fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core

Message ID 151062258598.8554.8157038002895095232.stgit@dwillia2-desk3.amr.corp.intel.com
State New
Headers show
Series
  • fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core
Related show

Commit Message

Dan Williams Nov. 14, 2017, 1:27 a.m.
While reviewing whether MAP_SYNC should strengthen its current guarantee
of syncing writes from the initiating process to also include
third-party readers observing dirty metadata, Dave pointed out that the
check of IOMAP_WRITE is misplaced.

The policy of what to with IOMAP_F_DIRTY should be separated from the
generic filesystem mechanism of reporting dirty metadata. Move this
policy to the fs-dax core to simplify the per-filesystem iomap handlers,
and further centralize code that implements the MAP_SYNC policy. This
otherwise should not change behavior, it just makes it easier to change
behavior in the future.

Cc: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Reported-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
This is an additional cleanup I want to include in the 4.15 merge
request for the MAP_SYNC feature. Please review, I'm looking to send the
pull request towards the end of the week.


 fs/dax.c           |   15 +++++++++++++--
 fs/ext4/inode.c    |    2 +-
 fs/xfs/xfs_iomap.c |    6 +++---
 3 files changed, 17 insertions(+), 6 deletions(-)

Comments

Darrick J. Wong Nov. 14, 2017, 2:14 a.m. | #1
On Mon, Nov 13, 2017 at 05:27:54PM -0800, Dan Williams wrote:
> While reviewing whether MAP_SYNC should strengthen its current guarantee
> of syncing writes from the initiating process to also include
> third-party readers observing dirty metadata, Dave pointed out that the
> check of IOMAP_WRITE is misplaced.
> 
> The policy of what to with IOMAP_F_DIRTY should be separated from the
> generic filesystem mechanism of reporting dirty metadata. Move this
> policy to the fs-dax core to simplify the per-filesystem iomap handlers,
> and further centralize code that implements the MAP_SYNC policy. This
> otherwise should not change behavior, it just makes it easier to change
> behavior in the future.

Yes, this was what I was looking for on my last read-through. :)

> Cc: Jan Kara <jack@suse.cz>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Darrick J. Wong <darrick.wong@oracle.com>
> Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> Reported-by: Dave Chinner <david@fromorbit.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
> This is an additional cleanup I want to include in the 4.15 merge
> request for the MAP_SYNC feature. Please review, I'm looking to send the
> pull request towards the end of the week.
> 
> 
>  fs/dax.c           |   15 +++++++++++++--
>  fs/ext4/inode.c    |    2 +-
>  fs/xfs/xfs_iomap.c |    6 +++---
>  3 files changed, 17 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 78233c716757..27ba300660ff 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1079,6 +1079,17 @@ static int dax_fault_return(int error)
>  	return VM_FAULT_SIGBUS;
>  }
>  
> +/*
> + * MAP_SYNC on a dax mapping guarantees dirty metadata is
> + * flushed on write-faults (non-cow), but not read-faults.
> + */
> +static bool dax_fault_is_synchronous(unsigned long flags,
> +		struct vm_area_struct *vma, struct iomap *iomap)
> +{
> +	return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC)
> +		&& (iomap->flags & IOMAP_F_DIRTY);
> +}
> +
>  static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  			       const struct iomap_ops *ops)
>  {
> @@ -1170,7 +1181,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  		goto finish_iomap;
>  	}
>  
> -	sync = (vma->vm_flags & VM_SYNC) && (iomap.flags & IOMAP_F_DIRTY);
> +	sync = dax_fault_is_synchronous(flags, vma, &iomap);
>  
>  	switch (iomap.type) {
>  	case IOMAP_MAPPED:
> @@ -1390,7 +1401,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  	if (iomap.offset + iomap.length < pos + PMD_SIZE)
>  		goto finish_iomap;
>  
> -	sync = (vma->vm_flags & VM_SYNC) && (iomap.flags & IOMAP_F_DIRTY);
> +	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);
>  
>  	switch (iomap.type) {
>  	case IOMAP_MAPPED:
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 13a198924a0f..ee4d907a4251 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3479,7 +3479,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
>  	}
>  
>  	iomap->flags = 0;
> -	if ((flags & IOMAP_WRITE) && ext4_inode_datasync_dirty(inode))
> +	if (ext4_inode_datasync_dirty(inode))
>  		iomap->flags |= IOMAP_F_DIRTY;
>  	iomap->bdev = inode->i_sb->s_bdev;
>  	iomap->dax_dev = sbi->s_daxdev;
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index b43be199fbdf..888b60189983 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -1087,9 +1087,9 @@ xfs_file_iomap_begin(
>  		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
>  	}
>  
> -	if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
> -	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> -		iomap->flags |= IOMAP_F_DIRTY;
> +	if (xfs_ipincount(ip))
> +		if (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)

Why not if (xfs_ipincount(ip) && (ip->... & ~XFS_ILOG_TIMESTAMP)) ?

Otherwise looks ok (just this patch, will rvb the rest separately),
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>

--D

> +			iomap->flags |= IOMAP_F_DIRTY;
>  
>  	xfs_bmbt_to_iomap(ip, iomap, &imap);
>  
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
Dave Chinner Nov. 14, 2017, 4:12 a.m. | #2
On Mon, Nov 13, 2017 at 05:27:54PM -0800, Dan Williams wrote:
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index b43be199fbdf..888b60189983 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -1087,9 +1087,9 @@ xfs_file_iomap_begin(
>  		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
>  	}
>  
> -	if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
> -	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> -		iomap->flags |= IOMAP_F_DIRTY;
> +	if (xfs_ipincount(ip))
> +		if (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)
> +			iomap->flags |= IOMAP_F_DIRTY;

Please make a helper for this, and use it in xfs_file_fsync() where
the same dirty checks are done. e.g.

static inline bool
xfs_inode_need_fsync(struct xfs_inode *ip, bool datasync)
{
	if (!xfs_ipincount(ip))
		return false;
	if (xfs_inode_clean(ip))
		return false;
	if (datasync &&
	    !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
		return false;
	return true;
}

Cheers,

Dave.
Christoph Hellwig Nov. 14, 2017, 5:59 a.m. | #3
> -	if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
> -	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> -		iomap->flags |= IOMAP_F_DIRTY;
> +	if (xfs_ipincount(ip))
> +		if (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)
> +			iomap->flags |= IOMAP_F_DIRTY;

Please don't split up the conditional and make it harder to read.

With that fixed up this looks fine to me:

Reviewed-by: Christoph Hellwig <hch@lst.de>
Christoph Hellwig Nov. 14, 2017, 6:01 a.m. | #4
On Tue, Nov 14, 2017 at 03:12:28PM +1100, Dave Chinner wrote:
> On Mon, Nov 13, 2017 at 05:27:54PM -0800, Dan Williams wrote:
> > diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> > index b43be199fbdf..888b60189983 100644
> > --- a/fs/xfs/xfs_iomap.c
> > +++ b/fs/xfs/xfs_iomap.c
> > @@ -1087,9 +1087,9 @@ xfs_file_iomap_begin(
> >  		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
> >  	}
> >  
> > -	if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
> > -	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> > -		iomap->flags |= IOMAP_F_DIRTY;
> > +	if (xfs_ipincount(ip))
> > +		if (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)
> > +			iomap->flags |= IOMAP_F_DIRTY;
> 
> Please make a helper for this, and use it in xfs_file_fsync() where
> the same dirty checks are done. e.g.

Let's keep that sort of cleanup separate.  I initially considered
it when doing the MAP_SYNC work, but fsync works a little different
in that it looks at ili_last_lsn, so your little helper below won't
work as-is.  You can send it as an incremental patch later and we
can see if we can come up with something workable.
Jan Kara Nov. 14, 2017, 9:31 a.m. | #5
On Mon 13-11-17 17:27:54, Dan Williams wrote:
> While reviewing whether MAP_SYNC should strengthen its current guarantee
> of syncing writes from the initiating process to also include
> third-party readers observing dirty metadata, Dave pointed out that the
> check of IOMAP_WRITE is misplaced.
> 
> The policy of what to with IOMAP_F_DIRTY should be separated from the
> generic filesystem mechanism of reporting dirty metadata. Move this
> policy to the fs-dax core to simplify the per-filesystem iomap handlers,
> and further centralize code that implements the MAP_SYNC policy. This
> otherwise should not change behavior, it just makes it easier to change
> behavior in the future.
> 
> Cc: Jan Kara <jack@suse.cz>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Darrick J. Wong <darrick.wong@oracle.com>
> Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> Reported-by: Dave Chinner <david@fromorbit.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
> This is an additional cleanup I want to include in the 4.15 merge
> request for the MAP_SYNC feature. Please review, I'm looking to send the
> pull request towards the end of the week.

The patch looks fine to me. You can add:

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

								Honza

> 
> 
>  fs/dax.c           |   15 +++++++++++++--
>  fs/ext4/inode.c    |    2 +-
>  fs/xfs/xfs_iomap.c |    6 +++---
>  3 files changed, 17 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 78233c716757..27ba300660ff 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1079,6 +1079,17 @@ static int dax_fault_return(int error)
>  	return VM_FAULT_SIGBUS;
>  }
>  
> +/*
> + * MAP_SYNC on a dax mapping guarantees dirty metadata is
> + * flushed on write-faults (non-cow), but not read-faults.
> + */
> +static bool dax_fault_is_synchronous(unsigned long flags,
> +		struct vm_area_struct *vma, struct iomap *iomap)
> +{
> +	return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC)
> +		&& (iomap->flags & IOMAP_F_DIRTY);
> +}
> +
>  static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  			       const struct iomap_ops *ops)
>  {
> @@ -1170,7 +1181,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  		goto finish_iomap;
>  	}
>  
> -	sync = (vma->vm_flags & VM_SYNC) && (iomap.flags & IOMAP_F_DIRTY);
> +	sync = dax_fault_is_synchronous(flags, vma, &iomap);
>  
>  	switch (iomap.type) {
>  	case IOMAP_MAPPED:
> @@ -1390,7 +1401,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  	if (iomap.offset + iomap.length < pos + PMD_SIZE)
>  		goto finish_iomap;
>  
> -	sync = (vma->vm_flags & VM_SYNC) && (iomap.flags & IOMAP_F_DIRTY);
> +	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);
>  
>  	switch (iomap.type) {
>  	case IOMAP_MAPPED:
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 13a198924a0f..ee4d907a4251 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3479,7 +3479,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
>  	}
>  
>  	iomap->flags = 0;
> -	if ((flags & IOMAP_WRITE) && ext4_inode_datasync_dirty(inode))
> +	if (ext4_inode_datasync_dirty(inode))
>  		iomap->flags |= IOMAP_F_DIRTY;
>  	iomap->bdev = inode->i_sb->s_bdev;
>  	iomap->dax_dev = sbi->s_daxdev;
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index b43be199fbdf..888b60189983 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -1087,9 +1087,9 @@ xfs_file_iomap_begin(
>  		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
>  	}
>  
> -	if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
> -	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> -		iomap->flags |= IOMAP_F_DIRTY;
> +	if (xfs_ipincount(ip))
> +		if (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)
> +			iomap->flags |= IOMAP_F_DIRTY;
>  
>  	xfs_bmbt_to_iomap(ip, iomap, &imap);
>  
>

Patch

diff --git a/fs/dax.c b/fs/dax.c
index 78233c716757..27ba300660ff 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1079,6 +1079,17 @@  static int dax_fault_return(int error)
 	return VM_FAULT_SIGBUS;
 }
 
+/*
+ * MAP_SYNC on a dax mapping guarantees dirty metadata is
+ * flushed on write-faults (non-cow), but not read-faults.
+ */
+static bool dax_fault_is_synchronous(unsigned long flags,
+		struct vm_area_struct *vma, struct iomap *iomap)
+{
+	return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC)
+		&& (iomap->flags & IOMAP_F_DIRTY);
+}
+
 static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       const struct iomap_ops *ops)
 {
@@ -1170,7 +1181,7 @@  static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		goto finish_iomap;
 	}
 
-	sync = (vma->vm_flags & VM_SYNC) && (iomap.flags & IOMAP_F_DIRTY);
+	sync = dax_fault_is_synchronous(flags, vma, &iomap);
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
@@ -1390,7 +1401,7 @@  static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
-	sync = (vma->vm_flags & VM_SYNC) && (iomap.flags & IOMAP_F_DIRTY);
+	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 13a198924a0f..ee4d907a4251 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3479,7 +3479,7 @@  static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	}
 
 	iomap->flags = 0;
-	if ((flags & IOMAP_WRITE) && ext4_inode_datasync_dirty(inode))
+	if (ext4_inode_datasync_dirty(inode))
 		iomap->flags |= IOMAP_F_DIRTY;
 	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->dax_dev = sbi->s_daxdev;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index b43be199fbdf..888b60189983 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1087,9 +1087,9 @@  xfs_file_iomap_begin(
 		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
 	}
 
-	if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
-	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
-		iomap->flags |= IOMAP_F_DIRTY;
+	if (xfs_ipincount(ip))
+		if (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)
+			iomap->flags |= IOMAP_F_DIRTY;
 
 	xfs_bmbt_to_iomap(ip, iomap, &imap);