ocfs2: mknod: fix recursive locking hung
diff mbox

Message ID 1508300302-5155-1-git-send-email-junxiao.bi@oracle.com
State New
Headers show

Commit Message

Junxiao Bi Oct. 18, 2017, 4:18 a.m. UTC
Here another recursive lock caught and it caused the cluster hung.

 #0 [ffff88008e3935a8] __schedule at ffffffff816e4722
 #1 [ffff88008e393600] schedule at ffffffff816e4dee
 #2 [ffff88008e393620] schedule_timeout at ffffffff816e7cd5
 #3 [ffff88008e3936c0] wait_for_completion at ffffffff816e631f
 #4 [ffff88008e393740] __ocfs2_cluster_lock at ffffffffa05a9111 [ocfs2]
 #5 [ffff88008e393890] ocfs2_inode_lock_full_nested at ffffffffa05aec14 [ocfs2]
 #6 [ffff88008e393910] ocfs2_inode_lock_tracker at ffffffffa05af02f [ocfs2]
 #7 [ffff88008e393970] ocfs2_iop_get_acl at ffffffffa0620c92 [ocfs2]
 #8 [ffff88008e3939d0] get_acl at ffffffff8126ae79
 #9 [ffff88008e3939f0] posix_acl_create at ffffffff8126b27a
 #10 [ffff88008e393a20] ocfs2_mknod at ffffffffa05cedcc [ocfs2]
 #11 [ffff88008e393b60] ocfs2_create at ffffffffa05cfb13 [ocfs2]
 #12 [ffff88008e393bd0] vfs_create at ffffffff81217338
 #13 [ffff88008e393c10] lookup_open at ffffffff81217a85
 #14 [ffff88008e393ca0] do_last at ffffffff8121ac6d
 #15 [ffff88008e393d30] path_openat at ffffffff8121b112
 #16 [ffff88008e393df0] do_filp_open at ffffffff8121b53a
 #17 [ffff88008e393ed0] do_sys_open at ffffffff81209a5a
 #18 [ffff88008e393f40] sys_open at ffffffff81209bae
 #19 [ffff88008e393f50] system_call_fastpath at ffffffff816e902e

inode lock is got by ocfs2_mknod() before call into posix_acl_create().

Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: <stable@vger.kernel.org>
---
 fs/ocfs2/namei.c |   14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

Comments

Gang He Oct. 18, 2017, 4:41 a.m. UTC | #1
Hi Junxiao,

The problem looks easy to reproduce?
Could you share the trigger script/code for this issue?


Thanks
Gang


>>> 
> Here another recursive lock caught and it caused the cluster hung.
> 
>  #0 [ffff88008e3935a8] __schedule at ffffffff816e4722
>  #1 [ffff88008e393600] schedule at ffffffff816e4dee
>  #2 [ffff88008e393620] schedule_timeout at ffffffff816e7cd5
>  #3 [ffff88008e3936c0] wait_for_completion at ffffffff816e631f
>  #4 [ffff88008e393740] __ocfs2_cluster_lock at ffffffffa05a9111 [ocfs2]
>  #5 [ffff88008e393890] ocfs2_inode_lock_full_nested at ffffffffa05aec14 
> [ocfs2]
>  #6 [ffff88008e393910] ocfs2_inode_lock_tracker at ffffffffa05af02f [ocfs2]
>  #7 [ffff88008e393970] ocfs2_iop_get_acl at ffffffffa0620c92 [ocfs2]
>  #8 [ffff88008e3939d0] get_acl at ffffffff8126ae79
>  #9 [ffff88008e3939f0] posix_acl_create at ffffffff8126b27a
>  #10 [ffff88008e393a20] ocfs2_mknod at ffffffffa05cedcc [ocfs2]
>  #11 [ffff88008e393b60] ocfs2_create at ffffffffa05cfb13 [ocfs2]
>  #12 [ffff88008e393bd0] vfs_create at ffffffff81217338
>  #13 [ffff88008e393c10] lookup_open at ffffffff81217a85
>  #14 [ffff88008e393ca0] do_last at ffffffff8121ac6d
>  #15 [ffff88008e393d30] path_openat at ffffffff8121b112
>  #16 [ffff88008e393df0] do_filp_open at ffffffff8121b53a
>  #17 [ffff88008e393ed0] do_sys_open at ffffffff81209a5a
>  #18 [ffff88008e393f40] sys_open at ffffffff81209bae
>  #19 [ffff88008e393f50] system_call_fastpath at ffffffff816e902e
> 
> inode lock is got by ocfs2_mknod() before call into posix_acl_create().
> 
> Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
> Cc: <stable@vger.kernel.org>
> ---
>  fs/ocfs2/namei.c |   14 ++++++++------
>  1 file changed, 8 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
> index 3b0a10d9b36f..f0ee52e600ff 100644
> --- a/fs/ocfs2/namei.c
> +++ b/fs/ocfs2/namei.c
> @@ -260,6 +260,8 @@ static int ocfs2_mknod(struct inode *dir,
>  	sigset_t oldset;
>  	int did_block_signals = 0;
>  	struct ocfs2_dentry_lock *dl = NULL;
> +	int locked;
> +	struct ocfs2_lock_holder oh;
>  
>  	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
>  			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
> @@ -274,11 +276,11 @@ static int ocfs2_mknod(struct inode *dir,
>  	/* get our super block */
>  	osb = OCFS2_SB(dir->i_sb);
>  
> -	status = ocfs2_inode_lock(dir, &parent_fe_bh, 1);
> -	if (status < 0) {
> -		if (status != -ENOENT)
> -			mlog_errno(status);
> -		return status;
> +	locked = ocfs2_inode_lock_tracker(dir, &parent_fe_bh, 1, &oh);
> +	if (locked < 0) {
> +		if (locked != -ENOENT)
> +			mlog_errno(locked);
> +		return locked;
>  	}
>  
>  	if (S_ISDIR(mode) && (dir->i_nlink >= ocfs2_link_max(osb))) {
> @@ -462,7 +464,7 @@ static int ocfs2_mknod(struct inode *dir,
>  	if (handle)
>  		ocfs2_commit_trans(osb, handle);
>  
> -	ocfs2_inode_unlock(dir, 1);
> +	ocfs2_inode_unlock_tracker(dir, 1, &oh, locked);
>  	if (did_block_signals)
>  		ocfs2_unblock_signals(&oldset);
>  
> -- 
> 1.7.9.5
> 
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel@oss.oracle.com 
> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
Junxiao Bi Oct. 18, 2017, 4:44 a.m. UTC | #2
On 10/18/2017 12:41 PM, Gang He wrote:
> Hi Junxiao,
> 
> The problem looks easy to reproduce?
> Could you share the trigger script/code for this issue?
Please run ocfs2-test multiple reflink test.

Thanks,
Junxiao.
> 
> 
> Thanks
> Gang
> 
> 
>>>>
>> Here another recursive lock caught and it caused the cluster hung.
>>
>>  #0 [ffff88008e3935a8] __schedule at ffffffff816e4722
>>  #1 [ffff88008e393600] schedule at ffffffff816e4dee
>>  #2 [ffff88008e393620] schedule_timeout at ffffffff816e7cd5
>>  #3 [ffff88008e3936c0] wait_for_completion at ffffffff816e631f
>>  #4 [ffff88008e393740] __ocfs2_cluster_lock at ffffffffa05a9111 [ocfs2]
>>  #5 [ffff88008e393890] ocfs2_inode_lock_full_nested at ffffffffa05aec14 
>> [ocfs2]
>>  #6 [ffff88008e393910] ocfs2_inode_lock_tracker at ffffffffa05af02f [ocfs2]
>>  #7 [ffff88008e393970] ocfs2_iop_get_acl at ffffffffa0620c92 [ocfs2]
>>  #8 [ffff88008e3939d0] get_acl at ffffffff8126ae79
>>  #9 [ffff88008e3939f0] posix_acl_create at ffffffff8126b27a
>>  #10 [ffff88008e393a20] ocfs2_mknod at ffffffffa05cedcc [ocfs2]
>>  #11 [ffff88008e393b60] ocfs2_create at ffffffffa05cfb13 [ocfs2]
>>  #12 [ffff88008e393bd0] vfs_create at ffffffff81217338
>>  #13 [ffff88008e393c10] lookup_open at ffffffff81217a85
>>  #14 [ffff88008e393ca0] do_last at ffffffff8121ac6d
>>  #15 [ffff88008e393d30] path_openat at ffffffff8121b112
>>  #16 [ffff88008e393df0] do_filp_open at ffffffff8121b53a
>>  #17 [ffff88008e393ed0] do_sys_open at ffffffff81209a5a
>>  #18 [ffff88008e393f40] sys_open at ffffffff81209bae
>>  #19 [ffff88008e393f50] system_call_fastpath at ffffffff816e902e
>>
>> inode lock is got by ocfs2_mknod() before call into posix_acl_create().
>>
>> Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
>> Cc: <stable@vger.kernel.org>
>> ---
>>  fs/ocfs2/namei.c |   14 ++++++++------
>>  1 file changed, 8 insertions(+), 6 deletions(-)
>>
>> diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
>> index 3b0a10d9b36f..f0ee52e600ff 100644
>> --- a/fs/ocfs2/namei.c
>> +++ b/fs/ocfs2/namei.c
>> @@ -260,6 +260,8 @@ static int ocfs2_mknod(struct inode *dir,
>>  	sigset_t oldset;
>>  	int did_block_signals = 0;
>>  	struct ocfs2_dentry_lock *dl = NULL;
>> +	int locked;
>> +	struct ocfs2_lock_holder oh;
>>  
>>  	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
>>  			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
>> @@ -274,11 +276,11 @@ static int ocfs2_mknod(struct inode *dir,
>>  	/* get our super block */
>>  	osb = OCFS2_SB(dir->i_sb);
>>  
>> -	status = ocfs2_inode_lock(dir, &parent_fe_bh, 1);
>> -	if (status < 0) {
>> -		if (status != -ENOENT)
>> -			mlog_errno(status);
>> -		return status;
>> +	locked = ocfs2_inode_lock_tracker(dir, &parent_fe_bh, 1, &oh);
>> +	if (locked < 0) {
>> +		if (locked != -ENOENT)
>> +			mlog_errno(locked);
>> +		return locked;
>>  	}
>>  
>>  	if (S_ISDIR(mode) && (dir->i_nlink >= ocfs2_link_max(osb))) {
>> @@ -462,7 +464,7 @@ static int ocfs2_mknod(struct inode *dir,
>>  	if (handle)
>>  		ocfs2_commit_trans(osb, handle);
>>  
>> -	ocfs2_inode_unlock(dir, 1);
>> +	ocfs2_inode_unlock_tracker(dir, 1, &oh, locked);
>>  	if (did_block_signals)
>>  		ocfs2_unblock_signals(&oldset);
>>  
>> -- 
>> 1.7.9.5
>>
>>
>> _______________________________________________
>> Ocfs2-devel mailing list
>> Ocfs2-devel@oss.oracle.com 
>> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>
Zhen Ren Oct. 23, 2017, 6:51 a.m. UTC | #3
Hi,

On 10/18/2017 12:44 PM, Junxiao Bi wrote:
> On 10/18/2017 12:41 PM, Gang He wrote:
>> Hi Junxiao,
>>
>> The problem looks easy to reproduce?
>> Could you share the trigger script/code for this issue?
> Please run ocfs2-test multiple reflink test.
Hmm, strange, we do run ocfs2-test quite often.

Eric
Junxiao Bi Oct. 24, 2017, 12:49 a.m. UTC | #4
On 10/23/2017 02:51 PM, Eric Ren wrote:
> Hi,
> 
> On 10/18/2017 12:44 PM, Junxiao Bi wrote:
>> On 10/18/2017 12:41 PM, Gang He wrote:
>>> Hi Junxiao,
>>>
>>> The problem looks easy to reproduce?
>>> Could you share the trigger script/code for this issue?
>> Please run ocfs2-test multiple reflink test.
> Hmm, strange, we do run ocfs2-test quite often.
Indeed this issue not exist in upstream.
commit c25a1e0671fb ("ocfs2: fix posix_acl_create deadlock") already
fixed it.

Thanks,
Junxiao.
> 
> Eric

Patch
diff mbox

diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3b0a10d9b36f..f0ee52e600ff 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -260,6 +260,8 @@  static int ocfs2_mknod(struct inode *dir,
 	sigset_t oldset;
 	int did_block_signals = 0;
 	struct ocfs2_dentry_lock *dl = NULL;
+	int locked;
+	struct ocfs2_lock_holder oh;
 
 	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
 			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
@@ -274,11 +276,11 @@  static int ocfs2_mknod(struct inode *dir,
 	/* get our super block */
 	osb = OCFS2_SB(dir->i_sb);
 
-	status = ocfs2_inode_lock(dir, &parent_fe_bh, 1);
-	if (status < 0) {
-		if (status != -ENOENT)
-			mlog_errno(status);
-		return status;
+	locked = ocfs2_inode_lock_tracker(dir, &parent_fe_bh, 1, &oh);
+	if (locked < 0) {
+		if (locked != -ENOENT)
+			mlog_errno(locked);
+		return locked;
 	}
 
 	if (S_ISDIR(mode) && (dir->i_nlink >= ocfs2_link_max(osb))) {
@@ -462,7 +464,7 @@  static int ocfs2_mknod(struct inode *dir,
 	if (handle)
 		ocfs2_commit_trans(osb, handle);
 
-	ocfs2_inode_unlock(dir, 1);
+	ocfs2_inode_unlock_tracker(dir, 1, &oh, locked);
 	if (did_block_signals)
 		ocfs2_unblock_signals(&oldset);