Merge branch 'master' into instanced-arrays

Conflicts:
	src/gallium/auxiliary/tgsi/tgsi_dump.c
	src/gallium/include/pipe/p_shader_tokens.h

5 files changed, 82 insertions, 19 deletions

diff --git a/src/gallium/drivers/nv30/nv30_context.c b/src/gallium/drivers/nv30/nv30_context.c
index 46a821a48b1..38b39159f19 100644
--- a/src/gallium/drivers/nv30/nv30_context.c
+++ b/src/gallium/drivers/nv30/nv30_context.c
@@ -25,6 +25,12 @@ static void
 nv30_destroy(struct pipe_context *pipe)
 {
 	struct nv30_context *nv30 = nv30_context(pipe);
+	unsigned i;
+
+	for (i = 0; i < NV30_STATE_MAX; i++) {
+		if (nv30->state.hw[i])
+			so_ref(NULL, &nv30->state.hw[i]);
+	}
 
 	if (nv30->draw)
 		draw_destroy(nv30->draw);
diff --git a/src/gallium/drivers/nv30/nv30_fragprog.c b/src/gallium/drivers/nv30/nv30_fragprog.c
index 40965a97723..d1ff18e2dfb 100644
--- a/src/gallium/drivers/nv30/nv30_fragprog.c
+++ b/src/gallium/drivers/nv30/nv30_fragprog.c
@@ -435,10 +435,11 @@ nv30_fragprog_parse_instruction(struct nv30_fpc *fpc,
 		arith(fpc, sat, ADD, dst, mask, src[0], src[1], none);
 		break;
 	case TGSI_OPCODE_CMP:
-		tmp = temp(fpc);
-		arith(fpc, sat, MOV, dst, mask, src[2], none, none);
+		tmp = nv30_sr(NV30SR_NONE, 0);
 		tmp.cc_update = 1;
 		arith(fpc, 0, MOV, tmp, 0xf, src[0], none, none);
+		dst.cc_test = NV30_VP_INST_COND_GE;
+		arith(fpc, sat, MOV, dst, mask, src[2], none, none);
 		dst.cc_test = NV30_VP_INST_COND_LT;
 		arith(fpc, sat, MOV, dst, mask, src[1], none, none);
 		break;
@@ -517,13 +518,28 @@ nv30_fragprog_parse_instruction(struct nv30_fpc *fpc,
 		arith(fpc, sat, RSQ, dst, mask, abs(swz(src[0], X, X, X, X)), none, none);
 		break;
 	case TGSI_OPCODE_SCS:
-		if (mask & MASK_X) {
-			arith(fpc, sat, COS, dst, MASK_X,
-			      swz(src[0], X, X, X, X), none, none);
+		/* avoid overwriting the source */
+		if(src[0].swz[SWZ_X] != SWZ_X)
+		{
+			if (mask & MASK_X) {
+				arith(fpc, sat, COS, dst, MASK_X,
+				      swz(src[0], X, X, X, X), none, none);
+			}
+			if (mask & MASK_Y) {
+				arith(fpc, sat, SIN, dst, MASK_Y,
+				      swz(src[0], X, X, X, X), none, none);
+			}
 		}
-		if (mask & MASK_Y) {
-			arith(fpc, sat, SIN, dst, MASK_Y,
-			      swz(src[0], X, X, X, X), none, none);
+		else
+		{
+			if (mask & MASK_Y) {
+				arith(fpc, sat, SIN, dst, MASK_Y,
+				      swz(src[0], X, X, X, X), none, none);
+			}
+			if (mask & MASK_X) {
+				arith(fpc, sat, COS, dst, MASK_X,
+				      swz(src[0], X, X, X, X), none, none);
+			}
 		}
 		break;
 	case TGSI_OPCODE_SIN:
@@ -870,6 +886,12 @@ void
 nv30_fragprog_destroy(struct nv30_context *nv30,
 		      struct nv30_fragment_program *fp)
 {
+	if (fp->buffer)
+		pipe_buffer_reference(&fp->buffer, NULL);
+
+	if (fp->so)
+		so_ref(NULL, &fp->so);
+
 	if (fp->insn_len)
 		FREE(fp->insn);
 }
diff --git a/src/gallium/drivers/nv30/nv30_miptree.c b/src/gallium/drivers/nv30/nv30_miptree.c
index ce95d9700f6..8fbba38e78f 100644
--- a/src/gallium/drivers/nv30/nv30_miptree.c
+++ b/src/gallium/drivers/nv30/nv30_miptree.c
@@ -5,6 +5,7 @@
 #include "util/u_math.h"
 
 #include "nv30_context.h"
+#include "../nv04/nv04_surface_2d.h"
 
 static void
 nv30_miptree_layout(struct nv30_miptree *nv30mt)
@@ -108,6 +109,12 @@ nv30_miptree_create(struct pipe_screen *pscreen, const struct pipe_texture *pt)
 	if (pt->tex_usage & PIPE_TEXTURE_USAGE_DYNAMIC)
 		buf_usage |= PIPE_BUFFER_USAGE_CPU_READ_WRITE;
 
+	/* apparently we can't render to swizzled surfaces smaller than 64 bytes, so make them linear.
+	 * If the user did not ask for a render target, they can still render to it, but it will cost them an extra copy.
+	 * This also happens for small mipmaps of large textures. */
+	if (pt->tex_usage & PIPE_TEXTURE_USAGE_RENDER_TARGET && util_format_get_stride(pt->format, pt->width0) < 64)
+		mt->base.tex_usage |= NOUVEAU_TEXTURE_USAGE_LINEAR;
+
 	nv30_miptree_layout(mt);
 
 	mt->buffer = pscreen->buffer_create(pscreen, 256, buf_usage,
@@ -196,12 +203,27 @@ nv30_miptree_surface_new(struct pipe_screen *pscreen, struct pipe_texture *pt,
 		ns->base.offset = nv30mt->level[level].image_offset[0];
 	}
 
+	/* create a linear temporary that we can render into if necessary.
+	 * Note that ns->pitch is always a multiple of 64 for linear surfaces and swizzled surfaces are POT, so
+	 * ns->pitch & 63 is equivalent to (ns->pitch < 64 && swizzled)*/
+	if((ns->pitch & 63) && (ns->base.usage & (PIPE_BUFFER_USAGE_GPU_WRITE | NOUVEAU_BUFFER_USAGE_NO_RENDER)) == PIPE_BUFFER_USAGE_GPU_WRITE)
+		return &nv04_surface_wrap_for_render(pscreen, ((struct nv30_screen*)pscreen)->eng2d, ns)->base;
+
 	return &ns->base;
 }
 
 static void
 nv30_miptree_surface_del(struct pipe_surface *ps)
 {
+	struct nv04_surface* ns = (struct nv04_surface*)ps;
+	if(ns->backing)
+	{
+		struct nv30_screen* screen = (struct nv30_screen*)ps->texture->screen;
+		if(ns->backing->base.usage & PIPE_BUFFER_USAGE_GPU_WRITE)
+			screen->eng2d->copy(screen->eng2d, &ns->backing->base, 0, 0, ps, 0, 0, ns->base.width, ns->base.height);
+		nv30_miptree_surface_del(&ns->backing->base);
+	}
+
 	pipe_texture_reference(&ps->texture, NULL);
 	FREE(ps);
 }
diff --git a/src/gallium/drivers/nv30/nv30_screen.c b/src/gallium/drivers/nv30/nv30_screen.c
index 7cd36902eb4..760467f7367 100644
--- a/src/gallium/drivers/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nv30/nv30_screen.c
@@ -156,6 +156,12 @@ static void
 nv30_screen_destroy(struct pipe_screen *pscreen)
 {
 	struct nv30_screen *screen = nv30_screen(pscreen);
+	unsigned i;
+
+	for (i = 0; i < NV30_STATE_MAX; i++) {
+		if (screen->state[i])
+			so_ref(NULL, &screen->state[i]);
+	}
 
 	nouveau_resource_free(&screen->vp_exec_heap);
 	nouveau_resource_free(&screen->vp_data_heap);
@@ -163,6 +169,9 @@ nv30_screen_destroy(struct pipe_screen *pscreen)
 	nouveau_notifier_free(&screen->query);
 	nouveau_notifier_free(&screen->sync);
 	nouveau_grobj_free(&screen->rankine);
+	nv04_surface_2d_takedown(&screen->eng2d);
+
+	nouveau_screen_fini(&screen->base);
 
 	FREE(pscreen);
 }
diff --git a/src/gallium/drivers/nv30/nv30_transfer.c b/src/gallium/drivers/nv30/nv30_transfer.c
index 2255a02caed..65598991c68 100644
--- a/src/gallium/drivers/nv30/nv30_transfer.c
+++ b/src/gallium/drivers/nv30/nv30_transfer.c
@@ -16,14 +16,14 @@ struct nv30_transfer {
 };
 
 static void
-nv30_compatible_transfer_tex(struct pipe_texture *pt, unsigned level,
+nv30_compatible_transfer_tex(struct pipe_texture *pt, unsigned width, unsigned height,
                              struct pipe_texture *template)
 {
 	memset(template, 0, sizeof(struct pipe_texture));
 	template->target = pt->target;
 	template->format = pt->format;
-	template->width0 = u_minify(pt->width0, level);
-	template->height0 = u_minify(pt->height0, level);
+	template->width0 = width;
+	template->height0 = height;
 	template->depth0 = 1;
 	template->last_level = 0;
 	template->nr_samples = pt->nr_samples;
@@ -71,7 +71,7 @@ nv30_transfer_new(struct pipe_screen *pscreen, struct pipe_texture *pt,
 
 	tx->direct = false;
 
-	nv30_compatible_transfer_tex(pt, level, &tx_tex_template);
+	nv30_compatible_transfer_tex(pt, w, h, &tx_tex_template);
 
 	tx_tex = pscreen->texture_create(pscreen, &tx_tex_template);
 	if (!tx_tex)
@@ -80,6 +80,8 @@ nv30_transfer_new(struct pipe_screen *pscreen, struct pipe_texture *pt,
 		return NULL;
 	}
 
+	tx->base.stride = ((struct nv30_miptree*)tx_tex)->level[0].pitch;
+
 	tx->surface = pscreen->get_tex_surface(pscreen, tx_tex,
 	                                       0, 0, 0,
 	                                       pipe_transfer_buffer_flags(&tx->base));
@@ -105,8 +107,8 @@ nv30_transfer_new(struct pipe_screen *pscreen, struct pipe_texture *pt,
 		/* TODO: Check if SIFM can un-swizzle */
 		nvscreen->eng2d->copy(nvscreen->eng2d,
 		                      tx->surface, 0, 0,
-		                      src, 0, 0,
-		                      src->width, src->height);
+		                      src, x, y,
+		                      w, h);
 
 		pipe_surface_reference(&src, NULL);
 	}
@@ -126,13 +128,13 @@ nv30_transfer_del(struct pipe_transfer *ptx)
 
 		dst = pscreen->get_tex_surface(pscreen, ptx->texture,
 	                                       ptx->face, ptx->level, ptx->zslice,
-	                                       PIPE_BUFFER_USAGE_GPU_WRITE);
+	                                       PIPE_BUFFER_USAGE_GPU_WRITE | NOUVEAU_BUFFER_USAGE_NO_RENDER);
 
 		/* TODO: Check if SIFM can deal with x,y,w,h when swizzling */
 		nvscreen->eng2d->copy(nvscreen->eng2d,
-		                      dst, 0, 0,
+		                      dst, tx->base.x, tx->base.y,
 		                      tx->surface, 0, 0,
-		                      dst->width, dst->height);
+		                      tx->base.width, tx->base.height);
 
 		pipe_surface_reference(&dst, NULL);
 	}
@@ -151,8 +153,10 @@ nv30_transfer_map(struct pipe_screen *pscreen, struct pipe_transfer *ptx)
 	void *map = pipe_buffer_map(pscreen, mt->buffer,
 	                            pipe_transfer_buffer_flags(ptx));
 
-	return map + ns->base.offset +
-	       ptx->y * ns->pitch + ptx->x * util_format_get_blocksize(ptx->texture->format);
+	if(!tx->direct)
+		return map + ns->base.offset;
+	else
+		return map + ns->base.offset + ptx->y * ns->pitch + ptx->x * util_format_get_blocksize(ptx->texture->format);
 }
 
 static void