drm/amd/display: Add debug option for allocating extra way for cursor

[Why and How]
- Add a debug option for allocating extra way for cursor
- Remove usage of cache_cursor_addr since it's not gaurenteed
  to be populated
- Include cursor size in MALL calculation if it exceeds the
  DCN cursor buffer size (and don't need extra way for cursor)
Reviewed-by: NAurabindo Pillai <Aurabindo.Pillai@amd.com>
Acked-by: NWayne Lin <wayne.lin@amd.com>
Signed-off-by: NAlvin Lee <Alvin.Lee2@amd.com>
Tested-by: NDaniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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

@@ -832,6 +832,7 @@ struct dc_debug_options {
 	bool force_subvp_mclk_switch;
 	bool allow_sw_cursor_fallback;
 	unsigned int force_subvp_num_ways;
+	bool alloc_extra_way_for_cursor;
 	bool force_usr_allow;
 	/* uses value at boot and disables switch */
 	bool disable_dtb_ref_clk_switch;

drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c

@@ -304,7 +304,8 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 				 * using the max for calculation
 				 */
 				if (hubp->curs_attr.width > 0) {
-					cursor_size = hubp->curs_attr.width * hubp->curs_attr.height;
+					// Round cursor width to next multiple of 64
+					cursor_size = (((hubp->curs_attr.width + 63) / 64) * 64) * hubp->curs_attr.height;
 					break;
 				}
 		}
@@ -325,7 +326,8 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 			break;
 		}
 
-		if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) {
+		if (stream->cursor_position.enable && !dc->debug.alloc_extra_way_for_cursor &&
+				cursor_size > 16384) {
 			cache_lines_used += dcn32_cache_lines_for_surface(dc, cursor_size,
 					plane->address.grph.cursor_cache_addr.quad_part);
 		}
@@ -345,8 +347,8 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 			plane = ctx->stream_status[i].plane_states[j];
 
 			if (stream->cursor_position.enable && plane &&
-				!plane->address.grph.cursor_cache_addr.quad_part &&
-				cursor_size > 16384) {
+					dc->debug.alloc_extra_way_for_cursor &&
+					cursor_size > 16384) {
 				/* Cursor caching is not supported since it won't be on the same line.
 				 * So we need an extra line to accommodate it. With large cursors and a single 4k monitor
 				 * this case triggers corruption. If we're at the edge, then dont trigger display refresh

drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c

@@ -720,6 +720,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
 	.allow_sw_cursor_fallback = false,
+	.alloc_extra_way_for_cursor = true,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {

drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c

@@ -720,6 +720,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
 	.allow_sw_cursor_fallback = false,
+	.alloc_extra_way_for_cursor = true,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {