2016-03-30 20:53:49

by Luis de Bethencourt

Subject: [PATCH 1/2] btrfs: fix mixed block count of available space

Metadata for mixed block is already accounted in total data and should not
be counted as part of the free metadata space.

Signed-off-by: Luis de Bethencourt <[email protected]>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=114281
---
fs/btrfs/super.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 00b8f37..bdca79c 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2051,6 +2051,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
u64 thresh = 0;
+ int mixed = 0;

/*
* holding chunk_muext to avoid allocating new chunks, holding
@@ -2076,8 +2077,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
}
}
}
- if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
- total_free_meta += found->disk_total - found->disk_used;
+
+ /*
+ * Metadata in mixed block goup profiles are accounted in data
+ */
+ if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
+ if (found->flags & BTRFS_BLOCK_GROUP_DATA)
+ mixed = 1;
+ else
+ total_free_meta += found->disk_total -
+ found->disk_used;
+ }

total_used += found->disk_used;
}
@@ -2115,7 +2125,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
*/
thresh = 4 * 1024 * 1024;

- if (total_free_meta - thresh < block_rsv->size)
+ if (!mixed && total_free_meta - thresh < block_rsv->size)
buf->f_bavail = 0;

buf->f_type = BTRFS_SUPER_MAGIC;
--
2.5.3

2016-03-30 20:53:53

by Luis de Bethencourt

Subject: [PATCH 2/2] btrfs: avoid overflowing f_bfree

Since mixed block groups accounting isn't byte-accurate and f_bree is an
unsigned integer, it could overflow. Avoid this.

Signed-off-by: Luis de Bethencourt <[email protected]>
Suggested-by: David Sterba <[email protected]>
---
fs/btrfs/super.c | 5 +++++
1 file changed, 5 insertions(+)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index bdca79c..93376d0 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2101,6 +2101,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
/* Account global block reserve as used, it's in logical size already */
spin_lock(&block_rsv->lock);
buf->f_bfree -= block_rsv->size >> bits;
+ /* Mixed block groups accounting is not byte-accurate, avoid overflow */
+ if (buf->f_bfree >= block_rsv->size >> bits)
+ buf->f_bfree -= block_rsv->size >> bits;
+ else
+ buf->f_bfree = 0;
spin_unlock(&block_rsv->lock);

buf->f_bavail = div_u64(total_free_data, factor);
--
2.5.3

2016-03-30 21:48:29

by Filipe Manana

Subject: Re: [PATCH 2/2] btrfs: avoid overflowing f_bfree

On Wed, Mar 30, 2016 at 9:53 PM, Luis de Bethencourt
<[email protected]> wrote:
> Since mixed block groups accounting isn't byte-accurate and f_bree is an
> unsigned integer, it could overflow. Avoid this.
>
> Signed-off-by: Luis de Bethencourt <[email protected]>
> Suggested-by: David Sterba <[email protected]>
> ---
> fs/btrfs/super.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
> index bdca79c..93376d0 100644
> --- a/fs/btrfs/super.c
> +++ b/fs/btrfs/super.c
> @@ -2101,6 +2101,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
> /* Account global block reserve as used, it's in logical size already */
> spin_lock(&block_rsv->lock);
> buf->f_bfree -= block_rsv->size >> bits;

You forgot to remove the line above, didn't you?

> + /* Mixed block groups accounting is not byte-accurate, avoid overflow */
> + if (buf->f_bfree >= block_rsv->size >> bits)
> + buf->f_bfree -= block_rsv->size >> bits;
> + else
> + buf->f_bfree = 0;
> spin_unlock(&block_rsv->lock);
>
> buf->f_bavail = div_u64(total_free_data, factor);
> --
> 2.5.3
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html



--
Filipe David Manana,

"Reasonable men adapt themselves to the world.
Unreasonable men adapt the world to themselves.
That's why all progress depends on unreasonable men."

2016-03-30 22:10:29

by Luis de Bethencourt

Subject: Re: [PATCH 2/2] btrfs: avoid overflowing f_bfree

On 30/03/16 22:48, Filipe Manana wrote:
> On Wed, Mar 30, 2016 at 9:53 PM, Luis de Bethencourt
> <[email protected]> wrote:
>> Since mixed block groups accounting isn't byte-accurate and f_bree is an
>> unsigned integer, it could overflow. Avoid this.
>>
>> Signed-off-by: Luis de Bethencourt <[email protected]>
>> Suggested-by: David Sterba <[email protected]>
>> ---
>> fs/btrfs/super.c | 5 +++++
>> 1 file changed, 5 insertions(+)
>>
>> diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
>> index bdca79c..93376d0 100644
>> --- a/fs/btrfs/super.c
>> +++ b/fs/btrfs/super.c
>> @@ -2101,6 +2101,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
>> /* Account global block reserve as used, it's in logical size already */
>> spin_lock(&block_rsv->lock);
>> buf->f_bfree -= block_rsv->size >> bits;
>
> You forgot to remove the line above, didn't you?
>

Shoot! Indeed I did, sorry. Thanks for noticing.

Sending version 2.

Luis

>> + /* Mixed block groups accounting is not byte-accurate, avoid overflow */
>> + if (buf->f_bfree >= block_rsv->size >> bits)
>> + buf->f_bfree -= block_rsv->size >> bits;
>> + else
>> + buf->f_bfree = 0;
>> spin_unlock(&block_rsv->lock);
>>
>> buf->f_bavail = div_u64(total_free_data, factor);
>> --
>> 2.5.3
>>
>> --