inline.c 22.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * 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.
 */
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
17
#include "truncate.h"
18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457

#define EXT4_XATTR_SYSTEM_DATA	"data"
#define EXT4_MIN_INLINE_DATA_SIZE	((sizeof(__le32) * EXT4_N_BLOCKS))

int ext4_get_inline_size(struct inode *inode)
{
	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);

		free += le32_to_cpu(entry->e_value_size);
		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;
}

int ext4_has_inline_data(struct inode *inode)
{
	return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
	       EXT4_I(inode)->i_inline_off;
}

/*
 * 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
 * value since it is already handled by ext4_xattr_ibody_set. That saves
 * us one memcpy.
 */
void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
			    void *buffer, loff_t pos, unsigned int len)
{
	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;

	error = ext4_journal_get_write_access(handle, is.iloc.bh);
	if (error)
		goto out;

	if (len > EXT4_MIN_INLINE_DATA_SIZE) {
		value = (void *)empty_zero_page;
		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);

	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
	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;

	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;

	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
	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;
}

int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
			     unsigned int len)
{
	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;

	error = ext4_journal_get_write_access(handle, is.iloc.bh);
	if (error)
		goto out;

	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
	if (error)
		goto out;

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

	if (EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
				      EXT4_FEATURE_INCOMPAT_EXTENTS)) {
		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
458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518
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;
}

519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
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:
	handle = ext4_journal_start(inode, needed_blocks);
	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);
		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;

	block_commit_write(page, from, to);
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.
	 */
	handle = ext4_journal_start(inode, 1);
	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;
}

750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773
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;
}

774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
/*
 * 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) {
		ext4_truncate_failed_write(inode);
		goto out;
	}

	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;

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

	handle = ext4_journal_start(inode, 1);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		handle = NULL;
		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)
			goto out;
	}

	if (ret == -ENOSPC) {
		ret = ext4_da_convert_inline_data_to_extent(mapping,
							    inode,
							    flags,
							    fsdata);
		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_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;
	handle = NULL;
	brelse(iloc.bh);
	return 1;
out_release_page:
	up_read(&EXT4_I(inode)->xattr_sem);
	unlock_page(page);
	page_cache_release(page);
out:
	if (handle)
		ext4_journal_stop(handle);
	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;
}
951

952 953 954 955 956 957 958 959 960 961
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;
}