drm/amd/pm: Add critical temp for GC v9.4.3

Add critical temperature message support func for smu v13.0.6
and expose critical temperature as part of hw mon attributes
for GC v9.4.3

v2:
Added comment for pmfw version requirement & move the check
to get_thermal_temperature_range function

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

3 files changed, 55 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 5b1d73b00ef7..f03647fa3df6 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3311,8 +3311,10 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	    (gc_ver != IP_VERSION(9, 4, 3)) &&
 	    (attr == &sensor_dev_attr_temp2_input.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp2_label.dev_attr.attr ||
+	     attr == &sensor_dev_attr_temp2_crit.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp3_input.dev_attr.attr ||
-	     attr == &sensor_dev_attr_temp3_label.dev_attr.attr))
+	     attr == &sensor_dev_attr_temp3_label.dev_attr.attr ||
+	     attr == &sensor_dev_attr_temp3_crit.dev_attr.attr))
 		return 0;
 
 	/* hotspot temperature for gc 9,4,3*/
@@ -3324,9 +3326,7 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	/* only SOC15 dGPUs support hotspot and mem temperatures */
 	if (((adev->flags & AMD_IS_APU) || gc_ver < IP_VERSION(9, 0, 0) ||
 	    (gc_ver == IP_VERSION(9, 4, 3))) &&
-	    (attr == &sensor_dev_attr_temp2_crit.dev_attr.attr ||
-	     attr == &sensor_dev_attr_temp2_crit_hyst.dev_attr.attr ||
-	     attr == &sensor_dev_attr_temp3_crit.dev_attr.attr ||
+	     (attr == &sensor_dev_attr_temp2_crit_hyst.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp3_crit_hyst.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp1_emergency.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp2_emergency.dev_attr.attr ||
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index f71fc99447f2..e57265cf637c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -84,6 +84,7 @@
        __SMU_DUMMY_MAP(SetTjMax),                     \
        __SMU_DUMMY_MAP(SetFanTemperatureTarget),      \
        __SMU_DUMMY_MAP(PrepareMp1ForUnload),          \
+       __SMU_DUMMY_MAP(GetCTFLimit),                  \
        __SMU_DUMMY_MAP(DramLogSetDramAddrHigh),       \
        __SMU_DUMMY_MAP(DramLogSetDramAddrLow),        \
        __SMU_DUMMY_MAP(DramLogSetDramSize),           \
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 6ed9cd0a1e4e..7d8af9b309b7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -132,6 +132,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                0),
 	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                0),
 	MSG_MAP(PrepareMp1ForUnload,                 PPSMC_MSG_PrepareForDriverUnload,          0),
+	MSG_MAP(GetCTFLimit,                         PPSMC_MSG_GetCTFLimit,                     0),
 };
 
 static const struct cmn2asic_mapping smu_v13_0_6_clk_map[SMU_CLK_COUNT] = {
@@ -2081,6 +2082,54 @@ out:
 	return ret;
 }
 
+static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu,
+						     struct smu_temperature_range *range)
+{
+	struct amdgpu_device *adev = smu->adev;
+	u32 aid_temp, xcd_temp;
+	uint32_t smu_version;
+	u32 ccd_temp = 0;
+	int ret;
+
+	if (amdgpu_sriov_vf(smu->adev))
+		return 0;
+
+	if (!range)
+		return -EINVAL;
+
+	/*Check smu version, GetCtfLimit message only supported for smu version 85.69 or higher */
+	smu_cmn_get_smc_version(smu, NULL, &smu_version);
+	if (smu_version < 0x554500)
+		return 0;
+
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+					      PPSMC_AID_THM_TYPE, &aid_temp);
+	if (ret)
+		goto failed;
+
+	if (adev->flags & AMD_IS_APU) {
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+						      PPSMC_CCD_THM_TYPE, &ccd_temp);
+		if (ret)
+			goto failed;
+	}
+
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+					      PPSMC_XCD_THM_TYPE, &xcd_temp);
+	if (ret)
+		goto failed;
+
+	range->hotspot_crit_max = max3(aid_temp, xcd_temp, ccd_temp);
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+					      PPSMC_HBM_THM_TYPE, &range->mem_crit_max);
+	if (ret)
+		goto failed;
+
+	return 0;
+failed:
+	return ret;
+}
+
 static int smu_v13_0_6_mode1_reset(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -2177,6 +2226,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
 	.get_gpu_metrics = smu_v13_0_6_get_gpu_metrics,
+	.get_thermal_temperature_range = smu_v13_0_6_get_thermal_temperature_range,
 	.mode1_reset_is_support = smu_v13_0_6_is_mode1_reset_supported,
 	.mode2_reset_is_support = smu_v13_0_6_is_mode2_reset_supported,
 	.mode1_reset = smu_v13_0_6_mode1_reset,