linux-stable.git/drivers/media, branch v5.4.26

media: v4l2-mem2mem.c: fix broken links

2020-03-12T12:00:21+00:00

commit 316e730f1d8bb029fe6cec2468fb2a50424485b3 upstream.

The topology that v4l2_m2m_register_media_controller() creates for a
processing block actually created a source-to-source link and a sink-to-sink
link instead of two source-to-sink links.

Unfortunately v4l2-compliance never checked for such bad links, so this
went unreported for quite some time.

Signed-off-by: Hans Verkuil 
Reported-by: Nicolas Dufresne 
Cc:       # for v4.19 and up
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Greg Kroah-Hartman

media: vicodec: process all 4 components for RGB32 formats

2020-03-12T12:00:21+00:00

commit 49a56266f96f2c6608373464af8755b431ef1513 upstream.

Only ARGB32-type pixelformat were assumed to have 4 components, which is
wrong since RGB32-type pixelformats may have an alpha channel, so they
should also assume 4 color components.

The XRGB32-type pixelformats really have only 3 color components, but this
complicated matters since that creates strides that are sometimes width * 3
and sometimes width * 4, and in fact this can result in buffer overflows.

Keep things simple by just always processing all 4 color components.

In the future we might want to optimize this again for the XRGB32-type
pixelformats, but for now keep it simple and robust.

Signed-off-by: Hans Verkuil 
Cc:       # for v5.4 and up
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Greg Kroah-Hartman

media: mc-entity.c: use & to check pad flags, not ==

2020-03-12T12:00:21+00:00

commit 044041cd5227ec9ccf969f4bf1cc08bffe13b9d3 upstream.

These are bits so to test if a pad is a sink you use & but not ==.

It looks like the only reason this hasn't caused problems before is that
media_get_pad_index() is currently only used with pads that do not set the
MEDIA_PAD_FL_MUST_CONNECT flag. So a pad really had only the SINK or SOURCE
flag set and nothing else.

Signed-off-by: Hans Verkuil 
Cc:       # for v5.3 and up
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Greg Kroah-Hartman

media: uvcvideo: Add a quirk to force GEO GC6500 Camera bits-per-pixel value

2020-02-24T07:36:56+00:00

[ Upstream commit 1dd2e8f942574e2be18374ebb81751082d8d467c ]

This device does not function correctly in raw mode in kernel
versions validating buffer sizes in bulk mode. It erroneously
announces 16 bits per pixel instead of 12 for NV12 format, so it
needs this quirk to fix computed frame size and avoid legitimate
frames getting discarded.

[Move info and div variables to local scope]

Signed-off-by: Sergey Zakharchenko 
Signed-off-by: Laurent Pinchart 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin

media: cx23885: Add support for AVerMedia CE310B

2020-02-24T07:36:35+00:00

[ Upstream commit dc4cac67e13515835ed8081d510aa507aacb013b ]

The AVerMedia CE310B is a simple composite + S-Video + stereo audio
capture card, and uses only the CX23888 to perform all of these
functions.

I've tested both video inputs and the audio interface and confirmed that
they're all working. However, there are some issues:

* Sometimes when I switch inputs the video signal turns black and can't
  be recovered until the system is rebooted. I haven't been able to
  determine the cause of this behavior, nor have I found a solution to
  fix it or any workarounds other than rebooting.
* The card sometimes seems to have trouble syncing to the video signal,
  and some of the VBI data appears as noise at the top of the frame, but
  I assume that to be a result of my very noisy RF environment and the
  card's unshielded input traces rather than a configuration issue.

Signed-off-by: Forest Crossman 
Signed-off-by: Hans Verkuil 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin

media: sti: bdisp: fix a possible sleep-in-atomic-context bug in bdisp_device_run()

2020-02-24T07:36:26+00:00

[ Upstream commit bb6d42061a05d71dd73f620582d9e09c8fbf7f5b ]

The driver may sleep while holding a spinlock.
The function call path (from bottom to top) in Linux 4.19 is:

drivers/media/platform/sti/bdisp/bdisp-hw.c, 385:
    msleep in bdisp_hw_reset
drivers/media/platform/sti/bdisp/bdisp-v4l2.c, 341:
    bdisp_hw_reset in bdisp_device_run
drivers/media/platform/sti/bdisp/bdisp-v4l2.c, 317:
    _raw_spin_lock_irqsave in bdisp_device_run

To fix this bug, msleep() is replaced with udelay().

This bug is found by a static analysis tool STCheck written by myself.

Signed-off-by: Jia-Ju Bai 
Reviewed-by: Fabien Dessenne 
Signed-off-by: Hans Verkuil 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin

media: sun4i-csi: Fix [HV]sync polarity handling

2020-02-24T07:36:25+00:00

[ Upstream commit 1948dcf0f928b8bcdca57ca3fba8545ba380fc29 ]

The Allwinner camera sensor interface has a different definition of
[HV]sync. While the timing diagram uses the names HSYNC and VSYNC,
the note following the diagram and register names use HREF and VREF.
Combined they imply the hardware uses either [HV]REF or inverted
[HV]SYNC. There are also registers to set horizontal skip lengths
in pixels and vertical skip lengths in lines, also known as back
porches.

Fix the polarity handling by using the opposite polarity flag for
the checks. Also rename `[hv]sync_pol` to `[hv]ref_pol` to better
match the hardware register description.

Fixes: 577bbf23b758 ("media: sunxi: Add A10 CSI driver")
Signed-off-by: Chen-Yu Tsai 
Acked-by: Maxime Ripard 
Signed-off-by: Sakari Ailus 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin

media: sun4i-csi: Fix data sampling polarity handling

2020-02-24T07:36:25+00:00

[ Upstream commit cf9e6d5dbdd56ef2aa72f28c806711c4293c8848 ]

The CLK_POL field specifies whether data is sampled on the falling or
rising edge of PCLK, not whether the data lines are active high or low.
Evidence of this can be found in the timing diagram labeled "horizontal
size setting and pixel clock timing".

Fix the setting by checking the correct flag, V4L2_MBUS_PCLK_SAMPLE_RISING.
While at it, reorder the three polarity flag checks so HSYNC and VSYNC
are grouped together.

Fixes: 577bbf23b758 ("media: sunxi: Add A10 CSI driver")
Signed-off-by: Chen-Yu Tsai 
Acked-by: Maxime Ripard 
Signed-off-by: Sakari Ailus 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin

media: sun4i-csi: Deal with DRAM offset

2020-02-24T07:36:25+00:00

[ Upstream commit 249b286171fa9c358e8d5c825b48c4ebea97c498 ]

On Allwinner SoCs, some high memory bandwidth devices do DMA directly
over the memory bus (called MBUS), instead of the system bus. These
devices include the CSI camera sensor interface, video (codec) engine,
display subsystem, etc.. The memory bus has a different addressing
scheme without the DRAM starting offset.

Deal with this using the "interconnects" property from the device tree,
or if that is not available, set dev->dma_pfn_offset to PHYS_PFN_OFFSET.

Fixes: 577bbf23b758 ("media: sunxi: Add A10 CSI driver")
Signed-off-by: Chen-Yu Tsai 
Acked-by: Maxime Ripard 
Signed-off-by: Sakari Ailus 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin

media: i2c: mt9v032: fix enum mbus codes and frame sizes

2020-02-24T07:36:25+00:00

[ Upstream commit 1451d5ae351d938a0ab1677498c893f17b9ee21d ]

This driver supports both the mt9v032 (color) and the mt9v022 (mono)
sensors. Depending on which sensor is used, the format from the sensor is
different. The format.code inside the dev struct holds this information.
The enum mbus and enum frame sizes need to take into account both type of
sensors, not just the color one. To solve this, use the format.code in
these functions instead of the hardcoded bayer color format (which is only
used for mt9v032).

[Sakari Ailus: rewrapped commit message]

Suggested-by: Wenyou Yang 
Signed-off-by: Eugen Hristev 
Reviewed-by: Laurent Pinchart 
Signed-off-by: Sakari Ailus 
Signed-off-by: Mauro Carvalho Chehab 
Signed-off-by: Sasha Levin