drm/amd/display: Add 3DLUT DMA load trigger

[Why/How]
Need to be able to trigger a DMA load to update 3DLUT contents in MPC.
Adding a HWSS function to serve as the trigger.
Reviewed-by: Krunoslav Kovac <krunoslav.kovac@amd.com>
Acked-by: Roman Li <roman.li@amd.com>
Signed-off-by: Ilya Bakoulin <ilya.bakoulin@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/core/dc.c

@@ -4074,6 +4074,14 @@ static void commit_planes_for_stream(struct dc *dc,
 				if (!should_update_pipe_for_plane(context, pipe_ctx, plane_state))
 					continue;
 
+				if (srf_updates[i].cm2_params &&
+						srf_updates[i].cm2_params->cm2_luts.lut3d_data.lut3d_src ==
+								DC_CM2_TRANSFER_FUNC_SOURCE_VIDMEM &&
+						srf_updates[i].cm2_params->component_settings.shaper_3dlut_setting ==
+								DC_CM2_SHAPER_3DLUT_SETTING_ENABLE_SHAPER_3DLUT &&
+						dc->hwss.trigger_3dlut_dma_load)
+					dc->hwss.trigger_3dlut_dma_load(dc, pipe_ctx);
+
 				/*program triple buffer after lock based on flip type*/
 				if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) {
 					/*only enable triplebuffer for  fast_update*/

drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c

@@ -498,10 +498,10 @@ void dcn401_populate_mcm_luts(struct dc *dc,
 		if (m_lut_params.pwl) {
 			if (mpc->funcs->populate_lut)
 				mpc->funcs->populate_lut(mpc, MCM_LUT_1DLUT, m_lut_params, lut_bank_a, mpcc_id);
+		}
 		if (mpc->funcs->program_lut_mode)
 			mpc->funcs->program_lut_mode(mpc, MCM_LUT_1DLUT, lut1d_xable, lut_bank_a, mpcc_id);
 	}
-	}
 
 	/* Shaper */
 	if (mcm_luts.shaper) {
@@ -519,10 +519,10 @@ void dcn401_populate_mcm_luts(struct dc *dc,
 		if (m_lut_params.pwl) {
 			if (mpc->funcs->populate_lut)
 				mpc->funcs->populate_lut(mpc, MCM_LUT_SHAPER, m_lut_params, lut_bank_a, mpcc_id);
+		}
 		if (mpc->funcs->program_lut_mode)
 			mpc->funcs->program_lut_mode(mpc, MCM_LUT_SHAPER, shaper_xable, lut_bank_a, mpcc_id);
 	}
-	}
 
 	/* 3DLUT */
 	switch (lut3d_src) {
@@ -635,6 +635,15 @@ void dcn401_populate_mcm_luts(struct dc *dc,
 	}
 }
 
+void dcn401_trigger_3dlut_dma_load(struct dc *dc, struct pipe_ctx *pipe_ctx)
+{
+	struct hubp *hubp = pipe_ctx->plane_res.hubp;
+
+	if (hubp->funcs->hubp_enable_3dlut_fl) {
+		hubp->funcs->hubp_enable_3dlut_fl(hubp, true);
+	}
+}
+
 bool dcn401_set_mcm_luts(struct pipe_ctx *pipe_ctx,
 				const struct dc_plane_state *plane_state)
 {

drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h

@@ -40,6 +40,8 @@ bool dcn401_set_mcm_luts(struct pipe_ctx *pipe_ctx,
 bool dcn401_set_output_transfer_func(struct dc *dc,
 				struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream);
+void dcn401_trigger_3dlut_dma_load(struct dc *dc,
+				struct pipe_ctx *pipe_ctx);
 void dcn401_calculate_dccg_tmds_div_value(struct pipe_ctx *pipe_ctx,
 				unsigned int *tmds_div);
 enum dc_status dcn401_enable_stream_timing(

drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c

@@ -24,6 +24,7 @@ static const struct hw_sequencer_funcs dcn401_funcs = {
 	.update_dchub = dcn10_update_dchub,
 	.update_pending_status = dcn10_update_pending_status,
 	.program_output_csc = dcn20_program_output_csc,
+	.trigger_3dlut_dma_load = dcn401_trigger_3dlut_dma_load,
 	.enable_accelerated_mode = dce110_enable_accelerated_mode,
 	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
 	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,

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

@@ -304,6 +304,7 @@ struct hw_sequencer_funcs {
 	void (*program_output_csc)(struct dc *dc, struct pipe_ctx *pipe_ctx,
 			enum dc_color_space colorspace,
 			uint16_t *matrix, int opp_id);
+	void (*trigger_3dlut_dma_load)(struct dc *dc, struct pipe_ctx *pipe_ctx);
 
 	/* VM Related */
 	int (*init_sys_ctx)(struct dce_hwseq *hws,