- 25 Apr, 2013 40 commits
-
-
Mauro Carvalho Chehab authored
The check if the values for c, h and n are within the range is always true, as, if one of this values is out of range, the previous "if" clauses will default to a value within the range. That fixes the following warning: drivers/media/dvb-frontends/dib0090.c: In function 'dib0090_set_EFUSE': drivers/media/dvb-frontends/dib0090.c:1545:5: warning: comparison is always true due to limited range of data type [-Wtype-limits] and makes the code easier to read. Signed-off-by:Mauro Carvalho Chehab <mchehab@redhat.com>
-
Mauro Carvalho Chehab authored
drivers/media/dvb-frontends/dib8000.c: In function 'dib8000_wait_lock': drivers/media/dvb-frontends/dib8000.c:3972:1: warning: 'value' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/media/dvb-frontends/dib8000.c:2419:6: note: 'value' was declared here Signed-off-by: -
Mauro Carvalho Chehab authored
isdbt_sb_subchannel is unsigned with 8 bits. So, it will never be -1. Instead, any value bigger than 13 is invalid. As is, the current code generates the following warnings: drivers/media/dvb-frontends/dib8000.c: In function 'dib8000_set_isdbt_common_channel': drivers/media/dvb-frontends/dib8000.c:2358:3: warning: comparison is always true due to limited range of data type [-Wtype-limits] drivers/media/dvb-frontends/dib8000.c: In function 'dib8000_tune': drivers/media/dvb-frontends/dib8000.c:3107:8: warning: comparison is always false due to limited range of data type [-Wtype-limits] drivers/media/dvb-frontends/dib8000.c:3153:9: warning: comparison is always false due to limited range of data type [-Wtype-limits] drivers/media/dvb-frontends/dib8000.c:3160:5: warning: comparison is always false It should also be noticed that ARIB STD-B31, item "3.15.6.8 Number of segments" at TMCC table defines the value 15 for unused segment, and 14 as reserved. So, better to change the check to consider any value bigger than 13 to mean that sub-channels should be disabled, fixing the warning and doing the right thing even if an invalid value is filled by userspace. Signed-off-by: -
Mauro Carvalho Chehab authored
dtv_property_cache is used on several places on very long lines. On all places it is used, a long list of struct reference is done. Instead of doing it, at the routines where it is used more than once, replace it by one temporary var. That may help the compiler to use a better code. It also makes easier to review the code, as the lines becomes closer to 80 columns, making them a way clearer to read. No functional changes. Signed-off-by: -
Mauro Carvalho Chehab authored
drivers/media/dvb-frontends/dib8000.c:2412:5: warning: no previous prototype for 'dib8000_wait_lock' [-Wmissing-prototypes] drivers/media/dvb-frontends/dib8000.c:2688:5: warning: no previous prototype for 'dib8000_get_symbol_duration' [-Wmissing-prototypes] Signed-off-by: -
Fengguang Wu authored
drivers/media/tuners/r820t.c: In function 'r820t_imr': drivers/media/tuners/r820t.c:1871:8: warning: 'n_ring' may be used uninitialized in this function [-Wmaybe-uninitialized] Mauro: This is a FALSE POSITIVE: the loop will always return a value for n_ring, as the last test will fill it with 15, if the loop fails. Signed-off-by:
Fengguang Wu <fengguang.wu@intel.com> Signed-off-by:
-
Dan Carpenter authored
I've moved the kfree(fe->tuner_priv) one line earlier, otherwise it is a no-op. Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
-
Dan Carpenter authored
The test as written is always false. It looks like the intent was to test that the bit was not set. Signed-off-by:
-
Mauro Carvalho Chehab authored
Those aren't used anywhere for a long time. Drop it. Signed-off-by: -
Mauro Carvalho Chehab authored
* topic/cx25821: (31 commits) [media] cx25821: remove cx25821-audio-upstream.c from the Makefile [media] cx25821: replace custom ioctls with write() [media] cx25821: drop cx25821-video-upstream-ch2.c/h [media] cx25821: add output format ioctls [media] cx25821: prepare querycap for output support [media] cx25821: group all fmt functions together [media] cx25821: setup output nodes correctly [media] cx25821: remove references to subdevices that aren't there [media] cx25821: remove custom ioctls that duplicate v4l2 ioctls [media] cx25821: g/s/try/enum_fmt related fixes and cleanups [media] cx25821: switch to v4l2_fh, add event and prio handling [media] cx25821: replace resource management functions with fh ownership [media] cx25821: move vidq from cx25821_fh to cx25821_channel [media] cx25821: remove 'type' field from cx25821_fh [media] cx25821: use core locking [media] cx25821: remove unnecessary debug messages [media] cx25821: remove TRUE/FALSE/STATUS_(UN)SUCCESSFUL defines [media] cx25821: convert to the control framework [media] cx25821: embed video_device, clean up some kernel log spam [media] cx25821: remove bogus dependencies ...
-
Mauro Carvalho Chehab authored
* topic/si476x: Revert "[media] mfd: Add chip properties handling code for SI476X MFD" Revert "[media] mfd: Add the main bulk of core driver for SI476x code" Revert "[media] mfd: Add commands abstraction layer for SI476X MFD" [media] v4l2: Add a V4L2 driver for SI476X MFD
-
Mauro Carvalho Chehab authored
* topic/r820t: (31 commits) [media] r820t: Don't divide the IF by two [media] r820t: disable auto gain/VGA setting [media] rtl2832: Fix IF calculus [media] r820t: put it into automatic gain mode [media] r820t: Fix hp_cor filter mask [media] r820t: fix PLL calculus [media] r820t: Don't put it in standby if not initialized yet [media] r820t: avoid rewrite all regs when not needed [media] r820t: Allow disabling IMR callibration [media] r820t: add a commented code for GPIO [media] r820t: add IMR calibrate code [media] r820t: proper initialize the PLL register [media] r820t: use usleep_range() [media] r820t: fix prefix of the r820t_read() function [media] r820t: split the function that read cached regs [media] r820t: better report signal strength [media] r820t: add support for diplexer [media] r820t: Show the read data in the bit-reversed order [media] r820t: use the second table for 7MHz [media] r820t: Invert bits for read ops ...
-
Geert Uytterhoeven authored
[mchehab@redhat.com: Fix a merge conflict] Signed-off-by:
Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by:
-
Geert Uytterhoeven authored
drivers/media/usb/dvb-usb-v2/anysee.c: In function ‘anysee_frontend_attach’: drivers/media/usb/dvb-usb-v2/anysee.c:641: warning: ‘ret’ may be used uninitialized in this function And gcc is right (see the ANYSEE_HW_507T case), so initialize ret to zero to fix this. Signed-off-by:
-
Mauro Carvalho Chehab authored
Memory maps typically require that the buffer size to be page aligned. Currently, two memops drivers do such alignment internally, but videobuf-vmalloc doesn't. Also, the buffer overflow check doesn't take it into account. So, instead of doing it at each memops driver, enforce it at VB2 core. Reported-by:
Prabhakar lad <prabhakar.csengg@gmail.com> Acked-by:
Laurent Pinchart <laurent.pinchart@ideasonboard.com> Acked-by:
Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by:
-
Frank Schaefer authored
[media] em28xx: save isoc endpoint number for DVB only if endpoint has alt settings with xMaxPacketSize != 0 X-Patchwork-Delegate: mchehab@redhat.com In addition to commit 72cc9ba3 "em28xx: ignore isoc DVB USB endpoints with wMaxPacketSize = 0 bytes for all alt settings" we should not save the endpoint number of the isoc DVB endpoint before it has been validated. While the current code works fine, dev->dvb_ep_isoc != 0 could be interpreted as indicator that the device provides DVB support. Signed-off-by:
Frank Schäfer <fschaefer.oss@googlemail.com> Signed-off-by:
-
Mauro Carvalho Chehab authored
videobuf_queue_dma_contig_init_cached() is not used anywhere. Drop support for it, cleaning up the code a little bit. Signed-off-by:
Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by:
-
Hans Verkuil authored
While testing v4l2-ctl I noticed that this m2m driver didn't set timestamp_type and that it spammed the kernel log with debug messages. Set timestamp_type correctly and add debug module option to enable debug messages. Signed-off-by:
Kamil Debski <k.debski@samsung.com> Signed-off-by:
-
Kamil Debski authored
Since the introduction of the timestamp_type field, it is necessary that the driver chooses which type it will use. This patch adds support for the timestamp_type. Signed-off-by:
Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by:
-
Kamil Debski authored
Since the introduction of the timestamp_type field, it is necessary that the driver chooses which type it will use. This patch adds support for the timestamp_type. Signed-off-by:
-
Kamil Debski authored
Since the introduction of the timestamp_type field, it is necessary that the driver chooses which type it will use. This patch adds support for the timestamp_type. Signed-off-by:
-
Kamil Debski authored
Since the introduction of the timestamp_type field, it is necessary that the driver chooses which type it will use. This patch adds support for the timestamp_type. Signed-off-by:
-
Kamil Debski authored
For the sake of simplicity and readability memcpy was replaced with assignment. Signed-off-by:
-
Kamil Debski authored
Since the introduction of the timestamp_type field, it is necessary that the driver chooses which type it will use. This patch adds support for the timestamp_type. Signed-off-by:
-
Kamil Debski authored
Since the introduction of the timestamp_type field, it is necessary that the driver chooses which type it will use. This patch adds support for the timestamp_type. Signed-off-by:
-
Sylwester Nawrocki authored
Add copying of buffer timestamps and set the timestamp_type to V4L2_BUF_FLAG_TIMESTAMP_COPY to avoid warnings about UNDEFINED timestamp type like: WARNING: at drivers/media/v4l2-core/videobuf2-core.c:2042 vb2_queue_init+0xe0/0x18c() Modules linked in: [<c0016ef0>] (unwind_backtrace+0x0/0x13c) from [<c0029b3c>] (warn_slowpath_common+0x54/0x64) [<c0029b3c>] (warn_slowpath_common+0x54/0x64) from [<c0029b68>] (warn_slowpath_null+0x1c/0x24) [<c0029b68>] (warn_slowpath_null+0x1c/0x24) from [<c03b7018>] (vb2_queue_init+0xe0/0x18c) [<c03b7018>] (vb2_queue_init+0xe0/0x18c) from [<c03b4e08>] (v4l2_m2m_ctx_init+0xa0/0xc4) [<c03b4e08>] (v4l2_m2m_ctx_init+0xa0/0xc4) from [<c03ca6c4>] (fimc_m2m_open+0x130/0x1f8) [<c03ca6c4>] (fimc_m2m_open+0x130/0x1f8) from [<c03a5dd4>] (v4l2_open+0xac/0xe8) [<c03a5dd4>] (v4l2_open+0xac/0xe8) from [<c0113920>] (chrdev_open+0x9c/0x158) [<c0113920>] (chrdev_open+0x9c/0x158) from [<c010e488>] (do_dentry_open+0x1f8/0x280) [<c010e488>] (do_dentry_open+0x1f8/0x280) from [<c010e600>] (finish_open+0x34/0x50) [<c010e600>] (finish_open+0x34/0x50) from [<c011cc58>] (do_last+0x5bc/0xc00) [<c011cc58>] (do_last+0x5bc/0xc00) from [<c011d34c>] (path_openat+0xb0/0x484) [<c011d34c>] (path_openat+0xb0/0x484) from [<c011d824>] (do_filp_open+0x30/0x84) [<c011d824>] (do_filp_open+0x30/0x84) from [<c010e0f8>] (do_sys_open+0xe8/0x170) [<c010e0f8>] (do_sys_open+0xe8/0x170) from [<c000f040>] (ret_fast_syscall+0x0/0x30) Signed-off-by:
Sylwester Nawrocki <s.nawrocki@samsung.com> Signed-off-by:
-
Sylwester Nawrocki authored
Ensure TRY format is propagated from the sink to source pad. The format at both pads is always same so the TRY format buffer for pad 0 is used to hold format for both pads. While at it remove redundant fmt->pad checking. Reported-by:
Jacek Anaszewski <j.anaszewski@samsung.com> Signed-off-by:
-
Sylwester Nawrocki authored
Originally struct v4l2_capability driver and card name was filled with name of the platform device. After switching to the device tree the device names have changed and now are 4 different driver names reported, depending on the video device opened. So instead of e.g. "exynos4-fimc" there is now one of: 11800000.fimc, 11810000.fimc, 11820000.fimc, 11830000.fimc. Fix this by using dev->driver_name, rather than platform device name. A common vidioc_querycap function is created for both M2M and capture video node. This fixes any breakage at user space should any application/library rely on the driver's name. Signed-off-by:
-
Wei Yongjun authored
Fix to return a negative error code from the error handling case instead of 0, as returned elsewhere in this function. Signed-off-by:
Wei Yongjun <yongjun_wei@trendmicro.com.cn> Acked-by:
-
Sylwester Nawrocki authored
Ensure there is no unbalanced pm_runtime_put(). Signed-off-by:
-
Sylwester Nawrocki authored
Due to hardware dependencies (clocks/power domain) the I2C bus controller needs to be unregistered before fimc-is. Signed-off-by:
-
Sylwester Nawrocki authored
Ensure both debugfs: fimc_is directory and the fw_log file are properly removed in the driver cleanup sequence. Signed-off-by:
-
Sylwester Nawrocki authored
Currently there is unbalanced module_put() on the s5p-csis module which prevents it from being unloaded. The subdev's owner module has reference count decremented in v4l2_device_unregister_subdev() so just remove this erroneous call. Signed-off-by:
-
Sylwester Nawrocki authored
The FIMC-LITE.n subdevs have currently sd->owner field not set, the exynos-fimc-lite module can be removed at any time, regardless it is in use by other modules. When this module is unloaded the kernel can crash easily by accessing video or media device nodes. Signed-off-by:
-
Sylwester Nawrocki authored
Add missing v4l2_device_unregister_subdev() call for the FIMC-IS subdevs (currently there is only the FIMC-IS-ISP subdev) so corresponding resources are properly freed upon the media device driver module removal. Signed-off-by:
-
Sylwester Nawrocki authored
It's an I2C client driver and it must not overwrite the struct v4l2_subdev dev_priv field, which is used by the v4l2 core to store a pointer to struct i2c_client. Signed-off-by:
-
Sylwester Nawrocki authored
Remove regulator_bulk_free() calls as devm_regulator_bulk_get() function is used to get the regulators so those will be freed automatically while the driver is removed. Missing gpio free is fixed by requesting a gpio with the devm_* API. All that is done now in the I2C client driver remove() callback is the media entity cleanup call. Signed-off-by:
-
Sylwester Nawrocki authored
Ensure the value of struct v4l2_subdev::flags field as set in v4l2_subdev_init() is preserved when initializing it in the subdev drivers. Signed-off-by:
-
Sylwester Nawrocki authored
Remove unneeded MODULE_DEVICE_TABLE(of,...) instances from files that are linked into same module. This fixes following error when building as a module: LD [M] drivers/media/platform/exynos4-is/s5p-fimc.o drivers/media/platform/exynos4-is/fimc-is-sensor.o: In function `.LANCHOR1': fimc-is-sensor.c:(.rodata+0x48): multiple definition of `__mod_of_device_table' drivers/media/platform/exynos4-is/fimc-is.o:fimc-is.c:(.rodata+0x174): first defined here drivers/media/platform/exynos4-is/fimc-is-i2c.o:(.rodata+0x5c): multiple definition of `__mod_of_device_table' drivers/media/platform/exynos4-is/fimc-is.o:fimc-is.c:(.rodata+0x174): first defined here make[4]: *** [drivers/media/platform/exynos4-is/exynos-fimc-is.o] Error 1 Also remove exporting fimc_is_(un)register_i2c_driver functions, it is not needed since these functions should be called only from our module. Signed-off-by:
-
Sylwester Nawrocki authored
This is needed to free any resources requested in the .registered subdev op. Signed-off-by:
-
