[v2,2/2] xfs: Close race between direct IO and xfs_break_layouts()

Message ID 153374915981.40645.3350205963852459041.stgit@djiang5-desk3.ch.intel.com
State Not Applicable
Headers show
Series
  • [v2,1/2] ext4: Close race between direct IO and ext4_break_layouts()
Related show

Commit Message

Dave Jiang Aug. 8, 2018, 5:26 p.m.
This patch is the duplicate of ross's fix for ext4 for xfs.

If the refcount of a page is lowered between the time that it is returned
by dax_busy_page() and when the refcount is again checked in
xfs_break_layouts() => ___wait_var_event(), the waiting function
xfs_wait_dax_page() will never be called.  This means that
xfs_break_layouts() will still have 'retry' set to false, so we'll stop
looping and never check the refcount of other pages in this inode.

Instead, always continue looping as long as dax_layout_busy_page() gives us
a page which it found with an elevated refcount.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---

v2:
- Rename parameter from did_unlock to retry (Jan) 

 fs/xfs/xfs_file.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

Comments

Jan Kara Aug. 9, 2018, 8:57 a.m. | #1
On Wed 08-08-18 10:26:36, Dave Jiang wrote:
> This patch is the duplicate of ross's fix for ext4 for xfs.
> 
> If the refcount of a page is lowered between the time that it is returned
> by dax_busy_page() and when the refcount is again checked in
> xfs_break_layouts() => ___wait_var_event(), the waiting function
> xfs_wait_dax_page() will never be called.  This means that
> xfs_break_layouts() will still have 'retry' set to false, so we'll stop
> looping and never check the refcount of other pages in this inode.
> 
> Instead, always continue looping as long as dax_layout_busy_page() gives us
> a page which it found with an elevated refcount.
> 
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>

I think I gave you my reviewed-by tag already for the previous version. But
here it is again:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
> 
> v2:
> - Rename parameter from did_unlock to retry (Jan) 
> 
>  fs/xfs/xfs_file.c |    9 ++++-----
>  1 file changed, 4 insertions(+), 5 deletions(-)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index a3e7767a5715..cd6f0d8c4922 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -721,12 +721,10 @@ xfs_file_write_iter(
>  
>  static void
>  xfs_wait_dax_page(
> -	struct inode		*inode,
> -	bool			*did_unlock)
> +	struct inode		*inode)
>  {
>  	struct xfs_inode        *ip = XFS_I(inode);
>  
> -	*did_unlock = true;
>  	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
>  	schedule();
>  	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
> @@ -736,7 +734,7 @@ static int
>  xfs_break_dax_layouts(
>  	struct inode		*inode,
>  	uint			iolock,
> -	bool			*did_unlock)
> +	bool			*retry)
>  {
>  	struct page		*page;
>  
> @@ -746,9 +744,10 @@ xfs_break_dax_layouts(
>  	if (!page)
>  		return 0;
>  
> +	*retry = true;
>  	return ___wait_var_event(&page->_refcount,
>  			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
> -			0, 0, xfs_wait_dax_page(inode, did_unlock));
> +			0, 0, xfs_wait_dax_page(inode));
>  }
>  
>  int
>
Dave Jiang Aug. 9, 2018, 4:21 p.m. | #2
On 08/09/2018 01:57 AM, Jan Kara wrote:
> On Wed 08-08-18 10:26:36, Dave Jiang wrote:
>> This patch is the duplicate of ross's fix for ext4 for xfs.
>>
>> If the refcount of a page is lowered between the time that it is returned
>> by dax_busy_page() and when the refcount is again checked in
>> xfs_break_layouts() => ___wait_var_event(), the waiting function
>> xfs_wait_dax_page() will never be called.  This means that
>> xfs_break_layouts() will still have 'retry' set to false, so we'll stop
>> looping and never check the refcount of other pages in this inode.
>>
>> Instead, always continue looping as long as dax_layout_busy_page() gives us
>> a page which it found with an elevated refcount.
>>
>> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> 
> I think I gave you my reviewed-by tag already for the previous version. But
> here it is again:
> 
> Reviewed-by: Jan Kara <jack@suse.cz>

Yes you did. I forgot to append it when I sent it out the first time. I
resent it. :)

> 
> 								Honza
> 
>> ---
>>
>> v2:
>> - Rename parameter from did_unlock to retry (Jan) 
>>
>>  fs/xfs/xfs_file.c |    9 ++++-----
>>  1 file changed, 4 insertions(+), 5 deletions(-)
>>
>> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
>> index a3e7767a5715..cd6f0d8c4922 100644
>> --- a/fs/xfs/xfs_file.c
>> +++ b/fs/xfs/xfs_file.c
>> @@ -721,12 +721,10 @@ xfs_file_write_iter(
>>  
>>  static void
>>  xfs_wait_dax_page(
>> -	struct inode		*inode,
>> -	bool			*did_unlock)
>> +	struct inode		*inode)
>>  {
>>  	struct xfs_inode        *ip = XFS_I(inode);
>>  
>> -	*did_unlock = true;
>>  	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
>>  	schedule();
>>  	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
>> @@ -736,7 +734,7 @@ static int
>>  xfs_break_dax_layouts(
>>  	struct inode		*inode,
>>  	uint			iolock,
>> -	bool			*did_unlock)
>> +	bool			*retry)
>>  {
>>  	struct page		*page;
>>  
>> @@ -746,9 +744,10 @@ xfs_break_dax_layouts(
>>  	if (!page)
>>  		return 0;
>>  
>> +	*retry = true;
>>  	return ___wait_var_event(&page->_refcount,
>>  			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
>> -			0, 0, xfs_wait_dax_page(inode, did_unlock));
>> +			0, 0, xfs_wait_dax_page(inode));
>>  }
>>  
>>  int
>>

Patch

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a3e7767a5715..cd6f0d8c4922 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -721,12 +721,10 @@  xfs_file_write_iter(
 
 static void
 xfs_wait_dax_page(
-	struct inode		*inode,
-	bool			*did_unlock)
+	struct inode		*inode)
 {
 	struct xfs_inode        *ip = XFS_I(inode);
 
-	*did_unlock = true;
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	schedule();
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
@@ -736,7 +734,7 @@  static int
 xfs_break_dax_layouts(
 	struct inode		*inode,
 	uint			iolock,
-	bool			*did_unlock)
+	bool			*retry)
 {
 	struct page		*page;
 
@@ -746,9 +744,10 @@  xfs_break_dax_layouts(
 	if (!page)
 		return 0;
 
+	*retry = true;
 	return ___wait_var_event(&page->_refcount,
 			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
-			0, 0, xfs_wait_dax_page(inode, did_unlock));
+			0, 0, xfs_wait_dax_page(inode));
 }
 
 int