1 files changed, 222 insertions, 61 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f9889b6bc02c..423f4ca7d712 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -164,6 +164,62 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+static void __loop_update_dio(struct loop_device *lo, bool dio)
+{
+	struct file *file = lo->lo_backing_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned short sb_bsize = 0;
+	unsigned dio_align = 0;
+	bool use_dio;
+
+	if (inode->i_sb->s_bdev) {
+		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
+		dio_align = sb_bsize - 1;
+	}
+
+	/*
+	 * We support direct I/O only if lo_offset is aligned with the
+	 * logical I/O size of backing device, and the logical block
+	 * size of loop is bigger than the backing device's and the loop
+	 * needn't transform transfer.
+	 *
+	 * TODO: the above condition may be loosed in the future, and
+	 * direct I/O may be switched runtime at that time because most
+	 * of requests in sane appplications should be PAGE_SIZE algined
+	 */
+	if (dio) {
+		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
+				!(lo->lo_offset & dio_align) &&
+				mapping->a_ops->direct_IO &&
+				!lo->transfer)
+			use_dio = true;
+		else
+			use_dio = false;
+	} else {
+		use_dio = false;
+	}
+
+	if (lo->use_dio == use_dio)
+		return;
+
+	/* flush dirty pages before changing direct IO */
+	vfs_fsync(file, 0);
+
+	/*
+	 * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
+	 * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
+	 * will get updated by ioctl(LOOP_GET_STATUS)
+	 */
+	blk_mq_freeze_queue(lo->lo_queue);
+	lo->use_dio = use_dio;
+	if (use_dio)
+		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
+	else
+		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
+	blk_mq_unfreeze_queue(lo->lo_queue);
+}
+
 static int
 figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 {
@@ -389,6 +445,89 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
 	return ret;
 }
 
+static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
+{
+	if (bytes < 0 || (cmd->rq->cmd_flags & REQ_WRITE))
+		return;
+
+	if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+		struct bio *bio = cmd->rq->bio;
+
+		bio_advance(bio, bytes);
+		zero_fill_bio(bio);
+	}
+}
+
+static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
+{
+	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
+	struct request *rq = cmd->rq;
+
+	handle_partial_read(cmd, ret);
+
+	if (ret > 0)
+		ret = 0;
+	else if (ret < 0)
+		ret = -EIO;
+
+	blk_mq_complete_request(rq, ret);
+}
+
+static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
+		     loff_t pos, bool rw)
+{
+	struct iov_iter iter;
+	struct bio_vec *bvec;
+	struct bio *bio = cmd->rq->bio;
+	struct file *file = lo->lo_backing_file;
+	int ret;
+
+	/* nomerge for loop request queue */
+	WARN_ON(cmd->rq->bio != cmd->rq->biotail);
+
+	bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
+		      bio_segments(bio), blk_rq_bytes(cmd->rq));
+
+	cmd->iocb.ki_pos = pos;
+	cmd->iocb.ki_filp = file;
+	cmd->iocb.ki_complete = lo_rw_aio_complete;
+	cmd->iocb.ki_flags = IOCB_DIRECT;
+
+	if (rw == WRITE)
+		ret = file->f_op->write_iter(&cmd->iocb, &iter);
+	else
+		ret = file->f_op->read_iter(&cmd->iocb, &iter);
+
+	if (ret != -EIOCBQUEUED)
+		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
+	return 0;
+}
+
+
+static inline int lo_rw_simple(struct loop_device *lo,
+		struct request *rq, loff_t pos, bool rw)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (cmd->use_aio)
+		return lo_rw_aio(lo, cmd, pos, rw);
+
+	/*
+	 * lo_write_simple and lo_read_simple should have been covered
+	 * by io submit style function like lo_rw_aio(), one blocker
+	 * is that lo_read_simple() need to call flush_dcache_page after
+	 * the page is written from kernel, and it isn't easy to handle
+	 * this in io submit style function which submits all segments
+	 * of the req at one time. And direct read IO doesn't need to
+	 * run flush_dcache_page().
+	 */
+	if (rw == WRITE)
+		return lo_write_simple(lo, rq, pos);
+	else
+		return lo_read_simple(lo, rq, pos);
+}
+
 static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 {
 	loff_t pos;
@@ -404,13 +543,13 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 		else if (lo->transfer)
 			ret = lo_write_transfer(lo, rq, pos);
 		else
-			ret = lo_write_simple(lo, rq, pos);
+			ret = lo_rw_simple(lo, rq, pos, WRITE);
 
 	} else {
 		if (lo->transfer)
 			ret = lo_read_transfer(lo, rq, pos);
 		else
-			ret = lo_read_simple(lo, rq, pos);
+			ret = lo_rw_simple(lo, rq, pos, READ);
 	}
 
 	return ret;
@@ -421,6 +560,12 @@ struct switch_request {
 	struct completion wait;
 };
 
+static inline void loop_update_dio(struct loop_device *lo)
+{
+	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file) |
+			lo->use_dio);
+}
+
 /*
  * Do the actual switch; called from the BIO completion routine
  */
@@ -441,6 +586,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
 		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+	loop_update_dio(lo);
 }
 
 /*
@@ -627,11 +773,19 @@ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
 	return sprintf(buf, "%s\n", partscan ? "1" : "0");
 }
 
+static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
+{
+	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
+
+	return sprintf(buf, "%s\n", dio ? "1" : "0");
+}
+
 LOOP_ATTR_RO(backing_file);
 LOOP_ATTR_RO(offset);
 LOOP_ATTR_RO(sizelimit);
 LOOP_ATTR_RO(autoclear);
 LOOP_ATTR_RO(partscan);
+LOOP_ATTR_RO(dio);
 
 static struct attribute *loop_attrs[] = {
 	&loop_attr_backing_file.attr,
@@ -639,6 +793,7 @@ static struct attribute *loop_attrs[] = {
 	&loop_attr_sizelimit.attr,
 	&loop_attr_autoclear.attr,
 	&loop_attr_partscan.attr,
+	&loop_attr_dio.attr,
 	NULL,
 };
 
@@ -688,6 +843,23 @@ static void loop_config_discard(struct loop_device *lo)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
+static void loop_unprepare_queue(struct loop_device *lo)
+{
+	flush_kthread_worker(&lo->worker);
+	kthread_stop(lo->worker_task);
+}
+
+static int loop_prepare_queue(struct loop_device *lo)
+{
+	init_kthread_worker(&lo->worker);
+	lo->worker_task = kthread_run(kthread_worker_fn,
+			&lo->worker, "loop%d", lo->lo_number);
+	if (IS_ERR(lo->worker_task))
+		return -ENOMEM;
+	set_user_nice(lo->worker_task, MIN_NICE);
+	return 0;
+}
+
 static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		       struct block_device *bdev, unsigned int arg)
 {
@@ -745,17 +917,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	size = get_loop_size(lo, file);
 	if ((loff_t)(sector_t)size != size)
 		goto out_putf;
-	error = -ENOMEM;
-	lo->wq = alloc_workqueue("kloopd%d",
-			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 16,
-			lo->lo_number);
-	if (!lo->wq)
+	error = loop_prepare_queue(lo);
+	if (error)
 		goto out_putf;
 
 	error = 0;
 
 	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
 
+	lo->use_dio = false;
 	lo->lo_blocksize = lo_blocksize;
 	lo->lo_device = bdev;
 	lo->lo_flags = lo_flags;
@@ -769,6 +939,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
+	loop_update_dio(lo);
 	set_capacity(lo->lo_disk, size);
 	bd_set_size(bdev, size << 9);
 	loop_sysfs_init(lo);
@@ -903,8 +1074,7 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
-	destroy_workqueue(lo->wq);
-	lo->wq = NULL;
+	loop_unprepare_queue(lo);
 	mutex_unlock(&lo->lo_ctl_mutex);
 	/*
 	 * Need not hold lo_ctl_mutex to fput backing file.
@@ -988,6 +1158,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 		lo->lo_key_owner = uid;
 	}
 
+	/* update dio if lo_offset or transfer is changed */
+	__loop_update_dio(lo, lo->use_dio);
+
 	return 0;
 }
 
@@ -1138,6 +1311,20 @@ static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
 	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
 }
 
+static int loop_set_dio(struct loop_device *lo, unsigned long arg)
+{
+	int error = -ENXIO;
+	if (lo->lo_state != Lo_bound)
+		goto out;
+
+	__loop_update_dio(lo, !!arg);
+	if (lo->use_dio == !!arg)
+		return 0;
+	error = -EINVAL;
+ out:
+	return error;
+}
+
 static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
@@ -1181,6 +1368,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
 			err = loop_set_capacity(lo, bdev);
 		break;
+	case LOOP_SET_DIRECT_IO:
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_dio(lo, arg);
+		break;
 	default:
 		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
 	}
@@ -1461,23 +1653,13 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (lo->lo_state != Lo_bound)
 		return -EIO;
 
-	if (cmd->rq->cmd_flags & REQ_WRITE) {
-		struct loop_device *lo = cmd->rq->q->queuedata;
-		bool need_sched = true;
-
-		spin_lock_irq(&lo->lo_lock);
-		if (lo->write_started)
-			need_sched = false;
-		else
-			lo->write_started = true;
-		list_add_tail(&cmd->list, &lo->write_cmd_head);
-		spin_unlock_irq(&lo->lo_lock);
+	if (lo->use_dio && !(cmd->rq->cmd_flags & (REQ_FLUSH |
+					REQ_DISCARD)))
+		cmd->use_aio = true;
+	else
+		cmd->use_aio = false;
 
-		if (need_sched)
-			queue_work(lo->wq, &lo->write_work);
-	} else {
-		queue_work(lo->wq, &cmd->read_work);
-	}
+	queue_kthread_work(&lo->worker, &cmd->work);
 
 	return BLK_MQ_RQ_QUEUE_OK;
 }
@@ -1486,48 +1668,24 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 {
 	const bool write = cmd->rq->cmd_flags & REQ_WRITE;
 	struct loop_device *lo = cmd->rq->q->queuedata;
-	int ret = -EIO;
+	int ret = 0;
 
-	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
+	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
+		ret = -EIO;
 		goto failed;
+	}
 
 	ret = do_req_filebacked(lo, cmd->rq);
-
  failed:
-	if (ret)
-		cmd->rq->errors = -EIO;
-	blk_mq_complete_request(cmd->rq);
+	/* complete non-aio request */
+	if (!cmd->use_aio || ret)
+		blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
 }
 
-static void loop_queue_write_work(struct work_struct *work)
-{
-	struct loop_device *lo =
-		container_of(work, struct loop_device, write_work);
-	LIST_HEAD(cmd_list);
-
-	spin_lock_irq(&lo->lo_lock);
- repeat:
-	list_splice_init(&lo->write_cmd_head, &cmd_list);
-	spin_unlock_irq(&lo->lo_lock);
-
-	while (!list_empty(&cmd_list)) {
-		struct loop_cmd *cmd = list_first_entry(&cmd_list,
-				struct loop_cmd, list);
-		list_del_init(&cmd->list);
-		loop_handle_cmd(cmd);
-	}
-
-	spin_lock_irq(&lo->lo_lock);
-	if (!list_empty(&lo->write_cmd_head))
-		goto repeat;
-	lo->write_started = false;
-	spin_unlock_irq(&lo->lo_lock);
-}
-
-static void loop_queue_read_work(struct work_struct *work)
+static void loop_queue_work(struct kthread_work *work)
 {
 	struct loop_cmd *cmd =
-		container_of(work, struct loop_cmd, read_work);
+		container_of(work, struct loop_cmd, work);
 
 	loop_handle_cmd(cmd);
 }
@@ -1539,7 +1697,7 @@ static int loop_init_request(void *data, struct request *rq,
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
 	cmd->rq = rq;
-	INIT_WORK(&cmd->read_work, loop_queue_read_work);
+	init_kthread_work(&cmd->work, loop_queue_work);
 
 	return 0;
 }
@@ -1595,8 +1753,11 @@ static int loop_add(struct loop_device **l, int i)
 	}
 	lo->lo_queue->queuedata = lo;
 
-	INIT_LIST_HEAD(&lo->write_cmd_head);
-	INIT_WORK(&lo->write_work, loop_queue_write_work);
+	/*
+	 * It doesn't make sense to enable merge because the I/O
+	 * submitted to backing file is handled page by page.
+	 */
+	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)