[PATCH] ext4: fix possible overflow in ext4_trim_fs()

[PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

When determining last group through ext4_get_group_no_and_offset() the
result may be wrong in cases when range->start and range-len are too
big, because it may overflow when summing up those two numbers.

Fix that by checking range->len and limit its value to
ext4_blocks_count(). This commit was tested by myself with expected
result.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/mballoc.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5b4d4e3..7b05d92 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4819,6 +4819,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
 	ext4_grpblk_t cnt = 0, first_block, last_block;
 	uint64_t start, len, minlen, trimmed;
+	ext4_fsblk_t blocks_count = ext4_blocks_count(EXT4_SB(sb)->s_es);
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
@@ -4826,6 +4827,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	minlen = range->minlen >> sb->s_blocksize_bits;
 	trimmed = 0;
 
+	if (len > blocks_count)
+		len = blocks_count - start;
+
 	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
 		return -EINVAL;
 
-- 
1.7.2.3

[PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

When determining last group through ext4_get_group_no_and_offset() the
result may be wrong in cases when range->start and range-len are too
big, because it may overflow when summing up those two numbers.

Fix that by checking range->len and limit its value to
ext4_blocks_count(). This commit was tested by myself with expected
result.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/mballoc.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5b4d4e3..7b05d92 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4819,6 +4819,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
 	ext4_grpblk_t cnt = 0, first_block, last_block;
 	uint64_t start, len, minlen, trimmed;
+	ext4_fsblk_t blocks_count = ext4_blocks_count(EXT4_SB(sb)->s_es);
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
@@ -4826,6 +4827,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	minlen = range->minlen >> sb->s_blocksize_bits;
 	trimmed = 0;
 
+	if (len > blocks_count)
+		len = blocks_count - start;
+
 	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
 		return -EINVAL;
 
-- 
1.7.2.3

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Thu, 25 Nov 2010, Lukas Czerner wrote:

> When determining last group through ext4_get_group_no_and_offset() the
> result may be wrong in cases when range->start and range-len are too
> big, because it may overflow when summing up those two numbers.
> 
> Fix that by checking range->len and limit its value to
> ext4_blocks_count(). This commit was tested by myself with expected
> result.
> 
> Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> ---
>  fs/ext4/mballoc.c |    4 ++++
>  1 files changed, 4 insertions(+), 0 deletions(-)
> 
> diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> index 5b4d4e3..7b05d92 100644
> --- a/fs/ext4/mballoc.c
> +++ b/fs/ext4/mballoc.c
> @@ -4819,6 +4819,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
>  	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
>  	ext4_grpblk_t cnt = 0, first_block, last_block;
>  	uint64_t start, len, minlen, trimmed;
> +	ext4_fsblk_t blocks_count = ext4_blocks_count(EXT4_SB(sb)->s_es);
>  	int ret = 0;
>  
>  	start = range->start >> sb->s_blocksize_bits;
> @@ -4826,6 +4827,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
>  	minlen = range->minlen >> sb->s_blocksize_bits;
>  	trimmed = 0;
>  
> +	if (len > blocks_count)
> +		len = blocks_count - start;
> +
>  	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
>  		return -EINVAL;
>  
> 

Hi Ted,

what is the status of this patch ?

-Lukas

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Ted Ts'o]

On Thu, Nov 25, 2010 at 03:11:17PM +0100, Lukas Czerner wrote:
> When determining last group through ext4_get_group_no_and_offset() the
> result may be wrong in cases when range->start and range-len are too
> big, because it may overflow when summing up those two numbers.
> 
> Fix that by checking range->len and limit its value to
> ext4_blocks_count(). This commit was tested by myself with expected
> result.
> 
> Signed-off-by: Lukas Czerner <lczerner@redhat.com>

Added to the ext4 patch queue.  Thanks for the ping.

      	     	  		       	   - Ted

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Thu, 25 Nov 2010, Lukas Czerner wrote:

> When determining last group through ext4_get_group_no_and_offset() the
> result may be wrong in cases when range->start and range-len are too
> big, because it may overflow when summing up those two numbers.
> 
> Fix that by checking range->len and limit its value to
> ext4_blocks_count(). This commit was tested by myself with expected
> result.
> 
> Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> ---
>  fs/ext4/mballoc.c |    4 ++++
>  1 files changed, 4 insertions(+), 0 deletions(-)
> 
> diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> index 5b4d4e3..7b05d92 100644
> --- a/fs/ext4/mballoc.c
> +++ b/fs/ext4/mballoc.c
> @@ -4819,6 +4819,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
>  	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
>  	ext4_grpblk_t cnt = 0, first_block, last_block;
>  	uint64_t start, len, minlen, trimmed;
> +	ext4_fsblk_t blocks_count = ext4_blocks_count(EXT4_SB(sb)->s_es);
>  	int ret = 0;
>  
>  	start = range->start >> sb->s_blocksize_bits;
> @@ -4826,6 +4827,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
>  	minlen = range->minlen >> sb->s_blocksize_bits;
>  	trimmed = 0;
>  
> +	if (len > blocks_count)
> +		len = blocks_count - start;
> +
>  	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
>  		return -EINVAL;
>  
> 

Hi Ted,

what is the status of this one?

Thanks!
-Lukas

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Mon, 3 Jan 2011, Lukas Czerner wrote:

> On Thu, 25 Nov 2010, Lukas Czerner wrote:
> 
> > When determining last group through ext4_get_group_no_and_offset() the
> > result may be wrong in cases when range->start and range-len are too
> > big, because it may overflow when summing up those two numbers.
> > 
> > Fix that by checking range->len and limit its value to
> > ext4_blocks_count(). This commit was tested by myself with expected
> > result.
> > 
> > Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> > ---
> >  fs/ext4/mballoc.c |    4 ++++
> >  1 files changed, 4 insertions(+), 0 deletions(-)
> > 
> > diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> > index 5b4d4e3..7b05d92 100644
> > --- a/fs/ext4/mballoc.c
> > +++ b/fs/ext4/mballoc.c
> > @@ -4819,6 +4819,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
> >  	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
> >  	ext4_grpblk_t cnt = 0, first_block, last_block;
> >  	uint64_t start, len, minlen, trimmed;
> > +	ext4_fsblk_t blocks_count = ext4_blocks_count(EXT4_SB(sb)->s_es);
> >  	int ret = 0;
> >  
> >  	start = range->start >> sb->s_blocksize_bits;
> > @@ -4826,6 +4827,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
> >  	minlen = range->minlen >> sb->s_blocksize_bits;
> >  	trimmed = 0;
> >  
> > +	if (len > blocks_count)
> > +		len = blocks_count - start;
> > +
> >  	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
> >  		return -EINVAL;
> >  
> > 
> 
> Hi Ted,
> 
> what is the status of this one?
> 
> Thanks!
> -Lukas
> 

Oh, please ignore this, I just found "already applied" message. Sorry
for the noise.

-Lukas

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Mon, 20 Dec 2010, Ted Ts'o wrote:

> On Thu, Nov 25, 2010 at 03:11:17PM +0100, Lukas Czerner wrote:
> > When determining last group through ext4_get_group_no_and_offset() the
> > result may be wrong in cases when range->start and range-len are too
> > big, because it may overflow when summing up those two numbers.
> > 
> > Fix that by checking range->len and limit its value to
> > ext4_blocks_count(). This commit was tested by myself with expected
> > result.
> > 
> > Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> 
> Added to the ext4 patch queue.  Thanks for the ping.
> 
>       	     	  		       	   - Ted
> 

Hi Ted,

Actually the patch is not enough, there is still a possibility for
overflow to happen. Jan Kara notice the same bug in ext3 batched discard
implementation. I am sorry for this, I'll sen updated patch ASAP.

-Lukas

[PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

When determining last group through ext4_get_group_no_and_offset() the
result may be wrong in cases when range->start and range-len are too
big, because it may overflow when summing up those two numbers.

Fix that by checking range->len and limit its value to
ext4_blocks_count(). This commit was tested by myself with expected
result.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/mballoc.c |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5b4d4e3..5f3e8a3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4819,6 +4819,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
 	ext4_grpblk_t cnt = 0, first_block, last_block;
 	uint64_t start, len, minlen, trimmed;
+	ext4_fsblk_t blocks_count = ext4_blocks_count(EXT4_SB(sb)->s_es);
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
@@ -4826,6 +4827,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	minlen = range->minlen >> sb->s_blocksize_bits;
 	trimmed = 0;
 
+	if (start >= blocks_count)
+		return -EINVAL;
+	if (start + len > blocks_count)
+		len = blocks_count - start;
+
 	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
 		return -EINVAL;
 
-- 
1.7.2.3

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Ted Ts'o]

On Mon, Jan 10, 2011 at 12:25:05PM +0100, Lukas Czerner wrote:
> 
> Actually the patch is not enough, there is still a possibility for
> overflow to happen. Jan Kara notice the same bug in ext3 batched discard
> implementation. I am sorry for this, I'll sen updated patch ASAP.
> 

This isn't a new patch, and not a replacement for the previous one,
correct?

						- Ted

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Mon, 10 Jan 2011, Ted Ts'o wrote:

> On Mon, Jan 10, 2011 at 12:25:05PM +0100, Lukas Czerner wrote:
> > 
> > Actually the patch is not enough, there is still a possibility for
> > overflow to happen. Jan Kara notice the same bug in ext3 batched discard
> > implementation. I am sorry for this, I'll sen updated patch ASAP.
> > 
> 
> This isn't a new patch, and not a replacement for the previous one,
> correct?
> 
> 						- Ted
> 

It is the replacement for the previous one.

-Lukas

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Ted Ts'o]

On Mon, Jan 10, 2011 at 05:52:49PM +0100, Lukas Czerner wrote:
> 
> It is the replacement for the previous one.
> 

Ah, I see, I got it confused with another trim_fs patch.  I wish you
had sent this to me earlier, but ok, I'll fix it up.

    	      	    	     	     	  - Ted

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Mon, 10 Jan 2011, Ted Ts'o wrote:

> On Mon, Jan 10, 2011 at 05:52:49PM +0100, Lukas Czerner wrote:
> > 
> > It is the replacement for the previous one.
> > 
> 
> Ah, I see, I got it confused with another trim_fs patch.  I wish you
> had sent this to me earlier, but ok, I'll fix it up.
> 
>     	      	    	     	     	  - Ted
> 

Yes, sorry about that and thanks.

-Lukas

[PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

In ext4_trim_fs it is possible that start+len might overflow. Fix it by
decrementing the len so that start+len equals to the file system size in
the worst case.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/mballoc.c |    6 +++++-
 1 files changed, 5 insertions(+), 1 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 17a5a57..d86dc14 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4952,14 +4952,18 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	uint64_t start, len, minlen, trimmed = 0;
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
 	len = range->len >> sb->s_blocksize_bits;
 	minlen = range->minlen >> sb->s_blocksize_bits;
 
-	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)) ||
+	    unlikely(start > max_blks))
 		return -EINVAL;
+	if (unlikely(len > max_blks))
+		len = max_blks - start;
 	if (start + len <= first_data_blk)
 		goto out;
 	if (start < first_data_blk) {
-- 
1.7.4.4

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Tao Ma]

Hi Lucas,
On 09/05/2011 10:34 PM, Lukas Czerner wrote:
> In ext4_trim_fs it is possible that start+len might overflow. Fix it by
> decrementing the len so that start+len equals to the file system size in
> the worst case.
Actually start + len can never overflow since they are changed by
start = range->start >> sb->s_blocksize_bits;
len = range->len >> sb->s_blocksize_bits;

range->start and range->len are u64, and after they are shifted with
blocksize_bits, start+len(ext4_fsblk_t is also 64bit) can't overflow.

Thanks
Tao
> 
> Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> ---
>  fs/ext4/mballoc.c |    6 +++++-
>  1 files changed, 5 insertions(+), 1 deletions(-)
> 
> diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> index 17a5a57..d86dc14 100644
> --- a/fs/ext4/mballoc.c
> +++ b/fs/ext4/mballoc.c
> @@ -4952,14 +4952,18 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
>  	uint64_t start, len, minlen, trimmed = 0;
>  	ext4_fsblk_t first_data_blk =
>  			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
> +	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
>  	int ret = 0;
>  
>  	start = range->start >> sb->s_blocksize_bits;
>  	len = range->len >> sb->s_blocksize_bits;
>  	minlen = range->minlen >> sb->s_blocksize_bits;
>  
> -	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
> +	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)) ||
> +	    unlikely(start > max_blks))
>  		return -EINVAL;
> +	if (unlikely(len > max_blks))
> +		len = max_blks - start;
>  	if (start + len <= first_data_blk)
>  		goto out;
>  	if (start < first_data_blk) {

Re: [PATCH] ext4: fix possible overflow in ext4_trim_fs()

[Lukas Czerner]

On Tue, 6 Sep 2011, Tao Ma wrote:

> Hi Lucas,
> On 09/05/2011 10:34 PM, Lukas Czerner wrote:
> > In ext4_trim_fs it is possible that start+len might overflow. Fix it by
> > decrementing the len so that start+len equals to the file system size in
> > the worst case.
> Actually start + len can never overflow since they are changed by
> start = range->start >> sb->s_blocksize_bits;
> len = range->len >> sb->s_blocksize_bits;
> 
> range->start and range->len are u64, and after they are shifted with
> blocksize_bits, start+len(ext4_fsblk_t is also 64bit) can't overflow.
> 
> Thanks
> Tao

Hi Tao,

I am really sorry for badly worded commit description. The problem is
real, however as you pointed out the overflow does not happen in
len+start addition but in ext4_get_group_no_and_offset() when we are
storing group number into the ext4_group_t which is 32 bit long, but
the result of do_div() might be bigger than that.

I will rephrase the commit description and resend the patch. I was doing
similar thing for xfs and I have just used almost the same description
which is wrong.

Thanks!
-Lukas

> > 
> > Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> > ---
> >  fs/ext4/mballoc.c |    6 +++++-
> >  1 files changed, 5 insertions(+), 1 deletions(-)
> > 
> > diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> > index 17a5a57..d86dc14 100644
> > --- a/fs/ext4/mballoc.c
> > +++ b/fs/ext4/mballoc.c
> > @@ -4952,14 +4952,18 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
> >  	uint64_t start, len, minlen, trimmed = 0;
> >  	ext4_fsblk_t first_data_blk =
> >  			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
> > +	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
> >  	int ret = 0;
> >  
> >  	start = range->start >> sb->s_blocksize_bits;
> >  	len = range->len >> sb->s_blocksize_bits;
> >  	minlen = range->minlen >> sb->s_blocksize_bits;
> >  
> > -	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
> > +	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)) ||
> > +	    unlikely(start > max_blks))
> >  		return -EINVAL;
> > +	if (unlikely(len > max_blks))
> > +		len = max_blks - start;
> >  	if (start + len <= first_data_blk)
> >  		goto out;
> >  	if (start < first_data_blk) {
> 
> 

--