[media] media: st-rc: Remove .owner field for driver
There is no need to init .owner field.
Based on the patch from Peter Griffin <peter.griffin@linaro.org>
"mmc: remove .owner field for drivers using module_platform_driver"
This patch removes the superflous .owner field for drivers which
use the module_platform_driver API, as this is overriden in
platform_driver_register anyway."
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> Acked-by: Maxime Coquelin <maxime.coquelin@st.com> Acked-by: Peter Griffin <peter.griffin@linaro.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
[media] media: st-rc: move pm ops setup out of conditional compilation
This patch moves setting of pm_ops out of the CONFIG_PM_SLEEP condition.
Setting pm ops under CONFIG_PM_SLEEP does not make any sense.
This patch also remove unnecessary also remove CONFIG_PM condition for pm
member in st_rc_driver structure.
[media] media: st-rc: move to using reset_control_get_optional
This patch fixes a compilation error while building with the
random kernel configuration.
drivers/media/rc/st_rc.c: In function 'st_rc_probe':
drivers/media/rc/st_rc.c:281:2: error: implicit declaration of
function 'reset_control_get' [-Werror=implicit-function-declaration]
rc_dev->rstc = reset_control_get(dev, NULL);
drivers/media/rc/st_rc.c:281:15: warning: assignment makes pointer
from integer without a cast [enabled by default]
rc_dev->rstc = reset_control_get(dev, NULL);
Reported-by: Jim Davis <jim.epost@gmail.com> Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> Acked-by: Maxime Coquelin <maxime.coquelin@st.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Guoxiong Yan [Sun, 31 Aug 2014 02:39:10 +0000 (23:39 -0300)]
[media] rc: Introduce hix5hd2 IR transmitter driver
IR transmitter driver for Hisilicon hix5hd2 soc
By default all protocols are disabled.
For example nec decoder can be enabled by either
1. ir-keytable -p nec
2. echo nec > /sys/class/rc/rc0/protocols
See see Documentation/ABI/testing/sysfs-class-rc
[mchehab@osg.samsung.com: Add a fixup for the driver to compile on
archs that don't provide writel_relaxed() macro] Signed-off-by: Guoxiong Yan <yanguoxiong@huawei.com> Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Shuah Khan [Thu, 14 Aug 2014 01:09:24 +0000 (22:09 -0300)]
[media] media: tuner xc5000 - try to avoid firmware load in resume path
xc5000 doesn't load firmware at attach time instead loads it
when it needs to set and change configuration from its init,
frequency, digital and analog mode set interffaces. As a result,
when system is suspended before firmware is loaded, firmware
load can be avoided during resume. Loading formware in this
scenario results in slowpath warnings during resume as it won't
be in the suspend firmware cache.
[media] media: tuner xc5000 - release firmwware from xc5000_release()
xc5000 releases firmware right after loading it. Change it to
save the firmware and release it from xc5000_release(). This
helps avoid fecthing firmware when forced firmware load requests
come in to change analog tv frequence and when firmware needs to
be reloaded after suspend and resume.
drivers/media/pci/saa7134/saa7134-go7007.c: In function ‘saa7134_go7007_interface_reset’:
drivers/media/pci/saa7134/saa7134-go7007.c:147:6: warning: variable ‘status’ set but not used [-Wunused-but-set-variable]
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com> Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
drivers/media/pci/saa7134/saa7134-go7007.c:247:17: warning: incorrect type in argument 1 (different base types)
drivers/media/pci/saa7134/saa7134-go7007.c:247:17: expected unsigned int [unsigned] val
drivers/media/pci/saa7134/saa7134-go7007.c:247:17: got restricted __le32 [usertype] <noident>
drivers/media/pci/saa7134/saa7134-go7007.c:252:17: warning: incorrect type in argument 1 (different base types)
drivers/media/pci/saa7134/saa7134-go7007.c:252:17: expected unsigned int [unsigned] val
drivers/media/pci/saa7134/saa7134-go7007.c:252:17: got restricted __le32 [usertype] <noident>
drivers/media/pci/saa7134/saa7134-go7007.c:299:9: warning: incorrect type in argument 1 (different base types)
drivers/media/pci/saa7134/saa7134-go7007.c:299:9: expected unsigned int [unsigned] val
drivers/media/pci/saa7134/saa7134-go7007.c:299:9: got restricted __le32 [usertype] <noident>
drivers/media/pci/saa7134/saa7134-go7007.c:300:9: warning: incorrect type in argument 1 (different base types)
drivers/media/pci/saa7134/saa7134-go7007.c:300:9: expected unsigned int [unsigned] val
drivers/media/pci/saa7134/saa7134-go7007.c:300:9: got restricted __le32 [usertype] <noident>
[media] saa7134: Fix compilation breakage when go7007 is not selected
All error/warnings:
drivers/built-in.o: In function `saa7134_go7007_fini':
>> saa7134-go7007.c:(.text+0x3b628b): undefined reference to `go7007_snd_remove'
drivers/built-in.o: In function `saa7134_go7007_interface_reset':
>> saa7134-go7007.c:(.text+0x3b659a): undefined reference to `go7007_read_interrupt'
drivers/built-in.o: In function `saa7134_go7007_init':
>> saa7134-go7007.c:(.text+0x3b65fa): undefined reference to `go7007_alloc'
>> saa7134-go7007.c:(.text+0x3b66ed): undefined reference to `go7007_boot_encoder'
>> saa7134-go7007.c:(.text+0x3b66fe): undefined reference to `go7007_register_encoder'
drivers/built-in.o: In function `saa7134_go7007_irq_ts_done':
>> saa7134-go7007.c:(.text+0x3b6c2a): undefined reference to `go7007_parse_video_stream'
>> saa7134-go7007.c:(.text+0x3b6c86): undefined reference to `go7007_parse_video_stream'
This happens when:
- VIDEO_SAA7134 is either 'm' or 'y'
- VIDEO_GO7007 is not selected.
Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Sun, 21 Sep 2014 09:52:03 +0000 (06:52 -0300)]
[media] saa7134: add saa7134-go7007
This patch adds support to saa7134 for 'WIS Voyager or compatible' PCI boards
such as the Sensoray model 614 with which this patch was tested. It is a
saa7134-based PCI board with a go7007 MPEG encoder. This was a patch when the
go7007 was still in staging and was not applied when go7007 was moved to
drivers/media since it needed more work.
That work is now done and this last piece of go7007 support can now go in.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Tested-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Dan Carpenter [Mon, 22 Sep 2014 07:58:53 +0000 (04:58 -0300)]
[media] as102: remove some unneeded checks
We know "ret" is zero so we don't need to test for it. It upsets the
static checkers when we test stuff but we know the answer.
drivers/media/usb/as102/as102_usb_drv.c:164 as102_send_ep1() warn: we tested 'ret' before and it was 'false'
drivers/media/usb/as102/as102_usb_drv.c:189 as102_read_ep2() warn: we tested 'ret' before and it was 'false'
Also, we don't need to initialize "ret".
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Maciej Matraszek [Mon, 15 Sep 2014 08:14:48 +0000 (05:14 -0300)]
[media] v4l2-common: fix overflow in v4l_bound_align_image()
Fix clamp_align() used in v4l_bound_align_image() to prevent overflow
when passed large value like UINT32_MAX.
In the current implementation:
clamp_align(UINT32_MAX, 8, 8192, 3)
returns 8, because in line:
x = (x + (1 << (align - 1))) & mask;
x overflows to (-1 + 4) & 0x7 = 3, while expected value is 8192.
v4l_bound_align_image() is heavily used in VIDIOC_S_FMT and
VIDIOC_SUBDEV_S_FMT ioctls handlers, and documentation of the latter
explicitly states that:
"The modified format should be as close as possible to the original
request."
-- http://linuxtv.org/downloads/v4l-dvb-apis/vidioc-subdev-g-fmt.html
Thus one would expect, that passing UINT32_MAX as format width and
height will result in setting maximum possible resolution for the
device. Particularly, when the driver doesn't support
VIDIOC_ENUM_FRAMESIZES ioctl, which is common in the codebase.
Frank Schaefer [Sat, 13 Sep 2014 08:52:21 +0000 (05:52 -0300)]
[media] em28xx: get rid of field has_audio in struct em28xx_audio_mode
Field has_audio in struct em28xx_audio_mode is used together with value
EM28XX_NO_AC97 of field ac97 to determine the internal type of audio
(none/i2s/ac97). This makes the code difficult to understand:
Simplify the whole thing by introducing an enum em28xx_int_audio_type
which describes the internal audio type (none, ac97, i2s) and is hooked
directly to the device struct. Then get rid of field has_audio in struct
em28xx_audio_mode.
A follow-up patch will then remove struct em28xx_ac97_mode and finally
the whole struct em28xx_audio_mode.
Signed-off-by: Frank Schäfer <fschaefer.oss@googlemail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Frank Schaefer [Sat, 13 Sep 2014 08:52:20 +0000 (05:52 -0300)]
[media] em28xx: simplify usb audio class handling
As far as we know devices can either have audio class or vendor class
usb interfaces but not both at the same time. Even if both interface
types could be provided by devices at the same time, the current code is
totally broken for that case.
So clean up and simplify the usb audio class handling by replacing
fields "has_audio_class" (device has usb audio class compliant
interface) and "has_alsa_audio" (device has vendor audio interface) in
struct em28xx with a single enum em28xx_usb_audio_type.
Signed-off-by: Frank Schäfer <fschaefer.oss@googlemail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Frank Schaefer [Sat, 13 Sep 2014 08:52:19 +0000 (05:52 -0300)]
[media] em28xx: remove some unnecessary fields from struct em28xx_audio_mode
Fields "ac97_feat", "ac97_vendor_id" and "i2s_samplerates" of struct
em28xx_audio_mode are used nowhere, except in function
em28xx_audio_setup(). So get rid of them and use local variables
instead.
Signed-off-by: Frank Schäfer <fschaefer.oss@googlemail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Olli Salonen [Thu, 11 Sep 2014 20:01:38 +0000 (17:01 -0300)]
[media] si2157: Add support for Si2147-A30 tuner
This patch adds support for Si2147-A30 tuner. Fairly trivial, no firmware needed for this tuner. However, command 14 00 02 07 01 00 seems to be mandatory. On Si2157 and Si2158 the value 0x0100 is the default value, so this patch does not impact the existing tuners/devices. On Si2147 the default is 0x0000 and I can't get a lock with that value.
While here, fix the return length of the previous set command to 4 bytes.
Signed-off-by: Olli Salonen <olli.salonen@iki.fi> Acked-by: Antti Palosaari <crope@iki.fi> Reviewed-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Dan Carpenter [Tue, 9 Sep 2014 12:11:23 +0000 (09:11 -0300)]
[media] firewire: firedtv-avc: fix more potential buffer overflow
"program_info_length" is user controlled and can go up to 4095. The
operand[] array has 509 bytes so we need to add a limit here to prevent
buffer overflows.
The " - 4" in the limit check is because we have 4 bytes more data to
add after the memcpy().
[mchehab@osg.samsung.com: as I merged the version 1 of the patch, I needed
to rebase to apply just the differences between v1 and v2] Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
mceusb_init_rc_dev() does usb_get_dev(), but there is no any
usb_put_dev() in the driver.
The patch tries to straighten logic. It moves usb_get_dev()
directly to mceusb_dev_probe() and adds usb_put_dev() to an error path
and to mceusb_dev_disconnect().
Found by Linux Driver Verification project (linuxtesting.org).
"program_info_length" is user controlled and can go up to 4095. The
operand[] array has 509 bytes so we need to add a limit here to prevent
buffer overflows.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Stefan Richter <stefanr@s5r6.in-berlin.de> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
[media] em28xx: check if a device has audio earlier
Better to split chipset detection from the audio setup. So, move the
detection code to em28xx_init_dev().
It broke analog audio of the Hauppauge winTV HVR 900 and very likely many other
em28xx devices.
Background:
The local variable has_audio in em28xx_usb_probe() describes if the currently
probed _usb_interface_ has an audio endpoint, while dev->audio_mode.has_audio
means that the _device_ as a whole provides analog audio.
Hence it is wrong to set dev->audio_mode.has_audio = has_audio in em28xx_usb_probe().
As result, audio support is no longer detected and configured on devices which
have the audio endpoint on a separate interface, because em28xx_audio_setup()
bails out immediately at the beginning.
Revert the faulty commit to restore the old audio detection procedure, which checks
the chip configuration register to determine if the device has analog audio.
[media] cx231xx: Add support for Hauppauge WinTV-HVR-901H (1114xx)
Add support for:
[2040:b139] Hauppauge WinTV HVR-901H (1114xx)
According to the inf file, the hardware is similar to [2040:b131] Hauppauge WinTV 930C-HD (model 1114xx)
The only difference is the demod Si2161 instead of Si2165 (but both are
supported by the si2165 driver).
[media] cx231xx: Add support for Hauppauge WinTV-HVR-900H (111xxx)
Add support for:
[2040:b138] Hauppauge WinTV HVR-900H (111xxx)
The hardware is similar to [2040:b130] Hauppauge WinTV 930C-HD (model 1113xx)
The only difference is the demod Si2161 instead of Si2165 (but both are
supported by the si2165 driver).
Jingoo Han [Fri, 29 Aug 2014 03:49:43 +0000 (00:49 -0300)]
[media] v4l: ti-vpe: Remove casting the return value which is a void pointer
Casting the return value which is a void pointer is redundant.
The conversion from void pointer to any other pointer type is
guaranteed by the C programming language.
Signed-off-by: Jingoo Han <jg1.han@samsung.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
[media] au0828: explicitly identify boards with analog TV
Right now, the au0828 driver uses .tuner to detect if analog
tv is being used or not. By not filling .tuner fields at the
board struct, the I2C core can't do decisions based on it.
So, add a field to explicitly tell when analog TV is supported.
[media] au0828-cards: remove a comment about i2c clock stretching
This comment is already at the au0828-i2c where it belongs.
So, remove it from a board's entry. It doesn't make any sense
there, as we're setting the clock to 250kHz there, slowing it
down only at the au0828-i2c.
cab_state->modulation is initialized with a wrong value:
drivers/media/dvb-frontends/stv0367.c:3000:42: warning: mixing different enum types
drivers/media/dvb-frontends/stv0367.c:3000:42: int enum fe_modulation versus
drivers/media/dvb-frontends/stv0367.c:3000:42: int enum stv0367cab_mod
as it was declared as "enum stv0367cab_mod". While it could be fixed,
there's no value on it, as this is never used.
So, just remove the modulation from cab_state structure.
Frank Schaefer [Fri, 15 Aug 2014 18:16:58 +0000 (15:16 -0300)]
[media] em28xx-input: i2c IR decoders: improve i2c_client handling
Instead of using a temporary stack allocated i2c_client in em28xx_i2c_ir_handle_key(),
allocate/free the i2c_client at module init/uninit and hook it into struct em28xx_IR
(if the device has an i2c IR decoder).
This reduces the frame size of function em28xx_i2c_ir_handle_key() and speeds
it up a bit.
Also make sure that all fields of struct i2c_client are initialized properly.
Signed-off-by: Frank Schäfer <fschaefer.oss@googlemail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Wennborg [Thu, 7 Aug 2014 05:42:04 +0000 (02:42 -0300)]
[media] dvb: return the error from i2c_transfer if negative
Just returns whatever error that was returned by the i2c core,
in the case of errors, only returning -EREMOTEIO if the transfer size
is not what it was expected.
Signed-off-by: Hans Wennborg <hans@hanshq.net> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Morgan Phillips [Mon, 8 Sep 2014 12:49:47 +0000 (09:49 -0300)]
[media] sn9c20x: fix checkpatch warning: sizeof cmatrix should be sizeof(cmatrix)
Signed-off-by: Morgan Phillips <winter2718@gmail.com> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Morgan Phillips [Mon, 8 Sep 2014 12:32:22 +0000 (09:32 -0300)]
[media] sn9c20x.c: fix checkpatch error: that open brace { should be on the previous line
Signed-off-by: Morgan Phillips <winter2718@gmail.com> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Sat, 20 Sep 2014 13:19:33 +0000 (10:19 -0300)]
[media] cx23885: fix size helper functions
The norm_swidth function was unused and is dropped. It's not clear
what the purpose of that function was.
The norm_maxh function was changed so it tests for 60 Hz standards
rather than for 50 Hz standards. The is the preferred order.
The norm_maxw function was poorly written and used: it gives the maximum
allowed line width for the given standard. For 60 Hz that's 720, but
for 50 Hz that's 768 which allows for 768x576 which gives you square
pixels. For 60 Hz formats it is 640x480 that gives square pixels, so
there is no need to go beyond 720.
The initial width was set using norm_maxh(), which was wrong. Just set
to 720, that's what you normally use. Since the initial standard was
NTSC anyway the initial width was always 720 anyway.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Sat, 20 Sep 2014 13:19:32 +0000 (10:19 -0300)]
[media] cx23885: fix VBI support
Tested VBI support and discovered that the wrong offset was used.
After this change it is now working. Verified with CC/XDS for NTSC
and WSS/Teletext on PAL.
It also reported the wrong start lines for the second field. That's
now fixed as well.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Sat, 20 Sep 2014 10:36:39 +0000 (07:36 -0300)]
[media] adv7604/adv7842: fix il_vbackporch typo and zero the struct
Both adv7604 and adv7842 had the same typo in the code that sets
the vertical backporch for the second interlaced field: it was
assigned to vbackporch instead of il_vbackporch.
In addition, the timings struct wasn't zeroed in the adv7842 driver,
leaving several fields to undefined values causing the timing match
function to fail.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Sat, 20 Sep 2014 10:36:38 +0000 (07:36 -0300)]
[media] v4l2-dv-timings: only check standards if non-zero
If one or both of the timings being compared have the standards field
with value 0, then accept that. Only check for matching standards if
both timings have actually filled in that field.
Otherwise no match will ever be found since when timings are detected
the standards field will typically be set to 0 by the driver.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Sat, 20 Sep 2014 09:11:44 +0000 (06:11 -0300)]
[media] vivid: add teletext support to VBI capture
This is useful to test teletext capture applications like alevt and mtt.
It also fixes a previously undetected bug where the PAL VBI start line
of the second field was off by one. Using the new field start defines
helps a lot fixing such bugs.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
[media] v4l2: uvcvideo: Allow using larger buffers
A test in uvc_video_decode_isoc() checks whether an image has been
received from the camera completely. For this the data amount is compared
to the buffer length, which, however, doesn't have to be equal to the
image size. Switch to using formats .sizeimage field for an exact
expected image size.
drivers/media/usb/hackrf/hackrf.c:64:3: warning: this decimal constant is unsigned only in ISO C90 [enabled by default]
.rangehigh = 4294967294, /* max u32, hw goes over 7GHz */
^
[media] v4l: Add ARGB555X and XRGB555X pixel formats
The existing RGB555X pixel format is ill-defined in respect to its alpha
bit and its meaning is driver dependent. Create new standard ARGB555X
and XRGB555X variants with clearly defined meanings and make the
existing variant deprecated.
The new pixel formats 4CC values have been selected to match the DRM
4CCs for the same in-memory formats.
William Manley [Thu, 13 Mar 2014 12:38:48 +0000 (09:38 -0300)]
[media] uvcvideo: Work around buggy Logitech C920 firmware
The uvcvideo webcam driver exposes the v4l2 control "Exposure (Absolute)"
which allows the user to control the exposure time of the webcam,
essentially controlling the brightness of the received image. By default
the webcam automatically adjusts the exposure time automatically but the
if you set the control "Exposure, Auto"="Manual Mode" the user can fix
the exposure time.
Unfortunately it seems that the Logitech C920 has a firmware bug where
it will forget that it's in manual mode temporarily during initialisation.
This means that the camera doesn't respect the exposure time that the user
requested if they request it before starting to stream video. They end up
with a video stream which is either too bright or too dark and must reset
the controls after video starts streaming.
This patch introduces the quirk UVC_QUIRK_RESTORE_CTRLS_ON_INIT which
causes the cached controls to be re-uploaded to the camera immediately
after initialising the camera. This quirk is applied to the C920 to work
around this camera bug.
Vincent Palatin [Thu, 4 Sep 2014 00:47:48 +0000 (21:47 -0300)]
[media] v4l: uvcvideo: Add support for pan/tilt speed controls
Map V4L2_CID_TILT_SPEED and V4L2_CID_PAN_SPEED to the standard UVC
CT_PANTILT_RELATIVE_CONTROL terminal control request.
Tested by plugging a Logitech ConferenceCam C3000e USB camera
and controlling pan/tilt from the userspace using the VIDIOC_S_CTRL ioctl.
Verified that it can pan and tilt at the same time in both directions.
this patch removes unneeded dependency of ARCH_OMAP3
on VIDEO_DM6446_CCDC.
Also the top level platform Makefile descended into
davinci/ without any dependency so just drop the
dependency obj-y, as obj-$(CONFIG_ARCH_DAVINCI)
already exists.
Reported-by: Andreas Ruprecht <rupran@einserver.de> Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com> Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
[media] media: davinci: vpif_capture: fix the check on suspend/resume callbacks
It is possible to call STREAMON without having any buffers queued.
So vb2_is_streaming() can return true without start_streaming()
having been called. Only after at least one buffer has been
queued will start_streaming be called.
The check vb2_is_streaming() is incorrect as this would start
the DMA without having proper DMA pointers set up. this patch
uses vb2_start_streaming_called() instead to check is streaming
was called.
[media] media: davinci: vpif_display: fix the check on suspend/resume callbacks
It is possible to call STREAMON without having any buffers queued.
So vb2_is_streaming() can return true without start_streaming()
having been called. Only after at least one buffer has been
queued will start_streaming be called.
The check vb2_is_streaming() is incorrect as this would start
the DMA without having proper DMA pointers set up. this patch
uses vb2_start_streaming_called() instead to check is streaming
was called.
Hans de Goede [Sun, 31 Aug 2014 10:19:21 +0000 (07:19 -0300)]
[media] videobuf: Allow reqbufs(0) to free current buffers
All the infrastructure for this is already there, and despite our desires for
the old videobuf code to go away, it is currently still in use in 18 drivers.
Allowing reqbufs(0) makes these drivers behave consistent with modern drivers,
making live easier for userspace, see e.g. :
https://bugzilla.gnome.org/show_bug.cgi?id=735660
Signed-off-by: Hans de Goede <hdegoede@redhat.com> Acked-by: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Hans Verkuil [Mon, 25 Aug 2014 11:57:59 +0000 (08:57 -0300)]
[media] videobuf2-core: take mmap_sem before calling __qbuf_userptr
(Changes since v2: dropped local variable as suggested by Laurent)
Commit f035eb4e976ef5a059e30bc91cfd310ff030a7d3 (videobuf2: fix lockdep warning)
unfortunately removed the mmap_sem lock that is needed around the call to
__qbuf_userptr. Amazingly nobody noticed this (especially me as the author)
until Jan Kara pointed this out to me.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reported-by: Jan Kara <jack@suse.cz> Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Antti Palosaari [Mon, 4 Aug 2014 02:40:23 +0000 (23:40 -0300)]
[media] tda18212: rename state from 'priv' to 'dev'
foo_dev seems to be most correct term for the structure holding data
of each device instance. It is most used term in Kernel codebase and also
examples from book Linux Device Drivers, Third Edition, uses it.
Signed-off-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Antti Palosaari [Mon, 4 Aug 2014 02:26:27 +0000 (23:26 -0300)]
[media] tda18212: clean logging
There is no need to print module name nor function name as those
are done by kernel logging system when dev_xxx logging is used and
driver is proper I2C driver.
Signed-off-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Antti Palosaari [Mon, 4 Aug 2014 01:43:26 +0000 (22:43 -0300)]
[media] tda18212: prepare for I2C client conversion
We need carry pointer to frontend via config struct
(I2C platform_data ptr) when I2C model is used. Add that pointer
first in order to keep build unbreakable during conversion.
Signed-off-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Antti Palosaari [Thu, 4 Sep 2014 21:35:59 +0000 (18:35 -0300)]
[media] af9035: remove I2C client differently
It crash kernel when device was removed while it was streaming.
That is because we removed driver and frontend thread was still
running. Use new callback which allows I2C driver removal just
after frontend is unregistered.
V2: fixed by reported by Daniel
Reported-by: Daniel Glöckner <daniel-gl@gmx.net> Signed-off-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Antti Palosaari [Thu, 4 Sep 2014 21:31:40 +0000 (18:31 -0300)]
[media] dvb-usb-v2: add tuner_detach callback
Add tuner_detach callback in order to allow custom detach. It is
needed when tuner driver is implemented I2C client or some other
kernel bus, but not proprietary dvb_attach / dvb_detach.
Signed-off-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Antti Palosaari [Thu, 4 Sep 2014 20:04:44 +0000 (17:04 -0300)]
[media] dvb-usb-v2: add frontend_detach callback
Add frontend_detach callback in order to allow custom detach. It is
needed when demod driver is implemented I2C client or some other
kernel bus, but not proprietary dvb_attach / dvb_detach.
Signed-off-by: Antti Palosaari <crope@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
projects / karo-tx-linux.git / log