summaryrefslogtreecommitdiffstats
path: root/fs/dax.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2015-06-04 09:18:18 +1000
committerDave Chinner <david@fromorbit.com>2015-06-04 09:18:18 +1000
commite842f2903908934187af7232fb5b21da527d1757 (patch)
tree5fe6e2da05d58519d0f9360cf5116662a766906a /fs/dax.c
parentec56b1f1fdc69599963574ce94cc5693d535dd64 (diff)
downloadlinux-e842f2903908934187af7232fb5b21da527d1757.tar.gz
linux-e842f2903908934187af7232fb5b21da527d1757.tar.bz2
linux-e842f2903908934187af7232fb5b21da527d1757.zip
dax: don't abuse get_block mapping for endio callbacks
dax_fault() currently relies on the get_block callback to attach an io completion callback to the mapping buffer head so that it can run unwritten extent conversion after zeroing allocated blocks. Instead of this hack, pass the conversion callback directly into dax_fault() similar to the get_block callback. When the filesystem allocates unwritten extents, it will set the buffer_unwritten() flag, and hence the dax_fault code can call the completion function in the contexts where it is necessary without overloading the mapping buffer head. Note: The changes to ext4 to use this interface are suspect at best. In fact, the way ext4 did this end_io assignment in the first place looks suspect because it only set a completion callback when there wasn't already some other write() call taking place on the same inode. The ext4 end_io code looks rather intricate and fragile with all it's reference counting and passing to different contexts for modification via inode private pointers that aren't protected by locks... Signed-off-by: Dave Chinner <dchinner@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs/dax.c')
-rw-r--r--fs/dax.c21
1 files changed, 15 insertions, 6 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 6f65f00e58ec..4bb5b7cd5dfd 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -309,14 +309,11 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
out:
i_mmap_unlock_read(mapping);
- if (bh->b_end_io)
- bh->b_end_io(bh, 1);
-
return error;
}
static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+ get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
@@ -417,7 +414,19 @@ static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
page_cache_release(page);
}
+ /*
+ * If we successfully insert the new mapping over an unwritten extent,
+ * we need to ensure we convert the unwritten extent. If there is an
+ * error inserting the mapping, the filesystem needs to leave it as
+ * unwritten to prevent exposure of the stale underlying data to
+ * userspace, but we still need to call the completion function so
+ * the private resources on the mapping buffer can be released. We
+ * indicate what the callback should do via the uptodate variable, same
+ * as for normal BH based IO completions.
+ */
error = dax_insert_mapping(inode, &bh, vma, vmf);
+ if (buffer_unwritten(&bh))
+ complete_unwritten(&bh, !error);
out:
if (error == -ENOMEM)
@@ -445,7 +454,7 @@ static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
* fault handler for DAX files.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+ get_block_t get_block, dax_iodone_t complete_unwritten)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
@@ -454,7 +463,7 @@ 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);
+ result = do_dax_fault(vma, vmf, get_block, complete_unwritten);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);