summaryrefslogtreecommitdiffstats
path: root/sound/soc/soc-pcm.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* ASoC: soc-pcm: Merge for_each_rtd_cpu/codec_dais()Kuninori Morimoto2020-03-201-236/+75
| | | | | | | | | | | Now we can use for_each_rtd_dais(). Let's use it instead of for_each_rtd_cpu/codec_dais(). Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87sgi8olet.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: export DPCM runtime update functionsGuennadi Liakhovetski2020-03-121-1/+4
| | | | | | | | | | | | | This makes DPCM runtime update functions available for external calling. As an example, virtualised ASoC component drivers may need to call these when managing shared DAPM routes that are used by more than one driver (i.e. when host driver and guest drivers have a DAPM path from guest PCM to host DAI where some parts are owned by host driver and others by guest driver). Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com> Link: https://lore.kernel.org/r/20200312095214.15126-3-guennadi.liakhovetski@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: (cosmetic) simplify dpcm_prune_paths()Guennadi Liakhovetski2020-03-121-31/+32
| | | | | | | | | | | Currently dpcm_prune_paths() has up to 4 nested condition and loop levels, which forces the code to use flags for flow control. Extracting widget status verification code from dpcm_prune_paths() into a separate function simplifies the code. Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com> Link: https://lore.kernel.org/r/20200312095214.15126-2-guennadi.liakhovetski@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: pcm: Fix (again) possible buffer overflow in dpcm state sysfs outputTakashi Iwai2020-03-101-8/+8
| | | | | | | | | | | This is re-applying the fix that went into 5.6 (commit 6c89ffea60aa) as the changes were wiped out after merging the other code refactoring. Basically the same changes, just replacing the suspicious calls of snprintf() with scnprintf(). Signed-off-by: Takashi Iwai <tiwai@suse.de> Link: https://lore.kernel.org/r/20200310163625.10838-1-tiwai@suse.de Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: soc: use for_each_rtd_codecs/cpus_dai() macroKuninori Morimoto2020-03-101-62/+62
| | | | | | | | | | | | | | | | | | | | | | This patch switch to use plural form macro. - for_each_rtd_codec_dai() + for_each_rtd_codec_dais() - for_each_rtd_codec_dai_rollback() + for_each_rtd_codec_dais_rollback() - for_each_rtd_cpu_dai() + for_each_rtd_cpu_dais() - for_each_rtd_cpu_dai_rollback() + for_each_rtd_cpu_dais_rollback() Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87v9negogr.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* Merge series "ASoC: soc-pcm cleanup step5" from Kuninori Morimoto ↵Mark Brown2020-03-061-50/+47
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | <kuninori.morimoto.gx@renesas.com>: Hi Mark These are v2 resend of soc-pcm cleanup step5. 1) - 4) are rebased to latest for-5.7 branch. 5) - 6) are remaked of previous [6/8], [7/8] which were mistaken patch. Kuninori Morimoto (6): 1) ASoC: soc-pcm: move dpcm_fe_dai_close() 2) ASoC: soc-pcm: add dpcm_fe_dai_cleanup() 3) ASoC: soc-pcm: use snd_soc_dai_get_pcm_stream() at dpcm_set_fe_runtime() 4) ASoC: soc-pcm: tidyup dulicate handing at dpcm_fe_dai_startup() 5) ASoC: soc-pcm: check DAI's activity more simply 6) ASoC: soc-pcm: Do Digital Mute for both CPU/Codec in same timing. sound/soc/soc-pcm.c | 97 ++++++++++++++++++++++----------------------- 1 file changed, 47 insertions(+), 50 deletions(-) -- 2.17.1
| * ASoC: soc-pcm: Do Digital Mute for both CPU/Codec in same timing.Kuninori Morimoto2020-03-061-3/+8
| | | | | | | | | | | | | | | | | | | | | | | | Digital Mute for CPU is done at soc_pcm_close(), and Digital Mute for Codec is done at soc_pcm_hw_free(). It is just confusable. This patch do Digital Mute for both CPU/Codec in same timing. Then, it cares DAI activity Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87imjip9ty.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * ASoC: soc-pcm: check DAI's activity more simplyKuninori Morimoto2020-03-061-5/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | soc_pcm_hw_free() want to call snd_soc_dai_digital_mute() if it was last user of Playback or Capture. bool playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; int playback_active = dai->stream_active[SNDRV_PCM_STREAM_PLAYBACK]; int capture_active = dai->stream_active[SNDRV_PCM_STREAM_CAPTURE]; if ((playback && playback_active == 1) || (!playback && capture_active == 1)) snd_soc_dai_digital_mute(...) But it is same as int active = dai->stream_active[substream->stream]; if (active == 1) snd_soc_dai_digital_mute(...) This patch simplify the code. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87k13yp9ub.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * ASoC: soc-pcm: tidyup dulicate handing at dpcm_fe_dai_startup()Kuninori Morimoto2020-03-061-7/+3
| | | | | | | | | | | | | | | | | | | | | | error handling at dpcm_fe_dai_startup() has duplicate code. This patch tidyup it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87lfoep9ug.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * ASoC: soc-pcm: use snd_soc_dai_get_pcm_stream() at dpcm_set_fe_runtime()Kuninori Morimoto2020-03-061-6/+3
| | | | | | | | | | | | | | | | | | | | | | We already have snd_soc_dai_get_pcm_stream(), let's use it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87mu8up9ul.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * ASoC: soc-pcm: add dpcm_fe_dai_cleanup()Kuninori Morimoto2020-03-061-14/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | dpcm_fe_dai_close() and error case of dpcm_fe_dai_open() need to do same cleanup operation. To avoid duplicate code, this patch adds dpcm_fe_dai_cleanup() and use it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87o8tap9uq.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * ASoC: soc-pcm: move dpcm_fe_dai_close()Kuninori Morimoto2020-03-061-20/+20
| | | | | | | | | | | | | | | | | | | | | | move dpcm_fe_dai_close() next to dpcm_fe_dai_open(). This is prepare for dpcm_fe_dai_open() cleanup Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87pndqp9uv.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: pcm: Export parameter intersection logicSamuel Holland2020-03-061-18/+38
|/ | | | | | | | | | The logic to calculate the subset of stream parameters supported by all DAIs associated with a PCM stream is nontrivial. Export a helper function so it can be used to set up simple codec2codec DAI links. Signed-off-by: Samuel Holland <samuel@sholland.org> Link: https://lore.kernel.org/r/20200305051143.60691-3-samuel@sholland.org Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: soc-pcm: remove duplicate be check from dpcm_add_paths()Kuninori Morimoto2020-03-051-4/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dpcm_add_paths() checks returned be from dpcm_get_be() static int dpcm_add_paths(...) { ... for_each_dapm_widgets(list, i, widget) { ... be = dpcm_get_be(...); ... /* make sure BE is a real BE */ => if (!be->dai_link->no_pcm) continue; ... } ... } But, dpcm_get_be() itself is checking it already. dpcm_get_be(...) { ... for_each_card_rtds(card, be) { => if (!be->dai_link->no_pcm) continue; ... if (...) => return be; } return NULL } This patch removes duplicate check Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87lfoo7q1j.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: soc-pcm: use defined streamKuninori Morimoto2020-03-051-8/+7
| | | | | | | | | | | | Many functions defines "stream = substream->stream", but some of them is using "substream->stream" instead of "stream". It is pointless. This patch uses defined stream. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87mu947q1t.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: pcm: check if cpu-dai supports a given streamBard Liao2020-02-261-1/+50
| | | | | | | | | | Now multi-cpu-dais are supported, we can skip cpi-dais which don't support the current stream, following the example of multi-codec-dais. Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com> Link: https://lore.kernel.org/r/20200225133917.21314-7-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: Return error if the function does not support multi-cpuBard Liao2020-02-261-0/+18
| | | | | | | | | | | Multi cpu is not supported by all functions yet. Add an error message and return. Suggested-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com> Link: https://lore.kernel.org/r/20200225133917.21314-6-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org>
* ASoC: Add multiple CPU DAI support for PCM opsShreyas NC2020-02-261-135/+261
| | | | | | | | | | | | | | Add support in PCM operations to invoke multiple cpu dais as we do for multiple codec dais. Also the symmetry calculations are updated to reflect multiple cpu dais. Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com> Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Shreyas NC <shreyas.nc@intel.com> Signed-off-by: Vinod Koul <vkoul@kernel.org> Link: https://lore.kernel.org/r/20200225133917.21314-3-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org>
* Merge branch 'for-5.6' of ↵Mark Brown2020-02-241-1/+1
|\ | | | | | | https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into asoc-5.7
| * ASoC: soc-pcm/soc-compress: don't use snd_soc_dapm_stream_stop()Kuninori Morimoto2020-02-241-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit b0edff42360ab4 ("ASoC: soc-pcm/soc-compress: use snd_soc_dapm_stream_stop() for SND_SOC_DAPM_STREAM_STOP") uses snd_soc_dapm_stream_stop() for soc_compr_free_fe() and dpcm_fe_dai_shutdown() because it didn't care about pmdown_time. But, it didn't need to care. This patch rollback to original code. Some system will wait unneeded timed-out without this patch. Special Thanks for reporting to Chris Gorman. ... intel_sst_acpi 808622A8:00: Wait timed-out condition:0x0, msg_id:0x1 fw_state 0x3 intel_sst_acpi 808622A8:00: fw returned err -16 sst-mfld-platform sst-mfld-platform: ASoC: PRE_PMD: pcm0_in event failed: -16 ... Fixes: commit b0edff42360ab4 ("ASoC: soc-pcm/soc-compress: use snd_soc_dapm_stream_stop() for SND_SOC_DAPM_STREAM_STOP") Reported-by: Chris Gorman <chrisjohgorman@gmail.com> Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87lfowspeb.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * ASoC: pcm: Fix possible buffer overflow in dpcm state sysfs outputTakashi Iwai2020-02-191-8/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dpcm_show_state() invokes multiple snprintf() calls to concatenate formatted strings on the fixed size buffer. The usage of snprintf() is supposed for avoiding the buffer overflow, but it doesn't work as expected because snprintf() doesn't return the actual output size but the size to be written. Fix this bug by replacing all snprintf() calls with scnprintf() calls. Fixes: f86dcef87b77 ("ASoC: dpcm: Add debugFS support for DPCM") Signed-off-by: Takashi Iwai <tiwai@suse.de> Acked-by: Cezary Rojewski <cezary.rojewski@intel.com> Link: https://lore.kernel.org/r/20200218111737.14193-4-tiwai@suse.de Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm cleanup step4Mark Brown2020-02-241-253/+209
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Merge series from Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>: Hi Mark These are soc-pcm cleanup step4. [01/13] - [06/13] are posted but not yet accepted patches. To avoid conflict, I merged these into step4. These patches are already received Reviewed-by from Pierre-Louis. Subject: [PATCH 0/6] ASoC: use for_each_rtd_codec_dai() macro Date: Thu, 13 Feb 2020 13:08:07 +0900 Kuninori Morimoto (13): 1) ASoC: soundwaire: qcom: use for_each_rtd_codec_dai() macro 2) ASoC: qcom: sdm845: use for_each_rtd_codec_dai() macro 3) ASoC: qcom: apq8016_sbc: use for_each_rtd_codec_dai() macro 4) ASoC: intel: cml_rt1011_rt5682: use for_each_rtd_codec_dai() macro 5) ASoC: intel: kbl_da7219_max98927: use for_each_rtd_codec_dai() macro 6) ASoC: mediatek: mt8183-da7219-max98357: use for_each_rtd_codec_dai() macro 7) ASoC: soc-pcm: add snd_soc_dai_get_pcm_stream() 8) ASoC: soc-pcm: cleanup soc_pcm_apply_msb() 9) ASoC: soc-pcm: add snd_soc_dai_get_widget() 10) ASoC: soc-pcm: merge dpcm_run_new/old_update() into dpcm_fe_runtime_update() 11) ASoC: soc-pcm: move dpcm_path_put() to soc-pcm.c 12) ASoC: soc-pcm: move CONFIG_DEBUG_FS functions to top side 13) ASoC: soc-pcm: add dpcm_create/remove_debugfs_state() drivers/soundwire/qcom.c | 7 +- include/sound/soc-dai.h | 15 + include/sound/soc-dapm.h | 1 + include/sound/soc-dpcm.h | 7 +- sound/soc/intel/boards/cml_rt1011_rt5682.c | 3 +- sound/soc/intel/boards/kbl_da7219_max98927.c | 8 +- sound/soc/intel/skylake/skl-pcm.c | 10 +- .../mediatek/mt8183/mt8183-da7219-max98357.c | 8 +- sound/soc/qcom/apq8016_sbc.c | 7 +- sound/soc/qcom/sdm845.c | 20 +- sound/soc/soc-dai.c | 7 +- sound/soc/soc-dapm.c | 20 +- sound/soc/soc-pcm.c | 462 ++++++++---------- 13 files changed, 266 insertions(+), 309 deletions(-) -- 2.17.1 Thank you for your help !! Best regards --- Kuninori Morimoto
| * | ASoC: soc-pcm: add dpcm_create/remove_debugfs_state()Kuninori Morimoto2020-02-241-17/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | soc-pcm.c has implementation which depends on CONFIG_DEBUG_FS. But, we don't want to have random #ifdef. This patch adds dpcm_create/remove_debugfs_state() and care it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/877e0jjc9b.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * | ASoC: soc-pcm: move CONFIG_DEBUG_FS functions to top sideKuninori Morimoto2020-02-241-138/+138
| | | | | | | | | | | | | | | | | | | | | | | | This is prepare for CONFIG_DEBUG_FS cleanup Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/878skzjc9k.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * | ASoC: soc-pcm: move dpcm_path_put() to soc-pcm.cKuninori Morimoto2020-02-241-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dpcm_path_put() (A) is calling kfree(*list). The freed list is created by dapm_widget_list_create() (B) which is called from snd_soc_dapm_dai_get_connected_widgets() (C) which is called from dpcm_path_get() (D). (B) dapm_widget_list_create(**list, ...) { ... => *list = kzalloc(); ... } (C) snd_soc_dapm_dai_get_connected_widgets(..., **list, ...) { ... dapm_widget_list_create(list, ...); ... } (D) dpcm_path_get(..., **list) { ... snd_soc_dapm_dai_get_connected_widgets(..., list, ...); ... } (A) dpcm_path_put(**list) { => kfree(*list); } This kind of unbalance code is very difficult to read/understand. To avoid this issue, this patch adds each missing paired function dapm_widget_list_free() for dapm_widget_list_create() (B), and snd_soc_dapm_dai_free_widgets() for snd_soc_dapm_dai_get_connected_widgets() (C). This patch uses these, and moves dpcm_path_put() next to dpcm_path_get(). Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87a75fjc9q.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * | ASoC: soc-pcm: merge dpcm_run_new/old_update() into dpcm_fe_runtime_update()Kuninori Morimoto2020-02-241-28/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | soc-pcm has dpcm_run_new/old_update(), but these are used from dpcm_fe_runtime_update() only, and are very verbose functions. This patch disassembles these. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87blpvjc9v.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * | ASoC: soc-pcm: add snd_soc_dai_get_widget()Kuninori Morimoto2020-02-241-13/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | soc-pcm.c has dai_get_widget(), but it can be more generic. This patch renames it to snd_soc_dai_get_widget(), and use it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87d0abjca1.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * | ASoC: soc-pcm: cleanup soc_pcm_apply_msb()Kuninori Morimoto2020-02-241-17/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | soc_pcm_apply_msb() apply msb for CPU/Codec, but, it has duplicate code. The difference is only SNDRV_PCM_STREAM_PLAYBACK and SNDRV_PCM_STEAM_CAPTURE. It is very verbose and duplicate code. This patch simplify code by using snd_soc_dai_get_pcm_stream(). Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87eeurjca6.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
| * | ASoC: soc-pcm: add snd_soc_dai_get_pcm_stream()Kuninori Morimoto2020-02-241-40/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | DAI driver has playback/capture stream. OTOH, we have SNDRV_PCM_STREAM_PLAYBACK/CAPTURE. Because of this kind of implementation, ALSA SoC needs to have many verbose code. To solve this issue, this patch adds snd_soc_dai_get_pcm_stream() macro to get playback/capture stream pointer from stream. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/87ftf7jcab.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | | ASoC: soc-pcm: fix state tracking error in snd_soc_component_open/close()Kai Vehmanen2020-02-241-6/+21
|/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ASoC component open/close and snd_soc_component_module_get/put are called independently for each component-substream pair, so the logic added in commit dd03907bf129 ("ASoC: soc-pcm: call snd_soc_component_open/close() once") was not sufficient and led to PCM playback and module unload errors. Implement handling of failures directly in soc_pcm_components_open(), so that any successfully opened components are closed upon error with other components. This allows to clean up error handling in soc_pcm_open() without adding more state tracking. Fixes: dd03907bf129 ("ASoC: soc-pcm: call snd_soc_component_open/close() once") Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com> Tested-by: Dmitry Osipenko <digetx@gmail.com> Link: https://lore.kernel.org/r/20200220094955.16968-1-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: dpcm: remove confusing trace in dpcm_get_be()Jerome Brunet2020-02-201-3/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Now that dpcm_get_be() is used in dpcm_end_walk_at_be(), it is not a error if this function does not find a BE for the provided widget. Remove the related dev_err() trace which is confusing since things might be working as expected. When called from dpcm_add_paths(), it is an error if dpcm_get_be() fails to find a BE for the provided widget. The necessary error trace is already done in this case. Fixes: 027a48387183 ("ASoC: soc-pcm: use dpcm_get_be() at dpcm_end_walk_at_be()") Signed-off-by: Jerome Brunet <jbrunet@baylibre.com> Tested-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Cc: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/20200219115048.934678-1-jbrunet@baylibre.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: use for_each_pcm_streams() macroKuninori Morimoto2020-02-191-62/+35
| | | | | | | | | | | | | | | | Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/871rqtboth.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: merge playback/cature_active into stream_activeKuninori Morimoto2020-02-191-13/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | DAI has playback_active and capture_active to care usage count. OTOH, we have SNDRV_PCM_STREAM_PLAYBACK/CAPTURE. But because of this kind of implementation mismatch, ALSA SoC has many verbose code. To solve this issue, this patch merge playback_active/capture_active into stream_active[2]; Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/875zg5botu.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: use goto and remove multi returnKuninori Morimoto2020-02-191-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | When we use some kind of lock, we need to do unlock. In that time, multi unlock/return is not good implementation. This patch add label and use goto at dpcm_fe_dai_open() to reduce such code. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/877e0lboty.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: add snd_soc_dpcm_can_be() and remove duplicate codeKuninori Morimoto2020-02-191-35/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Below functions are doing very similar things, the difference is used state only. snd_soc_dpcm_can_be_free_stop() snd_soc_dpcm_can_be_params() This patch adds common snd_soc_dpcm_check_state(), and use it from snd_soc_dpcm_can_be_free_stop() / snd_soc_dpcm_can_be_params(). It can reduce duplicate code. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/878sl1bou2.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: remove snd_soc_dpcm_be_get/set_state()Kuninori Morimoto2020-02-191-16/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | No one is using snd_soc_dpcm_be_get/set_state(). If it exists only by assumption that "it may be necessary someday", let's remove it now. Otherwise code maintenance will be difficult. We can revive it when we really needed it. Let's remove it, so far. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87a75hbou7.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: remove soc_dpcm_be_digital_mute()Kuninori Morimoto2020-02-191-27/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | No one is using soc_dpcm_be_digital_mute(). If it exists only by assumption that "it may be necessary someday", let's remove it now. Otherwise code maintenance will be difficult. We can revive it when we really needed it. Let's remove it, so far. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87blpxbouc.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: use dpcm_get_be() at dpcm_end_walk_at_be()Kuninori Morimoto2020-02-191-17/+3
| | | | | | | | | | | | | | | | | | | | | | dpcm_end_walk_at_be() and dpcm_get_be() are almost same code. This patch uses dpcm_get_be() from dpcm_end_walk_at_be(). Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87d0adbouh.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: use dai_get_widget() at dpcm_end_walk_at_be()Kuninori Morimoto2020-02-191-21/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dpcm_end_walk_at_be() has very duplicate code. dpcm_end_walk_at_be() { ... if (stream == SNDRV_PCM_STREAM_PLAYBACK) { (1) /* code for Playback */ } else { (2) /* code for Capture */ } } The difference between Playback (1) and Capture (2) code is pointer only (= "playback_widget" or "caputre_widget"). OTOH, now we already has dai_get_widget() for it. This means we can merge (1) and (2). This patch do it and remove duplicated code. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87eeutboul.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: use dai_get_widget() at dpcm_get_be()Kuninori Morimoto2020-02-191-29/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dpcm_get_be() has very duplicate code. dpcm_get_be() { ... if (stream == SNDRV_PCM_STREAM_PLAYBACK) { (1) /* code for Playback */ } else { (2) /* code for Capture */ } } The difference between Playback (1) and Capture (2) code is pointer only (= "playback_widget" or "caputre_widget"). OTOH, now we already has dai_get_widget() for it. This means we can merge (1) and (2). This patch do it and remove duplicated code. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87ftf9bouq.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: move dai_get_widget()Kuninori Morimoto2020-02-191-9/+9
| | | | | | | | | | | | | | | | | | | | | | This patch moves dai_get_widget() to top side. This is prepare for cleanup soc-pcm.c Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/87h7zpbouu.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: fix regression in soc_new_pcm()Stephan Gerhold2020-02-181-9/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit af4bac11531f ("ASoC: soc-pcm: crash in snd_soc_dapm_new_dai") swapped the SNDRV_PCM_STREAM_* parameter in the snd_soc_dai_stream_valid(cpu_dai, ...) checks. But that works only for codec2codec links. For normal links it breaks registration of playback/capture-only PCM devices. E.g. on qcom/apq8016_sbc there is usually one playback-only and one capture-only PCM device, but they disappeared after the commit. The codec2codec case was added in commit a342031cdd08 ("ASoC: create pcm for codec2codec links as well") as an extra check (e.g. `playback = playback && cpu_playback->channels_min`). We should be able to simplify the code by checking directly for the correct stream type in the loop. This also fixes the regression because we check for PLAYBACK for both codec and cpu dai again when codec2codec is not used. Fixes: af4bac11531f ("ASoC: soc-pcm: crash in snd_soc_dapm_new_dai") Signed-off-by: Stephan Gerhold <stephan@gerhold.net> Tested-by: Jerome Brunet <jbrunet@baylibre.com> Reviewed-by: Jerome Brunet <jbrunet@baylibre.com> Cc: Jerome Brunet <jbrunet@baylibre.com> Cc: Sameer Pujar <spujar@nvidia.com> Link: https://lore.kernel.org/r/20200218103824.26708-1-stephan@gerhold.net Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: tidyup soc_pcm_open() orderKuninori Morimoto2020-02-131-18/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | soc_pcm_open() operation order is not good. At first, soc_pcm_open() operation order is 1) CPU DAI startup 2) Component open 3) Codec DAI startup 4) rtd startup But here, 2) will call try_module_get() if component has module_get_upon_open flags. This means 1) CPU DAI startup will be operated *before* its module was loaded. DAI should be called *after* Component. Second, soc_pcm_close() operation order is 1) CPU DAI shutdown 2) Codec DAI shutdown 3) rtd shutdown 4) Component close soc_pcm_open() and soc_pcm_close() are paired function, but, its operation order is unbalance. This patch tidyup soc_pcm_open() order to Component -> rtd -> DAI. This is one of prepare for cleanup soc-pcm-open() Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/871rr3cext.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: move soc_pcm_close() next to soc_pcm_open()Kuninori Morimoto2020-02-131-44/+44
| | | | | | | | | | | | | | | | | | | | This patch moves soc_pcm_close() next to soc_pcm_open(). This is prepare for soc_pcm_open() cleanup. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/8736bjcexx.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: call snd_soc_component_open/close() onceKuninori Morimoto2020-02-131-13/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Current soc_pcm_open() calls snd_soc_component_open() under loop. Thus, it needs to care about opened/not-yet-opened Component. But, if soc-component.c is handling it, soc-pcm.c don't need to care about it. This patch adds opened flag to soc-component.h, and simplify soc-pcm.c. This is one of prepare for cleanup soc-pcm-open() Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/874kvzcey1.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: call snd_soc_dai_startup()/shutdown() onceKuninori Morimoto2020-02-111-5/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Current soc_pcm_open() calls snd_soc_dai_startup() under loop. Thus, it needs to care about started/not-yet-started codec DAI. But, if soc-dai.c is handling it, soc-pcm.c don't need to care about it. This patch adds started flag to soc-dai.h, and simplify soc-pcm.c. This is one of prepare for cleanup soc-pcm-open() Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/875zgfcey5.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: don't use bit-OR'ed errorKuninori Morimoto2020-02-111-4/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Current soc-pcm is using bit-OR'ed error ret |= snd_soc_component_close(component, substream); ret |= snd_soc_component_hw_free(component, substream); The driver may return arbitrary error codes so they can conflict. The bit-OR'ed error works only if the return code is always consistent. This patch fixup it, and use *last* ret value. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Link: https://lore.kernel.org/r/877e0vceyc.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: add for_each_dapm_widgets() macroKuninori Morimoto2020-02-111-8/+9
| | | | | | | | | | | | | | | | | | This patch adds new for_each_dapm_widgets() macro and use it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/878slbceyg.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: adjustment for DAI member 0 resetKuninori Morimoto2020-02-111-9/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit 3635bf09a89cf ("ASoC: soc-pcm: add symmetry for channels and sample bits") set 0 not only to dai->rate but also to dai->channels and dai->sample_bits if DAI was not active at soc_pcm_close(). and commit d3383420c969c ("ASoC: soc-pcm: move DAIs parameters cleaning into hw_free()") moved it from soc_pcm_close() to soc_pcm_hw_free(). These happen at v3.14. But, maybe because of branch merge conflict or something similar happen then, soc_pcm_close() still has old settings (care only dai->rate, doesn't care dai->channels/sample_bits). This is 100% duplicated operation. This patch removes soc_pcm_close() side operation which supposed to already moved to soc_pcm_hw_free(). Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87a75rceyl.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
* | ASoC: soc-pcm: add snd_soc_runtime_action()Kuninori Morimoto2020-02-111-41/+26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | ALSA SoC has snd_soc_runtime_activate() / snd_soc_runtime_deactivate(). These increment or decrement DAI/Component activity, but the code difference is only +1 or -1. This patch adds common snd_soc_runtime_action() which can get +1 or -1 as parameter, and use it from snd_soc_runtime_activate/deactivate() to avoid duplicate implementation. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Link: https://lore.kernel.org/r/87blq7ceyq.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>