Release 4.10 fs/ext4/resize.c

/*
 *  linux/fs/ext4/resize.c
 *
 * Support for resizing an ext4 filesystem while it is mounted.
 *
 * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
 *
 * This could probably be made into a module, because it is not often in use.
 */



#define EXT4FS_DEBUG

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

#include "ext4_jbd2.h"



int ext4_resize_begin(struct super_block *sb)
{
	int ret = 0;

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

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

	/*
         * 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");
		return -EPERM;
	}

	if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
		ret = -EBUSY;

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
75
59.06%
2
50.00%
theodore tso
theodore tso
51
40.16%
1
25.00%
jakub wilk
jakub wilk
1
0.79%
1
25.00%
Total
127
100.00%
4
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
25
96.15%
1
50.00%
peter zijlstra
peter zijlstra
1
3.85%
1
50.00%
Total
26
100.00%
2
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
29
100.00%
1
100.00%
Total
29
100.00%
1
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
31
100.00%
1
100.00%
Total
31
100.00%
1
100.00%



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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
54
100.00%
1
100.00%
Total
54
100.00%
1
100.00%


#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,
			      struct ext4_new_group_data *input)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	ext4_fsblk_t start = ext4_blocks_count(es);
	ext4_fsblk_t end = start + input->blocks_count;
	ext4_group_t group = input->group;
	ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
	unsigned overhead;
	ext4_fsblk_t metaend;
	struct buffer_head *bh = NULL;
	ext4_grpblk_t free_blocks_count, offset;
	int err = -EINVAL;

	if (group != sbi->s_groups_count) {
		ext4_warning(sb, "Cannot add at group %u (only %u groups)",
			     input->group, sbi->s_groups_count);
		return -EINVAL;
	}

	overhead = ext4_group_overhead_blocks(sb, group);
	metaend = start + overhead;
	input->free_blocks_count = free_blocks_count =
		input->blocks_count - 2 - overhead - sbi->s_itb_per_group;

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

	ext4_get_group_no_and_offset(sb, start, NULL, &offset);
	if (offset != 0)
			ext4_warning(sb, "Last group not full");
	else if (input->reserved_blocks > input->blocks_count / 5)
		ext4_warning(sb, "Reserved blocks too high (%u)",
			     input->reserved_blocks);
	else if (free_blocks_count < 0)
		ext4_warning(sb, "Bad blocks count %u",
			     input->blocks_count);
	else if (!(bh = sb_bread(sb, end - 1)))
		ext4_warning(sb, "Cannot read last block (%llu)",
			     end - 1);
	else if (outside(input->block_bitmap, start, end))
		ext4_warning(sb, "Block bitmap not in group (block %llu)",
			     (unsigned long long)input->block_bitmap);
	else if (outside(input->inode_bitmap, start, end))
		ext4_warning(sb, "Inode bitmap not in group (block %llu)",
			     (unsigned long long)input->inode_bitmap);
	else if (outside(input->inode_table, start, end) ||
		 outside(itend - 1, start, end))
		ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
			     (unsigned long long)input->inode_table, itend - 1);
	else if (input->inode_bitmap == input->block_bitmap)
		ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
			     (unsigned long long)input->block_bitmap);
	else if (inside(input->block_bitmap, input->inode_table, itend))
		ext4_warning(sb, "Block bitmap (%llu) in inode table "
			     "(%llu-%llu)",
			     (unsigned long long)input->block_bitmap,
			     (unsigned long long)input->inode_table, itend - 1);
	else if (inside(input->inode_bitmap, input->inode_table, itend))
		ext4_warning(sb, "Inode bitmap (%llu) in inode table "
			     "(%llu-%llu)",
			     (unsigned long long)input->inode_bitmap,
			     (unsigned long long)input->inode_table, itend - 1);
	else if (inside(input->block_bitmap, start, metaend))
		ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
			     (unsigned long long)input->block_bitmap,
			     start, metaend - 1);
	else if (inside(input->inode_bitmap, start, metaend))
		ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
			     (unsigned long long)input->inode_bitmap,
			     start, metaend - 1);
	else if (inside(input->inode_table, start, metaend) ||
		 inside(itend - 1, start, metaend))
		ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
			     "(%llu-%llu)",
			     (unsigned long long)input->inode_table,
			     itend - 1, start, metaend - 1);
	else
		err = 0;
	brelse(bh);

	return err;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
dave kleikamp
dave kleikamp
500
76.34%
1
11.11%
randy dunlap
randy dunlap
55
8.40%
1
11.11%
theodore tso
theodore tso
44
6.72%
1
11.11%
mingming cao
mingming cao
42
6.41%
3
33.33%
eric sandeen
eric sandeen
8
1.22%
1
11.11%
laurent vivier
laurent vivier
5
0.76%
1
11.11%
avantika mathur
avantika mathur
1
0.15%
1
11.11%
Total
655
100.00%
9
100.00%

/*
 * 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;

	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
		goto out2;
	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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
124
89.21%
1
33.33%
haogang chen
haogang chen
14
10.07%
1
33.33%
insu yun
insu yun
1
0.72%
1
33.33%
Total
139
100.00%
3
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
30
100.00%
1
100.00%
Total
30
100.00%
1
100.00%

/*
 * 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
 *
 * Returns 0 on a successful allocation of the metadata blocks in the
 * block group.
 */


static int 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;
	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;
	__u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;

	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;
	if (src_group >= group_data[0].group + flex_gd->count)
		return -ENOSPC;
	start_blk = ext4_group_first_block_no(sb, src_group);
	last_blk = start_blk + group_data[src_group - group].blocks_count;

	overhead = ext4_group_overhead_blocks(sb, src_group);

	start_blk += overhead;

	/* We collect contiguous blocks as much as possible. */
	src_group++;
	for (; src_group <= last_group; src_group++) {
		overhead = ext4_group_overhead_blocks(sb, src_group);
		if (overhead == 0)
			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++;
		group = ext4_get_group_number(sb, start_blk - 1);
		group -= group_data[0].group;
		group_data[group].free_blocks_count--;
		flex_gd->bg_flags[group] &= uninit_mask;
	}

	/* 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++;
		group = ext4_get_group_number(sb, start_blk - 1);
		group -= group_data[0].group;
		group_data[group].free_blocks_count--;
		flex_gd->bg_flags[group] &= uninit_mask;
	}

	/* Allocate inode tables */
	for (; it_index < flex_gd->count; it_index++) {
		unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
		ext4_fsblk_t next_group_start;

		if (start_blk + itb > last_blk)
			goto next_group;
		group_data[it_index].inode_table = start_blk;
		group = ext4_get_group_number(sb, start_blk);
		next_group_start = ext4_group_first_block_no(sb, group + 1);
		group -= group_data[0].group;

		if (start_blk + itb > next_group_start) {
			flex_gd->bg_flags[group + 1] &= uninit_mask;
			overhead = start_blk + itb - next_group_start;
			group_data[group + 1].free_blocks_count -= overhead;
			itb -= overhead;
		}

		group_data[group].free_blocks_count -= itb;
		flex_gd->bg_flags[group] &= uninit_mask;
		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);
		}
	}
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
538
84.72%
3
60.00%
theodore tso
theodore tso
87
13.70%
1
20.00%
lukas czerner
lukas czerner
10
1.57%
1
20.00%
Total
635
100.00%
5
100.00%



static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
				  ext4_fsblk_t blk)
{
	struct buffer_head *bh;
	int err;

	bh = sb_getblk(sb, blk);
	if (unlikely(!bh))
		return ERR_PTR(-ENOMEM);
	BUFFER_TRACE(bh, "get_write_access");
	if ((err = ext4_journal_get_write_access(handle, bh))) {
		brelse(bh);
		bh = ERR_PTR(err);
	} else {
		memset(bh->b_data, 0, sb->s_blocksize);
		set_buffer_uptodate(bh);
	}

	return bh;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
dave kleikamp
dave kleikamp
97
88.18%
1
20.00%
liang xie
liang xie
7
6.36%
1
20.00%
wang shilong
wang shilong
3
2.73%
1
20.00%
mingming cao
mingming cao
2
1.82%
1
20.00%
theodore tso
theodore tso
1
0.91%
1
20.00%
Total
110
100.00%
5
100.00%

/*
 * 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.
 */


static int extend_or_restart_transaction(handle_t *handle, int thresh)
{
	int err;

	if (ext4_handle_has_enough_credits(handle, thresh))
		return 0;

	err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
	if (err < 0)
		return err;
	if (err) {
		err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
		if (err)
			return err;
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
eric sandeen
eric sandeen
66
92.96%
1
33.33%
frank mayhar
frank mayhar
4
5.63%
1
33.33%
yongqiang yang
yongqiang yang
1
1.41%
1
33.33%
Total
71
100.00%
3
100.00%

/*
 * 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;

		group = ext4_get_group_number(sb, block);
		start = ext4_group_first_block_no(sb, group);
		group -= flex_gd->groups[0].group;

		count2 = EXT4_BLOCKS_PER_GROUP(sb) - (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 (unlikely(!bh))
			return -ENOMEM;

		BUFFER_TRACE(bh, "get_write_access");
		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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
yongqiang yang
yongqiang yang
252
93.68%
1
16.67%
liang xie
liang xie
7
2.60%
1
16.67%
theodore tso
theodore tso
4
1.49%
2
33.33%
wang shilong
wang shilong
3
1.12%
1
16.67%
lukas czerner
lukas czerner
3
1.12%
1
16.67%
Total
269
100.00%
6
100.00%

/*
 * 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;
	int meta_bg;

	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);
	meta_bg = ext4_has_feature_meta_bg(sb);

	/* This transaction may be extended/restarted along the way */
	handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, 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;
		ext4_grpblk_t overhead;

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

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

		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);
		/* Copy all of the GDT blocks into the backup in this group */
		for (j = 0; 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 (unlikely(!gdb)) {
				err = -ENOMEM;
				goto out;
			}

			BUFFER_TRACE(gdb, "get_write_access");
			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;
		}

handle_itb:
		/* 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(