drm/amd/display: Toggle additional RCO options in DCN35

[Why]
With root clock optimization now enabled for DCN35 there
are still RCO registers still not being toggled

[How]
Add in logic to toggle RCO registers for DPPCLK,
DPSTREAMCLK and DSCCLK
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Roman Li <roman.li@amd.com>
Signed-off-by: Daniel Miess <daniel.miess@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/dc.h

@@ -695,6 +695,7 @@ enum pg_hw_pipe_resources {
 	PG_MPCC,
 	PG_OPP,
 	PG_OPTC,
+	PG_DPSTREAM,
 	PG_HW_PIPE_RESOURCES_NUM_ELEMENT
 };
 

drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c

@@ -49,15 +49,23 @@ static void dcn35_set_dppclk_enable(struct dccg *dccg,
 	switch (dpp_inst) {
 	case 0:
 		REG_UPDATE(DPPCLK_CTRL, DPPCLK0_EN, enable);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable);
 		break;
 	case 1:
 		REG_UPDATE(DPPCLK_CTRL, DPPCLK1_EN, enable);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable);
 		break;
 	case 2:
 		REG_UPDATE(DPPCLK_CTRL, DPPCLK2_EN, enable);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable);
 		break;
 	case 3:
 		REG_UPDATE(DPPCLK_CTRL, DPPCLK3_EN, enable);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable);
 		break;
 	default:
 		break;
@@ -100,6 +108,32 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst,
 	dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk;
 }
 
+static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg,
+		 uint32_t dpp_inst, uint32_t enable)
+{
+	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+		return;
+
+	switch (dpp_inst) {
+	case 0:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable);
+		break;
+	case 1:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable);
+		break;
+	case 2:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable);
+		break;
+	case 3:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable);
+		break;
+	default:
+		break;
+	}
+}
+
 static void dccg35_get_pixel_rate_div(
 		struct dccg *dccg,
 		uint32_t otg_inst,
@@ -333,21 +367,67 @@ static void dccg35_set_dpstreamclk(
 	/* enabled to select one of the DTBCLKs for pipe */
 	switch (dp_hpo_inst) {
 	case 0:
-		REG_UPDATE_2(DPSTREAMCLK_CNTL,
-				DPSTREAMCLK0_EN,
+		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK0_EN,
 				(src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, otg_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK0_ROOT_GATE_DISABLE, (src == REFCLK) ? 0 : 1);
 		break;
 	case 1:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK1_EN,
 				(src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, otg_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK1_ROOT_GATE_DISABLE, (src == REFCLK) ? 0 : 1);
 		break;
 	case 2:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK2_EN,
 				(src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, otg_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK2_ROOT_GATE_DISABLE, (src == REFCLK) ? 0 : 1);
 		break;
 	case 3:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK3_EN,
 				(src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, otg_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK3_ROOT_GATE_DISABLE, (src == REFCLK) ? 0 : 1);
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+}
+
+
+static void dccg35_set_dpstreamclk_root_clock_gating(
+		struct dccg *dccg,
+		int dp_hpo_inst,
+		bool enable)
+{
+	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+
+	switch (dp_hpo_inst) {
+	case 0:
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) {
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK0_ROOT_GATE_DISABLE, enable ? 1 : 0);
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK0_GATE_DISABLE, enable ? 1 : 0);
+		}
+		break;
+	case 1:
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) {
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK1_ROOT_GATE_DISABLE, enable ? 1 : 0);
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK1_GATE_DISABLE, enable ? 1 : 0);
+		}
+		break;
+	case 2:
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) {
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK2_ROOT_GATE_DISABLE, enable ? 1 : 0);
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK2_GATE_DISABLE, enable ? 1 : 0);
+		}
+		break;
+	case 3:
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) {
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK3_ROOT_GATE_DISABLE, enable ? 1 : 0);
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DPSTREAMCLK3_GATE_DISABLE, enable ? 1 : 0);
+		}
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -355,6 +435,8 @@ static void dccg35_set_dpstreamclk(
 	}
 }
 
+
+
 static void dccg35_set_physymclk_root_clock_gating(
 		struct dccg *dccg,
 		int phy_inst,
@@ -369,22 +451,32 @@ static void dccg35_set_physymclk_root_clock_gating(
 	case 0:
 		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
 				PHYASYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+//		REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//				PHYA_REFCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
 		break;
 	case 1:
 		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
 				PHYBSYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+//		REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//				PHYB_REFCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
 		break;
 	case 2:
 		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
 				PHYCSYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+//		REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//				PHYC_REFCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
 		break;
 	case 3:
 		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
 				PHYDSYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+//		REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//				PHYD_REFCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
 		break;
 	case 4:
 		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
 				PHYESYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+//		REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//				PHYE_REFCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -407,10 +499,16 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYASYMCLK_CLOCK_CNTL,
 					PHYASYMCLK_EN, 1,
 					PHYASYMCLK_SRC_SEL, clk_src);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYA_REFCLK_ROOT_GATE_DISABLE, 0);
 		} else {
 			REG_UPDATE_2(PHYASYMCLK_CLOCK_CNTL,
 					PHYASYMCLK_EN, 0,
 					PHYASYMCLK_SRC_SEL, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYA_REFCLK_ROOT_GATE_DISABLE, 1);
 		}
 		break;
 	case 1:
@@ -418,10 +516,16 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYBSYMCLK_CLOCK_CNTL,
 					PHYBSYMCLK_EN, 1,
 					PHYBSYMCLK_SRC_SEL, clk_src);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYB_REFCLK_ROOT_GATE_DISABLE, 0);
 		} else {
 			REG_UPDATE_2(PHYBSYMCLK_CLOCK_CNTL,
 					PHYBSYMCLK_EN, 0,
 					PHYBSYMCLK_SRC_SEL, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYB_REFCLK_ROOT_GATE_DISABLE, 1);
 		}
 		break;
 	case 2:
@@ -429,10 +533,16 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYCSYMCLK_CLOCK_CNTL,
 					PHYCSYMCLK_EN, 1,
 					PHYCSYMCLK_SRC_SEL, clk_src);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYC_REFCLK_ROOT_GATE_DISABLE, 0);
 		} else {
 			REG_UPDATE_2(PHYCSYMCLK_CLOCK_CNTL,
 					PHYCSYMCLK_EN, 0,
 					PHYCSYMCLK_SRC_SEL, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYC_REFCLK_ROOT_GATE_DISABLE, 1);
 		}
 		break;
 	case 3:
@@ -440,10 +550,16 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYDSYMCLK_CLOCK_CNTL,
 					PHYDSYMCLK_EN, 1,
 					PHYDSYMCLK_SRC_SEL, clk_src);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYD_REFCLK_ROOT_GATE_DISABLE, 0);
 		} else {
 			REG_UPDATE_2(PHYDSYMCLK_CLOCK_CNTL,
 					PHYDSYMCLK_EN, 0,
 					PHYDSYMCLK_SRC_SEL, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYD_REFCLK_ROOT_GATE_DISABLE, 1);
 		}
 		break;
 	case 4:
@@ -451,10 +567,16 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYESYMCLK_CLOCK_CNTL,
 					PHYESYMCLK_EN, 1,
 					PHYESYMCLK_SRC_SEL, clk_src);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYE_REFCLK_ROOT_GATE_DISABLE, 0);
 		} else {
 			REG_UPDATE_2(PHYESYMCLK_CLOCK_CNTL,
 					PHYESYMCLK_EN, 0,
 					PHYESYMCLK_SRC_SEL, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
+//						PHYE_REFCLK_ROOT_GATE_DISABLE, 1);
 		}
 		break;
 	default:
@@ -491,12 +613,12 @@ static void dccg35_dpp_root_clock_control(
 
 	if (clock_on) {
 		/* turn off the DTO and leave phase/modulo at max */
-		dcn35_set_dppclk_enable(dccg, dpp_inst, 0);
+		dcn35_set_dppclk_enable(dccg, dpp_inst, 1);
 		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
 			  DPPCLK0_DTO_PHASE, 0xFF,
 			  DPPCLK0_DTO_MODULO, 0xFF);
 	} else {
-		dcn35_set_dppclk_enable(dccg, dpp_inst, 1);
+		dcn35_set_dppclk_enable(dccg, dpp_inst, 0);
 		/* turn on the DTO to generate a 0hz clock */
 		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
 			  DPPCLK0_DTO_PHASE, 0,
@@ -575,18 +697,32 @@ void dccg35_init(struct dccg *dccg)
 		dccg35_disable_symclk32_se(dccg, otg_inst);
 
 	if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le)
-		for (otg_inst = 0; otg_inst < 2; otg_inst++)
+		for (otg_inst = 0; otg_inst < 2; otg_inst++) {
 			dccg31_disable_symclk32_le(dccg, otg_inst);
+			dccg31_set_symclk32_le_root_clock_gating(dccg, otg_inst, false);
+		}
+
+//	if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+//		for (otg_inst = 0; otg_inst < 4; otg_inst++)
+//			dccg35_disable_symclk_se(dccg, otg_inst, otg_inst);
+
 
 	if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream)
-		for (otg_inst = 0; otg_inst < 4; otg_inst++)
-			dccg314_set_dpstreamclk(dccg, REFCLK, otg_inst,
+		for (otg_inst = 0; otg_inst < 4; otg_inst++) {
+			dccg35_set_dpstreamclk(dccg, REFCLK, otg_inst,
 						otg_inst);
+			dccg35_set_dpstreamclk_root_clock_gating(dccg, otg_inst, false);
+		}
 
 	if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
 		for (otg_inst = 0; otg_inst < 5; otg_inst++)
 			dccg35_set_physymclk_root_clock_gating(dccg, otg_inst,
 					false);
+
+	if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+		for (otg_inst = 0; otg_inst < 4; otg_inst++)
+			dccg35_set_dppclk_root_clock_gating(dccg, otg_inst, 0);
+
 /*
 	dccg35_enable_global_fgcg_rep(
 		dccg, dccg->ctx->dc->debug.enable_fine_grain_clock_gating.bits
@@ -611,24 +747,32 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 				DSCCLK0_DTO_PHASE, 0,
 				DSCCLK0_DTO_MODULO, 0);
 		REG_UPDATE(DSCCLK_DTO_CTRL,	DSCCLK0_EN, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1);
 		break;
 	case 1:
 		REG_UPDATE_2(DSCCLK1_DTO_PARAM,
 				DSCCLK1_DTO_PHASE, 0,
 				DSCCLK1_DTO_MODULO, 0);
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1);
 		break;
 	case 2:
 		REG_UPDATE_2(DSCCLK2_DTO_PARAM,
 				DSCCLK2_DTO_PHASE, 0,
 				DSCCLK2_DTO_MODULO, 0);
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1);
 		break;
 	case 3:
 		REG_UPDATE_2(DSCCLK3_DTO_PARAM,
 				DSCCLK3_DTO_PHASE, 0,
 				DSCCLK3_DTO_MODULO, 0);
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK3_EN, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -650,24 +794,32 @@ static void dccg35_disable_dscclk(struct dccg *dccg,
 		REG_UPDATE_2(DSCCLK0_DTO_PARAM,
 				DSCCLK0_DTO_PHASE, 0,
 				DSCCLK0_DTO_MODULO, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 0);
 		break;
 	case 1:
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 0);
 		REG_UPDATE_2(DSCCLK1_DTO_PARAM,
 				DSCCLK1_DTO_PHASE, 0,
 				DSCCLK1_DTO_MODULO, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 0);
 		break;
 	case 2:
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 0);
 		REG_UPDATE_2(DSCCLK2_DTO_PARAM,
 				DSCCLK2_DTO_PHASE, 0,
 				DSCCLK2_DTO_MODULO, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 0);
 		break;
 	case 3:
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK3_EN, 0);
 		REG_UPDATE_2(DSCCLK3_DTO_PARAM,
 				DSCCLK3_DTO_PHASE, 0,
 				DSCCLK3_DTO_MODULO, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 0);
 		break;
 	default:
 		return;
@@ -682,22 +834,32 @@ static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst,
 	case 0:
 		REG_UPDATE(SYMCLKA_CLOCK_ENABLE,
 				SYMCLKA_CLOCK_ENABLE, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKA_ROOT_GATE_DISABLE, 1);
 		break;
 	case 1:
 		REG_UPDATE(SYMCLKB_CLOCK_ENABLE,
 				SYMCLKB_CLOCK_ENABLE, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKB_ROOT_GATE_DISABLE, 1);
 		break;
 	case 2:
 		REG_UPDATE(SYMCLKC_CLOCK_ENABLE,
 				SYMCLKC_CLOCK_ENABLE, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKC_ROOT_GATE_DISABLE, 1);
 		break;
 	case 3:
 		REG_UPDATE(SYMCLKD_CLOCK_ENABLE,
 				SYMCLKD_CLOCK_ENABLE, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKD_ROOT_GATE_DISABLE, 1);
 		break;
 	case 4:
 		REG_UPDATE(SYMCLKE_CLOCK_ENABLE,
 				SYMCLKE_CLOCK_ENABLE, 1);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKE_ROOT_GATE_DISABLE, 1);
 		break;
 	}
 
@@ -706,26 +868,36 @@ static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst,
 		REG_UPDATE_2(SYMCLKA_CLOCK_ENABLE,
 				SYMCLKA_FE_EN, 1,
 				SYMCLKA_FE_SRC_SEL, link_enc_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKA_FE_ROOT_GATE_DISABLE, 1);
 		break;
 	case 1:
 		REG_UPDATE_2(SYMCLKB_CLOCK_ENABLE,
 				SYMCLKB_FE_EN, 1,
 				SYMCLKB_FE_SRC_SEL, link_enc_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKB_FE_ROOT_GATE_DISABLE, 1);
 		break;
 	case 2:
 		REG_UPDATE_2(SYMCLKC_CLOCK_ENABLE,
 				SYMCLKC_FE_EN, 1,
 				SYMCLKC_FE_SRC_SEL, link_enc_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKC_FE_ROOT_GATE_DISABLE, 1);
 		break;
 	case 3:
 		REG_UPDATE_2(SYMCLKD_CLOCK_ENABLE,
 				SYMCLKD_FE_EN, 1,
 				SYMCLKD_FE_SRC_SEL, link_enc_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKD_FE_ROOT_GATE_DISABLE, 1);
 		break;
 	case 4:
 		REG_UPDATE_2(SYMCLKE_CLOCK_ENABLE,
 				SYMCLKE_FE_EN, 1,
 				SYMCLKE_FE_SRC_SEL, link_enc_inst);
+		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKE_FE_ROOT_GATE_DISABLE, 1);
 		break;
 	}
 }
@@ -786,26 +958,36 @@ static void dccg35_disable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst
 		REG_UPDATE_2(SYMCLKA_CLOCK_ENABLE,
 				SYMCLKA_FE_EN, 0,
 				SYMCLKA_FE_SRC_SEL, 0);
+//		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+//			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKA_FE_ROOT_GATE_DISABLE, 0);
 		break;
 	case 1:
 		REG_UPDATE_2(SYMCLKB_CLOCK_ENABLE,
 				SYMCLKB_FE_EN, 0,
 				SYMCLKB_FE_SRC_SEL, 0);
+//		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+//			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKB_FE_ROOT_GATE_DISABLE, 0);
 		break;
 	case 2:
 		REG_UPDATE_2(SYMCLKC_CLOCK_ENABLE,
 				SYMCLKC_FE_EN, 0,
 				SYMCLKC_FE_SRC_SEL, 0);
+//		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+//			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKC_FE_ROOT_GATE_DISABLE, 0);
 		break;
 	case 3:
 		REG_UPDATE_2(SYMCLKD_CLOCK_ENABLE,
 				SYMCLKD_FE_EN, 0,
 				SYMCLKD_FE_SRC_SEL, 0);
+//		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+//			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKD_FE_ROOT_GATE_DISABLE, 0);
 		break;
 	case 4:
 		REG_UPDATE_2(SYMCLKE_CLOCK_ENABLE,
 				SYMCLKE_FE_EN, 0,
 				SYMCLKE_FE_SRC_SEL, 0);
+//		if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
+//			REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKE_FE_ROOT_GATE_DISABLE, 0);
 		break;
 	}
 
@@ -818,22 +1000,32 @@ static void dccg35_disable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst
 		case 0:
 			REG_UPDATE(SYMCLKA_CLOCK_ENABLE,
 					SYMCLKA_CLOCK_ENABLE, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKA_ROOT_GATE_DISABLE, 0);
 			break;
 		case 1:
 			REG_UPDATE(SYMCLKB_CLOCK_ENABLE,
 					SYMCLKB_CLOCK_ENABLE, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKB_ROOT_GATE_DISABLE, 0);
 			break;
 		case 2:
 			REG_UPDATE(SYMCLKC_CLOCK_ENABLE,
 					SYMCLKC_CLOCK_ENABLE, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKC_ROOT_GATE_DISABLE, 0);
 			break;
 		case 3:
 			REG_UPDATE(SYMCLKD_CLOCK_ENABLE,
 					SYMCLKD_CLOCK_ENABLE, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKD_ROOT_GATE_DISABLE, 0);
 			break;
 		case 4:
 			REG_UPDATE(SYMCLKE_CLOCK_ENABLE,
 					SYMCLKE_CLOCK_ENABLE, 0);
+//			if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le)
+//				REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, SYMCLKE_ROOT_GATE_DISABLE, 0);
 			break;
 		}
 	}
@@ -845,6 +1037,7 @@ static const struct dccg_funcs dccg35_funcs = {
 	.get_dccg_ref_freq = dccg31_get_dccg_ref_freq,
 	.dccg_init = dccg35_init,
 	.set_dpstreamclk = dccg35_set_dpstreamclk,
+	.set_dpstreamclk_root_clock_gating = dccg35_set_dpstreamclk_root_clock_gating,
 	.enable_symclk32_se = dccg31_enable_symclk32_se,
 	.disable_symclk32_se = dccg35_disable_symclk32_se,
 	.enable_symclk32_le = dccg31_enable_symclk32_le,

drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h

@@ -1090,7 +1090,8 @@
 	type DPP_CLOCK_ENABLE; \
 	type CM_HDR_MULT_COEF; \
 	type CUR0_FP_BIAS; \
-	type CUR0_FP_SCALE;
+	type CUR0_FP_SCALE;\
+	type DISPCLK_R_GATE_DISABLE;
 
 struct dcn_dpp_shift {
 	TF_REG_FIELD_LIST(uint8_t)

drivers/gpu/drm/amd/display/dc/dpp/dcn35/dcn35_dpp.c

@@ -37,14 +37,73 @@
 	((const struct dcn35_dpp_shift *)(dpp->tf_shift))->field_name, \
 	((const struct dcn35_dpp_mask *)(dpp->tf_mask))->field_name
 
-bool dpp35_construct(struct dcn3_dpp *dpp, struct dc_context *ctx,
-		     uint32_t inst, const struct dcn3_dpp_registers *tf_regs,
-		     const struct dcn35_dpp_shift *tf_shift,
-		     const struct dcn35_dpp_mask *tf_mask)
+void dpp35_dppclk_control(
+		struct dpp *dpp_base,
+		bool dppclk_div,
+		bool enable)
 {
-	return dpp32_construct(dpp, ctx, inst, tf_regs,
+	struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base);
+
+	if (enable) {
+		if (dpp->tf_mask->DPPCLK_RATE_CONTROL)
+			REG_UPDATE_2(DPP_CONTROL,
+				DPPCLK_RATE_CONTROL, dppclk_div,
+				DPP_CLOCK_ENABLE, 1);
+		else
+			REG_UPDATE_2(DPP_CONTROL,
+					DPP_CLOCK_ENABLE, 1,
+					DISPCLK_R_GATE_DISABLE, 1);
+	} else
+		REG_UPDATE_2(DPP_CONTROL,
+				DPP_CLOCK_ENABLE, 0,
+				DISPCLK_R_GATE_DISABLE, 0);
+}
+
+static struct dpp_funcs dcn35_dpp_funcs = {
+	.dpp_program_gamcor_lut		= dpp3_program_gamcor_lut,
+	.dpp_read_state				= dpp30_read_state,
+	.dpp_reset					= dpp_reset,
+	.dpp_set_scaler				= dpp1_dscl_set_scaler_manual_scale,
+	.dpp_get_optimal_number_of_taps	= dpp3_get_optimal_number_of_taps,
+	.dpp_set_gamut_remap		= dpp3_cm_set_gamut_remap,
+	.dpp_set_csc_adjustment		= NULL,
+	.dpp_set_csc_default		= NULL,
+	.dpp_program_regamma_pwl	= NULL,
+	.dpp_set_pre_degam			= dpp3_set_pre_degam,
+	.dpp_program_input_lut		= NULL,
+	.dpp_full_bypass			= dpp1_full_bypass,
+	.dpp_setup					= dpp3_cnv_setup,
+	.dpp_program_degamma_pwl	= NULL,
+	.dpp_program_cm_dealpha		= dpp3_program_cm_dealpha,
+	.dpp_program_cm_bias		= dpp3_program_cm_bias,
+
+	.dpp_program_blnd_lut		= NULL, // BLNDGAM is removed completely in DCN3.2 DPP
+	.dpp_program_shaper_lut		= NULL, // CM SHAPER block is removed in DCN3.2 DPP, (it is in MPCC, programmable before or after BLND)
+	.dpp_program_3dlut			= NULL, // CM 3DLUT block is removed in DCN3.2 DPP, (it is in MPCC, programmable before or after BLND)
+
+	.dpp_program_bias_and_scale	= NULL,
+	.dpp_cnv_set_alpha_keyer	= dpp2_cnv_set_alpha_keyer,
+	.set_cursor_attributes		= dpp3_set_cursor_attributes,
+	.set_cursor_position		= dpp1_set_cursor_position,
+	.set_optional_cursor_attributes	= dpp1_cnv_set_optional_cursor_attributes,
+	.dpp_dppclk_control			= dpp35_dppclk_control,
+	.dpp_set_hdr_multiplier		= dpp3_set_hdr_multiplier,
+	.dpp_get_gamut_remap		= dpp3_cm_get_gamut_remap,
+};
+
+
+bool dpp35_construct(
+	struct dcn3_dpp *dpp, struct dc_context *ctx,
+	uint32_t inst, const struct dcn3_dpp_registers *tf_regs,
+	const struct dcn35_dpp_shift *tf_shift,
+	const struct dcn35_dpp_mask *tf_mask)
+{
+	bool ret = dpp32_construct(dpp, ctx, inst, tf_regs,
 			      (const struct dcn3_dpp_shift *)(tf_shift),
 			      (const struct dcn3_dpp_mask *)(tf_mask));
+
+	dpp->base.funcs = &dcn35_dpp_funcs;
+	return ret;
 }
 
 void dpp35_set_fgcg(struct dcn3_dpp *dpp, bool enable)

drivers/gpu/drm/amd/display/dc/dpp/dcn35/dcn35_dpp.h

@@ -31,7 +31,9 @@
 
 #define DPP_REG_LIST_SH_MASK_DCN35(mask_sh)  \
 	DPP_REG_LIST_SH_MASK_DCN30_COMMON(mask_sh), \
-		TF_SF(DPP_TOP0_DPP_CONTROL, DPP_FGCG_REP_DIS, mask_sh)
+		TF_SF(DPP_TOP0_DPP_CONTROL, DPP_FGCG_REP_DIS, mask_sh), \
+		TF_SF(DPP_TOP0_DPP_CONTROL, DPP_FGCG_REP_DIS, mask_sh), \
+		TF_SF(DPP_TOP0_DPP_CONTROL, DISPCLK_R_GATE_DISABLE, mask_sh)
 
 #define DPP_REG_FIELD_LIST_DCN35(type)         \
 	struct {                               \
@@ -47,6 +49,11 @@ struct dcn35_dpp_mask {
 	DPP_REG_FIELD_LIST_DCN35(uint32_t);
 };
 
+void dpp35_dppclk_control(
+		struct dpp *dpp_base,
+		bool dppclk_div,
+		bool enable);
+
 bool dpp35_construct(struct dcn3_dpp *dpp3, struct dc_context *ctx,
 		     uint32_t inst, const struct dcn3_dpp_registers *tf_regs,
 		     const struct dcn35_dpp_shift *tf_shift,

drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c

@@ -495,6 +495,17 @@ void dcn35_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst,
 	}
 }
 
+void dcn35_dpstream_root_clock_control(struct dce_hwseq *hws, unsigned int dp_hpo_inst, bool clock_on)
+{
+	if (!hws->ctx->dc->debug.root_clock_optimization.bits.dpstream)
+		return;
+
+	if (hws->ctx->dc->res_pool->dccg->funcs->set_dpstreamclk_root_clock_gating) {
+		hws->ctx->dc->res_pool->dccg->funcs->set_dpstreamclk_root_clock_gating(
+			hws->ctx->dc->res_pool->dccg, dp_hpo_inst, clock_on);
+	}
+}
+
 void dcn35_dsc_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dsc_inst,
@@ -1002,6 +1013,9 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
 
 		if (pipe_ctx->stream_res.opp)
 			update_state->pg_pipe_res_update[PG_OPP][pipe_ctx->stream_res.opp->inst] = false;
+
+		if (pipe_ctx->stream_res.hpo_dp_stream_enc)
+			update_state->pg_pipe_res_update[PG_DPSTREAM][pipe_ctx->stream_res.hpo_dp_stream_enc->inst] = false;
 	}
 	/*domain24 controls all the otg, mpc, opp, as long as one otg is still up, avoid enabling OTG PG*/
 	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
@@ -1059,6 +1073,9 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 
 				if (j == PG_OPTC && new_pipe->stream_res.tg)
 					update_state->pg_pipe_res_update[j][new_pipe->stream_res.tg->inst] = true;
+
+				if (j == PG_DPSTREAM && new_pipe->stream_res.hpo_dp_stream_enc)
+					update_state->pg_pipe_res_update[j][new_pipe->stream_res.hpo_dp_stream_enc->inst] = true;
 			}
 		} else if (cur_pipe->plane_state == new_pipe->plane_state ||
 				cur_pipe == new_pipe) {
@@ -1088,6 +1105,11 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 					cur_pipe->stream_res.tg != new_pipe->stream_res.tg &&
 					new_pipe->stream_res.tg)
 					update_state->pg_pipe_res_update[j][new_pipe->stream_res.tg->inst] = true;
+
+				if (j == PG_DPSTREAM &&
+					cur_pipe->stream_res.hpo_dp_stream_enc != new_pipe->stream_res.hpo_dp_stream_enc &&
+					new_pipe->stream_res.hpo_dp_stream_enc)
+					update_state->pg_pipe_res_update[j][new_pipe->stream_res.hpo_dp_stream_enc->inst] = true;
 			}
 		}
 	}
@@ -1234,6 +1256,9 @@ void dcn35_root_clock_control(struct dc *dc,
 				if (dc->hwseq->funcs.dpp_root_clock_control)
 					dc->hwseq->funcs.dpp_root_clock_control(dc->hwseq, i, power_on);
 			}
+			if (update_state->pg_pipe_res_update[PG_DPSTREAM][i])
+				if (dc->hwseq->funcs.dpstream_root_clock_control)
+					dc->hwseq->funcs.dpstream_root_clock_control(dc->hwseq, i, power_on);
 		}
 	for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) {
 		if (update_state->pg_pipe_res_update[PG_DSC][i]) {
@@ -1254,6 +1279,9 @@ void dcn35_root_clock_control(struct dc *dc,
 				if (dc->hwseq->funcs.dpp_root_clock_control)
 					dc->hwseq->funcs.dpp_root_clock_control(dc->hwseq, i, power_on);
 			}
+			if (update_state->pg_pipe_res_update[PG_DPSTREAM][i])
+				if (dc->hwseq->funcs.dpstream_root_clock_control)
+					dc->hwseq->funcs.dpstream_root_clock_control(dc->hwseq, i, power_on);
 		}
 }
 

drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h

@@ -37,6 +37,8 @@ void dcn35_dsc_pg_control(struct dce_hwseq *hws, unsigned int dsc_inst, bool pow
 
 void dcn35_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on);
 
+void dcn35_dpstream_root_clock_control(struct dce_hwseq *hws, unsigned int dp_hpo_inst, bool clock_on);
+
 void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable);
 
 void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable);

drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c

@@ -147,6 +147,7 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	//.hubp_pg_control = dcn35_hubp_pg_control,
 	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
+	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn35_update_odm,
 	.set_hdr_multiplier = dcn10_set_hdr_multiplier,

drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h

@@ -120,6 +120,10 @@ struct hwseq_private_funcs {
 			struct dce_hwseq *hws,
 			unsigned int dpp_inst,
 			bool clock_on);
+	void (*dpstream_root_clock_control)(
+			struct dce_hwseq *hws,
+			unsigned int dpp_inst,
+			bool clock_on);
 	void (*dpp_pg_control)(struct dce_hwseq *hws,
 			unsigned int dpp_inst,
 			bool power_on);

drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h

@@ -106,6 +106,10 @@ struct dccg_funcs {
 	void (*otg_drop_pixel)(struct dccg *dccg,
 			uint32_t otg_inst);
 	void (*dccg_init)(struct dccg *dccg);
+	void (*set_dpstreamclk_root_clock_gating)(
+			struct dccg *dccg,
+			int dp_hpo_inst,
+			bool enable);
 
 	void (*set_dpstreamclk)(
 			struct dccg *dccg,