1 files changed, 49 insertions, 36 deletions

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 10517cea9682..23837926c0c5 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -24,7 +24,7 @@
 
 struct iomap_dio {
 	struct kiocb		*iocb;
-	iomap_dio_end_io_t	*end_io;
+	const struct iomap_dio_ops *dops;
 	loff_t			i_size;
 	loff_t			size;
 	atomic_t		ref;
@@ -72,18 +72,14 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
+	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t offset = iocb->ki_pos;
-	ssize_t ret;
+	ssize_t ret = dio->error;
 
-	if (dio->end_io) {
-		ret = dio->end_io(iocb,
-				dio->error ? dio->error : dio->size,
-				dio->flags);
-	} else {
-		ret = dio->error;
-	}
+	if (dops && dops->end_io)
+		ret = dops->end_io(iocb, dio->size, ret, dio->flags);
 
 	if (likely(!ret)) {
 		ret = dio->size;
@@ -101,9 +97,9 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * 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
+	 * And this page cache invalidation has to be after ->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 &&
@@ -205,12 +201,12 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
 	unsigned int fs_block_size = i_blocksize(inode), pad;
 	unsigned int align = iov_iter_alignment(dio->submit.iter);
-	struct iov_iter iter;
 	struct bio *bio;
 	bool need_zeroout = false;
 	bool use_fua = false;
 	int nr_pages, ret = 0;
 	size_t copied = 0;
+	size_t orig_count;
 
 	if ((pos | length | align) & ((1 << blkbits) - 1))
 		return -EINVAL;
@@ -240,15 +236,18 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	}
 
 	/*
-	 * Operate on a partial iter trimmed to the extent we were called for.
-	 * We'll update the iter in the dio once we're done with this extent.
+	 * Save the original count and trim the iter to just the extent we
+	 * are operating on right now.  The iter will be re-expanded once
+	 * we are done.
 	 */
-	iter = *dio->submit.iter;
-	iov_iter_truncate(&iter, length);
+	orig_count = iov_iter_count(dio->submit.iter);
+	iov_iter_truncate(dio->submit.iter, length);
 
-	nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
-	if (nr_pages <= 0)
-		return nr_pages;
+	nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
+	if (nr_pages <= 0) {
+		ret = nr_pages;
+		goto out;
+	}
 
 	if (need_zeroout) {
 		/* zero out from the start of the block to the write offset */
@@ -261,7 +260,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		size_t n;
 		if (dio->error) {
 			iov_iter_revert(dio->submit.iter, copied);
-			return 0;
+			copied = ret = 0;
+			goto out;
 		}
 
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
@@ -272,7 +272,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
 
-		ret = bio_iov_iter_get_pages(bio, &iter);
+		ret = bio_iov_iter_get_pages(bio, dio->submit.iter);
 		if (unlikely(ret)) {
 			/*
 			 * We have to stop part way through an IO. We must fall
@@ -298,13 +298,11 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 				bio_set_pages_dirty(bio);
 		}
 
-		iov_iter_advance(dio->submit.iter, n);
-
 		dio->size += n;
 		pos += n;
 		copied += n;
 
-		nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
+		nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
 		iomap_dio_submit_bio(dio, iomap, bio);
 	} while (nr_pages);
 
@@ -322,7 +320,12 @@ zero_tail:
 		if (pad)
 			iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
 	}
-	return copied ? copied : ret;
+out:
+	/* Undo iter limitation to current extent */
+	iov_iter_reexpand(dio->submit.iter, orig_count - copied);
+	if (copied)
+		return copied;
+	return ret;
 }
 
 static loff_t
@@ -362,7 +365,7 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
 
 static loff_t
 iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+		void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct iomap_dio *dio = data;
 
@@ -396,15 +399,15 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  */
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
-		const struct iomap_ops *ops, iomap_dio_end_io_t end_io)
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	size_t count = iov_iter_count(iter);
-	loff_t pos = iocb->ki_pos, start = pos;
+	loff_t pos = iocb->ki_pos;
 	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
-	bool wait_for_completion = is_sync_kiocb(iocb);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
@@ -413,6 +416,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (!count)
 		return 0;
 
+	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
+		return -EIO;
+
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
 		return -ENOMEM;
@@ -421,7 +427,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	atomic_set(&dio->ref, 1);
 	dio->size = 0;
 	dio->i_size = i_size_read(inode);
-	dio->end_io = end_io;
+	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
 
@@ -434,7 +440,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (pos >= dio->i_size)
 			goto out_free_dio;
 
-		if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ)
+		if (iter_is_iovec(iter))
 			dio->flags |= IOMAP_DIO_DIRTY;
 	} else {
 		flags |= IOMAP_WRITE;
@@ -455,14 +461,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (filemap_range_has_page(mapping, start, end)) {
+		if (filemap_range_has_page(mapping, pos, end)) {
 			ret = -EAGAIN;
 			goto out_free_dio;
 		}
 		flags |= IOMAP_NOWAIT;
 	}
 
-	ret = filemap_write_and_wait_range(mapping, start, end);
+	ret = filemap_write_and_wait_range(mapping, pos, end);
 	if (ret)
 		goto out_free_dio;
 
@@ -473,7 +479,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	 * pretty crazy thing to do, so we don't support it 100%.
 	 */
 	ret = invalidate_inode_pages2_range(mapping,
-			start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+			pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
 	if (ret)
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
@@ -501,8 +507,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		}
 		pos += ret;
 
-		if (iov_iter_rw(iter) == READ && pos >= dio->i_size)
+		if (iov_iter_rw(iter) == READ && pos >= dio->i_size) {
+			/*
+			 * We only report that we've read data up to i_size.
+			 * Revert iter to a state corresponding to that as
+			 * some callers (such as splice code) rely on it.
+			 */
+			iov_iter_revert(iter, pos - dio->i_size);
 			break;
+		}
 	} while ((count = iov_iter_count(iter)) > 0);
 	blk_finish_plug(&plug);