drm/amdgpu: implement smu send rma reason for smu v13.0.6

implement smu send rma reason function for smu v13.0.6

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/pm/amdgpu_dpm.c

@@ -693,6 +693,21 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si
 	return ret;
 }
 
+int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+	int ret;
+
+	if (!is_support_sw_smu(adev))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&adev->pm.mutex);
+	ret = smu_send_rma_reason(smu);
+	mutex_unlock(&adev->pm.mutex);
+
+	return ret;
+}
+
 int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev,
 				  enum pp_clock_type type,
 				  uint32_t *min,

drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h

@@ -450,6 +450,7 @@ int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_versio
 int amdgpu_dpm_handle_passthrough_sbr(struct amdgpu_device *adev, bool enable);
 int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size);
 int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t size);
+int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev);
 int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev,
 				       enum pp_clock_type type,
 				       uint32_t *min,

drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c

@@ -3679,3 +3679,13 @@ int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size)
 
 	return ret;
 }
+
+int smu_send_rma_reason(struct smu_context *smu)
+{
+	int ret = 0;
+
+	if (smu->ppt_funcs && smu->ppt_funcs->send_rma_reason)
+		ret = smu->ppt_funcs->send_rma_reason(smu);
+
+	return ret;
+}

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

@@ -1341,6 +1341,11 @@ struct pptable_funcs {
 	 */
 	int (*send_hbm_bad_pages_num)(struct smu_context *smu, uint32_t size);
 
+	/**
+	 * @send_rma_reason: message rma reason event to SMU.
+	 */
+	int (*send_rma_reason)(struct smu_context *smu);
+
 	/**
 	 * @get_ecc_table:  message SMU to get ECC INFO table.
 	 */
@@ -1588,5 +1593,6 @@ int smu_stb_collect_info(struct smu_context *smu, void *buff, uint32_t size);
 void amdgpu_smu_stb_debug_fs_init(struct amdgpu_device *adev);
 int smu_send_hbm_bad_pages_num(struct smu_context *smu, uint32_t size);
 int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size);
+int smu_send_rma_reason(struct smu_context *smu);
 #endif
 #endif

drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h

@@ -91,7 +91,8 @@
 #define PPSMC_MSG_QueryValidMcaCeCount              0x3A
 #define PPSMC_MSG_McaBankCeDumpDW                   0x3B
 #define PPSMC_MSG_SelectPLPDMode                    0x40
-#define PPSMC_Message_Count                         0x41
+#define PPSMC_MSG_RmaDueToBadPageThreshold          0x43
+#define PPSMC_Message_Count                         0x44
 
 //PPSMC Reset Types for driver msg argument
 #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET        0x1

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

@@ -261,7 +261,8 @@
 	__SMU_DUMMY_MAP(SetSoftMaxVpe),	\
 	__SMU_DUMMY_MAP(SetSoftMinVpe), \
 	__SMU_DUMMY_MAP(GetMetricsVersion), \
-	__SMU_DUMMY_MAP(EnableUCLKShadow),
+	__SMU_DUMMY_MAP(EnableUCLKShadow), \
+	__SMU_DUMMY_MAP(RmaDueToBadPageThreshold),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type

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

@@ -172,6 +172,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(McaBankDumpDW,                       PPSMC_MSG_McaBankDumpDW,                   0),
 	MSG_MAP(McaBankCeDumpDW,                     PPSMC_MSG_McaBankCeDumpDW,                 0),
 	MSG_MAP(SelectPLPDMode,                      PPSMC_MSG_SelectPLPDMode,                  0),
+	MSG_MAP(RmaDueToBadPageThreshold,            PPSMC_MSG_RmaDueToBadPageThreshold,        0),
 };
 
 // clang-format on
@@ -2381,6 +2382,24 @@ static int smu_v13_0_6_smu_send_hbm_bad_page_num(struct smu_context *smu,
 	return ret;
 }
 
+static int smu_v13_0_6_send_rma_reason(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret;
+
+	/* NOTE: the message is only valid on dGPU with pmfw 85.90.0 and above */
+	if ((adev->flags & AMD_IS_APU) || smu->smc_fw_version < 0x00555a00)
+		return 0;
+
+	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RmaDueToBadPageThreshold, NULL);
+	if (ret)
+		dev_err(smu->adev->dev,
+			"[%s] failed to send BadPageThreshold event to SMU\n",
+			__func__);
+
+	return ret;
+}
+
 static int mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
 {
 	struct smu_context *smu = adev->powerplay.pp_handle;
@@ -3095,6 +3114,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.i2c_init = smu_v13_0_6_i2c_control_init,
 	.i2c_fini = smu_v13_0_6_i2c_control_fini,
 	.send_hbm_bad_pages_num = smu_v13_0_6_smu_send_hbm_bad_page_num,
+	.send_rma_reason = smu_v13_0_6_send_rma_reason,
 };
 
 void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)