February 2022 - Alsa-devel - mailman.alsa-project.org

[PATCH v2] soundwire: qcom: remove redundant wait for completion
by Srinivasa Rao Mandadapu 26 Feb '22

26 Feb '22

Remove wait_for_completion_timeout from soundwire probe as it seems unnecessary and device enumeration is anyway not happening here, hence this api is blocking till it completes max wait time. Also, as device enumeration event is dependent on wcd938x probe to be completed, its of no use waiting here. Waiting here increasing the boot time almost 4 seconds and impacting other modules like touch screen. Fixes: 06dd96738d618 ("soundwire: qcom: wait for enumeration to be complete in probe") Signed-off-by: Srinivasa Rao Mandadapu <quic_srivasam(a)quicinc.com> Co-developed-by: Venkata Prasad Potturu <quic_potturu(a)quicinc.com> Signed-off-by: Venkata Prasad Potturu <quic_potturu(a)quicinc.com> --- drivers/soundwire/qcom.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 5481341..9a32a24 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1309,8 +1309,6 @@ static int qcom_swrm_probe(struct platform_device *pdev) } qcom_swrm_init(ctrl); - wait_for_completion_timeout(&ctrl->enumeration, - msecs_to_jiffies(TIMEOUT_MS)); ret = qcom_swrm_register_dais(ctrl); if (ret) goto err_master_add; -- 2.7.4

3 5

[PATCH] "soundwire: qcom: revert wait for enumeration to be complete in probe"
by Srinivasa Rao Mandadapu 26 Feb '22

26 Feb '22

Revert wait for enumeration from soundwire probe as it seems unnecessary and device enumeration is anyway not happening here, hence this api is blocking till it completes max wait time. Also, as device enumeration event is dependent on wcd938x probe to be completed, its of no use waiting here. Waiting here increasing the boot time almost 4 seconds and impacting other modules like touch screen. Revert: commit 06dd96738d618 ("soundwire: qcom: wait for enumeration to be complete in probe") Signed-off-by: Srinivasa Rao Mandadapu <quic_srivasam(a)quicinc.com> Co-developed-by: Venkata Prasad Potturu <quic_potturu(a)quicinc.com> Signed-off-by: Venkata Prasad Potturu <quic_potturu(a)quicinc.com> --- drivers/soundwire/qcom.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 5481341..9eb31ba 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -133,7 +133,6 @@ struct qcom_swrm_ctrl { struct dentry *debugfs; #endif struct completion broadcast; - struct completion enumeration; struct work_struct slave_work; /* Port alloc/free lock */ struct mutex port_lock; @@ -486,7 +485,6 @@ static int qcom_swrm_enumerate(struct sdw_bus *bus) } } - complete(&ctrl->enumeration); return 0; } @@ -1262,7 +1260,6 @@ static int qcom_swrm_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, ctrl); mutex_init(&ctrl->port_lock); init_completion(&ctrl->broadcast); - init_completion(&ctrl->enumeration); ctrl->bus.ops = &qcom_swrm_ops; ctrl->bus.port_ops = &qcom_swrm_port_ops; @@ -1309,8 +1306,6 @@ static int qcom_swrm_probe(struct platform_device *pdev) } qcom_swrm_init(ctrl); - wait_for_completion_timeout(&ctrl->enumeration, - msecs_to_jiffies(TIMEOUT_MS)); ret = qcom_swrm_register_dais(ctrl); if (ret) goto err_master_add; -- 2.7.4

1 0

[RESEND v4 0/2] Add power domains support for digital macro codecs
by Srinivasa Rao Mandadapu 26 Feb '22

26 Feb '22

This patch set is to add power domains support for RX, TX and VA macros. Changes since v3: -- Add dt-bindings support. Changes since v2: -- Remove redundant local variable. -- Update pds error handling sequence. -- Update module description. -- Clean up pds init function. -- Remove redundant arguments. Changes since v1: -- Add missing macros in Kconfig. Srinivasa Rao Mandadapu (2): ASoC: codecs: Add power domains support in digital macro codecs ASoC: qcom: dt-bindings: Add bindings for power domains in lpass digital codecs .../bindings/sound/qcom,lpass-rx-macro.yaml | 8 +++ .../bindings/sound/qcom,lpass-tx-macro.yaml | 8 +++ .../bindings/sound/qcom,lpass-va-macro.yaml | 8 +++ sound/soc/codecs/Kconfig | 7 +++ sound/soc/codecs/Makefile | 2 + sound/soc/codecs/lpass-macro-common.c | 67 ++++++++++++++++++++++ sound/soc/codecs/lpass-macro-common.h | 17 ++++++ sound/soc/codecs/lpass-rx-macro.c | 12 +++- sound/soc/codecs/lpass-tx-macro.c | 10 ++++ sound/soc/codecs/lpass-va-macro.c | 12 ++++ sound/soc/qcom/Kconfig | 1 + 11 files changed, 151 insertions(+), 1 deletion(-) create mode 100644 sound/soc/codecs/lpass-macro-common.c create mode 100644 sound/soc/codecs/lpass-macro-common.h -- 2.7.4

1 2

Need help understanding DPCM
by Aidan MacDonald 25 Feb '22

25 Feb '22

Hi all. I want to extend an existing ASoC driver (jz4740-i2s) so it can be used with an external (discrete) codec; currently it is hardcoded to use a SoC internal codec. I'd like to be able to switch between the two codecs at runtime. Switching between the internal and external codecs is done by toggling a bit in a register. The switch determines where the I2S signals get routed: to the internal codec or the external one. Because of this only one of the codecs can be used at a time. It sounds like I need DPCM to handle this sort of thing - I have a single FIFO on the CPU for audio data (an FE DAI?) and it can connect to one of two codecs (the BE DAIs?) via a switch. But most of the drivers I see using DPCM look way more complicated: big DSP chips, and CPUs with a lot of DAIs. I am having a hard time separating out the essential bits from the overall "mess." The documentation is not very helpful either. Could someone helpfully explain what a (presumably) very basic DPCM setup for this situation would look like? Or is DPCM overkill - should I be doing something else entirely? I want to do this the "right" way so I can send patches upstream. If possible, I'd like to use one of the 'generic' audio card drivers like simple-audio-card. BTW, what is the difference between simple-audio-card, audio-graph-card, and audio-graph-card2? They all seem to do very similar things and share a lot of code. Thanks! Best regards, Aidan

1 0

[PATCH 1/9] ASoC: amd: vg: fix for pm resume callback sequence
by Vijendar Mukunda 25 Feb '22

25 Feb '22

The previous condition is used to cross check only the active stream status for I2S HS instance playback and capture use cases. Modified logic to invoke sequence for two i2s controller instances. Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda(a)amd.com> --- sound/soc/amd/vangogh/acp5x-pcm-dma.c | 62 ++++++++++++++------------- 1 file changed, 32 insertions(+), 30 deletions(-) diff --git a/sound/soc/amd/vangogh/acp5x-pcm-dma.c b/sound/soc/amd/vangogh/acp5x-pcm-dma.c index f10de38976cb..17853d8d56d3 100644 --- a/sound/soc/amd/vangogh/acp5x-pcm-dma.c +++ b/sound/soc/amd/vangogh/acp5x-pcm-dma.c @@ -426,6 +426,7 @@ static int acp5x_audio_remove(struct platform_device *pdev) static int __maybe_unused acp5x_pcm_resume(struct device *dev) { struct i2s_dev_data *adata; + struct i2s_stream_instance *rtd; u32 val, reg_val, frmt_val; reg_val = 0; @@ -433,44 +434,45 @@ static int __maybe_unused acp5x_pcm_resume(struct device *dev) adata = dev_get_drvdata(dev); if (adata->play_stream && adata->play_stream->runtime) { - struct i2s_stream_instance *rtd = - adata->play_stream->runtime->private_data; + rtd = adata->play_stream->runtime->private_data; config_acp5x_dma(rtd, SNDRV_PCM_STREAM_PLAYBACK); - switch (rtd->i2s_instance) { - case I2S_HS_INSTANCE: - reg_val = ACP_HSTDM_ITER; - frmt_val = ACP_HSTDM_TXFRMT; - break; - case I2S_SP_INSTANCE: - default: - reg_val = ACP_I2STDM_ITER; - frmt_val = ACP_I2STDM_TXFRMT; + acp_writel((rtd->xfer_resolution << 3), rtd->acp5x_base + ACP_HSTDM_ITER); + if (adata->tdm_mode == TDM_ENABLE) { + acp_writel(adata->tdm_fmt, adata->acp5x_base + ACP_HSTDM_TXFRMT); + val = acp_readl(adata->acp5x_base + ACP_HSTDM_ITER); + acp_writel(val | 0x2, adata->acp5x_base + ACP_HSTDM_ITER); + } + } + if (adata->i2ssp_play_stream && adata->i2ssp_play_stream->runtime) { + rtd = adata->i2ssp_play_stream->runtime->private_data; + config_acp5x_dma(rtd, SNDRV_PCM_STREAM_PLAYBACK); + acp_writel((rtd->xfer_resolution << 3), rtd->acp5x_base + ACP_I2STDM_ITER); + if (adata->tdm_mode == TDM_ENABLE) { + acp_writel(adata->tdm_fmt, adata->acp5x_base + ACP_I2STDM_TXFRMT); + val = acp_readl(adata->acp5x_base + ACP_I2STDM_ITER); + acp_writel(val | 0x2, adata->acp5x_base + ACP_I2STDM_ITER); } - acp_writel((rtd->xfer_resolution << 3), - rtd->acp5x_base + reg_val); } if (adata->capture_stream && adata->capture_stream->runtime) { - struct i2s_stream_instance *rtd = - adata->capture_stream->runtime->private_data; + rtd = adata->capture_stream->runtime->private_data; config_acp5x_dma(rtd, SNDRV_PCM_STREAM_CAPTURE); - switch (rtd->i2s_instance) { - case I2S_HS_INSTANCE: - reg_val = ACP_HSTDM_IRER; - frmt_val = ACP_HSTDM_RXFRMT; - break; - case I2S_SP_INSTANCE: - default: - reg_val = ACP_I2STDM_IRER; - frmt_val = ACP_I2STDM_RXFRMT; + acp_writel((rtd->xfer_resolution << 3), rtd->acp5x_base + ACP_HSTDM_IRER); + if (adata->tdm_mode == TDM_ENABLE) { + acp_writel(adata->tdm_fmt, adata->acp5x_base + ACP_HSTDM_RXFRMT); + val = acp_readl(adata->acp5x_base + ACP_HSTDM_IRER); + acp_writel(val | 0x2, adata->acp5x_base + ACP_HSTDM_IRER); } - acp_writel((rtd->xfer_resolution << 3), - rtd->acp5x_base + reg_val); } - if (adata->tdm_mode == TDM_ENABLE) { - acp_writel(adata->tdm_fmt, adata->acp5x_base + frmt_val); - val = acp_readl(adata->acp5x_base + reg_val); - acp_writel(val | 0x2, adata->acp5x_base + reg_val); + if (adata->i2ssp_capture_stream && adata->i2ssp_capture_stream->runtime) { + rtd = adata->i2ssp_capture_stream->runtime->private_data; + config_acp5x_dma(rtd, SNDRV_PCM_STREAM_CAPTURE); + acp_writel((rtd->xfer_resolution << 3), rtd->acp5x_base + ACP_I2STDM_IRER); + if (adata->tdm_mode == TDM_ENABLE) { + acp_writel(adata->tdm_fmt, adata->acp5x_base + ACP_I2STDM_RXFRMT); + val = acp_readl(adata->acp5x_base + ACP_I2STDM_IRER); + acp_writel(val | 0x2, adata->acp5x_base + ACP_I2STDM_IRER); + } } acp_writel(1, adata->acp5x_base + ACP_EXTERNAL_INTR_ENB); return 0; -- 2.17.1

4 14

[PATCH v2 00/16] ASoC: codecs: add pm runtime support for Qualcomm codecs
by Srinivas Kandagatla 25 Feb '22

25 Feb '22

This patchset adds support for runtime pm on tx/rx/wsa/wcd lpass macro, wsa881x and wcd938x codecs that are wired up on SoundWire bus. During pm testing it was also found that soundwire clks enabled by lpass macros are not enabling all the required clocks correctly, so last 3 patches corrects them. Tested this on SM8250 MTP along SoundWire In band Headset Button wakeup interrupts. Changes since v1: - move to handing clks individually from clk bluk apis - tidy up the clk provider side code by using devm variants - added error handling. Srinivas Kandagatla (16): ASoC: codecs: va-macro: move to individual clks from bulk ASoC: codecs: rx-macro: move clk provider to managed variants ASoC: codecs: tx-macro: move clk provider to managed variants ASoC: codecs: rx-macro: move to individual clks from bulk ASoC: codecs: tx-macro: move to individual clks from bulk ASoC: codecs: wsa-macro: move to individual clks from bulk ASoC: codecs: wsa-macro: setup soundwire clks correctly ASoC: codecs: tx-macro: setup soundwire clks correctly ASoC: codecs: rx-macro: setup soundwire clks correctly ASoC: codecs: va-macro: add runtime pm support ASoC: codecs: wsa-macro: add runtime pm support ASoC: codecs: rx-macro: add runtime pm support ASoC: codecs: tx-macro: add runtime pm support ASoC: codecs: wsa881x: add runtime pm support ASoC: codecs: wcd938x: add simple clk stop support ASoC: codecs: wcd-mbhc: add runtime pm support sound/soc/codecs/lpass-rx-macro.c | 168 +++++++++++++++++++++++----- sound/soc/codecs/lpass-tx-macro.c | 169 ++++++++++++++++++++++++----- sound/soc/codecs/lpass-va-macro.c | 106 ++++++++++++++---- sound/soc/codecs/lpass-wsa-macro.c | 157 +++++++++++++++++++++++---- sound/soc/codecs/wcd-mbhc-v2.c | 26 +++++ sound/soc/codecs/wcd938x-sdw.c | 1 + sound/soc/codecs/wsa881x.c | 54 +++++++++ 7 files changed, 580 insertions(+), 101 deletions(-) -- 2.21.0

3 19

[PATCH] ALSA: acp: check the return value of devm_kzalloc() in acp_legacy_dai_links_create()
by Jia-Ju Bai 25 Feb '22

25 Feb '22

The function devm_kzalloc() in acp_legacy_dai_links_create() can fail, so its return value should be checked. Fixes: d4c750f2c7d4 ("ASoC: amd: acp: Add generic machine driver support for ACP cards") Reported-by: TOTE Robot <oslab(a)tsinghua.edu.cn> Signed-off-by: Jia-Ju Bai <baijiaju1990(a)gmail.com> --- sound/soc/amd/acp/acp-mach-common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c index cd05ee2802c9..5247015e8b31 100644 --- a/sound/soc/amd/acp/acp-mach-common.c +++ b/sound/soc/amd/acp/acp-mach-common.c @@ -556,6 +556,8 @@ int acp_legacy_dai_links_create(struct snd_soc_card *card) num_links++; links = devm_kzalloc(dev, sizeof(struct snd_soc_dai_link) * num_links, GFP_KERNEL); + if (!links) + return -ENOMEM; if (drv_data->hs_cpu_id == I2S_SP) { links[i].name = "acp-headset-codec"; -- 2.17.1

2 1

[PATCH] ASoC: SOF: sof-priv: Drop duplicate sof_compressed_ops declaration
by Peter Ujfalusi 25 Feb '22

25 Feb '22

Other commit added the declaration of the sof_compressed_ops, drop the instance which added it as Platform specific ops, which the sof_compressed_ops is not. 76cdd90b27b4e ("ASoC: SOF: pcm: Add compress_ops for SOF platform component driver") Signed-off-by: Peter Ujfalusi <peter.ujfalusi(a)linux.intel.com> --- sound/soc/sof/sof-priv.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h index 1cc6dce17582..2e19ac619ad5 100644 --- a/sound/soc/sof/sof-priv.h +++ b/sound/soc/sof/sof-priv.h @@ -561,11 +561,6 @@ int snd_sof_debugfs_add_region_item_iomem(struct snd_sof_dev *sdev, enum snd_sof_fw_blk_type blk_type, u32 offset, size_t size, const char *name, enum sof_debugfs_access_type access_type); -/* - * Platform specific ops. - */ -extern struct snd_compress_ops sof_compressed_ops; - /* * DSP Architectures. */ -- 2.35.1

3 2

[PATCH] ASoC: qcom: lpass-platform: Update warning print to control excess logging
by Srinivasa Rao Mandadapu 25 Feb '22

25 Feb '22

Update dev_warn to dev_warn_ratelimit to control excess xrun logging in lpass platform driver. Signed-off-by: Srinivasa Rao Mandadapu <quic_srivasam(a)quicinc.com> Co-developed-by: Venkata Prasad Potturu <quic_potturu(a)quicinc.com> Signed-off-by: Venkata Prasad Potturu <quic_potturu(a)quicinc.com> --- sound/soc/qcom/lpass-platform.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index b3af971..1ce0878 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -986,7 +986,8 @@ static irqreturn_t lpass_dma_interrupt_handler( "error writing to irqclear reg: %d\n", rv); return IRQ_NONE; } - dev_warn(soc_runtime->dev, "xrun warning\n"); + dev_warn_ratelimited(soc_runtime->dev, "xrun warning\n"); + snd_pcm_stop_xrun(substream); ret = IRQ_HANDLED; } -- 2.7.4

2 1

[PATCH] ALSA: rt5663: check the return value of devm_kzalloc() in rt5663_parse_dp()
by Jia-Ju Bai 25 Feb '22

25 Feb '22

The function devm_kzalloc() in rt5663_parse_dp() can fail, so its return value should be checked. Fixes: 457c25efc592 ("ASoC: rt5663: Add the function of impedance sensing") Reported-by: TOTE Robot <oslab(a)tsinghua.edu.cn> Signed-off-by: Jia-Ju Bai <baijiaju1990(a)gmail.com> --- sound/soc/codecs/rt5663.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c index 2138f62e6af5..3a8fba101b20 100644 --- a/sound/soc/codecs/rt5663.c +++ b/sound/soc/codecs/rt5663.c @@ -3478,6 +3478,8 @@ static int rt5663_parse_dp(struct rt5663_priv *rt5663, struct device *dev) table_size = sizeof(struct impedance_mapping_table) * rt5663->pdata.impedance_sensing_num; rt5663->imp_table = devm_kzalloc(dev, table_size, GFP_KERNEL); + if (!rt5663->imp_table) + return -ENOMEM; ret = device_property_read_u32_array(dev, "realtek,impedance_sensing_table", (u32 *)rt5663->imp_table, table_size); -- 2.17.1

2 1