resize.c 57.2 KB
Newer Older
1
/*
2
 *  linux/fs/ext4/resize.c
3
 *
4
 * Support for resizing an ext4 filesystem while it is mounted.
5 6 7 8 9 10 11
 *
 * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
 *
 * This could probably be made into a module, because it is not often in use.
 */


12
#define EXT4FS_DEBUG
13 14 15 16

#include <linux/errno.h>
#include <linux/slab.h>

17
#include "ext4_jbd2.h"
18

19 20 21 22 23 24 25
int ext4_resize_begin(struct super_block *sb)
{
	int ret = 0;

	if (!capable(CAP_SYS_RESOURCE))
		return -EPERM;

26 27 28 29 30 31 32 33 34 35
	/*
	 * We are not allowed to do online-resizing on a filesystem mounted
	 * with error, because it can destroy the filesystem easily.
	 */
	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
		ext4_warning(sb, "There are errors in the filesystem, "
			     "so online resizing is not allowed\n");
		return -EPERM;
	}

36 37 38 39 40 41 42 43 44 45 46 47
	if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
		ret = -EBUSY;

	return ret;
}

void ext4_resize_end(struct super_block *sb)
{
	clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
	smp_mb__after_clear_bit();
}

48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69
static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,
					     ext4_group_t group) {
	return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) <<
	       EXT4_DESC_PER_BLOCK_BITS(sb);
}

static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb,
					     ext4_group_t group) {
	group = ext4_meta_bg_first_group(sb, group);
	return ext4_group_first_block_no(sb, group);
}

static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb,
						ext4_group_t group) {
	ext4_grpblk_t overhead;
	overhead = ext4_bg_num_gdb(sb, group);
	if (ext4_bg_has_super(sb, group))
		overhead += 1 +
			  le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
	return overhead;
}

70 71 72 73
#define outside(b, first, last)	((b) < (first) || (b) >= (last))
#define inside(b, first, last)	((b) >= (first) && (b) < (last))

static int verify_group_input(struct super_block *sb,
74
			      struct ext4_new_group_data *input)
75
{
76 77
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
L
Laurent Vivier 已提交
78
	ext4_fsblk_t start = ext4_blocks_count(es);
79
	ext4_fsblk_t end = start + input->blocks_count;
80
	ext4_group_t group = input->group;
81
	ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
82
	unsigned overhead = ext4_group_overhead_blocks(sb, group);
83
	ext4_fsblk_t metaend = start + overhead;
84
	struct buffer_head *bh = NULL;
85
	ext4_grpblk_t free_blocks_count, offset;
86 87 88 89 90 91
	int err = -EINVAL;

	input->free_blocks_count = free_blocks_count =
		input->blocks_count - 2 - overhead - sbi->s_itb_per_group;

	if (test_opt(sb, DEBUG))
92
		printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks "
93
		       "(%d free, %u reserved)\n",
94
		       ext4_bg_has_super(sb, input->group) ? "normal" :
95 96 97
		       "no-super", input->group, input->blocks_count,
		       free_blocks_count, input->reserved_blocks);

98
	ext4_get_group_no_and_offset(sb, start, NULL, &offset);
99
	if (group != sbi->s_groups_count)
100
		ext4_warning(sb, "Cannot add at group %u (only %u groups)",
101
			     input->group, sbi->s_groups_count);
102
	else if (offset != 0)
103
			ext4_warning(sb, "Last group not full");
104
	else if (input->reserved_blocks > input->blocks_count / 5)
105
		ext4_warning(sb, "Reserved blocks too high (%u)",
106 107
			     input->reserved_blocks);
	else if (free_blocks_count < 0)
108
		ext4_warning(sb, "Bad blocks count %u",
109 110
			     input->blocks_count);
	else if (!(bh = sb_bread(sb, end - 1)))
111
		ext4_warning(sb, "Cannot read last block (%llu)",
112 113
			     end - 1);
	else if (outside(input->block_bitmap, start, end))
114
		ext4_warning(sb, "Block bitmap not in group (block %llu)",
115
			     (unsigned long long)input->block_bitmap);
116
	else if (outside(input->inode_bitmap, start, end))
117
		ext4_warning(sb, "Inode bitmap not in group (block %llu)",
118
			     (unsigned long long)input->inode_bitmap);
119
	else if (outside(input->inode_table, start, end) ||
120
		 outside(itend - 1, start, end))
121
		ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
122
			     (unsigned long long)input->inode_table, itend - 1);
123
	else if (input->inode_bitmap == input->block_bitmap)
124
		ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
125
			     (unsigned long long)input->block_bitmap);
126
	else if (inside(input->block_bitmap, input->inode_table, itend))
127 128
		ext4_warning(sb, "Block bitmap (%llu) in inode table "
			     "(%llu-%llu)",
129 130
			     (unsigned long long)input->block_bitmap,
			     (unsigned long long)input->inode_table, itend - 1);
131
	else if (inside(input->inode_bitmap, input->inode_table, itend))
132 133
		ext4_warning(sb, "Inode bitmap (%llu) in inode table "
			     "(%llu-%llu)",
134 135
			     (unsigned long long)input->inode_bitmap,
			     (unsigned long long)input->inode_table, itend - 1);
136
	else if (inside(input->block_bitmap, start, metaend))
137
		ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
138 139
			     (unsigned long long)input->block_bitmap,
			     start, metaend - 1);
140
	else if (inside(input->inode_bitmap, start, metaend))
141
		ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
142 143
			     (unsigned long long)input->inode_bitmap,
			     start, metaend - 1);
144
	else if (inside(input->inode_table, start, metaend) ||
145
		 inside(itend - 1, start, metaend))
146 147
		ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
			     "(%llu-%llu)",
148 149
			     (unsigned long long)input->inode_table,
			     itend - 1, start, metaend - 1);
150 151 152 153 154 155 156
	else
		err = 0;
	brelse(bh);

	return err;
}

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
/*
 * ext4_new_flex_group_data is used by 64bit-resize interface to add a flex
 * group each time.
 */
struct ext4_new_flex_group_data {
	struct ext4_new_group_data *groups;	/* new_group_data for groups
						   in the flex group */
	__u16 *bg_flags;			/* block group flags of groups
						   in @groups */
	ext4_group_t count;			/* number of groups in @groups
						 */
};

/*
 * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
 * @flexbg_size.
 *
 * Returns NULL on failure otherwise address of the allocated structure.
 */
static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
{
	struct ext4_new_flex_group_data *flex_gd;

	flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
	if (flex_gd == NULL)
		goto out3;

184 185
	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
		goto out2;
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
	flex_gd->count = flexbg_size;

	flex_gd->groups = kmalloc(sizeof(struct ext4_new_group_data) *
				  flexbg_size, GFP_NOFS);
	if (flex_gd->groups == NULL)
		goto out2;

	flex_gd->bg_flags = kmalloc(flexbg_size * sizeof(__u16), GFP_NOFS);
	if (flex_gd->bg_flags == NULL)
		goto out1;

	return flex_gd;

out1:
	kfree(flex_gd->groups);
out2:
	kfree(flex_gd);
out3:
	return NULL;
}

static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
{
	kfree(flex_gd->bg_flags);
	kfree(flex_gd->groups);
	kfree(flex_gd);
}

214 215 216 217 218 219 220 221 222
/*
 * ext4_alloc_group_tables() allocates block bitmaps, inode bitmaps
 * and inode tables for a flex group.
 *
 * This function is used by 64bit-resize.  Note that this function allocates
 * group tables from the 1st group of groups contained by @flexgd, which may
 * be a partial of a flex group.
 *
 * @sb: super block of fs to which the groups belongs
223 224 225
 *
 * Returns 0 on a successful allocation of the metadata blocks in the
 * block group.
226
 */
227
static int ext4_alloc_group_tables(struct super_block *sb,
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
				struct ext4_new_flex_group_data *flex_gd,
				int flexbg_size)
{
	struct ext4_new_group_data *group_data = flex_gd->groups;
	ext4_fsblk_t start_blk;
	ext4_fsblk_t last_blk;
	ext4_group_t src_group;
	ext4_group_t bb_index = 0;
	ext4_group_t ib_index = 0;
	ext4_group_t it_index = 0;
	ext4_group_t group;
	ext4_group_t last_group;
	unsigned overhead;

	BUG_ON(flex_gd->count == 0 || group_data == NULL);

	src_group = group_data[0].group;
	last_group  = src_group + flex_gd->count - 1;

	BUG_ON((flexbg_size > 1) && ((src_group & ~(flexbg_size - 1)) !=
	       (last_group & ~(flexbg_size - 1))));
next_group:
	group = group_data[0].group;
251 252
	if (src_group >= group_data[0].group + flex_gd->count)
		return -ENOSPC;
253 254 255
	start_blk = ext4_group_first_block_no(sb, src_group);
	last_blk = start_blk + group_data[src_group - group].blocks_count;

256
	overhead = ext4_group_overhead_blocks(sb, src_group);
257 258 259 260 261

	start_blk += overhead;

	/* We collect contiguous blocks as much as possible. */
	src_group++;
262 263 264
	for (; src_group <= last_group; src_group++) {
		overhead = ext4_group_overhead_blocks(sb, src_group);
		if (overhead != 0)
265 266 267
			last_blk += group_data[src_group - group].blocks_count;
		else
			break;
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

	/* Allocate block bitmaps */
	for (; bb_index < flex_gd->count; bb_index++) {
		if (start_blk >= last_blk)
			goto next_group;
		group_data[bb_index].block_bitmap = start_blk++;
		ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
		group -= group_data[0].group;
		group_data[group].free_blocks_count--;
		if (flexbg_size > 1)
			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
	}

	/* Allocate inode bitmaps */
	for (; ib_index < flex_gd->count; ib_index++) {
		if (start_blk >= last_blk)
			goto next_group;
		group_data[ib_index].inode_bitmap = start_blk++;
		ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
		group -= group_data[0].group;
		group_data[group].free_blocks_count--;
		if (flexbg_size > 1)
			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
	}

	/* Allocate inode tables */
	for (; it_index < flex_gd->count; it_index++) {
		if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
			goto next_group;
		group_data[it_index].inode_table = start_blk;
		ext4_get_group_no_and_offset(sb, start_blk, &group, NULL);
		group -= group_data[0].group;
		group_data[group].free_blocks_count -=
					EXT4_SB(sb)->s_itb_per_group;
		if (flexbg_size > 1)
			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;

		start_blk += EXT4_SB(sb)->s_itb_per_group;
	}

	if (test_opt(sb, DEBUG)) {
		int i;
		group = group_data[0].group;

		printk(KERN_DEBUG "EXT4-fs: adding a flex group with "
		       "%d groups, flexbg size is %d:\n", flex_gd->count,
		       flexbg_size);

		for (i = 0; i < flex_gd->count; i++) {
			printk(KERN_DEBUG "adding %s group %u: %u "
			       "blocks (%d free)\n",
			       ext4_bg_has_super(sb, group + i) ? "normal" :
			       "no-super", group + i,
			       group_data[i].blocks_count,
			       group_data[i].free_blocks_count);
		}
	}
326
	return 0;
327 328
}

329
static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
330
				  ext4_fsblk_t blk)
331 332 333 334 335 336 337
{
	struct buffer_head *bh;
	int err;

	bh = sb_getblk(sb, blk);
	if (!bh)
		return ERR_PTR(-EIO);
338
	if ((err = ext4_journal_get_write_access(handle, bh))) {
339 340 341 342 343 344 345 346 347 348
		brelse(bh);
		bh = ERR_PTR(err);
	} else {
		memset(bh->b_data, 0, sb->s_blocksize);
		set_buffer_uptodate(bh);
	}

	return bh;
}

349 350 351 352 353
/*
 * If we have fewer than thresh credits, extend by EXT4_MAX_TRANS_DATA.
 * If that fails, restart the transaction & regain write access for the
 * buffer head which is used for block_bitmap modifications.
 */
354
static int extend_or_restart_transaction(handle_t *handle, int thresh)
355 356 357
{
	int err;

358
	if (ext4_handle_has_enough_credits(handle, thresh))
359 360 361 362 363 364
		return 0;

	err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
	if (err < 0)
		return err;
	if (err) {
365 366
		err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
		if (err)
367
			return err;
368
	}
369 370 371 372

	return 0;
}

373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459
/*
 * set_flexbg_block_bitmap() mark @count blocks starting from @block used.
 *
 * Helper function for ext4_setup_new_group_blocks() which set .
 *
 * @sb: super block
 * @handle: journal handle
 * @flex_gd: flex group data
 */
static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
			struct ext4_new_flex_group_data *flex_gd,
			ext4_fsblk_t block, ext4_group_t count)
{
	ext4_group_t count2;

	ext4_debug("mark blocks [%llu/%u] used\n", block, count);
	for (count2 = count; count > 0; count -= count2, block += count2) {
		ext4_fsblk_t start;
		struct buffer_head *bh;
		ext4_group_t group;
		int err;

		ext4_get_group_no_and_offset(sb, block, &group, NULL);
		start = ext4_group_first_block_no(sb, group);
		group -= flex_gd->groups[0].group;

		count2 = sb->s_blocksize * 8 - (block - start);
		if (count2 > count)
			count2 = count;

		if (flex_gd->bg_flags[group] & EXT4_BG_BLOCK_UNINIT) {
			BUG_ON(flex_gd->count > 1);
			continue;
		}

		err = extend_or_restart_transaction(handle, 1);
		if (err)
			return err;

		bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap);
		if (!bh)
			return -EIO;

		err = ext4_journal_get_write_access(handle, bh);
		if (err)
			return err;
		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block,
			   block - start, count2);
		ext4_set_bits(bh->b_data, block - start, count2);

		err = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (unlikely(err))
			return err;
		brelse(bh);
	}

	return 0;
}

/*
 * Set up the block and inode bitmaps, and the inode table for the new groups.
 * This doesn't need to be part of the main transaction, since we are only
 * changing blocks outside the actual filesystem.  We still do journaling to
 * ensure the recovery is correct in case of a failure just after resize.
 * If any part of this fails, we simply abort the resize.
 *
 * setup_new_flex_group_blocks handles a flex group as follow:
 *  1. copy super block and GDT, and initialize group tables if necessary.
 *     In this step, we only set bits in blocks bitmaps for blocks taken by
 *     super block and GDT.
 *  2. allocate group tables in block bitmaps, that is, set bits in block
 *     bitmap for blocks taken by group tables.
 */
static int setup_new_flex_group_blocks(struct super_block *sb,
				struct ext4_new_flex_group_data *flex_gd)
{
	int group_table_count[] = {1, 1, EXT4_SB(sb)->s_itb_per_group};
	ext4_fsblk_t start;
	ext4_fsblk_t block;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	struct ext4_new_group_data *group_data = flex_gd->groups;
	__u16 *bg_flags = flex_gd->bg_flags;
	handle_t *handle;
	ext4_group_t group, count;
	struct buffer_head *bh = NULL;
	int reserved_gdb, i, j, err = 0, err2;
460
	int meta_bg;
461 462 463 464 465

	BUG_ON(!flex_gd->count || !group_data ||
	       group_data[0].group != sbi->s_groups_count);

	reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
466
	meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
467 468 469 470 471 472 473 474 475

	/* This transaction may be extended/restarted along the way */
	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	group = group_data[0].group;
	for (i = 0; i < flex_gd->count; i++, group++) {
		unsigned long gdblocks;
476
		ext4_grpblk_t overhead;
477 478 479 480

		gdblocks = ext4_bg_num_gdb(sb, group);
		start = ext4_group_first_block_no(sb, group);

481
		if (meta_bg == 0 && !ext4_bg_has_super(sb, group))
482 483
			goto handle_itb;

484 485 486 487 488 489 490 491 492
		if (meta_bg == 1) {
			ext4_group_t first_group;
			first_group = ext4_meta_bg_first_group(sb, group);
			if (first_group != group + 1 &&
			    first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1)
				goto handle_itb;
		}

		block = start + ext4_bg_has_super(sb, group);
493
		/* Copy all of the GDT blocks into the backup in this group */
494
		for (j = 0; j < gdblocks; j++, block++) {
495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
			struct buffer_head *gdb;

			ext4_debug("update backup group %#04llx\n", block);
			err = extend_or_restart_transaction(handle, 1);
			if (err)
				goto out;

			gdb = sb_getblk(sb, block);
			if (!gdb) {
				err = -EIO;
				goto out;
			}

			err = ext4_journal_get_write_access(handle, gdb);
			if (err) {
				brelse(gdb);
				goto out;
			}
			memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data,
			       gdb->b_size);
			set_buffer_uptodate(gdb);

			err = ext4_handle_dirty_metadata(handle, NULL, gdb);
			if (unlikely(err)) {
				brelse(gdb);
				goto out;
			}
			brelse(gdb);
		}

		/* Zero out all of the reserved backup group descriptor
		 * table blocks
		 */
		if (ext4_bg_has_super(sb, group)) {
			err = sb_issue_zeroout(sb, gdblocks + start + 1,
					reserved_gdb, GFP_NOFS);
			if (err)
				goto out;
		}

535
handle_itb:
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
		/* Initialize group tables of the grop @group */
		if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED))
			goto handle_bb;

		/* Zero out all of the inode table blocks */
		block = group_data[i].inode_table;
		ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
			   block, sbi->s_itb_per_group);
		err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group,
				       GFP_NOFS);
		if (err)
			goto out;

handle_bb:
		if (bg_flags[i] & EXT4_BG_BLOCK_UNINIT)
			goto handle_ib;

		/* Initialize block bitmap of the @group */
		block = group_data[i].block_bitmap;
		err = extend_or_restart_transaction(handle, 1);
		if (err)
			goto out;

		bh = bclean(handle, sb, block);
		if (IS_ERR(bh)) {
			err = PTR_ERR(bh);
			goto out;
		}
564 565
		overhead = ext4_group_overhead_blocks(sb, group);
		if (overhead != 0) {
566 567
			ext4_debug("mark backup superblock %#04llx (+0)\n",
				   start);
568
			ext4_set_bits(bh->b_data, 0, overhead);
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
		}
		ext4_mark_bitmap_end(group_data[i].blocks_count,
				     sb->s_blocksize * 8, bh->b_data);
		err = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (err)
			goto out;
		brelse(bh);

handle_ib:
		if (bg_flags[i] & EXT4_BG_INODE_UNINIT)
			continue;

		/* Initialize inode bitmap of the @group */
		block = group_data[i].inode_bitmap;
		err = extend_or_restart_transaction(handle, 1);
		if (err)
			goto out;
		/* Mark unused entries in inode bitmap used */
		bh = bclean(handle, sb, block);
		if (IS_ERR(bh)) {
			err = PTR_ERR(bh);
			goto out;
		}

		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
				     sb->s_blocksize * 8, bh->b_data);
		err = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (err)
			goto out;
		brelse(bh);
	}
	bh = NULL;

	/* Mark group tables in block bitmap */
	for (j = 0; j < GROUP_TABLE_COUNT; j++) {
		count = group_table_count[j];
		start = (&group_data[0].block_bitmap)[j];
		block = start;
		for (i = 1; i < flex_gd->count; i++) {
			block += group_table_count[j];
			if (block == (&group_data[i].block_bitmap)[j]) {
				count += group_table_count[j];
				continue;
			}
			err = set_flexbg_block_bitmap(sb, handle,
						flex_gd, start, count);
			if (err)
				goto out;
			count = group_table_count[j];
			start = group_data[i].block_bitmap;
			block = start;
		}

		if (count) {
			err = set_flexbg_block_bitmap(sb, handle,
						flex_gd, start, count);
			if (err)
				goto out;
		}
	}

out:
	brelse(bh);
	err2 = ext4_journal_stop(handle);
	if (err2 && !err)
		err = err2;

	return err;
}

639 640
/*
 * Iterate through the groups which hold BACKUP superblock/GDT copies in an
641
 * ext4 filesystem.  The counters should be initialized to 1, 5, and 7 before
642 643 644 645
 * calling this for the first time.  In a sparse filesystem it will be the
 * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ...
 * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ...
 */
646
static unsigned ext4_list_backups(struct super_block *sb, unsigned *three,
647 648 649 650 651 652
				  unsigned *five, unsigned *seven)
{
	unsigned *min = three;
	int mult = 3;
	unsigned ret;

653 654
	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
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
		ret = *min;
		*min += 1;
		return ret;
	}

	if (*five < *min) {
		min = five;
		mult = 5;
	}
	if (*seven < *min) {
		min = seven;
		mult = 7;
	}

	ret = *min;
	*min *= mult;

	return ret;
}

/*
 * Check that all of the backup GDT blocks are held in the primary GDT block.
 * It is assumed that they are stored in group order.  Returns the number of
 * groups in current filesystem that have BACKUPS, or -ve error code.
 */
static int verify_reserved_gdb(struct super_block *sb,
681
			       ext4_group_t end,
682 683
			       struct buffer_head *primary)
{
684
	const ext4_fsblk_t blk = primary->b_blocknr;
685 686 687 688 689 690 691
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
	unsigned grp;
	__le32 *p = (__le32 *)primary->b_data;
	int gdbackups = 0;

692
	while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
L
Laurent Vivier 已提交
693 694
		if (le32_to_cpu(*p++) !=
		    grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
695
			ext4_warning(sb, "reserved GDT %llu"
696
				     " missing grp %d (%llu)",
697
				     blk, grp,
L
Laurent Vivier 已提交
698 699 700
				     grp *
				     (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
				     blk);
701 702
			return -EINVAL;
		}
703
		if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb))
704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
			return -EFBIG;
	}

	return gdbackups;
}

/*
 * Called when we need to bring a reserved group descriptor table block into
 * use from the resize inode.  The primary copy of the new GDT block currently
 * is an indirect block (under the double indirect block in the resize inode).
 * The new backup GDT blocks will be stored as leaf blocks in this indirect
 * block, in group order.  Even though we know all the block numbers we need,
 * we check to ensure that the resize inode has actually reserved these blocks.
 *
 * Don't need to update the block bitmaps because the blocks are still in use.
 *
 * We get all of the error cases out of the way, so that we are sure to not
 * fail once we start modifying the data on disk, because JBD has no rollback.
 */
static int add_new_gdb(handle_t *handle, struct inode *inode,
724
		       ext4_group_t group)
725 726
{
	struct super_block *sb = inode->i_sb;
727
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
728
	unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
729
	ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
730 731
	struct buffer_head **o_group_desc, **n_group_desc;
	struct buffer_head *dind;
732
	struct buffer_head *gdb_bh;
733
	int gdbackups;
734
	struct ext4_iloc iloc;
735 736 737 738 739
	__le32 *data;
	int err;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG
740
		       "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
741 742
		       gdb_num);

743 744
	/*
	 * If we are not using the primary superblock/GDT copy don't resize,
745 746 747
         * because the user tools have no way of handling this.  Probably a
         * bad time to do it anyways.
         */
748 749
	if (EXT4_SB(sb)->s_sbh->b_blocknr !=
	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
750
		ext4_warning(sb, "won't resize using backup superblock at %llu",
751
			(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
752 753 754
		return -EPERM;
	}

755 756
	gdb_bh = sb_bread(sb, gdblock);
	if (!gdb_bh)
757 758
		return -EIO;

759
	gdbackups = verify_reserved_gdb(sb, group, gdb_bh);
760
	if (gdbackups < 0) {
761 762 763 764
		err = gdbackups;
		goto exit_bh;
	}

765
	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
766 767 768 769 770 771 772
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_bh;
	}

	data = (__le32 *)dind->b_data;
773
	if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
774
		ext4_warning(sb, "new group %u GDT block %llu not reserved",
775
			     group, gdblock);
776 777 778 779
		err = -EINVAL;
		goto exit_dind;
	}

780 781
	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
	if (unlikely(err))
782 783
		goto exit_dind;

784
	err = ext4_journal_get_write_access(handle, gdb_bh);
785
	if (unlikely(err))
786 787
		goto exit_sbh;

788 789 790
	err = ext4_journal_get_write_access(handle, dind);
	if (unlikely(err))
		ext4_std_error(sb, err);
791

792
	/* ext4_reserve_inode_write() gets a reference on the iloc */
793 794
	err = ext4_reserve_inode_write(handle, inode, &iloc);
	if (unlikely(err))
795 796
		goto exit_dindj;

797 798 799
	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
				     sizeof(struct buffer_head *),
				     GFP_NOFS);
800 801
	if (!n_group_desc) {
		err = -ENOMEM;
802 803
		ext4_warning(sb, "not enough memory for %lu groups",
			     gdb_num + 1);
804 805 806 807 808 809 810 811 812 813 814 815
		goto exit_inode;
	}

	/*
	 * Finally, we have all of the possible failures behind us...
	 *
	 * Remove new GDT block from inode double-indirect block and clear out
	 * the new GDT block for use (which also "frees" the backup GDT blocks
	 * from the reserved inode).  We don't need to change the bitmaps for
	 * these blocks, because they are marked as in-use from being in the
	 * reserved inode, and will become GDT blocks (primary and backup).
	 */
816
	data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
817 818 819 820 821
	err = ext4_handle_dirty_metadata(handle, NULL, dind);
	if (unlikely(err)) {
		ext4_std_error(sb, err);
		goto exit_inode;
	}
822
	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
823
	ext4_mark_iloc_dirty(handle, inode, &iloc);
824 825
	memset(gdb_bh->b_data, 0, sb->s_blocksize);
	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
826 827 828 829 830
	if (unlikely(err)) {
		ext4_std_error(sb, err);
		goto exit_inode;
	}
	brelse(dind);
831

832
	o_group_desc = EXT4_SB(sb)->s_group_desc;
833
	memcpy(n_group_desc, o_group_desc,
834
	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
835
	n_group_desc[gdb_num] = gdb_bh;
836 837
	EXT4_SB(sb)->s_group_desc = n_group_desc;
	EXT4_SB(sb)->s_gdb_count++;
838
	ext4_kvfree(o_group_desc);
839

M
Marcin Slusarz 已提交
840
	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
841
	err = ext4_handle_dirty_super(handle, sb);
842 843
	if (err)
		ext4_std_error(sb, err);
844

845
	return err;
846 847

exit_inode:
848
	ext4_kvfree(n_group_desc);
849
	/* ext4_handle_release_buffer(handle, iloc.bh); */
850 851
	brelse(iloc.bh);
exit_dindj:
852
	/* ext4_handle_release_buffer(handle, dind); */
853
exit_sbh:
854
	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
855 856 857
exit_dind:
	brelse(dind);
exit_bh:
858
	brelse(gdb_bh);
859

860
	ext4_debug("leaving with error %d\n", err);
861 862 863
	return err;
}

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
/*
 * add_new_gdb_meta_bg is the sister of add_new_gdb.
 */
static int add_new_gdb_meta_bg(struct super_block *sb,
			       handle_t *handle, ext4_group_t group) {
	ext4_fsblk_t gdblock;
	struct buffer_head *gdb_bh;
	struct buffer_head **o_group_desc, **n_group_desc;
	unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
	int err;

	gdblock = ext4_meta_bg_first_block_no(sb, group) +
		   ext4_bg_has_super(sb, group);
	gdb_bh = sb_bread(sb, gdblock);
	if (!gdb_bh)
		return -EIO;
	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
				     sizeof(struct buffer_head *),
				     GFP_NOFS);
	if (!n_group_desc) {
		err = -ENOMEM;
		ext4_warning(sb, "not enough memory for %lu groups",
			     gdb_num + 1);
		return err;
	}

	o_group_desc = EXT4_SB(sb)->s_group_desc;
	memcpy(n_group_desc, o_group_desc,
	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
	n_group_desc[gdb_num] = gdb_bh;
	EXT4_SB(sb)->s_group_desc = n_group_desc;
	EXT4_SB(sb)->s_gdb_count++;
	ext4_kvfree(o_group_desc);
	err = ext4_journal_get_write_access(handle, gdb_bh);
	if (unlikely(err))
		brelse(gdb_bh);
	return err;
}

903 904 905 906 907 908 909 910 911 912 913 914 915 916
/*
 * Called when we are adding a new group which has a backup copy of each of
 * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
 * We need to add these reserved backup GDT blocks to the resize inode, so
 * that they are kept for future resizing and not allocated to files.
 *
 * Each reserved backup GDT block will go into a different indirect block.
 * The indirect blocks are actually the primary reserved GDT blocks,
 * so we know in advance what their block numbers are.  We only get the
 * double-indirect block to verify it is pointing to the primary reserved
 * GDT blocks so we don't overwrite a data block by accident.  The reserved
 * backup GDT blocks are stored in their reserved primary GDT block.
 */
static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
917
			      ext4_group_t group)
918 919
{
	struct super_block *sb = inode->i_sb;
920
	int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
921 922
	struct buffer_head **primary;
	struct buffer_head *dind;
923 924
	struct ext4_iloc iloc;
	ext4_fsblk_t blk;
925 926 927 928 929
	__le32 *data, *end;
	int gdbackups = 0;
	int res, i;
	int err;

930
	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_NOFS);
931 932 933
	if (!primary)
		return -ENOMEM;

934
	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
935 936 937 938 939 940
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_free;
	}

941
	blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
J
Josef Bacik 已提交
942 943
	data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
					 EXT4_ADDR_PER_BLOCK(sb));
944
	end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
945 946 947 948

	/* Get each reserved primary GDT block and verify it holds backups */
	for (res = 0; res < reserved_gdb; res++, blk++) {
		if (le32_to_cpu(*data) != blk) {
949
			ext4_warning(sb, "reserved block %llu"
950 951 952 953 954 955 956 957 958 959 960
				     " not at offset %ld",
				     blk,
				     (long)(data - (__le32 *)dind->b_data));
			err = -EINVAL;
			goto exit_bh;
		}
		primary[res] = sb_bread(sb, blk);
		if (!primary[res]) {
			err = -EIO;
			goto exit_bh;
		}
961 962
		gdbackups = verify_reserved_gdb(sb, group, primary[res]);
		if (gdbackups < 0) {
963 964 965 966 967 968 969 970 971
			brelse(primary[res]);
			err = gdbackups;
			goto exit_bh;
		}
		if (++data >= end)
			data = (__le32 *)dind->b_data;
	}

	for (i = 0; i < reserved_gdb; i++) {
972
		if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
973 974 975
			/*
			int j;
			for (j = 0; j < i; j++)
976
				ext4_handle_release_buffer(handle, primary[j]);
977 978 979 980 981
			 */
			goto exit_bh;
		}
	}

982
	if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
983 984 985 986 987 988
		goto exit_bh;

	/*
	 * Finally we can add each of the reserved backup GDT blocks from
	 * the new group to its reserved primary GDT block.
	 */
989
	blk = group * EXT4_BLOCKS_PER_GROUP(sb);
990 991 992 993 994 995 996
	for (i = 0; i < reserved_gdb; i++) {
		int err2;
		data = (__le32 *)primary[i]->b_data;
		/* printk("reserving backup %lu[%u] = %lu\n",
		       primary[i]->b_blocknr, gdbackups,
		       blk + primary[i]->b_blocknr); */
		data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
997
		err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
998 999 1000 1001
		if (!err)
			err = err2;
	}
	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
1002
	ext4_mark_iloc_dirty(handle, inode, &iloc);
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015

exit_bh:
	while (--res >= 0)
		brelse(primary[res]);
	brelse(dind);

exit_free:
	kfree(primary);

	return err;
}

/*
1016
 * Update the backup copies of the ext4 metadata.  These don't need to be part
1017 1018 1019 1020 1021 1022 1023
 * of the main resize transaction, because e2fsck will re-write them if there
 * is a problem (basically only OOM will cause a problem).  However, we
 * _should_ update the backups if possible, in case the primary gets trashed
 * for some reason and we need to run e2fsck from a backup superblock.  The
 * important part is that the new block and inode counts are in the backup
 * superblocks, and the location of the new group metadata in the GDT backups.
 *
1024 1025 1026 1027 1028 1029
 * We do not need take the s_resize_lock for this, because these
 * blocks are not otherwise touched by the filesystem code when it is
 * mounted.  We don't need to worry about last changing from
 * sbi->s_groups_count, because the worst that can happen is that we
 * do not copy the full number of backups at this time.  The resize
 * which changed s_groups_count will backup again.
1030
 */
1031 1032
static void update_backups(struct super_block *sb, int blk_off, char *data,
			   int size, int meta_bg)
1033
{
1034
	struct ext4_sb_info *sbi = EXT4_SB(sb);
1035
	ext4_group_t last;
1036
	const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
1037 1038 1039
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
1040
	ext4_group_t group = 0;
1041 1042 1043 1044
	int rest = sb->s_blocksize - size;
	handle_t *handle;
	int err = 0, err2;

1045
	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
1046 1047 1048 1049 1050 1051
	if (IS_ERR(handle)) {
		group = 1;
		err = PTR_ERR(handle);
		goto exit_err;
	}

1052 1053
	ext4_superblock_csum_set(sb, (struct ext4_super_block *)data);

1054 1055 1056 1057 1058 1059 1060 1061 1062
	if (meta_bg == 0) {
		group = ext4_list_backups(sb, &three, &five, &seven);
		last = sbi->s_groups_count;
	} else {
		group = ext4_meta_bg_first_group(sb, group) + 1;
		last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2);
	}

	while (group < sbi->s_groups_count) {
1063
		struct buffer_head *bh;
1064
		ext4_fsblk_t backup_block;
1065 1066

		/* Out of journal space, and can't get more - abort - so sad */
1067 1068
		if (ext4_handle_valid(handle) &&
		    handle->h_buffer_credits == 0 &&
1069 1070
		    ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
		    (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
1071 1072
			break;

1073 1074 1075 1076 1077 1078 1079
		if (meta_bg == 0)
			backup_block = group * bpg + blk_off;
		else
			backup_block = (ext4_group_first_block_no(sb, group) +
					ext4_bg_has_super(sb, group));

		bh = sb_getblk(sb, backup_block);
1080 1081 1082 1083
		if (!bh) {
			err = -EIO;
			break;
		}
1084 1085 1086
		ext4_debug("update metadata backup %llu(+%llu)\n",
			   backup_block, backup_block -
			   ext4_group_first_block_no(sb, group));
1087
		if ((err = ext4_journal_get_write_access(handle, bh)))
1088 1089 1090 1091 1092 1093 1094
			break;
		lock_buffer(bh);
		memcpy(bh->b_data, data, size);
		if (rest)
			memset(bh->b_data + size, 0, rest);
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
1095 1096 1097
		err = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (unlikely(err))
			ext4_std_error(sb, err);
1098
		brelse(bh);
1099 1100 1101 1102 1103 1104 1105

		if (meta_bg == 0)
			group = ext4_list_backups(sb, &three, &five, &seven);
		else if (group == last)
			break;
		else
			group = last;
1106
	}
1107
	if ((err2 = ext4_journal_stop(handle)) && !err)
1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
		err = err2;

	/*
	 * Ugh! Need to have e2fsck write the backup copies.  It is too
	 * late to revert the resize, we shouldn't fail just because of
	 * the backup copies (they are only needed in case of corruption).
	 *
	 * However, if we got here we have a journal problem too, so we
	 * can't really start a transaction to mark the superblock.
	 * Chicken out and just set the flag on the hope it will be written
	 * to disk, and if not - we will simply wait until next fsck.
	 */
exit_err:
	if (err) {
1122
		ext4_warning(sb, "can't update backup for group %u (err %d), "
1123
			     "forcing fsck on next reboot", group, err);
1124 1125
		sbi->s_mount_state &= ~EXT4_VALID_FS;
		sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
1126 1127 1128 1129
		mark_buffer_dirty(sbi->s_sbh);
	}
}

1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147
/*
 * ext4_add_new_descs() adds @count group descriptor of groups
 * starting at @group
 *
 * @handle: journal handle
 * @sb: super block
 * @group: the group no. of the first group desc to be added
 * @resize_inode: the resize inode
 * @count: number of group descriptors to be added
 */
static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
			      ext4_group_t group, struct inode *resize_inode,
			      ext4_group_t count)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	struct buffer_head *gdb_bh;
	int i, gdb_off, gdb_num, err = 0;
1148
	int meta_bg;
1149

1150
	meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169
	for (i = 0; i < count; i++, group++) {
		int reserved_gdb = ext4_bg_has_super(sb, group) ?
			le16_to_cpu(es->s_reserved_gdt_blocks) : 0;

		gdb_off = group % EXT4_DESC_PER_BLOCK(sb);
		gdb_num = group / EXT4_DESC_PER_BLOCK(sb);

		/*
		 * We will only either add reserved group blocks to a backup group
		 * or remove reserved blocks for the first group in a new group block.
		 * Doing both would be mean more complex code, and sane people don't
		 * use non-sparse filesystems anymore.  This is already checked above.
		 */
		if (gdb_off) {
			gdb_bh = sbi->s_group_desc[gdb_num];
			err = ext4_journal_get_write_access(handle, gdb_bh);

			if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
				err = reserve_backup_gdb(handle, resize_inode, group);
1170 1171 1172
		} else if (meta_bg != 0) {
			err = add_new_gdb_meta_bg(sb, handle, group);
		} else {
1173
			err = add_new_gdb(handle, resize_inode, group);
1174
		}
1175 1176 1177 1178 1179 1180
		if (err)
			break;
	}
	return err;
}

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
static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block)
{
	struct buffer_head *bh = sb_getblk(sb, block);
	if (!bh)
		return NULL;

	if (bitmap_uptodate(bh))
		return bh;

	lock_buffer(bh);
	if (bh_submit_read(bh) < 0) {
		unlock_buffer(bh);
		brelse(bh);
		return NULL;
	}
	unlock_buffer(bh);

	return bh;
}

static int ext4_set_bitmap_checksums(struct super_block *sb,
				     ext4_group_t group,
				     struct ext4_group_desc *gdp,
				     struct ext4_new_group_data *group_data)
{
	struct buffer_head *bh;

	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
		return 0;

	bh = ext4_get_bitmap(sb, group_data->inode_bitmap);
	if (!bh)
		return -EIO;
	ext4_inode_bitmap_csum_set(sb, group, gdp, bh,
				   EXT4_INODES_PER_GROUP(sb) / 8);
	brelse(bh);

1219 1220 1221 1222 1223 1224 1225
	bh = ext4_get_bitmap(sb, group_data->block_bitmap);
	if (!bh)
		return -EIO;
	ext4_block_bitmap_csum_set(sb, group, gdp, bh,
				   EXT4_BLOCKS_PER_GROUP(sb) / 8);
	brelse(bh);

1226 1227 1228
	return 0;
}

1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254
/*
 * ext4_setup_new_descs() will set up the group descriptor descriptors of a flex bg
 */
static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
				struct ext4_new_flex_group_data *flex_gd)
{
	struct ext4_new_group_data	*group_data = flex_gd->groups;
	struct ext4_group_desc		*gdp;
	struct ext4_sb_info		*sbi = EXT4_SB(sb);
	struct buffer_head		*gdb_bh;
	ext4_group_t			group;
	__u16				*bg_flags = flex_gd->bg_flags;
	int				i, gdb_off, gdb_num, err = 0;
	

	for (i = 0; i < flex_gd->count; i++, group_data++, bg_flags++) {
		group = group_data->group;

		gdb_off = group % EXT4_DESC_PER_BLOCK(sb);
		gdb_num = group / EXT4_DESC_PER_BLOCK(sb);

		/*
		 * get_write_access() has been called on gdb_bh by ext4_add_new_desc().
		 */
		gdb_bh = sbi->s_group_desc[gdb_num];
		/* Update group descriptor block for new group */
1255
		gdp = (struct ext4_group_desc *)(gdb_bh->b_data +
1256 1257 1258 1259 1260
						 gdb_off * EXT4_DESC_SIZE(sb));

		memset(gdp, 0, EXT4_DESC_SIZE(sb));
		ext4_block_bitmap_set(sb, gdp, group_data->block_bitmap);
		ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap);
1261 1262 1263 1264 1265 1266
		err = ext4_set_bitmap_checksums(sb, group, gdp, group_data);
		if (err) {
			ext4_std_error(sb, err);
			break;
		}

1267 1268 1269 1270
		ext4_inode_table_set(sb, gdp, group_data->inode_table);
		ext4_free_group_clusters_set(sb, gdp,
					     EXT4_B2C(sbi, group_data->free_blocks_count));
		ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
1271 1272 1273
		if (ext4_has_group_desc_csum(sb))
			ext4_itable_unused_set(sb, gdp,
					       EXT4_INODES_PER_GROUP(sb));
1274
		gdp->bg_flags = cpu_to_le16(*bg_flags);
1275
		ext4_group_desc_csum_set(sb, group, gdp);
1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293

		err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
		if (unlikely(err)) {
			ext4_std_error(sb, err);
			break;
		}

		/*
		 * We can allocate memory for mb_alloc based on the new group
		 * descriptor
		 */
		err = ext4_mb_add_groupinfo(sb, group, gdp);
		if (err)
			break;
	}
	return err;
}

1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309
/*
 * ext4_update_super() updates the super block so that the newly added
 * groups can be seen by the filesystem.
 *
 * @sb: super block
 * @flex_gd: new added groups
 */
static void ext4_update_super(struct super_block *sb,
			     struct ext4_new_flex_group_data *flex_gd)
{
	ext4_fsblk_t blocks_count = 0;
	ext4_fsblk_t free_blocks = 0;
	ext4_fsblk_t reserved_blocks = 0;
	struct ext4_new_group_data *group_data = flex_gd->groups;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
1310
	int i;
1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328

	BUG_ON(flex_gd->count == 0 || group_data == NULL);
	/*
	 * Make the new blocks and inodes valid next.  We do this before
	 * increasing the group count so that once the group is enabled,
	 * all of its blocks and inodes are already valid.
	 *
	 * We always allocate group-by-group, then block-by-block or
	 * inode-by-inode within a group, so enabling these
	 * blocks/inodes before the group is live won't actually let us
	 * allocate the new space yet.
	 */
	for (i = 0; i < flex_gd->count; i++) {
		blocks_count += group_data[i].blocks_count;
		free_blocks += group_data[i].free_blocks_count;
	}

	reserved_blocks = ext4_r_blocks_count(es) * 100;
1329
	reserved_blocks = div64_u64(reserved_blocks, ext4_blocks_count(es));
1330 1331 1332 1333
	reserved_blocks *= blocks_count;
	do_div(reserved_blocks, 100);

	ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
1334
	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
1335 1336
	le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
		     flex_gd->count);
1337 1338
	le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) *
		     flex_gd->count);
1339

1340
	ext4_debug("free blocks count %llu", ext4_free_blocks_count(es));
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
	/*
	 * We need to protect s_groups_count against other CPUs seeing
	 * inconsistent state in the superblock.
	 *
	 * The precise rules we use are:
	 *
	 * * Writers must perform a smp_wmb() after updating all
	 *   dependent data and before modifying the groups count
	 *
	 * * Readers must perform an smp_rmb() after reading the groups
	 *   count and before reading any dependent data.
	 *
	 * NB. These rules can be relaxed when checking the group count
	 * while freeing data, as we can only allocate from a block
	 * group after serialising against the group count, and we can
	 * only then free after serialising in turn against that
	 * allocation.
	 */
	smp_wmb();

	/* Update the global fs size fields */
	sbi->s_groups_count += flex_gd->count;

	/* Update the reserved block counts only once the new group is
	 * active. */
	ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
				reserved_blocks);

	/* Update the free space counts */
	percpu_counter_add(&sbi->s_freeclusters_counter,
			   EXT4_B2C(sbi, free_blocks));
	percpu_counter_add(&sbi->s_freeinodes_counter,
			   EXT4_INODES_PER_GROUP(sb) * flex_gd->count);

1375 1376
	ext4_debug("free blocks count %llu",
		   percpu_counter_read(&sbi->s_freeclusters_counter));
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
	if (EXT4_HAS_INCOMPAT_FEATURE(sb,
				      EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
	    sbi->s_log_groups_per_flex) {
		ext4_group_t flex_group;
		flex_group = ext4_flex_group(sbi, group_data[0].group);
		atomic_add(EXT4_B2C(sbi, free_blocks),
			   &sbi->s_flex_groups[flex_group].free_clusters);
		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
			   &sbi->s_flex_groups[flex_group].free_inodes);
	}

1388 1389 1390 1391 1392
	/*
	 * Update the fs overhead information
	 */
	ext4_calculate_overhead(sb);

1393 1394 1395 1396 1397 1398
	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG "EXT4-fs: added group %u:"
		       "%llu blocks(%llu free %llu reserved)\n", flex_gd->count,
		       blocks_count, free_blocks, reserved_blocks);
}

1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464
/* Add a flex group to an fs. Ensure we handle all possible error conditions
 * _before_ we start modifying the filesystem, because we cannot abort the
 * transaction and not have it write the data to disk.
 */
static int ext4_flex_group_add(struct super_block *sb,
			       struct inode *resize_inode,
			       struct ext4_new_flex_group_data *flex_gd)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	ext4_fsblk_t o_blocks_count;
	ext4_grpblk_t last;
	ext4_group_t group;
	handle_t *handle;
	unsigned reserved_gdb;
	int err = 0, err2 = 0, credit;

	BUG_ON(!flex_gd->count || !flex_gd->groups || !flex_gd->bg_flags);

	reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
	o_blocks_count = ext4_blocks_count(es);
	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
	BUG_ON(last);

	err = setup_new_flex_group_blocks(sb, flex_gd);
	if (err)
		goto exit;
	/*
	 * We will always be modifying at least the superblock and  GDT
	 * block.  If we are adding a group past the last current GDT block,
	 * we will also modify the inode and the dindirect block.  If we
	 * are adding a group with superblock/GDT backups  we will also
	 * modify each of the reserved GDT dindirect blocks.
	 */
	credit = flex_gd->count * 4 + reserved_gdb;
	handle = ext4_journal_start_sb(sb, credit);
	if (IS_ERR(handle)) {
		err = PTR_ERR(handle);
		goto exit;
	}

	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
	if (err)
		goto exit_journal;

	group = flex_gd->groups[0].group;
	BUG_ON(group != EXT4_SB(sb)->s_groups_count);
	err = ext4_add_new_descs(handle, sb, group,
				resize_inode, flex_gd->count);
	if (err)
		goto exit_journal;

	err = ext4_setup_new_descs(handle, sb, flex_gd);
	if (err)
		goto exit_journal;

	ext4_update_super(sb, flex_gd);

	err = ext4_handle_dirty_super(handle, sb);

exit_journal:
	err2 = ext4_journal_stop(handle);
	if (!err)
		err = err2;

	if (!err) {
1465 1466 1467
		int gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
		int gdb_num_end = ((group + flex_gd->count - 1) /
				   EXT4_DESC_PER_BLOCK(sb));
1468 1469
		int meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb,
				EXT4_FEATURE_INCOMPAT_META_BG);
1470

1471
		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
1472
			       sizeof(struct ext4_super_block), 0);
1473
		for (; gdb_num <= gdb_num_end; gdb_num++) {
1474
			struct buffer_head *gdb_bh;
1475

1476 1477
			gdb_bh = sbi->s_group_desc[gdb_num];
			update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
1478
				       gdb_bh->b_size, meta_bg);
1479 1480 1481 1482 1483 1484
		}
	}
exit:
	return err;
}

1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521
static int ext4_setup_next_flex_gd(struct super_block *sb,
				    struct ext4_new_flex_group_data *flex_gd,
				    ext4_fsblk_t n_blocks_count,
				    unsigned long flexbg_size)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	struct ext4_new_group_data *group_data = flex_gd->groups;
	ext4_fsblk_t o_blocks_count;
	ext4_group_t n_group;
	ext4_group_t group;
	ext4_group_t last_group;
	ext4_grpblk_t last;
	ext4_grpblk_t blocks_per_group;
	unsigned long i;

	blocks_per_group = EXT4_BLOCKS_PER_GROUP(sb);

	o_blocks_count = ext4_blocks_count(es);

	if (o_blocks_count == n_blocks_count)
		return 0;

	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
	BUG_ON(last);
	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);

	last_group = group | (flexbg_size - 1);
	if (last_group > n_group)
		last_group = n_group;

	flex_gd->count = last_group - group + 1;

	for (i = 0; i < flex_gd->count; i++) {
		int overhead;

		group_data[i].group = group + i;
		group_data[i].blocks_count = blocks_per_group;
1522
		overhead = ext4_group_overhead_blocks(sb, group + i);
1523
		group_data[i].free_blocks_count = blocks_per_group - overhead;
1524
		if (ext4_has_group_desc_csum(sb))
1525 1526 1527 1528 1529 1530
			flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT |
					       EXT4_BG_INODE_UNINIT;
		else
			flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED;
	}

1531
	if (last_group == n_group && ext4_has_group_desc_csum(sb))
1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
		/* We need to initialize block bitmap of last group. */
		flex_gd->bg_flags[i - 1] &= ~EXT4_BG_BLOCK_UNINIT;

	if ((last_group == n_group) && (last != blocks_per_group - 1)) {
		group_data[i - 1].blocks_count = last + 1;
		group_data[i - 1].free_blocks_count -= blocks_per_group-
					last - 1;
	}

	return 1;
}

1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556
/* Add group descriptor data to an existing or new group descriptor block.
 * Ensure we handle all possible error conditions _before_ we start modifying
 * the filesystem, because we cannot abort the transaction and not have it
 * write the data to disk.
 *
 * If we are on a GDT block boundary, we need to get the reserved GDT block.
 * Otherwise, we may need to add backup GDT blocks for a sparse group.
 *
 * We only need to hold the superblock lock while we are actually adding
 * in the new group's counts to the superblock.  Prior to that we have
 * not really "added" the group at all.  We re-check that we are still
 * adding in the last group in case things have changed since verifying.
 */
1557
int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
1558
{
1559
	struct ext4_new_flex_group_data flex_gd;
1560 1561 1562
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
1563 1564 1565
		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
	struct inode *inode = NULL;
	int gdb_off, gdb_num;
1566 1567
	int err;
	__u16 bg_flags = 0;
1568

1569 1570
	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
	gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
1571

1572 1573
	if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
1574
		ext4_warning(sb, "Can't resize non-sparse filesystem further");
1575 1576 1577
		return -EPERM;
	}

L
Laurent Vivier 已提交
1578 1579
	if (ext4_blocks_count(es) + input->blocks_count <
	    ext4_blocks_count(es)) {
1580
		ext4_warning(sb, "blocks_count overflow");
1581 1582 1583
		return -EINVAL;
	}

1584
	if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
1585
	    le32_to_cpu(es->s_inodes_count)) {
1586
		ext4_warning(sb, "inodes_count overflow");
1587 1588 1589 1590
		return -EINVAL;
	}

	if (reserved_gdb || gdb_off == 0) {
1591
		if (!EXT4_HAS_COMPAT_FEATURE(sb,
1592 1593
					     EXT4_FEATURE_COMPAT_RESIZE_INODE)
		    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
1594
			ext4_warning(sb,
1595 1596 1597
				     "No reserved GDT blocks, can't resize");
			return -EPERM;
		}
1598 1599
		inode = ext4_iget(sb, EXT4_RESIZE_INO);
		if (IS_ERR(inode)) {
1600
			ext4_warning(sb, "Error opening resize inode");
1601
			return PTR_ERR(inode);
1602 1603 1604
		}
	}

1605

1606
	err = verify_group_input(sb, input);
1607
	if (err)
1608
		goto out;
1609

1610 1611 1612 1613
	err = ext4_alloc_flex_bg_array(sb, input->group + 1);
	if (err)
		return err;

1614 1615 1616 1617
	err = ext4_mb_alloc_groupinfo(sb, input->group + 1);
	if (err)
		goto out;

1618 1619 1620 1621 1622
	flex_gd.count = 1;
	flex_gd.groups = input;
	flex_gd.bg_flags = &bg_flags;
	err = ext4_flex_group_add(sb, inode, &flex_gd);
out:
1623 1624
	iput(inode);
	return err;
1625
} /* ext4_group_add */
1626

1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653
/*
 * extend a group without checking assuming that checking has been done.
 */
static int ext4_group_extend_no_check(struct super_block *sb,
				      ext4_fsblk_t o_blocks_count, ext4_grpblk_t add)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	handle_t *handle;
	int err = 0, err2;

	/* We will update the superblock, one block bitmap, and
	 * one group descriptor via ext4_group_add_blocks().
	 */
	handle = ext4_journal_start_sb(sb, 3);
	if (IS_ERR(handle)) {
		err = PTR_ERR(handle);
		ext4_warning(sb, "error %d on journal start", err);
		return err;
	}

	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
	if (err) {
		ext4_warning(sb, "error %d on journal write access", err);
		goto errout;
	}

	ext4_blocks_count_set(es, o_blocks_count + add);
1654
	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669
	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
		   o_blocks_count + add);
	/* We add the blocks to the bitmap and set the group need init bit */
	err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
	if (err)
		goto errout;
	ext4_handle_dirty_super(handle, sb);
	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
		   o_blocks_count + add);
errout:
	err2 = ext4_journal_stop(handle);
	if (err2 && !err)
		err = err2;

	if (!err) {
1670 1671
		ext4_fsblk_t first_block;
		first_block = ext4_group_first_block_no(sb, 0);
1672 1673 1674
		if (test_opt(sb, DEBUG))
			printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
			       "blocks\n", ext4_blocks_count(es));
1675 1676
		update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr - first_block,
			       (char *)es, sizeof(struct ext4_super_block), 0);
1677 1678 1679 1680
	}
	return err;
}

1681 1682
/*
 * Extend the filesystem to the new number of blocks specified.  This entry
1683 1684 1685 1686
 * point is only used to extend the current filesystem to the end of the last
 * existing group.  It can be accessed via ioctl, or by "remount,resize=<size>"
 * for emergencies (because it has no dependencies on reserved blocks).
 *
1687
 * If we _really_ wanted, we could use default values to call ext4_group_add()
1688 1689 1690
 * allow the "remount" trick to work for arbitrary resizing, assuming enough
 * GDT blocks are reserved to grow to the desired size.
 */
1691 1692
int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
		      ext4_fsblk_t n_blocks_count)
1693
{
1694 1695 1696
	ext4_fsblk_t o_blocks_count;
	ext4_grpblk_t last;
	ext4_grpblk_t add;
1697
	struct buffer_head *bh;
1698
	int err;
1699
	ext4_group_t group;
1700

L
Laurent Vivier 已提交
1701
	o_blocks_count = ext4_blocks_count(es);
1702 1703

	if (test_opt(sb, DEBUG))
1704 1705 1706
		ext4_msg(sb, KERN_DEBUG,
			 "extending last group from %llu to %llu blocks",
			 o_blocks_count, n_blocks_count);
1707 1708 1709 1710 1711

	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
		return 0;

	if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
1712 1713 1714
		ext4_msg(sb, KERN_ERR,
			 "filesystem too large to resize to %llu blocks safely",
			 n_blocks_count);
1715
		if (sizeof(sector_t) < 8)
1716
			ext4_warning(sb, "CONFIG_LBDAF not enabled");
1717 1718 1719 1720
		return -EINVAL;
	}

	if (n_blocks_count < o_blocks_count) {
1721
		ext4_warning(sb, "can't shrink FS - resize aborted");
1722
		return -EINVAL;
1723 1724 1725
	}

	/* Handle the remaining blocks in the last group only. */
1726
	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
1727 1728

	if (last == 0) {
1729
		ext4_warning(sb, "need to use ext2online to resize further");
1730 1731 1732
		return -EPERM;
	}

1733
	add = EXT4_BLOCKS_PER_GROUP(sb) - last;
1734 1735

	if (o_blocks_count + add < o_blocks_count) {
1736
		ext4_warning(sb, "blocks_count overflow");
1737 1738 1739 1740 1741 1742 1743
		return -EINVAL;
	}

	if (o_blocks_count + add > n_blocks_count)
		add = n_blocks_count - o_blocks_count;

	if (o_blocks_count + add < n_blocks_count)
1744
		ext4_warning(sb, "will only finish group (%llu blocks, %u new)",
1745 1746 1747
			     o_blocks_count + add, add);

	/* See if the device is actually as big as what was requested */
1748
	bh = sb_bread(sb, o_blocks_count + add - 1);
1749
	if (!bh) {
1750
		ext4_warning(sb, "can't read last block, resize aborted");
1751 1752 1753 1754
		return -ENOSPC;
	}
	brelse(bh);

1755
	err = ext4_group_extend_no_check(sb, o_blocks_count, add);
1756
	return err;
1757
} /* ext4_group_extend */
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 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851

static int num_desc_blocks(struct super_block *sb, ext4_group_t groups)
{
	return (groups + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb);
}

/*
 * Release the resize inode and drop the resize_inode feature if there
 * are no more reserved gdt blocks, and then convert the file system
 * to enable meta_bg
 */
static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
{
	handle_t *handle;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	struct ext4_inode_info *ei = 0;
	ext4_fsblk_t nr;
	int i, ret, err = 0;
	int credits = 1;

	ext4_msg(sb, KERN_INFO, "Converting file system to meta_bg");
	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE)) {
		if (es->s_reserved_gdt_blocks) {
			ext4_error(sb, "Unexpected non-zero "
				   "s_reserved_gdt_blocks");
			return -EPERM;
		}
		if (!inode) {
			ext4_error(sb, "Unexpected NULL resize_inode");
			return -EPERM;
		}
		ei = EXT4_I(inode);

		/* Do a quick sanity check of the resize inode */
		if (inode->i_blocks != 1 << (inode->i_blkbits - 9))
			goto invalid_resize_inode;
		for (i = 0; i < EXT4_N_BLOCKS; i++) {
			if (i == EXT4_DIND_BLOCK) {
				if (ei->i_data[i])
					continue;
				else
					goto invalid_resize_inode;
			}
			if (ei->i_data[i])
				goto invalid_resize_inode;
		}
		credits += 3;	/* block bitmap, bg descriptor, resize inode */
	}

	handle = ext4_journal_start_sb(sb, credits);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
	if (err)
		goto errout;

	EXT4_CLEAR_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE);
	EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
	sbi->s_es->s_first_meta_bg =
		cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));

	err = ext4_handle_dirty_super(handle, sb);
	if (err) {
		ext4_std_error(sb, err);
		goto errout;
	}

	if (inode) {
		nr = le32_to_cpu(ei->i_data[EXT4_DIND_BLOCK]);
		ext4_free_blocks(handle, inode, NULL, nr, 1,
				 EXT4_FREE_BLOCKS_METADATA |
				 EXT4_FREE_BLOCKS_FORGET);
		ei->i_data[EXT4_DIND_BLOCK] = 0;
		inode->i_blocks = 0;

		err = ext4_mark_inode_dirty(handle, inode);
		if (err)
			ext4_std_error(sb, err);
	}

errout:
	ret = ext4_journal_stop(handle);
	if (!err)
		err = ret;
	return ret;

invalid_resize_inode:
	ext4_error(sb, "corrupted/inconsistent resize inode");
	return -EINVAL;
}

1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863
/*
 * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count
 *
 * @sb: super block of the fs to be resized
 * @n_blocks_count: the number of blocks resides in the resized fs
 */
int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
{
	struct ext4_new_flex_group_data *flex_gd = NULL;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	struct buffer_head *bh;
1864 1865
	struct inode *resize_inode = NULL;
	ext4_grpblk_t add, offset;
1866 1867
	unsigned long n_desc_blocks;
	unsigned long o_desc_blocks;
1868 1869 1870
	ext4_group_t o_group;
	ext4_group_t n_group;
	ext4_fsblk_t o_blocks_count;
1871
	ext4_fsblk_t n_blocks_count_retry = 0;
1872
	unsigned long last_update_time = 0;
1873
	int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex;
1874
	int meta_bg;
1875

1876
retry:
1877 1878 1879
	o_blocks_count = ext4_blocks_count(es);

	if (test_opt(sb, DEBUG))
1880 1881
		ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu "
		       "to %llu blocks", o_blocks_count, n_blocks_count);
1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893

	if (n_blocks_count < o_blocks_count) {
		/* On-line shrinking not supported */
		ext4_warning(sb, "can't shrink FS - resize aborted");
		return -EINVAL;
	}

	if (n_blocks_count == o_blocks_count)
		/* Nothing need to do */
		return 0;

	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
1894
	ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
1895

1896 1897
	n_desc_blocks = num_desc_blocks(sb, n_group + 1);
	o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count);
1898

1899
	meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
1900

1901 1902 1903 1904 1905 1906
	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE)) {
		if (meta_bg) {
			ext4_error(sb, "resize_inode and meta_bg enabled "
				   "simultaneously");
			return -EINVAL;
		}
1907 1908 1909 1910 1911 1912 1913 1914
		if (n_desc_blocks > o_desc_blocks +
		    le16_to_cpu(es->s_reserved_gdt_blocks)) {
			n_blocks_count_retry = n_blocks_count;
			n_desc_blocks = o_desc_blocks +
				le16_to_cpu(es->s_reserved_gdt_blocks);
			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
			n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb);
			n_group--; /* set to last group number */
1915
		}
1916 1917 1918

		if (!resize_inode)
			resize_inode = ext4_iget(sb, EXT4_RESIZE_INO);
1919 1920 1921 1922
		if (IS_ERR(resize_inode)) {
			ext4_warning(sb, "Error opening resize inode");
			return PTR_ERR(resize_inode);
		}
1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937
	}

	if ((!resize_inode && !meta_bg) || n_group == o_group) {
		err = ext4_convert_meta_bg(sb, resize_inode);
		if (err)
			goto out;
		if (resize_inode) {
			iput(resize_inode);
			resize_inode = NULL;
		}
		if (n_blocks_count_retry) {
			n_blocks_count = n_blocks_count_retry;
			n_blocks_count_retry = 0;
			goto retry;
		}
1938 1939 1940 1941 1942 1943 1944 1945 1946 1947
	}

	/* See if the device is actually as big as what was requested */
	bh = sb_bread(sb, n_blocks_count - 1);
	if (!bh) {
		ext4_warning(sb, "can't read last block, resize aborted");
		return -ENOSPC;
	}
	brelse(bh);

1948 1949 1950 1951 1952 1953
	/* extend the last group */
	if (n_group == o_group)
		add = n_blocks_count - o_blocks_count;
	else
		add = EXT4_BLOCKS_PER_GROUP(sb) - (offset + 1);
	if (add > 0) {
1954 1955 1956 1957 1958
		err = ext4_group_extend_no_check(sb, o_blocks_count, add);
		if (err)
			goto out;
	}

1959
	if (ext4_blocks_count(es) == n_blocks_count)
1960 1961
		goto out;

1962 1963 1964 1965
	err = ext4_alloc_flex_bg_array(sb, n_group + 1);
	if (err)
		return err;

1966 1967 1968 1969
	err = ext4_mb_alloc_groupinfo(sb, n_group + 1);
	if (err)
		goto out;

1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980
	flex_gd = alloc_flex_gd(flexbg_size);
	if (flex_gd == NULL) {
		err = -ENOMEM;
		goto out;
	}

	/* Add flex groups. Note that a regular group is a
	 * flex group with 1 group.
	 */
	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
					      flexbg_size)) {
1981 1982 1983 1984 1985 1986 1987
		if (jiffies - last_update_time > HZ * 10) {
			if (last_update_time)
				ext4_msg(sb, KERN_INFO,
					 "resized to %llu blocks",
					 ext4_blocks_count(es));
			last_update_time = jiffies;
		}
1988 1989
		if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0)
			break;
1990 1991 1992 1993 1994
		err = ext4_flex_group_add(sb, resize_inode, flex_gd);
		if (unlikely(err))
			break;
	}

1995 1996 1997 1998 1999 2000 2001 2002
	if (!err && n_blocks_count_retry) {
		n_blocks_count = n_blocks_count_retry;
		n_blocks_count_retry = 0;
		free_flex_gd(flex_gd);
		flex_gd = NULL;
		goto retry;
	}

2003 2004 2005
out:
	if (flex_gd)
		free_flex_gd(flex_gd);
2006 2007
	if (resize_inode != NULL)
		iput(resize_inode);
2008
	if (test_opt(sb, DEBUG))
2009 2010
		ext4_msg(sb, KERN_DEBUG, "resized filesystem to %llu",
			 n_blocks_count);
2011 2012
	return err;
}