nv50: proper linkage between VP and FP

This moves construction of the mapping between VP outputs
and FP inputs into validation.

The map also contains slots for special outputs like clip
distance and point size, so we need to at least merge the
VP related and FP related parts on validation if we want
to support those.

Now we match every single FP input component with results
from the VP and leave those not read out of the map, or
replace those not written by 0 (xyz) or 1 (w).
The bitmap indicating linear interpolants is also filled,
and flat FP inputs are mapped in only after non-flat ones,
as is required.

Furthermore, we can save some space by only fetching VP
attrs we actually use, and avoid wasting any output regs
because of TGSI using less than 4 components.

1 files changed, 22 insertions, 8 deletions

diff --git a/src/gallium/drivers/nv50/nv50_program.h b/src/gallium/drivers/nv50/nv50_program.h
index 096e0476aa..5745e0b1ee 100644
--- a/src/gallium/drivers/nv50/nv50_program.h
+++ b/src/gallium/drivers/nv50/nv50_program.h
@@ -15,6 +15,15 @@ struct nv50_program_exec {
 	} param;
 };
 
+struct nv50_sreg4 {
+	uint8_t hw;
+	uint8_t id_vp;
+	uint8_t id_fp;
+
+	uint8_t mask;
+	boolean linear;
+};
+
 struct nv50_program {
 	struct pipe_shader_state pipe;
 	struct tgsi_shader_info info;
@@ -36,14 +45,19 @@ struct nv50_program {
 	struct {
 		unsigned high_temp;
 		unsigned high_result;
-		struct {
-			unsigned attr[2];
-		} vp;
-		struct {
-			unsigned regs[4];
-			unsigned map[5];
-			unsigned high_map;
-		} fp;
+
+		uint32_t attr[2];
+		uint32_t regs[4];
+
+		/* for VPs, io_nr doesn't count 'private' results (PSIZ etc.) */
+		unsigned io_nr;
+		struct nv50_sreg4 io[PIPE_MAX_SHADER_OUTPUTS];
+
+		/* FP colour inputs, VP/GP back colour outputs */
+		struct nv50_sreg4 two_side[2];
+
+		/* VP only */
+		uint8_t clpd, clpd_nr;
 	} cfg;
 };