[Mesa-dev] [PATCH 6/6] radeonsi: set DB_EQAA.MAX_ANCHOR_SAMPLES correctly

[Dieter Nützel]

For the series:

Tested-by: Dieter Nützel <Dieter at nuetzel-hh.de>

on RX580

with UH, UV, glmark2, Blender 2.79, FreeCAD 0.17, Gimp 2.10, digikam 
5.9.0, Krita 4.0.3 and some Mesa-demos

Dieter

  17.05.2018 03:47, schrieb Marek Olšák:
> From: Marek Olšák <marek.olsak at amd.com>
> 
> ---
>  src/gallium/drivers/radeonsi/si_state.c | 16 ++++++++++++----
>  1 file changed, 12 insertions(+), 4 deletions(-)
> 
> diff --git a/src/gallium/drivers/radeonsi/si_state.c
> b/src/gallium/drivers/radeonsi/si_state.c
> index f4e29f68b29..3a7e928df53 100644
> --- a/src/gallium/drivers/radeonsi/si_state.c
> +++ b/src/gallium/drivers/radeonsi/si_state.c
> @@ -3333,21 +3333,21 @@ static void si_emit_msaa_config(struct 
> si_context *sctx)
>  		S_028A4C_WALK_ALIGN8_PRIM_FITS_ST(1) |
>  		S_028A4C_SUPERTILE_WALK_ORDER_ENABLE(1) |
>  		S_028A4C_TILE_WALK_ORDER_ENABLE(1) |
>  		S_028A4C_MULTI_SHADER_ENGINE_PRIM_DISCARD_ENABLE(1) |
>  		S_028A4C_FORCE_EOV_CNTDWN_ENABLE(1) |
>  		S_028A4C_FORCE_EOV_REZ_ENABLE(1);
>  	unsigned db_eqaa = S_028804_HIGH_QUALITY_INTERSECTIONS(1) |
>  			   S_028804_INCOHERENT_EQAA_READS(1) |
>  			   S_028804_INTERPOLATE_COMP_Z(1) |
>  			   S_028804_STATIC_ANCHOR_ASSOCIATIONS(1);
> -	unsigned coverage_samples, color_samples;
> +	unsigned coverage_samples, color_samples, z_samples;
> 
>  	/* S: Coverage samples (up to 16x):
>  	 * - Scan conversion samples (PA_SC_AA_CONFIG.MSAA_NUM_SAMPLES)
>  	 * - CB FMASK samples (CB_COLORi_ATTRIB.NUM_SAMPLES)
>  	 *
>  	 * Z: Z/S samples (up to 8x, must be <= coverage samples and >=
> color samples):
>  	 * - Value seen by DB (DB_Z_INFO.NUM_SAMPLES)
>  	 * - Value seen by CB, must be correct even if Z/S is unbound
> (DB_EQAA.MAX_ANCHOR_SAMPLES)
>  	 * # Missing samples are derived from Z planes if Z is compressed
> (up to 16x quality), or
>  	 * # from the closest defined sample if Z is uncompressed (same
> quality as the number of
> @@ -3379,24 +3379,31 @@ static void si_emit_msaa_config(struct 
> si_context *sctx)
>  	 *   EQAA  8s 8z 2f - might look the same as 8x MSAA with low-density 
> geometry
>  	 *   EQAA  8s 4z 4f - might look the same as 8x MSAA if Z is 
> compressed
>  	 *   EQAA  8s 4z 2f - might look the same as 8x MSAA with
> low-density geometry if Z is compressed
>  	 *   EQAA  4s 4z 4f = 4x MSAA
>  	 *   EQAA  4s 4z 2f - might look the same as 4x MSAA with low-density 
> geometry
>  	 *   EQAA  2s 2z 2f = 2x MSAA
>  	 */
>  	if (sctx->framebuffer.nr_samples > 1) {
>  		coverage_samples = sctx->framebuffer.nr_samples;
>  		color_samples = sctx->framebuffer.nr_color_samples;
> +
> +		if (sctx->framebuffer.state.zsbuf) {
> +			z_samples = sctx->framebuffer.state.zsbuf->texture->nr_samples;
> +			z_samples = MAX2(1, z_samples);
> +		} else {
> +			z_samples = coverage_samples;
> +		}
>  	} else if (sctx->smoothing_enabled) {
> -		coverage_samples = color_samples = SI_NUM_SMOOTH_AA_SAMPLES;
> +		coverage_samples = color_samples = z_samples = 
> SI_NUM_SMOOTH_AA_SAMPLES;
>  	} else {
> -		coverage_samples = color_samples = 1;
> +		coverage_samples = color_samples = z_samples = 1;
>  	}
> 
>  	/* Required by OpenGL line rasterization.
>  	 *
>  	 * TODO: We should also enable perpendicular endcaps for AA lines,
>  	 *       but that requires implementing line stippling in the pixel
>  	 *       shader. SC can only do line stippling with axis-aligned
>  	 *       endcaps.
>  	 */
>  	unsigned sc_line_cntl = S_028BDC_DX10_DIAMOND_TEST_ENA(1);
> @@ -3404,34 +3411,35 @@ static void si_emit_msaa_config(struct 
> si_context *sctx)
>  	if (coverage_samples > 1) {
>  		/* distance from the pixel center, indexed by log2(nr_samples) */
>  		static unsigned max_dist[] = {
>  			0, /* unused */
>  			4, /* 2x MSAA */
>  			6, /* 4x MSAA */
>  			7, /* 8x MSAA */
>  			8, /* 16x MSAA */
>  		};
>  		unsigned log_samples = util_logbase2(coverage_samples);
> +		unsigned log_z_samples = util_logbase2(z_samples);
>  		unsigned ps_iter_samples = si_get_ps_iter_samples(sctx);
>  		unsigned log_ps_iter_samples = util_logbase2(ps_iter_samples);
> 
>  		radeon_set_context_reg_seq(cs, R_028BDC_PA_SC_LINE_CNTL, 2);
>  		radeon_emit(cs, sc_line_cntl |
>  			    S_028BDC_EXPAND_LINE_WIDTH(1)); /* R_028BDC_PA_SC_LINE_CNTL */
>  		radeon_emit(cs, S_028BE0_MSAA_NUM_SAMPLES(log_samples) |
>  			    S_028BE0_MAX_SAMPLE_DIST(max_dist[log_samples]) |
>  			    S_028BE0_MSAA_EXPOSED_SAMPLES(log_samples)); /*
> R_028BE0_PA_SC_AA_CONFIG */
> 
>  		if (sctx->framebuffer.nr_samples > 1) {
>  			radeon_set_context_reg(cs, R_028804_DB_EQAA,
>  					       db_eqaa |
> -					       S_028804_MAX_ANCHOR_SAMPLES(log_samples) |
> +					       S_028804_MAX_ANCHOR_SAMPLES(log_z_samples) |
>  					       S_028804_PS_ITER_SAMPLES(log_ps_iter_samples) |
>  					       S_028804_MASK_EXPORT_NUM_SAMPLES(log_samples) |
>  					       S_028804_ALPHA_TO_MASK_NUM_SAMPLES(log_samples));
>  			radeon_set_context_reg(cs, R_028A4C_PA_SC_MODE_CNTL_1,
>  					       S_028A4C_PS_ITER_SAMPLE(ps_iter_samples > 1) |
>  					       sc_mode_cntl_1);
>  		} else if (sctx->smoothing_enabled) {
>  			radeon_set_context_reg(cs, R_028804_DB_EQAA,
>  					       db_eqaa |
>  					       S_028804_OVERRASTERIZATION_AMOUNT(log_samples));