[PATCH v5 4/5] block: loop: prepare for supporing direct IO

[Ming Lei]

This patches provides two approaches for enabling direct IO
from user space:

	- userspace(such as losetup) can pass 'file' which is
	opened/fcntl as O_DIRECT
	- sysfs file is provided to run dio tests easily

Also __loop_update_dio() is introduced to check if direct I/O
can be used on current loop setting.

Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxxxxx>
---
 drivers/block/loop.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/block/loop.h |  1 +
 2 files changed, 77 insertions(+)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 555b895..0b1ee2b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -421,6 +421,44 @@ struct switch_request {
 	struct completion wait;
 };
 
+static void __loop_update_dio(struct loop_device *lo, bool dio)
+{
+	struct file *file = lo->lo_backing_file;
+	struct inode *inode = file->f_mapping->host;
+	bool use_dio;
+
+	/*
+	 * loop block's logical block size is 512, now
+	 * we support direct I/O only if the backing
+	 * block devices' minimize I/O size is 512.
+	 */
+	if (dio) {
+		if (inode->i_sb->s_bdev &&
+			bdev_io_min(inode->i_sb->s_bdev) == 512)
+			use_dio = true;
+		else
+			use_dio = false;
+	} else {
+		use_dio = false;
+	}
+
+	if (lo->use_dio == use_dio)
+		return;
+
+	/* flush dirty pages to avoid stale data from following dio */
+	if (use_dio)
+		vfs_fsync(file, 0);
+
+	blk_mq_freeze_queue(lo->lo_queue);
+	lo->use_dio = use_dio;
+	blk_mq_unfreeze_queue(lo->lo_queue);
+}
+
+static inline void loop_update_dio(struct loop_device *lo)
+{
+	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file));
+}
+
 /*
  * Do the actual switch; called from the BIO completion routine
  */
@@ -441,6 +479,7 @@ 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);
 }
 
 /*
@@ -627,6 +666,41 @@ 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_do_show_use_dio(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct loop_device *lo = disk->private_data;
+
+	return sprintf(buf, "%s\n", lo->use_dio ? "1" : "0");
+}
+
+ssize_t loop_attr_do_store_use_dio(struct device *dev,
+		struct device_attribute *attr, const char *buf,
+		size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct loop_device *lo = disk->private_data;
+	int err;
+	unsigned long v;
+
+	if (!lo->lo_backing_file)
+		return -ENODEV;
+
+	err = kstrtoul(buf, 10, &v);
+	if (err < 0)
+		return err;
+
+	__loop_update_dio(lo, !!v);
+	if  (lo->use_dio != !!v)
+		return -EINVAL;
+	return count;
+}
+
+static struct device_attribute loop_attr_use_dio =
+	__ATTR(use_dio, S_IRUGO | S_IWUSR, loop_attr_do_show_use_dio,
+			loop_attr_do_store_use_dio);
+
 LOOP_ATTR_RO(backing_file);
 LOOP_ATTR_RO(offset);
 LOOP_ATTR_RO(sizelimit);
@@ -639,6 +713,7 @@ static struct attribute *loop_attrs[] = {
 	&loop_attr_sizelimit.attr,
 	&loop_attr_autoclear.attr,
 	&loop_attr_partscan.attr,
+	&loop_attr_use_dio.attr,
 	NULL,
 };
 
@@ -783,6 +858,7 @@ 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);
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index b6c7d21..d1de221 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -58,6 +58,7 @@ struct loop_device {
 	struct mutex		lo_ctl_mutex;
 	struct kthread_worker	worker;
 	struct task_struct	*worker_task;
+	bool			use_dio;
 
 	struct request_queue	*lo_queue;
 	struct blk_mq_tag_set	tag_set;
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/