[media] BKL: trivial BKL removal from V4L2 radio drivers

The patch converts a bunch of V4L2 radio drivers to unlocked_ioctl.

These are all simple conversions: most already had a lock and so the ioctl
fop could simply be replaced by unlocked_ioctl.

radio-miropcm20.c was converted to use the new V4L2 core lock.

While doing this work I noticed that many of these drivers initialized
some more fields or muted audio or something like that *after* creating
the device node. This should be done before the device node is created
to prevent problems. Especially hal tends to grab a device node as soon
as it is created.

In one or two cases the mutex_init was even done after the device creation!

Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
diff --git a/drivers/media/radio/radio-gemtek-pci.c b/drivers/media/radio/radio-gemtek-pci.c
index 7903967..28fa85b 100644
--- a/drivers/media/radio/radio-gemtek-pci.c
+++ b/drivers/media/radio/radio-gemtek-pci.c
@@ -361,7 +361,7 @@
 
 static const struct v4l2_file_operations gemtek_pci_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops gemtek_pci_ioctl_ops = {
@@ -422,11 +422,11 @@
 	card->vdev.release = video_device_release_empty;
 	video_set_drvdata(&card->vdev, card);
 
+	gemtek_pci_mute(card);
+
 	if (video_register_device(&card->vdev, VFL_TYPE_RADIO, nr_radio) < 0)
 		goto err_video;
 
-	gemtek_pci_mute(card);
-
 	v4l2_info(v4l2_dev, "Gemtek PCI Radio (rev. %d) found at 0x%04x-0x%04x.\n",
 		pdev->revision, card->iobase, card->iobase + card->length - 1);