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>

4 files changed, 38 insertions, 24 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 6f65f00..4bb5b7c 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);
 
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 3a0a6c6..3b57c9f 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -28,12 +28,12 @@
 #ifdef CONFIG_FS_DAX
 static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_fault(vma, vmf, ext2_get_block);
+	return dax_fault(vma, vmf, ext2_get_block, NULL);
 }
 
 static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext2_get_block);
+	return dax_mkwrite(vma, vmf, ext2_get_block, NULL);
 }
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0613c25..f713cfcc 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -192,15 +192,27 @@ out:
 }
 
 #ifdef CONFIG_FS_DAX
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+	struct inode *inode = bh->b_assoc_map->host;
+	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+	int err;
+	if (!uptodate)
+		return;
+	WARN_ON(!buffer_unwritten(bh));
+	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_fault(vma, vmf, ext4_get_block);
+	return dax_fault(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
 					/* Is this the right get_block? */
 }
 
 static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext4_get_block);
+	return dax_mkwrite(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
 }
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 55b187c..7c38ed3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -656,18 +656,6 @@ has_zeroout:
 	return retval;
 }
 
-static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
-{
-	struct inode *inode = bh->b_assoc_map->host;
-	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
-	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
-	int err;
-	if (!uptodate)
-		return;
-	WARN_ON(!buffer_unwritten(bh));
-	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
-}
-
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -705,10 +693,15 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
-		if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+		if (IS_DAX(inode) && buffer_unwritten(bh)) {
+			/*
+			 * dgc: I suspect unwritten conversion on ext4+DAX is
+			 * fundamentally broken here when there are concurrent
+			 * read/write in progress on this inode.
+			 */
+			WARN_ON_ONCE(io_end);
 			bh->b_assoc_map = inode->i_mapping;
 			bh->b_private = (void *)(unsigned long)iblock;
-			bh->b_end_io = ext4_end_io_unwritten;
 		}
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);