- Aug 03, 2010
-
-
Axel Lin authored
There is a memory leak found if wm8978_register() fail. This patch moves the buffer allocate and release at the same level to prevent the memory leak. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Reviewed-by:
Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
wm8974 is allocated in wm8974_i2c_probe() but is not freed if wm8974_register() return -EINVAL (if another WM8974 is registered). Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
This patch fixes the error path in wm8961_register to properly free resources. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
This patch fixes the error path in wm8955_register to properly free resources. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
This patch adds checking for wm8940_register return value, and does kfree(wm8940) if wm8940_register() fail. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
This patch includes below fixes: 1. wm8904 need to be kfreed in wm8904_register() error path before return. 2. fix the error path for snd_soc_register_codec() fail and snd_soc_register_dai() fail to properly free resources. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
wm8711 is allocated in either wm8711_spi_probe() or wm8711_i2c_probe() but is not freed if wm8711_register() return -EINVAL(if another ad1836 is registered). Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
This patch includes below fixes: 1. If another WM8523 is registered, need to kfree wm8523 before return -EINVAL. 2. If snd_soc_register_codec failed, goto error path to properly free resources. 3. Instead of using mixed in-line and goto style cleanup, use goto style error handling if snd_soc_register_dai failed. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
da7210 should be kfreed if da7210_init() return error. This patch also fixes the error handing in the case of snd_soc_register_dai() fail by adding snd_soc_unregister_codec() in error path. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
ak4642 should be kfreed if ak4642_init() return error. Signed-off-by:
Axel Lin <axel.lin@gmail.com> Reviewed-by:
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Axel Lin authored
ad1836 is allocated in ad1836_spi_probe() but is not freed if ad1836_register() return -EINVAL (if another ad1836 is registered). Signed-off-by:
Axel Lin <axel.lin@gmail.com> Acked-by:
Barry Song <21cnbao@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Ian Lartey authored
The WM8741 is a very high performance stereo DAC designed for audio applications such as professional recording systems, A/V receivers and high specification CD, DVD and home theatre systems. The device supports PCM data input word lengths from 16 to 32-bits and sampling rates up to 192kHz. The WM8741 also supports DSD bit-stream data format, in both direct DSD and PCM-converted DSD modes. TODO: Expand wm8741_set_dai_sysclk and rate_constraint members to allow for all supported sample rate / Master Clock frequency combinations. Fully enable control of supplies. Signed-off-by:
Ian Lartey <ian@opensource.wolfsonmicro.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
- Aug 02, 2010
-
-
Takashi Iwai authored
Merge branch 'for-2.6.36' of git://git.kernel.org/pub/scm/linux/kernel/git/lrg/asoc-2.6 into topic/asoc
-
Peter Ujfalusi authored
The use of sDMA packet mode in THRESHOLD mode removes the restriction on the period size. With the extended THRESHOLD mode user space can ask for any period size it wishes, and the driver will configure the sDMA and McBSP FIFO accordingly. Replace the hw_rule for the period size with static constraint, which will make sure that the period size will be always even (to avoid prime period size, which could be possible in mono stream) Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Jarkko Nikula <jhnikula@gmail.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Peter Ujfalusi authored
Utilize the sDMA controller's packet syncronization mode, when the McBSP FIFO is in use (by extending the THRESHOLD mode). When the sDMA is configured for packet mode, the sDMA frame size does not need to match with the McBSP threshold configuration. Uppon DMA request the sDMA will transfer packet size number of words, and still trigger interrupt on frame boundary. The patch extends the original THRESHOLD mode by doing the following: if (period_words <= max_threshold) Current THRESHOLD mode configuration Otherwise (period_words > max_threshold) McBSP threshold = sDMA packet size sDMA frame size = period size With the extended THRESHOLD mode we can remove the constraint for the maximum period size, since if the period size is bigger than the maximum allowed threshold, than the driver will switch to packet mode, and picks the best (biggest) threshold value, which can divide evenly the period size. Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Jarkko Nikula <jhnikula@gmail.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Peter Ujfalusi authored
To make the code a bit more readable, change the indexed references to the omap_mcbsp_dai_dma_params elements with pointer. Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Jarkko Nikula <jhnikula@gmail.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Peter Ujfalusi authored
In preparation for the extended threshold mode (sDMA packet mode support), the code need to be restructured. Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Jarkko Nikula <jhnikula@gmail.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
- Jul 30, 2010
-
-
Kuninori Morimoto authored
Signed-off-by:
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Kuninori Morimoto authored
Current FSI driver id is not only 0 Signed-off-by:
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Kuninori Morimoto authored
Signed-off-by:
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
- Jul 29, 2010
-
-
Peter Ujfalusi authored
Platform parameter to enable automatic FIFO configuration when the codec is in Mode1 or Mode7 FIFO mode. When this mode is selected, the controls for changing nSample (in Mode1), and UTHR (in Mode7) are not added. The driver configures the FIFO configuration based on the stream's period size in a way, that every burst will read period size of data from the host. In Mode7 we need to use a formula, which gives close enough aproximation for the burst length from the host point of view. Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Peter Ujfalusi authored
Replace the hardwired latency definition with platform data parameter, and simplify the nSample parameter calculation. Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
- Jul 27, 2010
-
-
Peter Ujfalusi authored
There is no need to handle POST_PMU, POST_PMD event with the Capture Route widget. It is enough to handle POST_REG event, since that will come when the user changes the routing, and we will switch the needed bits in the registers. Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
- Jul 23, 2010
-
-
Kuninori Morimoto authored
HeadPhone Playback Volume control register of DA7210 has reserved area. This patch considered it as mute. Signed-off-by:
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
- Jul 21, 2010
-
-
Takashi Iwai authored
Merge branch 'for-2.6.36' of git://git.kernel.org/pub/scm/linux/kernel/git/lrg/asoc-2.6 into topic/asoc
-
Peter Ujfalusi authored
When digital microphones are connected to twl, delay is needed after enabling the digimic interface of the codec. Add new parameter for the setup data, which can be used to pass the apropriate delay in ms after the digimic interface has been enabled. Without certain delay (in certain HW configuration) the beggining of the recorded sample contains a glitch, which is generated by the digital microphones. Delaying the micbias1, 2 (which is the bias for the digimic0 or 1) does not help, since the glitch is coming after switching the digimic interface. Reversing the micbias and digimic enable order does not work either (in that case the wait need to be added after the micbias enabled). Signed-off-by:
Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
- Jul 20, 2010
-
-
Mark Brown authored
AIF1ADC TDM mode has no effect other than causing the ADCDAT line to be tristated rather than driven low on clock cycles where there is no data to be transmitted. If the clock cycle is idle then there should be no devices using the data so tristating should have no adverse effects. Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Sekhar Nori authored
Currently the EDMA queue to be used by for servicing ASP through internal RAM is fixed to EDMAQ_0 and that to service internal RAM from external RAM is fixed to EDMAQ_1. This may not be the desirable configuration on all platforms. For example, on DM365, queue 0 has large fifo size and is more suitable for video transfers. Having audio and video transfers on the same queue may lead to starvation on audio side. platform data as defined currently passes a queue number to the driver but that remains unused inside the driver. Fix this by defining one queue each for ASP and RAM transfers in the platform data and using it inside the driver. Since EDMAQ_0 maps to 0, thats the queue that will be used if the asp queue number is not initialized. None of the platforms currently utilize ping-pong transfers through internal RAM so that functionality remains unchanged too. This patch has been tested on DM644x and OMAP-L138 EVMs. Signed-off-by:
Sekhar Nori <nsekhar@ti.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Chanwoo Choi authored
This patch modify I2Sv2 driver to support Samsung SoC(S5PV210). Signed-off-by:
Chanwoo Choi <cw00.choi@samsung.com> Signed-off-by:
Joonyoung Shim <jy0922.shim@samsung.com> Signed-off-by:
Kyungmin Park <kyungmin.park@samsung.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Mark Brown authored
-
Chanwoo Choi authored
Otherwise all machine drivers need to do so. Signed-off-by:
Chanwoo Choi <cw00.choi@samsung.com> Signed-off-by:
Joonyoung Shim <jy0922.shim@samsung.com> Signed-off-by:
Kyungmin Park <kyungmin.park@samsung.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Mark Brown authored
Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Mark Brown authored
Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Eric Bénard authored
Signed-off-by:
Eric Bénard <eric@eukrea.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
- Jul 18, 2010
-
-
Kulikov Vasiliy authored
If kzalloc() fails we must exit with -ENOMEM. Also we must free allocated runtime->private_data on error as it would be lost on next call to snd_imx_open(). Signed-off-by:
Kulikov Vasiliy <segooon@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Kulikov Vasiliy authored
If kzalloc() fails we must exit with -ENOMEM. Also we must free allocated runtime->private_data on error as it would be lost on next call to snd_imx_open(). Signed-off-by:
Kulikov Vasiliy <segooon@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Kulikov Vasiliy authored
The code checks 'davinci_vc' after kzalloc() and do not checks 'davinci_vcif_dev' that kzalloc() result is assigned to. It seems that it is a typo (autocompletion?). Signed-off-by:
Kulikov Vasiliy <segooon@gmail.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Kuninori Morimoto authored
Specified ID is necessary, when some codecs are used with FSI. Signed-off-by:
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com>
-
Mark Brown authored
-
Mark Brown authored
Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by:
Liam Girdwood <lrg@slimlogic.co.uk> Cc: stable@kernel.org
-