In wm2000_i2c_probe(), if we take the true branch in

"
  ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_wm2000,
                               NULL, 0);
  if (ret != 0)
          goto err_fw;
"

then we'll release_firmware(fw) at the 'err_fw' label. But we've already
done that just a few lines above. That's a use-after-free bug.

This patch restructures the code so that we always call
release_firmware(fw) before leaving the function, but only ever call
it once.
This means that we have to initialize 'fw' to NULL since some paths
may now end up calling it without having called request_firmware(),
but since request_firmware() deals gracefully with NULL pointers, we
are fine if we just NULL initialize it.
Signed-off-by: NJesper Juhl <jj@chaosbits.net>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

To print a value of type size_t one should use %zd, not %d.
Signed-off-by: NJesper Juhl <jj@chaosbits.net>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

We should be allowing a 5ms delay after the charge pump is started in
order to ensure it has finished ramping.
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

On a mx28evk board the following errors happens on mxs-sgtl5000 probe:

[    0.660000] saif0_clk_set_rate: divider writing timeout
[    0.670000] mxs-sgtl5000: probe of mxs-sgtl5000.0 failed with error -110
[    0.670000] ALSA device list:
[    0.680000]   No soundcards found.

This timeout happens because clk_set_rate will result in writing to the DIV bits
of register HW_CLKCTRL_SAIF0 with the saif clock gated (CLKGATE bit set to one).

MX28 Reference states the following about CLKGATE:

"The DIV field can change ONLY when this clock gate bit field is low."

So call clk_prepare_enable prior to clk_set_rate to fix this problem.

After this change the mxs-saif driver can be correctly probed and audio is functional.
Signed-off-by: NFabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

With a low frequency SYSCLK and a fast I2C clock register synchronisation
may occasionally take too long to take effect, causing I/O issues. Disable
synchronisation in order to avoid any issues.
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

These are all to either uncached registers or fixes to register defaults,
in the former case the cache won't do anything and in the latter case
we're fixing things so the cache sync will do the right thing.
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

Writing to the registers won't work if we do actually manage to hit a fully
powered off state.
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

Register LDOCTLEN must always be initialized to clear the analog power
control bit, otherwise the analog block will stay deactivated.
Signed-off-by: NWolfram Sang <w.sang@pengutronix.de>
Acked-by: NJavier Martin <javier.martin@vista-silicon.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Dividers (such as MDAC) are always needed, independent of the codec
being I2S master or slave. Needed on a custom board where the codec has
to be slave.
Signed-off-by: NWolfram Sang <w.sang@pengutronix.de>
Acked-by: NJavier Martin <javier.martin@vista-silicon.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Correct SGTL5000_CHIP_CLK_CTRL to SGTL5000_CHIP_REF_CTRL in
sgtl5000_restore_regs(), and add comment to explain the
restore order.
Reported-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NZeng Zhaoming <zengzm.kernel@gmail.com>
Acked-by: NDong Aisheng <dong.aisheng@linaro.org>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Ensure the FLL is locked before we return from set_fll().
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Fix platform removal by freeing the platform DAPM resources and remove
it from the DAPM list.
Signed-off-by: NLiam Girdwood <lrg@ti.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Fixes a NULL pointer dereference in dapm_power_widgets() if the dapm context
has no codec.
Signed-off-by: NLiam Girdwood <lrg@ti.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Update MODULE_AUTHOR email address.
Signed-off-by: NZeng Zhaoming <zengzm.kernel@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

This change ensures the platform device name matches nuc900-ac97 platform
driver name.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NWan Zongshun <mcuos.com@gmail.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

"snd_imx_pcm_hw_params" callback can be called
several times by the user (i.e. OSS emulation)
leading to a DMA channel leak.
Signed-off-by: NJavier Martin <javier.martin@vista-silicon.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

The DL1 PDM interface adds a little gain depending on the output device.
Add a method to retrieve the gain value for machine driver usage.
Signed-off-by: NLiam Girdwood <lrg@ti.com>

The device model needs a release() function so it can free devices when
they become dereferenced.  Do that for rtds.
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

commit 739be96a "ASoC: Fix build dependency for SND_ATMEL_SOC_SSC"
introduces below build warnings:

drivers/misc/Kconfig:212:error: recursive dependency detected!
drivers/misc/Kconfig:212:       symbol ATMEL_SSC is selected by SND_ATMEL_SOC_SSC
sound/soc/atmel/Kconfig:9:      symbol SND_ATMEL_SOC_SSC is selected by SND_AT91_SOC_SAM9G20_WM8731
sound/soc/atmel/Kconfig:18:     symbol SND_AT91_SOC_SAM9G20_WM8731 depends on ATMEL_SSC

SND_ATMEL_SOC_SSC needs ATMEL_SSC to pass compilation.
This patch remove the "select ATMEL_SSC" from SND_ATMEL_SOC_SSC to avoid above
warnings. And then ensures all the machine drivers that select SND_ATMEL_SOC_SSC
need to depend on ATMEL_SSC.
Reported-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Now that a regulator device for controlling the codec chip reset state
over a platform agnostic regulator API is available on the only board
using this driver so far, extend the driver with a bias control function
which will request virtual power to the codec chip from that virtual
regulator, and will supersede the present implementation existing at the
sound card level.

Thanks to the regulator sharing mechanism, both the old (the sound card)
and the new (the codec) implementations should coexist smoothly until
the sound card file is updated. For this to work as expected, update the
sound card .set_bias_level callback to not touch codec->dapm.bias_level.

While extending the cx20442 structure, drop unused control_type member.

Created against linxu-3.2-rc6, tested on top of patch 1/4 "ARM: OMAP1:
ams-delta: set up a regulator over the modem reset GPIO pin".
Signed-off-by: NJanusz Krzysztofik <jkrzyszt@tis.icnet.pl>
Acked-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: NLiam Girdwood <lrg@ti.com>

Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

This is a follow up on 53dea36c which fixes the other affected
pcm engines.

Description from 53dea36c:
 Don't rely on the codec's channels_min information to decide wheter or
 not allocate a substream's DMA buffer. Rather check if the substream
 itself was allocated previously.

Without this patch I was seeing null-pointer dereferenc in atmel-pcm.
Signed-off-by: NJoachim Eastwood <joachim.eastwood@jotron.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Make SND_ATMEL_SOC_SSC select ATMEL_SSC to fix below build errors:

  LD      .tmp_vmlinux1
sound/built-in.o: In function `atmel_ssc_remove':
sound/soc/atmel/atmel_ssc_dai.c:713: undefined reference to `ssc_free'
sound/built-in.o: In function `atmel_ssc_probe':
sound/soc/atmel/atmel_ssc_dai.c:700: undefined reference to `ssc_request'
sound/built-in.o: In function `atmel_ssc_set_audio':
sound/soc/atmel/atmel_ssc_dai.c:845: undefined reference to `ssc_request'
sound/soc/atmel/atmel_ssc_dai.c:851: undefined reference to `ssc_free'
make: *** [.tmp_vmlinux1] Error 1
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

For a given ir and fs, there is at most one possible match for the case
mclk_ratios[ir][j].ratio * fs == freq.
Thus we can break from the inner loop once a match is found.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NJohannes Stezenbach <js@sig21.net>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

The original code does not cover the case that two DAIs(CPU) have different
ASoC core PCM operations(like mmap, pointer...). Currently we have only one
global soc_pcm_ops for ASoC core PCM operation. When two DAIs have different
pointer functions, second DAI's pointer function is set for both first DAI
and second DAI in case of original code.

This patch uses runtime's pcm_ops instead of global pcm_ops for each DAIs. So
each DAIs can have different ASoC core PCM operations. This is needed to
support multiple DAIs.
Signed-off-by: NSangsu Park <sangsu4u.park@samsung.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Use snd_soc_register_card() instead of creating a "soc-audio" platform device.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NHaojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

We can't just pass back the return value of snd_soc_update_bits() as it
will be 1 if a bit changed rather than zero.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NHaojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

We can't just pass back the return value of snd_soc_update_bits() as it
will be 1 if a bit changed rather than zero.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Also remove a unsued ret variable to silence the build warning.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Also remove a unused ret variable to silence the build warning.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NHaojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NHaojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Acked-by: NHaojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

We can't just pass back the return value of snd_soc_update_bits() as it
will be 1 if a bit changed rather than zero.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

We can't just pass back the return value of snd_soc_update_bits() as it
will be 1 if a bit changed rather than zero.
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

The various devm_ functions allocate memory that is released when a driver
detaches.  This patch uses devm_kzalloc, devm_request_mem_region and
devm_ioremap for data that is allocated in the probe function of a platform
device and is only freed in the remove function.
Signed-off-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

The various devm_ functions allocate memory that is released when a driver
detaches.  This patch uses devm_kzalloc, devm_request_mem_region and
devm_ioremap for data that is allocated in the probe function of a platform
device and is only freed in the remove function.
Signed-off-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>