- 09 Jun, 2013 4 commits
-
-
Katsuya Matsubara authored
In the sh_veu driver, only the interrupt handler 'sh_veu_bh' can invoke the v4l2_m2m_job_finish() function. So the hardware must be alive for handling interrupts until returning from v4l2_m2m_ctx_release(). Signed-off-by:
Katsuya Matsubara <matsu@igel.co.jp> Signed-off-by:
Guennadi Liakhovetski <g.liakhovetski@gmx.de> Signed-off-by:
Mauro Carvalho Chehab <mchehab@redhat.com>
-
Katsuya Matsubara authored
v4l2_m2m_job_finish() should be invoked even if the current ongoing job has been aborted since v4l2_m2m_ctx_release() which has issued the job abort may wait until the finish function is invoked. Signed-off-by:
-
Hans Verkuil authored
The clips pointer is a userspace pointer, not a kernelspace pointer, so you can't dereference the clips pointer. Also add a few missing commas and newlines. Signed-off-by:
Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by:
-
Hans Verkuil authored
The radio filter function that filters controls that are valid for a radio device should also accept V4L2_CTRL_CLASS_FM_RX controls. Signed-off-by:
-
- 08 Jun, 2013 6 commits
-
-
Hans Verkuil authored
This fixes a NULL pointer deference when loading the cx88_dvb module for a Hauppauge HVR4000. The bugzilla bug report is here: https://bugzilla.kernel.org/show_bug.cgi?id=56271 The cause is that the wm8775 is optional, so even though the board info says there is one, it doesn't have to be there. Checking whether the module was actually loaded is much safer. Note that this driver is quite buggy when it comes to unloading and reloading modules. Unloading cx8800 and reloading it again will still cause a crash, most likely because either the i2c bus isn't unloaded at the right time and/or the v4l2_device_unregister isn't called at the right time. Signed-off-by:
Sebastian Frei <sebastian@familie-frei.net> Signed-off-by:
-
Hans Verkuil authored
The version number was still 3.9: update to 3.10. Signed-off-by:
-
Sylwester Nawrocki authored
The "sysreg" clock is required by multiple subsystems and none of the other drivers handles this clock explicitly. It is currently assumed that this clock is always on, left in its default state after system reset. Remove handling of this clock from the FIMC-IS driver to avoid breaking other subsystems. Signed-off-by:
Sylwester Nawrocki <s.nawrocki@samsung.com> Signed-off-by:
Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by:
-
Sylwester Nawrocki authored
The FIMC-IS-ISP handles only Bayer formats thus V4L2_COLORSPACE_SRGB should be used. This change applies to the code first added in v3.10. Signed-off-by:
-
Sylwester Nawrocki authored
Use clk_prepare_enable/clk_unprepare_disable instead of preparing the clocks during the driver initalization and then using just clk_disable/ clk_enable. The clock framework doesn't guarantee a clock will not get enabled during e.g. clk_set_parent if clk_prepare has been called on it. So we ensure clk_prepare() is called only when it is safe to enable the clocks, i.e. the parent clocks and the clocks' frequencies are set. It must be ensured the FIMC-IS clocks have proper frequencies before they are enabled, otherwise the whole system will hang. Signed-off-by:
-
Sylwester Nawrocki authored
Ensure the firmware isn't accessed in the driver when the firmware loading routine has not completed. This fixes a potential kernel crash: [ 96.510000] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 96.520000] pgd = ee604000 [ 96.520000] [00000000] *pgd=6e947831, *pte=00000000, *ppte=00000000 [ 96.530000] Internal error: Oops: 17 [#1] PREEMPT SMP ARM [ 96.530000] Modules linked in: [ 96.530000] CPU: 2 PID: 2787 Comm: camera_test Not tainted 3.10.0-rc1-00269-gcdbde37-dirty #2158 [ 96.545000] task: ee42e400 ti: edfcc000 task.ti: edfcc000 [ 96.545000] PC is at fimc_is_start_firmware+0x14/0x94 [ 96.545000] LR is at fimc_isp_subdev_s_power+0x13c/0x1f8 ... [ 96.745000] [<c03e0354>] (fimc_is_start_firmware+0x14/0x94) from [<c03e1cc4>] (fimc_isp_subdev_s_power+0x13c/0x1f8) [ 96.745000] [<c03e1cc4>] (fimc_isp_subdev_s_power+0x13c/0x1f8) from [<c03ed088>] (__subdev_set_power+0x70/0x84) [ 96.745000] [<c03ed088>] (__subdev_set_power+0x70/0x84) from [<c03ed164>] (fimc_pipeline_s_power+0xc8/0x164) [ 96.745000] [<c03ed164>] (fimc_pipeline_s_power+0xc8/0x164) from [<c03ee2b8>] (__fimc_pipeline_open+0x90/0x268) [ 96.745000] [<c03ee2b8>] (__fimc_pipeline_open+0x90/0x268) from [<c03ec5f0>] (fimc_capture_open+0xe4/0x1ec) [ 96.745000] [<c03ec5f0>] (fimc_capture_open+0xe4/0x1ec) from [<c03c5560>] (v4l2_open+0xa8/0xe4) [ 96.745000] [<c03c5560>] (v4l2_open+0xa8/0xe4) from [<c0112900>] (chrdev_open+0x9c/0x158) [ 96.745000] [<c0112900>] (chrdev_open+0x9c/0x158) from [<c010d3e0>] (do_dentry_open+0x1f4/0x27c) [ 96.745000] [<c010d3e0>] (do_dentry_open+0x1f4/0x27c) from [<c010d558>] (finish_open+0x34/0x50) [ 96.745000] [<c010d558>] (finish_open+0x34/0x50) from [<c011bea0>] (do_last+0x59c/0xbcc) [ 96.745000] [<c011bea0>] (do_last+0x59c/0xbcc) from [<c011c580>] (path_openat+0xb0/0x484) [ 96.745000] [<c011c580>] (path_openat+0xb0/0x484) from [<c011ca58>] (do_filp_open+0x30/0x84) [ 96.745000] [<c011ca58>] (do_filp_open+0x30/0x84) from [<c010d060>] (do_sys_open+0xe8/0x170) [ 96.745000] [<c010d060>] (do_sys_open+0xe8/0x170) from [<c000f040>] (ret_fast_syscall+0x0/0x30) Signed-off-by:
-
- 03 Jun, 2013 12 commits
-
-
Sachin Kamat authored
In certain cases, dma_alloc_coherent returns NULL. Add check for NULL pointer. Signed-off-by:
Sachin Kamat <sachin.kamat@linaro.org> Signed-off-by:
Kamil Debski <k.debski@samsung.com> Signed-off-by:
-
Andrzej Hajda authored
Many debug messages missed end-of-line. Signed-off-by:
Andrzej Hajda <a.hajda@samsung.com> Signed-off-by:
-
Andrzej Hajda authored
Callback .start_streaming is called once for every queue, so v4l2_ctrl_handler_setup was called twice during stream start. Moving v4l2_ctrl_handler_setup to context initialization reduces numbers of calls and seems to be more consistent with API. Signed-off-by:
-
Andrzej Hajda authored
This patch fixes a bug which caused overwriting h264 codec parameters by mpeg4 parameters during V4L2 control setting. Signed-off-by:
-
Arun Kumar K authored
MFC uses two clocks - MFC gate clock and special clock which is named as "sclk_mfc" in exynos4 and "aclk_333" in exynos5 SoC. The driver was doing just a clk_prepare on this special clock without a clk_enable call. As this sclk is the parent of gate clock, it gets prepared and enabled along with the gate clock. So there is no need for the driver to use this sclk. This patch removes the sclk usage from driver. Signed-off-by:
Arun Kumar K <arun.kk@samsung.com> Signed-off-by:
-
Sylwester Nawrocki authored
This patch fixes following compilation warning: CC [M] drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.o drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c:1733:12: warning: ‘s5p_mfc_get_decoded_status_v6’ defined but not used It assigns existing but not used s5p_mfc_get_dec_status_v6() function to the get_dec_status callback. It seems the get_dec_status callback is not used anyway, as there is no corresponding s5p_mfc_hw_call(). Signed-off-by:
Sylwester Nawrocki <sylvester.nawrocki@gmail.com> Signed-off-by:
-
John Sheu authored
Save flags correctly when taking spinlocks in v4l2_m2m_try_schedule. Signed-off-by:
John Sheu <sheu@google.com> Signed-off-by:
-
Philipp Zabel authored
Signed-off-by:
Philipp Zabel <p.zabel@pengutronix.de> Signed-off-by:
-
Philipp Zabel authored
Signed-off-by:
-
Seung-Woo Kim authored
The v4l2_m2m_poll() does not need to wait if there is already a buffer in done_list of source and destination queues, but current v4l2_m2m_poll() always waits. So done_list of each queue is checked before calling poll_wait(). Signed-off-by:
Seung-Woo Kim <sw0312.kim@samsung.com> Acked-by:
Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by:
-
Seung-Woo Kim authored
The vb2_poll() does not need to wait next vb_buffer_done() if there is already a buffer in done_list of queue, but current vb2_poll() always waits. So done_list is checked before calling poll_wait(). Signed-off-by:
-
Arun Kumar K authored
MFC v6 needs minimum number of output buffers to be queued for encoder depending on the stream type and profile. The patch modifies the driver so that encoding cannot be started with lesser number of OUTPUT buffers than required. This also fixes the crash happeninig during multi instance encoder-decoder simultaneous run due to memory allocation happening from interrupt context. Signed-off-by:
-
- 27 May, 2013 2 commits
-
-
Xiong Zhou authored
Make sure FONT_8x16 can be found by find_font(). Signed-off-by:
Xiong Zhou <jencce.kernel@gmail.com> Signed-off-by:
-
Lad, Prabhakar authored
from commit 3778d050 [media: davinci: kconfig: fix incorrect selects] VIDEO_VPFE_CAPTURE was removed but there was a negative dependancy for building the DM365 VPFE MC based capture driver (VIDEO_DM365_VPFE), This patch fixes this dependency by replacing the VIDEO_VPFE_CAPTURE with VIDEO_DM365_ISIF, so as when older DM365 ISIF v4l driver is selected the newer media controller driver for DM365 isnt visible. Reported-by:
Paul Bolle <pebolle@tiscali.nl> Signed-off-by:
Lad, Prabhakar <prabhakar.csengg@gmail.com> Signed-off-by:
-
- 21 May, 2013 12 commits
-
-
Sylwester Nawrocki authored
Ensure the compatible property for FIMC-LITE IP blocks is properly documented, a cut&paste error fix. Signed-off-by:
-
Axel Lin authored
Current code uses is->config_index as array subscript, thus the valid value range is 0 ... ARRAY_SIZE(cmd) - 1. Signed-off-by:
Axel Lin <axel.lin@ingics.com> Signed-off-by:
-
Axel Lin authored
Current code uses fie->index as array subscript, thus the valid value range is 0 ... ARRAY_SIZE(s5c73m3_intervals) - 1. Signed-off-by:
-
Sachin Kamat authored
'rotation' was an 8 bit variable and hence could not have values greater than 255. Since we need higher values, change it to 16 bit type. Signed-off-by:
-
Sachin Kamat authored
When 'node' is NULL, the print statement tries to dereference it. Hence replace the variable with the one that is accessible. Signed-off-by:
-
Hans Verkuil authored
Signed-off-by:
-
Hans Verkuil authored
The Codec section in the V4L2 specification was marked as 'suspended', even though codec support has been around for quite some time. Update this section, explaining a bit about memory-to-memory devices and pointing to the MPEG controls section. Signed-off-by:
-
Arnd Bergmann authored
It is not possible to select SND_SOC_SI476X if we have not also enabled SND_SOC. warning: (RADIO_SI476X) selects SND_SOC_SI476X which has unmet direct dependencies (SOUND && !M68K && !UML && SND && SND_SOC) Signed-off-by:
Arnd Bergmann <arnd@arndb.de> [hans.verkuil@cisco.com: fixed wrong driver name in subject] Acked-by:
-
Geert Uytterhoeven authored
Gcc < 4.3 doesn't understand binary constanrs (0b*): drivers/media/radio/radio-si476x.c:862:20: error: invalid suffix "b10000000" on integer constant Hence use a hexadecimal constant (0x*) instead. Signed-off-by:
Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by:
-
Wei Yongjun authored
Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Signed-off-by:
Wei Yongjun <yongjun_wei@trendmicro.com.cn> Acked-by:
-
Lad, Prabhakar authored
The error path on failure was calling mutex_unlock(), but there was no actuall call before for mutex_lock(). This patch fixes this issue by pointing it to proper go label. Reported-by:
Jose Pablo Carballo <jose.carballo@ridgerun.com> Signed-off-by:
-
Lad, Prabhakar authored
For NV12 format, even if display data is single image, both VIDWIN0 and VIDWIN1 parameters must be used. The start address of Y data plane and C data plane is configured in VIDEOWIN0ADH/L and VIDEOWIN1ADH/L respectively. cuurently only one layer was requested, which is suffice for yuv422, but for yuv420(NV12) two layers are required and fix the same by requesting for other layer if pix fmt is NV12 during set_fmt. Signed-off-by:
-
- 07 May, 2013 2 commits
-
-
Hans de Goede authored
For some unknown reason we need to increase hstart by 1 on when using the PAS202 on the sn9c103 (versus on the sn9c102), otherwise we get the wrong colors, due to shifting of the bayer pattern. Reported-by:
Patrizio Bassi <patrizio.bassi@gmail.com> Tested-by:
Hans de Goede <hdegoede@redhat.com> Signed-off-by:
-
Hans de Goede authored
With all the changes to handle the locking in the v4l2-core rather then at the driver level, the order in which the 2 pwc locks need to be taken has changed, update the comment in the header file to correctly reflect this. Signed-off-by:
-
- 30 Apr, 2013 2 commits
-
-
Mauro Carvalho Chehab authored
* patchwork: (831 commits) [media] cx88: make core less verbose [media] em28xx: fix oops at em28xx_dvb_bus_ctrl() [media] s5c73m3: fix indentation of the help section in Kconfig [media] cx25821-alsa: get rid of a __must_check warning [media] cx25821-video: declare cx25821_vidioc_s_std as static [media] cx25821-video: remove maxw from cx25821_vidioc_try_fmt_vid_cap [media] r820t: Remove a warning for an unused value [media] dib0090: Fix a warning at dib0090_set_EFUSE [media] dib8000: fix a warning [media] dib8000: Fix sub-channel range [media] dib8000: store dtv_property_cache in a temp var [media] dib8000: warning fix: declare internal functions as static [media] r820t: quiet gcc warning on n_ring [media] r820t: memory leak in release() [media] r820t: precendence bug in r820t_xtal_check() [media] videodev2.h: Remove the unused old V4L1 buffer types [media] anysee: Grammar s/report the/report to/ [media] anysee: Initialize ret = 0 in anysee_frontend_attach() [media] media: videobuf2: fix the length check for mmap [media] em28xx: save isoc endpoint number for DVB only if endpoint has alt settings with xMaxPacketSize != 0 ... Conflicts: drivers/media/pci/cx25821/cx25821-video.c drivers/media/platform/Kconfig
-
Mauro Carvalho Chehab authored
Linux 3.9 * tag 'v3.9': (1099 commits) Linux 3.9 vm: add no-mmu vm_iomap_memory() stub efivars: only check for duplicates on the registered list TTY: fix atime/mtime regression aio: fix possible invalid memory access when DEBUG is enabled parisc: use spin_lock_irqsave/spin_unlock_irqrestore for PTE updates parisc: disable -mlong-calls compiler option for kernel modules parisc: uaccess: fix compiler warnings caused by __put_user casting parisc: Change kunmap macro to static inline function parisc: Provide __ucmpdi2 to resolve undefined references in 32 bit builds. sparc64: Fix missing put_cpu_var() in tlb_batch_add_one() when not batching. Revert "gpio: pxa: set initcall level to module init" efi: Check EFI revision in setup_efi_vars x86, efi: Fix a build warning Revert "MIPS: page.h: Provide more readable definition for PAGE_MASK." kernel/hz.bc: ignore. Linux 3.9-rc8 events: Protect access via task_subsys_state_check() net: fix incorrect credentials passing x86, microcode: Verify the family before dispatching microcode patching ...
-
