Marko Ristola [Sat, 7 Aug 2010 11:16:15 +0000 (08:16 -0300)]
[media] Refactor Mantis DMA transfer to deliver 16Kb TS data per interrupt
With VDR streaming HDTV into network, generating an interrupt once per 16kb,
implemented in this patch, seems to support more robust throughput with HDTV.
Fix leaking almost 64kb data from the previous TS after changing the TS.
One effect of the old version was, that the DMA transfer and driver's
DMA buffer access might happen at the same time - a race condition.
Signed-off-by: Marko M. Ristola <marko.ristola@kolumbus.fi> Reviewed-by: Manu Abraham <manu@linuxtv.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Chris Rankin [Sat, 24 Sep 2011 14:02:32 +0000 (11:02 -0300)]
[media] em28xx: fix race on disconnect
This patch closes the race on the device and extension lists at USB disconnect
time. Previously, the device was removed from the device list during
em28xx_release_resources(), and then passed to the em28xx_close_extension()
function so that all extensions could run their fini() operations. However, this
left a (brief, theoretical, highly unlikely ;-)) window between these two calls
during which a new module could call em28xx_register_extension(). The result
would have been that the em28xx_usb_disconnect() function would also have passed
the device to the new extension's fini() function, despite never having called
the extension's init() function.
This patch also restores em28xx_close_extension()'s symmetry with
em28xx_init_extension(), and establishes the property that every device in the
device list must have been initialised for every extension in the extension list.
Signed-off-by: Chris Rankin <rankincj@yahoo.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Andy Walls [Sun, 19 Dec 2010 22:10:28 +0000 (19:10 -0300)]
[media] cx23885, cx25840: Provide IR Rx timeout event reports
(Resending because Mauro reported losing some emails on IRC)
Provide CX2388[578] IR receive timeout (RTO) reports in the
final space raw event sent up the chain to the raw IR pulse
decoders. This should allow the lirc decoder to actually
measure the inter-transmission gap properly.
Signed-off-by: Andy Walls <awalls@md.metrocast.net> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
[media] v4l2: Add polarity flag definitions for the parallel bus FIELD signal
FIELD signal is used for indicating frame field type to the frame grabber
in interlaced scan mode, as specified in ITU-R BT.601 standard.
In normal operation mode FIELD = 0 selects Field1 (odd) and FIELD = 1
selects Field2 (even). When the FIELD signal is inverted it's the other
way around.
Add corresponding flags for configuring the FIELD signal polarity,
V4L2_MBUS_FIELD_EVEN_HIGH for the standard (non-inverted) case and
V4L2_MBUS_FIELD_EVEN_LOW for inverted case.
Also add a comment about usage of V4L2_MBUS_[HV]SYNC* flags for
the hardware that uses [HV]REF signals.
Pekka Enberg [Fri, 23 Sep 2011 13:19:07 +0000 (10:19 -0300)]
[media] media, rc: Use static inline functions to kill warnings
This patch converts some ifdef'd wrapper functions from macros to static inline
functions to kill the following warnings issued by GCC:
CC [M] drivers/media/rc/ir-raw.o
drivers/media/rc/ir-raw.c: In function ‘init_decoders’:
drivers/media/rc/ir-raw.c:353:2: warning: statement with no effect [-Wunused-value]
drivers/media/rc/ir-raw.c:354:2: warning: statement with no effect [-Wunused-value]
drivers/media/rc/ir-raw.c:355:2: warning: statement with no effect [-Wunused-value]
drivers/media/rc/ir-raw.c:356:2: warning: statement with no effect [-Wunused-value]
drivers/media/rc/ir-raw.c:357:2: warning: statement with no effect [-Wunused-value]
drivers/media/rc/ir-raw.c:359:2: warning: statement with no effect [-Wunused-value]
[media] gspca - main: Handle the xHCI error on usb_set_interface()
This patch is adapted from a patch from Sarah Sharp (2010/05/03).
The xHCD handler checks the USB bandwidth on usb_set_interface()
instead of on usb_submit_urb().
Now, the same treatment is applied in case of error of both functions.
[media] gspca - main: Use a better altsetting for image transfer
Previously image transfer used to use the highest altsetting, which, most of
the time, took the whole USB bandwidth.
Now, the altsetting is chosen according to an estimation of the bandwidth
needed for image transfer.
This is an improved version of the patch I sent a little ago.
The problem was:
On my DC-1125 webcam chip from Syntek, whenever the webcam turns
on, the LED light on it is turned on also and never turns off again unless
system is shut downed or restarted.
The previous version seemed to break some other laptop webcam work. Thanks
to Andrea Anacleto for the bug report and solution.
Signed-off-by: Andrea Anacleto <andreaanacleto@libero.it> Signed-off-by: Arvydas Sidorenko <asido4@gmail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
[media] v4l subdev: add dispatching for VIDIOC_DBG_G_REGISTER and VIDIOC_DBG_S_REGISTER
Ioctls on the subdevs node currently don't dispatch the register access debug
driver callbacks. Add the dispatching with the same security checks are for
non subdev video nodes (i.e. only capable(CAP_SYS_ADMIN may call the register
access ioctls).
Al Cooper [Thu, 18 Aug 2011 13:28:29 +0000 (10:28 -0300)]
[media] media: Fix a UVC performance problem on systems with non-coherent DMA
The UVC driver uses usb_alloc_coherent() to allocate DMA data buffers.
On systems without coherent DMA this ends up allocating buffers in
uncached memory. The subsequent memcpy's done to coalesce the DMA
chunks into contiguous buffers then run VERY slowly. On a MIPS test
system the memcpy is about 200 times slower. This issue prevents the
system from keeping up with 720p YUYV data at 10fps.
The following patch uses kmalloc to alloc the DMA buffers instead of
usb_alloc_coherent on systems without coherent DMA. With this patch
the system was easily able to keep up with 720p at 10fps.
Signed-off-by: Al Cooper <alcooperx@gmail.com> Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
The UVCIOC_CTRL_ADD, UVCIOC_CTRL_MAP_OLD, UVCIOC_CTRL_GET and
UVCIOC_CTRL_SET ioctls are deprecated and were scheduled for removal for
v2.6.42. As v2.6.42 == v3.2, remove them.
drivers/media/rc/keymaps/rc-snapstream-firefly.c:105:16: error: expected declaration specifiers or ‘...’ before string constant
drivers/media/rc/keymaps/rc-snapstream-firefly.c:106:15: error: expected declaration specifiers or ‘...’ before string constant
[media] altera-stapl: it is time to move out from staging
[mchehab@redhat.com: Fix a merge conflict] Signed-off-by: Igor M. Liplianin <liplianin@netup.ru> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Anssi Hannula [Sat, 6 Aug 2011 21:18:12 +0000 (18:18 -0300)]
[media] ati_remote: add support for SnapStream Firefly remote
The protocol differs by having two toggle bits in the scancode. Since
one of the bits is otherwise unused, we can safely handle the bits
unconditionally.
[mchehab@redhat.com: Fix some bad whitespacing] Signed-off-by: Anssi Hannula <anssi.hannula@iki.fi> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Anssi Hannula [Sat, 6 Aug 2011 21:18:10 +0000 (18:18 -0300)]
[media] ati_remote: fix check for a weird byte
The ati_remote_dump() function tries to not print "Weird byte" warning
for 1-byte responses that contain 0xff or 0x00, but it doesn't work
properly as it simply falls back to the "Weird data" warning in the else
clause.
Mats Randgaard [Tue, 3 Aug 2010 07:18:04 +0000 (04:18 -0300)]
[media] TVP7002: Changed register values
Register values changed according to the data sheet and Texas Instruments DaVinci_PSP_03_02_00_37.
- TVP7002_RGB_COARSE_CLAMP_CTL changed to the default value in data sheet.
- TVP7002_HPLL_PHASE_SEL deleted because the registers write to reserved bits. The default value works fine.
[media] [1/2,ver,1.89] DM04/QQBOX Interupt Urb and Timing changes
Reduce buffer size of Interupt urb to 128 bytes and polling
interval to 8.
The devices buffer appears to only handle a maxium of 40 bytes.
If the buffer is full a slowing effect is noticed causing occasionnal
dropped streaming packets.
Chris Rankin [Sun, 4 Sep 2011 18:26:21 +0000 (15:26 -0300)]
[media] em28xx: Fix em28xx_devused cleanup logic on error
On 04/09/11 00:49, Mauro Carvalho Chehab wrote:
> This is an automatic generated email to let you know that the following patch were queued at the
> http://git.linuxtv.org/media_tree.git tree:
>
> Subject: [media] em28xx: use atomic bit operations for devices-in-use mask
> Author: Chris Rankin<rankincj@yahoo.com>
> Date: Sat Aug 20 08:21:03 2011 -0300
>
> Use atomic bit operations for the em28xx_devused mask, to prevent an
> unlikely race condition should two adapters be plugged in
> simultaneously. The operations also clearer than explicit bit
> manipulation anyway.
>
> Signed-off-by: Chris Rankin<rankincj@yahoo.com>
> Signed-off-by: Mauro Carvalho Chehab<mchehab@redhat.com>
>
> drivers/media/video/em28xx/em28xx-cards.c | 33 ++++++++++++++---------------
Some devices support fast access to registers using the USB interface
while others require a certain delay after each operation. This commit
adds a quirk that can be enabled by devices that don't need the delay.
Laurent Pinchart [Sat, 13 Aug 2011 16:13:32 +0000 (13:13 -0300)]
[media] omap3isp: video: Avoid crashes when pipeline set stream operation fails
If streaming can't be enabled on the pipeline, the DMA buffers queue is
not emptied. If the buffers then get freed the queue will end up
referencing free memory. This is usually not an issue, as the DMA queue
will be reinitialized the next time streaming is enabled, before
enabling the hardware.
However, if the sensor connected at the pipeline input is free-running,
the CCDC will start generating interrupts as soon as it gets powered up,
before the streaming gets enabled on the hardware. This will make the
CCDC interrupt handler access freed memory, causing a crash.
Reinitialize the DMA buffers queue in isp_video_streamon() if the error
path to make sure this situation won't happen.
Laurent Pinchart [Sat, 13 Aug 2011 16:09:11 +0000 (13:09 -0300)]
[media] omap3isp: Don't fail streamon when the sensor doesn't implement s_stream
The code handles subdevs with no s_stream operation correctly, but
returns -ENOIOCTLCMD by mistake if the first subdev in the chain has no
s_stream operation. Return 0 in that case.
Jarod Wilson [Tue, 19 Jul 2011 15:12:47 +0000 (12:12 -0300)]
[media] imon: don't parse scancodes until intf configured
The imon devices have either 1 or 2 usb interfaces on them, each wired
up to its own urb callback. The interface 0 urb callback is wired up
before the imon context's rc_dev pointer is filled in, which is
necessary for imon 0xffdc device auto-detection to work properly, but we
need to make sure we don't actually run the callback routines until
we've entirely filled in the necessary bits for each given interface,
lest we wind up oopsing. Technically, any imon device could have hit
this, but the issue is exacerbated on the 0xffdc devices, which send a
constant stream of interrupts, even when they have no valid key data.
CC: Andy Walls <awalls@md.metrocast.net> CC: Chris W <lkml@psychogeeks.com> Reported-by: Chris W <lkml@psychogeeks.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
[media] STV0288 frontend provide wider carrier search and DVB-S2 drop out. resend
The following patch provides wider carrier search.
As with existing code search starts at MSB aligned. The boundary
is widened to start at -9. In order to save time, if no carrier is
detected at the start it advances to the next alignment until carrier
is found.
The stv0288 will detect a DVB-S2 carrier on all steps , a
time out of 11 steps is introduced to drop out of the loop.
In stv0288_set_symbol carrier and timing loops are restored to
default values (inittab) before setting the symbol rate on each tune. A
slight drift was noticed with full scan in the higher IF frequencies of
each band.
Remove the now unneeded check for the platform data in s_power
handler and the platform data pointer in struct noon010_info.
Also do not reset the configured output resolution and pixel
format when cycling sensor's power.
Add small delay for proper reset signal shape.
[media] noon010pc30: Conversion to the media controller API
Replace g/s_mbus_fmt ops with the pad level get/set_fmt operations.
Add media entity initialization and set subdev flags so the host driver
creates a subdev device node for the driver.
A mutex was added for serializing the subdev operations. When setting
format is attempted during streaming an (EBUSY) error will be returned.
After the device is powered up it will now remain in "power sleep"
mode until s_stream(1) is called. The "power sleep" mode is used
to suspend/resume frame generation at the sensor's output through
s_stream op.
Hans Verkuil [Fri, 26 Aug 2011 11:46:29 +0000 (08:46 -0300)]
[media] saa7115: use the new auto cluster support
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Hans Verkuil [Fri, 26 Aug 2011 11:46:13 +0000 (08:46 -0300)]
[media] pwc: add support for VIDIOC_LOG_STATUS
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Hans Verkuil [Fri, 26 Aug 2011 11:45:38 +0000 (08:45 -0300)]
[media] vivi: add support for VIDIOC_LOG_STATUS
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Hans Verkuil [Fri, 26 Aug 2011 11:40:43 +0000 (08:40 -0300)]
[media] pwc: switch to the new auto-cluster volatile handling
Now that the auto cluster core changed to a different scheme of how to
handle volatile controls (including how to switch from auto to manual mode)
the pwc code can be simplified to use that new core support.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Hans Verkuil [Fri, 26 Aug 2011 11:35:59 +0000 (08:35 -0300)]
[media] v4l2-controls.txt: update auto cluster documentation
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Hans Verkuil [Fri, 26 Aug 2011 10:53:53 +0000 (07:53 -0300)]
[media] v4l2-ctrls: implement new volatile autocluster scheme
The problem tackled in this patch is how to handle volatile autoclusters
correctly. A volatile autocluster is a cluster of related controls where one
control is the control that toggles between manual and auto mode and the other
controls are the values for the manual mode. For example autogain and gain,
autoexposure and exposure, etc.
If the hardware lets you read out the automatically calculated manual values
while in automode, then those manual controls should be marked volatile.
gain value as calculated by the autogain circuitry, then you would mark the
gain control as volatile (i.e. continuously changing).
The question in such use cases is what to do when switching from the auto
mode to the manual mode. Should we switch to the last set manual values or
should the volatile values be copied and used as the initial manual values.
For example: suppose the mode is manual gain and gain is set to 5. Then
autogain is turned on and the gain is set by the hardware to 2. Finally
the user switches back to manual gain. What should the gain be? 2 or 5?
After a long discussion the decisions was made to keep the last value as
calculated by the auto mode (so 2 in the example above).
The reason is that webcams that do such things will adapt themselves to
the current light conditions and when you switch back to manual mode you
expect that you keep the same picture. If you would switch back to old
manual values, then that would give you a suddenly different picture,
which is jarring for the user.
Additionally, this would be difficult to implement in applications that
store and restore the control values at application exit and start.
If you want to keep the old manual values when you switch from auto to
manual, then there would have to be a way for applications to get hold
of those old values while in auto mode, but there isn't.
So this patch will do all the heavy lifting in v4l2-ctrls.c: if you go
from auto mode to manual mode and the manual controls are volatile, then
g_volatile_ctrl will be called to get the current values for the manual
controls before switching to manual mode.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
projects / mv-sheeva.git / log