From: Kai Vehmanen kai.vehmanen@linux.intel.com

When the sampling rates going in (host) and out (dai) from the DSP are different, the IPC4 delay reporting does not work correctly. Add support for this case by scaling the all raw position values to a common timebase before calculating real-time delay for the PCM.

Cc: stable@vger.kernel.org Fixes: 0ea06680dfcb ("ASoC: SOF: ipc4-pcm: Correct the delay calculation") Signed-off-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Péter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Bard Liao yung-chuan.liao@linux.intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com --- sound/soc/sof/ipc4-pcm.c | 83 ++++++++++++++++++++++++++++++---------- 1 file changed, 62 insertions(+), 21 deletions(-)

diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index 24f82a6f3610..075388d5cb3c 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -19,12 +19,14 @@ * struct sof_ipc4_timestamp_info - IPC4 timestamp info * @host_copier: the host copier of the pcm stream * @dai_copier: the dai copier of the pcm stream - * @stream_start_offset: reported by fw in memory window (converted to frames) - * @stream_end_offset: reported by fw in memory window (converted to frames) + * @stream_start_offset: reported by fw in memory window (converted to + * frames at host_copier sampling rate) + * @stream_end_offset: reported by fw in memory window (converted to + * frames at host_copier sampling rate) * @llp_offset: llp offset in memory window - * @boundary: wrap boundary should be used for the LLP frame counter * @delay: Calculated and stored in pointer callback. The stored value is - * returned in the delay callback. + * returned in the delay callback. Expressed in frames at host copier + * sampling rate. */ struct sof_ipc4_timestamp_info { struct sof_ipc4_copier *host_copier; @@ -33,7 +35,6 @@ struct sof_ipc4_timestamp_info { u64 stream_end_offset; u32 llp_offset;

- u64 boundary; snd_pcm_sframes_t delay; };

@@ -48,6 +49,16 @@ struct sof_ipc4_pcm_stream_priv { bool chain_dma_allocated; };

+/* + * Modulus to use to compare host and link position counters. The sampling + * rates may be different, so the raw hardware counters will wrap + * around at different times. To calculate differences, use + * DELAY_BOUNDARY as a common modulus. This value must be smaller than + * the wrap-around point of any hardware counter, and larger than any + * valid delay measurement. + */ +#define DELAY_BOUNDARY U32_MAX + static inline struct sof_ipc4_timestamp_info * sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps) { @@ -1049,6 +1060,35 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, return 0; }

+static u64 sof_ipc4_frames_dai_to_host(struct sof_ipc4_timestamp_info *time_info, u64 value) +{ + u64 dai_rate, host_rate; + + if (!time_info->dai_copier || !time_info->host_copier) + return value; + + /* + * copiers do not change sampling rate, so we can use the + * out_format independently of stream direction + */ + dai_rate = time_info->dai_copier->data.out_format.sampling_frequency; + host_rate = time_info->host_copier->data.out_format.sampling_frequency; + + if (!dai_rate || !host_rate || dai_rate == host_rate) + return value; + + /* take care not to overflow u64, rates can be up to 768000 */ + if (value > U32_MAX) { + value = div64_u64(value, dai_rate); + value *= host_rate; + } else { + value *= host_rate; + value = div64_u64(value, dai_rate); + } + + return value; +} + static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream, struct snd_sof_pcm_stream *sps, @@ -1099,14 +1139,13 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, time_info->stream_end_offset = ppl_reg.stream_end_offset; do_div(time_info->stream_end_offset, dai_sample_size);

+ /* convert to host frame time */ + time_info->stream_start_offset = + sof_ipc4_frames_dai_to_host(time_info, time_info->stream_start_offset); + time_info->stream_end_offset = + sof_ipc4_frames_dai_to_host(time_info, time_info->stream_end_offset); + out: - /* - * Calculate the wrap boundary need to be used for delay calculation - * The host counter is in bytes, it will wrap earlier than the frames - * based link counter. - */ - time_info->boundary = div64_u64(~((u64)0), - frames_to_bytes(substream->runtime, 1)); /* Initialize the delay value to 0 (no delay) */ time_info->delay = 0;

@@ -1149,6 +1188,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,

/* For delay calculation we need the host counter */ host_cnt = snd_sof_pcm_get_host_byte_counter(sdev, component, substream); + + /* Store the original value to host_ptr */ host_ptr = host_cnt;

/* convert the host_cnt to frames */ @@ -1167,6 +1208,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, sof_mailbox_read(sdev, time_info->llp_offset, &llp, sizeof(llp)); dai_cnt = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l; } + + dai_cnt = sof_ipc4_frames_dai_to_host(time_info, dai_cnt); dai_cnt += time_info->stream_end_offset;

/* In two cases dai dma counter is not accurate @@ -1200,8 +1243,9 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, dai_cnt -= time_info->stream_start_offset; }

- /* Wrap the dai counter at the boundary where the host counter wraps */ - div64_u64_rem(dai_cnt, time_info->boundary, &dai_cnt); + /* Convert to a common base before comparisons */ + dai_cnt &= DELAY_BOUNDARY; + host_cnt &= DELAY_BOUNDARY;

if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { head_cnt = host_cnt; @@ -1211,14 +1255,11 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, tail_cnt = host_cnt; }

- if (head_cnt < tail_cnt) { - time_info->delay = time_info->boundary - tail_cnt + head_cnt; - goto out; - } - - time_info->delay = head_cnt - tail_cnt; + if (unlikely(head_cnt < tail_cnt)) + time_info->delay = DELAY_BOUNDARY - tail_cnt + head_cnt; + else + time_info->delay = head_cnt - tail_cnt;

-out: /* * Convert the host byte counter to PCM pointer which wraps in buffer * and it is in frames

Add dev_dbg_ratelimited() wrapper for snd_sof_pcm specific debug prints that needs rate limited.

Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Bard Liao yung-chuan.liao@linux.intel.com --- sound/soc/sof/sof-audio.h | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index db6973c8eac3..a8b93a2eec9c 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -629,6 +629,11 @@ void snd_sof_pcm_init_elapsed_work(struct work_struct *work); (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir, \ ##__VA_ARGS__)

+#define spcm_dbg_ratelimited(__spcm, __dir, __fmt, ...) \ + dev_dbg_ratelimited((__spcm)->scomp->dev, "pcm%u (%s), dir %d: " __fmt, \ + (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir, \ + ##__VA_ARGS__) + #define spcm_err(__spcm, __dir, __fmt, ...) \ dev_err((__spcm)->scomp->dev, "%s: pcm%u (%s), dir %d: " __fmt, \ __func__, (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir, \

It is allowed to mix Link and Host DMA channels in a way that their index is different. In this case we would read the LLP from a channel which is not used or used for other operation.

Such case can be reproduced on cAVS2.5 or ACE1 platforms with soundwire configuration: playback to SDW would take Host channel 0 (stream_tag 1) and no Link DMA used Second playback to HDMI (HDA) would use Host channel 1 (stream_tag 2) and Link channel 0 (stream_tag 1).

In this case reading the LLP from channel 2 is incorrect as that is not the Link channel used for the HDMI playback.

To correct this, we should look up the BE and get the channel used on the Link side.

Fixes: 67b182bea08a ("ASoC: SOF: Intel: hda: Implement get_stream_position (Linear Link Position)") Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Ranjani Sridharan ranjani.sridharan@linux.intel.com --- sound/soc/sof/intel/hda-stream.c | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index a34f472ef175..9c3b3a9aaf83 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -1129,10 +1129,35 @@ u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev, struct snd_soc_component *component, struct snd_pcm_substream *substream) { - struct hdac_stream *hstream = substream->runtime->private_data; - struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream); + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct snd_soc_pcm_runtime *be_rtd = NULL; + struct hdac_ext_stream *hext_stream; + struct snd_soc_dai *cpu_dai; + struct snd_soc_dpcm *dpcm; u32 llp_l, llp_u;

+ /* + * The LLP needs to be read from the Link DMA used for this FE as it is + * allowed to use any combination of Link and Host channels + */ + for_each_dpcm_be(rtd, substream->stream, dpcm) { + if (dpcm->fe != rtd) + continue; + + be_rtd = dpcm->be; + } + + if (!be_rtd) + return 0; + + cpu_dai = snd_soc_rtd_to_cpu(be_rtd, 0); + if (!cpu_dai) + return 0; + + hext_stream = snd_soc_dai_get_dma_data(cpu_dai, substream); + if (!hext_stream) + return 0; + /* * The pplc_addr have been calculated during probe in * hda_dsp_stream_init():