aboutsummaryrefslogtreecommitdiffstats
path: root/drivers (follow)
AgeCommit message (Collapse)AuthorFilesLines
2020-01-04media: sun4i-csi: Add support for A10 CSI1 camera sensor interfaceChen-Yu Tsai2-5/+32
The A10/A20 Allwinner SoCs have two camera sensor interface blocks, named CSI0 and CSI1. The two have the same register layouts with slightly different features: - CSI0 has an image signal processor (ISP); CSI1 doesn't - CSI0 can support up to four separate channels under CCIR656; CSI1 can only support one - CSI0 can support up to 16-bit wide bus with YUV422; CSI1 can support up to 24-bit wide bus with YUV444 For now the driver doesn't support wide busses, nor CCIR656. So the only relevant difference is whether a clock needs to be taken and enabled for the ISP. Add structs to record the differences, tie them to the compatible strings, and deal with the ISP clock. Support for the new CSI1 hardware block is added as well. Signed-off-by: Chen-Yu Tsai <wens@csie.org> Acked-by: Maxime Ripard <mripard@kernel.org> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: sun4i-csi: Deal with DRAM offsetChen-Yu Tsai1-0/+22
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 <wens@csie.org> Acked-by: Maxime Ripard <mripard@kernel.org> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: sun4i-csi: Fix [HV]sync polarity handlingChen-Yu Tsai2-7/+15
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 <wens@csie.org> Acked-by: Maxime Ripard <mripard@kernel.org> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: sun4i-csi: Fix data sampling polarity handlingChen-Yu Tsai1-1/+1
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 <wens@csie.org> Acked-by: Maxime Ripard <mripard@kernel.org> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: staging/intel-ipu3: make imgu use fixed running modeBingbu Cao3-74/+9
Currently, the imgu running mode need user to set by v4l2 ctrl. However, imgu only support 2 pipes and 2 operation modes - video and still. This patch make the first imgu subdev running as video and second one running as still, it will make the user understand easily, it can also cover current camera use cases requirement. The running mode is set during subdev registering, no race-condition after change, so it is safe to change the mode data type to integer. Signed-off-by: Bingbu Cao <bingbu.cao@intel.com> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: staging/intel-ipu3: set the main output as mandatoryBingbu Cao2-3/+5
From firmware perspective, the main output for each pipe is mandatory and must be enabled. This patch set the link between imgu subdev and main output as IMMUTABLE by default. Signed-off-by: Bingbu Cao <bingbu.cao@intel.com> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: i2c: mt9v032: fix enum mbus codes and frame sizesEugen Hristev1-2/+8
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 <wenyou.yang@microchip.com> Signed-off-by: Eugen Hristev <eugen.hristev@microchip.com> Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: staging: ipu3: replace 0 with falseJules Irenge1-1/+1
Replace 0 with false to clear warning of assignment of 0/1 to bool variable. Issue detected by coccinelle tool. Signed-off-by: Jules Irenge <jbi.octave@gmail.com> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: ov5640: Fix check for PLL1 exceeding max allowed rateAdam Ford1-1/+1
The variable _rate is by ov5640_compute_sys_clk() which returns zero if the PLL exceeds 1GHz. Unfortunately, the check to see if the max PLL1 output is checking 'rate' and not '_rate' and 'rate' does not ever appear to be 0. This patch changes the check against the returned value of '_rate' to determine if the PLL1 output exceeds 1GHz. Fixes: aa2882481cad ("media: ov5640: Adjust the clock based on the expected rate") Signed-off-by: Adam Ford <aford173@gmail.com> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-04media: ov5640: Put max framerate into table and simplify checkAdam Ford1-17/+22
Currently the various modes are placed into a table, but when ov5640_find_mode is called, it has to double check whether or not the requested framerate is tolerated by the mode. The determination is based on checking hact, vact, and frame rate. Only 640x480 is allowed at 60fps and QSXGA is limited to 15fps, but as the number of permitted frame rates change, this will begin to add more and more complexity to the check. This patch simplifies the check by adding the max framerate allowed for each mode into the table of modes. It then compares the requested framerate to the max permitted in the mode's table. This reduces the number of comparisions to one down from three at run-time. Signed-off-by: Adam Ford <aford173@gmail.com> Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: smiapp: Put the device again if starting streaming failsSakari Ailus1-1/+4
If there was an error in starting streaming, put the runtime usage count of the device. Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: smiapp: Avoid maintaining power state informationSakari Ailus3-90/+113
Instead of keeping track of the power state ourselves, let runtime PM handle it. This also splits handling controls between side effect management and writing the new configuration to the sensor's registers. Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: omap3isp: Don't restart CCDC if we're about to stopSakari Ailus1-4/+8
The omap3isp driver set the new buffer and enabled the CCDC in a situation a new buffer was available but streaming was about to be stopped on the CCDC. This lead to frequent system crashes in case there were buffers queued when streming was being stopped. Fix this by first checking whether there's an intent to stop streaming and if there isn't, then set the new buffer and re-enable CCDC. Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: omap3isp: Ignore failure of stopping streaming on external subdevSakari Ailus1-4/+4
The isp was marked to have failed to stop if stopping streaming on an external subdev failed. The return value from the external subdev should be ignored instead as it is not part of the ISP and thus the ISP does not need to be reset for that reason. Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: dvb: add support for TerraTec TC2 Stick (193534)Tomasz Maciej Nowak1-5/+10
Seems to be a clone of Logilink VG0022A. Supports DVB-C, DVB-T and DVB-T2. Only terrestrial reception was tested on Polish and Czech multiplexes. Signed-off-by: Tomasz Maciej Nowak <tmn505@gmail.com> Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: serial_ir: change "ignoring spike" to debug levelBodo Eggert1-1/+1
At least on my system with a self-made IR receiver, my kernel log is filled with: serial_ir serial_ir.0: ignoring spike: 1 1 1419988034627194ns 1419956080709377ns These messages happen at random and do not prevent the receiver from working. Also I cannot change the features of the IC, therefore they are not useful. Probably they are not useful at all. However they fill the console, they accumulate and fill the dmesg log, by doing this, they prevent me from seeing important message. Signed-off-by: Bodo Eggert <7eggert@gmx.de> Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: rtl28xxu: Add support for PROlectrix DV107669 DVB-T dongleDavid J. Fiddes1-0/+2
This adds support for the PROlectrix DV107669 DVT-T dongle which uses an RTL2832 and FC0012 tuner. Tests: - Verified correct operation of DVB-T reception with VLC across several UK multiplexes Signed-off-by: David J. Fiddes <D.J@fiddes.net> Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: dvb_dummy_fe: Add blank line after declarationDaniel W. S. Almeida1-1/+2
Fix checkpatch.pl error by adding a blank line Signed-off-by: Daniel W. S. Almeida <dwlsalmeida@gmail.com> Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: dvb_dummy_fe: place EXPORT_SYMBOL below corresponding functionDaniel W. S. Almeida1-4/+3
dvb_dummy_fe.c had all its EXPORT_SYMBOL macros located at the end of the file. Now these are located directly below the symbol they are exporting for increased readability. Suggested-by: Shuah Khan <skhan@linuxfoundation.org> Signed-off-by: Daniel W. S. Almeida <dwlsalmeida@gmail.com> Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: rc: ensure lirc is initialized before registering input deviceSean Young1-11/+16
Once rc_open is called on the input device, lirc events can be delivered. Ensure lirc is ready to do so else we might get this: Registered IR keymap rc-hauppauge rc rc0: Hauppauge WinTV PVR-350 as /devices/pci0000:00/0000:00:1e.0/0000:04:00.0/i2c-0/0-0018/rc/rc0 input: Hauppauge WinTV PVR-350 as /devices/pci0000:00/0000:00:1e.0/0000:04:00.0/i2c-0/0-0018/rc/rc0/input9 BUG: kernel NULL pointer dereference, address: 0000000000000038 PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 1 PID: 17 Comm: kworker/1:0 Not tainted 5.3.11-300.fc31.x86_64 #1 Hardware name: /DG43NB, BIOS NBG4310H.86A.0096.2009.0903.1845 09/03/2009 Workqueue: events ir_work [ir_kbd_i2c] RIP: 0010:ir_lirc_scancode_event+0x3d/0xb0 Code: a6 b4 07 00 00 49 81 c6 b8 07 00 00 55 53 e8 ba a7 9d ff 4c 89 e7 49 89 45 00 e8 5e 7a 25 00 49 8b 1e 48 89 c5 4c 39 f3 74 58 <8b> 43 38 8b 53 40 89 c1 2b 4b 3c 39 ca 72 41 21 d0 49 8b 7d 00 49 RSP: 0018:ffffaae2000b3d88 EFLAGS: 00010017 RAX: 0000000000000002 RBX: 0000000000000000 RCX: 0000000000000019 RDX: 0000000000000001 RSI: 006e801b1f26ce6a RDI: ffff9e39797c37b4 RBP: 0000000000000002 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: ffff9e39797c37b4 R13: ffffaae2000b3db8 R14: ffff9e39797c37b8 R15: ffff9e39797c33d8 FS: 0000000000000000(0000) GS:ffff9e397b680000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 0000000035844000 CR4: 00000000000006e0 Call Trace: ir_do_keydown+0x8e/0x2b0 rc_keydown+0x52/0xc0 ir_work+0xb8/0x130 [ir_kbd_i2c] process_one_work+0x19d/0x340 worker_thread+0x50/0x3b0 kthread+0xfb/0x130 ? process_one_work+0x340/0x340 ? kthread_park+0x80/0x80 ret_from_fork+0x35/0x40 Modules linked in: rc_hauppauge tuner msp3400 saa7127 saa7115 ivtv(+) tveeprom cx2341x v4l2_common videodev mc i2c_algo_bit ir_kbd_i2c ip_tables firewire_ohci e1000e serio_raw firewire_core ata_generic crc_itu_t pata_acpi pata_jmicron fuse CR2: 0000000000000038 ---[ end trace c67c2697a99fa74b ]--- RIP: 0010:ir_lirc_scancode_event+0x3d/0xb0 Code: a6 b4 07 00 00 49 81 c6 b8 07 00 00 55 53 e8 ba a7 9d ff 4c 89 e7 49 89 45 00 e8 5e 7a 25 00 49 8b 1e 48 89 c5 4c 39 f3 74 58 <8b> 43 38 8b 53 40 89 c1 2b 4b 3c 39 ca 72 41 21 d0 49 8b 7d 00 49 RSP: 0018:ffffaae2000b3d88 EFLAGS: 00010017 RAX: 0000000000000002 RBX: 0000000000000000 RCX: 0000000000000019 RDX: 0000000000000001 RSI: 006e801b1f26ce6a RDI: ffff9e39797c37b4 RBP: 0000000000000002 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: ffff9e39797c37b4 R13: ffffaae2000b3db8 R14: ffff9e39797c37b8 R15: ffff9e39797c33d8 FS: 0000000000000000(0000) GS:ffff9e397b680000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 0000000035844000 CR4: 00000000000006e0 rc rc0: lirc_dev: driver ir_kbd_i2c registered at minor = 0, scancode receiver, no transmitter tuner-simple 0-0061: creating new instance tuner-simple 0-0061: type set to 2 (Philips NTSC (FI1236,FM1236 and compatibles)) ivtv0: Registered device video0 for encoder MPG (4096 kB) ivtv0: Registered device video32 for encoder YUV (2048 kB) ivtv0: Registered device vbi0 for encoder VBI (1024 kB) ivtv0: Registered device video24 for encoder PCM (320 kB) ivtv0: Registered device radio0 for encoder radio ivtv0: Registered device video16 for decoder MPG (1024 kB) ivtv0: Registered device vbi8 for decoder VBI (64 kB) ivtv0: Registered device vbi16 for decoder VOUT ivtv0: Registered device video48 for decoder YUV (1024 kB) Cc: stable@vger.kernel.org Tested-by: Nick French <nickfrench@gmail.com> Reported-by: Nick French <nickfrench@gmail.com> Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: cxusb: use dev_dbg() rather than hand-rolled debugSean Young1-18/+15
This solves the following compiler warnings: drivers/media/usb/dvb-usb/cxusb.c: In function ‘cxusb_gpio_tuner’: drivers/media/usb/dvb-usb/cxusb.c:128:35: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] 128 | deb_info("gpio_write failed.\n"); | ^ drivers/media/usb/dvb-usb/cxusb.c: In function ‘cxusb_bluebird_gpio_rw’: drivers/media/usb/dvb-usb/cxusb.c:145:44: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] 145 | deb_info("bluebird_gpio_write failed.\n"); | ^ drivers/media/usb/dvb-usb/cxusb.c: In function ‘cxusb_i2c_xfer’: drivers/media/usb/dvb-usb/cxusb.c:251:42: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] 251 | deb_i2c("i2c read may have failed\n"); | ^ drivers/media/usb/dvb-usb/cxusb.c:274:43: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] 274 | deb_i2c("i2c write may have failed\n"); | ^ Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: vp7045: do not read uninitialized values if usb transfer failsSean Young1-7/+14
It is not a fatal error if reading the mac address or the remote control decoder state fails. Reported-by: syzbot+ec869945d3dde5f33b43@syzkaller.appspotmail.com Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: af9005: uninitialized variable printkedSean Young1-1/+1
If usb_bulk_msg() fails, actual_length can be uninitialized. Reported-by: syzbot+9d42b7773d2fecd983ab@syzkaller.appspotmail.com Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: digitv: don't continue if remote control state can't be readSean Young1-3/+7
This results in an uninitialized variable read. Reported-by: syzbot+6bf9606ee955b646c0e1@syzkaller.appspotmail.com Signed-off-by: Sean Young <sean@mess.org> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2-core: fix compat v4l2_buffer handling for time64 ABIArnd Bergmann1-1/+267
Add support for the four new variants of ioctl commands for 64-bit time_t in v4l2_buffer. The existing v4l2_buffer32 structure for the traditional format gets changed to match the new v4l2_buffer format, and the old layout is now called v4l2_buffer32_time32. Neither of these matches the native 64-bit architecture format of v4l2_buffer, so both require special handling in compat code. Duplicating the existing handlers for the new types is a safe conversion for now, but unfortunately this may turn into a maintenance burden later. A larger-scale rework of the compat code might be a better alternative, but is out of scope of the y2038 work. Note: x32 support for v4l2_buffer32 has always been broken and remains so after this change, fixing it would have required even more duplication, and apparently nobody has cared so far. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> [hverkuil-cisco@xs4all.nl: remove spurious newline] Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2-core: fix compat VIDIOC_DQEVENT for time64 ABIArnd Bergmann1-1/+59
The native code supports the variant of struct v4l2_event for 64-bit time_t, so add the compat version as well. Here, a new incompatibility arises: while almost all 32-bit architectures now use the same layout as 64-bit architectures and the commands can simply be passed through, on x86 the internal alignment of v4l2_event is different because of the 64-bit member in v4l2_event_ctrl. To handle all architectures, this now requires defining four different versions of the structure to cover all possible combinations. The compat handling for VIDIOC_DQEVENT32 and VIDIOC_DQEVENT32_TIME32 is now inside of an #ifdef so it does not get used on architectures other than x86. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2-core: fix v4l2_buffer handling for time64 ABIArnd Bergmann1-4/+70
The v4l2_buffer structure contains a 'struct timeval' member that is defined by the user space C library, creating an ABI incompatibility when that gets updated to a 64-bit time_t. As in v4l2_event, handle this with a special case in video_put_user() and video_get_user() to replace the memcpy there. Since the structure also contains a pointer, there are now two native versions (on 32-bit systems) as well as two compat versions (on 64-bit systems), which unfortunately complicates the compat handler quite a bit. Duplicating the existing handlers for the new types is a safe conversion for now, but unfortunately this may turn into a maintenance burden later. A larger-scale rework of the compat code might be a better alternative, but is out of scope of the y2038 work. Sparc64 needs a special case because of their special suseconds_t definition. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2-core: fix VIDIOC_DQEVENT for time64 ABIArnd Bergmann3-3/+57
The v4l2_event structure contains a 'struct timespec' member that is defined by the user space C library, creating an ABI incompatibility when that gets updated to a 64-bit time_t. While passing a 32-bit time_t here would be sufficient for CLOCK_MONOTONIC timestamps, simply redefining the structure to use the kernel's __kernel_old_timespec would not work for any library that uses a copy of the linux/videodev2.h header file rather than including the copy from the latest kernel headers. This means the kernel has to be changed to handle both versions of the structure layout on a 32-bit architecture. The easiest way to do this is during the copy from/to user space. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2-core: split out data copy from video_usercopyArnd Bergmann1-39/+69
The copy-in/out portions of video_usercopy() are about to get more complex, so turn then into separate functions as a cleanup first. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2-core: compat: ignore native command codesArnd Bergmann1-73/+75
The do_video_ioctl() compat handler converts the compat command codes into the native ones before processing further, but this causes problems for 32-bit user applications that pass a command code that matches a 64-bit native number, which will then be handled the same way. Specifically, this breaks VIDIOC_DQEVENT_TIME from user space applications with 64-bit time_t, as the structure layout is the same as the native 64-bit layout on many architectures (x86 being the notable exception). Change the handler to use the converted command code only for passing into the native ioctl handler, not for deciding on the conversion, in order to make the compat behavior match the native behavior. Actual support for the 64-bit time_t version of VIDIOC_DQEVENT_TIME and other commands still needs to be added in a separate patch. Cc: stable@vger.kernel.org Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2020-01-03media: v4l2: abstract timeval handling in v4l2_bufferArnd Bergmann6-11/+12
As a preparation for adding 64-bit time_t support in the uapi, change the drivers to no longer care about the format of the timestamp field in struct v4l2_buffer. The v4l2_timeval_to_ns() function is no longer needed in the kernel after this, but there is userspace code relying on it to be part of the uapi header. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> [hverkuil-cisco@xs4all.nl: replace spaces by tabs] Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: vivid: support multiplanar touch devicesHans Verkuil4-8/+60
The v4l2-compliance tests failed with the touch device when multiplanar was enabled in vivid. Since it is perfectly fine to support the multiplanar API for touch, add support for this in vivid. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: v4l2-ioctl.c: allow multiplanar for touchHans Verkuil1-1/+1
There is no reason to prohibit multiplanar support for touch devices, so just allow it. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: vivid: set field to NONE for touchHans Verkuil1-0/+1
The v4l2_buffer's 'field' value was never initialized in vivid for the touch capture device, causing v4l2-compliance errors. Set it to NONE. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: log when a CEC message is receivedHans Verkuil1-0/+4
Log (if debug > 0) when a CEC message is received. This is done for transmits already, so it makes sense to do the same for receives. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: schedule next ping after current ping finishedHans Verkuil1-1/+1
Don't schedule the next ping before the current ping is sent, schedule it after. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: use adap_free callbackHans Verkuil1-7/+13
Don't free everything in the disconnect callback, instead use the adap_free callback, which is called when the last open filehandle is closed. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: queue received messages in an arrayHans Verkuil1-19/+61
It turns out that received CEC messages can arrive faster than can be processed by the CEC framework, resulting in lost messages. Instead of storing only one CEC message, store up to 8. Also fix a bug where the EOM bit wasn't checked for a received message of length 1, so POLL messages weren't properly reported. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: move the transmit to a workqueueHans Verkuil1-51/+81
Instead of adap_transmit waiting until the full message is transmitted (and thus hoarding the adap->lock mutex), have it kick off a transmit workqueue. This prevents adap->lock from being locked for a very long time. Also skip FAILED_ACK reports for broadcast messages: this makes no sense, and it seems a spurious message coming from the Pulse-Eight, since some time later I see the SUCCEEDED message. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: set tx_done_status for transmit_done statusHans Verkuil1-20/+21
Instead of translating work_result to a transmit_done status in pulse8_irq_work_handler(), pass the CEC_TX_STATUS via a new tx_done_status field. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: add 2nd debug levelHans Verkuil1-7/+17
Use debug level 2 to show the low-level Pulse-Eight commands. Also show the message to transmit on debug level 1 and add a debug log to show where the transmit failed. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: locking improvementsHans Verkuil1-21/+26
Drop the write_lock, rename config_lock to plain lock since this now locks access to the adapter. Use 'lock' when transmitting a message, ensuring that nothing interferes with the transmit. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: reorganize function orderHans Verkuil1-256/+248
Reorganize the order of the functions in the source, going from low-level to high-level. No functional changes were made. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: pulse8-cec: improve debuggingHans Verkuil1-5/+60
Add and use pulse8_msgname() to show the message codes as a human readable text instead of a number. Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: hantro: Support color conversion via post-processingEzequiel Garcia11-11/+343
The Hantro G1 decoder is able to enable a post-processor on the decoding pipeline, which can be used to perform scaling and color conversion. The post-processor is integrated to the decoder, and it's possible to use it in a way that is completely transparent to the user. This commit enables color conversion via post-processing, which means the driver now exposes YUV packed, in addition to NV12. Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com> Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: hantro: Rename {prepare,finish}_run to {start,end}_prepare_runEzequiel Garcia10-18/+18
hantro_prepare_run() and hantro_finish_run() are slightly misleading, so let's rename it to something a bit more clear. Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: hantro: Cleanup format negotiation helpersEzequiel Garcia1-33/+20
Format negotiation helpers, hantro_find_format() and hantro_get_default_fmt() can be simplified, making the code a little bit clearer. More importantly, this change is preparation work for the post-processor usage. Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: adv7604: extend deep color mode to ADV7611Dragos Bogdan1-11/+21
The AD7611 chip supports the same Deep Color Mode settings as the AD7604. This change extends support for this feature to the AD7611 by adding a wrapper function for the `read_hdmi_pixelclock` hook and adding the same frequency adjustment logic. Signed-off-by: Dragos Bogdan <dragos.bogdan@analog.com> Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: vimc: Implement get/set selection in sinkGuilherme Alcarde Gallo1-15/+151
Add support for the sink pad of scaler subdevice to respond VIDIOC_G_SELECTION and VIDIOC_S_SELECTION ioctls with the following targets: V4L2_SEL_TGT_COMPOSE_BOUNDS and V4L2_SEL_TGT_CROP. * Add new const struct crop_rect_default to initialize subdev scaler properly. * Make changes in sink pad format reflect to the crop rectangle. E.g. changing the frame format to a smaller size one can make the former crop rectangle selects a non existing frame area. To solve this situation the crop rectangle is clamped to the frame boundaries. * Clamp crop rectangle respecting the sink bounds during set_selection ioctl. Co-developed-by: Danilo Figueiredo Rocha <drocha.figueiredo@gmail.com> Signed-off-by: Guilherme Alcarde Gallo <gagallo7@gmail.com> Signed-off-by: Danilo Figueiredo Rocha <drocha.figueiredo@gmail.com> Acked-by: Helen Koike <helen.koike@collabora.com> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
2019-12-16media: imx7-mipi-csis: remove subdev_notifierRui Miguel Silva1-3/+0
It was defined a notifier in the csi_state structure that is never allocated. And besides that it's unregister in the remove, even though it is a no-op, just remove both. Fixes: 7807063b862b ("media: staging/imx7: add MIPI CSI-2 receiver subdev for i.MX7") Reported-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Suggested-by: Dan Carpenter <dan.carpenter@oracle.com> Suggested-by: Philipp Zabel <p.zabel@pengutronix.de> Signed-off-by: Rui Miguel Silva <rui.silva@linaro.org> Reviewed-by: Steve Longerbeam <slongerbeam@gmail.com> Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.