- 21 Sep, 2014 40 commits
-
-
Antti Palosaari authored
AF9030 and IT9130 series has different memory location for firmware version. Choose correct location according to chip type. Signed-off-by:
Antti Palosaari <crope@iki.fi> Signed-off-by:
Mauro Carvalho Chehab <mchehab@osg.samsung.com>
-
Antti Palosaari authored
udelay based I/O polling loop is a bad idea, especially system performance point of view. Kernel jiffies are preferred solution for such situations. Use it instead. Signed-off-by:
-
Antti Palosaari authored
Refactor code largely. Try to keep order of register read/write same as windows driver does as it makes comparing sniffs easier. Signed-off-by:
-
Antti Palosaari authored
Used script loader is quite useless and hides register numbers making code hard to understand. Get rid of it and use standard RegMap register write functions directly. it913x_priv.h file leaves empty after that change and is also removed. Signed-off-by:
-
Antti Palosaari authored
Remove unused tuner set template. Signed-off-by:
-
Antti Palosaari authored
Re-implement sleep. Based USB sniffs taken from the latest Hauppauge windows driver version 07/10/2014, 14.6.23.32191. Signed-off-by:
-
Antti Palosaari authored
Use RegMap API to cover I2C register access routines. Signed-off-by:
-
Antti Palosaari authored
foo_dev seems to be most correct term for the structure holding data of each device instance. It is most used term in Kernel and also examples from book Linux Device Drivers, Third Edition, uses it. Signed-off-by:
-
Antti Palosaari authored
Change register write and read routines to similar which are typically used. We have to add processor core as a part of register address in order to simplify register access. Chip has two cores, called link and ofdm. As for now, use address bit 24 to address used core. Bits 15:0 are register address in given core. Signed-off-by:
-
Antti Palosaari authored
Change the it913x driver to use the I2C high lever tuner binding model. As af9035 depends on it, add a code there to do the binding. [mchehab@osg.samsung.com: Merge 3 patches into one, because we don't want to break bisect due to the conversion] Signed-off-by:
-
Antti Palosaari authored
Remove tuner_ prefix from module name and file names. Prefix was added due to file name conflict on media out-tree build system. Demodulator having same name does not exists anymore. So lets remove dumb prefix. Signed-off-by:
-
Antti Palosaari authored
Correct issues reported by checkpatch.pl Signed-off-by:
-
Antti Palosaari authored
Correct issues reported by checkpatch.pl. Signed-off-by:
-
Antti Palosaari authored
Correct issues reported by checkpatch.pl. Signed-off-by:
-
Antti Palosaari authored
Reverts commit 3ab25123 [media] af9035: override tuner for AVerMedia A835B devices Original commit itself is correct, but it was replaced by more general solution (commit 1cbbf90d). This old solution was committed by a accident and is not needed anymore. Signed-off-by:
-
Antti Palosaari authored
Old IT9135 AX needs a little bit different register settings for sleep than newer IT9135 BX. This has been broken always, as power management of the whole driver, but it started to be problem as I fixed clock. Earlier clock was disabled very first on sleep and rest of the commands were skipped by the chip as no clock, leaving tuner full power state. When I fixed clocks these PM bugs started raising out as I/O errors. Cc: Bimow Chen <Bimow.Chen@ite.com.tw> Signed-off-by:
-
Antti Palosaari authored
Error on init leaves some internal divisor zero, which causes oops later. Fix it by populating divisors even it fails. Signed-off-by:
-
Antti Palosaari authored
IT913x tuner driver disables own clock, provided by demod core, as very a first operation when tuner is put on *sleep*. That likely causes failure of all the rest commands on sleep sequence, which leads situation where tuner is not actually on sleep, but consuming a lot of power. I measured 102mA current consumption from the USB before change and after change it was only 32mA. Used device was single tuner IT9135 BX. Second reason to remove that register from tuner driver is reason it is simply on wrong driver (demod vs. tuner), breaking the principle of correct driver. Clock is now provided more correctly af9033 demod driver as a config option. Cc: Bimow Chen <Bimow.Chen@ite.com.tw> Signed-off-by:
-
Antti Palosaari authored
Integrated RF tuner of IT9135 is connected to demod clock source named dyn0_clk. Enable that clock source in order to provide stable clock early enough. Cc: Bimow Chen <Bimow.Chen@ite.com.tw> Signed-off-by:
-
Antti Palosaari authored
AF903x/IT913x demod provides clock source(s). It seems that this clock source is used for integrated RF tuner of IT913x. It is enabled by default, but firmware disables it automatically when suspend is requested (suspend_flag (0x004c) + trigger_ofsm (0x0000)). Automatic disable behavior seems to be similar for both AF903x and IT913x I tested, though there is no likely any real clock user in a case of AF903x. Cc: Bimow Chen <Bimow.Chen@ite.com.tw> Signed-off-by:
-
Bimow Chen authored
IT9135 firmware update. Signed-off-by:
Bimow Chen <Bimow.Chen@ite.com.tw> Signed-off-by:
-
Fabio Estevam authored
coda-bit uses kmalloc/kfree functions, so the slab header needs to be included in order to fix the following build errors: drivers/media/platform/coda/coda-bit.c: In function 'coda_fill_bitstream': drivers/media/platform/coda/coda-bit.c:231:4: error: implicit declaration of function 'kmalloc' [-Werror=implicit-function-declaration] drivers/media/platform/coda/coda-bit.c: In function 'coda_alloc_framebuffers': drivers/media/platform/coda/coda-bit.c:312:3: error: implicit declaration of function 'kfree' [-Werror=implicit-function-declaration] Signed-off-by:
Fabio Estevam <fabio.estevam@freescale.com> Acked-by:
Philipp Zabel <p.zabel@pengutronix.de> Signed-off-by:
-
Antti Palosaari authored
There is 2 different versions of that chip available, master and slave. Slave is used only on dual tuner devices with master tuner. Laser printing top of chip is 18212/M or 18212/S according to chip version. Signed-off-by:
-
Olli Salonen authored
Add a variable to keep track if firmware is loaded or not and skip parts of the initialization if fw is already loaded. Resume from sleep with a different command compared to initial power up and run command 85 after resume command. This behaviour is observed when using manufacturer provided binary-only si2168 driver for TechnoTrend CT2-4400. Signed-off-by:
Olli Salonen <olli.salonen@iki.fi> Signed-off-by:
-
Olli Salonen authored
Add a variable into state to keep track if firmware has been loaded or not. Skip firmware loading in case it is already loaded (resume from sleep). Signed-off-by:
-
Olli Salonen authored
Instead of sending command 13 to the tuner, send command 16 when sleeping. This behaviour is observed when using manufacturer provided binary-only Linux driver for TechnoTrend CT2-4400 (Windows driver does not do power management). The issue with command 13 is that firmware loading is necessary after that. This is not an issue with tuners that do not require firmware, but starting streaming after sleep on an Si2158 takes noticeable time as firmware is loaded on resume. Signed-off-by:
-
Antti Palosaari authored
Remove function name from debug logs. Logging system could add it automatically. Signed-off-by:
-
Antti Palosaari authored
Sample rate calculation gives a little bit too large results because in real life there was around one milliseconds (~one usb packet) too much data for given time. Calculate time more accurate in order to provide better results. Signed-off-by:
-
Antti Palosaari authored
There is no need to init flags before calling spin_lock_irqsave(). spin_lock_irqsave is macro which stores value to 'flags' Signed-off-by:
-
Antti Palosaari authored
Remove function name from debug logs. Logging system could add it automatically. Signed-off-by:
-
Antti Palosaari authored
There is no need to init flags before calling spin_lock_irqsave(). spin_lock_irqsave is macro which stores value to 'flags'. Signed-off-by:
-
Antti Palosaari authored
Remove function name from debug logs. Logging system could add it automatically. Signed-off-by:
-
Antti Palosaari authored
Kernel logging system needs pointer to usb interface device in order to print names and bus numbers properly. There was wrong device pointer given and log printings wasn't correct. Signed-off-by:
-
Antti Palosaari authored
Sample rate calculation gives a little bit too large results because in real life there was around one milliseconds (~one usb packet) too much data for given time. Calculate time more accurate in order to provide better results. Signed-off-by:
-
Antti Palosaari authored
There is no need to init flags before calling spin_lock_irqsave(). spin_lock_irqsave is a macro which stores value to 'flags'. Signed-off-by:
-
Antti Palosaari authored
Kernel logging system needs pointer to usb interface device in order to print names and bus numbers properly. There was wrong device pointer given and log printings wasn't correct. Remove some debug logging from v4l2 ioctl functions. v4l2 core debug prints almost same information when enabled. Signed-off-by:
-
Antti Palosaari authored
Fix issues reported by checkpatch.pl. Signed-off-by:
-
Antti Palosaari authored
Free all reserved USB buffers and URBs on failure. Return all queued buffers to vb2 with state queued on error case. Signed-off-by:
-
Mauro Carvalho Chehab authored
There are some patches that depends on media-v3.16-rc6. So, merge back from upstream before applying them. * linus/master: (1123 commits) drm/nouveau: ltc/gf100-: fix cbc issues on certain boards drm/bochs: add missing drm_connector_register call drm/cirrus: add missing drm_connector_register call staging: vt6655: buffer overflow in ioctl USB: storage: Add quirks for Entrega/Xircom USB to SCSI converters USB: storage: Add quirk for Ariston Technologies iConnect USB to SCSI adapter USB: storage: Add quirk for Adaptec USBConnect 2000 USB-to-SCSI Adapter USB: EHCI: unlink QHs even after the controller has stopped [SCSI] fix for bidi use after free [SCSI] fix regression that accidentally disabled block-based tcq [SCSI] libiscsi: fix potential buffer overrun in __iscsi_conn_send_pdu drm/radeon: Fix typo 'addr' -> 'entry' in rs400_gart_set_page drm/nouveau/runpm: fix module unload drm/radeon/px: fix module unload vgaswitcheroo: add vga_switcheroo_fini_domain_pm_ops drm/radeon: don't reset dma on r6xx-evergreen init drm/radeon: don't reset sdma on CIK init drm/radeon: don't reset dma on NI/SI init drm/radeon/dpm: fix resume on mullins drm/radeon: Disable HDP flush before every CS again for < r600 ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-mediaLinus Torvalds authored
Pull media fixes from Mauro Carvalho Chehab: "some media bug fixes: - a Kconfig dependency issue - some fixes for af9033/it913x demod to be more reliable and address a performance regression - cx18: fix an oops on devices with tda8290 tuner - two new USB IDs for af9035 - a couple fixes on smapp driver" * tag 'media-v3.17-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media: [media] af9035: new IDs: add support for PCTV 78e and PCTV 79e [media] af9033: feed clock to RF tuner [media] it913x: init tuner on attach [media] af9033: update IT9135 tuner inittabs [media] Kconfig: do not select SPI bus on sub-driver auto-select [media] cx18: fix kernel oops with tda8290 tuner [media] smiapp: Set sub-device owner [media] smiapp: Fix power count handling
-
