Merge tag 'drm-fixes-2023-12-08' of git://anongit.freedesktop.org/drm…

…/drm

Pull drm fixes from Dave Airlie:
 "Regular weekly fixes, mostly amdgpu and i915 as usual. A couple of
  nouveau, panfrost, one core and one bridge Kconfig.

  Seems about normal for rc5.

  atomic-helpers:
   - invoke end_fb_access while owning plane state

  i915:
   - fix a missing dep for a previous fix
   - Relax BXT/GLK DSI transcoder hblank limits
   - Fix DP MST .mode_valid_ctx() return values
   - Reject DP MST modes that require bigjoiner (as it's not yet
     supported on DP MST)
   - Fix _intel_dsb_commit() variable type to allow negative values

  nouveau:
   - document some bits of gsp rm
   - flush vmm more on tu102 to avoid hangs

  panfrost:
   - fix imported dma-buf objects residency
   - fix device freq update

  bridge:
   - tc358768 - fix Kconfig

  amdgpu:
   - Disable MCBP on gfx9
   - DC vbios fix
   - eDP fix
   - dml2 UBSAN fix
   - SMU 14 fix
   - RAS fixes
   - dml KASAN/KCSAN fix
   - PSP 13 fix
   - Clockgating fixes
   - Suspend fix

  exynos:
   - fix pointer dereference
   - fix wrong error check"

* tag 'drm-fixes-2023-12-08' of git://anongit.freedesktop.org/drm/drm: (27 commits)
  drm/exynos: fix a wrong error checking
  drm/exynos: fix a potential error pointer dereference
  drm/amdgpu: fix buffer funcs setting order on suspend
  drm/amdgpu: Avoid querying DRM MGCG status
  drm/amdgpu: Update HDP 4.4.2 clock gating flags
  drm/amdgpu: Add NULL checks for function pointers
  drm/amdgpu: Restrict extended wait to PSP v13.0.6
  drm/amd/display: Increase frame warning limit with KASAN or KCSAN in dml
  drm/amdgpu: optimize the printing order of error data
  drm/amdgpu: Update fw version for boot time error query
  drm/amd/pm: support new mca smu error code decoding
  drm/amd/swsmu: update smu v14_0_0 driver if version and metrics table
  drm/amd/display: Fix array-index-out-of-bounds in dml2
  drm/amd/display: Add monitor patch for specific eDP
  drm/amd/display: Use channel_width = 2 for vram table 3.0
  drm/amdgpu: disable MCBP by default
  drm/atomic-helpers: Invoke end_fb_access while owning plane state
  drm/i915: correct the input parameter on _intel_dsb_commit()
  drm/i915/mst: Reject modes that require the bigjoiner
  drm/i915/mst: Fix .mode_valid_ctx() return values
  ...

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3791,10 +3791,6 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 		adev->gfx.mcbp = true;
 	else if (amdgpu_mcbp == 0)
 		adev->gfx.mcbp = false;
-	else if ((amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 0, 0)) &&
-		 (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(10, 0, 0)) &&
-		 adev->gfx.num_gfx_rings)
-		adev->gfx.mcbp = true;
 
 	if (amdgpu_sriov_vf(adev))
 		adev->gfx.mcbp = true;
@@ -4531,6 +4527,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (r)
 		return r;
 
+	amdgpu_ttm_set_buffer_funcs_status(adev, false);
+
 	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h

@@ -46,6 +46,8 @@
 #define MCA_REG__STATUS__ERRORCODEEXT(x)	MCA_REG_FIELD(x, 21, 16)
 #define MCA_REG__STATUS__ERRORCODE(x)		MCA_REG_FIELD(x, 15, 0)
 
+#define MCA_REG__SYND__ERRORINFORMATION(x)	MCA_REG_FIELD(x, 17, 0)
+
 enum amdgpu_mca_ip {
 	AMDGPU_MCA_IP_UNKNOW = -1,
 	AMDGPU_MCA_IP_PSP = 0,

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -28,6 +28,7 @@
 #include <linux/reboot.h>
 #include <linux/syscalls.h>
 #include <linux/pm_runtime.h>
+#include <linux/list_sort.h>
 
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
@@ -3665,6 +3666,21 @@ static struct ras_err_node *amdgpu_ras_error_node_new(void)
 	return err_node;
 }
 
+static int ras_err_info_cmp(void *priv, const struct list_head *a, const struct list_head *b)
+{
+	struct ras_err_node *nodea = container_of(a, struct ras_err_node, node);
+	struct ras_err_node *nodeb = container_of(b, struct ras_err_node, node);
+	struct amdgpu_smuio_mcm_config_info *infoa = &nodea->err_info.mcm_info;
+	struct amdgpu_smuio_mcm_config_info *infob = &nodeb->err_info.mcm_info;
+
+	if (unlikely(infoa->socket_id != infob->socket_id))
+		return infoa->socket_id - infob->socket_id;
+	else
+		return infoa->die_id - infob->die_id;
+
+	return 0;
+}
+
 static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_data,
 						      struct amdgpu_smuio_mcm_config_info *mcm_info)
 {
@@ -3682,6 +3698,7 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 
 	err_data->err_list_count++;
 	list_add_tail(&err_node->node, &err_data->err_node_list);
+	list_sort(NULL, &err_data->err_node_list, ras_err_info_cmp);
 
 	return &err_node->err_info;
 }

drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c

@@ -129,6 +129,11 @@ static void hdp_v4_0_get_clockgating_state(struct amdgpu_device *adev,
 {
 	int data;
 
+	if (amdgpu_ip_version(adev, HDP_HWIP, 0) == IP_VERSION(4, 4, 2)) {
+		/* Default enabled */
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+		return;
+	}
 	/* AMD_CG_SUPPORT_HDP_LS */
 	data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_LS));
 	if (data & HDP_MEM_POWER_LS__LS_ENABLE_MASK)

drivers/gpu/drm/amd/amdgpu/psp_v13_0.c

@@ -60,7 +60,7 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin");
 #define GFX_CMD_USB_PD_USE_LFB 0x480
 
 /* Retry times for vmbx ready wait */
-#define PSP_VMBX_POLLING_LIMIT 20000
+#define PSP_VMBX_POLLING_LIMIT 3000
 
 /* VBIOS gfl defines */
 #define MBOX_READY_MASK 0x80000000
@@ -161,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp)
 static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
-	int retry_loop, ret;
+	int retry_loop, retry_cnt, ret;
 
+	retry_cnt =
+		(amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6)) ?
+			PSP_VMBX_POLLING_LIMIT :
+			10;
 	/* Wait for bootloader to signify that it is ready having bit 31 of
 	 * C2PMSG_35 set to 1. All other bits are expected to be cleared.
 	 * If there is an error in processing command, bits[7:0] will be set.
 	 * This is applicable for PSP v13.0.6 and newer.
 	 */
-	for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) {
+	for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) {
 		ret = psp_wait_for(
 			psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
 			0x80000000, 0xffffffff, false);
@@ -821,7 +825,7 @@ static int psp_v13_0_query_boot_status(struct psp_context *psp)
 	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))
 		return 0;
 
-	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007)
+	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10109)
 		return 0;
 
 	for_each_inst(i, inst_mask) {

drivers/gpu/drm/amd/amdgpu/soc15.c

@@ -1423,11 +1423,14 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	adev->nbio.funcs->get_clockgating_state(adev, flags);
+	if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state)
+		adev->nbio.funcs->get_clockgating_state(adev, flags);
 
-	adev->hdp.funcs->get_clock_gating_state(adev, flags);
+	if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state)
+		adev->hdp.funcs->get_clock_gating_state(adev, flags);
 
-	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) {
+	if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) &&
+	    (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))) {
 		/* AMD_CG_SUPPORT_DRM_MGCG */
 		data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0));
 		if (!(data & 0x01000000))
@@ -1440,9 +1443,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	}
 
 	/* AMD_CG_SUPPORT_ROM_MGCG */
-	adev->smuio.funcs->get_clock_gating_state(adev, flags);
+	if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state)
+		adev->smuio.funcs->get_clock_gating_state(adev, flags);
 
-	adev->df.funcs->get_clockgating_state(adev, flags);
+	if (adev->df.funcs && adev->df.funcs->get_clockgating_state)
+		adev->df.funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c

@@ -63,6 +63,12 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
 		DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id);
 		edid_caps->panel_patch.disable_fams = true;
 		break;
+	/* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */
+	case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB):
+	case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B):
+		DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id);
+		edid_caps->panel_patch.remove_sink_ext_caps = true;
+		break;
 	default:
 		return;
 	}

drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c

@@ -2386,7 +2386,13 @@ static enum bp_result get_vram_info_v30(
 		return BP_RESULT_BADBIOSTABLE;
 
 	info->num_chans = info_v30->channel_num;
-	info->dram_channel_width_bytes = (1 << info_v30->channel_width) / 8;
+	/* As suggested by VBIOS we should always use
+	 * dram_channel_width_bytes = 2 when using VRAM
+	 * table version 3.0. This is because the channel_width
+	 * param in the VRAM info table is changed in 7000 series and
+	 * no longer represents the memory channel width.
+	 */
+	info->dram_channel_width_bytes = 2;
 
 	return result;
 }

drivers/gpu/drm/amd/display/dc/dml/Makefile

@@ -61,8 +61,12 @@ endif
 endif
 
 ifneq ($(CONFIG_FRAME_WARN),0)
+ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
+frame_warn_flag := -Wframe-larger-than=3072
+else
 frame_warn_flag := -Wframe-larger-than=2048
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)

drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c

@@ -9447,12 +9447,12 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 
 		// Output
 		CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark
-		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[j];
+		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0];
 		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
 		CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[]
-		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[j];
+		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0];
 		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported
-		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[j];
+		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0];
 
 		CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 			&mode_lib->scratch,

drivers/gpu/drm/amd/include/kgd_pp_interface.h

@@ -1085,6 +1085,10 @@ struct gpu_metrics_v3_0 {
 	uint16_t			average_dram_reads;
 	/* time filtered DRAM write bandwidth [MB/sec] */
 	uint16_t			average_dram_writes;
+	/* time filtered IPU read bandwidth [MB/sec] */
+	uint16_t			average_ipu_reads;
+	/* time filtered IPU write bandwidth [MB/sec] */
+	uint16_t			average_ipu_writes;
 
 	/* Driver attached timestamp (in ns) */
 	uint64_t			system_clock_counter;
@@ -1104,6 +1108,8 @@ struct gpu_metrics_v3_0 {
 	uint32_t			average_all_core_power;
 	/* calculated core power [mW] */
 	uint16_t			average_core_power[16];
+	/* time filtered total system power [mW] */
+	uint16_t			average_sys_power;
 	/* maximum IRM defined STAPM power limit [mW] */
 	uint16_t			stapm_power_limit;
 	/* time filtered STAPM power limit [mW] */
@@ -1116,6 +1122,8 @@ struct gpu_metrics_v3_0 {
 	uint16_t			average_ipuclk_frequency;
 	uint16_t			average_fclk_frequency;
 	uint16_t			average_vclk_frequency;
+	uint16_t			average_uclk_frequency;
+	uint16_t			average_mpipu_frequency;
 
 	/* Current clocks */
 	/* target core frequency [MHz] */
@@ -1125,6 +1133,15 @@ struct gpu_metrics_v3_0 {
 	/* GFXCLK frequency limit enforced on GFX [MHz] */
 	uint16_t			current_gfx_maxfreq;
 
+	/* Throttle Residency (ASIC dependent) */
+	uint32_t			throttle_residency_prochot;
+	uint32_t			throttle_residency_spl;
+	uint32_t			throttle_residency_fppt;
+	uint32_t			throttle_residency_sppt;
+	uint32_t			throttle_residency_thm_core;
+	uint32_t			throttle_residency_thm_gfx;
+	uint32_t			throttle_residency_thm_soc;
+
 	/* Metrics table alpha filter time constant [us] */
 	uint32_t			time_filter_alphavalue;
 };

drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h

@@ -1408,6 +1408,16 @@ typedef enum {
 	METRICS_PCIE_WIDTH,
 	METRICS_CURR_FANPWM,
 	METRICS_CURR_SOCKETPOWER,
+	METRICS_AVERAGE_VPECLK,
+	METRICS_AVERAGE_IPUCLK,
+	METRICS_AVERAGE_MPIPUCLK,
+	METRICS_THROTTLER_RESIDENCY_PROCHOT,
+	METRICS_THROTTLER_RESIDENCY_SPL,
+	METRICS_THROTTLER_RESIDENCY_FPPT,
+	METRICS_THROTTLER_RESIDENCY_SPPT,
+	METRICS_THROTTLER_RESIDENCY_THM_CORE,
+	METRICS_THROTTLER_RESIDENCY_THM_GFX,
+	METRICS_THROTTLER_RESIDENCY_THM_SOC,
 } MetricsMember_t;
 
 enum smu_cmn2asic_mapping_type {

drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h

@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 6
+#define PMFW_DRIVER_IF_VERSION 7
 
 typedef struct {
   int32_t value;
@@ -150,37 +150,50 @@ typedef struct {
 } DpmClocks_t;
 
 typedef struct {
-  uint16_t CoreFrequency[16];        //Target core frequency [MHz]
-  uint16_t CorePower[16];            //CAC calculated core power [mW]
-  uint16_t CoreTemperature[16];      //TSEN measured core temperature [centi-C]
-  uint16_t GfxTemperature;           //TSEN measured GFX temperature [centi-C]
-  uint16_t SocTemperature;           //TSEN measured SOC temperature [centi-C]
-  uint16_t StapmOpnLimit;            //Maximum IRM defined STAPM power limit [mW]
-  uint16_t StapmCurrentLimit;        //Time filtered STAPM power limit [mW]
-  uint16_t InfrastructureCpuMaxFreq; //CCLK frequency limit enforced on classic cores [MHz]
-  uint16_t InfrastructureGfxMaxFreq; //GFXCLK frequency limit enforced on GFX [MHz]
-  uint16_t SkinTemp;                 //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C]
-  uint16_t GfxclkFrequency;          //Time filtered target GFXCLK frequency [MHz]
-  uint16_t FclkFrequency;            //Time filtered target FCLK frequency [MHz]
-  uint16_t GfxActivity;              //Time filtered GFX busy % [0-100]
-  uint16_t SocclkFrequency;          //Time filtered target SOCCLK frequency [MHz]
-  uint16_t VclkFrequency;            //Time filtered target VCLK frequency [MHz]
-  uint16_t VcnActivity;              //Time filtered VCN busy % [0-100]
-  uint16_t VpeclkFrequency;          //Time filtered target VPECLK frequency [MHz]
-  uint16_t IpuclkFrequency;          //Time filtered target IPUCLK frequency [MHz]
-  uint16_t IpuBusy[8];               //Time filtered IPU per-column busy % [0-100]
-  uint16_t DRAMReads;                //Time filtered DRAM read bandwidth [MB/sec]
-  uint16_t DRAMWrites;               //Time filtered DRAM write bandwidth [MB/sec]
-  uint16_t CoreC0Residency[16];      //Time filtered per-core C0 residency % [0-100]
-  uint16_t IpuPower;                 //Time filtered IPU power [mW]
-  uint32_t ApuPower;                 //Time filtered APU power [mW]
-  uint32_t GfxPower;                 //Time filtered GFX power [mW]
-  uint32_t dGpuPower;                //Time filtered dGPU power [mW]
-  uint32_t SocketPower;              //Time filtered power used for PPT/STAPM [APU+dGPU] [mW]
-  uint32_t AllCorePower;             //Time filtered sum of core power across all cores in the socket [mW]
-  uint32_t FilterAlphaValue;         //Metrics table alpha filter time constant [us]
-  uint32_t MetricsCounter;           //Counter that is incremented on every metrics table update [PM_TIMER cycles]
-  uint32_t spare[16];
+  uint16_t CoreFrequency[16];          //Target core frequency [MHz]
+  uint16_t CorePower[16];              //CAC calculated core power [mW]
+  uint16_t CoreTemperature[16];        //TSEN measured core temperature [centi-C]
+  uint16_t GfxTemperature;             //TSEN measured GFX temperature [centi-C]
+  uint16_t SocTemperature;             //TSEN measured SOC temperature [centi-C]
+  uint16_t StapmOpnLimit;              //Maximum IRM defined STAPM power limit [mW]
+  uint16_t StapmCurrentLimit;          //Time filtered STAPM power limit [mW]
+  uint16_t InfrastructureCpuMaxFreq;   //CCLK frequency limit enforced on classic cores [MHz]
+  uint16_t InfrastructureGfxMaxFreq;   //GFXCLK frequency limit enforced on GFX [MHz]
+  uint16_t SkinTemp;                   //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C]
+  uint16_t GfxclkFrequency;            //Time filtered target GFXCLK frequency [MHz]
+  uint16_t FclkFrequency;              //Time filtered target FCLK frequency [MHz]
+  uint16_t GfxActivity;                //Time filtered GFX busy % [0-100]
+  uint16_t SocclkFrequency;            //Time filtered target SOCCLK frequency [MHz]
+  uint16_t VclkFrequency;              //Time filtered target VCLK frequency [MHz]
+  uint16_t VcnActivity;                //Time filtered VCN busy % [0-100]
+  uint16_t VpeclkFrequency;            //Time filtered target VPECLK frequency [MHz]
+  uint16_t IpuclkFrequency;            //Time filtered target IPUCLK frequency [MHz]
+  uint16_t IpuBusy[8];                 //Time filtered IPU per-column busy % [0-100]
+  uint16_t DRAMReads;                  //Time filtered DRAM read bandwidth [MB/sec]
+  uint16_t DRAMWrites;                 //Time filtered DRAM write bandwidth [MB/sec]
+  uint16_t CoreC0Residency[16];        //Time filtered per-core C0 residency % [0-100]
+  uint16_t IpuPower;                   //Time filtered IPU power [mW]
+  uint32_t ApuPower;                   //Time filtered APU power [mW]
+  uint32_t GfxPower;                   //Time filtered GFX power [mW]
+  uint32_t dGpuPower;                  //Time filtered dGPU power [mW]
+  uint32_t SocketPower;                //Time filtered power used for PPT/STAPM [APU+dGPU] [mW]
+  uint32_t AllCorePower;               //Time filtered sum of core power across all cores in the socket [mW]
+  uint32_t FilterAlphaValue;           //Metrics table alpha filter time constant [us]
+  uint32_t MetricsCounter;             //Counter that is incremented on every metrics table update [PM_TIMER cycles]
+  uint16_t MemclkFrequency;            //Time filtered target MEMCLK frequency [MHz]
+  uint16_t MpipuclkFrequency;          //Time filtered target MPIPUCLK frequency [MHz]
+  uint16_t IpuReads;                   //Time filtered IPU read bandwidth [MB/sec]
+  uint16_t IpuWrites;                  //Time filtered IPU write bandwidth [MB/sec]
+  uint32_t ThrottleResidency_PROCHOT;  //Counter that is incremented on every metrics table update when PROCHOT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_SPL;      //Counter that is incremented on every metrics table update when SPL was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_FPPT;     //Counter that is incremented on every metrics table update when fast PPT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_SPPT;     //Counter that is incremented on every metrics table update when slow PPT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_CORE; //Counter that is incremented on every metrics table update when CORE thermal throttling was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_GFX;  //Counter that is incremented on every metrics table update when GFX thermal throttling was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_SOC;  //Counter that is incremented on every metrics table update when SOC thermal throttling was engaged [PM_TIMER cycles]
+  uint16_t Psys;                       //Time filtered Psys power [mW]
+  uint16_t spare1;
+  uint32_t spare[6];
 } SmuMetrics_t;
 
 //ISP tile definitions

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c

@@ -2593,13 +2593,20 @@ static bool mca_gfx_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct
 static bool mca_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
 				  enum amdgpu_mca_error_type type, struct mca_bank_entry *entry)
 {
+	struct smu_context *smu = adev->powerplay.pp_handle;
 	uint32_t errcode, instlo;
 
 	instlo = REG_GET_FIELD(entry->regs[MCA_REG_IDX_IPID], MCMP1_IPIDT0, InstanceIdLo);
 	if (instlo != 0x03b30400)
 		return false;
 
-	errcode = REG_GET_FIELD(entry->regs[MCA_REG_IDX_STATUS], MCMP1_STATUST0, ErrorCode);
+	if (!(adev->flags & AMD_IS_APU) && smu->smc_fw_version >= 0x00555600) {
+		errcode = MCA_REG__SYND__ERRORINFORMATION(entry->regs[MCA_REG_IDX_SYND]);
+		errcode &= 0xff;
+	} else {
+		errcode = REG_GET_FIELD(entry->regs[MCA_REG_IDX_STATUS], MCMP1_STATUST0, ErrorCode);
+	}
+
 	return mca_smu_check_error_code(adev, mca_ras, errcode);
 }