[2/2] ocfs2: fix deadlocks when taking inode lock at vfs entry points

Commit Message

Zhen Ren Jan. 5, 2017, 3:31 p.m. UTC

Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()")
results in a deadlock, as the author "Tariq Saeed" realized shortly
after the patch was merged. The discussion happened here
(https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).

The reason why taking cluster inode lock at vfs entry points opens up
a self deadlock window, is explained in the previous patch of this
series.

So far, we have seen two different code paths that have this issue.
1. do_sys_open
     may_open
      inode_permission
       ocfs2_permission
        ocfs2_inode_lock() <=== take PR
         generic_permission
          get_acl
           ocfs2_iop_get_acl
            ocfs2_inode_lock() <=== take PR
2. fchmod|fchmodat
    chmod_common
     notify_change
      ocfs2_setattr <=== take EX
       posix_acl_chmod
        get_acl
         ocfs2_iop_get_acl <=== take PR
        ocfs2_iop_set_acl <=== take EX

Fixes them by adding the tracking logic (in the previous patch) for
these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
ocfs2_setattr().

Signed-off-by: Eric Ren <[e-mail]>
---
 fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
 fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
 2 files changed, 68 insertions(+), 15 deletions(-)

Comments

Joseph Qi Jan. 6, 2017, 6:09 a.m. UTC | #1

Hi Eric,


On 17/1/5 23:31, Eric Ren wrote:
> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()")
> results in a deadlock, as the author "Tariq Saeed" realized shortly
> after the patch was merged. The discussion happened here
> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
>
> The reason why taking cluster inode lock at vfs entry points opens up
> a self deadlock window, is explained in the previous patch of this
> series.
>
> So far, we have seen two different code paths that have this issue.
> 1. do_sys_open
>       may_open
>        inode_permission
>         ocfs2_permission
>          ocfs2_inode_lock() <=== take PR
>           generic_permission
>            get_acl
>             ocfs2_iop_get_acl
>              ocfs2_inode_lock() <=== take PR
> 2. fchmod|fchmodat
>      chmod_common
>       notify_change
>        ocfs2_setattr <=== take EX
>         posix_acl_chmod
>          get_acl
>           ocfs2_iop_get_acl <=== take PR
>          ocfs2_iop_set_acl <=== take EX
>
> Fixes them by adding the tracking logic (in the previous patch) for
> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
> ocfs2_setattr().
As described cases above, shall we just add the tracking logic only for 
set/get_acl()?

Thanks,
Joseph
>
> Signed-off-by: Eric Ren <[e-mail]>
> ---
>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>   2 files changed, 68 insertions(+), 15 deletions(-)
>
> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
> index bed1fcb..c539890 100644
> --- a/fs/ocfs2/acl.c
> +++ b/fs/ocfs2/acl.c
> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
>   {
>   	struct buffer_head *bh = NULL;
>   	int status = 0;
> -
> -	status = ocfs2_inode_lock(inode, &bh, 1);
> +	int arg_flags = 0, has_locked;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
> +
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
> +	if (has_locked)
> +		arg_flags = OCFS2_META_LOCK_GETBH;
> +	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>   	if (status < 0) {
>   		if (status != -ENOENT)
>   			mlog_errno(status);
>   		return status;
>   	}
> +	if (!has_locked)
> +		ocfs2_add_holder(lockres, &oh);
> +
>   	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
> -	ocfs2_inode_unlock(inode, 1);
> +
> +	if (!has_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
> +		ocfs2_inode_unlock(inode, 1);
> +	}
>   	brelse(bh);
> +
>   	return status;
>   }
>   
> @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
>   	struct buffer_head *di_bh = NULL;
>   	struct posix_acl *acl;
>   	int ret;
> +	int arg_flags = 0, has_locked;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
>   
>   	osb = OCFS2_SB(inode->i_sb);
>   	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>   		return NULL;
> -	ret = ocfs2_inode_lock(inode, &di_bh, 0);
> +
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
> +	if (has_locked)
> +		arg_flags = OCFS2_META_LOCK_GETBH;
> +	ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>   	if (ret < 0) {
>   		if (ret != -ENOENT)
>   			mlog_errno(ret);
>   		return ERR_PTR(ret);
>   	}
> +	if (!has_locked)
> +		ocfs2_add_holder(lockres, &oh);
>   
>   	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>   
> -	ocfs2_inode_unlock(inode, 0);
> +	if (!has_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
> +		ocfs2_inode_unlock(inode, 0);
> +	}
>   	brelse(di_bh);
> +
>   	return acl;
>   }
>   
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index c488965..62be75d 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>   	handle_t *handle = NULL;
>   	struct dquot *transfer_to[MAXQUOTAS] = { };
>   	int qtype;
> +	int arg_flags = 0, had_lock;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
>   
>   	trace_ocfs2_setattr(inode, dentry,
>   			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>   		}
>   	}
>   
> -	status = ocfs2_inode_lock(inode, &bh, 1);
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
> +	if (had_lock)
> +		arg_flags = OCFS2_META_LOCK_GETBH;
> +	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>   	if (status < 0) {
>   		if (status != -ENOENT)
>   			mlog_errno(status);
>   		goto bail_unlock_rw;
>   	}
> -	inode_locked = 1;
> +	if (!had_lock) {
> +		ocfs2_add_holder(lockres, &oh);
> +		inode_locked = 1;
> +	}
>   
>   	if (size_change) {
>   		status = inode_newsize_ok(inode, attr->ia_size);
> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>   bail_commit:
>   	ocfs2_commit_trans(osb, handle);
>   bail_unlock:
> -	if (status) {
> +	if (status && inode_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
>   		ocfs2_inode_unlock(inode, 1);
>   		inode_locked = 0;
>   	}
> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>   		if (status < 0)
>   			mlog_errno(status);
>   	}
> -	if (inode_locked)
> +	if (inode_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
>   		ocfs2_inode_unlock(inode, 1);
> +	}
>   
>   	brelse(bh);
>   	return status;
> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>   int ocfs2_permission(struct inode *inode, int mask)
>   {
>   	int ret;
> +	int has_locked;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
>   
>   	if (mask & MAY_NOT_BLOCK)
>   		return -ECHILD;
>   
> -	ret = ocfs2_inode_lock(inode, NULL, 0);
> -	if (ret) {
> -		if (ret != -ENOENT)
> -			mlog_errno(ret);
> -		goto out;
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
> +	if (!has_locked) {
> +		ret = ocfs2_inode_lock(inode, NULL, 0);
> +		if (ret) {
> +			if (ret != -ENOENT)
> +				mlog_errno(ret);
> +			goto out;
> +		}
> +		ocfs2_add_holder(lockres, &oh);
>   	}
>   
>   	ret = generic_permission(inode, mask);
>   
> -	ocfs2_inode_unlock(inode, 0);
> +	if (!has_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
> +		ocfs2_inode_unlock(inode, 0);
> +	}
>   out:
>   	return ret;
>   }

Zhen Ren Jan. 6, 2017, 6:56 a.m. UTC | #2

On 01/06/2017 02:09 PM, Joseph Qi wrote:
> Hi Eric,
>
>
> On 17/1/5 23:31, Eric Ren wrote:
>> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()")
>> results in a deadlock, as the author "Tariq Saeed" realized shortly
>> after the patch was merged. The discussion happened here
>> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
>>
>> The reason why taking cluster inode lock at vfs entry points opens up
>> a self deadlock window, is explained in the previous patch of this
>> series.
>>
>> So far, we have seen two different code paths that have this issue.
>> 1. do_sys_open
>>       may_open
>>        inode_permission
>>         ocfs2_permission
>>          ocfs2_inode_lock() <=== take PR
>>           generic_permission
>>            get_acl
>>             ocfs2_iop_get_acl
>>              ocfs2_inode_lock() <=== take PR
>> 2. fchmod|fchmodat
>>      chmod_common
>>       notify_change
>>        ocfs2_setattr <=== take EX
>>         posix_acl_chmod
>>          get_acl
>>           ocfs2_iop_get_acl <=== take PR
>>          ocfs2_iop_set_acl <=== take EX
>>
>> Fixes them by adding the tracking logic (in the previous patch) for
>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>> ocfs2_setattr().
> As described cases above, shall we just add the tracking logic only for set/get_acl()?

The idea is to detect recursive locking on the running task stack. Take case 1) for example 
if ocfs2_permisssion()
is not changed:

ocfs2_permission() <=== take PR, ocfs2_holder is not added
    ocfs2_iop_get_acl <=== still take PR, because there is no lock holder on the tracking list

Thanks for your review;-)
Eric

>
> Thanks,
> Joseph
>>
>> Signed-off-by: Eric Ren <[e-mail]>
>> ---
>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>
>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>> index bed1fcb..c539890 100644
>> --- a/fs/ocfs2/acl.c
>> +++ b/fs/ocfs2/acl.c
>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, 
>> int type)
>>   {
>>       struct buffer_head *bh = NULL;
>>       int status = 0;
>> -
>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>> +    int arg_flags = 0, has_locked;
>> +    struct ocfs2_holder oh;
>> +    struct ocfs2_lock_res *lockres;
>> +
>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>> +    if (has_locked)
>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>       if (status < 0) {
>>           if (status != -ENOENT)
>>               mlog_errno(status);
>>           return status;
>>       }
>> +    if (!has_locked)
>> +        ocfs2_add_holder(lockres, &oh);
>> +
>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>> -    ocfs2_inode_unlock(inode, 1);
>> +
>> +    if (!has_locked) {
>> +        ocfs2_remove_holder(lockres, &oh);
>> +        ocfs2_inode_unlock(inode, 1);
>> +    }
>>       brelse(bh);
>> +
>>       return status;
>>   }
>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
>>       struct buffer_head *di_bh = NULL;
>>       struct posix_acl *acl;
>>       int ret;
>> +    int arg_flags = 0, has_locked;
>> +    struct ocfs2_holder oh;
>> +    struct ocfs2_lock_res *lockres;
>>         osb = OCFS2_SB(inode->i_sb);
>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>           return NULL;
>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>> +
>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>> +    if (has_locked)
>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>       if (ret < 0) {
>>           if (ret != -ENOENT)
>>               mlog_errno(ret);
>>           return ERR_PTR(ret);
>>       }
>> +    if (!has_locked)
>> +        ocfs2_add_holder(lockres, &oh);
>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>   -    ocfs2_inode_unlock(inode, 0);
>> +    if (!has_locked) {
>> +        ocfs2_remove_holder(lockres, &oh);
>> +        ocfs2_inode_unlock(inode, 0);
>> +    }
>>       brelse(di_bh);
>> +
>>       return acl;
>>   }
>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>> index c488965..62be75d 100644
>> --- a/fs/ocfs2/file.c
>> +++ b/fs/ocfs2/file.c
>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>       handle_t *handle = NULL;
>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>       int qtype;
>> +    int arg_flags = 0, had_lock;
>> +    struct ocfs2_holder oh;
>> +    struct ocfs2_lock_res *lockres;
>>         trace_ocfs2_setattr(inode, dentry,
>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>           }
>>       }
>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>> +    if (had_lock)
>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>       if (status < 0) {
>>           if (status != -ENOENT)
>>               mlog_errno(status);
>>           goto bail_unlock_rw;
>>       }
>> -    inode_locked = 1;
>> +    if (!had_lock) {
>> +        ocfs2_add_holder(lockres, &oh);
>> +        inode_locked = 1;
>> +    }
>>         if (size_change) {
>>           status = inode_newsize_ok(inode, attr->ia_size);
>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>   bail_commit:
>>       ocfs2_commit_trans(osb, handle);
>>   bail_unlock:
>> -    if (status) {
>> +    if (status && inode_locked) {
>> +        ocfs2_remove_holder(lockres, &oh);
>>           ocfs2_inode_unlock(inode, 1);
>>           inode_locked = 0;
>>       }
>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>           if (status < 0)
>>               mlog_errno(status);
>>       }
>> -    if (inode_locked)
>> +    if (inode_locked) {
>> +        ocfs2_remove_holder(lockres, &oh);
>>           ocfs2_inode_unlock(inode, 1);
>> +    }
>>         brelse(bh);
>>       return status;
>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>   int ocfs2_permission(struct inode *inode, int mask)
>>   {
>>       int ret;
>> +    int has_locked;
>> +    struct ocfs2_holder oh;
>> +    struct ocfs2_lock_res *lockres;
>>         if (mask & MAY_NOT_BLOCK)
>>           return -ECHILD;
>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>> -    if (ret) {
>> -        if (ret != -ENOENT)
>> -            mlog_errno(ret);
>> -        goto out;
>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>> +    if (!has_locked) {
>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>> +        if (ret) {
>> +            if (ret != -ENOENT)
>> +                mlog_errno(ret);
>> +            goto out;
>> +        }
>> +        ocfs2_add_holder(lockres, &oh);
>>       }
>>         ret = generic_permission(inode, mask);
>>   -    ocfs2_inode_unlock(inode, 0);
>> +    if (!has_locked) {
>> +        ocfs2_remove_holder(lockres, &oh);
>> +        ocfs2_inode_unlock(inode, 0);
>> +    }
>>   out:
>>       return ret;
>>   }
>
>

Joseph Qi Jan. 6, 2017, 7:14 a.m. UTC | #3

On 17/1/6 14:56, Eric Ren wrote:
> On 01/06/2017 02:09 PM, Joseph Qi wrote:
>> Hi Eric,
>>
>>
>> On 17/1/5 23:31, Eric Ren wrote:
>>> Commit 743b5f1434f5 ("ocfs2: take inode lock in 
>>> ocfs2_iop_set/get_acl()")
>>> results in a deadlock, as the author "Tariq Saeed" realized shortly
>>> after the patch was merged. The discussion happened here
>>> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html). 
>>>
>>>
>>> The reason why taking cluster inode lock at vfs entry points opens up
>>> a self deadlock window, is explained in the previous patch of this
>>> series.
>>>
>>> So far, we have seen two different code paths that have this issue.
>>> 1. do_sys_open
>>>       may_open
>>>        inode_permission
>>>         ocfs2_permission
>>>          ocfs2_inode_lock() <=== take PR
>>>           generic_permission
>>>            get_acl
>>>             ocfs2_iop_get_acl
>>>              ocfs2_inode_lock() <=== take PR
>>> 2. fchmod|fchmodat
>>>      chmod_common
>>>       notify_change
>>>        ocfs2_setattr <=== take EX
>>>         posix_acl_chmod
>>>          get_acl
>>>           ocfs2_iop_get_acl <=== take PR
>>>          ocfs2_iop_set_acl <=== take EX
>>>
>>> Fixes them by adding the tracking logic (in the previous patch) for
>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>> ocfs2_setattr().
>> As described cases above, shall we just add the tracking logic only 
>> for set/get_acl()?
>
> The idea is to detect recursive locking on the running task stack. 
> Take case 1) for example if ocfs2_permisssion()
> is not changed:
>
> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>    ocfs2_iop_get_acl <=== still take PR, because there is no lock 
> holder on the tracking list
I mean we have no need to check if locked by me, just do inode lock and 
add holder.
This will make code more clean, IMO.

Thanks,
Joseph
>
> Thanks for your review;-)
> Eric
>
>>
>> Thanks,
>> Joseph
>>>
>>> Signed-off-by: Eric Ren <[e-mail]>
>>> ---
>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>
>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>> index bed1fcb..c539890 100644
>>> --- a/fs/ocfs2/acl.c
>>> +++ b/fs/ocfs2/acl.c
>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, 
>>> struct posix_acl *acl, int type)
>>>   {
>>>       struct buffer_head *bh = NULL;
>>>       int status = 0;
>>> -
>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>> +    int arg_flags = 0, has_locked;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>> +
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> +    if (has_locked)
>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>       if (status < 0) {
>>>           if (status != -ENOENT)
>>>               mlog_errno(status);
>>>           return status;
>>>       }
>>> +    if (!has_locked)
>>> +        ocfs2_add_holder(lockres, &oh);
>>> +
>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>> -    ocfs2_inode_unlock(inode, 1);
>>> +
>>> +    if (!has_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>> +        ocfs2_inode_unlock(inode, 1);
>>> +    }
>>>       brelse(bh);
>>> +
>>>       return status;
>>>   }
>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct 
>>> inode *inode, int type)
>>>       struct buffer_head *di_bh = NULL;
>>>       struct posix_acl *acl;
>>>       int ret;
>>> +    int arg_flags = 0, has_locked;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>>         osb = OCFS2_SB(inode->i_sb);
>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>           return NULL;
>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>> +
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> +    if (has_locked)
>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>       if (ret < 0) {
>>>           if (ret != -ENOENT)
>>>               mlog_errno(ret);
>>>           return ERR_PTR(ret);
>>>       }
>>> +    if (!has_locked)
>>> +        ocfs2_add_holder(lockres, &oh);
>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>   -    ocfs2_inode_unlock(inode, 0);
>>> +    if (!has_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>> +        ocfs2_inode_unlock(inode, 0);
>>> +    }
>>>       brelse(di_bh);
>>> +
>>>       return acl;
>>>   }
>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>> index c488965..62be75d 100644
>>> --- a/fs/ocfs2/file.c
>>> +++ b/fs/ocfs2/file.c
>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, 
>>> struct iattr *attr)
>>>       handle_t *handle = NULL;
>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>       int qtype;
>>> +    int arg_flags = 0, had_lock;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>>         trace_ocfs2_setattr(inode, dentry,
>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, 
>>> struct iattr *attr)
>>>           }
>>>       }
>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> +    if (had_lock)
>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>       if (status < 0) {
>>>           if (status != -ENOENT)
>>>               mlog_errno(status);
>>>           goto bail_unlock_rw;
>>>       }
>>> -    inode_locked = 1;
>>> +    if (!had_lock) {
>>> +        ocfs2_add_holder(lockres, &oh);
>>> +        inode_locked = 1;
>>> +    }
>>>         if (size_change) {
>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, 
>>> struct iattr *attr)
>>>   bail_commit:
>>>       ocfs2_commit_trans(osb, handle);
>>>   bail_unlock:
>>> -    if (status) {
>>> +    if (status && inode_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>>           ocfs2_inode_unlock(inode, 1);
>>>           inode_locked = 0;
>>>       }
>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, 
>>> struct iattr *attr)
>>>           if (status < 0)
>>>               mlog_errno(status);
>>>       }
>>> -    if (inode_locked)
>>> +    if (inode_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>>           ocfs2_inode_unlock(inode, 1);
>>> +    }
>>>         brelse(bh);
>>>       return status;
>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>   {
>>>       int ret;
>>> +    int has_locked;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>>         if (mask & MAY_NOT_BLOCK)
>>>           return -ECHILD;
>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>> -    if (ret) {
>>> -        if (ret != -ENOENT)
>>> -            mlog_errno(ret);
>>> -        goto out;
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> +    if (!has_locked) {
>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>> +        if (ret) {
>>> +            if (ret != -ENOENT)
>>> +                mlog_errno(ret);
>>> +            goto out;
>>> +        }
>>> +        ocfs2_add_holder(lockres, &oh);
>>>       }
>>>         ret = generic_permission(inode, mask);
>>>   -    ocfs2_inode_unlock(inode, 0);
>>> +    if (!has_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>> +        ocfs2_inode_unlock(inode, 0);
>>> +    }
>>>   out:
>>>       return ret;
>>>   }
>>
>>
>

Zhen Ren Jan. 6, 2017, 8:21 a.m. UTC | #4

On 01/06/2017 03:14 PM, Joseph Qi wrote:
>
>
> On 17/1/6 14:56, Eric Ren wrote:
>> On 01/06/2017 02:09 PM, Joseph Qi wrote:
>>> Hi Eric,
>>>
>>>
>>> On 17/1/5 23:31, Eric Ren wrote:
>>>> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()")
>>>> results in a deadlock, as the author "Tariq Saeed" realized shortly
>>>> after the patch was merged. The discussion happened here
>>>> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
>>>>
>>>> The reason why taking cluster inode lock at vfs entry points opens up
>>>> a self deadlock window, is explained in the previous patch of this
>>>> series.
>>>>
>>>> So far, we have seen two different code paths that have this issue.
>>>> 1. do_sys_open
>>>>       may_open
>>>>        inode_permission
>>>>         ocfs2_permission
>>>>          ocfs2_inode_lock() <=== take PR
>>>>           generic_permission
>>>>            get_acl
>>>>             ocfs2_iop_get_acl
>>>>              ocfs2_inode_lock() <=== take PR
>>>> 2. fchmod|fchmodat
>>>>      chmod_common
>>>>       notify_change
>>>>        ocfs2_setattr <=== take EX
>>>>         posix_acl_chmod
>>>>          get_acl
>>>>           ocfs2_iop_get_acl <=== take PR
>>>>          ocfs2_iop_set_acl <=== take EX
>>>>
>>>> Fixes them by adding the tracking logic (in the previous patch) for
>>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>>> ocfs2_setattr().
>>> As described cases above, shall we just add the tracking logic only for set/get_acl()?
>>
>> The idea is to detect recursive locking on the running task stack. Take case 1) for 
>> example if ocfs2_permisssion()
>> is not changed:
>>
>> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>>    ocfs2_iop_get_acl <=== still take PR, because there is no lock holder on the tracking 
>> list
> I mean we have no need to check if locked by me, just do inode lock and add holder.
> This will make code more clean, IMO.
Oh, sorry, I get your point this time. I think we need to check it if there are more than 
one processes that hold
PR lock on the same resource.  If I don't understand you correctly, please tell me why you 
think it's not neccessary
to check before getting lock?

Thanks,
Eric
>
> Thanks,
> Joseph
>>
>> Thanks for your review;-)
>> Eric
>>
>>>
>>> Thanks,
>>> Joseph
>>>>
>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>> ---
>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>
>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>> index bed1fcb..c539890 100644
>>>> --- a/fs/ocfs2/acl.c
>>>> +++ b/fs/ocfs2/acl.c
>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, 
>>>> int type)
>>>>   {
>>>>       struct buffer_head *bh = NULL;
>>>>       int status = 0;
>>>> -
>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>> +    int arg_flags = 0, has_locked;
>>>> +    struct ocfs2_holder oh;
>>>> +    struct ocfs2_lock_res *lockres;
>>>> +
>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>> +    if (has_locked)
>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>       if (status < 0) {
>>>>           if (status != -ENOENT)
>>>>               mlog_errno(status);
>>>>           return status;
>>>>       }
>>>> +    if (!has_locked)
>>>> +        ocfs2_add_holder(lockres, &oh);
>>>> +
>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>>> -    ocfs2_inode_unlock(inode, 1);
>>>> +
>>>> +    if (!has_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>> +        ocfs2_inode_unlock(inode, 1);
>>>> +    }
>>>>       brelse(bh);
>>>> +
>>>>       return status;
>>>>   }
>>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
>>>>       struct buffer_head *di_bh = NULL;
>>>>       struct posix_acl *acl;
>>>>       int ret;
>>>> +    int arg_flags = 0, has_locked;
>>>> +    struct ocfs2_holder oh;
>>>> +    struct ocfs2_lock_res *lockres;
>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>           return NULL;
>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>> +
>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>> +    if (has_locked)
>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>       if (ret < 0) {
>>>>           if (ret != -ENOENT)
>>>>               mlog_errno(ret);
>>>>           return ERR_PTR(ret);
>>>>       }
>>>> +    if (!has_locked)
>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>> +    if (!has_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>> +        ocfs2_inode_unlock(inode, 0);
>>>> +    }
>>>>       brelse(di_bh);
>>>> +
>>>>       return acl;
>>>>   }
>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>> index c488965..62be75d 100644
>>>> --- a/fs/ocfs2/file.c
>>>> +++ b/fs/ocfs2/file.c
>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>       handle_t *handle = NULL;
>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>       int qtype;
>>>> +    int arg_flags = 0, had_lock;
>>>> +    struct ocfs2_holder oh;
>>>> +    struct ocfs2_lock_res *lockres;
>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>           }
>>>>       }
>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>> +    if (had_lock)
>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>       if (status < 0) {
>>>>           if (status != -ENOENT)
>>>>               mlog_errno(status);
>>>>           goto bail_unlock_rw;
>>>>       }
>>>> -    inode_locked = 1;
>>>> +    if (!had_lock) {
>>>> +        ocfs2_add_holder(lockres, &oh);
>>>> +        inode_locked = 1;
>>>> +    }
>>>>         if (size_change) {
>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>   bail_commit:
>>>>       ocfs2_commit_trans(osb, handle);
>>>>   bail_unlock:
>>>> -    if (status) {
>>>> +    if (status && inode_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>           ocfs2_inode_unlock(inode, 1);
>>>>           inode_locked = 0;
>>>>       }
>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>           if (status < 0)
>>>>               mlog_errno(status);
>>>>       }
>>>> -    if (inode_locked)
>>>> +    if (inode_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>           ocfs2_inode_unlock(inode, 1);
>>>> +    }
>>>>         brelse(bh);
>>>>       return status;
>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>   {
>>>>       int ret;
>>>> +    int has_locked;
>>>> +    struct ocfs2_holder oh;
>>>> +    struct ocfs2_lock_res *lockres;
>>>>         if (mask & MAY_NOT_BLOCK)
>>>>           return -ECHILD;
>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>> -    if (ret) {
>>>> -        if (ret != -ENOENT)
>>>> -            mlog_errno(ret);
>>>> -        goto out;
>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>> +    if (!has_locked) {
>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>> +        if (ret) {
>>>> +            if (ret != -ENOENT)
>>>> +                mlog_errno(ret);
>>>> +            goto out;
>>>> +        }
>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>       }
>>>>         ret = generic_permission(inode, mask);
>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>> +    if (!has_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>> +        ocfs2_inode_unlock(inode, 0);
>>>> +    }
>>>>   out:
>>>>       return ret;
>>>>   }
>>>
>>>
>>
>
>

Joseph Qi Jan. 6, 2017, 9:03 a.m. UTC | #5

On 17/1/6 16:21, Eric Ren wrote:
> On 01/06/2017 03:14 PM, Joseph Qi wrote:
>>
>>
>> On 17/1/6 14:56, Eric Ren wrote:
>>> On 01/06/2017 02:09 PM, Joseph Qi wrote:
>>>> Hi Eric,
>>>>
>>>>
>>>> On 17/1/5 23:31, Eric Ren wrote:
>>>>> Commit 743b5f1434f5 ("ocfs2: take inode lock in 
>>>>> ocfs2_iop_set/get_acl()")
>>>>> results in a deadlock, as the author "Tariq Saeed" realized shortly
>>>>> after the patch was merged. The discussion happened here
>>>>> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html). 
>>>>>
>>>>>
>>>>> The reason why taking cluster inode lock at vfs entry points opens up
>>>>> a self deadlock window, is explained in the previous patch of this
>>>>> series.
>>>>>
>>>>> So far, we have seen two different code paths that have this issue.
>>>>> 1. do_sys_open
>>>>>       may_open
>>>>>        inode_permission
>>>>>         ocfs2_permission
>>>>>          ocfs2_inode_lock() <=== take PR
>>>>>           generic_permission
>>>>>            get_acl
>>>>>             ocfs2_iop_get_acl
>>>>>              ocfs2_inode_lock() <=== take PR
>>>>> 2. fchmod|fchmodat
>>>>>      chmod_common
>>>>>       notify_change
>>>>>        ocfs2_setattr <=== take EX
>>>>>         posix_acl_chmod
>>>>>          get_acl
>>>>>           ocfs2_iop_get_acl <=== take PR
>>>>>          ocfs2_iop_set_acl <=== take EX
>>>>>
>>>>> Fixes them by adding the tracking logic (in the previous patch) for
>>>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>>>> ocfs2_setattr().
>>>> As described cases above, shall we just add the tracking logic only 
>>>> for set/get_acl()?
>>>
>>> The idea is to detect recursive locking on the running task stack. 
>>> Take case 1) for example if ocfs2_permisssion()
>>> is not changed:
>>>
>>> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>>>    ocfs2_iop_get_acl <=== still take PR, because there is no lock 
>>> holder on the tracking list
>> I mean we have no need to check if locked by me, just do inode lock 
>> and add holder.
>> This will make code more clean, IMO.
> Oh, sorry, I get your point this time. I think we need to check it if 
> there are more than one processes that hold
> PR lock on the same resource.  If I don't understand you correctly, 
> please tell me why you think it's not neccessary
> to check before getting lock?
The code logic can only check if it is locked by myself. In the case
described above, ocfs2_permission is the first entry to take inode lock.
And even if check succeeds, it is a bug without unlock, but not the case
of recursive lock.

Thanks,
Joseph
>
> Thanks,
> Eric
>>
>> Thanks,
>> Joseph
>>>
>>> Thanks for your review;-)
>>> Eric
>>>
>>>>
>>>> Thanks,
>>>> Joseph
>>>>>
>>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>>> ---
>>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>>
>>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>>> index bed1fcb..c539890 100644
>>>>> --- a/fs/ocfs2/acl.c
>>>>> +++ b/fs/ocfs2/acl.c
>>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, 
>>>>> struct posix_acl *acl, int type)
>>>>>   {
>>>>>       struct buffer_head *bh = NULL;
>>>>>       int status = 0;
>>>>> -
>>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>> +    int arg_flags = 0, has_locked;
>>>>> +    struct ocfs2_holder oh;
>>>>> +    struct ocfs2_lock_res *lockres;
>>>>> +
>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>> +    if (has_locked)
>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>       if (status < 0) {
>>>>>           if (status != -ENOENT)
>>>>>               mlog_errno(status);
>>>>>           return status;
>>>>>       }
>>>>> +    if (!has_locked)
>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>> +
>>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>>>> -    ocfs2_inode_unlock(inode, 1);
>>>>> +
>>>>> +    if (!has_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>> +        ocfs2_inode_unlock(inode, 1);
>>>>> +    }
>>>>>       brelse(bh);
>>>>> +
>>>>>       return status;
>>>>>   }
>>>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct 
>>>>> inode *inode, int type)
>>>>>       struct buffer_head *di_bh = NULL;
>>>>>       struct posix_acl *acl;
>>>>>       int ret;
>>>>> +    int arg_flags = 0, has_locked;
>>>>> +    struct ocfs2_holder oh;
>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>>           return NULL;
>>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>>> +
>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>> +    if (has_locked)
>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>>       if (ret < 0) {
>>>>>           if (ret != -ENOENT)
>>>>>               mlog_errno(ret);
>>>>>           return ERR_PTR(ret);
>>>>>       }
>>>>> +    if (!has_locked)
>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>> +    if (!has_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>> +    }
>>>>>       brelse(di_bh);
>>>>> +
>>>>>       return acl;
>>>>>   }
>>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>>> index c488965..62be75d 100644
>>>>> --- a/fs/ocfs2/file.c
>>>>> +++ b/fs/ocfs2/file.c
>>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>> struct iattr *attr)
>>>>>       handle_t *handle = NULL;
>>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>>       int qtype;
>>>>> +    int arg_flags = 0, had_lock;
>>>>> +    struct ocfs2_holder oh;
>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>> struct iattr *attr)
>>>>>           }
>>>>>       }
>>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>> +    if (had_lock)
>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>       if (status < 0) {
>>>>>           if (status != -ENOENT)
>>>>>               mlog_errno(status);
>>>>>           goto bail_unlock_rw;
>>>>>       }
>>>>> -    inode_locked = 1;
>>>>> +    if (!had_lock) {
>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>> +        inode_locked = 1;
>>>>> +    }
>>>>>         if (size_change) {
>>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>> struct iattr *attr)
>>>>>   bail_commit:
>>>>>       ocfs2_commit_trans(osb, handle);
>>>>>   bail_unlock:
>>>>> -    if (status) {
>>>>> +    if (status && inode_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>           inode_locked = 0;
>>>>>       }
>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>> struct iattr *attr)
>>>>>           if (status < 0)
>>>>>               mlog_errno(status);
>>>>>       }
>>>>> -    if (inode_locked)
>>>>> +    if (inode_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>> +    }
>>>>>         brelse(bh);
>>>>>       return status;
>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>>   {
>>>>>       int ret;
>>>>> +    int has_locked;
>>>>> +    struct ocfs2_holder oh;
>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>         if (mask & MAY_NOT_BLOCK)
>>>>>           return -ECHILD;
>>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>> -    if (ret) {
>>>>> -        if (ret != -ENOENT)
>>>>> -            mlog_errno(ret);
>>>>> -        goto out;
>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>> +    if (!has_locked) {
>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>> +        if (ret) {
>>>>> +            if (ret != -ENOENT)
>>>>> +                mlog_errno(ret);
>>>>> +            goto out;
>>>>> +        }
>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>       }
>>>>>         ret = generic_permission(inode, mask);
>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>> +    if (!has_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>> +    }
>>>>>   out:
>>>>>       return ret;
>>>>>   }
>>>>
>>>>
>>>
>>
>>
>

Zhen Ren Jan. 6, 2017, 9:13 a.m. UTC | #6

Hi,

>>>>>>
>>>>>> Fixes them by adding the tracking logic (in the previous patch) for
>>>>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>>>>> ocfs2_setattr().
>>>>> As described cases above, shall we just add the tracking logic only for set/get_acl()?
>>>>
>>>> The idea is to detect recursive locking on the running task stack. Take case 1) for 
>>>> example if ocfs2_permisssion()
>>>> is not changed:
>>>>
>>>> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>>>>    ocfs2_iop_get_acl <=== still take PR, because there is no lock holder on the 
>>>> tracking list
>>> I mean we have no need to check if locked by me, just do inode lock and add holder.
>>> This will make code more clean, IMO.
>> Oh, sorry, I get your point this time. I think we need to check it if there are more than 
>> one processes that hold
>> PR lock on the same resource.  If I don't understand you correctly, please tell me why 
>> you think it's not neccessary
>> to check before getting lock?
> The code logic can only check if it is locked by myself. In the case
Why only...?
> described above, ocfs2_permission is the first entry to take inode lock.
> And even if check succeeds, it is a bug without unlock, but not the case
> of recursive lock.

By checking succeeds, you mean it's locked by me, right? If so, this flag
                       "arg_flags = OCFS2_META_LOCK_GETBH"
will be passed down to ocfs2_inode_lock_full(), which gets back buffer head of
the disk inode for us if necessary, but doesn't take cluster locking again. So, there is
no need to unlock in such case.

Thanks,
Eric

>
> Thanks,
> Joseph
>>
>> Thanks,
>> Eric
>>>
>>> Thanks,
>>> Joseph
>>>>
>>>> Thanks for your review;-)
>>>> Eric
>>>>
>>>>>
>>>>> Thanks,
>>>>> Joseph
>>>>>>
>>>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>>>> ---
>>>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>>>
>>>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>>>> index bed1fcb..c539890 100644
>>>>>> --- a/fs/ocfs2/acl.c
>>>>>> +++ b/fs/ocfs2/acl.c
>>>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl 
>>>>>> *acl, int type)
>>>>>>   {
>>>>>>       struct buffer_head *bh = NULL;
>>>>>>       int status = 0;
>>>>>> -
>>>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>> +    int arg_flags = 0, has_locked;
>>>>>> +    struct ocfs2_holder oh;
>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>> +
>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>> +    if (has_locked)
>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>       if (status < 0) {
>>>>>>           if (status != -ENOENT)
>>>>>>               mlog_errno(status);
>>>>>>           return status;
>>>>>>       }
>>>>>> +    if (!has_locked)
>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>> +
>>>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>>>>> -    ocfs2_inode_unlock(inode, 1);
>>>>>> +
>>>>>> +    if (!has_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>> +        ocfs2_inode_unlock(inode, 1);
>>>>>> +    }
>>>>>>       brelse(bh);
>>>>>> +
>>>>>>       return status;
>>>>>>   }
>>>>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int 
>>>>>> type)
>>>>>>       struct buffer_head *di_bh = NULL;
>>>>>>       struct posix_acl *acl;
>>>>>>       int ret;
>>>>>> +    int arg_flags = 0, has_locked;
>>>>>> +    struct ocfs2_holder oh;
>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>>>           return NULL;
>>>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>>>> +
>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>> +    if (has_locked)
>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>>>       if (ret < 0) {
>>>>>>           if (ret != -ENOENT)
>>>>>>               mlog_errno(ret);
>>>>>>           return ERR_PTR(ret);
>>>>>>       }
>>>>>> +    if (!has_locked)
>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>> +    if (!has_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>> +    }
>>>>>>       brelse(di_bh);
>>>>>> +
>>>>>>       return acl;
>>>>>>   }
>>>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>>>> index c488965..62be75d 100644
>>>>>> --- a/fs/ocfs2/file.c
>>>>>> +++ b/fs/ocfs2/file.c
>>>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>       handle_t *handle = NULL;
>>>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>>>       int qtype;
>>>>>> +    int arg_flags = 0, had_lock;
>>>>>> +    struct ocfs2_holder oh;
>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>           }
>>>>>>       }
>>>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>> +    if (had_lock)
>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>       if (status < 0) {
>>>>>>           if (status != -ENOENT)
>>>>>>               mlog_errno(status);
>>>>>>           goto bail_unlock_rw;
>>>>>>       }
>>>>>> -    inode_locked = 1;
>>>>>> +    if (!had_lock) {
>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>> +        inode_locked = 1;
>>>>>> +    }
>>>>>>         if (size_change) {
>>>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>   bail_commit:
>>>>>>       ocfs2_commit_trans(osb, handle);
>>>>>>   bail_unlock:
>>>>>> -    if (status) {
>>>>>> +    if (status && inode_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>           inode_locked = 0;
>>>>>>       }
>>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>           if (status < 0)
>>>>>>               mlog_errno(status);
>>>>>>       }
>>>>>> -    if (inode_locked)
>>>>>> +    if (inode_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>> +    }
>>>>>>         brelse(bh);
>>>>>>       return status;
>>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>>>   {
>>>>>>       int ret;
>>>>>> +    int has_locked;
>>>>>> +    struct ocfs2_holder oh;
>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>         if (mask & MAY_NOT_BLOCK)
>>>>>>           return -ECHILD;
>>>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>> -    if (ret) {
>>>>>> -        if (ret != -ENOENT)
>>>>>> -            mlog_errno(ret);
>>>>>> -        goto out;
>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>> +    if (!has_locked) {
>>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>> +        if (ret) {
>>>>>> +            if (ret != -ENOENT)
>>>>>> +                mlog_errno(ret);
>>>>>> +            goto out;
>>>>>> +        }
>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>       }
>>>>>>         ret = generic_permission(inode, mask);
>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>> +    if (!has_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>> +    }
>>>>>>   out:
>>>>>>       return ret;
>>>>>>   }
>>>>>
>>>>>
>>>>
>>>
>>>
>>
>
>

Joseph Qi Jan. 6, 2017, 9:55 a.m. UTC | #7

On 17/1/6 17:13, Eric Ren wrote:
> Hi,
>
>>>>>>>
>>>>>>> Fixes them by adding the tracking logic (in the previous patch) for
>>>>>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>>>>>> ocfs2_setattr().
>>>>>> As described cases above, shall we just add the tracking logic 
>>>>>> only for set/get_acl()?
>>>>>
>>>>> The idea is to detect recursive locking on the running task stack. 
>>>>> Take case 1) for example if ocfs2_permisssion()
>>>>> is not changed:
>>>>>
>>>>> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>>>>>    ocfs2_iop_get_acl <=== still take PR, because there is no lock 
>>>>> holder on the tracking list
>>>> I mean we have no need to check if locked by me, just do inode lock 
>>>> and add holder.
>>>> This will make code more clean, IMO.
>>> Oh, sorry, I get your point this time. I think we need to check it 
>>> if there are more than one processes that hold
>>> PR lock on the same resource.  If I don't understand you correctly, 
>>> please tell me why you think it's not neccessary
>>> to check before getting lock?
>> The code logic can only check if it is locked by myself. In the case
> Why only...?
>> described above, ocfs2_permission is the first entry to take inode lock.
>> And even if check succeeds, it is a bug without unlock, but not the case
>> of recursive lock.
>
> By checking succeeds, you mean it's locked by me, right? If so, this flag
>                       "arg_flags = OCFS2_META_LOCK_GETBH"
> will be passed down to ocfs2_inode_lock_full(), which gets back buffer 
> head of
> the disk inode for us if necessary, but doesn't take cluster locking 
> again. So, there is
> no need to unlock in such case.
I am trying to state my point more clearly...
The issue case you are trying to fix is:
Process A
take inode lock (phase1)
...
<<< race window (phase2, Process B)
...
take inode lock again (phase3)

Deadlock happens because Process B in phase2 and Process A in phase3
are waiting for each other.
So you are trying to fix it by making phase3 finish without really doing
__ocfs2_cluster_lock, then Process B can continue either.
Let us bear in mind that phase1 and phase3 are in the same context and
executed in order. That's why I think there is no need to check if locked
by myself in phase1.
If phase1 finds it is already locked by myself, that means the holder
is left by last operation without dec holder. That's why I think it is a bug
instead of a recursive lock case.

Thanks,
Joseph
>
> Thanks,
> Eric
>
>>
>> Thanks,
>> Joseph
>>>
>>> Thanks,
>>> Eric
>>>>
>>>> Thanks,
>>>> Joseph
>>>>>
>>>>> Thanks for your review;-)
>>>>> Eric
>>>>>
>>>>>>
>>>>>> Thanks,
>>>>>> Joseph
>>>>>>>
>>>>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>>>>> ---
>>>>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>>>>
>>>>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>>>>> index bed1fcb..c539890 100644
>>>>>>> --- a/fs/ocfs2/acl.c
>>>>>>> +++ b/fs/ocfs2/acl.c
>>>>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, 
>>>>>>> struct posix_acl *acl, int type)
>>>>>>>   {
>>>>>>>       struct buffer_head *bh = NULL;
>>>>>>>       int status = 0;
>>>>>>> -
>>>>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>> +    struct ocfs2_holder oh;
>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>> +
>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>> +    if (has_locked)
>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>       if (status < 0) {
>>>>>>>           if (status != -ENOENT)
>>>>>>>               mlog_errno(status);
>>>>>>>           return status;
>>>>>>>       }
>>>>>>> +    if (!has_locked)
>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>> +
>>>>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, 
>>>>>>> NULL);
>>>>>>> -    ocfs2_inode_unlock(inode, 1);
>>>>>>> +
>>>>>>> +    if (!has_locked) {
>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>> +        ocfs2_inode_unlock(inode, 1);
>>>>>>> +    }
>>>>>>>       brelse(bh);
>>>>>>> +
>>>>>>>       return status;
>>>>>>>   }
>>>>>>>   @@ -303,21 +318,35 @@ struct posix_acl 
>>>>>>> *ocfs2_iop_get_acl(struct inode *inode, int type)
>>>>>>>       struct buffer_head *di_bh = NULL;
>>>>>>>       struct posix_acl *acl;
>>>>>>>       int ret;
>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>> +    struct ocfs2_holder oh;
>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>>>>           return NULL;
>>>>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>>>>> +
>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>> +    if (has_locked)
>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>>>>       if (ret < 0) {
>>>>>>>           if (ret != -ENOENT)
>>>>>>>               mlog_errno(ret);
>>>>>>>           return ERR_PTR(ret);
>>>>>>>       }
>>>>>>> +    if (!has_locked)
>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>> +    if (!has_locked) {
>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>> +    }
>>>>>>>       brelse(di_bh);
>>>>>>> +
>>>>>>>       return acl;
>>>>>>>   }
>>>>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>>>>> index c488965..62be75d 100644
>>>>>>> --- a/fs/ocfs2/file.c
>>>>>>> +++ b/fs/ocfs2/file.c
>>>>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>>>> struct iattr *attr)
>>>>>>>       handle_t *handle = NULL;
>>>>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>>>>       int qtype;
>>>>>>> +    int arg_flags = 0, had_lock;
>>>>>>> +    struct ocfs2_holder oh;
>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>>>> struct iattr *attr)
>>>>>>>           }
>>>>>>>       }
>>>>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>> +    if (had_lock)
>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>       if (status < 0) {
>>>>>>>           if (status != -ENOENT)
>>>>>>>               mlog_errno(status);
>>>>>>>           goto bail_unlock_rw;
>>>>>>>       }
>>>>>>> -    inode_locked = 1;
>>>>>>> +    if (!had_lock) {
>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>> +        inode_locked = 1;
>>>>>>> +    }
>>>>>>>         if (size_change) {
>>>>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>>>> struct iattr *attr)
>>>>>>>   bail_commit:
>>>>>>>       ocfs2_commit_trans(osb, handle);
>>>>>>>   bail_unlock:
>>>>>>> -    if (status) {
>>>>>>> +    if (status && inode_locked) {
>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>           inode_locked = 0;
>>>>>>>       }
>>>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>>>> struct iattr *attr)
>>>>>>>           if (status < 0)
>>>>>>>               mlog_errno(status);
>>>>>>>       }
>>>>>>> -    if (inode_locked)
>>>>>>> +    if (inode_locked) {
>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>> +    }
>>>>>>>         brelse(bh);
>>>>>>>       return status;
>>>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>>>>   {
>>>>>>>       int ret;
>>>>>>> +    int has_locked;
>>>>>>> +    struct ocfs2_holder oh;
>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>         if (mask & MAY_NOT_BLOCK)
>>>>>>>           return -ECHILD;
>>>>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>> -    if (ret) {
>>>>>>> -        if (ret != -ENOENT)
>>>>>>> -            mlog_errno(ret);
>>>>>>> -        goto out;
>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>> +    if (!has_locked) {
>>>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>> +        if (ret) {
>>>>>>> +            if (ret != -ENOENT)
>>>>>>> +                mlog_errno(ret);
>>>>>>> +            goto out;
>>>>>>> +        }
>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>       }
>>>>>>>         ret = generic_permission(inode, mask);
>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>> +    if (!has_locked) {
>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>> +    }
>>>>>>>   out:
>>>>>>>       return ret;
>>>>>>>   }
>>>>>>
>>>>>>
>>>>>
>>>>
>>>>
>>>
>>
>>
>

Zhen Ren Jan. 6, 2017, 11:56 a.m. UTC | #8

Hi!

On 01/06/2017 05:55 PM, Joseph Qi wrote:
> On 17/1/6 17:13, Eric Ren wrote:
>> Hi,
>>
>>>>>>>>
>>>>>>>> Fixes them by adding the tracking logic (in the previous patch) for
>>>>>>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>>>>>>> ocfs2_setattr().
>>>>>>> As described cases above, shall we just add the tracking logic only for set/get_acl()?
>>>>>>
>>>>>> The idea is to detect recursive locking on the running task stack. Take case 1) for 
>>>>>> example if ocfs2_permisssion()
>>>>>> is not changed:
>>>>>>
>>>>>> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>>>>>>    ocfs2_iop_get_acl <=== still take PR, because there is no lock holder on the 
>>>>>> tracking list
>>>>> I mean we have no need to check if locked by me, just do inode lock and add holder.
>>>>> This will make code more clean, IMO.
>>>> Oh, sorry, I get your point this time. I think we need to check it if there are more 
>>>> than one processes that hold
>>>> PR lock on the same resource.  If I don't understand you correctly, please tell me why 
>>>> you think it's not neccessary
>>>> to check before getting lock?
>>> The code logic can only check if it is locked by myself. In the case
>> Why only...?
>>> described above, ocfs2_permission is the first entry to take inode lock.
>>> And even if check succeeds, it is a bug without unlock, but not the case
>>> of recursive lock.
>>
>> By checking succeeds, you mean it's locked by me, right? If so, this flag
>>                       "arg_flags = OCFS2_META_LOCK_GETBH"
>> will be passed down to ocfs2_inode_lock_full(), which gets back buffer head of
>> the disk inode for us if necessary, but doesn't take cluster locking again. So, there is
>> no need to unlock in such case.
> I am trying to state my point more clearly...

Thanks a lot!

> The issue case you are trying to fix is:
> Process A
> take inode lock (phase1)
> ...
> <<< race window (phase2, Process B)

The deadlock only happens if process B is on a remote node and request EX lock.

Quote the patch[1/2]'s commit message:

A deadlock will occur if a remote EX request comes in between two of
ocfs2_inode_lock().  Briefly describe how the deadlock is formed:

On one hand, OCFS2_LOCK_BLOCKED flag of this lockres is set in
BAST(ocfs2_generic_handle_bast) when downconvert is started on behalf of
the remote EX lock request.  Another hand, the recursive cluster lock (the
second one) will be blocked in in __ocfs2_cluster_lock() because of
OCFS2_LOCK_BLOCKED.  But, the downconvert never complete, why?  because
there is no chance for the first cluster lock on this node to be unlocked
- we block ourselves in the code path.
---

> ...
> take inode lock again (phase3)
>
> Deadlock happens because Process B in phase2 and Process A in phase3
> are waiting for each other.
It's local lock's (like i_mutex) responsibility to protect critical section from racing
among processes on the same node.

> So you are trying to fix it by making phase3 finish without really doing

Phase3 can go ahead because this node is already under protection of cluster lock.

> __ocfs2_cluster_lock, then Process B can continue either.
> Let us bear in mind that phase1 and phase3 are in the same context and
> executed in order. That's why I think there is no need to check if locked
> by myself in phase1.
> If phase1 finds it is already locked by myself, that means the holder
> is left by last operation without dec holder. That's why I think it is a bug
> instead of a recursive lock case.

Did I answer your question?

Thanks!
Eric

>
> Thanks,
> Joseph
>>
>> Thanks,
>> Eric
>>
>>>
>>> Thanks,
>>> Joseph
>>>>
>>>> Thanks,
>>>> Eric
>>>>>
>>>>> Thanks,
>>>>> Joseph
>>>>>>
>>>>>> Thanks for your review;-)
>>>>>> Eric
>>>>>>
>>>>>>>
>>>>>>> Thanks,
>>>>>>> Joseph
>>>>>>>>
>>>>>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>>>>>> ---
>>>>>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>>>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>>>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>>>>>
>>>>>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>>>>>> index bed1fcb..c539890 100644
>>>>>>>> --- a/fs/ocfs2/acl.c
>>>>>>>> +++ b/fs/ocfs2/acl.c
>>>>>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl 
>>>>>>>> *acl, int type)
>>>>>>>>   {
>>>>>>>>       struct buffer_head *bh = NULL;
>>>>>>>>       int status = 0;
>>>>>>>> -
>>>>>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>> +
>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>> +    if (has_locked)
>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>>       if (status < 0) {
>>>>>>>>           if (status != -ENOENT)
>>>>>>>>               mlog_errno(status);
>>>>>>>>           return status;
>>>>>>>>       }
>>>>>>>> +    if (!has_locked)
>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>> +
>>>>>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>>>>>>> -    ocfs2_inode_unlock(inode, 1);
>>>>>>>> +
>>>>>>>> +    if (!has_locked) {
>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>> +        ocfs2_inode_unlock(inode, 1);
>>>>>>>> +    }
>>>>>>>>       brelse(bh);
>>>>>>>> +
>>>>>>>>       return status;
>>>>>>>>   }
>>>>>>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, 
>>>>>>>> int type)
>>>>>>>>       struct buffer_head *di_bh = NULL;
>>>>>>>>       struct posix_acl *acl;
>>>>>>>>       int ret;
>>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>>>>>           return NULL;
>>>>>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>>>>>> +
>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>> +    if (has_locked)
>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>>>>>       if (ret < 0) {
>>>>>>>>           if (ret != -ENOENT)
>>>>>>>>               mlog_errno(ret);
>>>>>>>>           return ERR_PTR(ret);
>>>>>>>>       }
>>>>>>>> +    if (!has_locked)
>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>>> +    if (!has_locked) {
>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>>> +    }
>>>>>>>>       brelse(di_bh);
>>>>>>>> +
>>>>>>>>       return acl;
>>>>>>>>   }
>>>>>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>>>>>> index c488965..62be75d 100644
>>>>>>>> --- a/fs/ocfs2/file.c
>>>>>>>> +++ b/fs/ocfs2/file.c
>>>>>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>       handle_t *handle = NULL;
>>>>>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>>>>>       int qtype;
>>>>>>>> +    int arg_flags = 0, had_lock;
>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>>>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>           }
>>>>>>>>       }
>>>>>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>> +    if (had_lock)
>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>>       if (status < 0) {
>>>>>>>>           if (status != -ENOENT)
>>>>>>>>               mlog_errno(status);
>>>>>>>>           goto bail_unlock_rw;
>>>>>>>>       }
>>>>>>>> -    inode_locked = 1;
>>>>>>>> +    if (!had_lock) {
>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>> +        inode_locked = 1;
>>>>>>>> +    }
>>>>>>>>         if (size_change) {
>>>>>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>   bail_commit:
>>>>>>>>       ocfs2_commit_trans(osb, handle);
>>>>>>>>   bail_unlock:
>>>>>>>> -    if (status) {
>>>>>>>> +    if (status && inode_locked) {
>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>>           inode_locked = 0;
>>>>>>>>       }
>>>>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>           if (status < 0)
>>>>>>>>               mlog_errno(status);
>>>>>>>>       }
>>>>>>>> -    if (inode_locked)
>>>>>>>> +    if (inode_locked) {
>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>> +    }
>>>>>>>>         brelse(bh);
>>>>>>>>       return status;
>>>>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>>>>>   {
>>>>>>>>       int ret;
>>>>>>>> +    int has_locked;
>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>         if (mask & MAY_NOT_BLOCK)
>>>>>>>>           return -ECHILD;
>>>>>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>>> -    if (ret) {
>>>>>>>> -        if (ret != -ENOENT)
>>>>>>>> -            mlog_errno(ret);
>>>>>>>> -        goto out;
>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>> +    if (!has_locked) {
>>>>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>>> +        if (ret) {
>>>>>>>> +            if (ret != -ENOENT)
>>>>>>>> +                mlog_errno(ret);
>>>>>>>> +            goto out;
>>>>>>>> +        }
>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>       }
>>>>>>>>         ret = generic_permission(inode, mask);
>>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>>> +    if (!has_locked) {
>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>>> +    }
>>>>>>>>   out:
>>>>>>>>       return ret;
>>>>>>>>   }
>>>>>>>
>>>>>>>
>>>>>>
>>>>>
>>>>>
>>>>
>>>
>>>
>>
>
>

kernel test robot Jan. 6, 2017, 2:52 p.m. UTC | #9

Hi Eric,

[auto build test ERROR on linus/master]
[also build test ERROR on v4.10-rc2 next-20170106]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Eric-Ren/fix-deadlock-caused-by-recursive-cluster-locking/20170106-200837
config: ia64-allyesconfig (attached as .config)
compiler: ia64-linux-gcc (GCC) 6.2.0
reproduce:
        wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=ia64 

All errors (new ones prefixed by >>):

   In file included from fs/ocfs2/acl.c:31:0:
   fs/ocfs2/acl.c: In function 'ocfs2_iop_set_acl':
>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
    inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
                                ^~~~~~~~~~~~~~~~~~~~~
   fs/ocfs2/acl.c:292:16: note: called from here
     has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   In file included from fs/ocfs2/acl.c:31:0:
>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
    inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
                                ^~~~~~~~~~~~~~~~~~~~~
   fs/ocfs2/acl.c:292:16: note: called from here
     has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   In file included from fs/ocfs2/acl.c:31:0:
>> fs/ocfs2/dlmglue.h:185:13: error: inlining failed in call to always_inline 'ocfs2_add_holder': function body not available
    inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
                ^~~~~~~~~~~~~~~~
   fs/ocfs2/acl.c:302:3: note: called from here
      ocfs2_add_holder(lockres, &oh);
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   In file included from fs/ocfs2/acl.c:31:0:
>> fs/ocfs2/dlmglue.h:187:13: error: inlining failed in call to always_inline 'ocfs2_remove_holder': function body not available
    inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
                ^~~~~~~~~~~~~~~~~~~
   fs/ocfs2/acl.c:307:3: note: called from here
      ocfs2_remove_holder(lockres, &oh);
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
--
   In file included from arch/ia64/include/uapi/asm/intrinsics.h:21:0,
                    from arch/ia64/include/asm/intrinsics.h:10,
                    from arch/ia64/include/asm/bitops.h:18,
                    from include/linux/bitops.h:36,
                    from include/linux/kernel.h:10,
                    from include/linux/list.h:8,
                    from include/linux/wait.h:6,
                    from include/linux/fs.h:5,
                    from fs/ocfs2/file.c:27:
   fs/ocfs2/file.c: In function 'ocfs2_file_write_iter':
   arch/ia64/include/uapi/asm/cmpxchg.h:56:2: warning: value computed is not used [-Wunused-value]
    ((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr))))
    ~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   fs/ocfs2/file.c:2334:3: note: in expansion of macro 'xchg'
      xchg(&iocb->ki_complete, saved_ki_complete);
      ^~~~
   In file included from fs/ocfs2/file.c:49:0:
   fs/ocfs2/file.c: In function 'ocfs2_permission':
>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
    inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
                                ^~~~~~~~~~~~~~~~~~~~~
   fs/ocfs2/file.c:1345:16: note: called from here
     has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   In file included from fs/ocfs2/file.c:49:0:
>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
    inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
                                ^~~~~~~~~~~~~~~~~~~~~
   fs/ocfs2/file.c:1345:16: note: called from here
     has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   In file included from fs/ocfs2/file.c:49:0:
>> fs/ocfs2/dlmglue.h:185:13: error: inlining failed in call to always_inline 'ocfs2_add_holder': function body not available
    inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
                ^~~~~~~~~~~~~~~~
   fs/ocfs2/file.c:1353:3: note: called from here
      ocfs2_add_holder(lockres, &oh);
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   In file included from fs/ocfs2/file.c:49:0:
>> fs/ocfs2/dlmglue.h:187:13: error: inlining failed in call to always_inline 'ocfs2_remove_holder': function body not available
    inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
                ^~~~~~~~~~~~~~~~~~~
   fs/ocfs2/file.c:1359:3: note: called from here
      ocfs2_remove_holder(lockres, &oh);
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

vim +/ocfs2_is_locked_by_me +189 fs/ocfs2/dlmglue.h

63e0c48a Joel Becker 2008-01-30  179  void ocfs2_set_locking_protocol(void);
9fb5ed3a Eric Ren    2017-01-05  180  
9fb5ed3a Eric Ren    2017-01-05  181  /*
9fb5ed3a Eric Ren    2017-01-05  182   * Keep a list of processes who have interest in a lockres.
9fb5ed3a Eric Ren    2017-01-05  183   * Note: this is now only uesed for check recursive cluster lock.
9fb5ed3a Eric Ren    2017-01-05  184   */
9fb5ed3a Eric Ren    2017-01-05 @185  inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren    2017-01-05  186  			     struct ocfs2_holder *oh);
9fb5ed3a Eric Ren    2017-01-05 @187  inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren    2017-01-05  188  			     struct ocfs2_holder *oh);
9fb5ed3a Eric Ren    2017-01-05 @189  inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
9fb5ed3a Eric Ren    2017-01-05  190  
ccd979bd Mark Fasheh 2005-12-15  191  #endif	/* DLMGLUE_H */

:::::: The code at line 189 was first introduced by commit
:::::: 9fb5ed3abab2100ae8d99cee9b25fb92e3154224 ocfs2/dlmglue: prepare tracking logic to avoid recursive cluster lock

:::::: TO: Eric Ren <[e-mail]>
:::::: CC: 0day robot <[e-mail]>

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

kernel test robot Jan. 6, 2017, 5:53 p.m. UTC | #10

Hi Eric,

[auto build test WARNING on linus/master]
[also build test WARNING on v4.10-rc2 next-20170106]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Eric-Ren/fix-deadlock-caused-by-recursive-cluster-locking/20170106-200837
reproduce:
        # apt-get install sparse
        make ARCH=x86_64 allmodconfig
        make C=1 CF=-D__CHECK_ENDIAN__


sparse warnings: (new ones prefixed by >>)

   include/linux/compiler.h:253:8: sparse: attribute 'no_sanitize_address': unknown attribute
>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
--
   include/linux/compiler.h:253:8: sparse: attribute 'no_sanitize_address': unknown attribute
>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
   fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition

vim +189 fs/ocfs2/dlmglue.h

34d024f8 Mark Fasheh 2007-09-24  173  void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb);
ccd979bd Mark Fasheh 2005-12-15  174  
ccd979bd Mark Fasheh 2005-12-15  175  struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void);
ccd979bd Mark Fasheh 2005-12-15  176  void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug);
ccd979bd Mark Fasheh 2005-12-15  177  
63e0c48a Joel Becker 2008-01-30  178  /* To set the locking protocol on module initialization */
63e0c48a Joel Becker 2008-01-30  179  void ocfs2_set_locking_protocol(void);
9fb5ed3a Eric Ren    2017-01-05  180  
9fb5ed3a Eric Ren    2017-01-05  181  /*
9fb5ed3a Eric Ren    2017-01-05  182   * Keep a list of processes who have interest in a lockres.
9fb5ed3a Eric Ren    2017-01-05  183   * Note: this is now only uesed for check recursive cluster lock.
9fb5ed3a Eric Ren    2017-01-05  184   */
9fb5ed3a Eric Ren    2017-01-05  185  inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren    2017-01-05  186  			     struct ocfs2_holder *oh);
9fb5ed3a Eric Ren    2017-01-05  187  inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren    2017-01-05  188  			     struct ocfs2_holder *oh);
9fb5ed3a Eric Ren    2017-01-05 @189  inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
9fb5ed3a Eric Ren    2017-01-05  190  
ccd979bd Mark Fasheh 2005-12-15  191  #endif	/* DLMGLUE_H */

:::::: The code at line 189 was first introduced by commit
:::::: 9fb5ed3abab2100ae8d99cee9b25fb92e3154224 ocfs2/dlmglue: prepare tracking logic to avoid recursive cluster lock

:::::: TO: Eric Ren <[e-mail]>
:::::: CC: 0day robot <[e-mail]>

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

Joseph Qi Jan. 9, 2017, 1:13 a.m. UTC | #11

On 17/1/6 19:56, Eric Ren wrote:
> Hi!
>
> On 01/06/2017 05:55 PM, Joseph Qi wrote:
>> On 17/1/6 17:13, Eric Ren wrote:
>>> Hi,
>>>
>>>>>>>>>
>>>>>>>>> Fixes them by adding the tracking logic (in the previous 
>>>>>>>>> patch) for
>>>>>>>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>>>>>>>> ocfs2_setattr().
>>>>>>>> As described cases above, shall we just add the tracking logic 
>>>>>>>> only for set/get_acl()?
>>>>>>>
>>>>>>> The idea is to detect recursive locking on the running task 
>>>>>>> stack. Take case 1) for example if ocfs2_permisssion()
>>>>>>> is not changed:
>>>>>>>
>>>>>>> ocfs2_permission() <=== take PR, ocfs2_holder is not added
>>>>>>>    ocfs2_iop_get_acl <=== still take PR, because there is no 
>>>>>>> lock holder on the tracking list
>>>>>> I mean we have no need to check if locked by me, just do inode 
>>>>>> lock and add holder.
>>>>>> This will make code more clean, IMO.
>>>>> Oh, sorry, I get your point this time. I think we need to check it 
>>>>> if there are more than one processes that hold
>>>>> PR lock on the same resource.  If I don't understand you 
>>>>> correctly, please tell me why you think it's not neccessary
>>>>> to check before getting lock?
>>>> The code logic can only check if it is locked by myself. In the case
>>> Why only...?
>>>> described above, ocfs2_permission is the first entry to take inode 
>>>> lock.
>>>> And even if check succeeds, it is a bug without unlock, but not the 
>>>> case
>>>> of recursive lock.
>>>
>>> By checking succeeds, you mean it's locked by me, right? If so, this 
>>> flag
>>>                       "arg_flags = OCFS2_META_LOCK_GETBH"
>>> will be passed down to ocfs2_inode_lock_full(), which gets back 
>>> buffer head of
>>> the disk inode for us if necessary, but doesn't take cluster locking 
>>> again. So, there is
>>> no need to unlock in such case.
>> I am trying to state my point more clearly...
>
> Thanks a lot!
>
>> The issue case you are trying to fix is:
>> Process A
>> take inode lock (phase1)
>> ...
>> <<< race window (phase2, Process B)
>
> The deadlock only happens if process B is on a remote node and request 
> EX lock.
>
> Quote the patch[1/2]'s commit message:
>
> A deadlock will occur if a remote EX request comes in between two of
> ocfs2_inode_lock().  Briefly describe how the deadlock is formed:
>
> On one hand, OCFS2_LOCK_BLOCKED flag of this lockres is set in
> BAST(ocfs2_generic_handle_bast) when downconvert is started on behalf of
> the remote EX lock request.  Another hand, the recursive cluster lock 
> (the
> second one) will be blocked in in __ocfs2_cluster_lock() because of
> OCFS2_LOCK_BLOCKED.  But, the downconvert never complete, why? because
> there is no chance for the first cluster lock on this node to be unlocked
> - we block ourselves in the code path.
> ---
>
>> ...
>> take inode lock again (phase3)
>>
>> Deadlock happens because Process B in phase2 and Process A in phase3
>> are waiting for each other.
> It's local lock's (like i_mutex) responsibility to protect critical 
> section from racing
> among processes on the same node.
I know we are talking a cluster lock issue. And the Process B I described is
downconvert thread.
>
>> So you are trying to fix it by making phase3 finish without really doing
>
> Phase3 can go ahead because this node is already under protection of 
> cluster lock.
You said it was blocked...
"Another hand, the recursive cluster lock (the second one) will be 
blocked in
__ocfs2_cluster_lock() because of OCFS2_LOCK_BLOCKED."
>
>> __ocfs2_cluster_lock, then Process B can continue either.
>> Let us bear in mind that phase1 and phase3 are in the same context and
>> executed in order. That's why I think there is no need to check if 
>> locked
>> by myself in phase1.
>> If phase1 finds it is already locked by myself, that means the holder
>> is left by last operation without dec holder. That's why I think it 
>> is a bug
>> instead of a recursive lock case.
>
> Did I answer your question?
>
> Thanks!
> Eric
>
>>
>> Thanks,
>> Joseph
>>>
>>> Thanks,
>>> Eric
>>>
>>>>
>>>> Thanks,
>>>> Joseph
>>>>>
>>>>> Thanks,
>>>>> Eric
>>>>>>
>>>>>> Thanks,
>>>>>> Joseph
>>>>>>>
>>>>>>> Thanks for your review;-)
>>>>>>> Eric
>>>>>>>
>>>>>>>>
>>>>>>>> Thanks,
>>>>>>>> Joseph
>>>>>>>>>
>>>>>>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>>>>>>> ---
>>>>>>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>>>>>>   fs/ocfs2/file.c | 44 
>>>>>>>>> ++++++++++++++++++++++++++++++++++----------
>>>>>>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>>>>>>
>>>>>>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>>>>>>> index bed1fcb..c539890 100644
>>>>>>>>> --- a/fs/ocfs2/acl.c
>>>>>>>>> +++ b/fs/ocfs2/acl.c
>>>>>>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode 
>>>>>>>>> *inode, struct posix_acl *acl, int type)
>>>>>>>>>   {
>>>>>>>>>       struct buffer_head *bh = NULL;
>>>>>>>>>       int status = 0;
>>>>>>>>> -
>>>>>>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>> +
>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>> +    if (has_locked)
>>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>>>       if (status < 0) {
>>>>>>>>>           if (status != -ENOENT)
>>>>>>>>>               mlog_errno(status);
>>>>>>>>>           return status;
>>>>>>>>>       }
>>>>>>>>> +    if (!has_locked)
>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>> +
>>>>>>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, 
>>>>>>>>> NULL);
>>>>>>>>> -    ocfs2_inode_unlock(inode, 1);
>>>>>>>>> +
>>>>>>>>> +    if (!has_locked) {
>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>> +        ocfs2_inode_unlock(inode, 1);
>>>>>>>>> +    }
>>>>>>>>>       brelse(bh);
>>>>>>>>> +
>>>>>>>>>       return status;
>>>>>>>>>   }
>>>>>>>>>   @@ -303,21 +318,35 @@ struct posix_acl 
>>>>>>>>> *ocfs2_iop_get_acl(struct inode *inode, int type)
>>>>>>>>>       struct buffer_head *di_bh = NULL;
>>>>>>>>>       struct posix_acl *acl;
>>>>>>>>>       int ret;
>>>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>>>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>>>>>>           return NULL;
>>>>>>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>>>>>>> +
>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>> +    if (has_locked)
>>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>>>>>>       if (ret < 0) {
>>>>>>>>>           if (ret != -ENOENT)
>>>>>>>>>               mlog_errno(ret);
>>>>>>>>>           return ERR_PTR(ret);
>>>>>>>>>       }
>>>>>>>>> +    if (!has_locked)
>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>>>> +    if (!has_locked) {
>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>>>> +    }
>>>>>>>>>       brelse(di_bh);
>>>>>>>>> +
>>>>>>>>>       return acl;
>>>>>>>>>   }
>>>>>>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>>>>>>> index c488965..62be75d 100644
>>>>>>>>> --- a/fs/ocfs2/file.c
>>>>>>>>> +++ b/fs/ocfs2/file.c
>>>>>>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>>>>>> struct iattr *attr)
>>>>>>>>>       handle_t *handle = NULL;
>>>>>>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>>>>>>       int qtype;
>>>>>>>>> +    int arg_flags = 0, had_lock;
>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>>>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>>>>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry 
>>>>>>>>> *dentry, struct iattr *attr)
>>>>>>>>>           }
>>>>>>>>>       }
>>>>>>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>> +    if (had_lock)
>>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>>>       if (status < 0) {
>>>>>>>>>           if (status != -ENOENT)
>>>>>>>>>               mlog_errno(status);
>>>>>>>>>           goto bail_unlock_rw;
>>>>>>>>>       }
>>>>>>>>> -    inode_locked = 1;
>>>>>>>>> +    if (!had_lock) {
>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>> +        inode_locked = 1;
>>>>>>>>> +    }
>>>>>>>>>         if (size_change) {
>>>>>>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>>>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, 
>>>>>>>>> struct iattr *attr)
>>>>>>>>>   bail_commit:
>>>>>>>>>       ocfs2_commit_trans(osb, handle);
>>>>>>>>>   bail_unlock:
>>>>>>>>> -    if (status) {
>>>>>>>>> +    if (status && inode_locked) {
>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>>>           inode_locked = 0;
>>>>>>>>>       }
>>>>>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry 
>>>>>>>>> *dentry, struct iattr *attr)
>>>>>>>>>           if (status < 0)
>>>>>>>>>               mlog_errno(status);
>>>>>>>>>       }
>>>>>>>>> -    if (inode_locked)
>>>>>>>>> +    if (inode_locked) {
>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>>> +    }
>>>>>>>>>         brelse(bh);
>>>>>>>>>       return status;
>>>>>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>>>>>>   {
>>>>>>>>>       int ret;
>>>>>>>>> +    int has_locked;
>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>         if (mask & MAY_NOT_BLOCK)
>>>>>>>>>           return -ECHILD;
>>>>>>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>>>> -    if (ret) {
>>>>>>>>> -        if (ret != -ENOENT)
>>>>>>>>> -            mlog_errno(ret);
>>>>>>>>> -        goto out;
>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>> +    if (!has_locked) {
>>>>>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>>>> +        if (ret) {
>>>>>>>>> +            if (ret != -ENOENT)
>>>>>>>>> +                mlog_errno(ret);
>>>>>>>>> +            goto out;
>>>>>>>>> +        }
>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>>       }
>>>>>>>>>         ret = generic_permission(inode, mask);
>>>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>>>> +    if (!has_locked) {
>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>>>> +    }
>>>>>>>>>   out:
>>>>>>>>>       return ret;
>>>>>>>>>   }
>>>>>>>>
>>>>>>>>
>>>>>>>
>>>>>>
>>>>>>
>>>>>
>>>>
>>>>
>>>
>>
>>
>

Zhen Ren Jan. 9, 2017, 2:13 a.m. UTC | #12

Hi,

On 01/09/2017 09:13 AM, Joseph Qi wrote:
> ...
>>
>>> The issue case you are trying to fix is:
>>> Process A
>>> take inode lock (phase1)
>>> ...
>>> <<< race window (phase2, Process B)
>>
>> The deadlock only happens if process B is on a remote node and request EX lock.
>>
>> Quote the patch[1/2]'s commit message:
>>
>> A deadlock will occur if a remote EX request comes in between two of
>> ocfs2_inode_lock().  Briefly describe how the deadlock is formed:
>>
>> On one hand, OCFS2_LOCK_BLOCKED flag of this lockres is set in
>> BAST(ocfs2_generic_handle_bast) when downconvert is started on behalf of
>> the remote EX lock request.  Another hand, the recursive cluster lock (the
>> second one) will be blocked in in __ocfs2_cluster_lock() because of
>> OCFS2_LOCK_BLOCKED.  But, the downconvert never complete, why? because
>> there is no chance for the first cluster lock on this node to be unlocked
>> - we block ourselves in the code path.
>> ---
>>
>>> ...
>>> take inode lock again (phase3)
>>>
>>> Deadlock happens because Process B in phase2 and Process A in phase3
>>> are waiting for each other.
>> It's local lock's (like i_mutex) responsibility to protect critical section from racing
>> among processes on the same node.
> I know we are talking a cluster lock issue. And the Process B I described is
> downconvert thread.

That's fine!

>>
>>> So you are trying to fix it by making phase3 finish without really doing
>>
>> Phase3 can go ahead because this node is already under protection of cluster lock.
> You said it was blocked...

Oh, sorry, I meant phase3 can go ahead if this patch set is applied;-)

> "Another hand, the recursive cluster lock (the second one) will be blocked in
> __ocfs2_cluster_lock() because of OCFS2_LOCK_BLOCKED."
>>
>>> __ocfs2_cluster_lock, then Process B can continue either.
>>> Let us bear in mind that phase1 and phase3 are in the same context and
>>> executed in order. That's why I think there is no need to check if locked
>>> by myself in phase1.
Sorry, I still cannot see it. Without keeping track of the first cluster lock, how can we 
know if
we are under a context that has already been in the protecting of cluster lock? How can we 
handle
the recursive locking (the second cluster lock) if we don't have this information?
>>> If phase1 finds it is already locked by myself, that means the holder
>>> is left by last operation without dec holder. That's why I think it is a bug
>>> instead of a recursive lock case.
I think I got your point here. Do you mean that we should just add the lock holder at the 
first locking position
without checking before that? Unfortunately, it's tricky here to know exactly which ocfs2 
routine will be the first vfs
entry point, such as ocfs2_get_acl() which can be both the first vfs entry point and the 
second vfs entry point after
ocfs2_permission(), right?

It will be a coding bug if the problem you concern about happens. I think we don't need to 
worry about this much because
the code logic here is quite simple;-)

Thanks for your patience!
Eric

>>
>> Did I answer your question?
>>
>> Thanks!
>> Eric
>>
>>>
>>> Thanks,
>>> Joseph
>>>>
>>>> Thanks,
>>>> Eric
>>>>
>>>>>
>>>>> Thanks,
>>>>> Joseph
>>>>>>
>>>>>> Thanks,
>>>>>> Eric
>>>>>>>
>>>>>>> Thanks,
>>>>>>> Joseph
>>>>>>>>
>>>>>>>> Thanks for your review;-)
>>>>>>>> Eric
>>>>>>>>
>>>>>>>>>
>>>>>>>>> Thanks,
>>>>>>>>> Joseph
>>>>>>>>>>
>>>>>>>>>> Signed-off-by: Eric Ren <[e-mail]>
>>>>>>>>>> ---
>>>>>>>>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>>>>>>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>>>>>>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>>>>>>>>
>>>>>>>>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>>>>>>>>> index bed1fcb..c539890 100644
>>>>>>>>>> --- a/fs/ocfs2/acl.c
>>>>>>>>>> +++ b/fs/ocfs2/acl.c
>>>>>>>>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl 
>>>>>>>>>> *acl, int type)
>>>>>>>>>>   {
>>>>>>>>>>       struct buffer_head *bh = NULL;
>>>>>>>>>>       int status = 0;
>>>>>>>>>> -
>>>>>>>>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>> +
>>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>>> +    if (has_locked)
>>>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>>>>       if (status < 0) {
>>>>>>>>>>           if (status != -ENOENT)
>>>>>>>>>>               mlog_errno(status);
>>>>>>>>>>           return status;
>>>>>>>>>>       }
>>>>>>>>>> +    if (!has_locked)
>>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>>> +
>>>>>>>>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>>>>>>>>> -    ocfs2_inode_unlock(inode, 1);
>>>>>>>>>> +
>>>>>>>>>> +    if (!has_locked) {
>>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>> +        ocfs2_inode_unlock(inode, 1);
>>>>>>>>>> +    }
>>>>>>>>>>       brelse(bh);
>>>>>>>>>> +
>>>>>>>>>>       return status;
>>>>>>>>>>   }
>>>>>>>>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, 
>>>>>>>>>> int type)
>>>>>>>>>>       struct buffer_head *di_bh = NULL;
>>>>>>>>>>       struct posix_acl *acl;
>>>>>>>>>>       int ret;
>>>>>>>>>> +    int arg_flags = 0, has_locked;
>>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>>         osb = OCFS2_SB(inode->i_sb);
>>>>>>>>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>>>>>>>>           return NULL;
>>>>>>>>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>>>>>>>>> +
>>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>>> +    if (has_locked)
>>>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>>>>>>>>       if (ret < 0) {
>>>>>>>>>>           if (ret != -ENOENT)
>>>>>>>>>>               mlog_errno(ret);
>>>>>>>>>>           return ERR_PTR(ret);
>>>>>>>>>>       }
>>>>>>>>>> +    if (!has_locked)
>>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>>>>> +    if (!has_locked) {
>>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>>>>> +    }
>>>>>>>>>>       brelse(di_bh);
>>>>>>>>>> +
>>>>>>>>>>       return acl;
>>>>>>>>>>   }
>>>>>>>>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>>>>>>>>> index c488965..62be75d 100644
>>>>>>>>>> --- a/fs/ocfs2/file.c
>>>>>>>>>> +++ b/fs/ocfs2/file.c
>>>>>>>>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>>>       handle_t *handle = NULL;
>>>>>>>>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>>>>>>>>       int qtype;
>>>>>>>>>> +    int arg_flags = 0, had_lock;
>>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>>         trace_ocfs2_setattr(inode, dentry,
>>>>>>>>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>>>>>>>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>>>           }
>>>>>>>>>>       }
>>>>>>>>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>>> +    if (had_lock)
>>>>>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>>>>>       if (status < 0) {
>>>>>>>>>>           if (status != -ENOENT)
>>>>>>>>>>               mlog_errno(status);
>>>>>>>>>>           goto bail_unlock_rw;
>>>>>>>>>>       }
>>>>>>>>>> -    inode_locked = 1;
>>>>>>>>>> +    if (!had_lock) {
>>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>>> +        inode_locked = 1;
>>>>>>>>>> +    }
>>>>>>>>>>         if (size_change) {
>>>>>>>>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>>>>>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>>>   bail_commit:
>>>>>>>>>>       ocfs2_commit_trans(osb, handle);
>>>>>>>>>>   bail_unlock:
>>>>>>>>>> -    if (status) {
>>>>>>>>>> +    if (status && inode_locked) {
>>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>>>>           inode_locked = 0;
>>>>>>>>>>       }
>>>>>>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>>>>>>>>>           if (status < 0)
>>>>>>>>>>               mlog_errno(status);
>>>>>>>>>>       }
>>>>>>>>>> -    if (inode_locked)
>>>>>>>>>> +    if (inode_locked) {
>>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>>           ocfs2_inode_unlock(inode, 1);
>>>>>>>>>> +    }
>>>>>>>>>>         brelse(bh);
>>>>>>>>>>       return status;
>>>>>>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>>>>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>>>>>>>>   {
>>>>>>>>>>       int ret;
>>>>>>>>>> +    int has_locked;
>>>>>>>>>> +    struct ocfs2_holder oh;
>>>>>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>>>>>         if (mask & MAY_NOT_BLOCK)
>>>>>>>>>>           return -ECHILD;
>>>>>>>>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>>>>> -    if (ret) {
>>>>>>>>>> -        if (ret != -ENOENT)
>>>>>>>>>> -            mlog_errno(ret);
>>>>>>>>>> -        goto out;
>>>>>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>>>>>>> +    if (!has_locked) {
>>>>>>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>>>>>> +        if (ret) {
>>>>>>>>>> +            if (ret != -ENOENT)
>>>>>>>>>> +                mlog_errno(ret);
>>>>>>>>>> +            goto out;
>>>>>>>>>> +        }
>>>>>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>>>>>       }
>>>>>>>>>>         ret = generic_permission(inode, mask);
>>>>>>>>>>   -    ocfs2_inode_unlock(inode, 0);
>>>>>>>>>> +    if (!has_locked) {
>>>>>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>>>>>> +    }
>>>>>>>>>>   out:
>>>>>>>>>>       return ret;
>>>>>>>>>>   }
>>>>>>>>>
>>>>>>>>>
>>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>
>>>>>
>>>>>
>>>>
>>>
>>>
>>
>
>

Zhen Ren Jan. 9, 2017, 5:24 a.m. UTC | #13

Hi Fengguang,

On 01/06/2017 10:52 PM, kbuild test robot wrote:
> Hi Eric,
>
> [auto build test ERROR on linus/master]
> [also build test ERROR on v4.10-rc2 next-20170106]
> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
>
> url:    https://github.com/0day-ci/linux/commits/Eric-Ren/fix-deadlock-caused-by-recursive-cluster-locking/20170106-200837
> config: ia64-allyesconfig (attached as .config)
> compiler: ia64-linux-gcc (GCC) 6.2.0
> reproduce:
>          wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
>          chmod +x ~/bin/make.cross
>          # save the attached .config to linux build tree
>          make.cross ARCH=ia64

I failed to reproduce this issue locally by following the above instructions, after rebasing 
my patch set onto the lastest
mainline(Linux 4.10-rc3), only seeing this compiler error message:
"
test:/mnt/build/linux # make.cross ARCH=ia64
make CROSS_COMPILE=/opt/gcc-4.9.0-nolibc/ia64-linux/bin/ia64-linux- --jobs=4 ARCH=ia64
...
   CALL    scripts/checksyscalls.sh
<stdin>:1184:2: warning: #warning syscall perf_event_open not implemented [-Wcpp]
<stdin>:1238:2: warning: #warning syscall seccomp not implemented [-Wcpp]
<stdin>:1316:2: warning: #warning syscall pkey_mprotect not implemented [-Wcpp]
<stdin>:1319:2: warning: #warning syscall pkey_alloc not implemented [-Wcpp]
<stdin>:1322:2: warning: #warning syscall pkey_free not implemented [-Wcpp]
...
  AS      arch/ia64/kernel/gate.o
arch/ia64/kernel/entry.S: Assembler messages:
arch/ia64/kernel/entry.S:622: Error: Operand 2 of `adds' should be a 14-bit integer (-8192-8191)
arch/ia64/kernel/entry.S:729: Error: Operand 2 of `adds' should be a 14-bit integer (-8192-8191)
arch/ia64/kernel/entry.S:860: Error: Operand 2 of `adds' should be a 14-bit integer (-8192-8191)
make[1]: *** [scripts/Makefile.build:393: arch/ia64/kernel/entry.o] Error 1
make[1]: *** Waiting for unfinished jobs....
make: *** [Makefile:988: arch/ia64/kernel] Error 2
make: *** Waiting for unfinished jobs....
"

The obvious difference I noticed is my gcc version is little newer than kbuild, not sure if 
it's related:
"
test:/mnt/build/linux # gcc -v
gcc version 6.2.1 20160830 [gcc-6-branch revision 239856] (SUSE Linux)
"

>
> All errors (new ones prefixed by >>):
>
>     In file included from fs/ocfs2/acl.c:31:0:
>     fs/ocfs2/acl.c: In function 'ocfs2_iop_set_acl':
>>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
>      inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);

This error is probably because I should not add "inline" at the declaration while putting 
the function body into source file.
But, no error or warning occurred when I built and tested locally this way:
"
test:/mnt/build/linux/fs/ocfs2 # make -C /lib/modules/4.9.0-2-vanilla/build M=`pwd` modules
"

Anyway, I wanna make kbuild silent before resending again;-) Please correct me if I'm 
missing something?

Thanks!
Eric
>                                  ^~~~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/acl.c:292:16: note: called from here
>       has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>                     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     In file included from fs/ocfs2/acl.c:31:0:
>>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
>      inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
>                                  ^~~~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/acl.c:292:16: note: called from here
>       has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>                     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     In file included from fs/ocfs2/acl.c:31:0:
>>> fs/ocfs2/dlmglue.h:185:13: error: inlining failed in call to always_inline 'ocfs2_add_holder': function body not available
>      inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
>                  ^~~~~~~~~~~~~~~~
>     fs/ocfs2/acl.c:302:3: note: called from here
>        ocfs2_add_holder(lockres, &oh);
>        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     In file included from fs/ocfs2/acl.c:31:0:
>>> fs/ocfs2/dlmglue.h:187:13: error: inlining failed in call to always_inline 'ocfs2_remove_holder': function body not available
>      inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
>                  ^~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/acl.c:307:3: note: called from here
>        ocfs2_remove_holder(lockres, &oh);
>        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> --
>     In file included from arch/ia64/include/uapi/asm/intrinsics.h:21:0,
>                      from arch/ia64/include/asm/intrinsics.h:10,
>                      from arch/ia64/include/asm/bitops.h:18,
>                      from include/linux/bitops.h:36,
>                      from include/linux/kernel.h:10,
>                      from include/linux/list.h:8,
>                      from include/linux/wait.h:6,
>                      from include/linux/fs.h:5,
>                      from fs/ocfs2/file.c:27:
>     fs/ocfs2/file.c: In function 'ocfs2_file_write_iter':
>     arch/ia64/include/uapi/asm/cmpxchg.h:56:2: warning: value computed is not used [-Wunused-value]
>      ((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr))))
>      ~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/file.c:2334:3: note: in expansion of macro 'xchg'
>        xchg(&iocb->ki_complete, saved_ki_complete);
>        ^~~~
>     In file included from fs/ocfs2/file.c:49:0:
>     fs/ocfs2/file.c: In function 'ocfs2_permission':
>>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
>      inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
>                                  ^~~~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/file.c:1345:16: note: called from here
>       has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>                     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     In file included from fs/ocfs2/file.c:49:0:
>>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to always_inline 'ocfs2_is_locked_by_me': function body not available
>      inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
>                                  ^~~~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/file.c:1345:16: note: called from here
>       has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>                     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     In file included from fs/ocfs2/file.c:49:0:
>>> fs/ocfs2/dlmglue.h:185:13: error: inlining failed in call to always_inline 'ocfs2_add_holder': function body not available
>      inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
>                  ^~~~~~~~~~~~~~~~
>     fs/ocfs2/file.c:1353:3: note: called from here
>        ocfs2_add_holder(lockres, &oh);
>        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>     In file included from fs/ocfs2/file.c:49:0:
>>> fs/ocfs2/dlmglue.h:187:13: error: inlining failed in call to always_inline 'ocfs2_remove_holder': function body not available
>      inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
>                  ^~~~~~~~~~~~~~~~~~~
>     fs/ocfs2/file.c:1359:3: note: called from here
>        ocfs2_remove_holder(lockres, &oh);
>        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
> vim +/ocfs2_is_locked_by_me +189 fs/ocfs2/dlmglue.h
>
> 63e0c48a Joel Becker 2008-01-30  179  void ocfs2_set_locking_protocol(void);
> 9fb5ed3a Eric Ren    2017-01-05  180
> 9fb5ed3a Eric Ren    2017-01-05  181  /*
> 9fb5ed3a Eric Ren    2017-01-05  182   * Keep a list of processes who have interest in a lockres.
> 9fb5ed3a Eric Ren    2017-01-05  183   * Note: this is now only uesed for check recursive cluster lock.
> 9fb5ed3a Eric Ren    2017-01-05  184   */
> 9fb5ed3a Eric Ren    2017-01-05 @185  inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
> 9fb5ed3a Eric Ren    2017-01-05  186  			     struct ocfs2_holder *oh);
> 9fb5ed3a Eric Ren    2017-01-05 @187  inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
> 9fb5ed3a Eric Ren    2017-01-05  188  			     struct ocfs2_holder *oh);
> 9fb5ed3a Eric Ren    2017-01-05 @189  inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
> 9fb5ed3a Eric Ren    2017-01-05  190
> ccd979bd Mark Fasheh 2005-12-15  191  #endif	/* DLMGLUE_H */
>
> :::::: The code at line 189 was first introduced by commit
> :::::: 9fb5ed3abab2100ae8d99cee9b25fb92e3154224 ocfs2/dlmglue: prepare tracking logic to avoid recursive cluster lock
>
> :::::: TO: Eric Ren <[e-mail]>
> :::::: CC: 0day robot <[e-mail]>
>
> ---
> 0-DAY kernel test infrastructure                Open Source Technology Center
> https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

Zhen Ren Jan. 12, 2017, 11:24 a.m. UTC | #14

Hi Joseph,

On 01/09/2017 10:13 AM, Eric Ren wrote:
>>>> So you are trying to fix it by making phase3 finish without really doing
>>> Phase3 can go ahead because this node is already under protection of cluster lock.
>> You said it was blocked...
> Oh, sorry, I meant phase3 can go ahead if this patch set is applied;-)
>
>> "Another hand, the recursive cluster lock (the second one) will be blocked in
>> __ocfs2_cluster_lock() because of OCFS2_LOCK_BLOCKED."
>>>> __ocfs2_cluster_lock, then Process B can continue either.
>>>> Let us bear in mind that phase1 and phase3 are in the same context and
>>>> executed in order. That's why I think there is no need to check if locked
>>>> by myself in phase1.
> Sorry, I still cannot see it. Without keeping track of the first cluster lock, how can we
> know if
> we are under a context that has already been in the protecting of cluster lock? How can we
> handle
> the recursive locking (the second cluster lock) if we don't have this information?
>>>> If phase1 finds it is already locked by myself, that means the holder
>>>> is left by last operation without dec holder. That's why I think it is a bug
>>>> instead of a recursive lock case.
> I think I got your point here. Do you mean that we should just add the lock holder at the
> first locking position
> without checking before that? Unfortunately, it's tricky here to know exactly which ocfs2
> routine will be the first vfs
> entry point, such as ocfs2_get_acl() which can be both the first vfs entry point and the
> second vfs entry point after
> ocfs2_permission(), right?
>
> It will be a coding bug if the problem you concern about happens. I think we don't need to
> worry about this much because
> the code logic here is quite simple;-)
Ping...

Did I clear your doubts by the last email? I really want to get your point, if not.

If there's any problem, I will fix them in the next version;-)

Thanks,
Eric

>
> Thanks for your patience!
> Eric
>
>>> D

Joseph Qi Jan. 12, 2017, 11:36 a.m. UTC | #15

On 17/1/12 19:24, Eric Ren wrote:
> Hi Joseph,
>
> On 01/09/2017 10:13 AM, Eric Ren wrote:
>>>>> So you are trying to fix it by making phase3 finish without really 
>>>>> doing
>>>> Phase3 can go ahead because this node is already under protection 
>>>> of cluster lock.
>>> You said it was blocked...
>> Oh, sorry, I meant phase3 can go ahead if this patch set is applied;-)
>>
>>> "Another hand, the recursive cluster lock (the second one) will be 
>>> blocked in
>>> __ocfs2_cluster_lock() because of OCFS2_LOCK_BLOCKED."
>>>>> __ocfs2_cluster_lock, then Process B can continue either.
>>>>> Let us bear in mind that phase1 and phase3 are in the same context 
>>>>> and
>>>>> executed in order. That's why I think there is no need to check if 
>>>>> locked
>>>>> by myself in phase1.
>> Sorry, I still cannot see it. Without keeping track of the first 
>> cluster lock, how can we
>> know if
>> we are under a context that has already been in the protecting of 
>> cluster lock? How can we
>> handle
>> the recursive locking (the second cluster lock) if we don't have this 
>> information?
>>>>> If phase1 finds it is already locked by myself, that means the holder
>>>>> is left by last operation without dec holder. That's why I think 
>>>>> it is a bug
>>>>> instead of a recursive lock case.
>> I think I got your point here. Do you mean that we should just add 
>> the lock holder at the
>> first locking position
>> without checking before that? Unfortunately, it's tricky here to know 
>> exactly which ocfs2
>> routine will be the first vfs
>> entry point, such as ocfs2_get_acl() which can be both the first vfs 
>> entry point and the
>> second vfs entry point after
>> ocfs2_permission(), right?
>>
>> It will be a coding bug if the problem you concern about happens. I 
>> think we don't need to
>> worry about this much because
>> the code logic here is quite simple;-)
> Ping...
>
> Did I clear your doubts by the last email? I really want to get your 
> point, if not.
>
> If there's any problem, I will fix them in the next version;-)
Yes, but I still worry about the code bug case will be hidden behind 
recursive lock...
Anyway, It depends on others...

Thanks,
Joseph
>
> Thanks,
> Eric
>
>>
>> Thanks for your patience!
>> Eric
>>
>>>> D
>

Junxiao Bi Jan. 13, 2017, 4:22 a.m. UTC | #16

On 01/05/2017 11:31 PM, Eric Ren wrote:
> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()")
> results in a deadlock, as the author "Tariq Saeed" realized shortly
> after the patch was merged. The discussion happened here
> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
> 
> The reason why taking cluster inode lock at vfs entry points opens up
> a self deadlock window, is explained in the previous patch of this
> series.
> 
> So far, we have seen two different code paths that have this issue.
> 1. do_sys_open
>      may_open
>       inode_permission
>        ocfs2_permission
>         ocfs2_inode_lock() <=== take PR
>          generic_permission
>           get_acl
>            ocfs2_iop_get_acl
>             ocfs2_inode_lock() <=== take PR
> 2. fchmod|fchmodat
>     chmod_common
>      notify_change
>       ocfs2_setattr <=== take EX
>        posix_acl_chmod
>         get_acl
>          ocfs2_iop_get_acl <=== take PR
>         ocfs2_iop_set_acl <=== take EX
> 
> Fixes them by adding the tracking logic (in the previous patch) for
> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
> ocfs2_setattr().
> 
> Signed-off-by: Eric Ren <[e-mail]>
> ---
>  fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>  fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>  2 files changed, 68 insertions(+), 15 deletions(-)
> 
> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
> index bed1fcb..c539890 100644
> --- a/fs/ocfs2/acl.c
> +++ b/fs/ocfs2/acl.c
> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
>  {
>  	struct buffer_head *bh = NULL;
>  	int status = 0;
> -
> -	status = ocfs2_inode_lock(inode, &bh, 1);
> +	int arg_flags = 0, has_locked;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
> +
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
> +	if (has_locked)
> +		arg_flags = OCFS2_META_LOCK_GETBH;
> +	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>  	if (status < 0) {
>  		if (status != -ENOENT)
>  			mlog_errno(status);
>  		return status;
>  	}
> +	if (!has_locked)
> +		ocfs2_add_holder(lockres, &oh);
> +
>  	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
> -	ocfs2_inode_unlock(inode, 1);
> +
> +	if (!has_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
> +		ocfs2_inode_unlock(inode, 1);
> +	}
>  	brelse(bh);
> +
>  	return status;
>  }
>  
> @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
>  	struct buffer_head *di_bh = NULL;
>  	struct posix_acl *acl;
>  	int ret;
> +	int arg_flags = 0, has_locked;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
>  
>  	osb = OCFS2_SB(inode->i_sb);
>  	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>  		return NULL;
> -	ret = ocfs2_inode_lock(inode, &di_bh, 0);
> +
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
> +	if (has_locked)
> +		arg_flags = OCFS2_META_LOCK_GETBH;
> +	ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>  	if (ret < 0) {
>  		if (ret != -ENOENT)
>  			mlog_errno(ret);
>  		return ERR_PTR(ret);
>  	}
> +	if (!has_locked)
> +		ocfs2_add_holder(lockres, &oh);
>  
>  	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>  
> -	ocfs2_inode_unlock(inode, 0);
> +	if (!has_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
> +		ocfs2_inode_unlock(inode, 0);
> +	}
>  	brelse(di_bh);
> +
>  	return acl;
>  }
>  
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index c488965..62be75d 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>  	handle_t *handle = NULL;
>  	struct dquot *transfer_to[MAXQUOTAS] = { };
>  	int qtype;
> +	int arg_flags = 0, had_lock;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
>  
>  	trace_ocfs2_setattr(inode, dentry,
>  			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>  		}
>  	}
>  
> -	status = ocfs2_inode_lock(inode, &bh, 1);
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);

If had_lock==true, it is a bug? I think we should BUG_ON for it, that
can help us catch bug at the first time.


> +	if (had_lock)
> +		arg_flags = OCFS2_META_LOCK_GETBH;
> +	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>  	if (status < 0) {
>  		if (status != -ENOENT)
>  			mlog_errno(status);
>  		goto bail_unlock_rw;
>  	}
> -	inode_locked = 1;
> +	if (!had_lock) {
> +		ocfs2_add_holder(lockres, &oh);
> +		inode_locked = 1;
> +	}
>  
>  	if (size_change) {
>  		status = inode_newsize_ok(inode, attr->ia_size);
> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>  bail_commit:
>  	ocfs2_commit_trans(osb, handle);
>  bail_unlock:
> -	if (status) {
> +	if (status && inode_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
>  		ocfs2_inode_unlock(inode, 1);
>  		inode_locked = 0;
>  	}
> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>  		if (status < 0)
>  			mlog_errno(status);
>  	}
> -	if (inode_locked)
> +	if (inode_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
>  		ocfs2_inode_unlock(inode, 1);
> +	}
>  
>  	brelse(bh);
>  	return status;
> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>  int ocfs2_permission(struct inode *inode, int mask)
>  {
>  	int ret;
> +	int has_locked;
> +	struct ocfs2_holder oh;
> +	struct ocfs2_lock_res *lockres;
>  
>  	if (mask & MAY_NOT_BLOCK)
>  		return -ECHILD;
>  
> -	ret = ocfs2_inode_lock(inode, NULL, 0);
> -	if (ret) {
> -		if (ret != -ENOENT)
> -			mlog_errno(ret);
> -		goto out;
> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);

The same thing as ocfs2_setattr.

Thanks,
Junxiao.
> +	if (!has_locked) {
> +		ret = ocfs2_inode_lock(inode, NULL, 0);
> +		if (ret) {
> +			if (ret != -ENOENT)
> +				mlog_errno(ret);
> +			goto out;
> +		}
> +		ocfs2_add_holder(lockres, &oh);
>  	}
>  
>  	ret = generic_permission(inode, mask);
>  
> -	ocfs2_inode_unlock(inode, 0);
> +	if (!has_locked) {
> +		ocfs2_remove_holder(lockres, &oh);
> +		ocfs2_inode_unlock(inode, 0);
> +	}
>  out:
>  	return ret;
>  }
>

Zhen Ren Jan. 13, 2017, 6:19 a.m. UTC | #17

Hi!

On 01/13/2017 12:22 PM, Junxiao Bi wrote:
> On 01/05/2017 11:31 PM, Eric Ren wrote:
>> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()")
>> results in a deadlock, as the author "Tariq Saeed" realized shortly
>> after the patch was merged. The discussion happened here
>> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
>>
>> The reason why taking cluster inode lock at vfs entry points opens up
>> a self deadlock window, is explained in the previous patch of this
>> series.
>>
>> So far, we have seen two different code paths that have this issue.
>> 1. do_sys_open
>>       may_open
>>        inode_permission
>>         ocfs2_permission
>>          ocfs2_inode_lock() <=== take PR
>>           generic_permission
>>            get_acl
>>             ocfs2_iop_get_acl
>>              ocfs2_inode_lock() <=== take PR
>> 2. fchmod|fchmodat
>>      chmod_common
>>       notify_change
>>        ocfs2_setattr <=== take EX
>>         posix_acl_chmod
>>          get_acl
>>           ocfs2_iop_get_acl <=== take PR
>>          ocfs2_iop_set_acl <=== take EX
>>
>> Fixes them by adding the tracking logic (in the previous patch) for
>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>> ocfs2_setattr().
>>
>> Signed-off-by: Eric Ren <[e-mail]>
>> ---
>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>
>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>> index bed1fcb..c539890 100644
>> --- a/fs/ocfs2/acl.c
>> +++ b/fs/ocfs2/acl.c
>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
>>   {
>>   	struct buffer_head *bh = NULL;
>>   	int status = 0;
>> -
>> -	status = ocfs2_inode_lock(inode, &bh, 1);
>> +	int arg_flags = 0, has_locked;
>> +	struct ocfs2_holder oh;
>> +	struct ocfs2_lock_res *lockres;
>> +
>> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>> +	if (has_locked)
>> +		arg_flags = OCFS2_META_LOCK_GETBH;
>> +	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>   	if (status < 0) {
>>   		if (status != -ENOENT)
>>   			mlog_errno(status);
>>   		return status;
>>   	}
>> +	if (!has_locked)
>> +		ocfs2_add_holder(lockres, &oh);
>> +
>>   	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>> -	ocfs2_inode_unlock(inode, 1);
>> +
>> +	if (!has_locked) {
>> +		ocfs2_remove_holder(lockres, &oh);
>> +		ocfs2_inode_unlock(inode, 1);
>> +	}
>>   	brelse(bh);
>> +
>>   	return status;
>>   }
>>   
>> @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
>>   	struct buffer_head *di_bh = NULL;
>>   	struct posix_acl *acl;
>>   	int ret;
>> +	int arg_flags = 0, has_locked;
>> +	struct ocfs2_holder oh;
>> +	struct ocfs2_lock_res *lockres;
>>   
>>   	osb = OCFS2_SB(inode->i_sb);
>>   	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>   		return NULL;
>> -	ret = ocfs2_inode_lock(inode, &di_bh, 0);
>> +
>> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>> +	if (has_locked)
>> +		arg_flags = OCFS2_META_LOCK_GETBH;
>> +	ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>   	if (ret < 0) {
>>   		if (ret != -ENOENT)
>>   			mlog_errno(ret);
>>   		return ERR_PTR(ret);
>>   	}
>> +	if (!has_locked)
>> +		ocfs2_add_holder(lockres, &oh);
>>   
>>   	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>   
>> -	ocfs2_inode_unlock(inode, 0);
>> +	if (!has_locked) {
>> +		ocfs2_remove_holder(lockres, &oh);
>> +		ocfs2_inode_unlock(inode, 0);
>> +	}
>>   	brelse(di_bh);
>> +
>>   	return acl;
>>   }
>>   
>> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>> index c488965..62be75d 100644
>> --- a/fs/ocfs2/file.c
>> +++ b/fs/ocfs2/file.c
>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>   	handle_t *handle = NULL;
>>   	struct dquot *transfer_to[MAXQUOTAS] = { };
>>   	int qtype;
>> +	int arg_flags = 0, had_lock;
>> +	struct ocfs2_holder oh;
>> +	struct ocfs2_lock_res *lockres;
>>   
>>   	trace_ocfs2_setattr(inode, dentry,
>>   			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>   		}
>>   	}
>>   
>> -	status = ocfs2_inode_lock(inode, &bh, 1);
>> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +	had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
> If had_lock==true, it is a bug? I think we should BUG_ON for it, that
> can help us catch bug at the first time.

Good idea! But I'm not sure if "ocfs2_setattr" is always the first one who takes the cluster 
lock.
It's harder for me to name all the possible paths;-/

>
>
>> +	if (had_lock)
>> +		arg_flags = OCFS2_META_LOCK_GETBH;
>> +	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>   	if (status < 0) {
>>   		if (status != -ENOENT)
>>   			mlog_errno(status);
>>   		goto bail_unlock_rw;
>>   	}
>> -	inode_locked = 1;
>> +	if (!had_lock) {
>> +		ocfs2_add_holder(lockres, &oh);
>> +		inode_locked = 1;
>> +	}
>>   
>>   	if (size_change) {
>>   		status = inode_newsize_ok(inode, attr->ia_size);
>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>   bail_commit:
>>   	ocfs2_commit_trans(osb, handle);
>>   bail_unlock:
>> -	if (status) {
>> +	if (status && inode_locked) {
>> +		ocfs2_remove_holder(lockres, &oh);
>>   		ocfs2_inode_unlock(inode, 1);
>>   		inode_locked = 0;
>>   	}
>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
>>   		if (status < 0)
>>   			mlog_errno(status);
>>   	}
>> -	if (inode_locked)
>> +	if (inode_locked) {
>> +		ocfs2_remove_holder(lockres, &oh);
>>   		ocfs2_inode_unlock(inode, 1);
>> +	}
>>   
>>   	brelse(bh);
>>   	return status;
>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>   int ocfs2_permission(struct inode *inode, int mask)
>>   {
>>   	int ret;
>> +	int has_locked;
>> +	struct ocfs2_holder oh;
>> +	struct ocfs2_lock_res *lockres;
>>   
>>   	if (mask & MAY_NOT_BLOCK)
>>   		return -ECHILD;
>>   
>> -	ret = ocfs2_inode_lock(inode, NULL, 0);
>> -	if (ret) {
>> -		if (ret != -ENOENT)
>> -			mlog_errno(ret);
>> -		goto out;
>> +	lockres = &OCFS2_I(inode)->ip_inode_lockres;
>> +	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
> The same thing as ocfs2_setattr.
OK. I will think over your suggestions!

Thanks,
Eric

>
> Thanks,
> Junxiao.
>> +	if (!has_locked) {
>> +		ret = ocfs2_inode_lock(inode, NULL, 0);
>> +		if (ret) {
>> +			if (ret != -ENOENT)
>> +				mlog_errno(ret);
>> +			goto out;
>> +		}
>> +		ocfs2_add_holder(lockres, &oh);
>>   	}
>>   
>>   	ret = generic_permission(inode, mask);
>>   
>> -	ocfs2_inode_unlock(inode, 0);
>> +	if (!has_locked) {
>> +		ocfs2_remove_holder(lockres, &oh);
>> +		ocfs2_inode_unlock(inode, 0);
>> +	}
>>   out:
>>   	return ret;
>>   }
>>
>

Junxiao Bi Jan. 16, 2017, 2:46 a.m. UTC | #18

On 01/13/2017 02:19 PM, Eric Ren wrote:
> Hi!
> 
> On 01/13/2017 12:22 PM, Junxiao Bi wrote:
>> On 01/05/2017 11:31 PM, Eric Ren wrote:
>>> Commit 743b5f1434f5 ("ocfs2: take inode lock in
>>> ocfs2_iop_set/get_acl()")
>>> results in a deadlock, as the author "Tariq Saeed" realized shortly
>>> after the patch was merged. The discussion happened here
>>> (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
>>>
>>>
>>> The reason why taking cluster inode lock at vfs entry points opens up
>>> a self deadlock window, is explained in the previous patch of this
>>> series.
>>>
>>> So far, we have seen two different code paths that have this issue.
>>> 1. do_sys_open
>>>       may_open
>>>        inode_permission
>>>         ocfs2_permission
>>>          ocfs2_inode_lock() <=== take PR
>>>           generic_permission
>>>            get_acl
>>>             ocfs2_iop_get_acl
>>>              ocfs2_inode_lock() <=== take PR
>>> 2. fchmod|fchmodat
>>>      chmod_common
>>>       notify_change
>>>        ocfs2_setattr <=== take EX
>>>         posix_acl_chmod
>>>          get_acl
>>>           ocfs2_iop_get_acl <=== take PR
>>>          ocfs2_iop_set_acl <=== take EX
>>>
>>> Fixes them by adding the tracking logic (in the previous patch) for
>>> these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
>>> ocfs2_setattr().
>>>
>>> Signed-off-by: Eric Ren <[e-mail]>
>>> ---
>>>   fs/ocfs2/acl.c  | 39 ++++++++++++++++++++++++++++++++++-----
>>>   fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
>>>   2 files changed, 68 insertions(+), 15 deletions(-)
>>>
>>> diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
>>> index bed1fcb..c539890 100644
>>> --- a/fs/ocfs2/acl.c
>>> +++ b/fs/ocfs2/acl.c
>>> @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode,
>>> struct posix_acl *acl, int type)
>>>   {
>>>       struct buffer_head *bh = NULL;
>>>       int status = 0;
>>> -
>>> -    status = ocfs2_inode_lock(inode, &bh, 1);
>>> +    int arg_flags = 0, has_locked;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>> +
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> +    if (has_locked)
>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>       if (status < 0) {
>>>           if (status != -ENOENT)
>>>               mlog_errno(status);
>>>           return status;
>>>       }
>>> +    if (!has_locked)
>>> +        ocfs2_add_holder(lockres, &oh);
>>> +
>>>       status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
>>> -    ocfs2_inode_unlock(inode, 1);
>>> +
>>> +    if (!has_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>> +        ocfs2_inode_unlock(inode, 1);
>>> +    }
>>>       brelse(bh);
>>> +
>>>       return status;
>>>   }
>>>   @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct
>>> inode *inode, int type)
>>>       struct buffer_head *di_bh = NULL;
>>>       struct posix_acl *acl;
>>>       int ret;
>>> +    int arg_flags = 0, has_locked;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>>         osb = OCFS2_SB(inode->i_sb);
>>>       if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
>>>           return NULL;
>>> -    ret = ocfs2_inode_lock(inode, &di_bh, 0);
>>> +
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> +    if (has_locked)
>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>> +    ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
>>>       if (ret < 0) {
>>>           if (ret != -ENOENT)
>>>               mlog_errno(ret);
>>>           return ERR_PTR(ret);
>>>       }
>>> +    if (!has_locked)
>>> +        ocfs2_add_holder(lockres, &oh);
>>>         acl = ocfs2_get_acl_nolock(inode, type, di_bh);
>>>   -    ocfs2_inode_unlock(inode, 0);
>>> +    if (!has_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>> +        ocfs2_inode_unlock(inode, 0);
>>> +    }
>>>       brelse(di_bh);
>>> +
>>>       return acl;
>>>   }
>>>   diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
>>> index c488965..62be75d 100644
>>> --- a/fs/ocfs2/file.c
>>> +++ b/fs/ocfs2/file.c
>>> @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct
>>> iattr *attr)
>>>       handle_t *handle = NULL;
>>>       struct dquot *transfer_to[MAXQUOTAS] = { };
>>>       int qtype;
>>> +    int arg_flags = 0, had_lock;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>>         trace_ocfs2_setattr(inode, dentry,
>>>                   (unsigned long long)OCFS2_I(inode)->ip_blkno,
>>> @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry,
>>> struct iattr *attr)
>>>           }
>>>       }
>>>   -    status = ocfs2_inode_lock(inode, &bh, 1);
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
>> If had_lock==true, it is a bug? I think we should BUG_ON for it, that
>> can help us catch bug at the first time.
> 
> Good idea! But I'm not sure if "ocfs2_setattr" is always the first one
> who takes the cluster lock.
> It's harder for me to name all the possible paths;-/
The BUG_ON() can help catch the path where ocfs2_setattr is not the
first one.

Thanks,
Junxiao.

> 
>>
>>
>>> +    if (had_lock)
>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>       if (status < 0) {
>>>           if (status != -ENOENT)
>>>               mlog_errno(status);
>>>           goto bail_unlock_rw;
>>>       }
>>> -    inode_locked = 1;
>>> +    if (!had_lock) {
>>> +        ocfs2_add_holder(lockres, &oh);
>>> +        inode_locked = 1;
>>> +    }
>>>         if (size_change) {
>>>           status = inode_newsize_ok(inode, attr->ia_size);
>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct
>>> iattr *attr)
>>>   bail_commit:
>>>       ocfs2_commit_trans(osb, handle);
>>>   bail_unlock:
>>> -    if (status) {
>>> +    if (status && inode_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>>           ocfs2_inode_unlock(inode, 1);
>>>           inode_locked = 0;
>>>       }
>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry,
>>> struct iattr *attr)
>>>           if (status < 0)
>>>               mlog_errno(status);
>>>       }
>>> -    if (inode_locked)
>>> +    if (inode_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>>           ocfs2_inode_unlock(inode, 1);
>>> +    }
>>>         brelse(bh);
>>>       return status;
>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>   int ocfs2_permission(struct inode *inode, int mask)
>>>   {
>>>       int ret;
>>> +    int has_locked;
>>> +    struct ocfs2_holder oh;
>>> +    struct ocfs2_lock_res *lockres;
>>>         if (mask & MAY_NOT_BLOCK)
>>>           return -ECHILD;
>>>   -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>> -    if (ret) {
>>> -        if (ret != -ENOENT)
>>> -            mlog_errno(ret);
>>> -        goto out;
>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>> The same thing as ocfs2_setattr.
> OK. I will think over your suggestions!
> 
> Thanks,
> Eric
> 
>>
>> Thanks,
>> Junxiao.
>>> +    if (!has_locked) {
>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>> +        if (ret) {
>>> +            if (ret != -ENOENT)
>>> +                mlog_errno(ret);
>>> +            goto out;
>>> +        }
>>> +        ocfs2_add_holder(lockres, &oh);
>>>       }
>>>         ret = generic_permission(inode, mask);
>>>   -    ocfs2_inode_unlock(inode, 0);
>>> +    if (!has_locked) {
>>> +        ocfs2_remove_holder(lockres, &oh);
>>> +        ocfs2_inode_unlock(inode, 0);
>>> +    }
>>>   out:
>>>       return ret;
>>>   }
>>>
>>
>

Zhen Ren Jan. 16, 2017, 3:06 a.m. UTC | #19

Hi Junxiao,

On 01/16/2017 10:46 AM, Junxiao Bi wrote:
>>> If had_lock==true, it is a bug? I think we should BUG_ON for it, that
>>> can help us catch bug at the first time.
>> Good idea! But I'm not sure if "ocfs2_setattr" is always the first one
>> who takes the cluster lock.
>> It's harder for me to name all the possible paths;-/
> The BUG_ON() can help catch the path where ocfs2_setattr is not the
> first one.
Yes, I understand. But, the problem is that the vfs entries calling order is out of our control.
I don't want to place an assertion where I'm not 100% sure it's absolutely right;-)

Thanks,
Eric

>
> Thanks,
> Junxiao.
>
>>>
>>>> +    if (had_lock)
>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>        if (status < 0) {
>>>>            if (status != -ENOENT)
>>>>                mlog_errno(status);
>>>>            goto bail_unlock_rw;
>>>>        }
>>>> -    inode_locked = 1;
>>>> +    if (!had_lock) {
>>>> +        ocfs2_add_holder(lockres, &oh);
>>>> +        inode_locked = 1;
>>>> +    }
>>>>          if (size_change) {
>>>>            status = inode_newsize_ok(inode, attr->ia_size);
>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct
>>>> iattr *attr)
>>>>    bail_commit:
>>>>        ocfs2_commit_trans(osb, handle);
>>>>    bail_unlock:
>>>> -    if (status) {
>>>> +    if (status && inode_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>            ocfs2_inode_unlock(inode, 1);
>>>>            inode_locked = 0;
>>>>        }
>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry,
>>>> struct iattr *attr)
>>>>            if (status < 0)
>>>>                mlog_errno(status);
>>>>        }
>>>> -    if (inode_locked)
>>>> +    if (inode_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>            ocfs2_inode_unlock(inode, 1);
>>>> +    }
>>>>          brelse(bh);
>>>>        return status;
>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>    int ocfs2_permission(struct inode *inode, int mask)
>>>>    {
>>>>        int ret;
>>>> +    int has_locked;
>>>> +    struct ocfs2_holder oh;
>>>> +    struct ocfs2_lock_res *lockres;
>>>>          if (mask & MAY_NOT_BLOCK)
>>>>            return -ECHILD;
>>>>    -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>> -    if (ret) {
>>>> -        if (ret != -ENOENT)
>>>> -            mlog_errno(ret);
>>>> -        goto out;
>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>> The same thing as ocfs2_setattr.
>> OK. I will think over your suggestions!
>>
>> Thanks,
>> Eric
>>
>>> Thanks,
>>> Junxiao.
>>>> +    if (!has_locked) {
>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>> +        if (ret) {
>>>> +            if (ret != -ENOENT)
>>>> +                mlog_errno(ret);
>>>> +            goto out;
>>>> +        }
>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>        }
>>>>          ret = generic_permission(inode, mask);
>>>>    -    ocfs2_inode_unlock(inode, 0);
>>>> +    if (!has_locked) {
>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>> +        ocfs2_inode_unlock(inode, 0);
>>>> +    }
>>>>    out:
>>>>        return ret;
>>>>    }
>>>>
>

Junxiao Bi Jan. 16, 2017, 3:13 a.m. UTC | #20

On 01/16/2017 11:06 AM, Eric Ren wrote:
> Hi Junxiao,
> 
> On 01/16/2017 10:46 AM, Junxiao Bi wrote:
>>>> If had_lock==true, it is a bug? I think we should BUG_ON for it, that
>>>> can help us catch bug at the first time.
>>> Good idea! But I'm not sure if "ocfs2_setattr" is always the first one
>>> who takes the cluster lock.
>>> It's harder for me to name all the possible paths;-/
>> The BUG_ON() can help catch the path where ocfs2_setattr is not the
>> first one.
> Yes, I understand. But, the problem is that the vfs entries calling
> order is out of our control.
> I don't want to place an assertion where I'm not 100% sure it's
> absolutely right;-)
If it is not the first one, is it another recursive locking bug? In this
case, if you don't like BUG_ON(), you can dump the call trace and print
some warning message.

Thanks,
Junxiao.
> 
> Thanks,
> Eric
> 
>>
>> Thanks,
>> Junxiao.
>>
>>>>
>>>>> +    if (had_lock)
>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>        if (status < 0) {
>>>>>            if (status != -ENOENT)
>>>>>                mlog_errno(status);
>>>>>            goto bail_unlock_rw;
>>>>>        }
>>>>> -    inode_locked = 1;
>>>>> +    if (!had_lock) {
>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>> +        inode_locked = 1;
>>>>> +    }
>>>>>          if (size_change) {
>>>>>            status = inode_newsize_ok(inode, attr->ia_size);
>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct
>>>>> iattr *attr)
>>>>>    bail_commit:
>>>>>        ocfs2_commit_trans(osb, handle);
>>>>>    bail_unlock:
>>>>> -    if (status) {
>>>>> +    if (status && inode_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>            ocfs2_inode_unlock(inode, 1);
>>>>>            inode_locked = 0;
>>>>>        }
>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry,
>>>>> struct iattr *attr)
>>>>>            if (status < 0)
>>>>>                mlog_errno(status);
>>>>>        }
>>>>> -    if (inode_locked)
>>>>> +    if (inode_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>            ocfs2_inode_unlock(inode, 1);
>>>>> +    }
>>>>>          brelse(bh);
>>>>>        return status;
>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>    int ocfs2_permission(struct inode *inode, int mask)
>>>>>    {
>>>>>        int ret;
>>>>> +    int has_locked;
>>>>> +    struct ocfs2_holder oh;
>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>          if (mask & MAY_NOT_BLOCK)
>>>>>            return -ECHILD;
>>>>>    -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>> -    if (ret) {
>>>>> -        if (ret != -ENOENT)
>>>>> -            mlog_errno(ret);
>>>>> -        goto out;
>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>> The same thing as ocfs2_setattr.
>>> OK. I will think over your suggestions!
>>>
>>> Thanks,
>>> Eric
>>>
>>>> Thanks,
>>>> Junxiao.
>>>>> +    if (!has_locked) {
>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>> +        if (ret) {
>>>>> +            if (ret != -ENOENT)
>>>>> +                mlog_errno(ret);
>>>>> +            goto out;
>>>>> +        }
>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>        }
>>>>>          ret = generic_permission(inode, mask);
>>>>>    -    ocfs2_inode_unlock(inode, 0);
>>>>> +    if (!has_locked) {
>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>> +    }
>>>>>    out:
>>>>>        return ret;
>>>>>    }
>>>>>
>>
>

Zhen Ren Jan. 16, 2017, 3:17 a.m. UTC | #21

On 01/16/2017 11:13 AM, Junxiao Bi wrote:
> On 01/16/2017 11:06 AM, Eric Ren wrote:
>> Hi Junxiao,
>>
>> On 01/16/2017 10:46 AM, Junxiao Bi wrote:
>>>>> If had_lock==true, it is a bug? I think we should BUG_ON for it, that
>>>>> can help us catch bug at the first time.
>>>> Good idea! But I'm not sure if "ocfs2_setattr" is always the first one
>>>> who takes the cluster lock.
>>>> It's harder for me to name all the possible paths;-/
>>> The BUG_ON() can help catch the path where ocfs2_setattr is not the
>>> first one.
>> Yes, I understand. But, the problem is that the vfs entries calling
>> order is out of our control.
>> I don't want to place an assertion where I'm not 100% sure it's
>> absolutely right;-)
> If it is not the first one, is it another recursive locking bug? In this
> case, if you don't like BUG_ON(), you can dump the call trace and print
> some warning message.

Yes! I like this idea, will add it in next version, thanks!

Eric

>
> Thanks,
> Junxiao.
>> Thanks,
>> Eric
>>
>>> Thanks,
>>> Junxiao.
>>>
>>>>>> +    if (had_lock)
>>>>>> +        arg_flags = OCFS2_META_LOCK_GETBH;
>>>>>> +    status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
>>>>>>         if (status < 0) {
>>>>>>             if (status != -ENOENT)
>>>>>>                 mlog_errno(status);
>>>>>>             goto bail_unlock_rw;
>>>>>>         }
>>>>>> -    inode_locked = 1;
>>>>>> +    if (!had_lock) {
>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>> +        inode_locked = 1;
>>>>>> +    }
>>>>>>           if (size_change) {
>>>>>>             status = inode_newsize_ok(inode, attr->ia_size);
>>>>>> @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct
>>>>>> iattr *attr)
>>>>>>     bail_commit:
>>>>>>         ocfs2_commit_trans(osb, handle);
>>>>>>     bail_unlock:
>>>>>> -    if (status) {
>>>>>> +    if (status && inode_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>             ocfs2_inode_unlock(inode, 1);
>>>>>>             inode_locked = 0;
>>>>>>         }
>>>>>> @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry,
>>>>>> struct iattr *attr)
>>>>>>             if (status < 0)
>>>>>>                 mlog_errno(status);
>>>>>>         }
>>>>>> -    if (inode_locked)
>>>>>> +    if (inode_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>>             ocfs2_inode_unlock(inode, 1);
>>>>>> +    }
>>>>>>           brelse(bh);
>>>>>>         return status;
>>>>>> @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
>>>>>>     int ocfs2_permission(struct inode *inode, int mask)
>>>>>>     {
>>>>>>         int ret;
>>>>>> +    int has_locked;
>>>>>> +    struct ocfs2_holder oh;
>>>>>> +    struct ocfs2_lock_res *lockres;
>>>>>>           if (mask & MAY_NOT_BLOCK)
>>>>>>             return -ECHILD;
>>>>>>     -    ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>> -    if (ret) {
>>>>>> -        if (ret != -ENOENT)
>>>>>> -            mlog_errno(ret);
>>>>>> -        goto out;
>>>>>> +    lockres = &OCFS2_I(inode)->ip_inode_lockres;
>>>>>> +    has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
>>>>> The same thing as ocfs2_setattr.
>>>> OK. I will think over your suggestions!
>>>>
>>>> Thanks,
>>>> Eric
>>>>
>>>>> Thanks,
>>>>> Junxiao.
>>>>>> +    if (!has_locked) {
>>>>>> +        ret = ocfs2_inode_lock(inode, NULL, 0);
>>>>>> +        if (ret) {
>>>>>> +            if (ret != -ENOENT)
>>>>>> +                mlog_errno(ret);
>>>>>> +            goto out;
>>>>>> +        }
>>>>>> +        ocfs2_add_holder(lockres, &oh);
>>>>>>         }
>>>>>>           ret = generic_permission(inode, mask);
>>>>>>     -    ocfs2_inode_unlock(inode, 0);
>>>>>> +    if (!has_locked) {
>>>>>> +        ocfs2_remove_holder(lockres, &oh);
>>>>>> +        ocfs2_inode_unlock(inode, 0);
>>>>>> +    }
>>>>>>     out:
>>>>>>         return ret;
>>>>>>     }
>>>>>>
>

Patch

diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index bed1fcb..c539890 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -284,16 +284,31 @@  int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	struct buffer_head *bh = NULL;
 	int status = 0;
-
-	status = ocfs2_inode_lock(inode, &bh, 1);
+	int arg_flags = 0, has_locked;
+	struct ocfs2_holder oh;
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
+	if (has_locked)
+		arg_flags = OCFS2_META_LOCK_GETBH;
+	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
 		return status;
 	}
+	if (!has_locked)
+		ocfs2_add_holder(lockres, &oh);
+
 	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
-	ocfs2_inode_unlock(inode, 1);
+
+	if (!has_locked) {
+		ocfs2_remove_holder(lockres, &oh);
+		ocfs2_inode_unlock(inode, 1);
+	}
 	brelse(bh);
+
 	return status;
 }
 
@@ -303,21 +318,35 @@  struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
 	struct buffer_head *di_bh = NULL;
 	struct posix_acl *acl;
 	int ret;
+	int arg_flags = 0, has_locked;
+	struct ocfs2_holder oh;
+	struct ocfs2_lock_res *lockres;
 
 	osb = OCFS2_SB(inode->i_sb);
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
 		return NULL;
-	ret = ocfs2_inode_lock(inode, &di_bh, 0);
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
+	if (has_locked)
+		arg_flags = OCFS2_META_LOCK_GETBH;
+	ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
 	if (ret < 0) {
 		if (ret != -ENOENT)
 			mlog_errno(ret);
 		return ERR_PTR(ret);
 	}
+	if (!has_locked)
+		ocfs2_add_holder(lockres, &oh);
 
 	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
 
-	ocfs2_inode_unlock(inode, 0);
+	if (!has_locked) {
+		ocfs2_remove_holder(lockres, &oh);
+		ocfs2_inode_unlock(inode, 0);
+	}
 	brelse(di_bh);
+
 	return acl;
 }
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index c488965..62be75d 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1138,6 +1138,9 @@  int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	handle_t *handle = NULL;
 	struct dquot *transfer_to[MAXQUOTAS] = { };
 	int qtype;
+	int arg_flags = 0, had_lock;
+	struct ocfs2_holder oh;
+	struct ocfs2_lock_res *lockres;
 
 	trace_ocfs2_setattr(inode, dentry,
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1173,13 +1176,20 @@  int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	status = ocfs2_inode_lock(inode, &bh, 1);
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
+	if (had_lock)
+		arg_flags = OCFS2_META_LOCK_GETBH;
+	status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
 		goto bail_unlock_rw;
 	}
-	inode_locked = 1;
+	if (!had_lock) {
+		ocfs2_add_holder(lockres, &oh);
+		inode_locked = 1;
+	}
 
 	if (size_change) {
 		status = inode_newsize_ok(inode, attr->ia_size);
@@ -1260,7 +1270,8 @@  int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
 bail_unlock:
-	if (status) {
+	if (status && inode_locked) {
+		ocfs2_remove_holder(lockres, &oh);
 		ocfs2_inode_unlock(inode, 1);
 		inode_locked = 0;
 	}
@@ -1278,8 +1289,10 @@  int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		if (status < 0)
 			mlog_errno(status);
 	}
-	if (inode_locked)
+	if (inode_locked) {
+		ocfs2_remove_holder(lockres, &oh);
 		ocfs2_inode_unlock(inode, 1);
+	}
 
 	brelse(bh);
 	return status;
@@ -1321,20 +1334,31 @@  int ocfs2_getattr(struct vfsmount *mnt,
 int ocfs2_permission(struct inode *inode, int mask)
 {
 	int ret;
+	int has_locked;
+	struct ocfs2_holder oh;
+	struct ocfs2_lock_res *lockres;
 
 	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
-	ret = ocfs2_inode_lock(inode, NULL, 0);
-	if (ret) {
-		if (ret != -ENOENT)
-			mlog_errno(ret);
-		goto out;
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
+	if (!has_locked) {
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			if (ret != -ENOENT)
+				mlog_errno(ret);
+			goto out;
+		}
+		ocfs2_add_holder(lockres, &oh);
 	}
 
 	ret = generic_permission(inode, mask);
 
-	ocfs2_inode_unlock(inode, 0);
+	if (!has_locked) {
+		ocfs2_remove_holder(lockres, &oh);
+		ocfs2_inode_unlock(inode, 0);
+	}
 out:
 	return ret;
 }