drm/amd/pm: add new data in metrics table

Export new data in the metrics table for gfx and memory
utilization counter, and each hbm temperature as well.

v2:
change the metrics table version to v1.1

v3:
fix the coding style
v4:
rebase against latest kernel

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 26 insertions, 18 deletions

diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 7d5b71e65019..79e309a789f3 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -231,6 +231,8 @@ enum pp_df_cstate {
 #define XGMI_MODE_PSTATE_D3 0
 #define XGMI_MODE_PSTATE_D0 1
 
+#define NUM_HBM_INSTANCES 4
+
 struct seq_file;
 enum amd_pp_clock_type;
 struct amd_pp_simple_clock_info;
@@ -449,6 +451,11 @@ struct gpu_metrics_v1_1 {
 	uint16_t			pcie_link_speed; // in 0.1 GT/s
 
 	uint16_t			padding;
+
+	uint32_t			gfx_activity_acc;
+	uint32_t			mem_activity_acc;
+
+	uint16_t			temperature_hbm[NUM_HBM_INSTANCES];
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h
index ef9dad9a51ff..80208e1eefc9 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h
@@ -265,8 +265,6 @@ int smu_v13_0_get_current_pcie_link_speed_level(struct smu_context *smu);
 
 int smu_v13_0_get_current_pcie_link_speed(struct smu_context *smu);
 
-void smu_v13_0_init_gpu_metrics_v1_0(struct gpu_metrics_v1_0 *gpu_metrics);
-
 int smu_v13_0_gfx_ulv_control(struct smu_context *smu,
 			      bool enablement);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index c463af1cafa0..c746cf4f8ea4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1296,10 +1296,10 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 					 void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_0 *gpu_metrics =
-		(struct gpu_metrics_v1_0 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_1 *gpu_metrics =
+		(struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table;
 	SmuMetrics_t metrics;
-	int ret = 0;
+	int i, ret = 0;
 
 	ret = smu_cmn_get_metrics_table(smu,
 					&metrics,
@@ -1307,7 +1307,7 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 	if (ret)
 		return ret;
 
-	smu_v13_0_init_gpu_metrics_v1_0(gpu_metrics);
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1);
 
 	gpu_metrics->temperature_edge = metrics.TemperatureEdge;
 	gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot;
@@ -1318,12 +1318,16 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
 	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
+	gpu_metrics->average_mm_activity = 0;
 
 	gpu_metrics->average_socket_power = metrics.AverageSocketPower;
+	gpu_metrics->energy_accumulator = 0;
 
 	gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency;
 	gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency;
 	gpu_metrics->average_uclk_frequency = metrics.AverageUclkFrequency;
+	gpu_metrics->average_vclk0_frequency = 0;
+	gpu_metrics->average_dclk0_frequency = 0;
 
 	gpu_metrics->current_gfxclk = metrics.CurrClock[PPCLK_GFXCLK];
 	gpu_metrics->current_socclk = metrics.CurrClock[PPCLK_SOCCLK];
@@ -1333,14 +1337,24 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->throttle_status = metrics.ThrottlerStatus;
 
+	gpu_metrics->current_fan_speed = 0;
+
 	gpu_metrics->pcie_link_width =
 		smu_v13_0_get_current_pcie_link_width(smu);
 	gpu_metrics->pcie_link_speed =
 		aldebaran_get_current_pcie_link_speed(smu);
 
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+
+	gpu_metrics->gfx_activity_acc = metrics.GfxBusyAcc;
+	gpu_metrics->mem_activity_acc = metrics.DramBusyAcc;
+
+	for (i = 0; i < NUM_HBM_INSTANCES; i++)
+		gpu_metrics->temperature_hbm[i] = metrics.TemperatureAllHBM[i];
+
 	*table = (void *)gpu_metrics;
 
-	return sizeof(struct gpu_metrics_v1_0);
+	return sizeof(struct gpu_metrics_v1_1);
 }
 
 static bool aldebaran_is_mode1_reset_supported(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index ce160f233323..bd3a9c89dc44 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1809,14 +1809,3 @@ int smu_v13_0_get_current_pcie_link_speed(struct smu_context *smu)
 	return link_speed[speed_level];
 }
 
-void smu_v13_0_init_gpu_metrics_v1_0(struct gpu_metrics_v1_0 *gpu_metrics)
-{
-	memset(gpu_metrics, 0xFF, sizeof(struct gpu_metrics_v1_0));
-
-	gpu_metrics->common_header.structure_size =
-		sizeof(struct gpu_metrics_v1_0);
-	gpu_metrics->common_header.format_revision = 1;
-	gpu_metrics->common_header.content_revision = 0;
-
-	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
-}