r600g: properly implement S8Z24 depth-stencil format for Evergreen

I should say "fix", but it has never been used until now.
S8Z24 is the format equivalent to the GL_UNSIGNED_INT_24_8 packing,
so we'll start to see it more often with st/mesa now making smart decisions
about formats.

The DB<->CB copy can change the channel ordering for transfers, other than
that, the internal DB format doesn't really matter.

R600-R700 support is possible except shadow mapping.
FMT_24_8 is broken if the SAMPLE_C instruction is used (no idea why).

Also the sampler swizzling was broken in theory and the fact it worked was
a lucky coincidence.

radeonsi might need to port this.

Reviewed-by: Jerome Glisse <[email protected]>

3 files changed, 47 insertions, 18 deletions

diff --git a/src/gallium/drivers/r600/evergreen_state.c b/src/gallium/drivers/r600/evergreen_state.c
index 29b22ab4c34..4d34d8ba1dd 100644
--- a/src/gallium/drivers/r600/evergreen_state.c
+++ b/src/gallium/drivers/r600/evergreen_state.c
@@ -200,6 +200,8 @@ static uint32_t r600_translate_dbformat(enum pipe_format format)
 		return V_028040_Z_16;
 	case PIPE_FORMAT_Z24X8_UNORM:
 	case PIPE_FORMAT_Z24_UNORM_S8_UINT:
+	case PIPE_FORMAT_X8Z24_UNORM:
+	case PIPE_FORMAT_S8_UINT_Z24_UNORM:
 		return V_028040_Z_24;
 	case PIPE_FORMAT_Z32_FLOAT:
 	case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
@@ -339,7 +341,7 @@ static uint32_t r600_translate_colorswap(enum pipe_format format)
 
 	case PIPE_FORMAT_X8Z24_UNORM:
 	case PIPE_FORMAT_S8_UINT_Z24_UNORM:
-		return V_028C70_SWAP_STD;
+		return V_028C70_SWAP_STD_REV;
 
 	case PIPE_FORMAT_R10G10B10A2_UNORM:
 	case PIPE_FORMAT_R10G10B10X2_SNORM:
@@ -1106,6 +1108,11 @@ evergreen_create_sampler_view_custom(struct pipe_context *ctx,
 		case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
 			pipe_format = PIPE_FORMAT_Z32_FLOAT;
 			break;
+		case PIPE_FORMAT_X8Z24_UNORM:
+		case PIPE_FORMAT_S8_UINT_Z24_UNORM:
+			/* Z24 is always stored like this. */
+			pipe_format = PIPE_FORMAT_Z24X8_UNORM;
+			break;
 		case PIPE_FORMAT_X24S8_UINT:
 		case PIPE_FORMAT_S8X24_UINT:
 		case PIPE_FORMAT_X32_S8X24_UINT:
@@ -1603,6 +1610,8 @@ static void evergreen_init_depth_surface(struct r600_context *rctx,
 	switch (surf->base.format) {
 	case PIPE_FORMAT_Z24X8_UNORM:
 	case PIPE_FORMAT_Z24_UNORM_S8_UINT:
+	case PIPE_FORMAT_X8Z24_UNORM:
+	case PIPE_FORMAT_S8_UINT_Z24_UNORM:
 		surf->pa_su_poly_offset_db_fmt_cntl =
 			S_028B78_POLY_OFFSET_NEG_NUM_DB_BITS((char)-24);
 		break;
@@ -2179,6 +2188,8 @@ static void evergreen_emit_polygon_offset(struct r600_context *rctx, struct r600
 	switch (state->zs_format) {
 	case PIPE_FORMAT_Z24X8_UNORM:
 	case PIPE_FORMAT_Z24_UNORM_S8_UINT:
+	case PIPE_FORMAT_X8Z24_UNORM:
+	case PIPE_FORMAT_S8_UINT_Z24_UNORM:
 		offset_units *= 2.0f;
 		break;
 	case PIPE_FORMAT_Z16_UNORM:
diff --git a/src/gallium/drivers/r600/r600_state.c b/src/gallium/drivers/r600/r600_state.c
index 3f359fb0dd7..ec06be6ae46 100644
--- a/src/gallium/drivers/r600/r600_state.c
+++ b/src/gallium/drivers/r600/r600_state.c
@@ -270,10 +270,6 @@ static uint32_t r600_translate_colorswap(enum pipe_format format)
 	case PIPE_FORMAT_Z24_UNORM_S8_UINT:
 		return V_0280A0_SWAP_STD;
 
-	case PIPE_FORMAT_X8Z24_UNORM:
-	case PIPE_FORMAT_S8_UINT_Z24_UNORM:
-		return V_0280A0_SWAP_STD;
-
 	case PIPE_FORMAT_R10G10B10A2_UNORM:
 	case PIPE_FORMAT_R10G10B10X2_SNORM:
 	case PIPE_FORMAT_R10SG10SB10SA2U_NORM:
@@ -440,10 +436,6 @@ static uint32_t r600_translate_colorformat(enum pipe_format format)
 	case PIPE_FORMAT_Z24_UNORM_S8_UINT:
 		return V_0280A0_COLOR_8_24;
 
-	case PIPE_FORMAT_X8Z24_UNORM:
-	case PIPE_FORMAT_S8_UINT_Z24_UNORM:
-		return V_0280A0_COLOR_24_8;
-
 	case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
 		return V_0280A0_COLOR_X24_8_32_FLOAT;
 
diff --git a/src/gallium/drivers/r600/r600_texture.c b/src/gallium/drivers/r600/r600_texture.c
index 85fc887971d..7f5752d81e6 100644
--- a/src/gallium/drivers/r600/r600_texture.c
+++ b/src/gallium/drivers/r600/r600_texture.c
@@ -985,11 +985,14 @@ uint32_t r600_translate_texformat(struct pipe_screen *screen,
 				  const unsigned char *swizzle_view,
 				  uint32_t *word4_p, uint32_t *yuv_format_p)
 {
+	struct r600_screen *rscreen = (struct r600_screen *)screen;
 	uint32_t result = 0, word4 = 0, yuv_format = 0;
 	const struct util_format_description *desc;
 	boolean uniform = TRUE;
 	static int r600_enable_s3tc = -1;
 	bool is_srgb_valid = FALSE;
+	const unsigned char swizzle_xxxx[4] = {0, 0, 0, 0};
+	const unsigned char swizzle_yyyy[4] = {1, 1, 1, 1};
 
 	int i;
 	const uint32_t sign_bit[4] = {
@@ -1000,38 +1003,62 @@ uint32_t r600_translate_texformat(struct pipe_screen *screen,
 	};
 	desc = util_format_description(format);
 
-	word4 |= r600_get_swizzle_combined(desc->swizzle, swizzle_view, FALSE);
+	/* Depth and stencil swizzling is handled separately. */
+	if (desc->colorspace != UTIL_FORMAT_COLORSPACE_ZS) {
+		word4 |= r600_get_swizzle_combined(desc->swizzle, swizzle_view, FALSE);
+	}
 
 	/* Colorspace (return non-RGB formats directly). */
 	switch (desc->colorspace) {
 	/* Depth stencil formats */
 	case UTIL_FORMAT_COLORSPACE_ZS:
 		switch (format) {
+		/* Depth sampler formats. */
 		case PIPE_FORMAT_Z16_UNORM:
+			word4 |= r600_get_swizzle_combined(swizzle_xxxx, swizzle_view, FALSE);
 			result = FMT_16;
 			goto out_word4;
-		case PIPE_FORMAT_X24S8_UINT:
-			word4 |= S_038010_NUM_FORMAT_ALL(V_038010_SQ_NUM_FORMAT_INT);
 		case PIPE_FORMAT_Z24X8_UNORM:
 		case PIPE_FORMAT_Z24_UNORM_S8_UINT:
+			word4 |= r600_get_swizzle_combined(swizzle_xxxx, swizzle_view, FALSE);
 			result = FMT_8_24;
 			goto out_word4;
-		case PIPE_FORMAT_S8X24_UINT:
-			word4 |= S_038010_NUM_FORMAT_ALL(V_038010_SQ_NUM_FORMAT_INT);
 		case PIPE_FORMAT_X8Z24_UNORM:
 		case PIPE_FORMAT_S8_UINT_Z24_UNORM:
+			if (rscreen->chip_class < EVERGREEN)
+				goto out_unknown;
+			word4 |= r600_get_swizzle_combined(swizzle_yyyy, swizzle_view, FALSE);
 			result = FMT_24_8;
 			goto out_word4;
+		case PIPE_FORMAT_Z32_FLOAT:
+			word4 |= r600_get_swizzle_combined(swizzle_xxxx, swizzle_view, FALSE);
+			result = FMT_32_FLOAT;
+			goto out_word4;
+		case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
+			word4 |= r600_get_swizzle_combined(swizzle_xxxx, swizzle_view, FALSE);
+			result = FMT_X24_8_32_FLOAT;
+			goto out_word4;
+		/* Stencil sampler formats. */
 		case PIPE_FORMAT_S8_UINT:
+			word4 |= S_038010_NUM_FORMAT_ALL(V_038010_SQ_NUM_FORMAT_INT);
+			word4 |= r600_get_swizzle_combined(swizzle_xxxx, swizzle_view, FALSE);
 			result = FMT_8;
+			goto out_word4;
+		case PIPE_FORMAT_X24S8_UINT:
 			word4 |= S_038010_NUM_FORMAT_ALL(V_038010_SQ_NUM_FORMAT_INT);
+			word4 |= r600_get_swizzle_combined(swizzle_yyyy, swizzle_view, FALSE);
+			result = FMT_8_24;
 			goto out_word4;
-		case PIPE_FORMAT_Z32_FLOAT:
-			result = FMT_32_FLOAT;
+		case PIPE_FORMAT_S8X24_UINT:
+			if (rscreen->chip_class < EVERGREEN)
+				goto out_unknown;
+			word4 |= S_038010_NUM_FORMAT_ALL(V_038010_SQ_NUM_FORMAT_INT);
+			word4 |= r600_get_swizzle_combined(swizzle_xxxx, swizzle_view, FALSE);
+			result = FMT_24_8;
 			goto out_word4;
 		case PIPE_FORMAT_X32_S8X24_UINT:
 			word4 |= S_038010_NUM_FORMAT_ALL(V_038010_SQ_NUM_FORMAT_INT);
-		case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
+			word4 |= r600_get_swizzle_combined(swizzle_yyyy, swizzle_view, FALSE);
 			result = FMT_X24_8_32_FLOAT;
 			goto out_word4;
 		default:
@@ -1057,7 +1084,6 @@ uint32_t r600_translate_texformat(struct pipe_screen *screen,
 	}
 
 	if (r600_enable_s3tc == -1) {
-		struct r600_screen *rscreen = (struct r600_screen *)screen;
 		if (rscreen->info.drm_minor >= 9)
 			r600_enable_s3tc = 1;
 		else