Ocfs2 devel - Nov 2018 - [PATCH V3] ocfs2: fix dead lock caused by ocfs2_defrag_extent

ocfs2_defrag_extent may fall into deadlock.

ocfs2_ioctl_move_extents
    ocfs2_ioctl_move_extents
      ocfs2_move_extents
        ocfs2_defrag_extent
          ocfs2_lock_allocators_move_extents

            ocfs2_reserve_clusters
              inode_lock GLOBAL_BITMAP_SYSTEM_INODE

	  __ocfs2_flush_truncate_log
              inode_lock GLOBAL_BITMAP_SYSTEM_INODE

As backtrace shows above, ocfs2_reserve_clusters() will call inode_lock
against the global bitmap if local allocator has not sufficient cluters.
Once global bitmap could meet the demand, ocfs2_reserve_cluster will
return success with global bitmap locked.

After ocfs2_reserve_cluster(), if truncate log is full,
__ocfs2_flush_truncate_log() will definitely fall into deadlock because it
needs to inode_lock global bitmap, which has already been locked.

To fix this bug, we could remove from ocfs2_lock_allocators_move_extents()
the code which intends to lock global allocator, and put the removed code
after __ocfs2_flush_truncate_log().

ocfs2_lock_allocators_move_extents() is referred by 2 places, one is here,
the other does not need the data allocator context, which means this patch
does not affect the caller so far.

Change log:
1. Correct the function comment.
2. Remove unused argument from ocfs2_lock_meta_allocator_move_extents.

Signed-off-by: Larry Chen <lchen at suse.com>
---
 fs/ocfs2/move_extents.c | 47 ++++++++++++++++++++++++++---------------------
 1 file changed, 26 insertions(+), 21 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 7eb3b0a6347e..f55f82ca3425 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -156,18 +156,14 @@ static int __ocfs2_move_extent(handle_t *handle,
 }
 
 /*
- * lock allocators, and reserving appropriate number of bits for
- * meta blocks and data clusters.
- *
- * in some cases, we don't need to reserve clusters, just let data_ac
- * be NULL.
+ * lock allocator, and reserve appropriate number of bits for
+ * meta blocks.
  */
-static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode,
 					struct ocfs2_extent_tree *et,
 					u32 clusters_to_move,
 					u32 extents_to_split,
 					struct ocfs2_alloc_context **meta_ac,
-					struct ocfs2_alloc_context **data_ac,
 					int extra_blocks,
 					int *credits)
 {
@@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode
*inode,
 		goto out;
 	}
 
-	if (data_ac) {
-		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
-		if (ret) {
-			mlog_errno(ret);
-			goto out;
-		}
-	}
 
 	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);
 
@@ -257,10 +246,10 @@ static int ocfs2_defrag_extent(struct
ocfs2_move_extents_context *context,
 		}
 	}
 
-	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1,
-						 &context->meta_ac,
-						 &context->data_ac,
-						 extra_blocks, &credits);
+	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+						*len, 1,
+						&context->meta_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -283,6 +272,21 @@ static int ocfs2_defrag_extent(struct
ocfs2_move_extents_context *context,
 		}
 	}
 
+	/*
+	 * Make sure ocfs2_reserve_cluster is called after
+	 * __ocfs2_flush_truncate_log, otherwise, dead lock may happen.
+	 *
+	 * If ocfs2_reserve_cluster is called
+	 * before __ocfs2_flush_truncate_log, dead lock on global bitmap
+	 * may happen.
+	 *
+	 */
+	ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_unlock_mutex;
+	}
+
 	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
@@ -600,9 +604,10 @@ static int ocfs2_move_extent(struct
ocfs2_move_extents_context *context,
 		}
 	}
 
-	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
-						 &context->meta_ac,
-						 NULL, extra_blocks, &credits);
+	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+						len, 1,
+						&context->meta_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
-- 
2.16.4

Hi Larry,

On 18/11/1 15:14, Larry Chen wrote:
> ocfs2_defrag_extent may fall into deadlock.
> 
> ocfs2_ioctl_move_extents
>     ocfs2_ioctl_move_extents
>       ocfs2_move_extents
>         ocfs2_defrag_extent
>           ocfs2_lock_allocators_move_extents
> 
>             ocfs2_reserve_clusters
>               inode_lock GLOBAL_BITMAP_SYSTEM_INODE
> 
> 	  __ocfs2_flush_truncate_log
>               inode_lock GLOBAL_BITMAP_SYSTEM_INODE
> 
> As backtrace shows above, ocfs2_reserve_clusters() will call inode_lock
> against the global bitmap if local allocator has not sufficient cluters.
> Once global bitmap could meet the demand, ocfs2_reserve_cluster will
> return success with global bitmap locked.
> 
> After ocfs2_reserve_cluster(), if truncate log is full,
> __ocfs2_flush_truncate_log() will definitely fall into deadlock because it
> needs to inode_lock global bitmap, which has already been locked.
> 
> To fix this bug, we could remove from ocfs2_lock_allocators_move_extents()
> the code which intends to lock global allocator, and put the removed code
> after __ocfs2_flush_truncate_log().
> 
> ocfs2_lock_allocators_move_extents() is referred by 2 places, one is here,
> the other does not need the data allocator context, which means this patch
> does not affect the caller so far.
> 
> Change log:
> 1. Correct the function comment.
> 2. Remove unused argument from ocfs2_lock_meta_allocator_move_extents.
> 
> Signed-off-by: Larry Chen <lchen at suse.com>
> ---
>  fs/ocfs2/move_extents.c | 47
++++++++++++++++++++++++++---------------------
>  1 file changed, 26 insertions(+), 21 deletions(-)
> 
> diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
> index 7eb3b0a6347e..f55f82ca3425 100644
> --- a/fs/ocfs2/move_extents.c
> +++ b/fs/ocfs2/move_extents.c
> @@ -156,18 +156,14 @@ static int __ocfs2_move_extent(handle_t *handle,
>  }
>  
>  /*
> - * lock allocators, and reserving appropriate number of bits for
> - * meta blocks and data clusters.
> - *
> - * in some cases, we don't need to reserve clusters, just let data_ac
> - * be NULL.
> + * lock allocator, and reserve appropriate number of bits for
> + * meta blocks.
>   */
> -static int ocfs2_lock_allocators_move_extents(struct inode *inode,
> +static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode,
>  					struct ocfs2_extent_tree *et,
>  					u32 clusters_to_move,
IMO, here clusters_to_move is only for data_ac, since we change this
function to only handle meta_ac, I'm afraid clusters_to_move related
logic has to been changed correspondingly.

Thanks,
Joseph
>  					u32 extents_to_split,
>  					struct ocfs2_alloc_context **meta_ac,
> -					struct ocfs2_alloc_context **data_ac,
>  					int extra_blocks,
>  					int *credits)
>  {
> @@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct
inode *inode,
>  		goto out;
>  	}
>  
> -	if (data_ac) {
> -		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
> -		if (ret) {
> -			mlog_errno(ret);
> -			goto out;
> -		}
> -	}
>  
>  	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);
>  
> @@ -257,10 +246,10 @@ static int ocfs2_defrag_extent(struct
ocfs2_move_extents_context *context,
>  		}
>  	}
>  
> -	ret = ocfs2_lock_allocators_move_extents(inode, &context->et,
*len, 1,
> -						 &context->meta_ac,
> -						 &context->data_ac,
> -						 extra_blocks, &credits);
> +	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
> +						*len, 1,
> +						&context->meta_ac,
> +						extra_blocks, &credits);
>  	if (ret) {
>  		mlog_errno(ret);
>  		goto out;
> @@ -283,6 +272,21 @@ static int ocfs2_defrag_extent(struct
ocfs2_move_extents_context *context,
>  		}
>  	}
>  
> +	/*
> +	 * Make sure ocfs2_reserve_cluster is called after
> +	 * __ocfs2_flush_truncate_log, otherwise, dead lock may happen.
> +	 *
> +	 * If ocfs2_reserve_cluster is called
> +	 * before __ocfs2_flush_truncate_log, dead lock on global bitmap
> +	 * may happen.
> +	 *
> +	 */
> +	ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac);
> +	if (ret) {
> +		mlog_errno(ret);
> +		goto out_unlock_mutex;
> +	}
> +
>  	handle = ocfs2_start_trans(osb, credits);
>  	if (IS_ERR(handle)) {
>  		ret = PTR_ERR(handle);
> @@ -600,9 +604,10 @@ static int ocfs2_move_extent(struct
ocfs2_move_extents_context *context,
>  		}
>  	}
>  
> -	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len,
1,
> -						 &context->meta_ac,
> -						 NULL, extra_blocks, &credits);
> +	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
> +						len, 1,
> +						&context->meta_ac,
> +						extra_blocks, &credits);
>  	if (ret) {
>  		mlog_errno(ret);
>  		goto out;
>

Hi Larry,

The change looks good to me.

On 2018/11/1 15:14, Larry Chen wrote:
> ocfs2_defrag_extent may fall into deadlock.
> 
> ocfs2_ioctl_move_extents
>      ocfs2_ioctl_move_extents
>        ocfs2_move_extents
>          ocfs2_defrag_extent
>            ocfs2_lock_allocators_move_extents
> 
>              ocfs2_reserve_clusters
>                inode_lock GLOBAL_BITMAP_SYSTEM_INODE
> 
> 	  __ocfs2_flush_truncate_log
>                inode_lock GLOBAL_BITMAP_SYSTEM_INODE
> 
> As backtrace shows above, ocfs2_reserve_clusters() will call inode_lock
> against the global bitmap if local allocator has not sufficient cluters.
> Once global bitmap could meet the demand, ocfs2_reserve_cluster will
> return success with global bitmap locked.
> 
> After ocfs2_reserve_cluster(), if truncate log is full,
> __ocfs2_flush_truncate_log() will definitely fall into deadlock because it
> needs to inode_lock global bitmap, which has already been locked.
> 
> To fix this bug, we could remove from ocfs2_lock_allocators_move_extents()
> the code which intends to lock global allocator, and put the removed code
> after __ocfs2_flush_truncate_log().
> 
> ocfs2_lock_allocators_move_extents() is referred by 2 places, one is here,
> the other does not need the data allocator context, which means this patch
> does not affect the caller so far.
> 
> Change log:
> 1. Correct the function comment.
> 2. Remove unused argument from ocfs2_lock_meta_allocator_move_extents.
> 
> Signed-off-by: Larry Chen <lchen at suse.com>
Reviewed-by: Changwei Ge <ge.changwei at h3c.com>
> ---
>   fs/ocfs2/move_extents.c | 47
++++++++++++++++++++++++++---------------------
>   1 file changed, 26 insertions(+), 21 deletions(-)
> 
> diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
> index 7eb3b0a6347e..f55f82ca3425 100644
> --- a/fs/ocfs2/move_extents.c
> +++ b/fs/ocfs2/move_extents.c
> @@ -156,18 +156,14 @@ static int __ocfs2_move_extent(handle_t *handle,
>   }
>   
>   /*
> - * lock allocators, and reserving appropriate number of bits for
> - * meta blocks and data clusters.
> - *
> - * in some cases, we don't need to reserve clusters, just let data_ac
> - * be NULL.
> + * lock allocator, and reserve appropriate number of bits for
> + * meta blocks.
>    */
> -static int ocfs2_lock_allocators_move_extents(struct inode *inode,
> +static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode,
>   					struct ocfs2_extent_tree *et,
>   					u32 clusters_to_move,
>   					u32 extents_to_split,
>   					struct ocfs2_alloc_context **meta_ac,
> -					struct ocfs2_alloc_context **data_ac,
>   					int extra_blocks,
>   					int *credits)
>   {
> @@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct
inode *inode,
>   		goto out;
>   	}
>   
> -	if (data_ac) {
> -		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
> -		if (ret) {
> -			mlog_errno(ret);
> -			goto out;
> -		}
> -	}
>   
>   	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);
>   
> @@ -257,10 +246,10 @@ static int ocfs2_defrag_extent(struct
ocfs2_move_extents_context *context,
>   		}
>   	}
>   
> -	ret = ocfs2_lock_allocators_move_extents(inode, &context->et,
*len, 1,
> -						 &context->meta_ac,
> -						 &context->data_ac,
> -						 extra_blocks, &credits);
> +	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
> +						*len, 1,
> +						&context->meta_ac,
> +						extra_blocks, &credits);
>   	if (ret) {
>   		mlog_errno(ret);
>   		goto out;
> @@ -283,6 +272,21 @@ static int ocfs2_defrag_extent(struct
ocfs2_move_extents_context *context,
>   		}
>   	}
>   
> +	/*
> +	 * Make sure ocfs2_reserve_cluster is called after
> +	 * __ocfs2_flush_truncate_log, otherwise, dead lock may happen.
> +	 *
> +	 * If ocfs2_reserve_cluster is called
> +	 * before __ocfs2_flush_truncate_log, dead lock on global bitmap
> +	 * may happen.
> +	 *
> +	 */
> +	ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac);
> +	if (ret) {
> +		mlog_errno(ret);
> +		goto out_unlock_mutex;
> +	}
> +
>   	handle = ocfs2_start_trans(osb, credits);
>   	if (IS_ERR(handle)) {
>   		ret = PTR_ERR(handle);
> @@ -600,9 +604,10 @@ static int ocfs2_move_extent(struct
ocfs2_move_extents_context *context,
>   		}
>   	}
>   
> -	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len,
1,
> -						 &context->meta_ac,
> -						 NULL, extra_blocks, &credits);
> +	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
> +						len, 1,
> +						&context->meta_ac,
> +						extra_blocks, &credits);
>   	if (ret) {
>   		mlog_errno(ret);
>   		goto out;
>