drm/amd/display: Line Buffer changes

DCN 3x increased Line buffer size for DCHUB latency hiding, from 4 lines
of 4K resolution lines to 5 lines of 4K resolution lines. All Line
Buffer can be used as extended memory for P State change latency hiding.
The maximum number of lines is increased to 32 lines. Finally,
LB_MEMORY_CONFIG_1 (LB memory piece 1) and LB_MEMORY _CONFIG_2 (LB
memory piece 2) are not affected, no change in size, only 3 pieces is
affected, i.e., when all 3 pieces are used in both LB_MEMORY_CONFIG_0
and LB_MEMORY_CONFIG_3 (for 4:2:0) modes.

Reviewed-by: Jun Lei <[email protected]>
Acked-by: Rodrigo Siqueira <[email protected]>
Signed-off-by: Nevenko Stupar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: Nevenko Stupar

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c

@@ -217,6 +217,8 @@ static void dpp1_dscl_set_lb(
 	const struct line_buffer_params *lb_params,
 	enum lb_memory_config mem_size_config)
 {
+	uint32_t max_partitions = 63; /* Currently hardcoded on all ASICs before DCN 3.2 */
+
 	/* LB */
 	if (dpp->base.caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) {
 		/* DSCL caps: pixel data processed in fixed format */
@@ -239,9 +241,12 @@ static void dpp1_dscl_set_lb(
 			LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
 	}
 
+	if (dpp->base.caps->max_lb_partitions == 31)
+		max_partitions = 31;
+
 	REG_SET_2(LB_MEMORY_CTRL, 0,
 		MEMORY_CONFIG, mem_size_config,
-		LB_MAX_PARTITIONS, 63);
+		LB_MAX_PARTITIONS, max_partitions);
 }
 
 static const uint16_t *dpp1_dscl_get_filter_coeffs_64p(int taps, struct fixed31_32 ratio)

drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c

@@ -383,13 +383,6 @@ bool dpp3_get_optimal_number_of_taps(
 	int min_taps_y, min_taps_c;
 	enum lb_memory_config lb_config;
 
-	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
-	if (scl_data->viewport.width  != scl_data->h_active &&
-		scl_data->viewport.height != scl_data->v_active &&
-		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
-		scl_data->format == PIXEL_FORMAT_FP16)
-		return false;
-
 	if (scl_data->viewport.width > scl_data->h_active &&
 		dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
 		scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
@@ -1440,15 +1433,6 @@ bool dpp3_construct(
 	dpp->tf_shift = tf_shift;
 	dpp->tf_mask = tf_mask;
 
-	dpp->lb_pixel_depth_supported =
-		LB_PIXEL_DEPTH_18BPP |
-		LB_PIXEL_DEPTH_24BPP |
-		LB_PIXEL_DEPTH_30BPP |
-		LB_PIXEL_DEPTH_36BPP;
-
-	dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
-	dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/
-
 	return true;
 }
 

drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h

@@ -154,6 +154,7 @@
 	SRI(COLOR_KEYER_BLUE, CNVC_CFG, id), \
 	SRI(CURSOR_CONTROL, CURSOR0_, id),\
 	SRI(OBUF_MEM_PWR_CTRL, DSCL, id),\
+	SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
 	SRI(DSCL_MEM_PWR_CTRL, DSCL, id)
 
 #define DPP_REG_LIST_DCN30(id)\
@@ -163,8 +164,6 @@
 	SRI(CM_SHAPER_LUT_DATA, CM, id),\
 	SRI(CM_MEM_PWR_CTRL2, CM, id), \
 	SRI(CM_MEM_PWR_STATUS2, CM, id), \
-	SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
-	SRI(DSCL_MEM_PWR_CTRL, DSCL, id), \
 	SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_B, CM, id),\
 	SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_G, CM, id),\
 	SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_R, CM, id),\

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

@@ -289,6 +289,9 @@ struct dpp_caps {
 	/* DSCL processing pixel data in fixed or float format */
 	enum dscl_data_processing_format dscl_data_proc_format;
 
+	/* max LB partitions */
+	unsigned int max_lb_partitions;
+
 	/* Calculates the number of partitions in the line buffer.
 	 * The implementation of this function is overloaded for
 	 * different versions of DSCL LB.