Hi,
This series adds missing hardware reset controls to I2S and AC97 drivers,
corrects runtime PM usage and drivers probe/remove order. Currently drivers
happen to work properly because reset is implicitly deasserted by tegra-clk
driver, but clk driver shouldn't touch the resets and we need to fix it
because this breaks other Tegra drivers. Previously we fixed the resets of
the AHUB and HDMI codec drivers, but turned out that we missed the I2C and
AC97 drivers.
Thanks to Paul Fertser for testing the pending clk patches and finding
that audio got broken on Tegra20 AC100 netbook because of the missing I2S
reset.
Changelog:
v5: - After taking another look at the drivers I noticed couple more
things that could be improved. These new patches correct runtime PM
and probe/remove order of the drivers:
ASoC: tegra20: spdif: Correct driver removal order
ASoC: tegra20: spdif: Remove handing of disabled runtime PM
ASoC: tegra20: i2s: Add system level suspend-resume callbacks
ASoC: tegra20: i2s: Correct driver removal order
ASoC: tegra20: i2s: Use devm_clk_get()
ASoC: tegra20: i2s: Remove handing of disabled runtime PM
ASoC: tegra30: i2s: Correct driver removal order
ASoC: tegra30: i2s: Use devm_clk_get()
ASoC: tegra30: i2s: Remove handing of disabled runtime PM
ASoC: tegra30: ahub: Reset global variable
ASoC: tegra30: ahub: Correct suspend-resume callbacks
ASoC: tegra30: ahub: Remove handing of disabled runtime PM
v4: - Added missing prototype for reset_control_bulk_put().
v3: - Fixed reset stubs for !CONFIG_RESET_CONTROLLER.
v2: - After some more testing I found that I2S control logic doesn't require
I2S clock to be enabled for resetting. Hence it's fine to have I2S to
be reset by parent AHUB driver, so I dropped "tegra30: i2s: Add reset
control" patch.
- While I was double-checking resets on Tegra30, I found that that
Tegra30 I2S driver has a broken runtime PM which doesn't restore
hardware state on resume and it's lost after AHUB RPM-resume.
Thus, added this new patch "tegra30: i2s: Restore hardware state
on runtime PM resume".
- Added new patches which switch AHUB driver to use reset-bulk API.
I took the RFC patch from Philipp Zabel, fixed it and added
devm_reset_control_bulk_optional_get_exclusive_released() that
will be useful for further Tegra GPU patches. This is a minor
improvement which makes code cleaner.
Dmitry Osipenko (16):
ASoC: tegra20: ac97: Add reset control
ASoC: tegra20: i2s: Add reset control
ASoC: tegra30: i2s: Restore hardware state on runtime PM resume
ASoC: tegra30: ahub: Switch to use reset-bulk API
ASoC: tegra20: spdif: Correct driver removal order
ASoC: tegra20: spdif: Remove handing of disabled runtime PM
ASoC: tegra20: i2s: Add system level suspend-resume callbacks
ASoC: tegra20: i2s: Correct driver removal order
ASoC: tegra20: i2s: Use devm_clk_get()
ASoC: tegra20: i2s: Remove handing of disabled runtime PM
ASoC: tegra30: i2s: Correct driver removal order
ASoC: tegra30: i2s: Use devm_clk_get()
ASoC: tegra30: i2s: Remove handing of disabled runtime PM
ASoC: tegra30: ahub: Reset global variable
ASoC: tegra30: ahub: Correct suspend-resume callbacks
ASoC: tegra30: ahub: Remove handing of disabled runtime PM
Philipp Zabel (1):
reset: Add reset_control_bulk API
drivers/reset/core.c | 215 ++++++++++++++++++++++
include/linux/reset.h | 315 ++++++++++++++++++++++++++++++++
sound/soc/tegra/tegra20_ac97.c | 21 +++
sound/soc/tegra/tegra20_ac97.h | 1 +
sound/soc/tegra/tegra20_i2s.c | 60 +++---
sound/soc/tegra/tegra20_i2s.h | 1 +
sound/soc/tegra/tegra20_spdif.c | 16 +-
sound/soc/tegra/tegra30_ahub.c | 168 ++++++-----------
sound/soc/tegra/tegra30_ahub.h | 5 +-
sound/soc/tegra/tegra30_i2s.c | 65 ++-----
10 files changed, 667 insertions(+), 200 deletions(-)
--
2.30.2
base-commit: a38fd87484
This patch adds jsl_rt5682_rt1015p which supports the RT5682 headset
codec and ALC1015Q-VB speaker amplifier combination on JasperLake
platform.
This driver also supports ALC1015Q-CG if running in auto-mode.
Following table shows the audio interface support of the two
amplifiers.
| ALC1015Q-CG | ALC1015Q-VB
=====================================
I2C | Yes | No
Auto-mode | 48K, 64fs | 16k, 32fs
| 48k, 32fs
| 48k, 64fs
Signed-off-by: Brent Lu <brent.lu@intel.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210317110824.20814-1-brent.lu@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
sound/soc/intel/skylake/skl-topology.c:3613:13: warning: stack frame
size of 1304 bytes in function 'skl_tplg_complete'
[-Wframe-larger-than=]
struct snd_ctl_elem_value is 1224 bytes in my configuration.
Heap allocate it, then free it within the current frame.
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Nick Desaulniers <nick.desaulniers@gmail.com>
Link: https://lore.kernel.org/r/20210315013908.217219-1-nick.desaulniers@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Runtime PM is always available on Tegra since commit 40b2bb1b13
("ARM: tegra: enforce PM requirement"), hence there is no need to
handle the case of a disabled RPM by Tegra drivers. Remove handing
of a disabled runtime PM from Tegra30 AHUB driver.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-18-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra30 AHUB driver always syncs hardware state on a runtime PM resume,
hence there is no needed to re-sync the state on system resume. Replace
the suspend-resume callbacks with a generic helpers which ensure that
AHUB is suspended using RPM callbacks across system suspend-resume.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-17-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra30 AHUB uses global variable that is never reset by the driver on
a probe failure and on driver removal, meaning that driver will never try
to re-probe and can't be unbound. Make driver to reset the variable.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-16-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Runtime PM is always available on Tegra since commit 40b2bb1b13
("ARM: tegra: enforce PM requirement"), hence there is no need to
handle the case of a disabled RPM by Tegra drivers. Remove handing
of a disabled runtime PM from Tegra30 I2S driver.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-15-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra30 I2S driver has a wrong driver removal order, which should be
opposite to the registration order, but it's not. In particular the
runtime PM is disabled in a wrong order. Fix the order.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-13-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Runtime PM is always available on Tegra since commit 40b2bb1b13
("ARM: tegra: enforce PM requirement"), hence there is no need to
handle the case of a disabled RPM by Tegra drivers. Remove handing
of a disabled runtime PM from Tegra20 I2S driver.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-12-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra20 I2S driver has a wrong driver removal order, which should be
opposite to the registration order, but it's not. In particular the
runtime PM is disabled in a wrong order. Fix the order.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-10-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Add system level suspend-resume callbacks in order to ensure that I2S
is gated before system is suspended. This puts Tegra20 I2S driver on
par with the Tegra30 I2S driver.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-9-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Runtime PM is always available on Tegra since commit 40b2bb1b13
("ARM: tegra: enforce PM requirement"), hence there is no need to
handle the case of a disabled RPM by Tegra drivers. Remove handing
of a disabled runtime PM from Tegra20 SPDIF driver.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-8-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra20 SPDIF driver has a wrong driver removal order, which should be
opposite to the registration order, but it's not. In particular the
runtime PM is disabled in a wrong order. Fix the order.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-7-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Follow the clock and regulator subsystems' lead and add a bulk API
for reset controls.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-5-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra30 I2S driver syncs regmap cache only on resume from system suspend,
but hardware is reset across the runtime suspend because RPM of the parent
AHUB driver resets the I2S hardware, hence h/w state is lost after each
RPM resume. The problem isn't visible because hardware happens to be fully
reprogrammed after each RPM resume. Move hardware syncing to RPM resume in
order to restore h/w state properly.
Fixes: ed9ce1ed22 ("ASoC: tegra: ahub: Reset hardware properly")
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-4-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
The I2S reset may be asserted at a boot time, in particular this is the
case on Tegra20 AC100 netbook. Tegra20 I2S driver doesn't manage the
reset control and currently it happens to work because reset is implicitly
deasserted by the tegra-clk driver when I2S clock is enabled. The I2S
permanently stays in a reset once tegra-clk is fixed to not touch the
resets, which it shouldn't be doing. Add reset control to the Tegra20
I2S driver.
Note that I2S reset was always specified in Tegra20 device-tree, hence
DTB ABI changes aren't required.
Tested-by: Paul Fertser <fercerpav@gmail.com> # T20 AC100
Reported-by: Paul Fertser <fercerpav@gmail.com>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-3-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Tegra20 AC97 driver doesn't manage the AC97 controller reset, relying on
implicit deassertion of the reset by tegra-clk driver, which needs to be
fixed since this behaviour is unacceptable by other Tegra drivers. Add
explicit reset control to the Tegra20 AC97 driver.
Note that AC97 reset was always specified in Tegra20 device-tree, hence
DTB ABI changes aren't required.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210314154459.15375-2-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
./sound/soc/fsl/imx-hdmi.c:226:3-8: No need to set .owner here. The core
will do it.
Remove .owner field if calls are used which set it automatically
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Link: https://lore.kernel.org/r/1614848881-29637-1-git-send-email-yang.lee@linux.alibaba.com
Signed-off-by: Mark Brown <broonie@kernel.org>
snd_pcm_hw_params_set_rate_near can return incorrect sample rate in
some cases, e.g. when the backend output rate is set to some value higher
than 48000 Hz and the input rate is 8000 Hz. So passing the value returned
by snd_pcm_hw_params_set_rate_near to snd_pcm_hw_params will result in
"FSO/FSI ratio error" and playing no audio at all while the userland
is not properly notified about the issue.
If SRC is unable to convert the requested sample rate to the sample rate
the backend is using, then the requested sample rate should be adjusted in
rsnd_hw_params. The userland will be notified about that change in the
returned hw_params structure.
Signed-off-by: Mikhail Durnev <mikhail_durnev@mentor.com>
Link: https://lore.kernel.org/r/1615870055-13954-1-git-send-email-mikhail_durnev@mentor.com
Signed-off-by: Mark Brown <broonie@kernel.org>
i.MX has been converted to a devicetree-only platform and
asoc-mx27vis.h is no longer used.
Get rid of this unused file.
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Link: https://lore.kernel.org/r/20210315193842.183042-1-festevam@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
When reading from IPC flood debugfs entries no need to check whether
.cache_buf is NULL - it's impossible since otherwise the initialisation
would have failed. This also fixes a klocwork reported issue:
passed to function and may be dereferenced there by passing argument 2
to function 'memcpy' at line 510.
sound/soc/sof/debug.c:510 | sof_dfsentry_read()
Reported-by: Keqiao Zhang <keqiao.zhang@intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Xiuli Pan <xiulipan@outlook.com>
Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210315163932.18663-4-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
snd_sof_debugfs_buf_item() is an exported function and is called from
different locations to initialise different debugfs entries. However
.cache_buf is only needed for IPC flood entries. Limit allocations
respectively.
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Xiuli Pan <xiulipan@outlook.com>
Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210315163932.18663-3-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
If debugfs initialisation fails partially in sof_probe_continue() some
debugfs files and the root directory might have been created
successfully. They have to be cleaned up if some of them failed too.
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Xiuli Pan <xiulipan@outlook.com>
Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210315163932.18663-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Hi All,
Here is a resent of the remaining patches from my
"[PATCH 0/5] AsoC: rt5640/rt5651: Volume control fixes" series,
with the controversial "[PATCH 3/5] ASoC: rt5640: Add emulated
'DAC1 Playback Switch' control" patch dropped, and these
remaining 2 patches rebased to still apply with that patch dropped.
Regards,
Hans
Hans de Goede (2):
ASoC: rt5640: Rename 'Mono DAC Playback Volume' to 'DAC2 Playback
Volume'
ASoC: Intel: bytcr_rt5640: Add used AIF to the components string
sound/soc/codecs/rt5640.c | 6 +++---
sound/soc/intel/boards/bytcr_rt5640.c | 11 ++++++++---
2 files changed, 11 insertions(+), 6 deletions(-)
--
2.30.1
v4:
corrected Fixes tag
Added added Krzysztof Kozlowski's r-v-b tag
reverted patch2 to v2 since this is the agreement.
v3:
Added Sylwester tag
Rebased and squashed fix with initial patch which was merged at some
point but can't be found in broonie/for-next (not sure what happened?)
Corrected patch subjects to tm2_wm5110
Reverted second patch to initial v1, after agreement between Krzysztof
and Sylwester
v2:
added Krzysztof Kozlowski's tags
added fix for first patch already merged as suggested by Krzysztof Kozlowski
moved variable to lower scope in patch6
Pierre-Louis Bossart (2):
ASoC: samsung: tm2_wm5110: check of of_parse return value
ASoC: samsung: tm2_wm5110: remove shadowed variable
sound/soc/samsung/tm2_wm5110.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
--
2.25.1
Request dma channel from specific dma controller instead of generic
dma controller list, otherwise, may get the wrong dma controller
if there are multi dma controllers such as i.MX8MP.
Signed-off-by: Robin Gong <yibin.gong@nxp.com>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://lore.kernel.org/r/1614935977-21638-1-git-send-email-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Depending on which AIF is used the UCM profile needs to setup
a different path through the rt5640's "Digital Mixer Path" graph.
ATM the UCM profiles solve this by just enabling paths to the outputs /
from the input from both AIF1 and AIF2 and then relying on the DAPM
framework to power-down the parts of the graph connected to the
unused AIF.
But in order to be able to use hardware-volumecontrol and to use
the hardware mute controls, which are necessary for mute LED control,
the UCM profiles need to know which AIF is actually being used.
Add a new "aif:1" or "aif:2" part to the component string to provide
info about the used AIF to userspace / to the UCM profiles.
Note the size of byt_rt5640_components is not increased because the
size of 32 chars already is big enough.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210307150503.34906-3-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Rename 'Mono DAC Playback Volume' to 'DAC2 Playback Volume' and move it
from rt5640_specific_snd_controls[] to rt5640_snd_controls[].
The RT5640_DAC2_DIG_VOL register controlled by this mixer-element has
nothing to do with the Mono (Amplified) output which is only available
on the ALC5640 chip and not on the ALC5642 chip.
The RT5640_DAC2_DIG_VOL volume-control is the main volume control for
audio coming from the I2S2 / AIF2 input of the chip and as such is also
available on the ALC5642.
This commit results in the following userspace visible changes:
1. On devices with an ACL5640 codec, the 'Mono DAC Playback Volume'
control is renamed to 'DAC2 Playback Volume' allowing the alsa-lib
mixer code to properly group it with the 'DAC2 Playback Switch' which
is controlling the mute bits in the RT5640_DAC2_DIG_VOL register.
Note the removal of the 'Mono DAC Playback Volume' is not an issue for
userspace because the UCM profiles do not use it (the UCM profiles are
shared betweent the 5640 and 5642 and only the 5640 had this control).
2. On devices with an ACL5642 codec, there now will be a new
'DAC2 Playback Volume', grouped with the 'DAC2 Playback Switch'
Having a complete 'DAC2 Playback Volume' / 'DAC2 Playback Switch' pair
on both variants will allow enabling hardware-volume control by
setting the UCM PlaybackMasterElem to "DAC2" on devices where the
I2S2/AIF2 interface of the codec is used.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210307150503.34906-2-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
cppcheck warning:
sound/soc/samsung/tm2_wm5110.c:605:6: style: Variable 'ret' is
reassigned a value before the old one has been
used. [redundantAssignment]
ret = devm_snd_soc_register_component(dev, &tm2_component,
^
sound/soc/samsung/tm2_wm5110.c:554:7: note: ret is assigned
ret = of_parse_phandle_with_args(dev->of_node, "i2s-controller",
^
sound/soc/samsung/tm2_wm5110.c:605:6: note: ret is overwritten
ret = devm_snd_soc_register_component(dev, &tm2_component,
^
The args is a stack variable, so it could have junk (uninitialized)
therefore args.np could have a non-NULL and random value even though
property was missing. Later could trigger invalid pointer dereference.
There's no need to check for args.np because args.np won't be
initialized on errors.
Fixes: 8d1513cef5 ("ASoC: samsung: Add support for HDMI audio on TM2 board")
Cc: <stable@vger.kernel.org>
Suggested-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Reviewed-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210312180231.2741-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
The Asus T100TAF uses the same jack-detect settings as the T100TA,
this has been confirmed on actual hardware.
Add these settings to the T100TAF quirks to enable jack-detect support
on the T100TAF.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210312114850.13832-1-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Hi Mark
These are v2 of soc-pcm cleanup patches.
These has no relationship to each other.
My 1 concern is [3/8] patch. I think it is no problem,
but I'm not 100% sure why current code was such code.
Pierre-Louis / Liam might about something.
v1 -> v2
- soc_cpu/codec_dai_name() is now inline function
- rename soc_pcm_care_symmetry() to soc_pcm_update_symmetry()
v2 -> v3
- log fix at [6/8]
- Thus, it will be minus users at (2).
+ Thus, users will be a negative number at (2)
Link: https://lore.kernel.org/r/87tupuqqc8.wl-kuninori.morimoto.gx@renesas.com
Link: https://lore.kernel.org/r/87tupqpg9x.wl-kuninori.morimoto.gx@renesas.com
Kuninori Morimoto (8):
ASoC: soc-pcm: check DAI activity under soc_pcm_apply_symmetry()
ASoC: soc-pcm: add soc_cpu/codec_dai_name() macro
ASoC: soc-pcm: direct copy at snd_soc_set_runtime_hwparams()
ASoC: soc-pcm: add soc_pcm_update_symmetry()
ASoC: soc-pcm: add soc_hw_sanity_check()
ASoC: soc-pcm: fixup dpcm_be_dai_startup() user count
ASoC: soc-pcm: remove unneeded !rtd->dai_link check
ASoC: soc-pcm: share DPCM BE DAI stop operation
include/sound/soc-dpcm.h | 8 +-
sound/soc/soc-compress.c | 2 +-
sound/soc/soc-pcm.c | 243 ++++++++++++++++-----------------------
3 files changed, 105 insertions(+), 148 deletions(-)
--
2.25.1
cppcheck warning:
sound/soc/mediatek/mt8173/mt8173-afe-pcm.c:929:28: style: Local
variable 'irq' shadows outer argument [shadowArgument]
struct mtk_base_afe_irq *irq;
^
sound/soc/mediatek/mt8173/mt8173-afe-pcm.c:914:47: note: Shadowed
declaration
static irqreturn_t mt8173_afe_irq_handler(int irq, void *dev_id)
^
sound/soc/mediatek/mt8173/mt8173-afe-pcm.c:929:28: note: Shadow
variable
struct mtk_base_afe_irq *irq;
^
Not a great idea to have two 'irq' variables in the same function...
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210311004904.121205-5-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
cppcheck warning:
sound/soc/mediatek/common/mtk-btcvsd.c:783:34: style: Variable 'avail'
is assigned a value that is never used. [unreadVariable]
int written_size = count, avail = 0, cur_write_idx, write_size, cont;
^
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210311004904.121205-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
soc-pcm has very similar but different DPCM BE DAI stop operation at
1) dpcm_be_dai_startup() error case rollback
2) dpcm_be_dai_startup_unwind()
3) dpcm_be_dai_shutdown()
The differences are
1) for rollback
2) Doesn't check by snd_soc_dpcm_be_can_update() (Is this bug ?)
3) Do soc_pcm_hw_free() if it was not !OPENed and !HW_FREEed,
and call soc_pcm_close().
We can share same code by
1) hw_free is not needed. Needs last dpcm as rollback.
2) hw_free is not needed.
3) hw_free is needed.
This patch adds new dpcm_be_dai_stop() and share these 3.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87a6rduoam.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
rtd->dai_link is setuped at soc_new_pcm_runtime(),
thus "rtd->dai_link == NULL" is never happen.
This patch removes unneeded !rtd->dai_link check
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87blbtuoar.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
At dpcm_be_dai_startup_unwind(), it indicates error message at (1)
if this function was called with no users.
But, it doesn't use "continue" here. Thus, users will be a
negative number at (2)
void dpcm_be_dai_startup_unwind(...)
{
...
for_each_dpcm_be(...) {
...
(1) if (be->dpcm[stream].users == 0)
dev_err(...);
(2) if (--be->dpcm[stream].users != 0)
continue;
At dpcm_be_dai_startup(), it indicates error message if
user reached to MAX USERS at (A).
But, it doesn't use "continue" here. Thus, it will be over
MAX USERS at (B).
int dpcm_be_dai_startup(...)
{
...
for_each_dpcm_be(...) {
...
(A) if (be->dpcm[stream].users == DPCM_MAX_BE_USERS)
dev_err(...);
(B) if (be->dpcm[stream].users++ != 0)
continue;
These are just bug. This patch fixup these.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87czw9uoav.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Current soc_pcm_open() is checking runtime->hw parameters, but having
such function is very helpful for reading code.
This patch adds new soc_hw_sanity_check() and checks runtime->hw
parameters there. And print its debug message there, too.
Debug message print out timing is exchanged after this patch,
but it is not a big deal, because it is for debug.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87eegpuob1.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Current soc-pcm has soc_pcm_has_symmetry() and using it as
if (soc_pcm_has_symmetry(substream))
substream->runtime->hw.info |= SNDRV_PCM_INFO_JOINT_DUPLEX;
We want to share same operation as same function.
This patch adds soc_pcm_update_symmetry() and pack above code in
one function.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87ft15uob6.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
