1 files changed, 38 insertions, 30 deletions

diff --git a/fs/iomap.c b/fs/iomap.c
index 4241bac905b1..b9f74803e56c 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -350,8 +350,8 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 		struct iomap *iomap)
 {
-	sector_t sector = iomap->blkno +
-		(((pos & ~(PAGE_SIZE - 1)) - iomap->offset) >> 9);
+	sector_t sector = (iomap->addr +
+			   (pos & PAGE_MASK) - iomap->offset) >> 9;
 
 	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
 			offset, bytes);
@@ -510,11 +510,12 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 		flags |= FIEMAP_EXTENT_MERGED;
 	if (iomap->flags & IOMAP_F_SHARED)
 		flags |= FIEMAP_EXTENT_SHARED;
+	if (iomap->flags & IOMAP_F_DATA_INLINE)
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
 
 	return fiemap_fill_next_extent(fi, iomap->offset,
-			iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0,
+			iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
 			iomap->length, flags);
-
 }
 
 static loff_t
@@ -714,23 +715,9 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	struct kiocb *iocb = dio->iocb;
 	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
-	/*
-	 * Try again to invalidate clean pages which might have been cached by
-	 * non-direct readahead, or faulted in by get_user_pages() if the source
-	 * of the write was an mmap'ed region of the file we're writing.  Either
-	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
-	 * this invalidation fails, tough, the write still worked...
-	 */
-	if (!dio->error &&
-	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(inode->i_mapping,
-				iocb->ki_pos >> PAGE_SHIFT,
-				(iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	if (dio->end_io) {
 		ret = dio->end_io(iocb,
 				dio->error ? dio->error : dio->size,
@@ -742,12 +729,33 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (likely(!ret)) {
 		ret = dio->size;
 		/* check for short read */
-		if (iocb->ki_pos + ret > dio->i_size &&
+		if (offset + ret > dio->i_size &&
 		    !(dio->flags & IOMAP_DIO_WRITE))
-			ret = dio->i_size - iocb->ki_pos;
+			ret = dio->i_size - offset;
 		iocb->ki_pos += ret;
 	}
 
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 *
+	 * And this page cache invalidation has to be after dio->end_io(), as
+	 * some filesystems convert unwritten extents to real allocations in
+	 * end_io() when necessary, otherwise a racing buffer read would cache
+	 * zeros from unwritten extents.
+	 */
+	if (!dio->error &&
+	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+		int err;
+		err = invalidate_inode_pages2_range(inode->i_mapping,
+				offset >> PAGE_SHIFT,
+				(offset + dio->size - 1) >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
+	}
+
 	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
@@ -823,7 +831,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	bio = bio_alloc(GFP_KERNEL, 1);
 	bio_set_dev(bio, iomap->bdev);
 	bio->bi_iter.bi_sector =
-		iomap->blkno + ((pos - iomap->offset) >> 9);
+		(iomap->addr + pos - iomap->offset) >> 9;
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
@@ -902,7 +910,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 		bio_set_dev(bio, iomap->bdev);
 		bio->bi_iter.bi_sector =
-			iomap->blkno + ((pos - iomap->offset) >> 9);
+			(iomap->addr + pos - iomap->offset) >> 9;
 		bio->bi_write_hint = dio->iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
@@ -1009,6 +1017,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	WARN_ON_ONCE(ret);
 	ret = 0;
 
+	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+	    !inode->i_sb->s_dio_done_wq) {
+		ret = sb_init_dio_done_wq(inode->i_sb);
+		if (ret < 0)
+			goto out_free_dio;
+	}
+
 	inode_dio_begin(inode);
 
 	blk_start_plug(&plug);
@@ -1031,13 +1046,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (ret < 0)
 		iomap_dio_set_error(dio, ret);
 
-	if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
-			!inode->i_sb->s_dio_done_wq) {
-		ret = sb_init_dio_done_wq(inode->i_sb);
-		if (ret < 0)
-			iomap_dio_set_error(dio, ret);
-	}
-
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!is_sync_kiocb(iocb))
 			return -EIOCBQUEUED;