[PATCH] ext4: fix error processing in mb_free_blocks

[PATCH] ext4: fix error processing in mb_free_blocks

[Shen Feng]

The error processing of the return value of mb_free_blocks
is meanless because it only return 0. This fix includes
*make mb_free_blocks return void
*remove the error processing part in callers
*unlock group before calling ext4_error in mb_free_blocks

Signed-off-by: Shen Feng <shen@cn.fujitsu.com>
---
 fs/ext4/mballoc.c |   13 +++++--------
 1 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a30a35d..6180ebc 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1044,7 +1044,7 @@ static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len)
 	}
 }
 
-static int mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
+static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 			  int first, int count)
 {
 	int block = 0;
@@ -1084,11 +1084,12 @@ static int mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 			blocknr += block;
 			blocknr +=
 			    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
-
+			ext4_unlock_group(sb, e4b->bd_group);
 			ext4_error(sb, __func__, "double-free of inode"
 				   " %lu's block %llu(bit %u in group %lu)\n",
 				   inode ? inode->i_ino : 0, blocknr, block,
 				   e4b->bd_group);
+			ext4_lock_group(sb, e4b->bd_group);
 		}
 		mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
 		e4b->bd_info->bb_counters[order]++;
@@ -1126,8 +1127,6 @@ static int mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		} while (1);
 	}
 	mb_check_buddy(e4b);
-
-	return 0;
 }
 
 static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
@@ -2561,8 +2560,7 @@ ext4_mb_free_committed_blocks(struct super_block *sb)
 		ext4_lock_group(sb, md->group);
 		for (i = 0; i < md->num; i++) {
 			mb_debug(" %u", md->blocks[i]);
-			err = mb_free_blocks(NULL, &e4b, md->blocks[i], 1);
-			BUG_ON(err != 0);
+			mb_free_blocks(NULL, &e4b, md->blocks[i], 1);
 		}
 		mb_debug("\n");
 		ext4_unlock_group(sb, md->group);
@@ -4326,10 +4324,9 @@ do_more:
 		ext4_mb_free_metadata(handle, &e4b, block_group, bit, count);
 	} else {
 		ext4_lock_group(sb, block_group);
-		err = mb_free_blocks(inode, &e4b, bit, count);
+		mb_free_blocks(inode, &e4b, bit, count);
 		ext4_mb_return_to_preallocation(inode, &e4b, block, count);
 		ext4_unlock_group(sb, block_group);
-		BUG_ON(err != 0);
 	}
 
 	spin_lock(sb_bgl_lock(sbi, block_group));
-- 
1.5.4.5

Re: [PATCH] ext4: fix error processing in mb_free_blocks

[Andrew Morton]

On Thu, 29 May 2008 11:21:18 +0800 Shen Feng <shen@cn.fujitsu.com> wrote:

> The error processing of the return value of mb_free_blocks
> is meanless because it only return 0. This fix includes
> *make mb_free_blocks return void
> *remove the error processing part in callers

This:

> *unlock group before calling ext4_error in mb_free_blocks

fixes a potential deadlock.

> @@ -1084,11 +1084,12 @@ static int mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
>  			blocknr += block;
>  			blocknr +=
>  			    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
> -
> +			ext4_unlock_group(sb, e4b->bd_group);
>  			ext4_error(sb, __func__, "double-free of inode"
>  				   " %lu's block %llu(bit %u in group %lu)\n",
>  				   inode ? inode->i_ino : 0, blocknr, block,
>  				   e4b->bd_group);
> +			ext4_lock_group(sb, e4b->bd_group);
>  		}
>  		mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
>  		e4b->bd_info->bb_counters[order]++;

but are we sure we can just drop the lock and then cheerfully proceed? 
Whatever data that lock is protecting might have changed..

A safer-looking fix would be to return an error from mb_free_blocks()
and handle the in the caller, once the ext4_unlock_group() has been
performed.

Re: [PATCH] ext4: fix error processing in mb_free_blocks

[Shen Feng]

Andrew Morton Wrote:
> On Thu, 29 May 2008 11:21:18 +0800 Shen Feng <shen@cn.fujitsu.com> wrote:
> 
>> The error processing of the return value of mb_free_blocks
>> is meanless because it only return 0. This fix includes
>> *make mb_free_blocks return void
>> *remove the error processing part in callers
> 
> This:
> 
>> *unlock group before calling ext4_error in mb_free_blocks
> 
> fixes a potential deadlock.
> 
>> @@ -1084,11 +1084,12 @@ static int mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
>>  			blocknr += block;
>>  			blocknr +=
>>  			    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
>> -
>> +			ext4_unlock_group(sb, e4b->bd_group);
>>  			ext4_error(sb, __func__, "double-free of inode"
>>  				   " %lu's block %llu(bit %u in group %lu)\n",
>>  				   inode ? inode->i_ino : 0, blocknr, block,
>>  				   e4b->bd_group);
>> +			ext4_lock_group(sb, e4b->bd_group);
>>  		}
>>  		mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
>>  		e4b->bd_info->bb_counters[order]++;
> 
> but are we sure we can just drop the lock and then cheerfully proceed? 
> Whatever data that lock is protecting might have changed..

That's a real question to me when I fixed this.
I got the similar code in balloc.c from line 740 in ext4_free_blocks_sb.

		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
						bit + i, bitmap_bh->b_data)) {
			jbd_unlock_bh_state(bitmap_bh);
			ext4_error(sb, __func__,
				   "bit already cleared for block %llu",
				   (ext4_fsblk_t)(block + i));
			jbd_lock_bh_state(bitmap_bh);
			BUFFER_TRACE(bitmap_bh, "bit already cleared");
		} else {
			group_freed++;
		}
 
So I did the same fix.
Maybe this also needs to be fixed.

> 
> A safer-looking fix would be to return an error from mb_free_blocks()
> and handle the in the caller, once the ext4_unlock_group() has been
> performed.
> 
> 
>