Merge tag 'asoc-fix-v6.18-merge-window' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Fixes for v6.18

A small pile of fixes, almost all for the Intel and SOF code surrounding
management of the host buffer.  We've also got one fix for Meson and new
device IDs and quirk supporting the RT722VB.

Author: tiwai

sound/soc/codecs/rt722-sdca-sdw.c

@@ -21,7 +21,7 @@ static int rt722_sdca_mbq_size(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case 0x2f01 ... 0x2f0a:
 	case 0x2f35 ... 0x2f36:
-	case 0x2f50:
+	case 0x2f50 ... 0x2f52:
 	case 0x2f54:
 	case 0x2f58 ... 0x2f5d:
 	case SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0):

sound/soc/codecs/rt722-sdca.c

@@ -1378,6 +1378,9 @@ static void rt722_sdca_dmic_preset(struct rt722_sdca_priv *rt722)
 		/* PHYtiming TDZ/TZD control */
 		regmap_write(rt722->regmap, 0x2f03, 0x06);
 
+		if (rt722->hw_vid == RT722_VB)
+			regmap_write(rt722->regmap, 0x2f52, 0x00);
+
 		/* clear flag */
 		regmap_write(rt722->regmap,
 			SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0),
@@ -1415,6 +1418,9 @@ static void rt722_sdca_amp_preset(struct rt722_sdca_priv *rt722)
 			SDW_SDCA_CTL(FUNC_NUM_AMP, RT722_SDCA_ENT_OT23,
 				RT722_SDCA_CTL_VENDOR_DEF, CH_08), 0x04);
 
+		if (rt722->hw_vid == RT722_VB)
+			regmap_write(rt722->regmap, 0x2f54, 0x00);
+
 		/* clear flag */
 		regmap_write(rt722->regmap,
 			SDW_SDCA_CTL(FUNC_NUM_AMP, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0),
@@ -1506,6 +1512,9 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722)
 		rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4,
 			0x0010);
 
+		if (rt722->hw_vid == RT722_VB)
+			regmap_write(rt722->regmap, 0x2f51, 0x00);
+
 		/* clear flag */
 		regmap_write(rt722->regmap,
 			SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0),
@@ -1516,6 +1525,7 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722)
 int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave)
 {
 	struct rt722_sdca_priv *rt722 = dev_get_drvdata(dev);
+	unsigned int val;
 
 	rt722->disable_irq = false;
 
@@ -1545,6 +1555,10 @@ int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave)
 
 	pm_runtime_get_noresume(&slave->dev);
 
+	rt722_sdca_index_read(rt722, RT722_VENDOR_REG, RT722_JD_PRODUCT_NUM, &val);
+	rt722->hw_vid = (val & 0x0f00) >> 8;
+	dev_dbg(&slave->dev, "%s hw_vid=0x%x\n", __func__, rt722->hw_vid);
+
 	rt722_sdca_dmic_preset(rt722);
 	rt722_sdca_amp_preset(rt722);
 	rt722_sdca_jack_preset(rt722);

sound/soc/codecs/rt722-sdca.h

@@ -39,6 +39,7 @@ struct  rt722_sdca_priv {
 	/* For DMIC */
 	bool fu1e_dapm_mute;
 	bool fu1e_mixer_mute[4];
+	int hw_vid;
 };
 
 struct rt722_sdca_dmic_kctrl_priv {
@@ -233,6 +234,11 @@ enum rt722_sdca_jd_src {
 	RT722_JD1,
 };
 
+enum rt722_sdca_version {
+	RT722_VA,
+	RT722_VB,
+};
+
 int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave);
 int rt722_sdca_init(struct device *dev, struct regmap *regmap, struct sdw_slave *slave);
 int rt722_sdca_index_write(struct rt722_sdca_priv *rt722,

sound/soc/meson/aiu-encoder-i2s.c

@@ -236,8 +236,12 @@ static int aiu_encoder_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	    inv == SND_SOC_DAIFMT_IB_IF)
 		val |= AIU_CLK_CTRL_LRCLK_INVERT;
 
-	if (inv == SND_SOC_DAIFMT_IB_NF ||
-	    inv == SND_SOC_DAIFMT_IB_IF)
+	/*
+	 * The SoC changes data on the rising edge of the bitclock
+	 * so an inversion of the bitclock is required in normal mode
+	 */
+	if (inv == SND_SOC_DAIFMT_NB_NF ||
+	    inv == SND_SOC_DAIFMT_NB_IF)
 		val |= AIU_CLK_CTRL_AOCLK_INVERT;
 
 	/* Signal skew */
@@ -328,4 +332,3 @@ const struct snd_soc_dai_ops aiu_encoder_i2s_dai_ops = {
 	.startup	= aiu_encoder_i2s_startup,
 	.shutdown	= aiu_encoder_i2s_shutdown,
 };
-

sound/soc/sof/intel/hda-pcm.c

@@ -29,6 +29,8 @@
 #define SDnFMT_BITS(x)	((x) << 4)
 #define SDnFMT_CHAN(x)	((x) << 0)
 
+#define HDA_MAX_PERIOD_TIME_HEADROOM	10
+
 static bool hda_always_enable_dmi_l1;
 module_param_named(always_enable_dmi_l1, hda_always_enable_dmi_l1, bool, 0444);
 MODULE_PARM_DESC(always_enable_dmi_l1, "SOF HDA always enable DMI l1");
@@ -291,19 +293,30 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
 	 * On playback start the DMA will transfer dsp_max_burst_size_in_ms
 	 * amount of data in one initial burst to fill up the host DMA buffer.
 	 * Consequent DMA burst sizes are shorter and their length can vary.
-	 * To make sure that userspace allocate large enough ALSA buffer we need
-	 * to place a constraint on the buffer time.
+	 * To avoid immediate xrun by the initial burst we need to place
+	 * constraint on the period size (via PERIOD_TIME) to cover the size of
+	 * the host buffer.
+	 * We need to add headroom of max 10ms as the firmware needs time to
+	 * settle to the 1ms pacing and initially it can run faster for few
+	 * internal periods.
 	 *
 	 * On capture the DMA will transfer 1ms chunks.
-	 *
-	 * Exact dsp_max_burst_size_in_ms constraint is racy, so set the
-	 * constraint to a minimum of 2x dsp_max_burst_size_in_ms.
 	 */
-	if (spcm->stream[direction].dsp_max_burst_size_in_ms)
+	if (spcm->stream[direction].dsp_max_burst_size_in_ms) {
+		unsigned int period_time = spcm->stream[direction].dsp_max_burst_size_in_ms;
+
+		/*
+		 * add headroom over the maximum burst size to cover the time
+		 * needed for the DMA pace to settle.
+		 * Limit the headroom time to HDA_MAX_PERIOD_TIME_HEADROOM
+		 */
+		period_time += min(period_time, HDA_MAX_PERIOD_TIME_HEADROOM);
+
 		snd_pcm_hw_constraint_minmax(substream->runtime,
-			SNDRV_PCM_HW_PARAM_BUFFER_TIME,
-			spcm->stream[direction].dsp_max_burst_size_in_ms * USEC_PER_MSEC * 2,
+			SNDRV_PCM_HW_PARAM_PERIOD_TIME,
+			period_time * USEC_PER_MSEC,
 			UINT_MAX);
+	}
 
 	/* binding pcm substream to hda stream */
 	substream->runtime->private_data = &dsp_stream->hstream;

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():

sound/soc/sof/ipc3-topology.c

@@ -2473,11 +2473,6 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
 	if (ret < 0)
 		return ret;
 
-	/* free all the scheduler widgets now */
-	ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
-	if (ret < 0)
-		return ret;
-
 	/*
 	 * Tear down all pipelines associated with PCMs that did not get suspended
 	 * and unset the prepare flag so that they can be set up again during resume.
@@ -2493,6 +2488,11 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
 		}
 	}
 
+	/* free all the scheduler widgets now. This will also power down the secondary cores */
+	ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
+	if (ret < 0)
+		return ret;
+
 	list_for_each_entry(sroute, &sdev->route_list, list)
 		sroute->setup = false;
 

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 +49,18 @@ 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
+
+#define DELAY_MAX		(DELAY_BOUNDARY >> 1)
+
 static inline struct sof_ipc4_timestamp_info *
 sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps)
 {
@@ -1049,6 +1062,35 @@ 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,
@@ -1068,18 +1110,24 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
 		return -EINVAL;
 	} else if (host_copier->data.gtw_cfg.node_id == SOF_IPC4_CHAIN_DMA_NODE_ID) {
 		/*
-		 * While the firmware does not supports time_info reporting for
+		 * While the firmware does not support time_info reporting for
 		 * streams using ChainDMA, it is granted that ChainDMA can only
 		 * be used on Host+Link pairs where the link position is
 		 * accessible from the host side.
 		 *
 		 * Enable delay calculation in case of ChainDMA via host
 		 * accessible registers.
 		 *
-		 * The ChainDMA uses 2x 1ms ping-pong buffer, dai side starts
-		 * when 1ms data is available
+		 * The ChainDMA prefills the link DMA with a preamble
+		 * of zero samples. Set the stream start offset based
+		 * on size of the preamble (driver provided fifo size
+		 * multiplied by 2.5). We add 1ms of margin as the FW
+		 * will align the buffer size to DMA hardware
+		 * alignment that is not known to host.
 		 */
-		time_info->stream_start_offset = substream->runtime->rate / MSEC_PER_SEC;
+		int pre_ms = SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS * 5 / 2 + 1;
+
+		time_info->stream_start_offset = pre_ms * substream->runtime->rate / MSEC_PER_SEC;
 		goto out;
 	}
 
@@ -1099,14 +1147,13 @@ 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 +1196,8 @@ 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 +1216,8 @@ 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 +1251,9 @@ 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 +1263,18 @@ 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;
-	}
+	if (unlikely(head_cnt < tail_cnt))
+		time_info->delay = DELAY_BOUNDARY - tail_cnt + head_cnt;
+	else
+		time_info->delay = head_cnt - tail_cnt;
 
-	time_info->delay =  head_cnt - tail_cnt;
+	if (time_info->delay > DELAY_MAX) {
+		spcm_dbg_ratelimited(spcm, substream->stream,
+				     "inaccurate delay, host %llu dai_cnt %llu",
+				     host_cnt, dai_cnt);
+		time_info->delay = 0;
+	}
 
-out:
 	/*
 	 * Convert the host byte counter to PCM pointer which wraps in buffer
 	 * and it is in frames