ASoC: SOF: Intel: mtl/lnl: Improve firmware boot state

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

This series improves the firmware/boot state handling which will allow
failed IMR boot recovery and human readable boot failure decoding.

Additionally a new debugfs file is added to force a purge/clean boot
of the DSP for developers.

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

@@ -15,6 +15,7 @@
  * Hardware interface for HDA DSP code loader
  */
 
+#include <linux/debugfs.h>
 #include <linux/firmware.h>
 #include <sound/hdaudio_ext.h>
 #include <sound/hda_register.h>
@@ -643,8 +644,12 @@ int hda_dsp_post_fw_run(struct snd_sof_dev *sdev)
 		/* Check if IMR boot is usable */
 		if (!sof_debug_check_flag(SOF_DBG_IGNORE_D3_PERSISTENT) &&
 		    (sdev->fw_ready.flags & SOF_IPC_INFO_D3_PERSISTENT ||
-		     sdev->pdata->ipc_type == SOF_IPC_TYPE_4))
+		     sdev->pdata->ipc_type == SOF_IPC_TYPE_4)) {
 			hdev->imrboot_supported = true;
+			debugfs_create_bool("skip_imr_boot",
+					    0644, sdev->debugfs_root,
+					    &hdev->skip_imr_boot);
+		}
 	}
 
 	hda_sdw_int_enable(sdev, true);

sound/soc/sof/intel/hda.c

@@ -19,6 +19,7 @@
 #include <sound/hda_register.h>
 
 #include <linux/acpi.h>
+#include <linux/debugfs.h>
 #include <linux/module.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_intel.h>
@@ -34,6 +35,7 @@
 #include "../ipc4-topology.h"
 #include "hda.h"
 #include "telemetry.h"
+#include "mtl.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sof_intel.h>
@@ -596,7 +598,7 @@ static const struct hda_dsp_msg_code hda_dsp_rom_fw_error_texts[] = {
 };
 
 #define FSR_ROM_STATE_ENTRY(state)	{FSR_STATE_ROM_##state, #state}
-static const struct hda_dsp_msg_code fsr_rom_state_names[] = {
+static const struct hda_dsp_msg_code cavs_fsr_rom_state_names[] = {
 	FSR_ROM_STATE_ENTRY(INIT),
 	FSR_ROM_STATE_ENTRY(INIT_DONE),
 	FSR_ROM_STATE_ENTRY(CSE_MANIFEST_LOADED),
@@ -619,6 +621,58 @@ static const struct hda_dsp_msg_code fsr_rom_state_names[] = {
 	FSR_ROM_STATE_ENTRY(CSE_IPC_DOWN),
 };
 
+static const struct hda_dsp_msg_code ace_fsr_rom_state_names[] = {
+	FSR_ROM_STATE_ENTRY(INIT),
+	FSR_ROM_STATE_ENTRY(INIT_DONE),
+	FSR_ROM_STATE_ENTRY(CSE_MANIFEST_LOADED),
+	FSR_ROM_STATE_ENTRY(FW_MANIFEST_LOADED),
+	FSR_ROM_STATE_ENTRY(FW_FW_LOADED),
+	FSR_ROM_STATE_ENTRY(FW_ENTERED),
+	FSR_ROM_STATE_ENTRY(VERIFY_FEATURE_MASK),
+	FSR_ROM_STATE_ENTRY(GET_LOAD_OFFSET),
+	FSR_ROM_STATE_ENTRY(RESET_VECTOR_DONE),
+	FSR_ROM_STATE_ENTRY(PURGE_BOOT),
+	FSR_ROM_STATE_ENTRY(RESTORE_BOOT),
+	FSR_ROM_STATE_ENTRY(FW_ENTRY_POINT),
+	FSR_ROM_STATE_ENTRY(VALIDATE_PUB_KEY),
+	FSR_ROM_STATE_ENTRY(POWER_DOWN_HPSRAM),
+	FSR_ROM_STATE_ENTRY(POWER_DOWN_ULPSRAM),
+	FSR_ROM_STATE_ENTRY(POWER_UP_ULPSRAM_STACK),
+	FSR_ROM_STATE_ENTRY(POWER_UP_HPSRAM_DMA),
+	FSR_ROM_STATE_ENTRY(BEFORE_EP_POINTER_READ),
+	FSR_ROM_STATE_ENTRY(VALIDATE_MANIFEST),
+	FSR_ROM_STATE_ENTRY(VALIDATE_FW_MODULE),
+	FSR_ROM_STATE_ENTRY(PROTECT_IMR_REGION),
+	FSR_ROM_STATE_ENTRY(PUSH_MODEL_ROUTINE),
+	FSR_ROM_STATE_ENTRY(PULL_MODEL_ROUTINE),
+	FSR_ROM_STATE_ENTRY(VALIDATE_PKG_DIR),
+	FSR_ROM_STATE_ENTRY(VALIDATE_CPD),
+	FSR_ROM_STATE_ENTRY(VALIDATE_CSS_MAN_HEADER),
+	FSR_ROM_STATE_ENTRY(VALIDATE_BLOB_SVN),
+	FSR_ROM_STATE_ENTRY(VERIFY_IFWI_PARTITION),
+	FSR_ROM_STATE_ENTRY(REMOVE_ACCESS_CONTROL),
+	FSR_ROM_STATE_ENTRY(AUTH_BYPASS),
+	FSR_ROM_STATE_ENTRY(AUTH_ENABLED),
+	FSR_ROM_STATE_ENTRY(INIT_DMA),
+	FSR_ROM_STATE_ENTRY(PURGE_FW_ENTRY),
+	FSR_ROM_STATE_ENTRY(PURGE_FW_END),
+	FSR_ROM_STATE_ENTRY(CLEAN_UP_BSS_DONE),
+	FSR_ROM_STATE_ENTRY(IMR_RESTORE_ENTRY),
+	FSR_ROM_STATE_ENTRY(IMR_RESTORE_END),
+	FSR_ROM_STATE_ENTRY(FW_MANIFEST_IN_DMA_BUFF),
+	FSR_ROM_STATE_ENTRY(LOAD_CSE_MAN_TO_IMR),
+	FSR_ROM_STATE_ENTRY(LOAD_FW_MAN_TO_IMR),
+	FSR_ROM_STATE_ENTRY(LOAD_FW_CODE_TO_IMR),
+	FSR_ROM_STATE_ENTRY(FW_LOADING_DONE),
+	FSR_ROM_STATE_ENTRY(FW_CODE_LOADED),
+	FSR_ROM_STATE_ENTRY(VERIFY_IMAGE_TYPE),
+	FSR_ROM_STATE_ENTRY(AUTH_API_INIT),
+	FSR_ROM_STATE_ENTRY(AUTH_API_PROC),
+	FSR_ROM_STATE_ENTRY(AUTH_API_FIRST_BUSY),
+	FSR_ROM_STATE_ENTRY(AUTH_API_FIRST_RESULT),
+	FSR_ROM_STATE_ENTRY(AUTH_API_CLEANUP),
+};
+
 #define FSR_BRINGUP_STATE_ENTRY(state)	{FSR_STATE_BRINGUP_##state, #state}
 static const struct hda_dsp_msg_code fsr_bringup_state_names[] = {
 	FSR_BRINGUP_STATE_ENTRY(INIT),
@@ -663,7 +717,7 @@ hda_dsp_get_state_text(u32 code, const struct hda_dsp_msg_code *msg_code,
 	return NULL;
 }
 
-static void hda_dsp_get_state(struct snd_sof_dev *sdev, const char *level)
+void hda_dsp_get_state(struct snd_sof_dev *sdev, const char *level)
 {
 	const struct sof_intel_dsp_desc *chip = get_chip_info(sdev->pdata);
 	const char *state_text, *error_text, *module_text;
@@ -679,12 +733,19 @@ static void hda_dsp_get_state(struct snd_sof_dev *sdev, const char *level)
 	else
 		module_text = fsr_module_names[module];
 
-	if (module == FSR_MOD_BRNGUP)
+	if (module == FSR_MOD_BRNGUP) {
 		state_text = hda_dsp_get_state_text(state, fsr_bringup_state_names,
 						    ARRAY_SIZE(fsr_bringup_state_names));
-	else
-		state_text = hda_dsp_get_state_text(state, fsr_rom_state_names,
-						    ARRAY_SIZE(fsr_rom_state_names));
+	} else {
+		if (chip->hw_ip_version < SOF_INTEL_ACE_1_0)
+			state_text = hda_dsp_get_state_text(state,
+							cavs_fsr_rom_state_names,
+							ARRAY_SIZE(cavs_fsr_rom_state_names));
+		else
+			state_text = hda_dsp_get_state_text(state,
+							ace_fsr_rom_state_names,
+							ARRAY_SIZE(ace_fsr_rom_state_names));
+	}
 
 	/* not for us, must be generic sof message */
 	if (!state_text) {

sound/soc/sof/intel/hda.h

@@ -695,6 +695,8 @@ int hda_dsp_ipc_get_window_offset(struct snd_sof_dev *sdev, u32 id);
 irqreturn_t hda_dsp_ipc_irq_thread(int irq, void *context);
 int hda_dsp_ipc_cmd_done(struct snd_sof_dev *sdev, int dir);
 
+void hda_dsp_get_state(struct snd_sof_dev *sdev, const char *level);
+
 /*
  * DSP Code loader.
  */

sound/soc/sof/intel/lnl.c

@@ -6,6 +6,7 @@
  * Hardware interface for audio DSP on LunarLake.
  */
 
+#include <linux/debugfs.h>
 #include <linux/firmware.h>
 #include <sound/hda_register.h>
 #include <sound/sof/ipc4/header.h>
@@ -16,6 +17,7 @@
 #include "hda-ipc.h"
 #include "../sof-audio.h"
 #include "mtl.h"
+#include "lnl.h"
 #include <sound/hda-mlink.h>
 
 /* LunarLake ops */
@@ -83,8 +85,12 @@ static int lnl_dsp_post_fw_run(struct snd_sof_dev *sdev)
 		struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
 
 		/* Check if IMR boot is usable */
-		if (!sof_debug_check_flag(SOF_DBG_IGNORE_D3_PERSISTENT))
+		if (!sof_debug_check_flag(SOF_DBG_IGNORE_D3_PERSISTENT)) {
 			hda->imrboot_supported = true;
+			debugfs_create_bool("skip_imr_boot",
+					    0644, sdev->debugfs_root,
+					    &hda->skip_imr_boot);
+		}
 	}
 
 	return 0;
@@ -192,7 +198,7 @@ const struct sof_intel_dsp_desc lnl_chip_info = {
 	.ipc_ack = MTL_DSP_REG_HFIPCXIDA,
 	.ipc_ack_mask = MTL_DSP_REG_HFIPCXIDA_DONE,
 	.ipc_ctl = MTL_DSP_REG_HFIPCXCTL,
-	.rom_status_reg = MTL_DSP_ROM_STS,
+	.rom_status_reg = LNL_DSP_REG_HFDSC,
 	.rom_init_timeout = 300,
 	.ssp_count = MTL_SSP_COUNT,
 	.d0i3_offset = MTL_HDA_VS_D0I3C,

sound/soc/sof/intel/lnl.h

+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * Copyright(c) 2024 Intel Corporation. All rights reserved.
+ */
+
+#ifndef __SOF_INTEL_LNL_H
+#define __SOF_INTEL_LNL_H
+
+#define LNL_DSP_REG_HFDSC		0x160200 /* DSP core0 status */
+#define LNL_DSP_REG_HFDEC		0x160204 /* DSP core0 error */
+
+#endif /* __SOF_INTEL_LNL_H */

sound/soc/sof/intel/mtl.c

@@ -9,6 +9,7 @@
  * Hardware interface for audio DSP on Meteorlake.
  */
 
+#include <linux/debugfs.h>
 #include <linux/firmware.h>
 #include <sound/sof/ipc4/header.h>
 #include <trace/events/sof_intel.h>
@@ -294,8 +295,12 @@ int mtl_dsp_post_fw_run(struct snd_sof_dev *sdev)
 		}
 
 		/* Check if IMR boot is usable */
-		if (!sof_debug_check_flag(SOF_DBG_IGNORE_D3_PERSISTENT))
+		if (!sof_debug_check_flag(SOF_DBG_IGNORE_D3_PERSISTENT)) {
 			hdev->imrboot_supported = true;
+			debugfs_create_bool("skip_imr_boot",
+					    0644, sdev->debugfs_root,
+					    &hdev->skip_imr_boot);
+		}
 	}
 
 	hda_sdw_int_enable(sdev, true);
@@ -305,22 +310,16 @@ int mtl_dsp_post_fw_run(struct snd_sof_dev *sdev)
 void mtl_dsp_dump(struct snd_sof_dev *sdev, u32 flags)
 {
 	char *level = (flags & SOF_DBG_DUMP_OPTIONAL) ? KERN_DEBUG : KERN_ERR;
-	u32 romdbgsts;
-	u32 romdbgerr;
 	u32 fwsts;
 	u32 fwlec;
 
+	hda_dsp_get_state(sdev, level);
 	fwsts = snd_sof_dsp_read(sdev, HDA_DSP_BAR, MTL_DSP_ROM_STS);
 	fwlec = snd_sof_dsp_read(sdev, HDA_DSP_BAR, MTL_DSP_ROM_ERROR);
-	romdbgsts = snd_sof_dsp_read(sdev, HDA_DSP_BAR, MTL_DSP_REG_HFFLGPXQWY);
-	romdbgerr = snd_sof_dsp_read(sdev, HDA_DSP_BAR, MTL_DSP_REG_HFFLGPXQWY_ERROR);
 
-	dev_err(sdev->dev, "ROM status: %#x, ROM error: %#x\n", fwsts, fwlec);
-	dev_err(sdev->dev, "ROM debug status: %#x, ROM debug error: %#x\n", romdbgsts,
-		romdbgerr);
-	romdbgsts = snd_sof_dsp_read(sdev, HDA_DSP_BAR, MTL_DSP_REG_HFFLGPXQWY + 0x8 * 3);
-	dev_printk(level, sdev->dev, "ROM feature bit%s enabled\n",
-		   romdbgsts & BIT(24) ? "" : " not");
+	if (fwsts != 0xffffffff)
+		dev_err(sdev->dev, "Firmware state: %#x, status/error code: %#x\n",
+			fwsts, fwlec);
 
 	sof_ipc4_intel_dump_telemetry_state(sdev, flags);
 }
@@ -439,7 +438,7 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot)
 {
 	struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
 	const struct sof_intel_dsp_desc *chip = hda->desc;
-	unsigned int status;
+	unsigned int status, target_status;
 	u32 ipc_hdr, flags;
 	char *dump_msg;
 	int ret;
@@ -485,13 +484,40 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot)
 
 	mtl_enable_ipc_interrupts(sdev);
 
+	if (chip->rom_status_reg == MTL_DSP_ROM_STS) {
+		/*
+		 * Workaround: when the ROM status register is pointing to
+		 * the SRAM window (MTL_DSP_ROM_STS) the platform cannot catch
+		 * ROM_INIT_DONE because of a very short timing window.
+		 * Follow the recommendations and skip target state waiting.
+		 */
+		return 0;
+	}
+
 	/*
-	 * ACE workaround: don't wait for ROM INIT.
-	 * The platform cannot catch ROM_INIT_DONE because of a very short
-	 * timing window. Follow the recommendations and skip this part.
+	 * step 7:
+	 * - Cold/Full boot: wait for ROM init to proceed to download the firmware
+	 * - IMR boot: wait for ROM firmware entered (firmware booted up from IMR)
 	 */
+	if (imr_boot)
+		target_status = FSR_STATE_FW_ENTERED;
+	else
+		target_status = FSR_STATE_INIT_DONE;
 
-	return 0;
+	ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
+					chip->rom_status_reg, status,
+					(FSR_TO_STATE_CODE(status) == target_status),
+					HDA_DSP_REG_POLL_INTERVAL_US,
+					chip->rom_init_timeout *
+					USEC_PER_MSEC);
+
+	if (!ret)
+		return 0;
+
+	if (hda->boot_iteration == HDA_FW_BOOT_ATTEMPTS)
+		dev_err(sdev->dev,
+			"%s: timeout with rom_status_reg (%#x) read\n",
+			__func__, chip->rom_status_reg);
 
 err:
 	flags = SOF_DBG_DUMP_PCI | SOF_DBG_DUMP_MBOX | SOF_DBG_DUMP_OPTIONAL;
@@ -503,6 +529,7 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot)
 	dump_msg = kasprintf(GFP_KERNEL, "Boot iteration failed: %d/%d",
 			     hda->boot_iteration, HDA_FW_BOOT_ATTEMPTS);
 	snd_sof_dsp_dbg_dump(sdev, dump_msg, flags);
+	mtl_enable_interrupts(sdev, false);
 	mtl_dsp_core_power_down(sdev, SOF_DSP_PRIMARY_CORE);
 
 	kfree(dump_msg);
@@ -727,7 +754,7 @@ const struct sof_intel_dsp_desc mtl_chip_info = {
 	.ipc_ack = MTL_DSP_REG_HFIPCXIDA,
 	.ipc_ack_mask = MTL_DSP_REG_HFIPCXIDA_DONE,
 	.ipc_ctl = MTL_DSP_REG_HFIPCXCTL,
-	.rom_status_reg = MTL_DSP_ROM_STS,
+	.rom_status_reg = MTL_DSP_REG_HFFLGPXQWY,
 	.rom_init_timeout	= 300,
 	.ssp_count = MTL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
@@ -755,7 +782,7 @@ const struct sof_intel_dsp_desc arl_s_chip_info = {
 	.ipc_ack = MTL_DSP_REG_HFIPCXIDA,
 	.ipc_ack_mask = MTL_DSP_REG_HFIPCXIDA_DONE,
 	.ipc_ctl = MTL_DSP_REG_HFIPCXCTL,
-	.rom_status_reg = MTL_DSP_ROM_STS,
+	.rom_status_reg = MTL_DSP_REG_HFFLGPXQWY,
 	.rom_init_timeout	= 300,
 	.ssp_count = MTL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,

sound/soc/sof/intel/mtl.h

@@ -70,8 +70,52 @@
 #define MTL_DSP_ROM_STS			MTL_SRAM_WINDOW_OFFSET(0) /* ROM status */
 #define MTL_DSP_ROM_ERROR		(MTL_SRAM_WINDOW_OFFSET(0) + 0x4) /* ROM error code */
 
-#define MTL_DSP_REG_HFFLGPXQWY		0x163200 /* ROM debug status */
-#define MTL_DSP_REG_HFFLGPXQWY_ERROR	0x163204 /* ROM debug error code */
+#define MTL_DSP_REG_HFFLGPXQWY		0x163200 /* DSP core0 status */
+#define MTL_DSP_REG_HFFLGPXQWY_ERROR	0x163204 /* DSP core0 error */
+
+/* FSR status codes */
+#define FSR_STATE_ROM_RESET_VECTOR_DONE		0x8
+#define FSR_STATE_ROM_PURGE_BOOT		0x9
+#define FSR_STATE_ROM_RESTORE_BOOT		0xA
+#define FSR_STATE_ROM_FW_ENTRY_POINT		0xB
+#define FSR_STATE_ROM_VALIDATE_PUB_KEY		0xC
+#define FSR_STATE_ROM_POWER_DOWN_HPSRAM		0xD
+#define FSR_STATE_ROM_POWER_DOWN_ULPSRAM	0xE
+#define FSR_STATE_ROM_POWER_UP_ULPSRAM_STACK	0xF
+#define FSR_STATE_ROM_POWER_UP_HPSRAM_DMA	0x10
+#define FSR_STATE_ROM_BEFORE_EP_POINTER_READ	0x11
+#define FSR_STATE_ROM_VALIDATE_MANIFEST		0x12
+#define FSR_STATE_ROM_VALIDATE_FW_MODULE	0x13
+#define FSR_STATE_ROM_PROTECT_IMR_REGION	0x14
+#define FSR_STATE_ROM_PUSH_MODEL_ROUTINE	0x15
+#define FSR_STATE_ROM_PULL_MODEL_ROUTINE	0x16
+#define FSR_STATE_ROM_VALIDATE_PKG_DIR		0x17
+#define FSR_STATE_ROM_VALIDATE_CPD		0x18
+#define FSR_STATE_ROM_VALIDATE_CSS_MAN_HEADER	0x19
+#define FSR_STATE_ROM_VALIDATE_BLOB_SVN		0x1A
+#define FSR_STATE_ROM_VERIFY_IFWI_PARTITION	0x1B
+#define FSR_STATE_ROM_REMOVE_ACCESS_CONTROL	0x1C
+#define FSR_STATE_ROM_AUTH_BYPASS		0x1D
+#define FSR_STATE_ROM_AUTH_ENABLED		0x1E
+#define FSR_STATE_ROM_INIT_DMA			0x1F
+#define FSR_STATE_ROM_PURGE_FW_ENTRY		0x20
+#define FSR_STATE_ROM_PURGE_FW_END		0x21
+#define FSR_STATE_ROM_CLEAN_UP_BSS_DONE		0x22
+#define FSR_STATE_ROM_IMR_RESTORE_ENTRY		0x23
+#define FSR_STATE_ROM_IMR_RESTORE_END		0x24
+#define FSR_STATE_ROM_FW_MANIFEST_IN_DMA_BUFF	0x25
+#define FSR_STATE_ROM_LOAD_CSE_MAN_TO_IMR	0x26
+#define FSR_STATE_ROM_LOAD_FW_MAN_TO_IMR	0x27
+#define FSR_STATE_ROM_LOAD_FW_CODE_TO_IMR	0x28
+#define FSR_STATE_ROM_FW_LOADING_DONE		0x29
+#define FSR_STATE_ROM_FW_CODE_LOADED		0x2A
+#define FSR_STATE_ROM_VERIFY_IMAGE_TYPE		0x2B
+#define FSR_STATE_ROM_AUTH_API_INIT		0x2C
+#define FSR_STATE_ROM_AUTH_API_PROC		0x2D
+#define FSR_STATE_ROM_AUTH_API_FIRST_BUSY	0x2E
+#define FSR_STATE_ROM_AUTH_API_FIRST_RESULT	0x2F
+#define FSR_STATE_ROM_AUTH_API_CLEANUP		0x30
+
 #define MTL_DSP_REG_HfIMRIS1		0x162088
 #define MTL_DSP_REG_HfIMRIS1_IU_MASK	BIT(0)