Merge tag 'amd-drm-next-5.14-2021-06-02' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.14-2021-06-02: amdgpu: - GC/MM register access macro clean up for SR-IOV - Beige Goby updates - W=1 Fixes - Aldebaran fixes - Misc display fixes - ACPI ATCS/ATIF handling rework - SR-IOV fixes - RAS fixes - 16bpc fixed point format support - Initial smartshift support - RV/PCO power tuning fixes for suspend/resume - More buffer object subclassing work - Add new INFO query for additional vbios information - Add new placement for preemptable SG buffers amdkfd: - Misc fixes radeon: - W=1 Fixes - Misc cleanups UAPI: - Add new INFO query for additional vbios information Useful for debugging vbios related issues. Proposed umr patch: https://patchwork.freedesktop.org/patch/433297/ - 16bpc fixed point format support IGT test: https://lists.freedesktop.org/archives/igt-dev/2021-May/031507.html Proposed Vulkan patch: a25d480207 - Add a new GEM flag which is only used internally in the kernel driver. Userspace is not allowed to set it. drm: - 16bpc fixed point format fourcc Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210602214009.4553-1-alexander.deucher@amd.com
2026-05-03 14:02:43 -04:00 · 2021-06-04 06:13:56 +10:00
parent ccd1950c2f 7d9c70d235
commit 5745d647d5
164 changed files with 2704 additions and 1497 deletions
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -822,6 +822,52 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 				now) ? "*" : ""));
 		break;

+	case SMU_VCLK:
+		ret = arcturus_get_current_clk_freq_by_table(smu, SMU_VCLK, &now);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get current vclk Failed!");
+			return ret;
+		}
+
+		single_dpm_table = &(dpm_context->dpm_tables.vclk_table);
+		ret = arcturus_get_clk_table(smu, &clocks, single_dpm_table);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get vclk levels Failed!");
+			return ret;
+		}
+
+		for (i = 0; i < single_dpm_table->count; i++)
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
+				i, single_dpm_table->dpm_levels[i].value,
+				(clocks.num_levels == 1) ? "*" :
+				(arcturus_freqs_in_same_level(
+				clocks.data[i].clocks_in_khz / 1000,
+				now) ? "*" : ""));
+		break;
+
+	case SMU_DCLK:
+		ret = arcturus_get_current_clk_freq_by_table(smu, SMU_DCLK, &now);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get current dclk Failed!");
+			return ret;
+		}
+
+		single_dpm_table = &(dpm_context->dpm_tables.dclk_table);
+		ret = arcturus_get_clk_table(smu, &clocks, single_dpm_table);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get dclk levels Failed!");
+			return ret;
+		}
+
+		for (i = 0; i < single_dpm_table->count; i++)
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
+				i, single_dpm_table->dpm_levels[i].value,
+				(clocks.num_levels == 1) ? "*" :
+				(arcturus_freqs_in_same_level(
+				clocks.data[i].clocks_in_khz / 1000,
+				now) ? "*" : ""));
+		break;
+
 	case SMU_PCIE:
 		gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu);
 		lane_width = smu_v11_0_get_current_pcie_link_width_level(smu);
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -505,7 +505,7 @@ static int navi10_tables_init(struct smu_context *smu)
 		goto err0_out;
 	smu_table->metrics_time = 0;

-	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_1);
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_3);
 	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
 	if (!smu_table->gpu_metrics_table)
 		goto err1_out;
@@ -1273,6 +1273,8 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 	case SMU_MCLK:
 	case SMU_UCLK:
 	case SMU_FCLK:
+	case SMU_VCLK:
+	case SMU_DCLK:
 	case SMU_DCEFCLK:
 		ret = navi10_get_current_clk_freq_by_table(smu, clk_type, &cur_value);
 		if (ret)
@@ -2627,8 +2629,8 @@ static ssize_t navi10_get_legacy_gpu_metrics(struct smu_context *smu,
 					     void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_1 *gpu_metrics =
-		(struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_3 *gpu_metrics =
+		(struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table;
 	SmuMetrics_legacy_t metrics;
 	int ret = 0;

@@ -2646,7 +2648,7 @@ static ssize_t navi10_get_legacy_gpu_metrics(struct smu_context *smu,

 	mutex_unlock(&smu->metrics_lock);

-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1);
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3);

 	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
 	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
@@ -2681,17 +2683,27 @@ static ssize_t navi10_get_legacy_gpu_metrics(struct smu_context *smu,

 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();

+	if (metrics.CurrGfxVoltageOffset)
+		gpu_metrics->voltage_gfx =
+			(155000 - 625 * metrics.CurrGfxVoltageOffset) / 100;
+	if (metrics.CurrMemVidOffset)
+		gpu_metrics->voltage_mem =
+			(155000 - 625 * metrics.CurrMemVidOffset) / 100;
+	if (metrics.CurrSocVoltageOffset)
+		gpu_metrics->voltage_soc =
+			(155000 - 625 * metrics.CurrSocVoltageOffset) / 100;
+
 	*table = (void *)gpu_metrics;

-	return sizeof(struct gpu_metrics_v1_1);
+	return sizeof(struct gpu_metrics_v1_3);
 }

 static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,
 				      void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_1 *gpu_metrics =
-		(struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_3 *gpu_metrics =
+		(struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table;
 	SmuMetrics_t metrics;
 	int ret = 0;

@@ -2709,7 +2721,7 @@ static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,

 	mutex_unlock(&smu->metrics_lock);

-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1);
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3);

 	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
 	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
@@ -2746,17 +2758,27 @@ static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,

 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();

+	if (metrics.CurrGfxVoltageOffset)
+		gpu_metrics->voltage_gfx =
+			(155000 - 625 * metrics.CurrGfxVoltageOffset) / 100;
+	if (metrics.CurrMemVidOffset)
+		gpu_metrics->voltage_mem =
+			(155000 - 625 * metrics.CurrMemVidOffset) / 100;
+	if (metrics.CurrSocVoltageOffset)
+		gpu_metrics->voltage_soc =
+			(155000 - 625 * metrics.CurrSocVoltageOffset) / 100;
+
 	*table = (void *)gpu_metrics;

-	return sizeof(struct gpu_metrics_v1_1);
+	return sizeof(struct gpu_metrics_v1_3);
 }

 static ssize_t navi12_get_legacy_gpu_metrics(struct smu_context *smu,
 					     void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_1 *gpu_metrics =
-		(struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_3 *gpu_metrics =
+		(struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table;
 	SmuMetrics_NV12_legacy_t metrics;
 	int ret = 0;

@@ -2774,7 +2796,7 @@ static ssize_t navi12_get_legacy_gpu_metrics(struct smu_context *smu,

 	mutex_unlock(&smu->metrics_lock);

-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1);
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3);

 	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
 	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
@@ -2814,17 +2836,27 @@ static ssize_t navi12_get_legacy_gpu_metrics(struct smu_context *smu,

 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();

+	if (metrics.CurrGfxVoltageOffset)
+		gpu_metrics->voltage_gfx =
+			(155000 - 625 * metrics.CurrGfxVoltageOffset) / 100;
+	if (metrics.CurrMemVidOffset)
+		gpu_metrics->voltage_mem =
+			(155000 - 625 * metrics.CurrMemVidOffset) / 100;
+	if (metrics.CurrSocVoltageOffset)
+		gpu_metrics->voltage_soc =
+			(155000 - 625 * metrics.CurrSocVoltageOffset) / 100;
+
 	*table = (void *)gpu_metrics;

-	return sizeof(struct gpu_metrics_v1_1);
+	return sizeof(struct gpu_metrics_v1_3);
 }

 static ssize_t navi12_get_gpu_metrics(struct smu_context *smu,
 				      void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_1 *gpu_metrics =
-		(struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_3 *gpu_metrics =
+		(struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table;
 	SmuMetrics_NV12_t metrics;
 	int ret = 0;

@@ -2842,7 +2874,7 @@ static ssize_t navi12_get_gpu_metrics(struct smu_context *smu,

 	mutex_unlock(&smu->metrics_lock);

-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1);
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3);

 	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
 	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
@@ -2884,9 +2916,19 @@ static ssize_t navi12_get_gpu_metrics(struct smu_context *smu,

 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();

+	if (metrics.CurrGfxVoltageOffset)
+		gpu_metrics->voltage_gfx =
+			(155000 - 625 * metrics.CurrGfxVoltageOffset) / 100;
+	if (metrics.CurrMemVidOffset)
+		gpu_metrics->voltage_mem =
+			(155000 - 625 * metrics.CurrMemVidOffset) / 100;
+	if (metrics.CurrSocVoltageOffset)
+		gpu_metrics->voltage_soc =
+			(155000 - 625 * metrics.CurrSocVoltageOffset) / 100;
+
 	*table = (void *)gpu_metrics;

-	return sizeof(struct gpu_metrics_v1_1);
+	return sizeof(struct gpu_metrics_v1_3);
 }

 static ssize_t navi1x_get_gpu_metrics(struct smu_context *smu,
@@ -2925,6 +2967,8 @@ static ssize_t navi1x_get_gpu_metrics(struct smu_context *smu,

 static int navi10_enable_mgpu_fan_boost(struct smu_context *smu)
 {
+	struct smu_table_context *table_context = &smu->smu_table;
+	PPTable_t *smc_pptable = table_context->driver_pptable;
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t param = 0;

@@ -2932,6 +2976,13 @@ static int navi10_enable_mgpu_fan_boost(struct smu_context *smu)
 	if (adev->asic_type == CHIP_NAVI12)
 		return 0;

+	/*
+	 * Skip the MGpuFanBoost setting for those ASICs
+	 * which do not support it
+	 */
+	if (!smc_pptable->MGpuFanBoostLimitRpm)
+		return 0;
+
 	/* Workaround for WS SKU */
 	if (adev->pdev->device == 0x7312 &&
 	    adev->pdev->revision == 0)
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -987,6 +987,10 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 	case SMU_MCLK:
 	case SMU_UCLK:
 	case SMU_FCLK:
+	case SMU_VCLK:
+	case SMU_VCLK1:
+	case SMU_DCLK:
+	case SMU_DCLK1:
 	case SMU_DCEFCLK:
 		ret = sienna_cichlid_get_current_clk_freq_by_table(smu, clk_type, &cur_value);
 		if (ret)
@@ -3690,6 +3694,16 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu,

 static int sienna_cichlid_enable_mgpu_fan_boost(struct smu_context *smu)
 {
+	struct smu_table_context *table_context = &smu->smu_table;
+	PPTable_t *smc_pptable = table_context->driver_pptable;
+
+	/*
+	 * Skip the MGpuFanBoost setting for those ASICs
+	 * which do not support it
+	 */
+	if (!smc_pptable->MGpuFanBoostLimitRpm)
+		return 0;
+
 	return smu_cmn_send_smc_msg_with_param(smu,
 					       SMU_MSG_SetMGpuFanBoostLimitRpm,
 					       0,
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -109,6 +109,8 @@ static struct cmn2asic_mapping renoir_clk_map[SMU_CLK_COUNT] = {
 	CLK_MAP(SOCCLK, CLOCK_SOCCLK),
 	CLK_MAP(UCLK, CLOCK_FCLK),
 	CLK_MAP(MCLK, CLOCK_FCLK),
+	CLK_MAP(VCLK, CLOCK_VCLK),
+	CLK_MAP(DCLK, CLOCK_DCLK),
 };

 static struct cmn2asic_mapping renoir_table_map[SMU_TABLE_COUNT] = {
@@ -202,6 +204,17 @@ static int renoir_get_dpm_clk_limited(struct smu_context *smu, enum smu_clk_type
 			return -EINVAL;
 		*freq = clk_table->FClocks[dpm_level].Freq;
 		break;
+	case SMU_VCLK:
+		if (dpm_level >= NUM_VCN_DPM_LEVELS)
+			return -EINVAL;
+		*freq = clk_table->VClocks[dpm_level].Freq;
+		break;
+	case SMU_DCLK:
+		if (dpm_level >= NUM_VCN_DPM_LEVELS)
+			return -EINVAL;
+		*freq = clk_table->DClocks[dpm_level].Freq;
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -532,6 +545,14 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 		count = NUM_FCLK_DPM_LEVELS;
 		cur_value = metrics.ClockFrequency[CLOCK_FCLK];
 		break;
+	case SMU_VCLK:
+		count = NUM_VCN_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_VCLK];
+		break;
+	case SMU_DCLK:
+		count = NUM_VCN_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_DCLK];
+		break;
 	default:
 		break;
 	}
@@ -543,6 +564,8 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 	case SMU_MCLK:
 	case SMU_DCEFCLK:
 	case SMU_FCLK:
+	case SMU_VCLK:
+	case SMU_DCLK:
 		for (i = 0; i < count; i++) {
 			ret = renoir_get_dpm_clk_limited(smu, clk_type, i, &value);
 			if (ret)
@@ -730,6 +753,16 @@ static int renoir_get_dpm_clock_table(struct smu_context *smu, struct dpm_clocks
 		clock_table->MemClocks[i].Vol = table->MemClocks[i].Vol;
 	}

+	for (i = 0; i < NUM_VCN_DPM_LEVELS; i++) {
+		clock_table->VClocks[i].Freq = table->VClocks[i].Freq;
+		clock_table->VClocks[i].Vol = table->VClocks[i].Vol;
+	}
+
+	for (i = 0; i < NUM_VCN_DPM_LEVELS; i++) {
+		clock_table->DClocks[i].Freq = table->DClocks[i].Freq;
+		clock_table->DClocks[i].Vol = table->DClocks[i].Vol;
+	}
+
 	return 0;
 }

--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -78,6 +78,12 @@

 #define smnPCIE_ESM_CTRL			0x111003D0

+static const struct smu_temperature_range smu13_thermal_policy[] =
+{
+	{-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+	{ 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,			     PPSMC_MSG_TestMessage,			0),
 	MSG_MAP(GetSmuVersion,			     PPSMC_MSG_GetSmuVersion,			1),
@@ -816,6 +822,52 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 								       now) ? "*" : ""));
 		break;

+	case SMU_VCLK:
+		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_VCLK, &now);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get current vclk Failed!");
+			return ret;
+		}
+
+		single_dpm_table = &(dpm_context->dpm_tables.vclk_table);
+		ret = aldebaran_get_clk_table(smu, &clocks, single_dpm_table);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get vclk levels Failed!");
+			return ret;
+		}
+
+		for (i = 0; i < single_dpm_table->count; i++)
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
+					i, single_dpm_table->dpm_levels[i].value,
+					(clocks.num_levels == 1) ? "*" :
+					(aldebaran_freqs_in_same_level(
+								       clocks.data[i].clocks_in_khz / 1000,
+								       now) ? "*" : ""));
+		break;
+
+	case SMU_DCLK:
+		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_DCLK, &now);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get current dclk Failed!");
+			return ret;
+		}
+
+		single_dpm_table = &(dpm_context->dpm_tables.dclk_table);
+		ret = aldebaran_get_clk_table(smu, &clocks, single_dpm_table);
+		if (ret) {
+			dev_err(smu->adev->dev, "Attempt to get dclk levels Failed!");
+			return ret;
+		}
+
+		for (i = 0; i < single_dpm_table->count; i++)
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
+					i, single_dpm_table->dpm_levels[i].value,
+					(clocks.num_levels == 1) ? "*" :
+					(aldebaran_freqs_in_same_level(
+								       clocks.data[i].clocks_in_khz / 1000,
+								       now) ? "*" : ""));
+		break;
+
 	default:
 		break;
 	}
@@ -1316,10 +1368,13 @@ static int aldebaran_usr_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_

 static bool aldebaran_is_dpm_running(struct smu_context *smu)
 {
-	int ret = 0;
+	int ret;
 	uint32_t feature_mask[2];
 	unsigned long feature_enabled;
+
 	ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2);
+	if (ret)
+		return false;
 	feature_enabled = (unsigned long)((uint64_t)feature_mask[0] |
 					  ((uint64_t)feature_mask[1] << 32));
 	return !!(feature_enabled & SMC_DPM_FEATURE);
@@ -1810,10 +1865,8 @@ static int aldebaran_set_mp1_state(struct smu_context *smu,
 	case PP_MP1_STATE_UNLOAD:
 		return smu_cmn_set_mp1_state(smu, mp1_state);
 	default:
-		return -EINVAL;
+		return 0;
 	}
-
-	return 0;
 }

 static const struct pptable_funcs aldebaran_ppt_funcs = {
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -764,6 +764,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev)
 	case METRICS_VERSION(1, 2):
 		structure_size = sizeof(struct gpu_metrics_v1_2);
 		break;
+	case METRICS_VERSION(1, 3):
+		structure_size = sizeof(struct gpu_metrics_v1_3);
+		break;
 	case METRICS_VERSION(2, 0):
 		structure_size = sizeof(struct gpu_metrics_v2_0);
 		break;