a3xx: make sure to actually clamp depth as requested

We were previously ... not clamping. I guess this meant that everything
got clamped to 1/0, which was enough to pass the existing tests. Or
perhaps the clamping would only happen to the rasterized depth value and
not the frag shader's output depth value.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97231
Signed-off-by: Ilia Mirkin <[email protected]>
Cc: [email protected]

2 files changed, 30 insertions, 2 deletions

diff --git a/src/gallium/drivers/freedreno/a3xx/a3xx.xml.h b/src/gallium/drivers/freedreno/a3xx/a3xx.xml.h
index dcb6dfb7414..bf787d1cc3a 100644
--- a/src/gallium/drivers/freedreno/a3xx/a3xx.xml.h
+++ b/src/gallium/drivers/freedreno/a3xx/a3xx.xml.h
@@ -1472,7 +1472,7 @@ static inline uint32_t A3XX_RB_DEPTH_CONTROL_ZFUNC(enum adreno_compare_func val)
 {
 	return ((val) << A3XX_RB_DEPTH_CONTROL_ZFUNC__SHIFT) & A3XX_RB_DEPTH_CONTROL_ZFUNC__MASK;
 }
-#define A3XX_RB_DEPTH_CONTROL_BF_ENABLE				0x00000080
+#define A3XX_RB_DEPTH_CONTROL_Z_CLAMP_ENABLE			0x00000080
 #define A3XX_RB_DEPTH_CONTROL_Z_TEST_ENABLE			0x80000000
 
 #define REG_A3XX_RB_DEPTH_CLEAR					0x00002101
diff --git a/src/gallium/drivers/freedreno/a3xx/fd3_emit.c b/src/gallium/drivers/freedreno/a3xx/fd3_emit.c
index 3466a0dd68b..e66836b43c2 100644
--- a/src/gallium/drivers/freedreno/a3xx/fd3_emit.c
+++ b/src/gallium/drivers/freedreno/a3xx/fd3_emit.c
@@ -31,6 +31,7 @@
 #include "util/u_memory.h"
 #include "util/u_helpers.h"
 #include "util/u_format.h"
+#include "util/u_viewport.h"
 
 #include "freedreno_resource.h"
 #include "freedreno_query_hw.h"
@@ -535,7 +536,7 @@ fd3_emit_state(struct fd_context *ctx, struct fd_ringbuffer *ring,
 				A3XX_RB_STENCILREFMASK_BF_STENCILREF(sr->ref_value[1]));
 	}
 
-	if (dirty & (FD_DIRTY_ZSA | FD_DIRTY_PROG)) {
+	if (dirty & (FD_DIRTY_ZSA | FD_DIRTY_RASTERIZER | FD_DIRTY_PROG)) {
 		uint32_t val = fd3_zsa_stateobj(ctx->zsa)->rb_depth_control;
 		if (fp->writes_pos) {
 			val |= A3XX_RB_DEPTH_CONTROL_FRAG_WRITES_Z;
@@ -544,6 +545,9 @@ fd3_emit_state(struct fd_context *ctx, struct fd_ringbuffer *ring,
 		if (fp->has_kill) {
 			val |= A3XX_RB_DEPTH_CONTROL_EARLY_Z_DISABLE;
 		}
+		if (!ctx->rasterizer->depth_clip) {
+			val |= A3XX_RB_DEPTH_CONTROL_Z_CLAMP_ENABLE;
+		}
 		OUT_PKT0(ring, REG_A3XX_RB_DEPTH_CONTROL, 1);
 		OUT_RING(ring, val);
 	}
@@ -647,6 +651,30 @@ fd3_emit_state(struct fd_context *ctx, struct fd_ringbuffer *ring,
 		OUT_RING(ring, A3XX_GRAS_CL_VPORT_ZSCALE(ctx->viewport.scale[2]));
 	}
 
+	if (dirty & (FD_DIRTY_VIEWPORT | FD_DIRTY_RASTERIZER | FD_DIRTY_FRAMEBUFFER)) {
+		float zmin, zmax;
+		int depth = 24;
+		if (ctx->batch->framebuffer.zsbuf) {
+			depth = util_format_get_component_bits(
+					pipe_surface_format(ctx->batch->framebuffer.zsbuf),
+					UTIL_FORMAT_COLORSPACE_ZS, 0);
+		}
+		util_viewport_zmin_zmax(&ctx->viewport, ctx->rasterizer->clip_halfz,
+								&zmin, &zmax);
+
+		OUT_PKT0(ring, REG_A3XX_RB_Z_CLAMP_MIN, 2);
+		if (depth == 32) {
+			OUT_RING(ring, (uint32_t)(zmin * 0xffffffff));
+			OUT_RING(ring, (uint32_t)(zmax * 0xffffffff));
+		} else if (depth == 16) {
+			OUT_RING(ring, (uint32_t)(zmin * 0xffff));
+			OUT_RING(ring, (uint32_t)(zmax * 0xffff));
+		} else {
+			OUT_RING(ring, (uint32_t)(zmin * 0xffffff));
+			OUT_RING(ring, (uint32_t)(zmax * 0xffffff));
+		}
+	}
+
 	if (dirty & (FD_DIRTY_PROG | FD_DIRTY_FRAMEBUFFER | FD_DIRTY_BLEND_DUAL)) {
 		struct pipe_framebuffer_state *pfb = &ctx->batch->framebuffer;
 		int nr_cbufs = pfb->nr_cbufs;