nvfx: rewrite draw code and buffer code

This is a full rewrite of the drawing and buffer management logic.

It offers a lot of improvements:
1. A copy of buffers is now always kept in system memory. This is
   necessary to allow software processing of them, which is necessary
   or improves performance in many cases.
2. Support for pushing vertices on the FIFO, with index lookup if necessary.
3. "Smart" draw code that tries to intelligently choose the cheapest
  way to draw something: whether to use inline vertices or hardware
  vertex buffer, and whether to use hardware index buffers
4. Support for all vertex formats supported by the hardware
5. Usage of translate to push vertices, supporting all formats that are
   sensible to use as vertex formats
6. Support for base vertex
7. Usage of Ben Skeggs' primitive splitter originally for nv50, allowing
   correct splitting of line loops, triangle fans, etc.
8. Support for instancing
9. Precomputation using the vertex elements CSO

Thanks to Ben Skeggs for his primitive splitter originally for nv50.

Thanks to Christoph Bumiller for his nv50 push code, that was the basis
of this work, even though I changed his code dramatically, in particular
to replace his ad-hoc vertex data emitter with translate.

The changes could also go into nv50 too, but there are substantial
differences due to the additional nv50 hardware features.

1 files changed, 0 insertions, 91 deletions

diff --git a/src/gallium/drivers/nouveau/nouveau_util.h b/src/gallium/drivers/nouveau/nouveau_util.h
deleted file mode 100644
index b165f7a611..0000000000
--- a/src/gallium/drivers/nouveau/nouveau_util.h
+++ /dev/null
@@ -1,91 +0,0 @@
-#ifndef __NOUVEAU_UTIL_H__
-#define __NOUVEAU_UTIL_H__
-
-/* Determine how many vertices can be pushed into the command stream.
- * Where the remaining space isn't large enough to represent all verices,
- * split the buffer at primitive boundaries.
- *
- * Returns a count of vertices that can be rendered, and an index to
- * restart drawing at after a flush.
- */
-static INLINE unsigned
-nouveau_vbuf_split(unsigned remaining, unsigned overhead, unsigned vpp,
-		   unsigned mode, unsigned start, unsigned count,
-		   unsigned *restart)
-{
-	int max, adj = 0;
-
-	max  = remaining - overhead;
-	if (max < 0)
-		return 0;
-
-	max *= vpp;
-	if (max >= count)
-		return count;
-
-	switch (mode) {
-	case PIPE_PRIM_POINTS:
-		break;
-	case PIPE_PRIM_LINES:
-		max = max & 1;
-		break;
-	case PIPE_PRIM_TRIANGLES:
-		max = max - (max % 3);
-		break;
-	case PIPE_PRIM_QUADS:
-		max = max & ~3;
-		break;
-	case PIPE_PRIM_LINE_LOOP:
-	case PIPE_PRIM_LINE_STRIP:
-		if (max < 2)
-			max = 0;
-		adj = 1;
-		break;
-	case PIPE_PRIM_POLYGON:
-	case PIPE_PRIM_TRIANGLE_STRIP:
-	case PIPE_PRIM_TRIANGLE_FAN:
-		if (max < 3)
-			max = 0;
-		adj = 2;
-		break;
-	case PIPE_PRIM_QUAD_STRIP:
-		if (max < 4)
-			max = 0;
-		adj = 3;
-		break;
-	default:
-		assert(0);
-	}
-
-	*restart = start + max - adj;
-	return max;
-}
-
-/* Integer base-2 logarithm, rounded towards zero. */
-static INLINE unsigned log2i(unsigned i)
-{
-	unsigned r = 0;
-
-	if (i & 0xffff0000) {
-		i >>= 16;
-		r += 16;
-	}
-	if (i & 0x0000ff00) {
-		i >>= 8;
-		r += 8;
-	}
-	if (i & 0x000000f0) {
-		i >>= 4;
-		r += 4;
-	}
-	if (i & 0x0000000c) {
-		i >>= 2;
-		r += 2;
-	}
-	if (i & 0x00000002) {
-		r += 1;
-	}
-	return r;
-}
-
-#endif