resize.c 50.2 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
#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,
52
			      struct ext4_new_group_data *input)
53
{
54 55
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
L
Laurent Vivier 已提交
56
	ext4_fsblk_t start = ext4_blocks_count(es);
57
	ext4_fsblk_t end = start + input->blocks_count;
58
	ext4_group_t group = input->group;
59 60 61
	ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
	unsigned overhead = ext4_bg_has_super(sb, group) ?
		(1 + ext4_bg_num_gdb(sb, group) +
62
		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
63
	ext4_fsblk_t metaend = start + overhead;
64
	struct buffer_head *bh = NULL;
65
	ext4_grpblk_t free_blocks_count, offset;
66 67 68 69 70 71
	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))
72
		printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks "
73
		       "(%d free, %u reserved)\n",
74
		       ext4_bg_has_super(sb, input->group) ? "normal" :
75 76 77
		       "no-super", input->group, input->blocks_count,
		       free_blocks_count, input->reserved_blocks);

78
	ext4_get_group_no_and_offset(sb, start, NULL, &offset);
79
	if (group != sbi->s_groups_count)
80
		ext4_warning(sb, "Cannot add at group %u (only %u groups)",
81
			     input->group, sbi->s_groups_count);
82
	else if (offset != 0)
83
			ext4_warning(sb, "Last group not full");
84
	else if (input->reserved_blocks > input->blocks_count / 5)
85
		ext4_warning(sb, "Reserved blocks too high (%u)",
86 87
			     input->reserved_blocks);
	else if (free_blocks_count < 0)
88
		ext4_warning(sb, "Bad blocks count %u",
89 90
			     input->blocks_count);
	else if (!(bh = sb_bread(sb, end - 1)))
91
		ext4_warning(sb, "Cannot read last block (%llu)",
92 93
			     end - 1);
	else if (outside(input->block_bitmap, start, end))
94
		ext4_warning(sb, "Block bitmap not in group (block %llu)",
95
			     (unsigned long long)input->block_bitmap);
96
	else if (outside(input->inode_bitmap, start, end))
97
		ext4_warning(sb, "Inode bitmap not in group (block %llu)",
98
			     (unsigned long long)input->inode_bitmap);
99
	else if (outside(input->inode_table, start, end) ||
100
		 outside(itend - 1, start, end))
101
		ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
102
			     (unsigned long long)input->inode_table, itend - 1);
103
	else if (input->inode_bitmap == input->block_bitmap)
104
		ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
105
			     (unsigned long long)input->block_bitmap);
106
	else if (inside(input->block_bitmap, input->inode_table, itend))
107 108
		ext4_warning(sb, "Block bitmap (%llu) in inode table "
			     "(%llu-%llu)",
109 110
			     (unsigned long long)input->block_bitmap,
			     (unsigned long long)input->inode_table, itend - 1);
111
	else if (inside(input->inode_bitmap, input->inode_table, itend))
112 113
		ext4_warning(sb, "Inode bitmap (%llu) in inode table "
			     "(%llu-%llu)",
114 115
			     (unsigned long long)input->inode_bitmap,
			     (unsigned long long)input->inode_table, itend - 1);
116
	else if (inside(input->block_bitmap, start, metaend))
117
		ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
118 119
			     (unsigned long long)input->block_bitmap,
			     start, metaend - 1);
120
	else if (inside(input->inode_bitmap, start, metaend))
121
		ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
122 123
			     (unsigned long long)input->inode_bitmap,
			     start, metaend - 1);
124
	else if (inside(input->inode_table, start, metaend) ||
125
		 inside(itend - 1, start, metaend))
126 127
		ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
			     "(%llu-%llu)",
128 129
			     (unsigned long long)input->inode_table,
			     itend - 1, start, metaend - 1);
130 131 132 133 134 135 136
	else
		err = 0;
	brelse(bh);

	return err;
}

137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191
/*
 * 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;

	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);
}

192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302
/*
 * 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
 */
static void ext4_alloc_group_tables(struct super_block *sb,
				struct ext4_new_flex_group_data *flex_gd,
				int flexbg_size)
{
	struct ext4_new_group_data *group_data = flex_gd->groups;
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	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;
	start_blk = ext4_group_first_block_no(sb, src_group);
	last_blk = start_blk + group_data[src_group - group].blocks_count;

	overhead = ext4_bg_has_super(sb, src_group) ?
		   (1 + ext4_bg_num_gdb(sb, src_group) +
		    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;

	start_blk += overhead;

	BUG_ON(src_group >= group_data[0].group + flex_gd->count);
	/* We collect contiguous blocks as much as possible. */
	src_group++;
	for (; src_group <= last_group; src_group++)
		if (!ext4_bg_has_super(sb, src_group))
			last_blk += group_data[src_group - group].blocks_count;
		else
			break;

	/* 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);
		}
	}
}

303
static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
304
				  ext4_fsblk_t blk)
305 306 307 308 309 310 311
{
	struct buffer_head *bh;
	int err;

	bh = sb_getblk(sb, blk);
	if (!bh)
		return ERR_PTR(-EIO);
312
	if ((err = ext4_journal_get_write_access(handle, bh))) {
313 314 315 316 317 318 319 320 321 322
		brelse(bh);
		bh = ERR_PTR(err);
	} else {
		memset(bh->b_data, 0, sb->s_blocksize);
		set_buffer_uptodate(bh);
	}

	return bh;
}

323 324 325 326 327
/*
 * 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.
 */
328
static int extend_or_restart_transaction(handle_t *handle, int thresh)
329 330 331
{
	int err;

332
	if (ext4_handle_has_enough_credits(handle, thresh))
333 334 335 336 337 338
		return 0;

	err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
	if (err < 0)
		return err;
	if (err) {
339 340
		err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
		if (err)
341
			return err;
342
	}
343 344 345 346

	return 0;
}

347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
/*
 * 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;

	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);

	/* 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;

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

		/* Copy all of the GDT blocks into the backup in this group */
		for (j = 0, block = start + 1; j < gdblocks; j++, block++) {
			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;
		}

		/* 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;
		}
		if (ext4_bg_has_super(sb, group)) {
			ext4_debug("mark backup superblock %#04llx (+0)\n",
				   start);
			ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb +
						     1);
		}
		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;
}

597 598
/*
 * Iterate through the groups which hold BACKUP superblock/GDT copies in an
599
 * ext4 filesystem.  The counters should be initialized to 1, 5, and 7 before
600 601 602 603
 * 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, ...
 */
604
static unsigned ext4_list_backups(struct super_block *sb, unsigned *three,
605 606 607 608 609 610
				  unsigned *five, unsigned *seven)
{
	unsigned *min = three;
	int mult = 3;
	unsigned ret;

611 612
	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
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
		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,
639
			       ext4_group_t end,
640 641
			       struct buffer_head *primary)
{
642
	const ext4_fsblk_t blk = primary->b_blocknr;
643 644 645 646 647 648 649
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
	unsigned grp;
	__le32 *p = (__le32 *)primary->b_data;
	int gdbackups = 0;

650
	while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
L
Laurent Vivier 已提交
651 652
		if (le32_to_cpu(*p++) !=
		    grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
653
			ext4_warning(sb, "reserved GDT %llu"
654
				     " missing grp %d (%llu)",
655
				     blk, grp,
L
Laurent Vivier 已提交
656 657 658
				     grp *
				     (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
				     blk);
659 660
			return -EINVAL;
		}
661
		if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb))
662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681
			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,
682
		       ext4_group_t group)
683 684
{
	struct super_block *sb = inode->i_sb;
685
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
686
	unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
687
	ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
688 689
	struct buffer_head **o_group_desc, **n_group_desc;
	struct buffer_head *dind;
690
	struct buffer_head *gdb_bh;
691
	int gdbackups;
692
	struct ext4_iloc iloc;
693 694 695 696 697
	__le32 *data;
	int err;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG
698
		       "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
699 700
		       gdb_num);

701 702
	/*
	 * If we are not using the primary superblock/GDT copy don't resize,
703 704 705
         * because the user tools have no way of handling this.  Probably a
         * bad time to do it anyways.
         */
706 707
	if (EXT4_SB(sb)->s_sbh->b_blocknr !=
	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
708
		ext4_warning(sb, "won't resize using backup superblock at %llu",
709
			(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
710 711 712
		return -EPERM;
	}

713 714
	gdb_bh = sb_bread(sb, gdblock);
	if (!gdb_bh)
715 716
		return -EIO;

717
	gdbackups = verify_reserved_gdb(sb, group, gdb_bh);
718
	if (gdbackups < 0) {
719 720 721 722
		err = gdbackups;
		goto exit_bh;
	}

723
	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
724 725 726 727 728 729 730
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_bh;
	}

	data = (__le32 *)dind->b_data;
731
	if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
732
		ext4_warning(sb, "new group %u GDT block %llu not reserved",
733
			     group, gdblock);
734 735 736 737
		err = -EINVAL;
		goto exit_dind;
	}

738 739
	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
	if (unlikely(err))
740 741
		goto exit_dind;

742
	err = ext4_journal_get_write_access(handle, gdb_bh);
743
	if (unlikely(err))
744 745
		goto exit_sbh;

746 747 748
	err = ext4_journal_get_write_access(handle, dind);
	if (unlikely(err))
		ext4_std_error(sb, err);
749

750
	/* ext4_reserve_inode_write() gets a reference on the iloc */
751 752
	err = ext4_reserve_inode_write(handle, inode, &iloc);
	if (unlikely(err))
753 754
		goto exit_dindj;

755 756 757
	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
				     sizeof(struct buffer_head *),
				     GFP_NOFS);
758 759
	if (!n_group_desc) {
		err = -ENOMEM;
760 761
		ext4_warning(sb, "not enough memory for %lu groups",
			     gdb_num + 1);
762 763 764 765 766 767 768 769 770 771 772 773
		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).
	 */
774
	data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
775 776 777 778 779
	err = ext4_handle_dirty_metadata(handle, NULL, dind);
	if (unlikely(err)) {
		ext4_std_error(sb, err);
		goto exit_inode;
	}
780
	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
781
	ext4_mark_iloc_dirty(handle, inode, &iloc);
782 783
	memset(gdb_bh->b_data, 0, sb->s_blocksize);
	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
784 785 786 787 788
	if (unlikely(err)) {
		ext4_std_error(sb, err);
		goto exit_inode;
	}
	brelse(dind);
789

790
	o_group_desc = EXT4_SB(sb)->s_group_desc;
791
	memcpy(n_group_desc, o_group_desc,
792
	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
793
	n_group_desc[gdb_num] = gdb_bh;
794 795
	EXT4_SB(sb)->s_group_desc = n_group_desc;
	EXT4_SB(sb)->s_gdb_count++;
796
	ext4_kvfree(o_group_desc);
797

M
Marcin Slusarz 已提交
798
	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
799
	err = ext4_handle_dirty_super_now(handle, sb);
800 801
	if (err)
		ext4_std_error(sb, err);
802

803
	return err;
804 805

exit_inode:
806
	ext4_kvfree(n_group_desc);
807
	/* ext4_handle_release_buffer(handle, iloc.bh); */
808 809
	brelse(iloc.bh);
exit_dindj:
810
	/* ext4_handle_release_buffer(handle, dind); */
811
exit_sbh:
812
	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
813 814 815
exit_dind:
	brelse(dind);
exit_bh:
816
	brelse(gdb_bh);
817

818
	ext4_debug("leaving with error %d\n", err);
819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
	return err;
}

/*
 * 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,
836
			      ext4_group_t group)
837 838
{
	struct super_block *sb = inode->i_sb;
839
	int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
840 841
	struct buffer_head **primary;
	struct buffer_head *dind;
842 843
	struct ext4_iloc iloc;
	ext4_fsblk_t blk;
844 845 846 847 848
	__le32 *data, *end;
	int gdbackups = 0;
	int res, i;
	int err;

849
	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_NOFS);
850 851 852
	if (!primary)
		return -ENOMEM;

853
	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
854 855 856 857 858 859
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_free;
	}

860
	blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
J
Josef Bacik 已提交
861 862
	data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
					 EXT4_ADDR_PER_BLOCK(sb));
863
	end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
864 865 866 867

	/* 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) {
868
			ext4_warning(sb, "reserved block %llu"
869 870 871 872 873 874 875 876 877 878 879
				     " 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;
		}
880 881
		gdbackups = verify_reserved_gdb(sb, group, primary[res]);
		if (gdbackups < 0) {
882 883 884 885 886 887 888 889 890
			brelse(primary[res]);
			err = gdbackups;
			goto exit_bh;
		}
		if (++data >= end)
			data = (__le32 *)dind->b_data;
	}

	for (i = 0; i < reserved_gdb; i++) {
891
		if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
892 893 894
			/*
			int j;
			for (j = 0; j < i; j++)
895
				ext4_handle_release_buffer(handle, primary[j]);
896 897 898 899 900
			 */
			goto exit_bh;
		}
	}

901
	if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
902 903 904 905 906 907
		goto exit_bh;

	/*
	 * Finally we can add each of the reserved backup GDT blocks from
	 * the new group to its reserved primary GDT block.
	 */
908
	blk = group * EXT4_BLOCKS_PER_GROUP(sb);
909 910 911 912 913 914 915
	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);
916
		err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
917 918 919 920
		if (!err)
			err = err2;
	}
	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
921
	ext4_mark_iloc_dirty(handle, inode, &iloc);
922 923 924 925 926 927 928 929 930 931 932 933 934

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

exit_free:
	kfree(primary);

	return err;
}

/*
935
 * Update the backup copies of the ext4 metadata.  These don't need to be part
936 937 938 939 940 941 942
 * 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.
 *
943 944 945 946 947 948
 * 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.
949 950 951 952
 */
static void update_backups(struct super_block *sb,
			   int blk_off, char *data, int size)
{
953
	struct ext4_sb_info *sbi = EXT4_SB(sb);
954
	const ext4_group_t last = sbi->s_groups_count;
955
	const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
956 957 958
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
959
	ext4_group_t group;
960 961 962 963
	int rest = sb->s_blocksize - size;
	handle_t *handle;
	int err = 0, err2;

964
	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
965 966 967 968 969 970
	if (IS_ERR(handle)) {
		group = 1;
		err = PTR_ERR(handle);
		goto exit_err;
	}

971 972
	ext4_superblock_csum_set(sb, (struct ext4_super_block *)data);

973
	while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) {
974 975 976
		struct buffer_head *bh;

		/* Out of journal space, and can't get more - abort - so sad */
977 978
		if (ext4_handle_valid(handle) &&
		    handle->h_buffer_credits == 0 &&
979 980
		    ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
		    (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
981 982 983 984 985 986 987
			break;

		bh = sb_getblk(sb, group * bpg + blk_off);
		if (!bh) {
			err = -EIO;
			break;
		}
988
		ext4_debug("update metadata backup %#04lx\n",
989
			  (unsigned long)bh->b_blocknr);
990
		if ((err = ext4_journal_get_write_access(handle, bh)))
991 992 993 994 995 996 997
			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);
998 999 1000
		err = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (unlikely(err))
			ext4_std_error(sb, err);
1001 1002
		brelse(bh);
	}
1003
	if ((err2 = ext4_journal_stop(handle)) && !err)
1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017
		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) {
1018
		ext4_warning(sb, "can't update backup for group %u (err %d), "
1019
			     "forcing fsck on next reboot", group, err);
1020 1021
		sbi->s_mount_state &= ~EXT4_VALID_FS;
		sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
1022 1023 1024 1025
		mark_buffer_dirty(sbi->s_sbh);
	}
}

1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071
/*
 * 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;

	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);
		} else
			err = add_new_gdb(handle, resize_inode, group);
		if (err)
			break;
	}
	return err;
}

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109
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);

1110 1111 1112 1113 1114 1115 1116
	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);

1117 1118 1119
	return 0;
}

1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151
/*
 * 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 */
		gdp = (struct ext4_group_desc *)((char *)gdb_bh->b_data +
						 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);
1152 1153 1154 1155 1156 1157
		err = ext4_set_bitmap_checksums(sb, group, gdp, group_data);
		if (err) {
			ext4_std_error(sb, err);
			break;
		}

1158 1159 1160 1161 1162
		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));
		gdp->bg_flags = cpu_to_le16(*bg_flags);
1163
		ext4_group_desc_csum_set(sb, group, gdp);
1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181

		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;
}

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 1220 1221
/*
 * 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;
	int i;

	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;
	do_div(reserved_blocks, ext4_blocks_count(es));
	reserved_blocks *= blocks_count;
	do_div(reserved_blocks, 100);

	ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
1222
	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
1223 1224
	le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
		     flex_gd->count);
1225 1226
	le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) *
		     flex_gd->count);
1227 1228 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 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278

	/*
	 * 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);

	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);
	}

	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);
}

1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
/* 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) {
		int i;
		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
			       sizeof(struct ext4_super_block));
		for (i = 0; i < flex_gd->count; i++, group++) {
			struct buffer_head *gdb_bh;
			int gdb_num;
			gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb);
			gdb_bh = sbi->s_group_desc[gdb_num];
			update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
				       gdb_bh->b_size);
		}
	}
exit:
	return err;
}

1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401
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;
		overhead = ext4_bg_has_super(sb, group + i) ?
			   (1 + ext4_bg_num_gdb(sb, group + i) +
			    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
		group_data[i].free_blocks_count = blocks_per_group - overhead;
1402
		if (ext4_has_group_desc_csum(sb))
1403 1404 1405 1406 1407 1408
			flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT |
					       EXT4_BG_INODE_UNINIT;
		else
			flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED;
	}

1409
	if (last_group == n_group && ext4_has_group_desc_csum(sb))
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
		/* 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;
}

1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434
/* 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.
 */
1435
int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
1436
{
1437
	struct ext4_new_flex_group_data flex_gd;
1438 1439 1440
	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) ?
1441 1442 1443
		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
	struct inode *inode = NULL;
	int gdb_off, gdb_num;
1444 1445
	int err;
	__u16 bg_flags = 0;
1446

1447 1448
	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
	gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
1449

1450 1451
	if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
1452
		ext4_warning(sb, "Can't resize non-sparse filesystem further");
1453 1454 1455
		return -EPERM;
	}

L
Laurent Vivier 已提交
1456 1457
	if (ext4_blocks_count(es) + input->blocks_count <
	    ext4_blocks_count(es)) {
1458
		ext4_warning(sb, "blocks_count overflow");
1459 1460 1461
		return -EINVAL;
	}

1462
	if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
1463
	    le32_to_cpu(es->s_inodes_count)) {
1464
		ext4_warning(sb, "inodes_count overflow");
1465 1466 1467 1468
		return -EINVAL;
	}

	if (reserved_gdb || gdb_off == 0) {
1469
		if (!EXT4_HAS_COMPAT_FEATURE(sb,
1470 1471
					     EXT4_FEATURE_COMPAT_RESIZE_INODE)
		    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
1472
			ext4_warning(sb,
1473 1474 1475
				     "No reserved GDT blocks, can't resize");
			return -EPERM;
		}
1476 1477
		inode = ext4_iget(sb, EXT4_RESIZE_INO);
		if (IS_ERR(inode)) {
1478
			ext4_warning(sb, "Error opening resize inode");
1479
			return PTR_ERR(inode);
1480 1481 1482
		}
	}

1483

1484
	err = verify_group_input(sb, input);
1485
	if (err)
1486
		goto out;
1487

1488 1489 1490 1491 1492
	flex_gd.count = 1;
	flex_gd.groups = input;
	flex_gd.bg_flags = &bg_flags;
	err = ext4_flex_group_add(sb, inode, &flex_gd);
out:
1493 1494
	iput(inode);
	return err;
1495
} /* ext4_group_add */
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 1522 1523
/*
 * 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);
1524
	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548
	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) {
		if (test_opt(sb, DEBUG))
			printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
			       "blocks\n", ext4_blocks_count(es));
		update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
			       sizeof(struct ext4_super_block));
	}
	return err;
}

1549 1550
/*
 * Extend the filesystem to the new number of blocks specified.  This entry
1551 1552 1553 1554
 * 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).
 *
1555
 * If we _really_ wanted, we could use default values to call ext4_group_add()
1556 1557 1558
 * allow the "remount" trick to work for arbitrary resizing, assuming enough
 * GDT blocks are reserved to grow to the desired size.
 */
1559 1560
int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
		      ext4_fsblk_t n_blocks_count)
1561
{
1562 1563 1564
	ext4_fsblk_t o_blocks_count;
	ext4_grpblk_t last;
	ext4_grpblk_t add;
1565
	struct buffer_head *bh;
1566
	int err;
1567
	ext4_group_t group;
1568

L
Laurent Vivier 已提交
1569
	o_blocks_count = ext4_blocks_count(es);
1570 1571

	if (test_opt(sb, DEBUG))
1572 1573 1574
		ext4_msg(sb, KERN_DEBUG,
			 "extending last group from %llu to %llu blocks",
			 o_blocks_count, n_blocks_count);
1575 1576 1577 1578 1579

	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)) {
1580 1581 1582
		ext4_msg(sb, KERN_ERR,
			 "filesystem too large to resize to %llu blocks safely",
			 n_blocks_count);
1583
		if (sizeof(sector_t) < 8)
1584
			ext4_warning(sb, "CONFIG_LBDAF not enabled");
1585 1586 1587 1588
		return -EINVAL;
	}

	if (n_blocks_count < o_blocks_count) {
1589
		ext4_warning(sb, "can't shrink FS - resize aborted");
1590
		return -EINVAL;
1591 1592 1593
	}

	/* Handle the remaining blocks in the last group only. */
1594
	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
1595 1596

	if (last == 0) {
1597
		ext4_warning(sb, "need to use ext2online to resize further");
1598 1599 1600
		return -EPERM;
	}

1601
	add = EXT4_BLOCKS_PER_GROUP(sb) - last;
1602 1603

	if (o_blocks_count + add < o_blocks_count) {
1604
		ext4_warning(sb, "blocks_count overflow");
1605 1606 1607 1608 1609 1610 1611
		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)
1612
		ext4_warning(sb, "will only finish group (%llu blocks, %u new)",
1613 1614 1615
			     o_blocks_count + add, add);

	/* See if the device is actually as big as what was requested */
1616
	bh = sb_bread(sb, o_blocks_count + add - 1);
1617
	if (!bh) {
1618
		ext4_warning(sb, "can't read last block, resize aborted");
1619 1620 1621 1622
		return -ENOSPC;
	}
	brelse(bh);

1623
	err = ext4_group_extend_no_check(sb, o_blocks_count, add);
1624
	return err;
1625
} /* ext4_group_extend */
1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642

/*
 * 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;
	struct inode *resize_inode;
	ext4_fsblk_t o_blocks_count;
	ext4_group_t o_group;
	ext4_group_t n_group;
1643
	ext4_grpblk_t offset, add;
1644 1645 1646 1647 1648 1649 1650 1651
	unsigned long n_desc_blocks;
	unsigned long o_desc_blocks;
	unsigned long desc_blocks;
	int err = 0, flexbg_size = 1;

	o_blocks_count = ext4_blocks_count(es);

	if (test_opt(sb, DEBUG))
1652 1653
		ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu "
		       "to %llu blocks", o_blocks_count, n_blocks_count);
1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665

	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);
1666
	ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694

	n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
			EXT4_DESC_PER_BLOCK(sb);
	o_desc_blocks = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
			EXT4_DESC_PER_BLOCK(sb);
	desc_blocks = n_desc_blocks - o_desc_blocks;

	if (desc_blocks &&
	    (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE) ||
	     le16_to_cpu(es->s_reserved_gdt_blocks) < desc_blocks)) {
		ext4_warning(sb, "No reserved GDT blocks, can't resize");
		return -EPERM;
	}

	resize_inode = ext4_iget(sb, EXT4_RESIZE_INO);
	if (IS_ERR(resize_inode)) {
		ext4_warning(sb, "Error opening resize inode");
		return PTR_ERR(resize_inode);
	}

	/* 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);

1695 1696 1697 1698 1699 1700
	/* 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) {
1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736
		err = ext4_group_extend_no_check(sb, o_blocks_count, add);
		if (err)
			goto out;
	}

	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
	    es->s_log_groups_per_flex)
		flexbg_size = 1 << es->s_log_groups_per_flex;

	o_blocks_count = ext4_blocks_count(es);
	if (o_blocks_count == n_blocks_count)
		goto out;

	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)) {
		ext4_alloc_group_tables(sb, flex_gd, flexbg_size);
		err = ext4_flex_group_add(sb, resize_inode, flex_gd);
		if (unlikely(err))
			break;
	}

out:
	if (flex_gd)
		free_flex_gd(flex_gd);

	iput(resize_inode);
	if (test_opt(sb, DEBUG))
1737 1738
		ext4_msg(sb, KERN_DEBUG, "resized filesystem from %llu "
		       "upto %llu blocks", o_blocks_count, n_blocks_count);
1739 1740
	return err;
}