From: Mikhail Durnev mikhail_durnev@mentor.com
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 --- sound/soc/sh/rcar/core.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 66 insertions(+), 1 deletion(-)
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 6e670b3..8ca3fb7 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1428,8 +1428,73 @@ static int rsnd_hw_params(struct snd_soc_component *component, } if (io->converted_chan) dev_dbg(dev, "convert channels = %d\n", io->converted_chan); - if (io->converted_rate) + if (io->converted_rate) { dev_dbg(dev, "convert rate = %d\n", io->converted_rate); + + /* + * SRC supports convert rates from params_rate(hw_params)/k_down + * to params_rate(hw_params)*k_up, where k_up is always 6, and + * k_down depends on number of channels and SRC unit. + * So all SRC units can upsample audio up to 6 times regardless + * its number of channels. And all SRC units can downsample + * 2 channel audio up to 6 times too. + */ + int k_up = 6; + int k_down = 6; + int channel; + struct rsnd_mod *src_mod = rsnd_io_to_mod_src(io); + + channel = io->converted_chan ? io->converted_chan : fe_channel; + + switch (rsnd_mod_id(src_mod)) { + /* + * SRC0 can downsample 4, 6 and 8 channel audio up to 4 times. + * SRC1, SRC3 and SRC4 can downsample 4 channel audio + * up to 4 times. + * SRC1, SRC3 and SRC4 can downsample 6 and 8 channel audio + * no more than twice. + */ + case 1: + case 3: + case 4: + if (channel > 4) { + k_down = 2; + break; + } + case 0: + if (channel > 2) + k_down = 4; + break; + + /* Other SRC units do not support more than 2 channels */ + default: + if (channel > 2) + return -EINVAL; + } + + if (params_rate(hw_params) > io->converted_rate * k_down) { + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->min = + io->converted_rate * k_down; + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->max = + io->converted_rate * k_down; + hw_params->cmask |= SNDRV_PCM_HW_PARAM_RATE; + } else if (params_rate(hw_params) * k_up < io->converted_rate) { + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->min = + (io->converted_rate + k_up - 1) / k_up; + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->max = + (io->converted_rate + k_up - 1) / k_up; + hw_params->cmask |= SNDRV_PCM_HW_PARAM_RATE; + } + + /* + * TBD: Max SRC input and output rates also depend on number + * of channels and SRC unit: + * SRC1, SRC3 and SRC4 do not support more than 128kHz + * for 6 channel and 96kHz for 8 channel audio. + * Perhaps this function should return EINVAL if the input or + * the output rate exceeds the limitation. + */ + } }
return rsnd_dai_call(hw_params, io, substream, hw_params);