drm/amd/display: optimize prgoram wm and clks

[Why]
In some display configuration like 1080P monitor playing a 1080P video,
if user use ALT+F4 to exit Movie and TV, there is a chance clocks are
same only water mark changed. Current clock optimization machanism will
result in water mark keeps high after exit Movie and TV app.

[How]
Return if watermark need to be optimized when doing program watermark,
perform the optimization after.
Signed-off-by: Yongqiang Sun <yongqiang.sun@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/core/dc.c

@@ -1365,7 +1365,7 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 	int i;
 	struct dc_state *context = dc->current_state;
 
-	if (!dc->optimized_required || dc->optimize_seamless_boot_streams > 0)
+	if ((!dc->clk_optimized_required && !dc->wm_optimized_required) || dc->optimize_seamless_boot_streams > 0)
 		return true;
 
 	post_surface_trace(dc);
@@ -1377,8 +1377,6 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 			dc->hwss.disable_plane(dc, &context->res_ctx.pipe_ctx[i]);
 		}
 
-	dc->optimized_required = false;
-
 	dc->hwss.optimize_bandwidth(dc, context);
 	return true;
 }
@@ -1826,10 +1824,10 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 		// If there's an available clock comparator, we use that.
 		if (dc->clk_mgr->funcs->are_clock_states_equal) {
 			if (!dc->clk_mgr->funcs->are_clock_states_equal(&dc->clk_mgr->clks, &dc->current_state->bw_ctx.bw.dcn.clk))
-				dc->optimized_required = true;
+				dc->clk_optimized_required = true;
 		// Else we fallback to mem compare.
 		} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
-			dc->optimized_required = true;
+			dc->clk_optimized_required = true;
 		}
 	}
 
@@ -2200,7 +2198,7 @@ static void commit_planes_for_stream(struct dc *dc,
 			dc->optimize_seamless_boot_streams--;
 
 			if (dc->optimize_seamless_boot_streams == 0)
-				dc->optimized_required = true;
+				dc->clk_optimized_required = true;
 		}
 	}
 

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

@@ -520,7 +520,8 @@ struct dc {
 	struct dce_hwseq *hwseq;
 
 	/* Require to optimize clocks and bandwidth for added/removed planes */
-	bool optimized_required;
+	bool clk_optimized_required;
+	bool wm_optimized_required;
 
 	/* Require to maintain clocks and bandwidth for UEFI enabled HW */
 	int optimize_seamless_boot_streams;

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h

@@ -308,7 +308,7 @@ bool hubbub1_verify_allow_pstate_change_high(
 
 void hubbub1_wm_change_req_wa(struct hubbub *hubbub);
 
-void hubbub1_program_watermarks(
+bool hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
@@ -331,17 +331,17 @@ void hubbub1_construct(struct hubbub *hubbub,
 	const struct dcn_hubbub_shift *hubbub_shift,
 	const struct dcn_hubbub_mask *hubbub_mask);
 
-void hubbub1_program_urgent_watermarks(
+bool hubbub1_program_urgent_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
-void hubbub1_program_stutter_watermarks(
+bool hubbub1_program_stutter_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
-void hubbub1_program_pstate_watermarks(
+bool hubbub1_program_pstate_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -1048,7 +1048,7 @@ void dcn10_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	if (opp != NULL)
 		opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 
-	dc->optimized_required = true;
+	dc->clk_optimized_required = true;
 
 	if (hubp->funcs->hubp_disconnect)
 		hubp->funcs->hubp_disconnect(hubp);
@@ -1099,7 +1099,7 @@ void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 				false);
 
 	hubp->power_gated = true;
-	dc->optimized_required = false; /* We're powering off, no need to optimize */
+	dc->clk_optimized_required = false; /* We're powering off, no need to optimize */
 
 	hws->funcs.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
@@ -2693,7 +2693,7 @@ void dcn10_prepare_bandwidth(
 				false);
 	}
 
-	hubbub->funcs->program_watermarks(hubbub,
+	dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
 			&context->bw_ctx.bw.dcn.watermarks,
 			dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 			true);
@@ -2717,19 +2717,30 @@ void dcn10_optimize_bandwidth(
 		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		if (context->stream_count == 0)
+		if (context->stream_count == 0) {
 			context->bw_ctx.bw.dcn.clk.phyclk_khz = 0;
 
-		dc->clk_mgr->funcs->update_clocks(
-				dc->clk_mgr,
-				context,
+			dc->clk_mgr->funcs->update_clocks(
+					dc->clk_mgr,
+					context,
+					true);
+		} else if (dc->clk_optimized_required || IS_DIAG_DC(dc->ctx->dce_environment)) {
+			dc->clk_mgr->funcs->update_clocks(
+								dc->clk_mgr,
+								context,
+								true);
+		}
+	}
+
+	if (dc->wm_optimized_required || IS_DIAG_DC(dc->ctx->dce_environment)) {
+		hubbub->funcs->program_watermarks(hubbub,
+				&context->bw_ctx.bw.dcn.watermarks,
+				dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 				true);
 	}
 
-	hubbub->funcs->program_watermarks(hubbub,
-			&context->bw_ctx.bw.dcn.watermarks,
-			dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
-			true);
+	dc->clk_optimized_required = false;
+	dc->wm_optimized_required = false;
 	dcn10_stereo_hw_frame_pack_wa(dc, context);
 
 	if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE)

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c

@@ -562,19 +562,23 @@ void hubbub2_get_dchub_ref_freq(struct hubbub *hubbub,
 	}
 }
 
-static void hubbub2_program_watermarks(
+static bool hubbub2_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+	bool wm_pending = false;
 	/*
 	 * Need to clamp to max of the register values (i.e. no wrap)
 	 * for dcn1, all wm registers are 21-bit wide
 	 */
-	hubbub1_program_urgent_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower);
-	hubbub1_program_stutter_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower);
+	if (hubbub1_program_urgent_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower))
+		wm_pending = true;
+
+	if (hubbub1_program_stutter_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower))
+		wm_pending = true;
 
 	/*
 	 * There's a special case when going from p-state support to p-state unsupported
@@ -592,6 +596,7 @@ static void hubbub2_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 180);
 
 	hubbub->funcs->allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	return wm_pending;
 }
 
 static const struct hubbub_funcs hubbub2_funcs = {

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

@@ -1627,7 +1627,7 @@ void dcn20_prepare_bandwidth(
 			false);
 
 	/* program dchubbub watermarks */
-	hubbub->funcs->program_watermarks(hubbub,
+	dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
@@ -1639,16 +1639,22 @@ void dcn20_optimize_bandwidth(
 {
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 
-	/* program dchubbub watermarks */
-	hubbub->funcs->program_watermarks(hubbub,
-					&context->bw_ctx.bw.dcn.watermarks,
-					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
-					true);
+	if (dc->wm_optimized_required || IS_DIAG_DC(dc->ctx->dce_environment)) {
+		/* program dchubbub watermarks */
+		hubbub->funcs->program_watermarks(hubbub,
+						&context->bw_ctx.bw.dcn.watermarks,
+						dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
+						true);
+		dc->wm_optimized_required = false;
+	}
 
-	dc->clk_mgr->funcs->update_clocks(
-			dc->clk_mgr,
-			context,
-			true);
+	if (dc->clk_optimized_required || IS_DIAG_DC(dc->ctx->dce_environment)) {
+		dc->clk_mgr->funcs->update_clocks(
+				dc->clk_mgr,
+				context,
+				true);
+		dc->wm_optimized_required = false;
+	}
 }
 
 bool dcn20_update_bandwidth(

drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h

@@ -113,22 +113,22 @@
 void dcn21_dchvm_init(struct hubbub *hubbub);
 int hubbub21_init_dchub(struct hubbub *hubbub,
 		struct dcn_hubbub_phys_addr_config *pa_config);
-void hubbub21_program_watermarks(
+bool hubbub21_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
-void hubbub21_program_urgent_watermarks(
+bool hubbub21_program_urgent_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
-void hubbub21_program_stutter_watermarks(
+bool hubbub21_program_stutter_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
-void hubbub21_program_pstate_watermarks(
+bool hubbub21_program_pstate_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,

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

@@ -134,7 +134,7 @@ struct hubbub_funcs {
 			unsigned int dccg_ref_freq_inKhz,
 			unsigned int *dchub_ref_freq_inKhz);
 
-	void (*program_watermarks)(
+	bool (*program_watermarks)(
 			struct hubbub *hubbub,
 			struct dcn_watermark_set *watermarks,
 			unsigned int refclk_mhz,