1 files changed, 59 insertions, 29 deletions

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 4ecd255e0511..b4dc51063d36 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -31,6 +31,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	size_t			done_before;
 	bool			wait_for_completion;
 
 	union {
@@ -38,8 +39,7 @@ struct iomap_dio {
 		struct {
 			struct iov_iter		*iter;
 			struct task_struct	*waiter;
-			struct request_queue	*last_queue;
-			blk_qc_t		cookie;
+			struct bio		*poll_bio;
 		} submit;
 
 		/* used for aio completion: */
@@ -49,29 +49,20 @@ struct iomap_dio {
 	};
 };
 
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
-{
-	struct request_queue *q = READ_ONCE(kiocb->private);
-
-	if (!q)
-		return 0;
-	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
-}
-EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
-
 static void iomap_dio_submit_bio(const struct iomap_iter *iter,
 		struct iomap_dio *dio, struct bio *bio, loff_t pos)
 {
 	atomic_inc(&dio->ref);
 
-	if (dio->iocb->ki_flags & IOCB_HIPRI)
+	if (dio->iocb->ki_flags & IOCB_HIPRI) {
 		bio_set_polled(bio, dio->iocb);
+		dio->submit.poll_bio = bio;
+	}
 
-	dio->submit.last_queue = bdev_get_queue(iter->iomap.bdev);
 	if (dio->dops && dio->dops->submit_io)
-		dio->submit.cookie = dio->dops->submit_io(iter, bio, pos);
+		dio->dops->submit_io(iter, bio, pos);
 	else
-		dio->submit.cookie = submit_bio(bio);
+		submit_bio(bio);
 }
 
 ssize_t iomap_dio_complete(struct iomap_dio *dio)
@@ -124,6 +115,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
+	if (ret > 0)
+		ret += dio->done_before;
+
 	kfree(dio);
 
 	return ret;
@@ -135,7 +129,7 @@ static void iomap_dio_complete_work(struct work_struct *work)
 	struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
 	struct kiocb *iocb = dio->iocb;
 
-	iocb->ki_complete(iocb, iomap_dio_complete(dio), 0);
+	iocb->ki_complete(iocb, iomap_dio_complete(dio));
 }
 
 /*
@@ -164,9 +158,11 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
 			struct inode *inode = file_inode(dio->iocb->ki_filp);
 
+			WRITE_ONCE(dio->iocb->private, NULL);
 			INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
 			queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work);
 		} else {
+			WRITE_ONCE(dio->iocb->private, NULL);
 			iomap_dio_complete_work(&dio->aio.work);
 		}
 	}
@@ -282,6 +278,13 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 	if (!iov_iter_count(dio->submit.iter))
 		goto out;
 
+	/*
+	 * We can only poll for single bio I/Os.
+	 */
+	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode)))
+		dio->iocb->ki_flags &= ~IOCB_HIPRI;
+
 	if (need_zeroout) {
 		/* zero out from the start of the block to the write offset */
 		pad = pos & (fs_block_size - 1);
@@ -339,6 +342,11 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 
 		nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter,
 						 BIO_MAX_VECS);
+		/*
+		 * We can only poll for single bio I/Os.
+		 */
+		if (nr_pages)
+			dio->iocb->ki_flags &= ~IOCB_HIPRI;
 		iomap_dio_submit_bio(iter, dio, bio, pos);
 		pos += n;
 	} while (nr_pages);
@@ -371,6 +379,8 @@ static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter,
 	loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
 
 	dio->size += length;
+	if (!length)
+		return -EFAULT;
 	return length;
 }
 
@@ -402,6 +412,8 @@ static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi,
 		copied = copy_to_iter(inline_data, length, iter);
 	}
 	dio->size += copied;
+	if (!copied)
+		return -EFAULT;
 	return copied;
 }
 
@@ -446,13 +458,21 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter,
  * may be pure data writes. In that case, we still need to do a full data sync
  * completion.
  *
+ * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL,
+ * __iomap_dio_rw can return a partial result if it encounters a non-resident
+ * page in @iter after preparing a transfer.  In that case, the non-resident
+ * pages can be faulted in and the request resumed with @done_before set to the
+ * number of bytes previously transferred.  The request will then complete with
+ * the correct total number of bytes transferred; this is essential for
+ * completing partial requests asynchronously.
+ *
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
 struct iomap_dio *
 __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -482,11 +502,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->done_before = done_before;
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
-	dio->submit.cookie = BLK_QC_T_NONE;
-	dio->submit.last_queue = NULL;
+	dio->submit.poll_bio = NULL;
 
 	if (iov_iter_rw(iter) == READ) {
 		if (iomi.pos >= dio->i_size)
@@ -565,8 +585,15 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	inode_dio_begin(inode);
 
 	blk_start_plug(&plug);
-	while ((ret = iomap_iter(&iomi, ops)) > 0)
+	while ((ret = iomap_iter(&iomi, ops)) > 0) {
 		iomi.processed = iomap_dio_iter(&iomi, dio);
+
+		/*
+		 * We can only poll for single bio I/Os.
+		 */
+		iocb->ki_flags &= ~IOCB_HIPRI;
+	}
+
 	blk_finish_plug(&plug);
 
 	/*
@@ -577,6 +604,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size)
 		iov_iter_revert(iter, iomi.pos - dio->i_size);
 
+	if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) {
+		if (!(iocb->ki_flags & IOCB_NOWAIT))
+			wait_for_completion = true;
+		ret = 0;
+	}
+
 	/* magic error code to fall back to buffered I/O */
 	if (ret == -ENOTBLK) {
 		wait_for_completion = true;
@@ -592,8 +625,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (dio->flags & IOMAP_DIO_WRITE_FUA)
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
-	WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie);
-	WRITE_ONCE(iocb->private, dio->submit.last_queue);
+	WRITE_ONCE(iocb->private, dio->submit.poll_bio);
 
 	/*
 	 * We are about to drop our additional submission reference, which
@@ -620,10 +652,8 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!READ_ONCE(dio->submit.waiter))
 				break;
 
-			if (!(iocb->ki_flags & IOCB_HIPRI) ||
-			    !dio->submit.last_queue ||
-			    !blk_poll(dio->submit.last_queue,
-					 dio->submit.cookie, true))
+			if (!dio->submit.poll_bio ||
+			    !bio_poll(dio->submit.poll_bio, NULL, 0))
 				blk_io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
@@ -642,11 +672,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct iomap_dio *dio;
 
-	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags);
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before);
 	if (IS_ERR_OR_NULL(dio))
 		return PTR_ERR_OR_ZERO(dio);
 	return iomap_dio_complete(dio);