move_extent.c 42.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd.
 * Written by Takashi Sato <t-sato@yk.jp.nec.com>
 *            Akira Fujita <a-fujita@rs.jp.nec.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 <linux/fs.h>
#include <linux/quotaops.h>
18
#include <linux/slab.h>
19 20 21
#include "ext4_jbd2.h"
#include "ext4.h"

22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41
/**
 * get_ext_path - Find an extent path for designated logical block number.
 *
 * @inode:	an inode which is searched
 * @lblock:	logical block number to find an extent path
 * @path:	pointer to an extent path pointer (for output)
 *
 * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value
 * on failure.
 */
static inline int
get_ext_path(struct inode *inode, ext4_lblk_t lblock,
		struct ext4_ext_path **path)
{
	int ret = 0;

	*path = ext4_ext_find_extent(inode, lblock, *path);
	if (IS_ERR(*path)) {
		ret = PTR_ERR(*path);
		*path = NULL;
42 43 44
	} else if ((*path)[ext_depth(inode)].p_ext == NULL)
		ret = -ENODATA;

45 46
	return ret;
}
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

/**
 * copy_extent_status - Copy the extent's initialization status
 *
 * @src:	an extent for getting initialize status
 * @dest:	an extent to be set the status
 */
static void
copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
{
	if (ext4_ext_is_uninitialized(src))
		ext4_ext_mark_uninitialized(dest);
	else
		dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
}

/**
 * mext_next_extent - Search for the next extent and set it to "extent"
 *
 * @inode:	inode which is searched
 * @path:	this will obtain data for the next extent
 * @extent:	pointer to the next extent we have just gotten
 *
 * Search the next extent in the array of ext4_ext_path structure (@path)
 * and set it to ext4_extent structure (@extent). In addition, the member of
 * @path (->p_ext) also points the next extent. Return 0 on success, 1 if
 * ext4_ext_path structure refers to the last extent, or a negative error
 * value on failure.
 */
static int
mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
		      struct ext4_extent **extent)
{
80
	struct ext4_extent_header *eh;
81 82 83 84 85 86
	int ppos, leaf_ppos = path->p_depth;

	ppos = leaf_ppos;
	if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
		/* leaf block */
		*extent = ++path[ppos].p_ext;
87
		path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
88 89 90 91 92 93 94 95 96 97
		return 0;
	}

	while (--ppos >= 0) {
		if (EXT_LAST_INDEX(path[ppos].p_hdr) >
		    path[ppos].p_idx) {
			int cur_ppos = ppos;

			/* index block */
			path[ppos].p_idx++;
98
			path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
99 100 101 102 103 104 105 106 107 108 109 110 111 112
			if (path[ppos+1].p_bh)
				brelse(path[ppos+1].p_bh);
			path[ppos+1].p_bh =
				sb_bread(inode->i_sb, path[ppos].p_block);
			if (!path[ppos+1].p_bh)
				return -EIO;
			path[ppos+1].p_hdr =
				ext_block_hdr(path[ppos+1].p_bh);

			/* Halfway index block */
			while (++cur_ppos < leaf_ppos) {
				path[cur_ppos].p_idx =
					EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
				path[cur_ppos].p_block =
113
					ext4_idx_pblock(path[cur_ppos].p_idx);
114 115 116 117 118 119 120 121 122 123
				if (path[cur_ppos+1].p_bh)
					brelse(path[cur_ppos+1].p_bh);
				path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
					path[cur_ppos].p_block);
				if (!path[cur_ppos+1].p_bh)
					return -EIO;
				path[cur_ppos+1].p_hdr =
					ext_block_hdr(path[cur_ppos+1].p_bh);
			}

124 125 126 127 128 129 130
			path[leaf_ppos].p_ext = *extent = NULL;

			eh = path[leaf_ppos].p_hdr;
			if (le16_to_cpu(eh->eh_entries) == 0)
				/* empty leaf is found */
				return -ENODATA;

131 132 133
			/* leaf block */
			path[leaf_ppos].p_ext = *extent =
				EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
134
			path[leaf_ppos].p_block =
135
					ext4_ext_pblock(path[leaf_ppos].p_ext);
136 137 138 139 140 141 142 143
			return 0;
		}
	}
	/* We found the last extent */
	return 1;
}

/**
144
 * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
145
 *
D
Dmitry Monakhov 已提交
146
 * Acquire write lock of i_data_sem of the two inodes
147 148
 */
static void
D
Dmitry Monakhov 已提交
149
double_down_write_data_sem(struct inode *first, struct inode *second)
150
{
D
Dmitry Monakhov 已提交
151 152 153 154 155 156
	if (first < second) {
		down_write(&EXT4_I(first)->i_data_sem);
		down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
	} else {
		down_write(&EXT4_I(second)->i_data_sem);
		down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
157 158 159 160 161

	}
}

/**
162
 * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
163 164 165
 *
 * @orig_inode:		original inode structure to be released its lock first
 * @donor_inode:	donor inode structure to be released its lock second
166
 * Release write lock of i_data_sem of two inodes (orig and donor).
167 168
 */
static void
169
double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
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
{
	up_write(&EXT4_I(orig_inode)->i_data_sem);
	up_write(&EXT4_I(donor_inode)->i_data_sem);
}

/**
 * mext_insert_across_blocks - Insert extents across leaf block
 *
 * @handle:		journal handle
 * @orig_inode:		original inode
 * @o_start:		first original extent to be changed
 * @o_end:		last original extent to be changed
 * @start_ext:		first new extent to be inserted
 * @new_ext:		middle of new extent to be inserted
 * @end_ext:		last new extent to be inserted
 *
 * Allocate a new leaf block and insert extents into it. Return 0 on success,
 * or a negative error value on failure.
 */
static int
mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
		struct ext4_extent *o_start, struct ext4_extent *o_end,
		struct ext4_extent *start_ext, struct ext4_extent *new_ext,
		struct ext4_extent *end_ext)
{
	struct ext4_ext_path *orig_path = NULL;
	ext4_lblk_t eblock = 0;
	int new_flag = 0;
	int end_flag = 0;
	int err = 0;

	if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) {
		if (o_start == o_end) {

			/*       start_ext   new_ext    end_ext
			 * donor |---------|-----------|--------|
			 * orig  |------------------------------|
			 */
			end_flag = 1;
		} else {

			/*       start_ext   new_ext   end_ext
			 * donor |---------|----------|---------|
			 * orig  |---------------|--------------|
			 */
			o_end->ee_block = end_ext->ee_block;
			o_end->ee_len = end_ext->ee_len;
217
			ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
218 219 220
		}

		o_start->ee_len = start_ext->ee_len;
221
		eblock = le32_to_cpu(start_ext->ee_block);
222 223 224 225 226 227 228 229 230 231
		new_flag = 1;

	} else if (start_ext->ee_len && new_ext->ee_len &&
		   !end_ext->ee_len && o_start == o_end) {

		/*	 start_ext	new_ext
		 * donor |--------------|---------------|
		 * orig  |------------------------------|
		 */
		o_start->ee_len = start_ext->ee_len;
232
		eblock = le32_to_cpu(start_ext->ee_block);
233 234 235 236 237 238 239 240 241 242 243
		new_flag = 1;

	} else if (!start_ext->ee_len && new_ext->ee_len &&
		   end_ext->ee_len && o_start == o_end) {

		/*	  new_ext	end_ext
		 * donor |--------------|---------------|
		 * orig  |------------------------------|
		 */
		o_end->ee_block = end_ext->ee_block;
		o_end->ee_len = end_ext->ee_len;
244
		ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
245 246 247 248 249 250 251 252 253 254 255 256 257 258 259

		/*
		 * Set 0 to the extent block if new_ext was
		 * the first block.
		 */
		if (new_ext->ee_block)
			eblock = le32_to_cpu(new_ext->ee_block);

		new_flag = 1;
	} else {
		ext4_debug("ext4 move extent: Unexpected insert case\n");
		return -EIO;
	}

	if (new_flag) {
260
		err = get_ext_path(orig_inode, eblock, &orig_path);
261
		if (err)
262 263 264
			goto out;

		if (ext4_ext_insert_extent(handle, orig_inode,
265
					orig_path, new_ext, 0))
266 267 268 269
			goto out;
	}

	if (end_flag) {
270 271
		err = get_ext_path(orig_inode,
				le32_to_cpu(end_ext->ee_block) - 1, &orig_path);
272
		if (err)
273 274 275
			goto out;

		if (ext4_ext_insert_extent(handle, orig_inode,
276
					   orig_path, end_ext, 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
			goto out;
	}
out:
	if (orig_path) {
		ext4_ext_drop_refs(orig_path);
		kfree(orig_path);
	}

	return err;

}

/**
 * mext_insert_inside_block - Insert new extent to the extent block
 *
 * @o_start:		first original extent to be moved
 * @o_end:		last original extent to be moved
 * @start_ext:		first new extent to be inserted
 * @new_ext:		middle of new extent to be inserted
 * @end_ext:		last new extent to be inserted
 * @eh:			extent header of target leaf block
 * @range_to_move:	used to decide how to insert extent
 *
 * Insert extents into the leaf block. The extent (@o_start) is overwritten
 * by inserted extents.
 */
static void
mext_insert_inside_block(struct ext4_extent *o_start,
			      struct ext4_extent *o_end,
			      struct ext4_extent *start_ext,
			      struct ext4_extent *new_ext,
			      struct ext4_extent *end_ext,
			      struct ext4_extent_header *eh,
			      int range_to_move)
{
	int i = 0;
	unsigned long len;

	/* Move the existing extents */
	if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) {
		len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) -
			(unsigned long)(o_end + 1);
		memmove(o_end + 1 + range_to_move, o_end + 1, len);
	}

	/* Insert start entry */
	if (start_ext->ee_len)
		o_start[i++].ee_len = start_ext->ee_len;

	/* Insert new entry */
	if (new_ext->ee_len) {
		o_start[i] = *new_ext;
329
		ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
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
	}

	/* Insert end entry */
	if (end_ext->ee_len)
		o_start[i] = *end_ext;

	/* Increment the total entries counter on the extent block */
	le16_add_cpu(&eh->eh_entries, range_to_move);
}

/**
 * mext_insert_extents - Insert new extent
 *
 * @handle:	journal handle
 * @orig_inode:	original inode
 * @orig_path:	path indicates first extent to be changed
 * @o_start:	first original extent to be changed
 * @o_end:	last original extent to be changed
 * @start_ext:	first new extent to be inserted
 * @new_ext:	middle of new extent to be inserted
 * @end_ext:	last new extent to be inserted
 *
 * Call the function to insert extents. If we cannot add more extents into
 * the leaf block, we call mext_insert_across_blocks() to create a
 * new leaf block. Otherwise call mext_insert_inside_block(). Return 0
 * on success, or a negative error value on failure.
 */
static int
mext_insert_extents(handle_t *handle, struct inode *orig_inode,
			 struct ext4_ext_path *orig_path,
			 struct ext4_extent *o_start,
			 struct ext4_extent *o_end,
			 struct ext4_extent *start_ext,
			 struct ext4_extent *new_ext,
			 struct ext4_extent *end_ext)
{
	struct  ext4_extent_header *eh;
	unsigned long need_slots, slots_range;
	int	range_to_move, depth, ret;

	/*
	 * The extents need to be inserted
	 * start_extent + new_extent + end_extent.
	 */
	need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) +
		(new_ext->ee_len ? 1 : 0);

	/* The number of slots between start and end */
	slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1)
		/ sizeof(struct ext4_extent);

	/* Range to move the end of extent */
	range_to_move = need_slots - slots_range;
	depth = orig_path->p_depth;
	orig_path += depth;
	eh = orig_path->p_hdr;

	if (depth) {
		/* Register to journal */
		ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
		if (ret)
			return ret;
	}

	/* Expansion */
	if (range_to_move > 0 &&
		(range_to_move > le16_to_cpu(eh->eh_max)
			- le16_to_cpu(eh->eh_entries))) {

		ret = mext_insert_across_blocks(handle, orig_inode, o_start,
					o_end, start_ext, new_ext, end_ext);
		if (ret < 0)
			return ret;
	} else
		mext_insert_inside_block(o_start, o_end, start_ext, new_ext,
						end_ext, eh, range_to_move);

	if (depth) {
		ret = ext4_handle_dirty_metadata(handle, orig_inode,
						 orig_path->p_bh);
		if (ret)
			return ret;
	} else {
		ret = ext4_mark_inode_dirty(handle, orig_inode);
		if (ret < 0)
			return ret;
	}

	return 0;
}

/**
 * mext_leaf_block - Move one leaf extent block into the inode.
 *
 * @handle:		journal handle
 * @orig_inode:		original inode
 * @orig_path:		path indicates first extent to be changed
 * @dext:		donor extent
 * @from:		start offset on the target file
 *
 * In order to insert extents into the leaf block, we must divide the extent
 * in the leaf block into three extents. The one is located to be inserted
 * extents, and the others are located around it.
 *
 * Therefore, this function creates structures to save extents of the leaf
 * block, and inserts extents by calling mext_insert_extents() with
 * created extents. Return 0 on success, or a negative error value on failure.
 */
static int
mext_leaf_block(handle_t *handle, struct inode *orig_inode,
		     struct ext4_ext_path *orig_path, struct ext4_extent *dext,
		     ext4_lblk_t *from)
{
	struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
	struct ext4_extent new_ext, start_ext, end_ext;
	ext4_lblk_t new_ext_end;
	int oext_alen, new_ext_alen, end_ext_alen;
	int depth = ext_depth(orig_inode);
	int ret;

450
	start_ext.ee_block = end_ext.ee_block = 0;
451 452 453 454 455
	o_start = o_end = oext = orig_path[depth].p_ext;
	oext_alen = ext4_ext_get_actual_len(oext);
	start_ext.ee_len = end_ext.ee_len = 0;

	new_ext.ee_block = cpu_to_le32(*from);
456
	ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
	new_ext.ee_len = dext->ee_len;
	new_ext_alen = ext4_ext_get_actual_len(&new_ext);
	new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;

	/*
	 * Case: original extent is first
	 * oext      |--------|
	 * new_ext      |--|
	 * start_ext |--|
	 */
	if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) &&
		le32_to_cpu(new_ext.ee_block) <
		le32_to_cpu(oext->ee_block) + oext_alen) {
		start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
					       le32_to_cpu(oext->ee_block));
472
		start_ext.ee_block = oext->ee_block;
473 474 475 476 477 478 479 480 481 482 483 484 485
		copy_extent_status(oext, &start_ext);
	} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
		prev_ext = oext - 1;
		/*
		 * We can merge new_ext into previous extent,
		 * if these are contiguous and same extent type.
		 */
		if (ext4_can_extents_be_merged(orig_inode, prev_ext,
					       &new_ext)) {
			o_start = prev_ext;
			start_ext.ee_len = cpu_to_le16(
				ext4_ext_get_actual_len(prev_ext) +
				new_ext_alen);
486
			start_ext.ee_block = oext->ee_block;
487 488 489 490 491 492 493 494 495 496
			copy_extent_status(prev_ext, &start_ext);
			new_ext.ee_len = 0;
		}
	}

	/*
	 * Case: new_ext_end must be less than oext
	 * oext      |-----------|
	 * new_ext       |-------|
	 */
497
	if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
498
		EXT4_ERROR_INODE(orig_inode,
499 500 501 502 503 504 505
			"new_ext_end(%u) should be less than or equal to "
			"oext->ee_block(%u) + oext_alen(%d) - 1",
			new_ext_end, le32_to_cpu(oext->ee_block),
			oext_alen);
		ret = -EIO;
		goto out;
	}
506 507 508 509 510 511 512 513 514 515 516 517 518 519 520

	/*
	 * Case: new_ext is smaller than original extent
	 * oext    |---------------|
	 * new_ext |-----------|
	 * end_ext             |---|
	 */
	if (le32_to_cpu(oext->ee_block) <= new_ext_end &&
		new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) {
		end_ext.ee_len =
			cpu_to_le16(le32_to_cpu(oext->ee_block) +
			oext_alen - 1 - new_ext_end);
		copy_extent_status(oext, &end_ext);
		end_ext_alen = ext4_ext_get_actual_len(&end_ext);
		ext4_ext_store_pblock(&end_ext,
521
			(ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
522 523 524 525 526 527 528
		end_ext.ee_block =
			cpu_to_le32(le32_to_cpu(o_end->ee_block) +
			oext_alen - end_ext_alen);
	}

	ret = mext_insert_extents(handle, orig_inode, orig_path, o_start,
				o_end, &start_ext, &new_ext, &end_ext);
529
out:
530 531 532 533 534 535 536 537 538 539
	return ret;
}

/**
 * mext_calc_swap_extents - Calculate extents for extent swapping.
 *
 * @tmp_dext:		the extent that will belong to the original inode
 * @tmp_oext:		the extent that will belong to the donor inode
 * @orig_off:		block offset of original inode
 * @donor_off:		block offset of donor inode
540
 * @max_count:		the maximum length of extents
541 542
 *
 * Return 0 on success, or a negative error value on failure.
543
 */
544
static int
545 546 547 548 549 550 551 552
mext_calc_swap_extents(struct ext4_extent *tmp_dext,
			      struct ext4_extent *tmp_oext,
			      ext4_lblk_t orig_off, ext4_lblk_t donor_off,
			      ext4_lblk_t max_count)
{
	ext4_lblk_t diff, orig_diff;
	struct ext4_extent dext_old, oext_old;

553 554 555 556 557 558 559 560 561 562 563 564 565
	BUG_ON(orig_off != donor_off);

	/* original and donor extents have to cover the same block offset */
	if (orig_off < le32_to_cpu(tmp_oext->ee_block) ||
	    le32_to_cpu(tmp_oext->ee_block) +
			ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off)
		return -ENODATA;

	if (orig_off < le32_to_cpu(tmp_dext->ee_block) ||
	    le32_to_cpu(tmp_dext->ee_block) +
			ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off)
		return -ENODATA;

566 567 568 569 570 571
	dext_old = *tmp_dext;
	oext_old = *tmp_oext;

	/* When tmp_dext is too large, pick up the target range. */
	diff = donor_off - le32_to_cpu(tmp_dext->ee_block);

572
	ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
573 574 575 576 577 578 579 580
	tmp_dext->ee_block =
			cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff);
	tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff);

	if (max_count < ext4_ext_get_actual_len(tmp_dext))
		tmp_dext->ee_len = cpu_to_le16(max_count);

	orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
581
	ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
582 583 584 585 586 587 588 589 590 591 592

	/* Adjust extent length if donor extent is larger than orig */
	if (ext4_ext_get_actual_len(tmp_dext) >
	    ext4_ext_get_actual_len(tmp_oext) - orig_diff)
		tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) -
						orig_diff);

	tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext));

	copy_extent_status(&oext_old, tmp_dext);
	copy_extent_status(&dext_old, tmp_oext);
593 594

	return 0;
595 596 597 598 599 600 601 602 603 604
}

/**
 * mext_replace_branches - Replace original extents with new extents
 *
 * @handle:		journal handle
 * @orig_inode:		original inode
 * @donor_inode:	donor inode
 * @from:		block offset of orig_inode
 * @count:		block count to be replaced
605
 * @err:		pointer to save return value
606 607 608 609 610 611 612 613 614 615
 *
 * Replace original inode extents and donor inode extents page by page.
 * We implement this replacement in the following three steps:
 * 1. Save the block information of original and donor inodes into
 *    dummy extents.
 * 2. Change the block information of original inode to point at the
 *    donor inode blocks.
 * 3. Change the block information of donor inode to point at the saved
 *    original inode blocks in the dummy extents.
 *
616
 * Return replaced block count.
617 618 619 620
 */
static int
mext_replace_branches(handle_t *handle, struct inode *orig_inode,
			   struct inode *donor_inode, ext4_lblk_t from,
621
			   ext4_lblk_t count, int *err)
622 623 624 625 626 627 628 629 630 631
{
	struct ext4_ext_path *orig_path = NULL;
	struct ext4_ext_path *donor_path = NULL;
	struct ext4_extent *oext, *dext;
	struct ext4_extent tmp_dext, tmp_oext;
	ext4_lblk_t orig_off = from, donor_off = from;
	int depth;
	int replaced_count = 0;
	int dext_alen;

632 633 634
	/* Protect extent trees against block allocations via delalloc */
	double_down_write_data_sem(orig_inode, donor_inode);

635
	/* Get the original extent for the block "orig_off" */
636 637
	*err = get_ext_path(orig_inode, orig_off, &orig_path);
	if (*err)
638 639 640
		goto out;

	/* Get the donor extent for the head */
641 642
	*err = get_ext_path(donor_inode, donor_off, &donor_path);
	if (*err)
643 644 645 646 647 648 649 650 651
		goto out;
	depth = ext_depth(orig_inode);
	oext = orig_path[depth].p_ext;
	tmp_oext = *oext;

	depth = ext_depth(donor_inode);
	dext = donor_path[depth].p_ext;
	tmp_dext = *dext;

652
	*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
653
				      donor_off, count);
654
	if (*err)
655
		goto out;
656 657 658 659

	/* Loop for the donor extents */
	while (1) {
		/* The extent for donor must be found. */
660
		if (!dext) {
661
			EXT4_ERROR_INODE(donor_inode,
662
				   "The extent for donor must be found");
663
			*err = -EIO;
664 665
			goto out;
		} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
666
			EXT4_ERROR_INODE(donor_inode,
667 668 669 670
				"Donor offset(%u) and the first block of donor "
				"extent(%u) should be equal",
				donor_off,
				le32_to_cpu(tmp_dext.ee_block));
671
			*err = -EIO;
672 673
			goto out;
		}
674 675

		/* Set donor extent to orig extent */
676
		*err = mext_leaf_block(handle, orig_inode,
677
					   orig_path, &tmp_dext, &orig_off);
678
		if (*err)
679 680 681
			goto out;

		/* Set orig extent to donor extent */
682
		*err = mext_leaf_block(handle, donor_inode,
683
					   donor_path, &tmp_oext, &donor_off);
684
		if (*err)
685 686 687 688 689 690 691 692 693 694 695 696 697
			goto out;

		dext_alen = ext4_ext_get_actual_len(&tmp_dext);
		replaced_count += dext_alen;
		donor_off += dext_alen;
		orig_off += dext_alen;

		/* Already moved the expected blocks */
		if (replaced_count >= count)
			break;

		if (orig_path)
			ext4_ext_drop_refs(orig_path);
698 699
		*err = get_ext_path(orig_inode, orig_off, &orig_path);
		if (*err)
700 701 702 703 704 705 706
			goto out;
		depth = ext_depth(orig_inode);
		oext = orig_path[depth].p_ext;
		tmp_oext = *oext;

		if (donor_path)
			ext4_ext_drop_refs(donor_path);
707 708
		*err = get_ext_path(donor_inode, donor_off, &donor_path);
		if (*err)
709 710 711 712 713
			goto out;
		depth = ext_depth(donor_inode);
		dext = donor_path[depth].p_ext;
		tmp_dext = *dext;

714
		*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
715
					   donor_off, count - replaced_count);
716
		if (*err)
717
			goto out;
718 719 720 721 722 723 724 725 726 727 728 729
	}

out:
	if (orig_path) {
		ext4_ext_drop_refs(orig_path);
		kfree(orig_path);
	}
	if (donor_path) {
		ext4_ext_drop_refs(donor_path);
		kfree(donor_path);
	}

730 731 732 733 734
	ext4_ext_invalidate_cache(orig_inode);
	ext4_ext_invalidate_cache(donor_inode);

	double_up_write_data_sem(orig_inode, donor_inode);

735
	return replaced_count;
736 737
}

738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849
/**
 * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2
 *
 * @inode1:	the inode structure
 * @inode2:	the inode structure
 * @index:	page index
 * @page:	result page vector
 *
 * Grab two locked pages for inode's by inode order
 */
static int
mext_page_double_lock(struct inode *inode1, struct inode *inode2,
		      pgoff_t index, struct page *page[2])
{
	struct address_space *mapping[2];
	unsigned fl = AOP_FLAG_NOFS;

	BUG_ON(!inode1 || !inode2);
	if (inode1 < inode2) {
		mapping[0] = inode1->i_mapping;
		mapping[1] = inode2->i_mapping;
	} else {
		mapping[0] = inode2->i_mapping;
		mapping[1] = inode1->i_mapping;
	}

	page[0] = grab_cache_page_write_begin(mapping[0], index, fl);
	if (!page[0])
		return -ENOMEM;

	page[1] = grab_cache_page_write_begin(mapping[1], index, fl);
	if (!page[1]) {
		unlock_page(page[0]);
		page_cache_release(page[0]);
		return -ENOMEM;
	}

	if (inode1 > inode2) {
		struct page *tmp;
		tmp = page[0];
		page[0] = page[1];
		page[1] = tmp;
	}
	return 0;
}

/* Force page buffers uptodate w/o dropping page's lock */
static int
mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	sector_t block;
	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
	unsigned int blocksize, block_start, block_end;
	int i, err,  nr = 0, partial = 0;
	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	if (PageUptodate(page))
		return 0;

	blocksize = 1 << inode->i_blkbits;
	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);

	head = page_buffers(page);
	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
	for (bh = head, block_start = 0; bh != head || !block_start;
	     block++, block_start = block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (!buffer_uptodate(bh))
				partial = 1;
			continue;
		}
		if (buffer_uptodate(bh))
			continue;
		if (!buffer_mapped(bh)) {
			int err = 0;
			err = ext4_get_block(inode, block, bh, 0);
			if (err) {
				SetPageError(page);
				return err;
			}
			if (!buffer_mapped(bh)) {
				zero_user(page, block_start, blocksize);
				if (!err)
					set_buffer_uptodate(bh);
				continue;
			}
		}
		BUG_ON(nr >= MAX_BUF_PER_PAGE);
		arr[nr++] = bh;
	}
	/* No io required */
	if (!nr)
		goto out;

	for (i = 0; i < nr; i++) {
		bh = arr[i];
		if (!bh_uptodate_or_lock(bh)) {
			err = bh_submit_read(bh);
			if (err)
				return err;
		}
	}
out:
	if (!partial)
		SetPageUptodate(page);
	return 0;
}

850 851 852 853 854 855 856 857 858
/**
 * move_extent_per_page - Move extent data per page
 *
 * @o_filp:			file structure of original file
 * @donor_inode:		donor inode
 * @orig_page_offset:		page index on original file
 * @data_offset_in_page:	block index where data swapping starts
 * @block_len_in_page:		the number of blocks to be swapped
 * @uninit:			orig extent is uninitialized or not
859
 * @err:			pointer to save return value
860 861 862
 *
 * Save the data in original inode blocks and replace original inode extents
 * with donor inode extents by calling mext_replace_branches().
863 864
 * Finally, write out the saved data in new original inode blocks. Return
 * replaced block count.
865 866
 */
static int
867
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
868
		  pgoff_t orig_page_offset, int data_offset_in_page,
869
		  int block_len_in_page, int uninit, int *err)
870 871
{
	struct inode *orig_inode = o_filp->f_dentry->d_inode;
872
	struct page *pagep[2] = {NULL, NULL};
873 874 875 876 877
	handle_t *handle;
	ext4_lblk_t orig_blk_offset;
	long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
	unsigned int w_flags = 0;
878
	unsigned int tmp_data_size, data_size, replaced_size;
879
	int err2, jblocks, retries = 0;
880
	int replaced_count = 0;
881
	int from = data_offset_in_page << orig_inode->i_blkbits;
882 883 884 885 886 887
	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;

	/*
	 * It needs twice the amount of ordinary journal buffers because
	 * inode and donor_inode may change each different metadata blocks.
	 */
888 889
again:
	*err = 0;
890 891 892
	jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
	handle = ext4_journal_start(orig_inode, jblocks);
	if (IS_ERR(handle)) {
893 894
		*err = PTR_ERR(handle);
		return 0;
895 896 897 898 899 900 901 902 903 904
	}

	if (segment_eq(get_fs(), KERNEL_DS))
		w_flags |= AOP_FLAG_UNINTERRUPTIBLE;

	orig_blk_offset = orig_page_offset * blocks_per_page +
		data_offset_in_page;

	offs = (long long)orig_blk_offset << orig_inode->i_blkbits;

905
	/* Calculate data_size */
906 907 908
	if ((orig_blk_offset + block_len_in_page - 1) ==
	    ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
		/* Replace the last block */
909
		tmp_data_size = orig_inode->i_size & (blocksize - 1);
910
		/*
911
		 * If data_size equal zero, it shows data_size is multiples of
912 913
		 * blocksize. So we set appropriate value.
		 */
914 915
		if (tmp_data_size == 0)
			tmp_data_size = blocksize;
916

917
		data_size = tmp_data_size +
918
			((block_len_in_page - 1) << orig_inode->i_blkbits);
919 920 921 922
	} else
		data_size = block_len_in_page << orig_inode->i_blkbits;

	replaced_size = data_size;
923

924 925
	*err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset,
				     pagep);
926
	if (unlikely(*err < 0))
927
		goto stop_journal;
928

929 930 931 932 933 934 935 936 937 938
	*err = mext_page_mkuptodate(pagep[0], from, from + replaced_size);
	if (*err)
		goto unlock_pages;

	/* At this point all buffers in range are uptodate, old mapping layout
	 * is no longer required, try to drop it now. */
	if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) ||
	    (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) {
		*err = -EBUSY;
		goto unlock_pages;
939 940
	}

941
	replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
942 943 944
					       orig_blk_offset,
					       block_len_in_page, err);
	if (*err) {
945 946 947 948
		if (replaced_count) {
			block_len_in_page = replaced_count;
			replaced_size =
				block_len_in_page << orig_inode->i_blkbits;
949
		} else
950
			goto unlock_pages;
951
	}
952 953 954 955 956 957
	/* Perform all necessary steps similar write_begin()/write_end()
	 * but keeping in mind that i_size will not change */
	*err = __block_write_begin(pagep[0], from, from + replaced_size,
				   ext4_get_block);
	if (!*err)
		*err = block_commit_write(pagep[0], from, from + replaced_size);
958

959 960 961 962 963 964 965 966 967 968 969 970 971
	if (unlikely(*err < 0))
		goto repair_branches;

	/* Even in case of data=writeback it is reasonable to pin
	 * inode to transaction, to prevent unexpected data loss */
	*err = ext4_jbd2_file_inode(handle, orig_inode);

unlock_pages:
	unlock_page(pagep[0]);
	page_cache_release(pagep[0]);
	unlock_page(pagep[1]);
	page_cache_release(pagep[1]);
stop_journal:
972
	ext4_journal_stop(handle);
973 974 975 976 977
	/* Buffer was busy because probably is pinned to journal transaction,
	 * force transaction commit may help to free it. */
	if (*err == -EBUSY && ext4_should_retry_alloc(orig_inode->i_sb,
						      &retries))
		goto again;
978
	return replaced_count;
979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998

repair_branches:
	/*
	 * This should never ever happen!
	 * Extents are swapped already, but we are not able to copy data.
	 * Try to swap extents to it's original places
	 */
	double_down_write_data_sem(orig_inode, donor_inode);
	replaced_count = mext_replace_branches(handle, donor_inode, orig_inode,
					       orig_blk_offset,
					       block_len_in_page, &err2);
	double_up_write_data_sem(orig_inode, donor_inode);
	if (replaced_count != block_len_in_page) {
		EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset),
				       "Unable to copy data block,"
				       " data will be lost.");
		*err = -EIO;
	}
	replaced_count = 0;
	goto unlock_pages;
999 1000 1001
}

/**
1002
 * mext_check_arguments - Check whether move extent can be done
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
 *
 * @orig_inode:		original inode
 * @donor_inode:	donor inode
 * @orig_start:		logical start offset in block for orig
 * @donor_start:	logical start offset in block for donor
 * @len:		the number of blocks to be moved
 *
 * Check the arguments of ext4_move_extents() whether the files can be
 * exchanged with each other.
 * Return 0 on success, or a negative error value on failure.
 */
static int
mext_check_arguments(struct inode *orig_inode,
1016 1017
		     struct inode *donor_inode, __u64 orig_start,
		     __u64 donor_start, __u64 *len)
1018
{
1019 1020 1021 1022
	ext4_lblk_t orig_blocks, donor_blocks;
	unsigned int blkbits = orig_inode->i_blkbits;
	unsigned int blocksize = 1 << blkbits;

1023 1024 1025 1026 1027 1028 1029
	if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
		ext4_debug("ext4 move extent: suid or sgid is set"
			   " to donor file [ino:orig %lu, donor %lu]\n",
			   orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}

1030 1031 1032
	if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
		return -EPERM;

1033 1034 1035 1036 1037 1038 1039 1040 1041
	/* Ext4 move extent does not support swapfile */
	if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
		ext4_debug("ext4 move extent: The argument files should "
			"not be swapfile [ino:orig %lu, donor %lu]\n",
			orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}

	/* Ext4 move extent supports only extent based file */
1042
	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
1043 1044 1045
		ext4_debug("ext4 move extent: orig file is not extents "
			"based file [ino:orig %lu]\n", orig_inode->i_ino);
		return -EOPNOTSUPP;
1046
	} else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064
		ext4_debug("ext4 move extent: donor file is not extents "
			"based file [ino:donor %lu]\n", donor_inode->i_ino);
		return -EOPNOTSUPP;
	}

	if ((!orig_inode->i_size) || (!donor_inode->i_size)) {
		ext4_debug("ext4 move extent: File size is 0 byte\n");
		return -EINVAL;
	}

	/* Start offset should be same */
	if (orig_start != donor_start) {
		ext4_debug("ext4 move extent: orig and donor's start "
			"offset are not same [ino:orig %lu, donor %lu]\n",
			orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}

1065 1066 1067 1068
	if ((orig_start >= EXT_MAX_BLOCKS) ||
	    (donor_start >= EXT_MAX_BLOCKS) ||
	    (*len > EXT_MAX_BLOCKS) ||
	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
1069
		ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
1070
			"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
1071 1072 1073 1074 1075
			orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}

	if (orig_inode->i_size > donor_inode->i_size) {
1076 1077 1078
		donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits;
		/* TODO: eliminate this artificial restriction */
		if (orig_start >= donor_blocks) {
1079
			ext4_debug("ext4 move extent: orig start offset "
1080 1081 1082
			"[%llu] should be less than donor file blocks "
			"[%u] [ino:orig %lu, donor %lu]\n",
			orig_start, donor_blocks,
1083 1084 1085 1086
			orig_inode->i_ino, donor_inode->i_ino);
			return -EINVAL;
		}

1087 1088
		/* TODO: eliminate this artificial restriction */
		if (orig_start + *len > donor_blocks) {
1089
			ext4_debug("ext4 move extent: End offset [%llu] should "
1090 1091
				"be less than donor file blocks [%u]."
				"So adjust length from %llu to %llu "
1092
				"[ino:orig %lu, donor %lu]\n",
1093 1094
				orig_start + *len, donor_blocks,
				*len, donor_blocks - orig_start,
1095
				orig_inode->i_ino, donor_inode->i_ino);
1096
			*len = donor_blocks - orig_start;
1097 1098
		}
	} else {
1099 1100
		orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits;
		if (orig_start >= orig_blocks) {
1101
			ext4_debug("ext4 move extent: start offset [%llu] "
1102 1103 1104
				"should be less than original file blocks "
				"[%u] [ino:orig %lu, donor %lu]\n",
				 orig_start, orig_blocks,
1105 1106 1107 1108
				orig_inode->i_ino, donor_inode->i_ino);
			return -EINVAL;
		}

1109
		if (orig_start + *len > orig_blocks) {
1110
			ext4_debug("ext4 move extent: Adjust length "
1111 1112
				"from %llu to %llu. Because it should be "
				"less than original file blocks "
1113
				"[ino:orig %lu, donor %lu]\n",
1114
				*len, orig_blocks - orig_start,
1115
				orig_inode->i_ino, donor_inode->i_ino);
1116
			*len = orig_blocks - orig_start;
1117 1118 1119 1120
		}
	}

	if (!*len) {
1121
		ext4_debug("ext4 move extent: len should not be 0 "
1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135
			"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
			donor_inode->i_ino);
		return -EINVAL;
	}

	return 0;
}

/**
 * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
 *
 * @inode1:	the inode structure
 * @inode2:	the inode structure
 *
D
Dmitry Monakhov 已提交
1136
 * Lock two inodes' i_mutex
1137
 */
D
Dmitry Monakhov 已提交
1138
static void
1139 1140
mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
{
D
Dmitry Monakhov 已提交
1141 1142
	BUG_ON(inode1 == inode2);
	if (inode1 < inode2) {
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158
		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
	} else {
		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
	}
}

/**
 * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
 *
 * @inode1:     the inode that is released first
 * @inode2:     the inode that is released second
 *
 */

D
Dmitry Monakhov 已提交
1159
static void
1160 1161
mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
{
D
Dmitry Monakhov 已提交
1162 1163
	mutex_unlock(&inode1->i_mutex);
	mutex_unlock(&inode2->i_mutex);
1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 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 1212 1213 1214 1215 1216 1217 1218 1219
}

/**
 * ext4_move_extents - Exchange the specified range of a file
 *
 * @o_filp:		file structure of the original file
 * @d_filp:		file structure of the donor file
 * @orig_start:		start offset in block for orig
 * @donor_start:	start offset in block for donor
 * @len:		the number of blocks to be moved
 * @moved_len:		moved block length
 *
 * This function returns 0 and moved block length is set in moved_len
 * if succeed, otherwise returns error value.
 *
 * Note: ext4_move_extents() proceeds the following order.
 * 1:ext4_move_extents() calculates the last block number of moving extent
 *   function by the start block number (orig_start) and the number of blocks
 *   to be moved (len) specified as arguments.
 *   If the {orig, donor}_start points a hole, the extent's start offset
 *   pointed by ext_cur (current extent), holecheck_path, orig_path are set
 *   after hole behind.
 * 2:Continue step 3 to step 5, until the holecheck_path points to last_extent
 *   or the ext_cur exceeds the block_end which is last logical block number.
 * 3:To get the length of continues area, call mext_next_extent()
 *   specified with the ext_cur (initial value is holecheck_path) re-cursive,
 *   until find un-continuous extent, the start logical block number exceeds
 *   the block_end or the extent points to the last extent.
 * 4:Exchange the original inode data with donor inode data
 *   from orig_page_offset to seq_end_page.
 *   The start indexes of data are specified as arguments.
 *   That of the original inode is orig_page_offset,
 *   and the donor inode is also orig_page_offset
 *   (To easily handle blocksize != pagesize case, the offset for the
 *   donor inode is block unit).
 * 5:Update holecheck_path and orig_path to points a next proceeding extent,
 *   then returns to step 2.
 * 6:Release holecheck_path, orig_path and set the len to moved_len
 *   which shows the number of moved blocks.
 *   The moved_len is useful for the command to calculate the file offset
 *   for starting next move extent ioctl.
 * 7:Return 0 on success, or a negative error value on failure.
 */
int
ext4_move_extents(struct file *o_filp, struct file *d_filp,
		 __u64 orig_start, __u64 donor_start, __u64 len,
		 __u64 *moved_len)
{
	struct inode *orig_inode = o_filp->f_dentry->d_inode;
	struct inode *donor_inode = d_filp->f_dentry->d_inode;
	struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL;
	struct ext4_extent *ext_prev, *ext_cur, *ext_dummy;
	ext4_lblk_t block_start = orig_start;
	ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0;
	ext4_lblk_t rest_blocks;
	pgoff_t orig_page_offset = 0, seq_end_page;
D
Dmitry Monakhov 已提交
1220
	int ret, depth, last_extent = 0;
1221 1222 1223 1224 1225
	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
	int data_offset_in_page;
	int block_len_in_page;
	int uninit;

D
Dmitry Monakhov 已提交
1226 1227 1228 1229 1230 1231 1232 1233 1234
	if (orig_inode->i_sb != donor_inode->i_sb) {
		ext4_debug("ext4 move extent: The argument files "
			"should be in same FS [ino:orig %lu, donor %lu]\n",
			orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}

	/* orig and donor should be different inodes */
	if (orig_inode == donor_inode) {
1235
		ext4_debug("ext4 move extent: The argument files should not "
D
Dmitry Monakhov 已提交
1236
			"be same inode [ino:orig %lu, donor %lu]\n",
1237 1238 1239 1240
			orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}

1241 1242 1243 1244 1245 1246 1247
	/* Regular file check */
	if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
		ext4_debug("ext4 move extent: The argument files should be "
			"regular file [ino:orig %lu, donor %lu]\n",
			orig_inode->i_ino, donor_inode->i_ino);
		return -EINVAL;
	}
1248 1249 1250 1251 1252 1253
	/* TODO: This is non obvious task to swap blocks for inodes with full
	   jornaling enabled */
	if (ext4_should_journal_data(orig_inode) ||
	    ext4_should_journal_data(donor_inode)) {
		return -EINVAL;
	}
1254
	/* Protect orig and donor inodes against a truncate */
D
Dmitry Monakhov 已提交
1255
	mext_inode_double_lock(orig_inode, donor_inode);
1256

1257 1258
	/* Protect extent tree against block allocations via delalloc */
	double_down_write_data_sem(orig_inode, donor_inode);
1259
	/* Check the filesystem environment whether move_extent can be done */
D
Dmitry Monakhov 已提交
1260
	ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
1261
				    donor_start, &len);
D
Dmitry Monakhov 已提交
1262
	if (ret)
1263
		goto out;
1264 1265 1266 1267 1268 1269

	file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
	block_end = block_start + len - 1;
	if (file_end < block_end)
		len -= block_end - file_end;

D
Dmitry Monakhov 已提交
1270 1271
	ret = get_ext_path(orig_inode, block_start, &orig_path);
	if (ret)
1272
		goto out;
1273 1274

	/* Get path structure to check the hole */
D
Dmitry Monakhov 已提交
1275 1276
	ret = get_ext_path(orig_inode, block_start, &holecheck_path);
	if (ret)
1277 1278 1279 1280 1281 1282
		goto out;

	depth = ext_depth(orig_inode);
	ext_cur = holecheck_path[depth].p_ext;

	/*
1283 1284
	 * Get proper starting location of block replacement if block_start was
	 * within the hole.
1285 1286 1287
	 */
	if (le32_to_cpu(ext_cur->ee_block) +
		ext4_ext_get_actual_len(ext_cur) - 1 < block_start) {
1288 1289 1290 1291
		/*
		 * The hole exists between extents or the tail of
		 * original file.
		 */
1292 1293 1294
		last_extent = mext_next_extent(orig_inode,
					holecheck_path, &ext_cur);
		if (last_extent < 0) {
D
Dmitry Monakhov 已提交
1295
			ret = last_extent;
1296 1297 1298 1299 1300
			goto out;
		}
		last_extent = mext_next_extent(orig_inode, orig_path,
							&ext_dummy);
		if (last_extent < 0) {
D
Dmitry Monakhov 已提交
1301
			ret = last_extent;
1302 1303
			goto out;
		}
1304 1305 1306 1307 1308 1309
		seq_start = le32_to_cpu(ext_cur->ee_block);
	} else if (le32_to_cpu(ext_cur->ee_block) > block_start)
		/* The hole exists at the beginning of original file. */
		seq_start = le32_to_cpu(ext_cur->ee_block);
	else
		seq_start = block_start;
1310 1311 1312 1313 1314

	/* No blocks within the specified range. */
	if (le32_to_cpu(ext_cur->ee_block) > block_end) {
		ext4_debug("ext4 move extent: The specified range of file "
							"may be the hole\n");
D
Dmitry Monakhov 已提交
1315
		ret = -EINVAL;
1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334
		goto out;
	}

	/* Adjust start blocks */
	add_blocks = min(le32_to_cpu(ext_cur->ee_block) +
			 ext4_ext_get_actual_len(ext_cur), block_end + 1) -
		     max(le32_to_cpu(ext_cur->ee_block), block_start);

	while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) {
		seq_blocks += add_blocks;

		/* Adjust tail blocks */
		if (seq_start + seq_blocks - 1 > block_end)
			seq_blocks = block_end - seq_start + 1;

		ext_prev = ext_cur;
		last_extent = mext_next_extent(orig_inode, holecheck_path,
						&ext_cur);
		if (last_extent < 0) {
D
Dmitry Monakhov 已提交
1335
			ret = last_extent;
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
			break;
		}
		add_blocks = ext4_ext_get_actual_len(ext_cur);

		/*
		 * Extend the length of contiguous block (seq_blocks)
		 * if extents are contiguous.
		 */
		if (ext4_can_extents_be_merged(orig_inode,
					       ext_prev, ext_cur) &&
		    block_end >= le32_to_cpu(ext_cur->ee_block) &&
		    !last_extent)
			continue;

		/* Is original extent is uninitialized */
		uninit = ext4_ext_is_uninitialized(ext_prev);

		data_offset_in_page = seq_start % blocks_per_page;

		/*
		 * Calculate data blocks count that should be swapped
		 * at the first page.
		 */
		if (data_offset_in_page + seq_blocks > blocks_per_page) {
			/* Swapped blocks are across pages */
			block_len_in_page =
					blocks_per_page - data_offset_in_page;
		} else {
			/* Swapped blocks are in a page */
			block_len_in_page = seq_blocks;
		}

		orig_page_offset = seq_start >>
				(PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
		seq_end_page = (seq_start + seq_blocks - 1) >>
				(PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
		seq_start = le32_to_cpu(ext_cur->ee_block);
		rest_blocks = seq_blocks;

1375 1376 1377 1378 1379 1380 1381 1382
		/*
		 * Up semaphore to avoid following problems:
		 * a. transaction deadlock among ext4_journal_start,
		 *    ->write_begin via pagefault, and jbd2_journal_commit
		 * b. racing with ->readpage, ->write_begin, and ext4_get_block
		 *    in move_extent_per_page
		 */
		double_up_write_data_sem(orig_inode, donor_inode);
1383 1384 1385 1386

		while (orig_page_offset <= seq_end_page) {

			/* Swap original branches with new branches */
1387 1388
			block_len_in_page = move_extent_per_page(
						o_filp, donor_inode,
1389 1390
						orig_page_offset,
						data_offset_in_page,
1391
						block_len_in_page, uninit,
D
Dmitry Monakhov 已提交
1392
						&ret);
1393

1394 1395
			/* Count how many blocks we have exchanged */
			*moved_len += block_len_in_page;
D
Dmitry Monakhov 已提交
1396
			if (ret < 0)
1397
				break;
1398
			if (*moved_len > len) {
1399
				EXT4_ERROR_INODE(orig_inode,
1400 1401 1402
					"We replaced blocks too much! "
					"sum of replaced: %llu requested: %llu",
					*moved_len, len);
D
Dmitry Monakhov 已提交
1403
				ret = -EIO;
1404
				break;
1405
			}
1406

1407
			orig_page_offset++;
1408 1409 1410 1411 1412 1413 1414 1415
			data_offset_in_page = 0;
			rest_blocks -= block_len_in_page;
			if (rest_blocks > blocks_per_page)
				block_len_in_page = blocks_per_page;
			else
				block_len_in_page = rest_blocks;
		}

1416
		double_down_write_data_sem(orig_inode, donor_inode);
D
Dmitry Monakhov 已提交
1417
		if (ret < 0)
1418 1419
			break;

1420 1421 1422
		/* Decrease buffer counter */
		if (holecheck_path)
			ext4_ext_drop_refs(holecheck_path);
D
Dmitry Monakhov 已提交
1423 1424
		ret = get_ext_path(orig_inode, seq_start, &holecheck_path);
		if (ret)
1425 1426 1427 1428 1429 1430
			break;
		depth = holecheck_path->p_depth;

		/* Decrease buffer counter */
		if (orig_path)
			ext4_ext_drop_refs(orig_path);
D
Dmitry Monakhov 已提交
1431 1432
		ret = get_ext_path(orig_inode, seq_start, &orig_path);
		if (ret)
1433 1434 1435 1436 1437 1438 1439 1440
			break;

		ext_cur = holecheck_path[depth].p_ext;
		add_blocks = ext4_ext_get_actual_len(ext_cur);
		seq_blocks = 0;

	}
out:
1441 1442 1443 1444 1445
	if (*moved_len) {
		ext4_discard_preallocations(orig_inode);
		ext4_discard_preallocations(donor_inode);
	}

1446 1447 1448 1449 1450 1451 1452 1453
	if (orig_path) {
		ext4_ext_drop_refs(orig_path);
		kfree(orig_path);
	}
	if (holecheck_path) {
		ext4_ext_drop_refs(holecheck_path);
		kfree(holecheck_path);
	}
1454
	double_up_write_data_sem(orig_inode, donor_inode);
D
Dmitry Monakhov 已提交
1455
	mext_inode_double_unlock(orig_inode, donor_inode);
1456

D
Dmitry Monakhov 已提交
1457
	return ret;
1458
}