[PATCH 1/2] nbd: make nbd device wait for its users

[Markus Pargmann]

From: "Pranay Kr. Srivastava" <pranjas@xxxxxxxxx>

When a timeout occurs or a recv fails, then instead of abruplty killing
nbd block device wait for it's users to finish.

This is more required when filesystem(s) like ext2 or ext3 don't expect
their buffer heads to disappear while the filesystem is mounted.

Each open is counted. The blockdevice is kept open until the last user
closes the block device. This offers the possibility as well to open a
new socket to be used while the filesystems are mounted.

Signed-off-by: Pranay Kr. Srivastava <pranjas@xxxxxxxxx>

[mpa: Keep the blockdevice open until all users left]
Signed-off-by: Markus Pargmann <mpa@xxxxxxxxxxxxxx>
---
Hi,

I used your patch and changed it a bit based on my ideas. The general
difference is that this keeps the block device open. After all users left, the
device is reset.

The followup patch then restricts access to ioctls after a disconnect. I wanted
to avoid that anyone sets up anything new without all the old users leaving.

Please let me know what you think about this.

Best Regards,

Markus

 drivers/block/nbd.c | 62 ++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 45 insertions(+), 17 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 1efc26bf1d21..620660f3ff0f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -69,6 +69,8 @@ struct nbd_device {
 #if IS_ENABLED(CONFIG_DEBUG_FS)
 	struct dentry *dbg_dir;
 #endif
+	atomic_t users; /* Users that opened the block device */
+	struct block_device *bdev;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -655,9 +657,26 @@ static int nbd_set_socket(struct nbd_device *nbd, struct socket *sock)
 	return ret;
 }
 
+static void nbd_bdev_reset(struct block_device *bdev)
+{
+	set_device_ro(bdev, false);
+	bdev->bd_inode->i_size = 0;
+	if (max_part > 0) {
+		blkdev_reread_part(bdev);
+		bdev->bd_invalidated = 1;
+	}
+}
+
 /* Reset all properties of an NBD device */
 static void nbd_reset(struct nbd_device *nbd)
 {
+	sock_shutdown(nbd);
+	nbd_clear_que(nbd);
+	if (nbd->bdev) {
+		kill_bdev(nbd->bdev);
+		nbd_bdev_reset(nbd->bdev);
+	}
+
 	nbd->disconnect = false;
 	nbd->timedout = false;
 	nbd->blksize = 1024;
@@ -669,16 +688,6 @@ static void nbd_reset(struct nbd_device *nbd)
 	del_timer_sync(&nbd->timeout_timer);
 }
 
-static void nbd_bdev_reset(struct block_device *bdev)
-{
-	set_device_ro(bdev, false);
-	bdev->bd_inode->i_size = 0;
-	if (max_part > 0) {
-		blkdev_reread_part(bdev);
-		bdev->bd_invalidated = 1;
-	}
-}
-
 static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
 {
 	if (nbd->flags & NBD_FLAG_READ_ONLY)
@@ -803,18 +812,11 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		mutex_lock(&nbd->tx_lock);
 		nbd->task_recv = NULL;
 
-		sock_shutdown(nbd);
-		nbd_clear_que(nbd);
-		kill_bdev(bdev);
-		nbd_bdev_reset(bdev);
-
 		if (nbd->disconnect) /* user requested, ignore socket errors */
 			error = 0;
 		if (nbd->timedout)
 			error = -ETIMEDOUT;
 
-		nbd_reset(nbd);
-
 		return error;
 	}
 
@@ -853,10 +855,35 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 	return error;
 }
 
+static int nbd_open(struct block_device *bdev, fmode_t mode)
+{
+	struct nbd_device *nbd = bdev->bd_disk->private_data;
+
+	atomic_inc(&nbd->users);
+
+	if (!nbd->bdev)
+		nbd->bdev = bdev;
+
+	return 0;
+}
+
+static void nbd_release(struct gendisk *disk, fmode_t mode)
+{
+	struct nbd_device *nbd = disk->private_data;
+
+	if (atomic_dec_and_test(&nbd->users)) {
+		mutex_lock(&nbd->tx_lock);
+		nbd_reset(nbd);
+		mutex_unlock(&nbd->tx_lock);
+	}
+}
+
 static const struct block_device_operations nbd_fops = {
 	.owner =	THIS_MODULE,
 	.ioctl =	nbd_ioctl,
 	.compat_ioctl =	nbd_ioctl,
+	.open =		nbd_open,
+	.release =	nbd_release,
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -1087,6 +1114,7 @@ static int __init nbd_init(void)
 		disk->private_data = &nbd_dev[i];
 		sprintf(disk->disk_name, "nbd%d", i);
 		nbd_reset(&nbd_dev[i]);
+		atomic_set(&nbd_dev[i].users, 0);
 		add_disk(disk);
 	}
 
-- 
2.1.4