dax: expose __dax_fault for filesystems with locking constraints

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>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dave Chinner <david@fromorbit.com>

diff --git a/fs/dax.c b/fs/dax.c
index 4bb5b7cd5dfd82eaa34120a323308c6c5b658c2f..99b5fbc38992db1f88be1a1e48dad4fda584a0c1 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -312,7 +312,17 @@ 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;
@@ -443,6 +453,7 @@ 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
@@ -463,7 +474,7 @@ 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 c9b4cca9e08d5230028c5dad99b5370542e91040..5784377e7c56361caa5f6bba11cd9aff575182f6 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2630,8 +2630,11 @@ 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);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+               dax_iodone_t);
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#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)
+#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,