ASoC: SOF: ipc4/Intel: Fix delay reporting

Merge series from Peter Ujfalusi <peter.ujfalusi@linux.intel.com>:

The current version of delay reporting code can report incorrect
values when paired with a firmware which enables this feature.

Unfortunately there are several smaller issues that needed to be addressed
to correct the behavior:

Wrong information was used for the host side of counter
For MTL/LNL used incorrect (in a sense that it was verified only on MTL)
link side counter function.
The link side counter needs compensation logic if pause/resume is used.
The offset values were not refreshed from firmware.
Finally, not strictly connected, but the ALSA buffer size needs to be
constrained to avoid constant xrun from media players (like mpv)

The series applies cleanly for 6.9 and 6.8.y stable, but older stable
would need manual backport, but it is questionable if it is needed as
MTL/LNL is missing features.

include/sound/hdaudio_ext.h

@@ -56,6 +56,9 @@ struct hdac_ext_stream {
 	u32 pphcldpl;
 	u32 pphcldpu;
 
+	u32 pplcllpl;
+	u32 pplcllpu;
+
 	bool decoupled:1;
 	bool link_locked:1;
 	bool link_prepared;

sound/soc/sof/intel/hda-common-ops.c

@@ -57,6 +57,9 @@ struct snd_sof_dsp_ops sof_hda_common_ops = {
 	.pcm_pointer	= hda_dsp_pcm_pointer,
 	.pcm_ack	= hda_dsp_pcm_ack,
 
+	.get_dai_frame_counter = hda_dsp_get_stream_llp,
+	.get_host_byte_counter = hda_dsp_get_stream_ldp,
+
 	/* firmware loading */
 	.load_firmware = snd_sof_load_firmware_raw,
 

sound/soc/sof/intel/hda-dai-ops.c

@@ -7,6 +7,7 @@
 
 #include <sound/pcm_params.h>
 #include <sound/hdaudio_ext.h>
+#include <sound/hda_register.h>
 #include <sound/hda-mlink.h>
 #include <sound/sof/ipc4/header.h>
 #include <uapi/sound/sof/header.h>
@@ -362,6 +363,16 @@ static int hda_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *cpu_dai,
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		snd_hdac_ext_stream_clear(hext_stream);
+
+		/*
+		 * Save the LLP registers in case the stream is
+		 * restarting due PAUSE_RELEASE, or START without a pcm
+		 * close/open since in this case the LLP register is not reset
+		 * to 0 and the delay calculation will return with invalid
+		 * results.
+		 */
+		hext_stream->pplcllpl = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL);
+		hext_stream->pplcllpu = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU);
 		break;
 	default:
 		dev_err(sdev->dev, "unknown trigger command %d\n", cmd);

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

@@ -259,8 +259,37 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
 		snd_pcm_hw_constraint_mask64(substream->runtime, SNDRV_PCM_HW_PARAM_FORMAT,
 					     SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S32);
 
+	/*
+	 * The dsp_max_burst_size_in_ms is the length of the maximum burst size
+	 * of the host DMA in the ALSA buffer.
+	 *
+	 * 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.
+	 *
+	 * 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)
+		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,
+			UINT_MAX);
+
 	/* binding pcm substream to hda stream */
 	substream->runtime->private_data = &dsp_stream->hstream;
+
+	/*
+	 * Reset the llp cache values (they are used for LLP compensation in
+	 * case the counter is not reset)
+	 */
+	dsp_stream->pplcllpl = 0;
+	dsp_stream->pplcllpu = 0;
+
 	return 0;
 }
 

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

@@ -1063,3 +1063,73 @@ snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream,
 
 	return pos;
 }
+
+#define merge_u64(u32_u, u32_l) (((u64)(u32_u) << 32) | (u32_l))
+
+/**
+ * hda_dsp_get_stream_llp - Retrieve the LLP (Linear Link Position) of the stream
+ * @sdev: SOF device
+ * @component: ASoC component
+ * @substream: PCM substream
+ *
+ * Returns the raw Linear Link Position value
+ */
+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);
+	u32 llp_l, llp_u;
+
+	/*
+	 * The pplc_addr have been calculated during probe in
+	 * hda_dsp_stream_init():
+	 * pplc_addr = sdev->bar[HDA_DSP_PP_BAR] +
+	 *	       SOF_HDA_PPLC_BASE +
+	 *	       SOF_HDA_PPLC_MULTI * total_stream +
+	 *	       SOF_HDA_PPLC_INTERVAL * stream_index
+	 *
+	 * Use this pre-calculated address to avoid repeated re-calculation.
+	 */
+	llp_l = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL);
+	llp_u = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU);
+
+	/* Compensate the LLP counter with the saved offset */
+	if (hext_stream->pplcllpl || hext_stream->pplcllpu)
+		return merge_u64(llp_u, llp_l) -
+		       merge_u64(hext_stream->pplcllpu, hext_stream->pplcllpl);
+
+	return merge_u64(llp_u, llp_l);
+}
+
+/**
+ * hda_dsp_get_stream_ldp - Retrieve the LDP (Linear DMA Position) of the stream
+ * @sdev: SOF device
+ * @component: ASoC component
+ * @substream: PCM substream
+ *
+ * Returns the raw Linear Link Position value
+ */
+u64 hda_dsp_get_stream_ldp(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);
+	u32 ldp_l, ldp_u;
+
+	/*
+	 * The pphc_addr have been calculated during probe in
+	 * hda_dsp_stream_init():
+	 * pphc_addr = sdev->bar[HDA_DSP_PP_BAR] +
+	 *	       SOF_HDA_PPHC_BASE +
+	 *	       SOF_HDA_PPHC_INTERVAL * stream_index
+	 *
+	 * Use this pre-calculated address to avoid repeated re-calculation.
+	 */
+	ldp_l = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPL);
+	ldp_u = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPU);
+
+	return ((u64)ldp_u << 32) | ldp_l;
+}

sound/soc/sof/intel/hda.h

@@ -662,6 +662,12 @@ bool hda_dsp_check_stream_irq(struct snd_sof_dev *sdev);
 
 snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream,
 					      int direction, bool can_sleep);
+u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev,
+			   struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream);
+u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev,
+			   struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream);
 
 struct hdac_ext_stream *
 	hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction, u32 flags);

sound/soc/sof/intel/lnl.c

@@ -134,8 +134,6 @@ int sof_lnl_ops_init(struct snd_sof_dev *sdev)
 		sof_lnl_ops.runtime_resume = lnl_hda_dsp_runtime_resume;
 	}
 
-	sof_lnl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position;
-
 	/* dsp core get/put */
 	sof_lnl_ops.core_get = mtl_dsp_core_get;
 	sof_lnl_ops.core_put = mtl_dsp_core_put;

sound/soc/sof/intel/mtl.c

@@ -626,18 +626,6 @@ static int mtl_dsp_disable_interrupts(struct snd_sof_dev *sdev)
 	return mtl_enable_interrupts(sdev, false);
 }
 
-u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev,
-					 struct snd_soc_component *component,
-					 struct snd_pcm_substream *substream)
-{
-	struct hdac_stream *hstream = substream->runtime->private_data;
-	u32 llp_l, llp_u;
-
-	llp_l = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPL(hstream->index));
-	llp_u = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPU(hstream->index));
-	return ((u64)llp_u << 32) | llp_l;
-}
-
 int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core)
 {
 	const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm;
@@ -707,8 +695,6 @@ int sof_mtl_ops_init(struct snd_sof_dev *sdev)
 	sof_mtl_ops.core_get = mtl_dsp_core_get;
 	sof_mtl_ops.core_put = mtl_dsp_core_put;
 
-	sof_mtl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position;
-
 	sdev->private = kzalloc(sizeof(struct sof_ipc4_fw_data), GFP_KERNEL);
 	if (!sdev->private)
 		return -ENOMEM;

sound/soc/sof/intel/mtl.h

@@ -6,12 +6,6 @@
  * Copyright(c) 2020-2022 Intel Corporation. All rights reserved.
  */
 
-/* HDA Registers */
-#define MTL_PPLCLLPL_BASE		0x948
-#define MTL_PPLCLLPU_STRIDE		0x10
-#define MTL_PPLCLLPL(x)			(MTL_PPLCLLPL_BASE + (x) * MTL_PPLCLLPU_STRIDE)
-#define MTL_PPLCLLPU(x)			(MTL_PPLCLLPL_BASE + 0x4 + (x) * MTL_PPLCLLPU_STRIDE)
-
 /* DSP Registers */
 #define MTL_HFDSSCS			0x1000
 #define MTL_HFDSSCS_SPA_MASK		BIT(16)
@@ -103,9 +97,5 @@ int mtl_dsp_ipc_get_window_offset(struct snd_sof_dev *sdev, u32 id);
 
 void mtl_ipc_dump(struct snd_sof_dev *sdev);
 
-u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev,
-					 struct snd_soc_component *component,
-					 struct snd_pcm_substream *substream);
-
 int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core);
 int mtl_dsp_core_put(struct snd_sof_dev *sdev, int core);

sound/soc/sof/ipc4-priv.h

@@ -92,20 +92,6 @@ struct sof_ipc4_fw_data {
 	struct mutex pipeline_state_mutex; /* protect pipeline triggers, ref counts and states */
 };
 
-/**
- * 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
- * @llp_offset: llp offset in memory window
- */
-struct sof_ipc4_timestamp_info {
-	struct sof_ipc4_copier *host_copier;
-	struct sof_ipc4_copier *dai_copier;
-	u64 stream_start_offset;
-	u32 llp_offset;
-};
-
 extern const struct sof_ipc_fw_loader_ops ipc4_loader_ops;
 extern const struct sof_ipc_tplg_ops ipc4_tplg_ops;
 extern const struct sof_ipc_tplg_control_ops tplg_ipc4_control_ops;

sound/soc/sof/ipc4-topology.c

@@ -412,8 +412,9 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
 	struct sof_ipc4_available_audio_format *available_fmt;
 	struct snd_soc_component *scomp = swidget->scomp;
 	struct sof_ipc4_copier *ipc4_copier;
+	struct snd_sof_pcm *spcm;
 	int node_type = 0;
-	int ret;
+	int ret, dir;
 
 	ipc4_copier = kzalloc(sizeof(*ipc4_copier), GFP_KERNEL);
 	if (!ipc4_copier)
@@ -447,6 +448,25 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
 	}
 	dev_dbg(scomp->dev, "host copier '%s' node_type %u\n", swidget->widget->name, node_type);
 
+	spcm = snd_sof_find_spcm_comp(scomp, swidget->comp_id, &dir);
+	if (!spcm)
+		goto skip_gtw_cfg;
+
+	if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
+		struct snd_sof_pcm_stream *sps = &spcm->stream[dir];
+
+		sof_update_ipc_object(scomp, &sps->dsp_max_burst_size_in_ms,
+				      SOF_COPIER_DEEP_BUFFER_TOKENS,
+				      swidget->tuples,
+				      swidget->num_tuples, sizeof(u32), 1);
+		/* Set default DMA buffer size if it is not specified in topology */
+		if (!sps->dsp_max_burst_size_in_ms)
+			sps->dsp_max_burst_size_in_ms = SOF_IPC4_MIN_DMA_BUFFER_SIZE;
+	} else {
+		/* Capture data is copied from DSP to host in 1ms bursts */
+		spcm->stream[dir].dsp_max_burst_size_in_ms = 1;
+	}
+
 skip_gtw_cfg:
 	ipc4_copier->gtw_attr = kzalloc(sizeof(*ipc4_copier->gtw_attr), GFP_KERNEL);
 	if (!ipc4_copier->gtw_attr) {

sound/soc/sof/ops.h

@@ -523,12 +523,26 @@ static inline int snd_sof_pcm_platform_ack(struct snd_sof_dev *sdev,
 	return 0;
 }
 
-static inline u64 snd_sof_pcm_get_stream_position(struct snd_sof_dev *sdev,
+static inline u64
+snd_sof_pcm_get_dai_frame_counter(struct snd_sof_dev *sdev,
 				  struct snd_soc_component *component,
 				  struct snd_pcm_substream *substream)
 {
-	if (sof_ops(sdev) && sof_ops(sdev)->get_stream_position)
-		return sof_ops(sdev)->get_stream_position(sdev, component, substream);
+	if (sof_ops(sdev) && sof_ops(sdev)->get_dai_frame_counter)
+		return sof_ops(sdev)->get_dai_frame_counter(sdev, component,
+							    substream);
+
+	return 0;
+}
+
+static inline u64
+snd_sof_pcm_get_host_byte_counter(struct snd_sof_dev *sdev,
+				  struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream)
+{
+	if (sof_ops(sdev) && sof_ops(sdev)->get_host_byte_counter)
+		return sof_ops(sdev)->get_host_byte_counter(sdev, component,
+							    substream);
 
 	return 0;
 }

sound/soc/sof/pcm.c

@@ -388,13 +388,21 @@ static snd_pcm_uframes_t sof_pcm_pointer(struct snd_soc_component *component,
 {
 	struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
+	const struct sof_ipc_pcm_ops *pcm_ops = sof_ipc_get_ops(sdev, pcm);
 	struct snd_sof_pcm *spcm;
 	snd_pcm_uframes_t host, dai;
+	int ret = -EOPNOTSUPP;
 
 	/* nothing to do for BE */
 	if (rtd->dai_link->no_pcm)
 		return 0;
 
+	if (pcm_ops && pcm_ops->pointer)
+		ret = pcm_ops->pointer(component, substream, &host);
+
+	if (ret != -EOPNOTSUPP)
+		return ret ? ret : host;
+
 	/* use dsp ops pointer callback directly if set */
 	if (sof_ops(sdev)->pcm_pointer)
 		return sof_ops(sdev)->pcm_pointer(sdev, substream);

sound/soc/sof/sof-audio.h

@@ -103,7 +103,10 @@ struct snd_sof_dai_config_data {
  *	       additional memory in the SOF PCM stream structure
  * @pcm_free: Function pointer for PCM free that can be used for freeing any
  *	       additional memory in the SOF PCM stream structure
- * @delay: Function pointer for pcm delay calculation
+ * @pointer: Function pointer for pcm pointer
+ *	     Note: the @pointer callback may return -EOPNOTSUPP which should be
+ *		   handled in a same way as if the callback is not provided
+ * @delay: Function pointer for pcm delay reporting
  * @reset_hw_params_during_stop: Flag indicating whether the hw_params should be reset during the
  *				 STOP pcm trigger
  * @ipc_first_on_start: Send IPC before invoking platform trigger during
@@ -124,6 +127,9 @@ struct sof_ipc_pcm_ops {
 	int (*dai_link_fixup)(struct snd_soc_pcm_runtime *rtd, struct snd_pcm_hw_params *params);
 	int (*pcm_setup)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm);
 	void (*pcm_free)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm);
+	int (*pointer)(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream,
+		       snd_pcm_uframes_t *pointer);
 	snd_pcm_sframes_t (*delay)(struct snd_soc_component *component,
 				   struct snd_pcm_substream *substream);
 	bool reset_hw_params_during_stop;
@@ -322,6 +328,7 @@ struct snd_sof_pcm_stream {
 	struct work_struct period_elapsed_work;
 	struct snd_soc_dapm_widget_list *list; /* list of connected DAPM widgets */
 	bool d0i3_compatible; /* DSP can be in D0I3 when this pcm is opened */
+	unsigned int dsp_max_burst_size_in_ms; /* The maximum size of the host DMA burst in ms */
 	/*
 	 * flag to indicate that the DSP pipelines should be kept
 	 * active or not while suspending the stream

sound/soc/sof/sof-priv.h

@@ -262,11 +262,23 @@ struct snd_sof_dsp_ops {
 	int (*pcm_ack)(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream); /* optional */
 
 	/*
-	 * optional callback to retrieve the link DMA position for the substream
-	 * when the position is not reported in the shared SRAM windows but
-	 * instead from a host-accessible hardware counter.
+	 * optional callback to retrieve the number of frames left/arrived from/to
+	 * the DSP on the DAI side (link/codec/DMIC/etc).
+	 *
+	 * The callback is used when the firmware does not provide this information
+	 * via the shared SRAM window and it can be retrieved by host.
+	 */
+	u64 (*get_dai_frame_counter)(struct snd_sof_dev *sdev,
+				     struct snd_soc_component *component,
+				     struct snd_pcm_substream *substream); /* optional */
+
+	/*
+	 * Optional callback to retrieve the number of bytes left/arrived from/to
+	 * the DSP on the host side (bytes between host ALSA buffer and DSP).
+	 *
+	 * The callback is needed for ALSA delay reporting.
 	 */
-	u64 (*get_stream_position)(struct snd_sof_dev *sdev,
+	u64 (*get_host_byte_counter)(struct snd_sof_dev *sdev,
 				     struct snd_soc_component *component,
 				     struct snd_pcm_substream *substream); /* optional */