[PATCH v9 4/6] block: loop: prepare for supporing direct IO

[PATCH v9 4/6] block: loop: prepare for supporing direct IO

[Ming Lei]

This patches provides one interface for enabling direct IO
from user space:

	- userspace(such as losetup) can pass 'file' which is
	opened/fcntl as O_DIRECT

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

The last big change is to introduce LO_FLAGS_DIRECT_IO flag
for userspace to know if direct IO is used to access backing
file.

Cc: linux-api@vger.kernel.org
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
 drivers/block/loop.c      | 65 ++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/block/loop.h      |  2 ++
 include/uapi/linux/loop.h |  1 +
 3 files changed, 67 insertions(+), 1 deletion(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1875aad..a56f973 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -164,6 +164,49 @@ 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;
+	bool use_dio;
+	unsigned dio_align = inode->i_sb->s_bdev ?
+		(bdev_io_min(inode->i_sb->s_bdev) - 1) : 0;
+
+	/*
+	 * We support direct I/O only if lo_offset is aligned
+	 * with the min I/O size of backing device.
+	 *
+	 * Request's offset and size will be checked in I/O path.
+	 */
+	if (dio) {
+		if (!(lo->lo_offset & dio_align) &&
+				mapping->a_ops->direct_IO)
+			use_dio = true;
+		else
+			use_dio = false;
+	} else {
+		use_dio = false;
+	}
+
+	/* 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;
+	lo->dio_align = dio_align;
+	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)
 {
@@ -173,8 +216,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 
 	if (unlikely((loff_t)x != size))
 		return -EFBIG;
-	if (lo->lo_offset != offset)
+	if (lo->lo_offset != offset) {
 		lo->lo_offset = offset;
+
+		/* update dio if lo_offset is changed*/
+		__loop_update_dio(lo, lo->use_dio);
+	}
 	if (lo->lo_sizelimit != sizelimit)
 		lo->lo_sizelimit = sizelimit;
 	set_capacity(lo->lo_disk, x);
@@ -421,6 +468,11 @@ 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));
+}
+
 /*
  * Do the actual switch; called from the BIO completion routine
  */
@@ -441,6 +493,7 @@ 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 +680,19 @@ 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 +700,7 @@ static struct attribute *loop_attrs[] = {
 	&loop_attr_sizelimit.attr,
 	&loop_attr_autoclear.attr,
 	&loop_attr_partscan.attr,
+	&loop_attr_dio.attr,
 	NULL,
 };
 
@@ -783,6 +845,7 @@ 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..63f8e14 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -58,6 +58,8 @@ struct loop_device {
 	struct mutex		lo_ctl_mutex;
 	struct kthread_worker	worker;
 	struct task_struct	*worker_task;
+	unsigned		dio_align;
+	bool			use_dio;
 
 	struct request_queue	*lo_queue;
 	struct blk_mq_tag_set	tag_set;
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index e0cecd2..949851c 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -21,6 +21,7 @@ enum {
 	LO_FLAGS_READ_ONLY	= 1,
 	LO_FLAGS_AUTOCLEAR	= 4,
 	LO_FLAGS_PARTSCAN	= 8,
+	LO_FLAGS_DIRECT_IO	= 16,
 };
 
 #include <asm/posix_types.h>	/* for __kernel_old_dev_t */
-- 
1.9.1

[PATCH v9 5/6] block: loop: introduce ioctl command of LOOP_SET_DIRECT_IO

[Ming Lei]

If loop block is mounted via 'mount -o loop', it isn't easy
to pass file descriptor opened as O_DIRECT, so this patch
introduces a new command to support direct IO for this case.

Cc: linux-api@vger.kernel.org
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
 drivers/block/loop.c      | 19 +++++++++++++++++++
 include/uapi/linux/loop.h |  1 +
 2 files changed, 20 insertions(+)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a56f973..06a737b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1214,6 +1214,20 @@ 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)
 {
@@ -1257,6 +1271,11 @@ 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;
 	}
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index 949851c..c8125ec 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -87,6 +87,7 @@ struct loop_info64 {
 #define LOOP_GET_STATUS64	0x4C05
 #define LOOP_CHANGE_FD		0x4C06
 #define LOOP_SET_CAPACITY	0x4C07
+#define LOOP_SET_DIRECT_IO	0x4C08
 
 /* /dev/loop-control interface */
 #define LOOP_CTL_ADD		0x4C80
-- 
1.9.1