Ocfs2 devel - Feb 2023 - [PATCH v2] ocfs2: fix non-auto defrag path not working issue

This fixes three issues on move extents ioctl without auto defrag:

a) In ocfs2_find_victim_alloc_group(), we have to convert bits to block
first in case of global bitmap.
b) In ocfs2_probe_alloc_group(), when finding enough bits in block group
bitmap, we have to back off move_len to start pos as well, otherwise it
may corrupt filesystem.
c) In ocfs2_ioctl_move_extents(), set me_threshold both for non-auto and
auto defrag paths. Otherwise it will set move_max_hop to 0 and finally
cause unexpectedly ENOSPC error.

Currently there is no tools triggering the above issues since
defragfs.ocfs2 enables auto defrag by default. Test with manually
changing defragfs.ocfs2 to run non auto defrag path.

Signed-off-by: Heming Zhao <heming.zhao at suse.com>
---
v2: revise commit log under review comment

---
 fs/ocfs2/move_extents.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 6251748c695b..b1e32ec4a9d4 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -434,7 +434,7 @@ static int ocfs2_find_victim_alloc_group(struct inode
*inode,
 			bg = (struct ocfs2_group_desc *)gd_bh->b_data;
 
 			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
-						le16_to_cpu(bg->bg_bits))) {
+						(le16_to_cpu(bg->bg_bits) << bits_per_unit))) {
 
 				*ret_bh = gd_bh;
 				*vict_bit = (vict_blkno - blkno) >>
@@ -549,6 +549,7 @@ static void ocfs2_probe_alloc_group(struct inode *inode,
struct buffer_head *bh,
 			last_free_bits++;
 
 		if (last_free_bits == move_len) {
+			i -= move_len;
 			*goal_bit = i;
 			*phys_cpos = base_cpos + i;
 			break;
@@ -1020,18 +1021,19 @@ int ocfs2_ioctl_move_extents(struct file *filp, void
__user *argp)
 
 	context->range = &range;
 
+	/*
+	 * ok, the default theshold for the defragmentation
+	 * is 1M, since our maximum clustersize was 1M also.
+	 * any thought?
+	 */
+	if (!range.me_threshold)
+		range.me_threshold = 1024 * 1024;
+
+	if (range.me_threshold > i_size_read(inode))
+		range.me_threshold = i_size_read(inode);
+
 	if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) {
 		context->auto_defrag = 1;
-		/*
-		 * ok, the default theshold for the defragmentation
-		 * is 1M, since our maximum clustersize was 1M also.
-		 * any thought?
-		 */
-		if (!range.me_threshold)
-			range.me_threshold = 1024 * 1024;
-
-		if (range.me_threshold > i_size_read(inode))
-			range.me_threshold = i_size_read(inode);
 
 		if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG)
 			context->partial = 1;
-- 
2.39.0

On 2/20/23 1:05 PM, Heming Zhao wrote:
> This fixes three issues on move extents ioctl without auto defrag:
> 
> a) In ocfs2_find_victim_alloc_group(), we have to convert bits to block
> first in case of global bitmap.
> b) In ocfs2_probe_alloc_group(), when finding enough bits in block group
> bitmap, we have to back off move_len to start pos as well, otherwise it
> may corrupt filesystem.
> c) In ocfs2_ioctl_move_extents(), set me_threshold both for non-auto and
> auto defrag paths. Otherwise it will set move_max_hop to 0 and finally
> cause unexpectedly ENOSPC error.
> 
> Currently there is no tools triggering the above issues since
> defragfs.ocfs2 enables auto defrag by default. Test with manually
> changing defragfs.ocfs2 to run non auto defrag path.
> 
> Signed-off-by: Heming Zhao <heming.zhao at suse.com>
Reviewed-by: Joseph Qi <joseph.qi at
linux.alibaba.com>
> ---
> v2: revise commit log under review comment
> 
> ---
>  fs/ocfs2/move_extents.c | 24 +++++++++++++-----------
>  1 file changed, 13 insertions(+), 11 deletions(-)
> 
> diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
> index 6251748c695b..b1e32ec4a9d4 100644
> --- a/fs/ocfs2/move_extents.c
> +++ b/fs/ocfs2/move_extents.c
> @@ -434,7 +434,7 @@ static int ocfs2_find_victim_alloc_group(struct inode
*inode,
>  			bg = (struct ocfs2_group_desc *)gd_bh->b_data;
>  
>  			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
> -						le16_to_cpu(bg->bg_bits))) {
> +						(le16_to_cpu(bg->bg_bits) << bits_per_unit))) {
>  
>  				*ret_bh = gd_bh;
>  				*vict_bit = (vict_blkno - blkno) >>
> @@ -549,6 +549,7 @@ static void ocfs2_probe_alloc_group(struct inode
*inode, struct buffer_head *bh,
>  			last_free_bits++;
>  
>  		if (last_free_bits == move_len) {
> +			i -= move_len;
>  			*goal_bit = i;
>  			*phys_cpos = base_cpos + i;
>  			break;
> @@ -1020,18 +1021,19 @@ int ocfs2_ioctl_move_extents(struct file *filp,
void __user *argp)
>  
>  	context->range = &range;
>  
> +	/*
> +	 * ok, the default theshold for the defragmentation
> +	 * is 1M, since our maximum clustersize was 1M also.
> +	 * any thought?
> +	 */
> +	if (!range.me_threshold)
> +		range.me_threshold = 1024 * 1024;
> +
> +	if (range.me_threshold > i_size_read(inode))
> +		range.me_threshold = i_size_read(inode);
> +
>  	if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) {
>  		context->auto_defrag = 1;
> -		/*
> -		 * ok, the default theshold for the defragmentation
> -		 * is 1M, since our maximum clustersize was 1M also.
> -		 * any thought?
> -		 */
> -		if (!range.me_threshold)
> -			range.me_threshold = 1024 * 1024;
> -
> -		if (range.me_threshold > i_size_read(inode))
> -			range.me_threshold = i_size_read(inode);
>  
>  		if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG)
>  			context->partial = 1;