[V4,09/13] fs/xfs: Add write aops lock to xfs layer
diff mbox series

Message ID 20200221004134.30599-10-ira.weiny@intel.com
State Superseded
Headers show
Series
  • Enable per-file/per-directory DAX operations V4
Related show

Commit Message

Ira Weiny Feb. 21, 2020, 12:41 a.m. UTC
From: Ira Weiny <ira.weiny@intel.com>

XFS requires the use of the aops of an inode to quiesced prior to
changing it to/from the DAX aops vector.

Take the aops write lock while changing DAX state.

We define a new XFS_DAX_EXCL lock type to carry the lock through to
transaction completion.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>

---
Changes from v3:
	Change locking function names to reflect changes in previous
	patches.

Changes from V2:
	Change name of patch (WAS: fs/xfs: Add lock/unlock state to xfs)
	Remove the xfs specific lock and move to the vfs layer.
		We still use XFS_LOCK_DAX_EXCL to be able to pass this
		flag through to the transaction code.  But we no longer
		have a lock specific to xfs.  This removes a lot of code
		from the XFS layer, preps us for using this in ext4, and
		is actually more straight forward now that all the
		locking requirements are better known.

	Fix locking order comment
	Rework for new 'state' names
	(Other comments on the previous patch are not applicable with
	new patch as much of the code was removed in favor of the vfs
	level lock)
---
 fs/xfs/xfs_inode.c | 22 ++++++++++++++++++++--
 fs/xfs/xfs_inode.h |  7 +++++--
 2 files changed, 25 insertions(+), 4 deletions(-)

Comments

Darrick J. Wong Feb. 22, 2020, 12:31 a.m. UTC | #1
On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> From: Ira Weiny <ira.weiny@intel.com>
> 
> XFS requires the use of the aops of an inode to quiesced prior to
> changing it to/from the DAX aops vector.
> 
> Take the aops write lock while changing DAX state.
> 
> We define a new XFS_DAX_EXCL lock type to carry the lock through to
> transaction completion.
> 
> Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> 
> ---
> Changes from v3:
> 	Change locking function names to reflect changes in previous
> 	patches.
> 
> Changes from V2:
> 	Change name of patch (WAS: fs/xfs: Add lock/unlock state to xfs)
> 	Remove the xfs specific lock and move to the vfs layer.
> 		We still use XFS_LOCK_DAX_EXCL to be able to pass this
> 		flag through to the transaction code.  But we no longer
> 		have a lock specific to xfs.  This removes a lot of code
> 		from the XFS layer, preps us for using this in ext4, and
> 		is actually more straight forward now that all the
> 		locking requirements are better known.
> 
> 	Fix locking order comment
> 	Rework for new 'state' names
> 	(Other comments on the previous patch are not applicable with
> 	new patch as much of the code was removed in favor of the vfs
> 	level lock)
> ---
>  fs/xfs/xfs_inode.c | 22 ++++++++++++++++++++--
>  fs/xfs/xfs_inode.h |  7 +++++--
>  2 files changed, 25 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> index 35df324875db..5b014c428f0f 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
>   *
>   * Basic locking order:
>   *
> - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock

"dax_sem"?  I thought this was now called i_aops_sem?

>   *
>   * mmap_sem locking order:
>   *
>   * i_rwsem -> page lock -> mmap_sem
> - * mmap_sem -> i_mmap_lock -> page_lock
> + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
>   *
>   * The difference in mmap_sem locking order mean that we cannot hold the
>   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> @@ -182,6 +182,9 @@ xfs_ilock(
>  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
>  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
>  
> +	if (lock_flags & XFS_DAX_EXCL)

And similarly, I think this should be XFS_OPSLOCK_EXCL...

--D

> +		inode_aops_down_write(VFS_I(ip));
> +
>  	if (lock_flags & XFS_IOLOCK_EXCL) {
>  		down_write_nested(&VFS_I(ip)->i_rwsem,
>  				  XFS_IOLOCK_DEP(lock_flags));
> @@ -224,6 +227,8 @@ xfs_ilock_nowait(
>  	 * You can't set both SHARED and EXCL for the same lock,
>  	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
>  	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
> +	 *
> +	 * XFS_DAX_* is not allowed
>  	 */
>  	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
>  	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
> @@ -232,6 +237,7 @@ xfs_ilock_nowait(
>  	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
>  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
>  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> +	ASSERT((lock_flags & XFS_DAX_EXCL) == 0);
>  
>  	if (lock_flags & XFS_IOLOCK_EXCL) {
>  		if (!down_write_trylock(&VFS_I(ip)->i_rwsem))
> @@ -318,6 +324,9 @@ xfs_iunlock(
>  	else if (lock_flags & XFS_ILOCK_SHARED)
>  		mrunlock_shared(&ip->i_lock);
>  
> +	if (lock_flags & XFS_DAX_EXCL)
> +		inode_aops_up_write(VFS_I(ip));
> +
>  	trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
>  }
>  
> @@ -333,6 +342,8 @@ xfs_ilock_demote(
>  	ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL));
>  	ASSERT((lock_flags &
>  		~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
> +	/* XFS_DAX_* is not allowed */
> +	ASSERT((lock_flags & XFS_DAX_EXCL) == 0);
>  
>  	if (lock_flags & XFS_ILOCK_EXCL)
>  		mrdemote(&ip->i_lock);
> @@ -465,6 +476,9 @@ xfs_lock_inodes(
>  	ASSERT(!(lock_mode & XFS_ILOCK_EXCL) ||
>  		inodes <= XFS_ILOCK_MAX_SUBCLASS + 1);
>  
> +	/* XFS_DAX_* is not allowed */
> +	ASSERT((lock_mode & XFS_DAX_EXCL) == 0);
> +
>  	if (lock_mode & XFS_IOLOCK_EXCL) {
>  		ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)));
>  	} else if (lock_mode & XFS_MMAPLOCK_EXCL)
> @@ -566,6 +580,10 @@ xfs_lock_two_inodes(
>  	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
>  	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
>  
> +	/* XFS_DAX_* is not allowed */
> +	ASSERT((ip0_mode & XFS_DAX_EXCL) == 0);
> +	ASSERT((ip1_mode & XFS_DAX_EXCL) == 0);
> +
>  	ASSERT(ip0->i_ino != ip1->i_ino);
>  
>  	if (ip0->i_ino > ip1->i_ino) {
> diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
> index 492e53992fa9..25fe20740bf7 100644
> --- a/fs/xfs/xfs_inode.h
> +++ b/fs/xfs/xfs_inode.h
> @@ -278,10 +278,12 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
>  #define	XFS_ILOCK_SHARED	(1<<3)
>  #define	XFS_MMAPLOCK_EXCL	(1<<4)
>  #define	XFS_MMAPLOCK_SHARED	(1<<5)
> +#define	XFS_DAX_EXCL		(1<<6)
>  
>  #define XFS_LOCK_MASK		(XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \
>  				| XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \
> -				| XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED)
> +				| XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED \
> +				| XFS_DAX_EXCL)
>  
>  #define XFS_LOCK_FLAGS \
>  	{ XFS_IOLOCK_EXCL,	"IOLOCK_EXCL" }, \
> @@ -289,7 +291,8 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
>  	{ XFS_ILOCK_EXCL,	"ILOCK_EXCL" }, \
>  	{ XFS_ILOCK_SHARED,	"ILOCK_SHARED" }, \
>  	{ XFS_MMAPLOCK_EXCL,	"MMAPLOCK_EXCL" }, \
> -	{ XFS_MMAPLOCK_SHARED,	"MMAPLOCK_SHARED" }
> +	{ XFS_MMAPLOCK_SHARED,	"MMAPLOCK_SHARED" }, \
> +	{ XFS_DAX_EXCL,		"DAX_EXCL" }
>  
>  
>  /*
> -- 
> 2.21.0
>
Ira Weiny Feb. 23, 2020, 3:04 p.m. UTC | #2
On Fri, Feb 21, 2020 at 04:31:09PM -0800, Darrick J. Wong wrote:
> On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> > From: Ira Weiny <ira.weiny@intel.com>
> > 
> > XFS requires the use of the aops of an inode to quiesced prior to
> > changing it to/from the DAX aops vector.
> > 
> > Take the aops write lock while changing DAX state.
> > 
> > We define a new XFS_DAX_EXCL lock type to carry the lock through to
> > transaction completion.
> > 
> > Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> > 
> > ---
> > Changes from v3:
> > 	Change locking function names to reflect changes in previous
> > 	patches.
> > 
> > Changes from V2:
> > 	Change name of patch (WAS: fs/xfs: Add lock/unlock state to xfs)
> > 	Remove the xfs specific lock and move to the vfs layer.
> > 		We still use XFS_LOCK_DAX_EXCL to be able to pass this
> > 		flag through to the transaction code.  But we no longer
> > 		have a lock specific to xfs.  This removes a lot of code
> > 		from the XFS layer, preps us for using this in ext4, and
> > 		is actually more straight forward now that all the
> > 		locking requirements are better known.
> > 
> > 	Fix locking order comment
> > 	Rework for new 'state' names
> > 	(Other comments on the previous patch are not applicable with
> > 	new patch as much of the code was removed in favor of the vfs
> > 	level lock)
> > ---
> >  fs/xfs/xfs_inode.c | 22 ++++++++++++++++++++--
> >  fs/xfs/xfs_inode.h |  7 +++++--
> >  2 files changed, 25 insertions(+), 4 deletions(-)
> > 
> > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > index 35df324875db..5b014c428f0f 100644
> > --- a/fs/xfs/xfs_inode.c
> > +++ b/fs/xfs/xfs_inode.c
> > @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
> >   *
> >   * Basic locking order:
> >   *
> > - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> 
> "dax_sem"?  I thought this was now called i_aops_sem?

:-/ yep...

> 
> >   *
> >   * mmap_sem locking order:
> >   *
> >   * i_rwsem -> page lock -> mmap_sem
> > - * mmap_sem -> i_mmap_lock -> page_lock
> > + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
> >   *
> >   * The difference in mmap_sem locking order mean that we cannot hold the
> >   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> > @@ -182,6 +182,9 @@ xfs_ilock(
> >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> >  
> > +	if (lock_flags & XFS_DAX_EXCL)
> 
> And similarly, I think this should be XFS_OPSLOCK_EXCL...

... and ... yes...

Thanks for the review, I'll clean it up.

Ira

> 
> --D
> 
> > +		inode_aops_down_write(VFS_I(ip));
> > +
> >  	if (lock_flags & XFS_IOLOCK_EXCL) {
> >  		down_write_nested(&VFS_I(ip)->i_rwsem,
> >  				  XFS_IOLOCK_DEP(lock_flags));
> > @@ -224,6 +227,8 @@ xfs_ilock_nowait(
> >  	 * You can't set both SHARED and EXCL for the same lock,
> >  	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
> >  	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
> > +	 *
> > +	 * XFS_DAX_* is not allowed
> >  	 */
> >  	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
> >  	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
> > @@ -232,6 +237,7 @@ xfs_ilock_nowait(
> >  	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
> >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> > +	ASSERT((lock_flags & XFS_DAX_EXCL) == 0);
> >  
> >  	if (lock_flags & XFS_IOLOCK_EXCL) {
> >  		if (!down_write_trylock(&VFS_I(ip)->i_rwsem))
> > @@ -318,6 +324,9 @@ xfs_iunlock(
> >  	else if (lock_flags & XFS_ILOCK_SHARED)
> >  		mrunlock_shared(&ip->i_lock);
> >  
> > +	if (lock_flags & XFS_DAX_EXCL)
> > +		inode_aops_up_write(VFS_I(ip));
> > +
> >  	trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
> >  }
> >  
> > @@ -333,6 +342,8 @@ xfs_ilock_demote(
> >  	ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL));
> >  	ASSERT((lock_flags &
> >  		~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
> > +	/* XFS_DAX_* is not allowed */
> > +	ASSERT((lock_flags & XFS_DAX_EXCL) == 0);
> >  
> >  	if (lock_flags & XFS_ILOCK_EXCL)
> >  		mrdemote(&ip->i_lock);
> > @@ -465,6 +476,9 @@ xfs_lock_inodes(
> >  	ASSERT(!(lock_mode & XFS_ILOCK_EXCL) ||
> >  		inodes <= XFS_ILOCK_MAX_SUBCLASS + 1);
> >  
> > +	/* XFS_DAX_* is not allowed */
> > +	ASSERT((lock_mode & XFS_DAX_EXCL) == 0);
> > +
> >  	if (lock_mode & XFS_IOLOCK_EXCL) {
> >  		ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)));
> >  	} else if (lock_mode & XFS_MMAPLOCK_EXCL)
> > @@ -566,6 +580,10 @@ xfs_lock_two_inodes(
> >  	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
> >  	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
> >  
> > +	/* XFS_DAX_* is not allowed */
> > +	ASSERT((ip0_mode & XFS_DAX_EXCL) == 0);
> > +	ASSERT((ip1_mode & XFS_DAX_EXCL) == 0);
> > +
> >  	ASSERT(ip0->i_ino != ip1->i_ino);
> >  
> >  	if (ip0->i_ino > ip1->i_ino) {
> > diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
> > index 492e53992fa9..25fe20740bf7 100644
> > --- a/fs/xfs/xfs_inode.h
> > +++ b/fs/xfs/xfs_inode.h
> > @@ -278,10 +278,12 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
> >  #define	XFS_ILOCK_SHARED	(1<<3)
> >  #define	XFS_MMAPLOCK_EXCL	(1<<4)
> >  #define	XFS_MMAPLOCK_SHARED	(1<<5)
> > +#define	XFS_DAX_EXCL		(1<<6)
> >  
> >  #define XFS_LOCK_MASK		(XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \
> >  				| XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \
> > -				| XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED)
> > +				| XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED \
> > +				| XFS_DAX_EXCL)
> >  
> >  #define XFS_LOCK_FLAGS \
> >  	{ XFS_IOLOCK_EXCL,	"IOLOCK_EXCL" }, \
> > @@ -289,7 +291,8 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
> >  	{ XFS_ILOCK_EXCL,	"ILOCK_EXCL" }, \
> >  	{ XFS_ILOCK_SHARED,	"ILOCK_SHARED" }, \
> >  	{ XFS_MMAPLOCK_EXCL,	"MMAPLOCK_EXCL" }, \
> > -	{ XFS_MMAPLOCK_SHARED,	"MMAPLOCK_SHARED" }
> > +	{ XFS_MMAPLOCK_SHARED,	"MMAPLOCK_SHARED" }, \
> > +	{ XFS_DAX_EXCL,		"DAX_EXCL" }
> >  
> >  
> >  /*
> > -- 
> > 2.21.0
> >
Dave Chinner Feb. 24, 2020, 12:34 a.m. UTC | #3
On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> From: Ira Weiny <ira.weiny@intel.com>
> 
> XFS requires the use of the aops of an inode to quiesced prior to
> changing it to/from the DAX aops vector.
> 
> Take the aops write lock while changing DAX state.
> 
> We define a new XFS_DAX_EXCL lock type to carry the lock through to
> transaction completion.
> 
> Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> 
> ---
> Changes from v3:
> 	Change locking function names to reflect changes in previous
> 	patches.
> 
> Changes from V2:
> 	Change name of patch (WAS: fs/xfs: Add lock/unlock state to xfs)
> 	Remove the xfs specific lock and move to the vfs layer.
> 		We still use XFS_LOCK_DAX_EXCL to be able to pass this
> 		flag through to the transaction code.  But we no longer
> 		have a lock specific to xfs.  This removes a lot of code
> 		from the XFS layer, preps us for using this in ext4, and
> 		is actually more straight forward now that all the
> 		locking requirements are better known.
> 
> 	Fix locking order comment
> 	Rework for new 'state' names
> 	(Other comments on the previous patch are not applicable with
> 	new patch as much of the code was removed in favor of the vfs
> 	level lock)
> ---
>  fs/xfs/xfs_inode.c | 22 ++++++++++++++++++++--
>  fs/xfs/xfs_inode.h |  7 +++++--
>  2 files changed, 25 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> index 35df324875db..5b014c428f0f 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
>   *
>   * Basic locking order:
>   *
> - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
>   *
>   * mmap_sem locking order:
>   *
>   * i_rwsem -> page lock -> mmap_sem
> - * mmap_sem -> i_mmap_lock -> page_lock
> + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
>   *
>   * The difference in mmap_sem locking order mean that we cannot hold the
>   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> @@ -182,6 +182,9 @@ xfs_ilock(
>  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
>  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
>  
> +	if (lock_flags & XFS_DAX_EXCL)
> +		inode_aops_down_write(VFS_I(ip));

I largely don't see the point of adding this to xfs_ilock/iunlock.

It's only got one caller, so I don't see much point in adding it to
an interface that has over a hundred other call sites that don't
need or use this lock. just open code it where it is needed in the
ioctl code.

Cheers,

Dave.
Ira Weiny Feb. 24, 2020, 7:57 p.m. UTC | #4
On Mon, Feb 24, 2020 at 11:34:55AM +1100, Dave Chinner wrote:
> On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> > From: Ira Weiny <ira.weiny@intel.com>
> > 

[snip]

> > 
> > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > index 35df324875db..5b014c428f0f 100644
> > --- a/fs/xfs/xfs_inode.c
> > +++ b/fs/xfs/xfs_inode.c
> > @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
> >   *
> >   * Basic locking order:
> >   *
> > - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> >   *
> >   * mmap_sem locking order:
> >   *
> >   * i_rwsem -> page lock -> mmap_sem
> > - * mmap_sem -> i_mmap_lock -> page_lock
> > + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
> >   *
> >   * The difference in mmap_sem locking order mean that we cannot hold the
> >   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> > @@ -182,6 +182,9 @@ xfs_ilock(
> >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> >  
> > +	if (lock_flags & XFS_DAX_EXCL)
> > +		inode_aops_down_write(VFS_I(ip));
> 
> I largely don't see the point of adding this to xfs_ilock/iunlock.
> 
> It's only got one caller, so I don't see much point in adding it to
> an interface that has over a hundred other call sites that don't
> need or use this lock. just open code it where it is needed in the
> ioctl code.

I know it seems overkill but if we don't do this we need to code a flag to be
returned from xfs_ioctl_setattr_dax_invalidate().  This flag is then used in
xfs_ioctl_setattr_get_trans() to create the transaction log item which can then
be properly used to unlock the lock in xfs_inode_item_release()

I don't know of a cleaner way to communicate to xfs_inode_item_release() to
unlock i_aops_sem after the transaction is complete.

Ira

> 
> Cheers,
> 
> Dave.
> -- 
> Dave Chinner
> david@fromorbit.com
Dave Chinner Feb. 24, 2020, 10:32 p.m. UTC | #5
On Mon, Feb 24, 2020 at 11:57:36AM -0800, Ira Weiny wrote:
> On Mon, Feb 24, 2020 at 11:34:55AM +1100, Dave Chinner wrote:
> > On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> > > From: Ira Weiny <ira.weiny@intel.com>
> > > 
> 
> [snip]
> 
> > > 
> > > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > > index 35df324875db..5b014c428f0f 100644
> > > --- a/fs/xfs/xfs_inode.c
> > > +++ b/fs/xfs/xfs_inode.c
> > > @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
> > >   *
> > >   * Basic locking order:
> > >   *
> > > - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > >   *
> > >   * mmap_sem locking order:
> > >   *
> > >   * i_rwsem -> page lock -> mmap_sem
> > > - * mmap_sem -> i_mmap_lock -> page_lock
> > > + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
> > >   *
> > >   * The difference in mmap_sem locking order mean that we cannot hold the
> > >   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> > > @@ -182,6 +182,9 @@ xfs_ilock(
> > >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> > >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> > >  
> > > +	if (lock_flags & XFS_DAX_EXCL)
> > > +		inode_aops_down_write(VFS_I(ip));
> > 
> > I largely don't see the point of adding this to xfs_ilock/iunlock.
> > 
> > It's only got one caller, so I don't see much point in adding it to
> > an interface that has over a hundred other call sites that don't
> > need or use this lock. just open code it where it is needed in the
> > ioctl code.
> 
> I know it seems overkill but if we don't do this we need to code a flag to be
> returned from xfs_ioctl_setattr_dax_invalidate().  This flag is then used in
> xfs_ioctl_setattr_get_trans() to create the transaction log item which can then
> be properly used to unlock the lock in xfs_inode_item_release()
> 
> I don't know of a cleaner way to communicate to xfs_inode_item_release() to
> unlock i_aops_sem after the transaction is complete.

We manually unlock inodes after transactions in many cases -
anywhere we do a rolling transaction, the inode locks do not get
released by the transaction. Hence for a one-off case like this it
doesn't really make sense to push all this infrastructure into the
transaction subsystem. Especially as we can manually lock before and
unlock after the transaction context without any real complexity.

This also means that we can, if necessary, do aops manipulation work
/after/ the transaction that changes on-disk state completes and we
still hold the aops reference exclusively. While we don't do that
now, I think it is worthwhile keeping our options open here....

Cheers,

Dave.
Ira Weiny Feb. 25, 2020, 9:12 p.m. UTC | #6
On Tue, Feb 25, 2020 at 09:32:45AM +1100, Dave Chinner wrote:
> On Mon, Feb 24, 2020 at 11:57:36AM -0800, Ira Weiny wrote:
> > On Mon, Feb 24, 2020 at 11:34:55AM +1100, Dave Chinner wrote:
> > > On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> > > > From: Ira Weiny <ira.weiny@intel.com>
> > > > 
> > 
> > [snip]
> > 
> > > > 
> > > > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > > > index 35df324875db..5b014c428f0f 100644
> > > > --- a/fs/xfs/xfs_inode.c
> > > > +++ b/fs/xfs/xfs_inode.c
> > > > @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
> > > >   *
> > > >   * Basic locking order:
> > > >   *
> > > > - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > > + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > >   *
> > > >   * mmap_sem locking order:
> > > >   *
> > > >   * i_rwsem -> page lock -> mmap_sem
> > > > - * mmap_sem -> i_mmap_lock -> page_lock
> > > > + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
> > > >   *
> > > >   * The difference in mmap_sem locking order mean that we cannot hold the
> > > >   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> > > > @@ -182,6 +182,9 @@ xfs_ilock(
> > > >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> > > >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> > > >  
> > > > +	if (lock_flags & XFS_DAX_EXCL)
> > > > +		inode_aops_down_write(VFS_I(ip));
> > > 
> > > I largely don't see the point of adding this to xfs_ilock/iunlock.
> > > 
> > > It's only got one caller, so I don't see much point in adding it to
> > > an interface that has over a hundred other call sites that don't
> > > need or use this lock. just open code it where it is needed in the
> > > ioctl code.
> > 
> > I know it seems overkill but if we don't do this we need to code a flag to be
> > returned from xfs_ioctl_setattr_dax_invalidate().  This flag is then used in
> > xfs_ioctl_setattr_get_trans() to create the transaction log item which can then
> > be properly used to unlock the lock in xfs_inode_item_release()
> > 
> > I don't know of a cleaner way to communicate to xfs_inode_item_release() to
> > unlock i_aops_sem after the transaction is complete.
> 
> We manually unlock inodes after transactions in many cases -
> anywhere we do a rolling transaction, the inode locks do not get
> released by the transaction. Hence for a one-off case like this it
> doesn't really make sense to push all this infrastructure into the
> transaction subsystem. Especially as we can manually lock before and
> unlock after the transaction context without any real complexity.

So does xfs_trans_commit() operate synchronously?

I want to understand this better because I have fought with a lot of ABBA
issues with these locks.  So...  can I hold the lock until after
xfs_trans_commit() and safely unlock it there... because the XFS_MMAPLOCK_EXCL,
XFS_IOLOCK_EXCL, and XFS_ILOCK_EXCL will be released at that point?  Thus
preserving the following lock order.

...
 * Basic locking order:
 *
 * i_aops_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
 *
...

Thanks for the review!
Ira

> 
> This also means that we can, if necessary, do aops manipulation work
> /after/ the transaction that changes on-disk state completes and we
> still hold the aops reference exclusively. While we don't do that
> now, I think it is worthwhile keeping our options open here....
> 
> Cheers,
> 
> Dave.
> -- 
> Dave Chinner
> david@fromorbit.com
Dave Chinner Feb. 25, 2020, 10:59 p.m. UTC | #7
On Tue, Feb 25, 2020 at 01:12:28PM -0800, Ira Weiny wrote:
> On Tue, Feb 25, 2020 at 09:32:45AM +1100, Dave Chinner wrote:
> > On Mon, Feb 24, 2020 at 11:57:36AM -0800, Ira Weiny wrote:
> > > On Mon, Feb 24, 2020 at 11:34:55AM +1100, Dave Chinner wrote:
> > > > On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> > > > > From: Ira Weiny <ira.weiny@intel.com>
> > > > > 
> > > 
> > > [snip]
> > > 
> > > > > 
> > > > > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > > > > index 35df324875db..5b014c428f0f 100644
> > > > > --- a/fs/xfs/xfs_inode.c
> > > > > +++ b/fs/xfs/xfs_inode.c
> > > > > @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
> > > > >   *
> > > > >   * Basic locking order:
> > > > >   *
> > > > > - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > > > + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > > >   *
> > > > >   * mmap_sem locking order:
> > > > >   *
> > > > >   * i_rwsem -> page lock -> mmap_sem
> > > > > - * mmap_sem -> i_mmap_lock -> page_lock
> > > > > + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
> > > > >   *
> > > > >   * The difference in mmap_sem locking order mean that we cannot hold the
> > > > >   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> > > > > @@ -182,6 +182,9 @@ xfs_ilock(
> > > > >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> > > > >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> > > > >  
> > > > > +	if (lock_flags & XFS_DAX_EXCL)
> > > > > +		inode_aops_down_write(VFS_I(ip));
> > > > 
> > > > I largely don't see the point of adding this to xfs_ilock/iunlock.
> > > > 
> > > > It's only got one caller, so I don't see much point in adding it to
> > > > an interface that has over a hundred other call sites that don't
> > > > need or use this lock. just open code it where it is needed in the
> > > > ioctl code.
> > > 
> > > I know it seems overkill but if we don't do this we need to code a flag to be
> > > returned from xfs_ioctl_setattr_dax_invalidate().  This flag is then used in
> > > xfs_ioctl_setattr_get_trans() to create the transaction log item which can then
> > > be properly used to unlock the lock in xfs_inode_item_release()
> > > 
> > > I don't know of a cleaner way to communicate to xfs_inode_item_release() to
> > > unlock i_aops_sem after the transaction is complete.
> > 
> > We manually unlock inodes after transactions in many cases -
> > anywhere we do a rolling transaction, the inode locks do not get
> > released by the transaction. Hence for a one-off case like this it
> > doesn't really make sense to push all this infrastructure into the
> > transaction subsystem. Especially as we can manually lock before and
> > unlock after the transaction context without any real complexity.
> 
> So does xfs_trans_commit() operate synchronously?

What do you mean by "synchronously", and what are you expecting to
occur (a)synchronously with respect to filesystem objects and/or
on-disk state?

Keep in mid that the xfs transaction subsystem is a complex
asynchronous IO engine full of feedback loops and resource
management, so asking if something is "synchronous" without any
other context is a difficult question to answer :)

> I want to understand this better because I have fought with a lot of ABBA
> issues with these locks.  So...  can I hold the lock until after
> xfs_trans_commit() and safely unlock it there... because the XFS_MMAPLOCK_EXCL,
> XFS_IOLOCK_EXCL, and XFS_ILOCK_EXCL will be released at that point?  Thus
> preserving the following lock order.

See how operations like xfs_create, xfs_unlink, etc work. The don't
specify flags to xfs_ijoin(), and so the transaction commits don't
automatically unlock the inode. This is necessary so that rolling
transactions are executed atomically w.r.t. inode access - no-one
can lock and access the inode while a multi-commit rolling
transaction on the inode is on-going.

In this case it's just a single commit and we don't need to keep
it locked after the change is made, so we can unlock the inode
on commit. So for the XFS internal locks the code is fine and
doesn't need to change. We just need to wrap the VFS aops lock (if
we keep it) around the outside of all the XFS locking until the
transaction commits and unlocks the XFS locks...

Cheers,

Dave.
Ira Weiny Feb. 26, 2020, 6:02 p.m. UTC | #8
On Wed, Feb 26, 2020 at 09:59:41AM +1100, Dave Chinner wrote:
> On Tue, Feb 25, 2020 at 01:12:28PM -0800, Ira Weiny wrote:
> > On Tue, Feb 25, 2020 at 09:32:45AM +1100, Dave Chinner wrote:
> > > On Mon, Feb 24, 2020 at 11:57:36AM -0800, Ira Weiny wrote:
> > > > On Mon, Feb 24, 2020 at 11:34:55AM +1100, Dave Chinner wrote:
> > > > > On Thu, Feb 20, 2020 at 04:41:30PM -0800, ira.weiny@intel.com wrote:
> > > > > > From: Ira Weiny <ira.weiny@intel.com>
> > > > > > 
> > > > 
> > > > [snip]
> > > > 
> > > > > > 
> > > > > > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > > > > > index 35df324875db..5b014c428f0f 100644
> > > > > > --- a/fs/xfs/xfs_inode.c
> > > > > > +++ b/fs/xfs/xfs_inode.c
> > > > > > @@ -142,12 +142,12 @@ xfs_ilock_attr_map_shared(
> > > > > >   *
> > > > > >   * Basic locking order:
> > > > > >   *
> > > > > > - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > > > > + * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
> > > > > >   *
> > > > > >   * mmap_sem locking order:
> > > > > >   *
> > > > > >   * i_rwsem -> page lock -> mmap_sem
> > > > > > - * mmap_sem -> i_mmap_lock -> page_lock
> > > > > > + * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
> > > > > >   *
> > > > > >   * The difference in mmap_sem locking order mean that we cannot hold the
> > > > > >   * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
> > > > > > @@ -182,6 +182,9 @@ xfs_ilock(
> > > > > >  	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
> > > > > >  	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
> > > > > >  
> > > > > > +	if (lock_flags & XFS_DAX_EXCL)
> > > > > > +		inode_aops_down_write(VFS_I(ip));
> > > > > 
> > > > > I largely don't see the point of adding this to xfs_ilock/iunlock.
> > > > > 
> > > > > It's only got one caller, so I don't see much point in adding it to
> > > > > an interface that has over a hundred other call sites that don't
> > > > > need or use this lock. just open code it where it is needed in the
> > > > > ioctl code.
> > > > 
> > > > I know it seems overkill but if we don't do this we need to code a flag to be
> > > > returned from xfs_ioctl_setattr_dax_invalidate().  This flag is then used in
> > > > xfs_ioctl_setattr_get_trans() to create the transaction log item which can then
> > > > be properly used to unlock the lock in xfs_inode_item_release()
> > > > 
> > > > I don't know of a cleaner way to communicate to xfs_inode_item_release() to
> > > > unlock i_aops_sem after the transaction is complete.
> > > 
> > > We manually unlock inodes after transactions in many cases -
> > > anywhere we do a rolling transaction, the inode locks do not get
> > > released by the transaction. Hence for a one-off case like this it
> > > doesn't really make sense to push all this infrastructure into the
> > > transaction subsystem. Especially as we can manually lock before and
> > > unlock after the transaction context without any real complexity.
> > 
> > So does xfs_trans_commit() operate synchronously?
> 
> What do you mean by "synchronously", and what are you expecting to
> occur (a)synchronously with respect to filesystem objects and/or
> on-disk state?
> 
> Keep in mid that the xfs transaction subsystem is a complex
> asynchronous IO engine full of feedback loops and resource
> management,

This is precisely why I added the lock to the transaction state.  So that I
could guarantee that the lock will be released in the proper order when the
complicated transaction subsystem was done with it.  I did not see any reason
to allow operations to proceed before that time.  And so this seemed safe...

> so asking if something is "synchronous" without any
> other context is a difficult question to answer :)

Or apparently it is difficult to even ask...  ;-)  (...not trying to be
sarcastic.)  Seriously, I'm not an expert in this area so I did what I thought
was most safe.  Which for me was the number 1 goal.

> 
> > I want to understand this better because I have fought with a lot of ABBA
> > issues with these locks.  So...  can I hold the lock until after
> > xfs_trans_commit() and safely unlock it there... because the XFS_MMAPLOCK_EXCL,
> > XFS_IOLOCK_EXCL, and XFS_ILOCK_EXCL will be released at that point?  Thus
> > preserving the following lock order.
> 
> See how operations like xfs_create, xfs_unlink, etc work. The don't
> specify flags to xfs_ijoin(), and so the transaction commits don't
> automatically unlock the inode.

xfs_ijoin()?  Do you mean xfs_trans_ijoin()?

> This is necessary so that rolling
> transactions are executed atomically w.r.t. inode access - no-one
> can lock and access the inode while a multi-commit rolling
> transaction on the inode is on-going.
> 
> In this case it's just a single commit and we don't need to keep
> it locked after the change is made, so we can unlock the inode
> on commit. So for the XFS internal locks the code is fine and
> doesn't need to change. We just need to wrap the VFS aops lock (if
> we keep it) around the outside of all the XFS locking until the
> transaction commits and unlocks the XFS locks...

Ok, I went ahead and coded it up and it is testing now.  Everything looks good.
I have to say that at this point I have to agree that I can't see how a
deadlock could occur so...

Thanks for the review,
Ira

> 
> Cheers,
> 
> Dave.
> -- 
> Dave Chinner
> david@fromorbit.com

Patch
diff mbox series

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 35df324875db..5b014c428f0f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -142,12 +142,12 @@  xfs_ilock_attr_map_shared(
  *
  * Basic locking order:
  *
- * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
+ * s_dax_sem -> i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
  *
  * mmap_sem locking order:
  *
  * i_rwsem -> page lock -> mmap_sem
- * mmap_sem -> i_mmap_lock -> page_lock
+ * s_dax_sem -> mmap_sem -> i_mmap_lock -> page_lock
  *
  * The difference in mmap_sem locking order mean that we cannot hold the
  * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
@@ -182,6 +182,9 @@  xfs_ilock(
 	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
 	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
 
+	if (lock_flags & XFS_DAX_EXCL)
+		inode_aops_down_write(VFS_I(ip));
+
 	if (lock_flags & XFS_IOLOCK_EXCL) {
 		down_write_nested(&VFS_I(ip)->i_rwsem,
 				  XFS_IOLOCK_DEP(lock_flags));
@@ -224,6 +227,8 @@  xfs_ilock_nowait(
 	 * You can't set both SHARED and EXCL for the same lock,
 	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
 	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
+	 *
+	 * XFS_DAX_* is not allowed
 	 */
 	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
 	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
@@ -232,6 +237,7 @@  xfs_ilock_nowait(
 	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
 	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
 	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
+	ASSERT((lock_flags & XFS_DAX_EXCL) == 0);
 
 	if (lock_flags & XFS_IOLOCK_EXCL) {
 		if (!down_write_trylock(&VFS_I(ip)->i_rwsem))
@@ -318,6 +324,9 @@  xfs_iunlock(
 	else if (lock_flags & XFS_ILOCK_SHARED)
 		mrunlock_shared(&ip->i_lock);
 
+	if (lock_flags & XFS_DAX_EXCL)
+		inode_aops_up_write(VFS_I(ip));
+
 	trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
 }
 
@@ -333,6 +342,8 @@  xfs_ilock_demote(
 	ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL));
 	ASSERT((lock_flags &
 		~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
+	/* XFS_DAX_* is not allowed */
+	ASSERT((lock_flags & XFS_DAX_EXCL) == 0);
 
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrdemote(&ip->i_lock);
@@ -465,6 +476,9 @@  xfs_lock_inodes(
 	ASSERT(!(lock_mode & XFS_ILOCK_EXCL) ||
 		inodes <= XFS_ILOCK_MAX_SUBCLASS + 1);
 
+	/* XFS_DAX_* is not allowed */
+	ASSERT((lock_mode & XFS_DAX_EXCL) == 0);
+
 	if (lock_mode & XFS_IOLOCK_EXCL) {
 		ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)));
 	} else if (lock_mode & XFS_MMAPLOCK_EXCL)
@@ -566,6 +580,10 @@  xfs_lock_two_inodes(
 	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
 	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
 
+	/* XFS_DAX_* is not allowed */
+	ASSERT((ip0_mode & XFS_DAX_EXCL) == 0);
+	ASSERT((ip1_mode & XFS_DAX_EXCL) == 0);
+
 	ASSERT(ip0->i_ino != ip1->i_ino);
 
 	if (ip0->i_ino > ip1->i_ino) {
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 492e53992fa9..25fe20740bf7 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -278,10 +278,12 @@  static inline void xfs_ifunlock(struct xfs_inode *ip)
 #define	XFS_ILOCK_SHARED	(1<<3)
 #define	XFS_MMAPLOCK_EXCL	(1<<4)
 #define	XFS_MMAPLOCK_SHARED	(1<<5)
+#define	XFS_DAX_EXCL		(1<<6)
 
 #define XFS_LOCK_MASK		(XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \
 				| XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \
-				| XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED)
+				| XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED \
+				| XFS_DAX_EXCL)
 
 #define XFS_LOCK_FLAGS \
 	{ XFS_IOLOCK_EXCL,	"IOLOCK_EXCL" }, \
@@ -289,7 +291,8 @@  static inline void xfs_ifunlock(struct xfs_inode *ip)
 	{ XFS_ILOCK_EXCL,	"ILOCK_EXCL" }, \
 	{ XFS_ILOCK_SHARED,	"ILOCK_SHARED" }, \
 	{ XFS_MMAPLOCK_EXCL,	"MMAPLOCK_EXCL" }, \
-	{ XFS_MMAPLOCK_SHARED,	"MMAPLOCK_SHARED" }
+	{ XFS_MMAPLOCK_SHARED,	"MMAPLOCK_SHARED" }, \
+	{ XFS_DAX_EXCL,		"DAX_EXCL" }
 
 
 /*