cp_len = 0;

	BUG_ON(!EXT4_I(inode)->i_inline_off);
	BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);

	raw_inode = ext4_raw_inode(iloc);
	buffer += pos;

	if (pos < EXT4_MIN_INLINE_DATA_SIZE) {
		cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ?
			 EXT4_MIN_INLINE_DATA_SIZE - pos : len;
		memcpy((void *)raw_inode->i_block + pos, buffer, cp_len);

		len -= cp_len;
		buffer += cp_len;
		pos += cp_len;
	}

	if (!len)
		return;

	pos -= EXT4_MIN_INLINE_DATA_SIZE;
	header = IHDR(inode, raw_inode);
	entry = (struct ext4_xattr_entry *)((void *)raw_inode +
					    EXT4_I(inode)->i_inline_off);

	memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos,
	       buffer, len);
}

static int ext4_create_inline_data(handle_t *handle,
				   struct inode *inode, unsigned len)
{
	int error;
	void *value = NULL;
	struct ext4_xattr_ibody_find is = {
		.s = { .not_found = -ENODATA, },
	};
	struct ext4_xattr_info i = {
		.name_index = EXT4_XATTR_INDEX_SYSTEM,
		.name = EXT4_XATTR_SYSTEM_DATA,
	};

	error = ext4_get_inode_loc(inode, &is.iloc);
	if (error)
		return error;

263
	BUFFER_TRACE(is.iloc.bh, "get_write_access");
264 265 266 267 268
	error = ext4_journal_get_write_access(handle, is.iloc.bh);
	if (error)
		goto out;

	if (len > EXT4_MIN_INLINE_DATA_SIZE) {
269
		value = EXT4_ZERO_XATTR_VALUE;
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
		len -= EXT4_MIN_INLINE_DATA_SIZE;
	} else {
		value = "";
		len = 0;
	}

	/* Insert the the xttr entry. */
	i.value = value;
	i.value_len = len;

	error = ext4_xattr_ibody_find(inode, &i, &is);
	if (error)
		goto out;

	BUG_ON(!is.s.not_found);

286
	error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
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
	if (error) {
		if (error == -ENOSPC)
			ext4_clear_inode_state(inode,
					       EXT4_STATE_MAY_INLINE_DATA);
		goto out;
	}

	memset((void *)ext4_raw_inode(&is.iloc)->i_block,
		0, EXT4_MIN_INLINE_DATA_SIZE);

	EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
				      (void *)ext4_raw_inode(&is.iloc));
	EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE;
	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
	ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA);
	get_bh(is.iloc.bh);
	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);

out:
	brelse(is.iloc.bh);
	return error;
}

static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
				   unsigned int len)
{
	int error;
	void *value = NULL;
	struct ext4_xattr_ibody_find is = {
		.s = { .not_found = -ENODATA, },
	};
	struct ext4_xattr_info i = {
		.name_index = EXT4_XATTR_INDEX_SYSTEM,
		.name = EXT4_XATTR_SYSTEM_DATA,
	};

	/* If the old space is ok, write the data directly. */
	if (len <= EXT4_I(inode)->i_inline_size)
		return 0;

	error = ext4_get_inode_loc(inode, &is.iloc);
	if (error)
		return error;

	error = ext4_xattr_ibody_find(inode, &i, &is);
	if (error)
		goto out;

	BUG_ON(is.s.not_found);

	len -= EXT4_MIN_INLINE_DATA_SIZE;
	value = kzalloc(len, GFP_NOFS);
	if (!value)
		goto out;

	error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
				     value, len);
	if (error == -ENODATA)
		goto out;

347
	BUFFER_TRACE(is.iloc.bh, "get_write_access");
348 349 350 351 352 353 354 355
	error = ext4_journal_get_write_access(handle, is.iloc.bh);
	if (error)
		goto out;

	/* Update the xttr entry. */
	i.value = value;
	i.value_len = len;

356
	error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373
	if (error)
		goto out;

	EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
				      (void *)ext4_raw_inode(&is.iloc));
	EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
				le32_to_cpu(is.s.here->e_value_size);
	ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
	get_bh(is.iloc.bh);
	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);

out:
	kfree(value);
	brelse(is.iloc.bh);
	return error;
}

374 375
static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
				    unsigned int len)
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
{
	int ret, size;
	struct ext4_inode_info *ei = EXT4_I(inode);

	if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
		return -ENOSPC;

	size = ext4_get_max_inline_size(inode);
	if (size < len)
		return -ENOSPC;

	down_write(&EXT4_I(inode)->xattr_sem);

	if (ei->i_inline_off)
		ret = ext4_update_inline_data(handle, inode, len);
	else
		ret = ext4_create_inline_data(handle, inode, len);

	up_write(&EXT4_I(inode)->xattr_sem);

	return ret;
}

static int ext4_destroy_inline_data_nolock(handle_t *handle,
					   struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	struct ext4_xattr_ibody_find is = {
		.s = { .not_found = 0, },
	};
	struct ext4_xattr_info i = {
		.name_index = EXT4_XATTR_INDEX_SYSTEM,
		.name = EXT4_XATTR_SYSTEM_DATA,
		.value = NULL,
		.value_len = 0,
	};
	int error;

	if (!ei->i_inline_off)
		return 0;

	error = ext4_get_inode_loc(inode, &is.iloc);
	if (error)
		return error;

	error = ext4_xattr_ibody_find(inode, &i, &is);
	if (error)
		goto out;

425
	BUFFER_TRACE(is.iloc.bh, "get_write_access");
426 427 428 429
	error = ext4_journal_get_write_access(handle, is.iloc.bh);
	if (error)
		goto out;

430
	error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
431 432 433 434 435 436
	if (error)
		goto out;

	memset((void *)ext4_raw_inode(&is.iloc)->i_block,
		0, EXT4_MIN_INLINE_DATA_SIZE);

437
	if (ext4_has_feature_extents(inode->i_sb)) {
438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458
		if (S_ISDIR(inode->i_mode) ||
		    S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) {
			ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
			ext4_ext_tree_init(handle, inode);
		}
	}
	ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);

	get_bh(is.iloc.bh);
	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);

	EXT4_I(inode)->i_inline_off = 0;
	EXT4_I(inode)->i_inline_size = 0;
	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
out:
	brelse(is.iloc.bh);
	if (error == -ENODATA)
		error = 0;
	return error;
}

T
Tao Ma 已提交
459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519
static int ext4_read_inline_page(struct inode *inode, struct page *page)
{
	void *kaddr;
	int ret = 0;
	size_t len;
	struct ext4_iloc iloc;

	BUG_ON(!PageLocked(page));
	BUG_ON(!ext4_has_inline_data(inode));
	BUG_ON(page->index);

	if (!EXT4_I(inode)->i_inline_off) {
		ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.",
			     inode->i_ino);
		goto out;
	}

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		goto out;

	len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
	kaddr = kmap_atomic(page);
	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
	flush_dcache_page(page);
	kunmap_atomic(kaddr);
	zero_user_segment(page, len, PAGE_CACHE_SIZE);
	SetPageUptodate(page);
	brelse(iloc.bh);

out:
	return ret;
}

int ext4_readpage_inline(struct inode *inode, struct page *page)
{
	int ret = 0;

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		up_read(&EXT4_I(inode)->xattr_sem);
		return -EAGAIN;
	}

	/*
	 * Current inline data can only exist in the 1st page,
	 * So for all the other pages, just set them uptodate.
	 */
	if (!page->index)
		ret = ext4_read_inline_page(inode, page);
	else if (!PageUptodate(page)) {
		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
		SetPageUptodate(page);
	}

	up_read(&EXT4_I(inode)->xattr_sem);

	unlock_page(page);
	return ret >= 0 ? 0 : ret;
}

520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
					      struct inode *inode,
					      unsigned flags)
{
	int ret, needed_blocks;
	handle_t *handle = NULL;
	int retries = 0, sem_held = 0;
	struct page *page = NULL;
	unsigned from, to;
	struct ext4_iloc iloc;

	if (!ext4_has_inline_data(inode)) {
		/*
		 * clear the flag so that no new write
		 * will trap here again.
		 */
		ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
		return 0;
	}

	needed_blocks = ext4_writepage_trans_blocks(inode);

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

retry:
547
	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		handle = NULL;
		goto out;
	}

	/* We cannot recurse into the filesystem as the transaction is already
	 * started */
	flags |= AOP_FLAG_NOFS;

	page = grab_cache_page_write_begin(mapping, 0, flags);
	if (!page) {
		ret = -ENOMEM;
		goto out;
	}

	down_write(&EXT4_I(inode)->xattr_sem);
	sem_held = 1;
	/* If some one has already done this for us, just exit. */
	if (!ext4_has_inline_data(inode)) {
		ret = 0;
		goto out;
	}

	from = 0;
	to = ext4_get_inline_size(inode);
	if (!PageUptodate(page)) {
		ret = ext4_read_inline_page(inode, page);
		if (ret < 0)
			goto out;
	}

	ret = ext4_destroy_inline_data_nolock(handle, inode);
	if (ret)
		goto out;

	if (ext4_should_dioread_nolock(inode))
		ret = __block_write_begin(page, from, to, ext4_get_block_write);
	else
		ret = __block_write_begin(page, from, to, ext4_get_block);

	if (!ret && ext4_should_journal_data(inode)) {
		ret = ext4_walk_page_buffers(handle, page_buffers(page),
					     from, to, NULL,
					     do_journal_get_write_access);
	}

	if (ret) {
		unlock_page(page);
		page_cache_release(page);
598
		page = NULL;
599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
		ext4_orphan_add(handle, inode);
		up_write(&EXT4_I(inode)->xattr_sem);
		sem_held = 0;
		ext4_journal_stop(handle);
		handle = NULL;
		ext4_truncate_failed_write(inode);
		/*
		 * If truncate failed early the inode might
		 * still be on the orphan list; we need to
		 * make sure the inode is removed from the
		 * orphan list in that case.
		 */
		if (inode->i_nlink)
			ext4_orphan_del(NULL, inode);
	}

	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
		goto retry;

618 619
	if (page)
		block_commit_write(page, from, to);
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660
out:
	if (page) {
		unlock_page(page);
		page_cache_release(page);
	}
	if (sem_held)
		up_write(&EXT4_I(inode)->xattr_sem);
	if (handle)
		ext4_journal_stop(handle);
	brelse(iloc.bh);
	return ret;
}

/*
 * Try to write data in the inode.
 * If the inode has inline data, check whether the new write can be
 * in the inode also. If not, create the page the handle, move the data
 * to the page make it update and let the later codes create extent for it.
 */
int ext4_try_to_write_inline_data(struct address_space *mapping,
				  struct inode *inode,
				  loff_t pos, unsigned len,
				  unsigned flags,
				  struct page **pagep)
{
	int ret;
	handle_t *handle;
	struct page *page;
	struct ext4_iloc iloc;

	if (pos + len > ext4_get_max_inline_size(inode))
		goto convert;

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

	/*
	 * The possible write could happen in the inode,
	 * so try to reserve the space in inode first.
	 */
661
	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		handle = NULL;
		goto out;
	}

	ret = ext4_prepare_inline_data(handle, inode, pos + len);
	if (ret && ret != -ENOSPC)
		goto out;

	/* We don't have space in inline inode, so convert it to extent. */
	if (ret == -ENOSPC) {
		ext4_journal_stop(handle);
		brelse(iloc.bh);
		goto convert;
	}

	flags |= AOP_FLAG_NOFS;

	page = grab_cache_page_write_begin(mapping, 0, flags);
	if (!page) {
		ret = -ENOMEM;
		goto out;
	}

	*pagep = page;
	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		ret = 0;
		unlock_page(page);
		page_cache_release(page);
		goto out_up_read;
	}

	if (!PageUptodate(page)) {
		ret = ext4_read_inline_page(inode, page);
		if (ret < 0)
			goto out_up_read;
	}

	ret = 1;
	handle = NULL;
out_up_read:
	up_read(&EXT4_I(inode)->xattr_sem);
out:
	if (handle)
		ext4_journal_stop(handle);
	brelse(iloc.bh);
	return ret;
convert:
	return ext4_convert_inline_data_to_extent(mapping,
						  inode, flags);
}

int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
			       unsigned copied, struct page *page)
{
	int ret;
	void *kaddr;
	struct ext4_iloc iloc;

	if (unlikely(copied < len)) {
		if (!PageUptodate(page)) {
			copied = 0;
			goto out;
		}
	}

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret) {
		ext4_std_error(inode->i_sb, ret);
		copied = 0;
		goto out;
	}

	down_write(&EXT4_I(inode)->xattr_sem);
	BUG_ON(!ext4_has_inline_data(inode));

	kaddr = kmap_atomic(page);
	ext4_write_inline_data(inode, &iloc, kaddr, pos, len);
	kunmap_atomic(kaddr);
	SetPageUptodate(page);
	/* clear page dirty so that writepages wouldn't work for us. */
	ClearPageDirty(page);

	up_write(&EXT4_I(inode)->xattr_sem);
	brelse(iloc.bh);
out:
	return copied;
}

753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
struct buffer_head *
ext4_journalled_write_inline_data(struct inode *inode,
				  unsigned len,
				  struct page *page)
{
	int ret;
	void *kaddr;
	struct ext4_iloc iloc;

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret) {
		ext4_std_error(inode->i_sb, ret);
		return NULL;
	}

	down_write(&EXT4_I(inode)->xattr_sem);
	kaddr = kmap_atomic(page);
	ext4_write_inline_data(inode, &iloc, kaddr, 0, len);
	kunmap_atomic(kaddr);
	up_write(&EXT4_I(inode)->xattr_sem);

	return iloc.bh;
}

777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814
/*
 * Try to make the page cache and handle ready for the inline data case.
 * We can call this function in 2 cases:
 * 1. The inode is created and the first write exceeds inline size. We can
 *    clear the inode state safely.
 * 2. The inode has inline data, then we need to read the data, make it
 *    update and dirty so that ext4_da_writepages can handle it. We don't
 *    need to start the journal since the file's metatdata isn't changed now.
 */
static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
						 struct inode *inode,
						 unsigned flags,
						 void **fsdata)
{
	int ret = 0, inline_size;
	struct page *page;

	page = grab_cache_page_write_begin(mapping, 0, flags);
	if (!page)
		return -ENOMEM;

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
		goto out;
	}

	inline_size = ext4_get_inline_size(inode);

	if (!PageUptodate(page)) {
		ret = ext4_read_inline_page(inode, page);
		if (ret < 0)
			goto out;
	}

	ret = __block_write_begin(page, 0, inline_size,
				  ext4_da_get_block_prep);
	if (ret) {
815 816 817
		up_read(&EXT4_I(inode)->xattr_sem);
		unlock_page(page);
		page_cache_release(page);
818
		ext4_truncate_failed_write(inode);
819
		return ret;
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
	}

	SetPageDirty(page);
	SetPageUptodate(page);
	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
	*fsdata = (void *)CONVERT_INLINE_DATA;

out:
	up_read(&EXT4_I(inode)->xattr_sem);
	if (page) {
		unlock_page(page);
		page_cache_release(page);
	}
	return ret;
}

/*
 * Prepare the write for the inline data.
 * If the the data can be written into the inode, we just read
 * the page and make it uptodate, and start the journal.
 * Otherwise read the page, makes it dirty so that it can be
 * handle in writepages(the i_disksize update is left to the
 * normal ext4_da_write_end).
 */
int ext4_da_write_inline_data_begin(struct address_space *mapping,
				    struct inode *inode,
				    loff_t pos, unsigned len,
				    unsigned flags,
				    struct page **pagep,
				    void **fsdata)
{
	int ret, inline_size;
	handle_t *handle;
	struct page *page;
	struct ext4_iloc iloc;
855
	int retries;
856 857 858 859 860

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

861
retry_journal:
862
	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
863 864 865 866 867 868 869 870 871 872 873
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out;
	}

	inline_size = ext4_get_max_inline_size(inode);

	ret = -ENOSPC;
	if (inline_size >= pos + len) {
		ret = ext4_prepare_inline_data(handle, inode, pos + len);
		if (ret && ret != -ENOSPC)
874
			goto out_journal;
875 876
	}

877 878 879 880 881 882
	/*
	 * We cannot recurse into the filesystem as the transaction
	 * is already started.
	 */
	flags |= AOP_FLAG_NOFS;

883 884 885 886 887
	if (ret == -ENOSPC) {
		ret = ext4_da_convert_inline_data_to_extent(mapping,
							    inode,
							    flags,
							    fsdata);
888 889 890 891
		ext4_journal_stop(handle);
		if (ret == -ENOSPC &&
		    ext4_should_retry_alloc(inode->i_sb, &retries))
			goto retry_journal;
892 893 894 895 896 897 898
		goto out;
	}


	page = grab_cache_page_write_begin(mapping, 0, flags);
	if (!page) {
		ret = -ENOMEM;
899
		goto out_journal;
900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921
	}

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		ret = 0;
		goto out_release_page;
	}

	if (!PageUptodate(page)) {
		ret = ext4_read_inline_page(inode, page);
		if (ret < 0)
			goto out_release_page;
	}

	up_read(&EXT4_I(inode)->xattr_sem);
	*pagep = page;
	brelse(iloc.bh);
	return 1;
out_release_page:
	up_read(&EXT4_I(inode)->xattr_sem);
	unlock_page(page);
	page_cache_release(page);
922 923
out_journal:
	ext4_journal_stop(handle);
924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
out:
	brelse(iloc.bh);
	return ret;
}

int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
				  unsigned len, unsigned copied,
				  struct page *page)
{
	int i_size_changed = 0;

	copied = ext4_write_inline_data_end(inode, pos, len, copied, page);

	/*
	 * No need to use i_size_read() here, the i_size
	 * cannot change under us because we hold i_mutex.
	 *
	 * But it's important to update i_size while still holding page lock:
	 * page writeout could otherwise come in and zero beyond i_size.
	 */
	if (pos+copied > inode->i_size) {
		i_size_write(inode, pos+copied);
		i_size_changed = 1;
	}
	unlock_page(page);
	page_cache_release(page);

	/*
	 * Don't mark the inode dirty under page lock. First, it unnecessarily
	 * makes the holding time of page lock longer. Second, it forces lock
	 * ordering of page lock and transaction start for journaling
	 * filesystems.
	 */
	if (i_size_changed)
		mark_inode_dirty(inode);

	return copied;
}
962

963 964 965 966 967 968 969 970 971 972 973 974 975
#ifdef INLINE_DIR_DEBUG
void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh,
			  void *inline_start, int inline_size)
{
	int offset;
	unsigned short de_len;
	struct ext4_dir_entry_2 *de = inline_start;
	void *dlimit = inline_start + inline_size;

	trace_printk("inode %lu\n", dir->i_ino);
	offset = 0;
	while ((void *)de < dlimit) {
		de_len = ext4_rec_len_from_disk(de->rec_len, inline_size);
976
		trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n",
977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996
			     offset, de_len, de->name_len, de->name,
			     de->name_len, le32_to_cpu(de->inode));
		if (ext4_check_dir_entry(dir, NULL, de, bh,
					 inline_start, inline_size, offset))
			BUG();

		offset += de_len;
		de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
	}
}
#else
#define ext4_show_inline_dir(dir, bh, inline_start, inline_size)
#endif

/*
 * Add a new entry into a inline dir.
 * It will return -ENOSPC if no space is available, and -EIO
 * and -EEXIST if directory entry already exists.
 */
static int ext4_add_dirent_to_inline(handle_t *handle,
997
				     struct ext4_filename *fname,
998
				     struct inode *dir,
999 1000 1001 1002 1003 1004 1005
				     struct inode *inode,
				     struct ext4_iloc *iloc,
				     void *inline_start, int inline_size)
{
	int		err;
	struct ext4_dir_entry_2 *de;

1006 1007
	err = ext4_find_dest_de(dir, inode, iloc->bh, inline_start,
				inline_size, fname, &de);
1008 1009 1010
	if (err)
		return err;

1011
	BUFFER_TRACE(iloc->bh, "get_write_access");
1012 1013 1014
	err = ext4_journal_get_write_access(handle, iloc->bh);
	if (err)
		return err;
1015
	ext4_insert_dentry(dir, inode, de, inline_size, fname);
1016 1017 1018 1019 1020 1021 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 1049 1050 1051 1052 1053 1054 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

	ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);

	/*
	 * XXX shouldn't update any times until successful
	 * completion of syscall, but too many callers depend
	 * on this.
	 *
	 * XXX similarly, too many callers depend on
	 * ext4_new_inode() setting the times, but error
	 * recovery deletes the inode, so the worst that can
	 * happen is that the times are slightly out of date
	 * and/or different from the directory change time.
	 */
	dir->i_mtime = dir->i_ctime = ext4_current_time(dir);
	ext4_update_dx_flag(dir);
	dir->i_version++;
	ext4_mark_inode_dirty(handle, dir);
	return 1;
}

static void *ext4_get_inline_xattr_pos(struct inode *inode,
				       struct ext4_iloc *iloc)
{
	struct ext4_xattr_entry *entry;
	struct ext4_xattr_ibody_header *header;

	BUG_ON(!EXT4_I(inode)->i_inline_off);

	header = IHDR(inode, ext4_raw_inode(iloc));
	entry = (struct ext4_xattr_entry *)((void *)ext4_raw_inode(iloc) +
					    EXT4_I(inode)->i_inline_off);

	return (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs);
}

/* Set the final de to cover the whole block. */
static void ext4_update_final_de(void *de_buf, int old_size, int new_size)
{
	struct ext4_dir_entry_2 *de, *prev_de;
	void *limit;
	int de_len;

	de = (struct ext4_dir_entry_2 *)de_buf;
	if (old_size) {
		limit = de_buf + old_size;
		do {
			prev_de = de;
			de_len = ext4_rec_len_from_disk(de->rec_len, old_size);
			de_buf += de_len;
			de = (struct ext4_dir_entry_2 *)de_buf;
		} while (de_buf < limit);

		prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size -
							old_size, new_size);
	} else {
		/* this is just created, so create an empty entry. */
		de->inode = 0;
		de->rec_len = ext4_rec_len_to_disk(new_size, new_size);
	}
}

static int ext4_update_inline_dir(handle_t *handle, struct inode *dir,
				  struct ext4_iloc *iloc)
{
	int ret;
	int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE;
	int new_size = get_max_inline_xattr_value_size(dir, iloc);

	if (new_size - old_size <= EXT4_DIR_REC_LEN(1))
		return -ENOSPC;

	ret = ext4_update_inline_data(handle, dir,
				      new_size + EXT4_MIN_INLINE_DATA_SIZE);
	if (ret)
		return ret;

	ext4_update_final_de(ext4_get_inline_xattr_pos(dir, iloc), old_size,
			     EXT4_I(dir)->i_inline_size -
						EXT4_MIN_INLINE_DATA_SIZE);
	dir->i_size = EXT4_I(dir)->i_disksize = EXT4_I(dir)->i_inline_size;
	return 0;
}

static void ext4_restore_inline_data(handle_t *handle, struct inode *inode,
				     struct ext4_iloc *iloc,
				     void *buf, int inline_size)
{
	ext4_create_inline_data(handle, inode, inline_size);
	ext4_write_inline_data(inode, iloc, buf, 0, inline_size);
	ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
}

static int ext4_finish_convert_inline_dir(handle_t *handle,
					  struct inode *inode,
					  struct buffer_head *dir_block,
					  void *buf,
					  int inline_size)
{
	int err, csum_size = 0, header_size = 0;
	struct ext4_dir_entry_2 *de;
	struct ext4_dir_entry_tail *t;
	void *target = dir_block->b_data;

	/*
	 * First create "." and ".." and then copy the dir information
	 * back to the block.
	 */
	de = (struct ext4_dir_entry_2 *)target;
	de = ext4_init_dot_dotdot(inode, de,
		inode->i_sb->s_blocksize, csum_size,
		le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1);
	header_size = (void *)de - target;

	memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
		inline_size - EXT4_INLINE_DOTDOT_SIZE);

1133
	if (ext4_has_metadata_csum(inode->i_sb))
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 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
		csum_size = sizeof(struct ext4_dir_entry_tail);

	inode->i_size = inode->i_sb->s_blocksize;
	i_size_write(inode, inode->i_sb->s_blocksize);
	EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
	ext4_update_final_de(dir_block->b_data,
			inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size,
			inode->i_sb->s_blocksize - csum_size);

	if (csum_size) {
		t = EXT4_DIRENT_TAIL(dir_block->b_data,
				     inode->i_sb->s_blocksize);
		initialize_dirent_tail(t, inode->i_sb->s_blocksize);
	}
	set_buffer_uptodate(dir_block);
	err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
	if (err)
		goto out;
	set_buffer_verified(dir_block);
out:
	return err;
}

static int ext4_convert_inline_data_nolock(handle_t *handle,
					   struct inode *inode,
					   struct ext4_iloc *iloc)
{
	int error;
	void *buf = NULL;
	struct buffer_head *data_bh = NULL;
	struct ext4_map_blocks map;
	int inline_size;

	inline_size = ext4_get_inline_size(inode);
	buf = kmalloc(inline_size, GFP_NOFS);
	if (!buf) {
		error = -ENOMEM;
		goto out;
	}

	error = ext4_read_inline_data(inode, buf, inline_size, iloc);
	if (error < 0)
		goto out;

1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
	/*
	 * Make sure the inline directory entries pass checks before we try to
	 * convert them, so that we avoid touching stuff that needs fsck.
	 */
	if (S_ISDIR(inode->i_mode)) {
		error = ext4_check_all_de(inode, iloc->bh,
					buf + EXT4_INLINE_DOTDOT_SIZE,
					inline_size - EXT4_INLINE_DOTDOT_SIZE);
		if (error)
			goto out;
	}

1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206
	error = ext4_destroy_inline_data_nolock(handle, inode);
	if (error)
		goto out;

	map.m_lblk = 0;
	map.m_len = 1;
	map.m_flags = 0;
	error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE);
	if (error < 0)
		goto out_restore;
	if (!(map.m_flags & EXT4_MAP_MAPPED)) {
		error = -EIO;
		goto out_restore;
	}

	data_bh = sb_getblk(inode->i_sb, map.m_pblk);
	if (!data_bh) {
1207
		error = -ENOMEM;
1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
		goto out_restore;
	}

	lock_buffer(data_bh);
	error = ext4_journal_get_create_access(handle, data_bh);
	if (error) {
		unlock_buffer(data_bh);
		error = -EIO;
		goto out_restore;
	}
	memset(data_bh->b_data, 0, inode->i_sb->s_blocksize);

	if (!S_ISDIR(inode->i_mode)) {
		memcpy(data_bh->b_data, buf, inline_size);
		set_buffer_uptodate(data_bh);
		error = ext4_handle_dirty_metadata(handle,
						   inode, data_bh);
	} else {
		error = ext4_finish_convert_inline_dir(handle, inode, data_bh,
						       buf, inline_size);
	}

	unlock_buffer(data_bh);
out_restore:
	if (error)
		ext4_restore_inline_data(handle, inode, iloc, buf, inline_size);

out:
	brelse(data_bh);
	kfree(buf);
	return error;
}

/*
 * Try to add the new entry to the inline data.
 * If succeeds, return 0. If not, extended the inline dir and copied data to
 * the new created block.
 */
1246
int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
1247
			      struct inode *dir, struct inode *inode)
1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264
{
	int ret, inline_size;
	void *inline_start;
	struct ext4_iloc iloc;

	ret = ext4_get_inode_loc(dir, &iloc);
	if (ret)
		return ret;

	down_write(&EXT4_I(dir)->xattr_sem);
	if (!ext4_has_inline_data(dir))
		goto out;

	inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
						 EXT4_INLINE_DOTDOT_SIZE;
	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;

1265
	ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc,
1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285
					inline_start, inline_size);
	if (ret != -ENOSPC)
		goto out;

	/* check whether it can be inserted to inline xattr space. */
	inline_size = EXT4_I(dir)->i_inline_size -
			EXT4_MIN_INLINE_DATA_SIZE;
	if (!inline_size) {
		/* Try to use the xattr space.*/
		ret = ext4_update_inline_dir(handle, dir, &iloc);
		if (ret && ret != -ENOSPC)
			goto out;

		inline_size = EXT4_I(dir)->i_inline_size -
				EXT4_MIN_INLINE_DATA_SIZE;
	}

	if (inline_size) {
		inline_start = ext4_get_inline_xattr_pos(dir, &iloc);

1286
		ret = ext4_add_dirent_to_inline(handle, fname, dir,
1287 1288
						inode, &iloc, inline_start,
						inline_size);
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307

		if (ret != -ENOSPC)
			goto out;
	}

	/*
	 * The inline space is filled up, so create a new block for it.
	 * As the extent tree will be created, we have to save the inline
	 * dir first.
	 */
	ret = ext4_convert_inline_data_nolock(handle, dir, &iloc);

out:
	ext4_mark_inode_dirty(handle, dir);
	up_write(&EXT4_I(dir)->xattr_sem);
	brelse(iloc.bh);
	return ret;
}

1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327
/*
 * This function fills a red-black tree with information from an
 * inlined dir.  It returns the number directory entries loaded
 * into the tree.  If there is an error it is returned in err.
 */
int htree_inlinedir_to_tree(struct file *dir_file,
			    struct inode *dir, ext4_lblk_t block,
			    struct dx_hash_info *hinfo,
			    __u32 start_hash, __u32 start_minor_hash,
			    int *has_inline_data)
{
	int err = 0, count = 0;
	unsigned int parent_ino;
	int pos;
	struct ext4_dir_entry_2 *de;
	struct inode *inode = file_inode(dir_file);
	int ret, inline_size = 0;
	struct ext4_iloc iloc;
	void *dir_buf = NULL;
	struct ext4_dir_entry_2 fake;
1328
	struct ext4_str tmp_str;
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 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		up_read(&EXT4_I(inode)->xattr_sem);
		*has_inline_data = 0;
		goto out;
	}

	inline_size = ext4_get_inline_size(inode);
	dir_buf = kmalloc(inline_size, GFP_NOFS);
	if (!dir_buf) {
		ret = -ENOMEM;
		up_read(&EXT4_I(inode)->xattr_sem);
		goto out;
	}

	ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
	up_read(&EXT4_I(inode)->xattr_sem);
	if (ret < 0)
		goto out;

	pos = 0;
	parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
	while (pos < inline_size) {
		/*
		 * As inlined dir doesn't store any information about '.' and
		 * only the inode number of '..' is stored, we have to handle
		 * them differently.
		 */
		if (pos == 0) {
			fake.inode = cpu_to_le32(inode->i_ino);
			fake.name_len = 1;
			strcpy(fake.name, ".");
			fake.rec_len = ext4_rec_len_to_disk(
						EXT4_DIR_REC_LEN(fake.name_len),
						inline_size);
			ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
			de = &fake;
			pos = EXT4_INLINE_DOTDOT_OFFSET;
		} else if (pos == EXT4_INLINE_DOTDOT_OFFSET) {
			fake.inode = cpu_to_le32(parent_ino);
			fake.name_len = 2;
			strcpy(fake.name, "..");
			fake.rec_len = ext4_rec_len_to_disk(
						EXT4_DIR_REC_LEN(fake.name_len),
						inline_size);
			ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
			de = &fake;
			pos = EXT4_INLINE_DOTDOT_SIZE;
		} else {
			de = (struct ext4_dir_entry_2 *)(dir_buf + pos);
			pos += ext4_rec_len_from_disk(de->rec_len, inline_size);
			if (ext4_check_dir_entry(inode, dir_file, de,
					 iloc.bh, dir_buf,
					 inline_size, pos)) {
				ret = count;
				goto out;
			}
		}

		ext4fs_dirhash(de->name, de->name_len, hinfo);
		if ((hinfo->hash < start_hash) ||
		    ((hinfo->hash == start_hash) &&
		     (hinfo->minor_hash < start_minor_hash)))
			continue;
		if (de->inode == 0)
			continue;
1400 1401 1402 1403
		tmp_str.name = de->name;
		tmp_str.len = de->name_len;
		err = ext4_htree_store_dirent(dir_file, hinfo->hash,
					      hinfo->minor_hash, de, &tmp_str);
1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416
		if (err) {
			count = err;
			goto out;
		}
		count++;
	}
	ret = count;
out:
	kfree(dir_buf);
	brelse(iloc.bh);
	return ret;
}

1417 1418 1419 1420 1421 1422 1423 1424
/*
 * So this function is called when the volume is mkfsed with
 * dir_index disabled. In order to keep f_pos persistent
 * after we convert from an inlined dir to a blocked based,
 * we just pretend that we are a normal dir and return the
 * offset as if '.' and '..' really take place.
 *
 */
A
Al Viro 已提交
1425 1426
int ext4_read_inline_dir(struct file *file,
			 struct dir_context *ctx,
T
Tao Ma 已提交
1427 1428 1429
			 int *has_inline_data)
{
	unsigned int offset, parent_ino;
A
Al Viro 已提交
1430
	int i;
T
Tao Ma 已提交
1431 1432
	struct ext4_dir_entry_2 *de;
	struct super_block *sb;
A
Al Viro 已提交
1433
	struct inode *inode = file_inode(file);
T
Tao Ma 已提交
1434 1435 1436
	int ret, inline_size = 0;
	struct ext4_iloc iloc;
	void *dir_buf = NULL;
1437
	int dotdot_offset, dotdot_size, extra_offset, extra_size;
T
Tao Ma 已提交
1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		up_read(&EXT4_I(inode)->xattr_sem);
		*has_inline_data = 0;
		goto out;
	}

	inline_size = ext4_get_inline_size(inode);
	dir_buf = kmalloc(inline_size, GFP_NOFS);
	if (!dir_buf) {
		ret = -ENOMEM;
		up_read(&EXT4_I(inode)->xattr_sem);
		goto out;
	}

	ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
	up_read(&EXT4_I(inode)->xattr_sem);
	if (ret < 0)
		goto out;

1463
	ret = 0;
T
Tao Ma 已提交
1464 1465
	sb = inode->i_sb;
	parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
A
Al Viro 已提交
1466
	offset = ctx->pos;
1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478

	/*
	 * dotdot_offset and dotdot_size is the real offset and
	 * size for ".." and "." if the dir is block based while
	 * the real size for them are only EXT4_INLINE_DOTDOT_SIZE.
	 * So we will use extra_offset and extra_size to indicate them
	 * during the inline dir iteration.
	 */
	dotdot_offset = EXT4_DIR_REC_LEN(1);
	dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2);
	extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
	extra_size = extra_offset + inline_size;
T
Tao Ma 已提交
1479

A
Al Viro 已提交
1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496
	/*
	 * If the version has changed since the last call to
	 * readdir(2), then we might be pointing to an invalid
	 * dirent right now.  Scan from the start of the inline
	 * dir to make sure.
	 */
	if (file->f_version != inode->i_version) {
		for (i = 0; i < extra_size && i < offset;) {
			/*
			 * "." is with offset 0 and
			 * ".." is dotdot_offset.
			 */
			if (!i) {
				i = dotdot_offset;
				continue;
			} else if (i == dotdot_offset) {
				i = dotdot_size;
1497 1498
				continue;
			}
A
Al Viro 已提交
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519
			/* for other entry, the real offset in
			 * the buf has to be tuned accordingly.
			 */
			de = (struct ext4_dir_entry_2 *)
				(dir_buf + i - extra_offset);
			/* It's too expensive to do a full
			 * dirent test each time round this
			 * loop, but we do have to test at
			 * least that it is non-zero.  A
			 * failure will be detected in the
			 * dirent test below. */
			if (ext4_rec_len_from_disk(de->rec_len, extra_size)
				< EXT4_DIR_REC_LEN(1))
				break;
			i += ext4_rec_len_from_disk(de->rec_len,
						    extra_size);
		}
		offset = i;
		ctx->pos = offset;
		file->f_version = inode->i_version;
	}
T
Tao Ma 已提交
1520

A
Al Viro 已提交
1521 1522 1523 1524 1525 1526 1527
	while (ctx->pos < extra_size) {
		if (ctx->pos == 0) {
			if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR))
				goto out;
			ctx->pos = dotdot_offset;
			continue;
		}
T
Tao Ma 已提交
1528

A
Al Viro 已提交
1529 1530 1531 1532 1533 1534
		if (ctx->pos == dotdot_offset) {
			if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR))
				goto out;
			ctx->pos = dotdot_size;
			continue;
		}
T
Tao Ma 已提交
1535

A
Al Viro 已提交
1536 1537 1538 1539 1540 1541 1542 1543 1544
		de = (struct ext4_dir_entry_2 *)
			(dir_buf + ctx->pos - extra_offset);
		if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf,
					 extra_size, ctx->pos))
			goto out;
		if (le32_to_cpu(de->inode)) {
			if (!dir_emit(ctx, de->name, de->name_len,
				      le32_to_cpu(de->inode),
				      get_dtype(sb, de->file_type)))
T
Tao Ma 已提交
1545 1546
				goto out;
		}
A
Al Viro 已提交
1547
		ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size);
T
Tao Ma 已提交
1548 1549 1550 1551 1552 1553 1554
	}
out:
	kfree(dir_buf);
	brelse(iloc.bh);
	return ret;
}

T
Tao Ma 已提交
1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569
struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
					struct ext4_dir_entry_2 **parent_de,
					int *retval)
{
	struct ext4_iloc iloc;

	*retval = ext4_get_inode_loc(inode, &iloc);
	if (*retval)
		return NULL;

	*parent_de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block;

	return iloc.bh;
}

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 1599 1600 1601 1602 1603 1604 1605 1606 1607
/*
 * Try to create the inline data for the new dir.
 * If it succeeds, return 0, otherwise return the error.
 * In case of ENOSPC, the caller should create the normal disk layout dir.
 */
int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent,
			       struct inode *inode)
{
	int ret, inline_size = EXT4_MIN_INLINE_DATA_SIZE;
	struct ext4_iloc iloc;
	struct ext4_dir_entry_2 *de;

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

	ret = ext4_prepare_inline_data(handle, inode, inline_size);
	if (ret)
		goto out;

	/*
	 * For inline dir, we only save the inode information for the ".."
	 * and create a fake dentry to cover the left space.
	 */
	de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block;
	de->inode = cpu_to_le32(parent->i_ino);
	de = (struct ext4_dir_entry_2 *)((void *)de + EXT4_INLINE_DOTDOT_SIZE);
	de->inode = 0;
	de->rec_len = ext4_rec_len_to_disk(
				inline_size - EXT4_INLINE_DOTDOT_SIZE,
				inline_size);
	set_nlink(inode, 2);
	inode->i_size = EXT4_I(inode)->i_disksize = inline_size;
out:
	brelse(iloc.bh);
	return ret;
}

1608
struct buffer_head *ext4_find_inline_entry(struct inode *dir,
1609
					struct ext4_filename *fname,
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
					const struct qstr *d_name,
					struct ext4_dir_entry_2 **res_dir,
					int *has_inline_data)
{
	int ret;
	struct ext4_iloc iloc;
	void *inline_start;
	int inline_size;

	if (ext4_get_inode_loc(dir, &iloc))
		return NULL;

	down_read(&EXT4_I(dir)->xattr_sem);
	if (!ext4_has_inline_data(dir)) {
		*has_inline_data = 0;
		goto out;
	}

	inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
						EXT4_INLINE_DOTDOT_SIZE;
	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
1631 1632
	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
			      dir, fname, d_name, 0, res_dir);
1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643
	if (ret == 1)
		goto out_find;
	if (ret < 0)
		goto out;

	if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE)
		goto out;

	inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
	inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;

1644 1645
	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
			      dir, fname, d_name, 0, res_dir);
1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656
	if (ret == 1)
		goto out_find;

out:
	brelse(iloc.bh);
	iloc.bh = NULL;
out_find:
	up_read(&EXT4_I(dir)->xattr_sem);
	return iloc.bh;
}

1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688
int ext4_delete_inline_entry(handle_t *handle,
			     struct inode *dir,
			     struct ext4_dir_entry_2 *de_del,
			     struct buffer_head *bh,
			     int *has_inline_data)
{
	int err, inline_size;
	struct ext4_iloc iloc;
	void *inline_start;

	err = ext4_get_inode_loc(dir, &iloc);
	if (err)
		return err;

	down_write(&EXT4_I(dir)->xattr_sem);
	if (!ext4_has_inline_data(dir)) {
		*has_inline_data = 0;
		goto out;
	}

	if ((void *)de_del - ((void *)ext4_raw_inode(&iloc)->i_block) <
		EXT4_MIN_INLINE_DATA_SIZE) {
		inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
					EXT4_INLINE_DOTDOT_SIZE;
		inline_size = EXT4_MIN_INLINE_DATA_SIZE -
				EXT4_INLINE_DOTDOT_SIZE;
	} else {
		inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
		inline_size = ext4_get_inline_size(dir) -
				EXT4_MIN_INLINE_DATA_SIZE;
	}

1689
	BUFFER_TRACE(bh, "get_write_access");
1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712
	err = ext4_journal_get_write_access(handle, bh);
	if (err)
		goto out;

	err = ext4_generic_delete_entry(handle, dir, de_del, bh,
					inline_start, inline_size, 0);
	if (err)
		goto out;

	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
	err = ext4_mark_inode_dirty(handle, dir);
	if (unlikely(err))
		goto out;

	ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);
out:
	up_write(&EXT4_I(dir)->xattr_sem);
	brelse(iloc.bh);
	if (err != -ENOENT)
		ext4_std_error(dir->i_sb, err);
	return err;
}

T
Tao Ma 已提交
1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802
/*
 * Get the inline dentry at offset.
 */
static inline struct ext4_dir_entry_2 *
ext4_get_inline_entry(struct inode *inode,
		      struct ext4_iloc *iloc,
		      unsigned int offset,
		      void **inline_start,
		      int *inline_size)
{
	void *inline_pos;

	BUG_ON(offset > ext4_get_inline_size(inode));

	if (offset < EXT4_MIN_INLINE_DATA_SIZE) {
		inline_pos = (void *)ext4_raw_inode(iloc)->i_block;
		*inline_size = EXT4_MIN_INLINE_DATA_SIZE;
	} else {
		inline_pos = ext4_get_inline_xattr_pos(inode, iloc);
		offset -= EXT4_MIN_INLINE_DATA_SIZE;
		*inline_size = ext4_get_inline_size(inode) -
				EXT4_MIN_INLINE_DATA_SIZE;
	}

	if (inline_start)
		*inline_start = inline_pos;
	return (struct ext4_dir_entry_2 *)(inline_pos + offset);
}

int empty_inline_dir(struct inode *dir, int *has_inline_data)
{
	int err, inline_size;
	struct ext4_iloc iloc;
	void *inline_pos;
	unsigned int offset;
	struct ext4_dir_entry_2 *de;
	int ret = 1;

	err = ext4_get_inode_loc(dir, &iloc);
	if (err) {
		EXT4_ERROR_INODE(dir, "error %d getting inode %lu block",
				 err, dir->i_ino);
		return 1;
	}

	down_read(&EXT4_I(dir)->xattr_sem);
	if (!ext4_has_inline_data(dir)) {
		*has_inline_data = 0;
		goto out;
	}

	de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block;
	if (!le32_to_cpu(de->inode)) {
		ext4_warning(dir->i_sb,
			     "bad inline directory (dir #%lu) - no `..'",
			     dir->i_ino);
		ret = 1;
		goto out;
	}

	offset = EXT4_INLINE_DOTDOT_SIZE;
	while (offset < dir->i_size) {
		de = ext4_get_inline_entry(dir, &iloc, offset,
					   &inline_pos, &inline_size);
		if (ext4_check_dir_entry(dir, NULL, de,
					 iloc.bh, inline_pos,
					 inline_size, offset)) {
			ext4_warning(dir->i_sb,
				     "bad inline directory (dir #%lu) - "
				     "inode %u, rec_len %u, name_len %d"
				     "inline size %d\n",
				     dir->i_ino, le32_to_cpu(de->inode),
				     le16_to_cpu(de->rec_len), de->name_len,
				     inline_size);
			ret = 1;
			goto out;
		}
		if (le32_to_cpu(de->inode)) {
			ret = 0;
			goto out;
		}
		offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
	}

out:
	up_read(&EXT4_I(dir)->xattr_sem);
	brelse(iloc.bh);
	return ret;
}

1803 1804 1805 1806 1807 1808 1809 1810 1811 1812
int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
{
	int ret;

	down_write(&EXT4_I(inode)->xattr_sem);
	ret = ext4_destroy_inline_data_nolock(handle, inode);
	up_write(&EXT4_I(inode)->xattr_sem);

	return ret;
}
T
Tao Ma 已提交
1813 1814 1815

int ext4_inline_data_fiemap(struct inode *inode,
			    struct fiemap_extent_info *fieinfo,
1816
			    int *has_inline, __u64 start, __u64 len)
T
Tao Ma 已提交
1817 1818
{
	__u64 physical = 0;
1819 1820 1821
	__u64 inline_len;
	__u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
		FIEMAP_EXTENT_LAST;
T
Tao Ma 已提交
1822 1823 1824 1825 1826 1827 1828 1829
	int error = 0;
	struct ext4_iloc iloc;

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		*has_inline = 0;
		goto out;
	}
1830 1831 1832 1833 1834 1835 1836
	inline_len = min_t(size_t, ext4_get_inline_size(inode),
			   i_size_read(inode));
	if (start >= inline_len)
		goto out;
	if (start + len < inline_len)
		inline_len = start + len;
	inline_len -= start;
T
Tao Ma 已提交
1837 1838 1839 1840 1841

	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		goto out;

1842
	physical = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits;
T
Tao Ma 已提交
1843 1844 1845 1846
	physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data;
	physical += offsetof(struct ext4_inode, i_block);

	if (physical)
1847 1848
		error = fiemap_fill_next_extent(fieinfo, start, physical,
						inline_len, flags);
T
Tao Ma 已提交
1849 1850 1851 1852 1853
	brelse(iloc.bh);
out:
	up_read(&EXT4_I(inode)->xattr_sem);
	return (error < 0 ? error : 0);
}
1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889

/*
 * Called during xattr set, and if we can sparse space 'needed',
 * just create the extent tree evict the data to the outer block.
 *
 * We use jbd2 instead of page cache to move data to the 1st block
 * so that the whole transaction can be committed as a whole and
 * the data isn't lost because of the delayed page cache write.
 */
int ext4_try_to_evict_inline_data(handle_t *handle,
				  struct inode *inode,
				  int needed)
{
	int error;
	struct ext4_xattr_entry *entry;
	struct ext4_inode *raw_inode;
	struct ext4_iloc iloc;

	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		return error;

	raw_inode = ext4_raw_inode(&iloc);
	entry = (struct ext4_xattr_entry *)((void *)raw_inode +
					    EXT4_I(inode)->i_inline_off);
	if (EXT4_XATTR_LEN(entry->e_name_len) +
	    EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
		error = -ENOSPC;
		goto out;
	}

	error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
out:
	brelse(iloc.bh);
	return error;
}
1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906

void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
	handle_t *handle;
	int inline_size, value_len, needed_blocks;
	size_t i_size;
	void *value = NULL;
	struct ext4_xattr_ibody_find is = {
		.s = { .not_found = -ENODATA, },
	};
	struct ext4_xattr_info i = {
		.name_index = EXT4_XATTR_INDEX_SYSTEM,
		.name = EXT4_XATTR_SYSTEM_DATA,
	};


	needed_blocks = ext4_writepage_trans_blocks(inode);
1907
	handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953
	if (IS_ERR(handle))
		return;

	down_write(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		*has_inline = 0;
		ext4_journal_stop(handle);
		return;
	}

	if (ext4_orphan_add(handle, inode))
		goto out;

	if (ext4_get_inode_loc(inode, &is.iloc))
		goto out;

	down_write(&EXT4_I(inode)->i_data_sem);
	i_size = inode->i_size;
	inline_size = ext4_get_inline_size(inode);
	EXT4_I(inode)->i_disksize = i_size;

	if (i_size < inline_size) {
		/* Clear the content in the xattr space. */
		if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
			if (ext4_xattr_ibody_find(inode, &i, &is))
				goto out_error;

			BUG_ON(is.s.not_found);

			value_len = le32_to_cpu(is.s.here->e_value_size);
			value = kmalloc(value_len, GFP_NOFS);
			if (!value)
				goto out_error;

			if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
						value, value_len))
				goto out_error;

			i.value = value;
			i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
					i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
			if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
				goto out_error;
		}

		/* Clear the content within i_blocks. */
1954 1955 1956 1957 1958
		if (i_size < EXT4_MIN_INLINE_DATA_SIZE) {
			void *p = (void *) ext4_raw_inode(&is.iloc)->i_block;
			memset(p + i_size, 0,
			       EXT4_MIN_INLINE_DATA_SIZE - i_size);
		}
1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981

		EXT4_I(inode)->i_inline_size = i_size <
					EXT4_MIN_INLINE_DATA_SIZE ?
					EXT4_MIN_INLINE_DATA_SIZE : i_size;
	}

out_error:
	up_write(&EXT4_I(inode)->i_data_sem);
out:
	brelse(is.iloc.bh);
	up_write(&EXT4_I(inode)->xattr_sem);
	kfree(value);
	if (inode->i_nlink)
		ext4_orphan_del(handle, inode);

	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
	ext4_mark_inode_dirty(handle, inode);
	if (IS_SYNC(inode))
		ext4_handle_sync(handle);

	ext4_journal_stop(handle);
	return;
}
1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000

int ext4_convert_inline_data(struct inode *inode)
{
	int error, needed_blocks;
	handle_t *handle;
	struct ext4_iloc iloc;

	if (!ext4_has_inline_data(inode)) {
		ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
		return 0;
	}

	needed_blocks = ext4_writepage_trans_blocks(inode);

	iloc.bh = NULL;
	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		return error;

2001
	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020
	if (IS_ERR(handle)) {
		error = PTR_ERR(handle);
		goto out_free;
	}

	down_write(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		up_write(&EXT4_I(inode)->xattr_sem);
		goto out;
	}

	error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
	up_write(&EXT4_I(inode)->xattr_sem);
out:
	ext4_journal_stop(handle);
out_free:
	brelse(iloc.bh);
	return error;
}