[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.c b/drivers/media/radio/radio-gemtek.c
index 73985f6..2599364 100644
--- a/drivers/media/radio/radio-gemtek.c
+++ b/drivers/media/radio/radio-gemtek.c
@@ -378,7 +378,7 @@
static const struct v4l2_file_operations gemtek_fops = {
.owner = THIS_MODULE,
- .ioctl = video_ioctl2,
+ .unlocked_ioctl = video_ioctl2,
};
static int vidioc_querycap(struct file *file, void *priv,
@@ -577,12 +577,6 @@
gt->vdev.release = video_device_release_empty;
video_set_drvdata(>->vdev, gt);
- if (video_register_device(>->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
- v4l2_device_unregister(v4l2_dev);
- release_region(gt->io, 1);
- return -EBUSY;
- }
-
/* Set defaults */
gt->lastfreq = GEMTEK_LOWFREQ;
gt->bu2614data = 0;
@@ -590,6 +584,12 @@
if (initmute)
gemtek_mute(gt);
+ if (video_register_device(>->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
+ v4l2_device_unregister(v4l2_dev);
+ release_region(gt->io, 1);
+ return -EBUSY;
+ }
+
return 0;
}