diff mbox

[3/8] dax: expose __dax_fault for filesystems with locking constraints

Message ID 1427194266-2885-4-git-send-email-david@fromorbit.com (mailing list archive)
State New, archived
Headers show

Commit Message

Dave Chinner March 24, 2015, 10:51 a.m. UTC 
From: Dave Chinner <dchinner@redhat.com>

Some filesystems cannot call dax_fault() directly because they have
different locking and/or allocation constraints in the page fault IO
path. To handle this, we need to follow the same model as the
generic block_page_mkwrite code, where the internals are exposed via
__block_page_mkwrite() so that filesystems can wrap the correct
locking and operations around the outside.

This is loosely based on a patch originally from Matthew Willcox.
Unlike the original patch, it does not change ext4 code, error
returns or unwritten extent conversion handling.  It also adds a
__dax_mkwrite() wrapper for .page_mkwrite implementations to do the
right thing, too.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/dax.c           | 15 +++++++++++++--
 include/linux/fs.h |  5 ++++-
 2 files changed, 17 insertions(+), 3 deletions(-)

Comments

Jan Kara April 1, 2015, 3:07 p.m. UTC | #1 
On Tue 24-03-15 21:51:01, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> Some filesystems cannot call dax_fault() directly because they have
> different locking and/or allocation constraints in the page fault IO
> path. To handle this, we need to follow the same model as the
> generic block_page_mkwrite code, where the internals are exposed via
> __block_page_mkwrite() so that filesystems can wrap the correct
> locking and operations around the outside.
> 
> This is loosely based on a patch originally from Matthew Willcox.
> Unlike the original patch, it does not change ext4 code, error
> returns or unwritten extent conversion handling.  It also adds a
> __dax_mkwrite() wrapper for .page_mkwrite implementations to do the
> right thing, too.
  We will need a normal error return from __dax_mkwrite() for proper ENOSPC
handling in ext4. You could do this when touching that code here if you
feel like that but if not, I can do that as a separate patch.

Anyway, feel free to add:
Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> ---
>  fs/dax.c           | 15 +++++++++++++--
>  include/linux/fs.h |  5 ++++-
>  2 files changed, 17 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 431ec2b..0121f7d 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -313,7 +313,17 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
>  	return error;
>  }
>  
> -static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
> +/**
> + * __dax_fault - handle a page fault on a DAX file
> + * @vma: The virtual memory area where the fault occurred
> + * @vmf: The description of the fault
> + * @get_block: The filesystem method used to translate file offsets to blocks
> + *
> + * When a page fault occurs, filesystems may call this helper in their
> + * fault handler for DAX files. __dax_fault() assumes the caller has done all
> + * the necessary locking for the page fault to proceed successfully.
> + */
> +int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
>  			get_block_t get_block, dax_iodone_t complete_unwritten)
>  {
>  	struct file *file = vma->vm_file;
> @@ -440,6 +450,7 @@ static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
>  	}
>  	goto out;
>  }
> +EXPORT_SYMBOL(__dax_fault);
>  
>  /**
>   * dax_fault - handle a page fault on a DAX file
> @@ -460,7 +471,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
>  		sb_start_pagefault(sb);
>  		file_update_time(vma->vm_file);
>  	}
> -	result = do_dax_fault(vma, vmf, get_block, complete_unwritten);
> +	result = __dax_fault(vma, vmf, get_block, complete_unwritten);
>  	if (vmf->flags & FAULT_FLAG_WRITE)
>  		sb_end_pagefault(sb);
>  
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 82100ae..7e5a2d6 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -2606,7 +2606,10 @@ int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
>  int dax_truncate_page(struct inode *, loff_t from, get_block_t);
>  int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
>  		dax_iodone_t);
> -#define dax_mkwrite(vma, vmf, gb, iod)	dax_fault(vma, vmf, gb, iod)
> +int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
> +		dax_iodone_t);
> +#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
> +#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
>  
>  #ifdef CONFIG_BLOCK
>  typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
> -- 
> 2.0.0
>
diff mbox

Patch

diff --git a/fs/dax.c b/fs/dax.c
index 431ec2b..0121f7d 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -313,7 +313,17 @@  static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	return error;
 }
 
-static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+/**
+ * __dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * fault handler for DAX files. __dax_fault() assumes the caller has done all
+ * the necessary locking for the page fault to proceed successfully.
+ */
+int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			get_block_t get_block, dax_iodone_t complete_unwritten)
 {
 	struct file *file = vma->vm_file;
@@ -440,6 +450,7 @@  static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	}
 	goto out;
 }
+EXPORT_SYMBOL(__dax_fault);
 
 /**
  * dax_fault - handle a page fault on a DAX file
@@ -460,7 +471,7 @@  int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 	}
-	result = do_dax_fault(vma, vmf, get_block, complete_unwritten);
+	result = __dax_fault(vma, vmf, get_block, complete_unwritten);
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(sb);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 82100ae..7e5a2d6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2606,7 +2606,10 @@  int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
 		dax_iodone_t);
-#define dax_mkwrite(vma, vmf, gb, iod)	dax_fault(vma, vmf, gb, iod)
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
+#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
 
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,