drm/amd/display: Add smu write msg id fail retry process

A benchmark stress test (12-40 machines x 48hours) found that DCN315 has
cases where DC writes to an indirect register to set the smu clock msg
id, but when we go to read the same indirect register the returned msg
id doesn't match with what we just set it to. So, to fix this retry the
write until the register's value matches with the requested value.

Cc: stable@vger.kernel.org # 6.1+
Fixes: f9490399 ("drm/amd/display: Add DCN315 CLK_MGR")
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Fudong Wang <fudong.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c

@@ -32,6 +32,7 @@
 
 #define MAX_INSTANCE                                        6
 #define MAX_SEGMENT                                         6
+#define SMU_REGISTER_WRITE_RETRY_COUNT                      5
 
 struct IP_BASE_INSTANCE {
     unsigned int segment[MAX_SEGMENT];
@@ -132,6 +133,8 @@ static int dcn315_smu_send_msg_with_param(
 		unsigned int msg_id, unsigned int param)
 {
 	uint32_t result;
+	uint32_t i = 0;
+	uint32_t read_back_data;
 
 	result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000);
 
@@ -148,10 +151,19 @@ static int dcn315_smu_send_msg_with_param(
 	/* Set the parameter register for the SMU message, unit is Mhz */
 	REG_WRITE(MP1_SMN_C2PMSG_37, param);
 
+	for (i = 0; i < SMU_REGISTER_WRITE_RETRY_COUNT; i++) {
 		/* Trigger the message transaction by writing the message ID */
 		generic_write_indirect_reg(CTX,
 			REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
 			mmMP1_C2PMSG_3, msg_id);
+		read_back_data = generic_read_indirect_reg(CTX,
+			REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
+			mmMP1_C2PMSG_3);
+		if (read_back_data == msg_id)
+			break;
+		udelay(2);
+		smu_print("SMU msg id write fail %x times. \n", i + 1);
+	}
 
 	result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000);