[PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Larry Chen]

ocfs2_defrag_extent may fall into dead lock.

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 back trace 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 dead lock
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

The ocfs2_lock_allocators_move_extents has been refered 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. rename ocfs2_lock_allocators_move_extents to
   ocfs2_lock_meta_allocator_move_extents

2. add some comments

Signed-off-by: Larry Chen <lchen@suse.com>
---
 fs/ocfs2/move_extents.c | 40 +++++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 7eb3b0a6347e..d85dc8a02bd6 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -162,7 +162,7 @@ static int __ocfs2_move_extent(handle_t *handle,
  * in some cases, we don't need to reserve clusters, just let data_ac
  * be NULL.
  */
-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,
@@ -192,13 +192,6 @@ 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 +250,11 @@ 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,
+						&context->data_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -283,6 +277,21 @@ 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 +609,10 @@ 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,
+						NULL, extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
-- 
2.13.7

[Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Larry Chen]

ocfs2_defrag_extent may fall into dead lock.

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 back trace 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 dead lock
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

The ocfs2_lock_allocators_move_extents has been refered 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. rename ocfs2_lock_allocators_move_extents to
   ocfs2_lock_meta_allocator_move_extents

2. add some comments

Signed-off-by: Larry Chen <lchen@suse.com>
---
 fs/ocfs2/move_extents.c | 40 +++++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 7eb3b0a6347e..d85dc8a02bd6 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -162,7 +162,7 @@ static int __ocfs2_move_extent(handle_t *handle,
  * in some cases, we don't need to reserve clusters, just let data_ac
  * be NULL.
  */
-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,
@@ -192,13 +192,6 @@ 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 +250,11 @@ 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,
+						&context->data_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -283,6 +277,21 @@ 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 +609,10 @@ 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,
+						NULL, extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
-- 
2.13.7

Re: [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Andrew Morton]

Folks, could we please review this patch for upstream inclusion?

Thanks.


From: Larry Chen <lchen@suse.com>
Subject: ocfs2: fix deadlock 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 refered 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.

[lchen@suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
  Link: http://lkml.kernel.org/r/20180902091455.23862-1-lchen@suse.com
Link: http://lkml.kernel.org/r/20180827080121.31145-1-lchen@suse.com
Signed-off-by: Larry Chen <lchen@suse.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <ge.changwei@h3c.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

--- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
+++ a/fs/ocfs2/move_extents.c
@@ -162,7 +162,7 @@ out:
  * in some cases, we don't need to reserve clusters, just let data_ac
  * be NULL.
  */
-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,
@@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
 		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
 		}
 	}
 
-	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,
+						&context->data_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
 		}
 	}
 
+	/*
+	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
 		}
 	}
 
-	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,
+						NULL, extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
_

[Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Andrew Morton]

Folks, could we please review this patch for upstream inclusion?

Thanks.


From: Larry Chen <lchen@suse.com>
Subject: ocfs2: fix deadlock 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 refered 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.

[lchen at suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
  Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
Signed-off-by: Larry Chen <lchen@suse.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <ge.changwei@h3c.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

--- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
+++ a/fs/ocfs2/move_extents.c
@@ -162,7 +162,7 @@ out:
  * in some cases, we don't need to reserve clusters, just let data_ac
  * be NULL.
  */
-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,
@@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
 		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
 		}
 	}
 
-	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,
+						&context->data_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
 		}
 	}
 
+	/*
+	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
 		}
 	}
 
-	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,
+						NULL, extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
_

Re: [Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Changwei Ge]

Hi Larry,

I still have a few tiny comments for your patch, please refer to them.

On 2018/11/1 5:28, Andrew Morton wrote:
> 
> Folks, could we please review this patch for upstream inclusion?
> 
> Thanks.
> 
> 
> From: Larry Chen <lchen@suse.com>
> Subject: ocfs2: fix deadlock 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 refered 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.
> 
> [lchen@suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
>    Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
> Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
> Signed-off-by: Larry Chen <lchen@suse.com>
> Cc: Mark Fasheh <mark@fasheh.com>
> Cc: Joel Becker <jlbec@evilplan.org>
> Cc: Junxiao Bi <junxiao.bi@oracle.com>
> Cc: Joseph Qi <jiangqi903@gmail.com>
> Cc: Changwei Ge <ge.changwei@h3c.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> ---
> 
>   fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
>   1 file changed, 25 insertions(+), 15 deletions(-)
> 
> --- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
> +++ a/fs/ocfs2/move_extents.c
> @@ -162,7 +162,7 @@ out:
>    * in some cases, we don't need to reserve clusters, just let data_ac
>    * be NULL.
>    */
> -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,

After removing 'reserving clusters logic' out of this function, I suggest to also change the function header comments.
And I think there is no need for arguments _data_ac_ now.
Otherwise this patch looks sane to me.

Thanks,
Changwei

> @@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
>   		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
>   		}
>   	}
>   
> -	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,
> +						&context->data_ac,
> +						extra_blocks, &credits);
>   	if (ret) {
>   		mlog_errno(ret);
>   		goto out;
> @@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
>   		}
>   	}
>   
> +	/*
> +	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
>   		}
>   	}
>   
> -	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,
> +						NULL, extra_blocks, &credits);
>   	if (ret) {
>   		mlog_errno(ret);
>   		goto out;
> _
> 
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel@oss.oracle.com
> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
> 

[Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Changwei Ge]

Hi Larry,

I still have a few tiny comments for your patch, please refer to them.

On 2018/11/1 5:28, Andrew Morton wrote:
> 
> Folks, could we please review this patch for upstream inclusion?
> 
> Thanks.
> 
> 
> From: Larry Chen <lchen@suse.com>
> Subject: ocfs2: fix deadlock 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 refered 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.
> 
> [lchen at suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
>    Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
> Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
> Signed-off-by: Larry Chen <lchen@suse.com>
> Cc: Mark Fasheh <mark@fasheh.com>
> Cc: Joel Becker <jlbec@evilplan.org>
> Cc: Junxiao Bi <junxiao.bi@oracle.com>
> Cc: Joseph Qi <jiangqi903@gmail.com>
> Cc: Changwei Ge <ge.changwei@h3c.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> ---
> 
>   fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
>   1 file changed, 25 insertions(+), 15 deletions(-)
> 
> --- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
> +++ a/fs/ocfs2/move_extents.c
> @@ -162,7 +162,7 @@ out:
>    * in some cases, we don't need to reserve clusters, just let data_ac
>    * be NULL.
>    */
> -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,

After removing 'reserving clusters logic' out of this function, I suggest to also change the function header comments.
And I think there is no need for arguments _data_ac_ now.
Otherwise this patch looks sane to me.

Thanks,
Changwei

> @@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
>   		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
>   		}
>   	}
>   
> -	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,
> +						&context->data_ac,
> +						extra_blocks, &credits);
>   	if (ret) {
>   		mlog_errno(ret);
>   		goto out;
> @@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
>   		}
>   	}
>   
> +	/*
> +	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
>   		}
>   	}
>   
> -	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,
> +						NULL, extra_blocks, &credits);
>   	if (ret) {
>   		mlog_errno(ret);
>   		goto out;
> _
> 
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel at oss.oracle.com
> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
> 

Re: [Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Larry Chen]

Hi Changwei,

Thanks for your review, I'll improve my patch and resend it later.

Thanks
Larry

On 11/1/18 11:11 AM, Changwei Ge wrote:
> Hi Larry,
> 
> I still have a few tiny comments for your patch, please refer to them.
> 
> On 2018/11/1 5:28, Andrew Morton wrote:
>>
>> Folks, could we please review this patch for upstream inclusion?
>>
>> Thanks.
>>
>>
>> From: Larry Chen <lchen@suse.com>
>> Subject: ocfs2: fix deadlock 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 refered 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.
>>
>> [lchen@suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
>>     Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
>> Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
>> Signed-off-by: Larry Chen <lchen@suse.com>
>> Cc: Mark Fasheh <mark@fasheh.com>
>> Cc: Joel Becker <jlbec@evilplan.org>
>> Cc: Junxiao Bi <junxiao.bi@oracle.com>
>> Cc: Joseph Qi <jiangqi903@gmail.com>
>> Cc: Changwei Ge <ge.changwei@h3c.com>
>> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
>> ---
>>
>>    fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
>>    1 file changed, 25 insertions(+), 15 deletions(-)
>>
>> --- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
>> +++ a/fs/ocfs2/move_extents.c
>> @@ -162,7 +162,7 @@ out:
>>     * in some cases, we don't need to reserve clusters, just let data_ac
>>     * be NULL.
>>     */
>> -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,
> 
> After removing 'reserving clusters logic' out of this function, I suggest to also change the function header comments.
> And I think there is no need for arguments _data_ac_ now.
> Otherwise this patch looks sane to me.
> 
> Thanks,
> Changwei
> 
>> @@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
>>    		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
>>    		}
>>    	}
>>    
>> -	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,
>> +						&context->data_ac,
>> +						extra_blocks, &credits);
>>    	if (ret) {
>>    		mlog_errno(ret);
>>    		goto out;
>> @@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
>>    		}
>>    	}
>>    
>> +	/*
>> +	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
>>    		}
>>    	}
>>    
>> -	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,
>> +						NULL, extra_blocks, &credits);
>>    	if (ret) {
>>    		mlog_errno(ret);
>>    		goto out;
>> _
>>
>>
>> _______________________________________________
>> Ocfs2-devel mailing list
>> Ocfs2-devel@oss.oracle.com
>> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>>
> 

[Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Larry Chen]

Hi Changwei,

Thanks for your review, I'll improve my patch and resend it later.

Thanks
Larry

On 11/1/18 11:11 AM, Changwei Ge wrote:
> Hi Larry,
> 
> I still have a few tiny comments for your patch, please refer to them.
> 
> On 2018/11/1 5:28, Andrew Morton wrote:
>>
>> Folks, could we please review this patch for upstream inclusion?
>>
>> Thanks.
>>
>>
>> From: Larry Chen <lchen@suse.com>
>> Subject: ocfs2: fix deadlock 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 refered 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.
>>
>> [lchen at suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
>>     Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
>> Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
>> Signed-off-by: Larry Chen <lchen@suse.com>
>> Cc: Mark Fasheh <mark@fasheh.com>
>> Cc: Joel Becker <jlbec@evilplan.org>
>> Cc: Junxiao Bi <junxiao.bi@oracle.com>
>> Cc: Joseph Qi <jiangqi903@gmail.com>
>> Cc: Changwei Ge <ge.changwei@h3c.com>
>> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
>> ---
>>
>>    fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
>>    1 file changed, 25 insertions(+), 15 deletions(-)
>>
>> --- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
>> +++ a/fs/ocfs2/move_extents.c
>> @@ -162,7 +162,7 @@ out:
>>     * in some cases, we don't need to reserve clusters, just let data_ac
>>     * be NULL.
>>     */
>> -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,
> 
> After removing 'reserving clusters logic' out of this function, I suggest to also change the function header comments.
> And I think there is no need for arguments _data_ac_ now.
> Otherwise this patch looks sane to me.
> 
> Thanks,
> Changwei
> 
>> @@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
>>    		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
>>    		}
>>    	}
>>    
>> -	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,
>> +						&context->data_ac,
>> +						extra_blocks, &credits);
>>    	if (ret) {
>>    		mlog_errno(ret);
>>    		goto out;
>> @@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
>>    		}
>>    	}
>>    
>> +	/*
>> +	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
>>    		}
>>    	}
>>    
>> -	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,
>> +						NULL, extra_blocks, &credits);
>>    	if (ret) {
>>    		mlog_errno(ret);
>>    		goto out;
>> _
>>
>>
>> _______________________________________________
>> Ocfs2-devel mailing list
>> Ocfs2-devel at oss.oracle.com
>> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>>
> 

Re: [Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Joseph Qi]

On 18/11/1 11:11, Changwei Ge wrote:
> Hi Larry,
> 
> I still have a few tiny comments for your patch, please refer to them.
> 
> On 2018/11/1 5:28, Andrew Morton wrote:
>>
>> Folks, could we please review this patch for upstream inclusion?
>>
>> Thanks.
>>
>>
>> From: Larry Chen <lchen@suse.com>
>> Subject: ocfs2: fix deadlock 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 refered 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.
>>
>> [lchen@suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
>>    Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
>> Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
>> Signed-off-by: Larry Chen <lchen@suse.com>
>> Cc: Mark Fasheh <mark@fasheh.com>
>> Cc: Joel Becker <jlbec@evilplan.org>
>> Cc: Junxiao Bi <junxiao.bi@oracle.com>
>> Cc: Joseph Qi <jiangqi903@gmail.com>
>> Cc: Changwei Ge <ge.changwei@h3c.com>
>> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
>> ---
>>
>>   fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
>>   1 file changed, 25 insertions(+), 15 deletions(-)
>>
>> --- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
>> +++ a/fs/ocfs2/move_extents.c
>> @@ -162,7 +162,7 @@ out:
>>    * in some cases, we don't need to reserve clusters, just let data_ac
>>    * be NULL.
>>    */
>> -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,
> 
> After removing 'reserving clusters logic' out of this function, I suggest to also change the function header comments.
> And I think there is no need for arguments _data_ac_ now.
> Otherwise this patch looks sane to me.
> 
Agree, I think I have commented this out before.

Thanks,
Joseph

> Thanks,
> Changwei
> 
>> @@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
>>   		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
>>   		}
>>   	}
>>   
>> -	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,
>> +						&context->data_ac,
>> +						extra_blocks, &credits);
>>   	if (ret) {
>>   		mlog_errno(ret);
>>   		goto out;
>> @@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
>>   		}
>>   	}
>>   
>> +	/*
>> +	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
>>   		}
>>   	}
>>   
>> -	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,
>> +						NULL, extra_blocks, &credits);
>>   	if (ret) {
>>   		mlog_errno(ret);
>>   		goto out;
>> _
>>
>>
>> _______________________________________________
>> Ocfs2-devel mailing list
>> Ocfs2-devel@oss.oracle.com
>> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>>
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel@oss.oracle.com
> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
> 

[Ocfs2-devel] [PATCH V2] ocfs2: fix dead lock caused by ocfs2_defrag_extent

[Joseph Qi]

On 18/11/1 11:11, Changwei Ge wrote:
> Hi Larry,
> 
> I still have a few tiny comments for your patch, please refer to them.
> 
> On 2018/11/1 5:28, Andrew Morton wrote:
>>
>> Folks, could we please review this patch for upstream inclusion?
>>
>> Thanks.
>>
>>
>> From: Larry Chen <lchen@suse.com>
>> Subject: ocfs2: fix deadlock 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 refered 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.
>>
>> [lchen at suse.com: rename ocfs2_lock_allocators_move_extents() to ocfs2_lock_meta_allocator_move_extents(), add some comments]
>>    Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180902091455.23862-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=3fQHFtwgixirPeQ5Px4fRBnd_UcSx3rvSsLKLidwESo&e=
>> Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__lkml.kernel.org_r_20180827080121.31145-2D1-2Dlchen-40suse.com&d=DwICAg&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=C7gAd4uDxlAvTdc0vmU6X8CMk6L2iDY8-HD0qT6Fo7Y&m=K8aRgOiMescamJW-IuHq-cW4mWedGQv2JTT-2KPy1RI&s=PQOJREyeElsg_1IlINdSGefNqA6w_cUrI1ezdVxyi7o&e=
>> Signed-off-by: Larry Chen <lchen@suse.com>
>> Cc: Mark Fasheh <mark@fasheh.com>
>> Cc: Joel Becker <jlbec@evilplan.org>
>> Cc: Junxiao Bi <junxiao.bi@oracle.com>
>> Cc: Joseph Qi <jiangqi903@gmail.com>
>> Cc: Changwei Ge <ge.changwei@h3c.com>
>> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
>> ---
>>
>>   fs/ocfs2/move_extents.c |   40 +++++++++++++++++++++++---------------
>>   1 file changed, 25 insertions(+), 15 deletions(-)
>>
>> --- a/fs/ocfs2/move_extents.c~fix-dead-lock-caused-by-ocfs2_defrag_extent
>> +++ a/fs/ocfs2/move_extents.c
>> @@ -162,7 +162,7 @@ out:
>>    * in some cases, we don't need to reserve clusters, just let data_ac
>>    * be NULL.
>>    */
>> -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,
> 
> After removing 'reserving clusters logic' out of this function, I suggest to also change the function header comments.
> And I think there is no need for arguments _data_ac_ now.
> Otherwise this patch looks sane to me.
> 
Agree, I think I have commented this out before.

Thanks,
Joseph

> Thanks,
> Changwei
> 
>> @@ -192,13 +192,6 @@ static int ocfs2_lock_allocators_move_ex
>>   		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 +250,11 @@ static int ocfs2_defrag_extent(struct oc
>>   		}
>>   	}
>>   
>> -	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,
>> +						&context->data_ac,
>> +						extra_blocks, &credits);
>>   	if (ret) {
>>   		mlog_errno(ret);
>>   		goto out;
>> @@ -283,6 +277,21 @@ static int ocfs2_defrag_extent(struct oc
>>   		}
>>   	}
>>   
>> +	/*
>> +	 * 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 +609,10 @@ static int ocfs2_move_extent(struct ocfs
>>   		}
>>   	}
>>   
>> -	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,
>> +						NULL, extra_blocks, &credits);
>>   	if (ret) {
>>   		mlog_errno(ret);
>>   		goto out;
>> _
>>
>>
>> _______________________________________________
>> Ocfs2-devel mailing list
>> Ocfs2-devel at oss.oracle.com
>> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>>
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel at oss.oracle.com
> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>