drm/amd/display: Fix 4to1 MPC black screen with DPP RCO

[Why]
DPP Root clock optimization when combined with 4to1 MPC combine results
in the screen turning black.

This is because the DPPCLK is stopped during the middle of an
optimize_bandwidth sequence during commit_minimal_transition without
going through plane power down/power up.

[How]
The intent of a 0Hz DPP clock through update_clocks is to disable the
DTO. This differs from the behavior of stopping the DPPCLK entirely
(utilizing a 0Hz clock on some ASIC) so it's better to move this logic
to reside next to plane power up/power down where we gate the HUBP/DPP
DOMAIN.

The new  sequence should be:
Power down: PG enabled -> RCO on
Power up: RCO off -> PG disabled

Rename power_on_plane to power_on_plane_resources to reflect the
actual operation that's occurring.

Cc: stable@vger.kernel.org
Cc: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@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/dcn10/dcn10_hw_sequencer.c

@@ -726,11 +726,15 @@ void dcn10_hubp_pg_control(
 	}
 }
 
-static void power_on_plane(
+static void power_on_plane_resources(
 	struct dce_hwseq *hws,
 	int plane_id)
 {
 	DC_LOGGER_INIT(hws->ctx->logger);
+
+	if (hws->funcs.dpp_root_clock_control)
+		hws->funcs.dpp_root_clock_control(hws, plane_id, true);
+
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
@@ -1237,11 +1241,15 @@ void dcn10_plane_atomic_power_down(struct dc *dc,
 			hws->funcs.hubp_pg_control(hws, hubp->inst, false);
 
 		dpp->funcs->dpp_reset(dpp);
+
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(
 				"Power gated front end %d\n", hubp->inst);
 	}
+
+	if (hws->funcs.dpp_root_clock_control)
+		hws->funcs.dpp_root_clock_control(hws, dpp->inst, false);
 }
 
 /* disable HW used by plane.
@@ -2462,7 +2470,7 @@ static void dcn10_enable_plane(
 
 	undo_DEGVIDCN10_253_wa(dc);
 
-	power_on_plane(dc->hwseq,
+	power_on_plane_resources(dc->hwseq,
 		pipe_ctx->plane_res.hubp->inst);
 
 	/* enable DCFCLK current DCHUB */

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c

@@ -1130,11 +1130,15 @@ void dcn20_blank_pixel_data(
 }
 
 
-static void dcn20_power_on_plane(
+static void dcn20_power_on_plane_resources(
 	struct dce_hwseq *hws,
 	struct pipe_ctx *pipe_ctx)
 {
 	DC_LOGGER_INIT(hws->ctx->logger);
+
+	if (hws->funcs.dpp_root_clock_control)
+		hws->funcs.dpp_root_clock_control(hws, pipe_ctx->plane_res.dpp->inst, true);
+
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
@@ -1158,7 +1162,7 @@ static void dcn20_enable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	//if (dc->debug.sanity_checks) {
 	//	dcn10_verify_allow_pstate_change_high(dc);
 	//}
-	dcn20_power_on_plane(dc->hwseq, pipe_ctx);
+	dcn20_power_on_plane_resources(dc->hwseq, pipe_ctx);
 
 	/* enable DCFCLK current DCHUB */
 	pipe_ctx->plane_res.hubp->funcs->hubp_clk_cntl(pipe_ctx->plane_res.hubp, true);

drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c

@@ -65,19 +65,10 @@ void dccg31_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk)
 				DPPCLK0_DTO_MODULO, modulo);
 		REG_UPDATE(DPPCLK_DTO_CTRL,
 				DPPCLK_DTO_ENABLE[dpp_inst], 1);
-	} else {
-		//DTO must be enabled to generate a 0Hz clock output
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) {
-			REG_UPDATE(DPPCLK_DTO_CTRL,
-					DPPCLK_DTO_ENABLE[dpp_inst], 1);
-			REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
-					DPPCLK0_DTO_PHASE, 0,
-					DPPCLK0_DTO_MODULO, 1);
 	} else {
 		REG_UPDATE(DPPCLK_DTO_CTRL,
 				DPPCLK_DTO_ENABLE[dpp_inst], 0);
 	}
-	}
 	dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk;
 }
 

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c

@@ -289,8 +289,31 @@ static void dccg314_set_valid_pixel_rate(
 	dccg314_set_dtbclk_dto(dccg, &dto_params);
 }
 
+static void dccg314_dpp_root_clock_control(
+		struct dccg *dccg,
+		unsigned int dpp_inst,
+		bool clock_on)
+{
+	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+
+	if (clock_on) {
+		/* turn off the DTO and leave phase/modulo at max */
+		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 0);
+		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
+			  DPPCLK0_DTO_PHASE, 0xFF,
+			  DPPCLK0_DTO_MODULO, 0xFF);
+	} else {
+		/* turn on the DTO to generate a 0hz clock */
+		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 1);
+		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
+			  DPPCLK0_DTO_PHASE, 0,
+			  DPPCLK0_DTO_MODULO, 1);
+	}
+}
+
 static const struct dccg_funcs dccg314_funcs = {
 	.update_dpp_dto = dccg31_update_dpp_dto,
+	.dpp_root_clock_control = dccg314_dpp_root_clock_control,
 	.get_dccg_ref_freq = dccg31_get_dccg_ref_freq,
 	.dccg_init = dccg31_init,
 	.set_dpstreamclk = dccg314_set_dpstreamclk,

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c

@@ -390,6 +390,16 @@ void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx)
 				pix_per_cycle);
 }
 
+void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on)
+{
+	if (!hws->ctx->dc->debug.root_clock_optimization.bits.dpp)
+		return;
+
+	if (hws->ctx->dc->res_pool->dccg->funcs->dpp_root_clock_control)
+		hws->ctx->dc->res_pool->dccg->funcs->dpp_root_clock_control(
+			hws->ctx->dc->res_pool->dccg, dpp_inst, clock_on);
+}
+
 void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on)
 {
 	struct dc_context *ctx = hws->ctx;

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h

@@ -43,4 +43,6 @@ void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx);
 
 void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on);
 
+void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on);
+
 #endif /* __DC_HWSS_DCN314_H__ */

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c

@@ -137,6 +137,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
 	.plane_atomic_disable = dcn20_plane_atomic_disable,
 	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
 	.enable_power_gating_plane = dcn314_enable_power_gating_plane,
+	.dpp_root_clock_control = dcn314_dpp_root_clock_control,
 	.hubp_pg_control = dcn314_hubp_pg_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn314_update_odm,

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

@@ -148,18 +148,21 @@ struct dccg_funcs {
 		struct dccg *dccg,
 		int inst);
 
-void (*set_pixel_rate_div)(
-        struct dccg *dccg,
+	void (*set_pixel_rate_div)(struct dccg *dccg,
 			uint32_t otg_inst,
 			enum pixel_rate_div k1,
 			enum pixel_rate_div k2);
 
-void (*set_valid_pixel_rate)(
+	void (*set_valid_pixel_rate)(
 			struct dccg *dccg,
 			int ref_dtbclk_khz,
 			int otg_inst,
 			int pixclk_khz);
 
+	void (*dpp_root_clock_control)(
+			struct dccg *dccg,
+			unsigned int dpp_inst,
+			bool clock_on);
 };
 
 #endif //__DAL_DCCG_H__

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

@@ -115,6 +115,10 @@ struct hwseq_private_funcs {
 	void (*plane_atomic_disable)(struct dc *dc, struct pipe_ctx *pipe_ctx);
 	void (*enable_power_gating_plane)(struct dce_hwseq *hws,
 		bool enable);
+	void (*dpp_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);