Increment version to 10.4.0-rc3

Signed-off-by: Emil Velikov <emil.l.velikov@gmail.com>

VERSION

@@ -1 +1 @@
-10.4.0-rc2
+10.4.0-rc3

configure.ac

@@ -2085,6 +2085,8 @@ AM_CONDITIONAL(HAVE_SPARC_ASM, test "x$asm_arch" = xsparc)
 
 AC_SUBST([NINE_MAJOR], 1)
 AC_SUBST([NINE_MINOR], 0)
+AC_SUBST([NINE_TINY], 0)
+AC_SUBST([NINE_VERSION], "$NINE_MAJOR.$NINE_MINOR.$NINE_TINY")
 
 AC_SUBST([VDPAU_MAJOR], 1)
 AC_SUBST([VDPAU_MINOR], 0)

src/gallium/auxiliary/util/u_snprintf.c

@@ -176,7 +176,7 @@
 #define HAVE_ASPRINTF 1 /* not needed */
 #define HAVE_STDARG_H 1
 #define HAVE_STDDEF_H 1
-#define HAVE_STDINT_H 0
+#define HAVE_STDINT_H 1
 #define HAVE_STDLIB_H 1
 #define HAVE_INTTYPES_H 0
 #define HAVE_LOCALE_H 0

src/gallium/drivers/freedreno/ir3/ir3_compiler.c

@@ -2350,6 +2350,9 @@ trans_idiv(const struct instr_translater *t,
 	if (t->tgsi_opc == TGSI_OPCODE_MOD || t->tgsi_opc == TGSI_OPCODE_UMOD) {
 		/* The division result will have ended up in q. */
 
+		if (is_rel_or_const(b))
+			b = get_unconst(ctx, b);
+
 		/* mull.u r, q, b */
 		instr = instr_create(ctx, 2, OPC_MULL_U);
 		vectorize(ctx, instr, &r_dst, 2, q_src, 0, b, 0);

src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp

@@ -924,7 +924,9 @@ CodeEmitterNV50::emitMINMAX(const Instruction *i)
          break;
       }
       code[1] |= i->src(0).mod.abs() << 20;
+      code[1] |= i->src(0).mod.neg() << 26;
       code[1] |= i->src(1).mod.abs() << 19;
+      code[1] |= i->src(1).mod.neg() << 27;
    }
    emitForm_MAD(i);
 }

src/gallium/drivers/nouveau/nv50/nv50_context.c

@@ -180,7 +180,12 @@ nv50_invalidate_resource_storage(struct nouveau_context *ctx,
       }
    }
 
-   if (res->bind & PIPE_BIND_VERTEX_BUFFER) {
+   if (res->bind & (PIPE_BIND_VERTEX_BUFFER |
+                    PIPE_BIND_INDEX_BUFFER |
+                    PIPE_BIND_CONSTANT_BUFFER |
+                    PIPE_BIND_STREAM_OUTPUT |
+                    PIPE_BIND_SAMPLER_VIEW)) {
+
       assert(nv50->num_vtxbufs <= PIPE_MAX_ATTRIBS);
       for (i = 0; i < nv50->num_vtxbufs; ++i) {
          if (nv50->vtxbuf[i].buffer == res) {
@@ -190,14 +195,11 @@ nv50_invalidate_resource_storage(struct nouveau_context *ctx,
                return ref;
          }
       }
-   }
-   if (res->bind & PIPE_BIND_INDEX_BUFFER) {
+
       if (nv50->idxbuf.buffer == res)
          if (!--ref)
             return ref;
-   }
 
-   if (res->bind & PIPE_BIND_SAMPLER_VIEW) {
       for (s = 0; s < 3; ++s) {
       assert(nv50->num_textures[s] <= PIPE_MAX_SAMPLERS);
       for (i = 0; i < nv50->num_textures[s]; ++i) {
@@ -210,12 +212,11 @@ nv50_invalidate_resource_storage(struct nouveau_context *ctx,
          }
       }
       }
-   }
 
-   if (res->bind & PIPE_BIND_CONSTANT_BUFFER) {
       for (s = 0; s < 3; ++s) {
-      assert(nv50->num_vtxbufs <= NV50_MAX_PIPE_CONSTBUFS);
-      for (i = 0; i < nv50->num_vtxbufs; ++i) {
+      for (i = 0; i < NV50_MAX_PIPE_CONSTBUFS; ++i) {
+         if (!(nv50->constbuf_valid[s] & (1 << i)))
+            continue;
          if (!nv50->constbuf[s][i].user &&
              nv50->constbuf[s][i].u.buf == res) {
             nv50->dirty |= NV50_NEW_CONSTBUF;

src/gallium/drivers/nouveau/nvc0/nvc0_context.c

@@ -196,7 +196,12 @@ nvc0_invalidate_resource_storage(struct nouveau_context *ctx,
       }
    }
 
-   if (res->bind & PIPE_BIND_VERTEX_BUFFER) {
+   if (res->bind & (PIPE_BIND_VERTEX_BUFFER |
+                    PIPE_BIND_INDEX_BUFFER |
+                    PIPE_BIND_CONSTANT_BUFFER |
+                    PIPE_BIND_STREAM_OUTPUT |
+                    PIPE_BIND_COMMAND_ARGS_BUFFER |
+                    PIPE_BIND_SAMPLER_VIEW)) {
       for (i = 0; i < nvc0->num_vtxbufs; ++i) {
          if (nvc0->vtxbuf[i].buffer == res) {
             nvc0->dirty |= NVC0_NEW_ARRAYS;
@@ -205,17 +210,14 @@ nvc0_invalidate_resource_storage(struct nouveau_context *ctx,
                return ref;
          }
       }
-   }
-   if (res->bind & PIPE_BIND_INDEX_BUFFER) {
+
       if (nvc0->idxbuf.buffer == res) {
          nvc0->dirty |= NVC0_NEW_IDXBUF;
          nouveau_bufctx_reset(nvc0->bufctx_3d, NVC0_BIND_IDX);
          if (!--ref)
             return ref;
       }
-   }
 
-   if (res->bind & PIPE_BIND_SAMPLER_VIEW) {
       for (s = 0; s < 5; ++s) {
       for (i = 0; i < nvc0->num_textures[s]; ++i) {
          if (nvc0->textures[s][i] &&
@@ -228,11 +230,11 @@ nvc0_invalidate_resource_storage(struct nouveau_context *ctx,
          }
       }
       }
-   }
 
-   if (res->bind & PIPE_BIND_CONSTANT_BUFFER) {
       for (s = 0; s < 5; ++s) {
-      for (i = 0; i < nvc0->num_vtxbufs; ++i) {
+      for (i = 0; i < NVC0_MAX_PIPE_CONSTBUFS; ++i) {
+         if (!(nvc0->constbuf_valid[s] & (1 << i)))
+            continue;
          if (!nvc0->constbuf[s][i].user &&
              nvc0->constbuf[s][i].u.buf == res) {
             nvc0->dirty |= NVC0_NEW_CONSTBUF;

src/gallium/drivers/r600/r600_llvm.c

@@ -23,7 +23,6 @@
 
 #define CONSTANT_BUFFER_0_ADDR_SPACE 8
 #define CONSTANT_BUFFER_1_ADDR_SPACE (CONSTANT_BUFFER_0_ADDR_SPACE + R600_UCP_CONST_BUFFER)
-#define CONSTANT_TXQ_BUFFER (CONSTANT_BUFFER_0_ADDR_SPACE + R600_TXQ_CONST_BUFFER)
 #define LLVM_R600_BUFFER_INFO_CONST_BUFFER \
 	(CONSTANT_BUFFER_0_ADDR_SPACE + R600_BUFFER_INFO_CONST_BUFFER)
 
@@ -690,7 +689,7 @@ static void llvm_emit_tex(
 		if (emit_data->inst->Dst[0].Register.WriteMask & 4) {
 			LLVMValueRef offset = lp_build_const_int32(bld_base->base.gallivm, 0);
 			LLVMValueRef ZLayer = LLVMBuildExtractElement(gallivm->builder,
-				llvm_load_const_buffer(bld_base, offset, CONSTANT_TXQ_BUFFER),
+				llvm_load_const_buffer(bld_base, offset, LLVM_R600_BUFFER_INFO_CONST_BUFFER),
 				lp_build_const_int32(gallivm, 0), "");
 
 			emit_data->output[0] = LLVMBuildInsertElement(gallivm->builder, emit_data->output[0], ZLayer, lp_build_const_int32(gallivm, 2), "");

src/gallium/drivers/r600/r600_pipe.h

@@ -44,20 +44,19 @@
 #define R600_TRACE_CS_DWORDS		7
 
 #define R600_MAX_USER_CONST_BUFFERS 13
-#define R600_MAX_DRIVER_CONST_BUFFERS 4
+#define R600_MAX_DRIVER_CONST_BUFFERS 3
 #define R600_MAX_CONST_BUFFERS (R600_MAX_USER_CONST_BUFFERS + R600_MAX_DRIVER_CONST_BUFFERS)
 
 /* start driver buffers after user buffers */
 #define R600_UCP_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS)
-#define R600_TXQ_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 1)
-#define R600_BUFFER_INFO_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 2)
-#define R600_GS_RING_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 3)
-/* Currently R600_MAX_CONST_BUFFERS is too large, the hardware only has 16 buffers, but the driver is
- * trying to use 17. Avoid accidentally aliasing with user UBOs for SAMPLE_POSITIONS by using an id<16.
+#define R600_BUFFER_INFO_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 1)
+#define R600_GS_RING_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 2)
+/* Currently R600_MAX_CONST_BUFFERS just fits on the hw, which has a limit
+ * of 16 const buffers.
  * UCP/SAMPLE_POSITIONS are never accessed by same shader stage so they can use the same id.
  *
- * Fixing this properly would require the driver to combine its buffers into a single hardware buffer,
- * which would also allow supporting the d3d 11 mandated minimum of 15 user const buffers.
+ * In order to support d3d 11 mandated minimum of 15 user const buffers
+ * we'd have to squash all use cases into one driver buffer.
  */
 #define R600_SAMPLE_POSITIONS_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS)
 
@@ -316,7 +315,6 @@ struct r600_samplerview_state {
 	uint32_t			dirty_mask;
 	uint32_t			compressed_depthtex_mask; /* which textures are depth */
 	uint32_t			compressed_colortex_mask;
-	boolean                         dirty_txq_constants;
 	boolean				dirty_buffer_constants;
 };
 

src/gallium/drivers/r600/r600_shader.c

@@ -5035,8 +5035,9 @@ static int r600_do_buffer_txq(struct r600_shader_ctx *ctx)
 	alu.op = ALU_OP1_MOV;
 
 	if (ctx->bc->chip_class >= EVERGREEN) {
-		alu.src[0].sel = 512 + (id / 4);
-		alu.src[0].chan = id % 4;
+		/* channel 0 or 2 of each word */
+		alu.src[0].sel = 512 + (id / 2);
+		alu.src[0].chan = (id % 2) * 2;
 	} else {
 		/* r600 we have them at channel 2 of the second dword */
 		alu.src[0].sel = 512 + (id * 2) + 1;
@@ -5095,6 +5096,14 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 	    inst->Instruction.Opcode == TGSI_OPCODE_TG4)
 		sampler_src_reg = 2;
 
+	/* TGSI moves the sampler to src reg 3 for TXD */
+	if (inst->Instruction.Opcode == TGSI_OPCODE_TXD)
+		sampler_src_reg = 3;
+
+	sampler_index_mode = inst->Src[sampler_src_reg].Indirect.Index == 2 ? 2 : 0; // CF_INDEX_1 : CF_INDEX_NONE
+	if (sampler_index_mode)
+		ctx->shader->uses_index_registers = true;
+
 	src_gpr = tgsi_tex_get_src_gpr(ctx, 0);
 
 	if (inst->Texture.Texture == TGSI_TEXTURE_BUFFER) {
@@ -5109,64 +5118,7 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 		}
 	}
 
-	if (inst->Instruction.Opcode == TGSI_OPCODE_TXD) {
-		/* TGSI moves the sampler to src reg 3 for TXD */
-		sampler_src_reg = 3;
-
-		sampler_index_mode = inst->Src[sampler_src_reg].Indirect.Index == 2 ? 2 : 0; // CF_INDEX_1 : CF_INDEX_NONE
-
-		for (i = 1; i < 3; i++) {
-			/* set gradients h/v */
-			memset(&tex, 0, sizeof(struct r600_bytecode_tex));
-			tex.op = (i == 1) ? FETCH_OP_SET_GRADIENTS_H :
-				FETCH_OP_SET_GRADIENTS_V;
-			tex.sampler_id = tgsi_tex_get_src_gpr(ctx, sampler_src_reg);
-			tex.sampler_index_mode = sampler_index_mode;
-			tex.resource_id = tex.sampler_id + R600_MAX_CONST_BUFFERS;
-			tex.resource_index_mode = sampler_index_mode;
-
-			if (tgsi_tex_src_requires_loading(ctx, i)) {
-				tex.src_gpr = r600_get_temp(ctx);
-				tex.src_sel_x = 0;
-				tex.src_sel_y = 1;
-				tex.src_sel_z = 2;
-				tex.src_sel_w = 3;
-
-				for (j = 0; j < 4; j++) {
-					memset(&alu, 0, sizeof(struct r600_bytecode_alu));
-					alu.op = ALU_OP1_MOV;
-                                        r600_bytecode_src(&alu.src[0], &ctx->src[i], j);
-                                        alu.dst.sel = tex.src_gpr;
-                                        alu.dst.chan = j;
-                                        if (j == 3)
-                                                alu.last = 1;
-                                        alu.dst.write = 1;
-                                        r = r600_bytecode_add_alu(ctx->bc, &alu);
-                                        if (r)
-                                                return r;
-				}
-
-			} else {
-				tex.src_gpr = tgsi_tex_get_src_gpr(ctx, i);
-				tex.src_sel_x = ctx->src[i].swizzle[0];
-				tex.src_sel_y = ctx->src[i].swizzle[1];
-				tex.src_sel_z = ctx->src[i].swizzle[2];
-				tex.src_sel_w = ctx->src[i].swizzle[3];
-				tex.src_rel = ctx->src[i].rel;
-			}
-			tex.dst_gpr = ctx->temp_reg; /* just to avoid confusing the asm scheduler */
-			tex.dst_sel_x = tex.dst_sel_y = tex.dst_sel_z = tex.dst_sel_w = 7;
-			if (inst->Texture.Texture != TGSI_TEXTURE_RECT) {
-				tex.coord_type_x = 1;
-				tex.coord_type_y = 1;
-				tex.coord_type_z = 1;
-				tex.coord_type_w = 1;
-			}
-			r = r600_bytecode_add_tex(ctx->bc, &tex);
-			if (r)
-				return r;
-		}
-	} else if (inst->Instruction.Opcode == TGSI_OPCODE_TXP) {
+	if (inst->Instruction.Opcode == TGSI_OPCODE_TXP) {
 		int out_chan;
 		/* Add perspective divide */
 		if (ctx->bc->chip_class == CAYMAN) {
@@ -5230,9 +5182,6 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 		src_gpr = ctx->temp_reg;
 	}
 
-	sampler_index_mode = inst->Src[sampler_src_reg].Indirect.Index == 2 ? 2 : 0; // CF_INDEX_1 : CF_INDEX_NONE
-	if (sampler_index_mode)
-		ctx->shader->uses_index_registers = true;
 
 	if ((inst->Texture.Texture == TGSI_TEXTURE_CUBE ||
 	     inst->Texture.Texture == TGSI_TEXTURE_CUBE_ARRAY ||
@@ -5451,6 +5400,69 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 		src_gpr = ctx->temp_reg;
 	}
 
+	if (inst->Instruction.Opcode == TGSI_OPCODE_TXD) {
+		int temp_h = 0, temp_v = 0;
+		int start_val = 0;
+
+		/* if we've already loaded the src (i.e. CUBE don't reload it). */
+		if (src_loaded == TRUE)
+			start_val = 1;
+		else
+			src_loaded = TRUE;
+		for (i = start_val; i < 3; i++) {
+			int treg = r600_get_temp(ctx);
+
+			if (i == 0)
+				src_gpr = treg;
+			else if (i == 1)
+				temp_h = treg;
+			else
+				temp_v = treg;
+
+			for (j = 0; j < 4; j++) {
+				memset(&alu, 0, sizeof(struct r600_bytecode_alu));
+				alu.op = ALU_OP1_MOV;
+                                r600_bytecode_src(&alu.src[0], &ctx->src[i], j);
+                                alu.dst.sel = treg;
+                                alu.dst.chan = j;
+                                if (j == 3)
+                                   alu.last = 1;
+                                alu.dst.write = 1;
+                                r = r600_bytecode_add_alu(ctx->bc, &alu);
+                                if (r)
+                                    return r;
+			}
+		}
+		for (i = 1; i < 3; i++) {
+			/* set gradients h/v */
+			memset(&tex, 0, sizeof(struct r600_bytecode_tex));
+			tex.op = (i == 1) ? FETCH_OP_SET_GRADIENTS_H :
+				FETCH_OP_SET_GRADIENTS_V;
+			tex.sampler_id = tgsi_tex_get_src_gpr(ctx, sampler_src_reg);
+			tex.sampler_index_mode = sampler_index_mode;
+			tex.resource_id = tex.sampler_id + R600_MAX_CONST_BUFFERS;
+			tex.resource_index_mode = sampler_index_mode;
+
+			tex.src_gpr = (i == 1) ? temp_h : temp_v;
+			tex.src_sel_x = 0;
+			tex.src_sel_y = 1;
+			tex.src_sel_z = 2;
+			tex.src_sel_w = 3;
+
+			tex.dst_gpr = r600_get_temp(ctx); /* just to avoid confusing the asm scheduler */
+			tex.dst_sel_x = tex.dst_sel_y = tex.dst_sel_z = tex.dst_sel_w = 7;
+			if (inst->Texture.Texture != TGSI_TEXTURE_RECT) {
+				tex.coord_type_x = 1;
+				tex.coord_type_y = 1;
+				tex.coord_type_z = 1;
+				tex.coord_type_w = 1;
+			}
+			r = r600_bytecode_add_tex(ctx->bc, &tex);
+			if (r)
+				return r;
+		}
+	}
+
 	if (src_requires_loading && !src_loaded) {
 		for (i = 0; i < 4; i++) {
 			memset(&alu, 0, sizeof(struct r600_bytecode_alu));
@@ -5686,9 +5698,16 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
 		alu.op = ALU_OP1_MOV;
 
-		alu.src[0].sel = 512 + (id / 4);
-		alu.src[0].kc_bank = R600_TXQ_CONST_BUFFER;
-		alu.src[0].chan = id % 4;
+		if (ctx->bc->chip_class >= EVERGREEN) {
+			/* channel 1 or 3 of each word */
+			alu.src[0].sel = 512 + (id / 2);
+			alu.src[0].chan = ((id % 2) * 2) + 1;
+		} else {
+			/* r600 we have them at channel 2 of the second dword */
+			alu.src[0].sel = 512 + (id * 2) + 1;
+			alu.src[0].chan = 2;
+		}
+		alu.src[0].kc_bank = R600_BUFFER_INFO_CONST_BUFFER;
 		tgsi_dst(ctx, &inst->Dst[0], 2, &alu.dst);
 		alu.last = 1;
 		r = r600_bytecode_add_alu(ctx->bc, &alu);

src/gallium/drivers/r600/r600_state_common.c

@@ -649,7 +649,6 @@ static void r600_set_sampler_views(struct pipe_context *pipe, unsigned shader,
 	dst->views.dirty_mask |= new_mask;
 	dst->views.compressed_depthtex_mask &= dst->views.enabled_mask;
 	dst->views.compressed_colortex_mask &= dst->views.enabled_mask;
-	dst->views.dirty_txq_constants = TRUE;
 	dst->views.dirty_buffer_constants = TRUE;
 	r600_sampler_views_dirty(rctx, &dst->views);
 
@@ -984,6 +983,7 @@ static void r600_set_sample_mask(struct pipe_context *pipe, unsigned sample_mask
  * then in the shader, we AND the 4 components with 0xffffffff or 0,
  * then OR the alpha with the value given here.
  * We use a 6th constant to store the txq buffer size in
+ * we use 7th slot for number of cube layers in a cube map array.
  */
 static void r600_setup_buffer_constants(struct r600_context *rctx, int shader_type)
 {
@@ -1022,6 +1022,7 @@ static void r600_setup_buffer_constants(struct r600_context *rctx, int shader_ty
 				samplers->buffer_constants[offset + 4] = 0;
 
 			samplers->buffer_constants[offset + 5] = samplers->views.views[i]->base.texture->width0 / util_format_get_blocksize(samplers->views.views[i]->base.format);
+			samplers->buffer_constants[offset + 6] = samplers->views.views[i]->base.texture->array_size / 6;
 		}
 	}
 
@@ -1033,7 +1034,10 @@ static void r600_setup_buffer_constants(struct r600_context *rctx, int shader_ty
 	pipe_resource_reference(&cb.buffer, NULL);
 }
 
-/* On evergreen we only need to store the buffer size for TXQ */
+/* On evergreen we store two values
+ * 1. buffer size for TXQ
+ * 2. number of cube layers in a cube map array.
+ */
 static void eg_setup_buffer_constants(struct r600_context *rctx, int shader_type)
 {
 	struct r600_textures_info *samplers = &rctx->samplers[shader_type];
@@ -1048,12 +1052,16 @@ static void eg_setup_buffer_constants(struct r600_context *rctx, int shader_type
 	samplers->views.dirty_buffer_constants = FALSE;
 
 	bits = util_last_bit(samplers->views.enabled_mask);
-	array_size = bits * sizeof(uint32_t) * 4;
+	array_size = bits * 2 * sizeof(uint32_t) * 4;
 	samplers->buffer_constants = realloc(samplers->buffer_constants, array_size);
 	memset(samplers->buffer_constants, 0, array_size);
-	for (i = 0; i < bits; i++)
-		if (samplers->views.enabled_mask & (1 << i))
-		   samplers->buffer_constants[i] = samplers->views.views[i]->base.texture->width0 / util_format_get_blocksize(samplers->views.views[i]->base.format);
+	for (i = 0; i < bits; i++) {
+		if (samplers->views.enabled_mask & (1 << i)) {
+			uint32_t offset = i * 2;
+			samplers->buffer_constants[offset] = samplers->views.views[i]->base.texture->width0 / util_format_get_blocksize(samplers->views.views[i]->base.format);
+			samplers->buffer_constants[offset + 1] = samplers->views.views[i]->base.texture->array_size / 6;
+		}
+	}
 
 	cb.buffer = NULL;
 	cb.user_buffer = samplers->buffer_constants;
@@ -1063,35 +1071,6 @@ static void eg_setup_buffer_constants(struct r600_context *rctx, int shader_type
 	pipe_resource_reference(&cb.buffer, NULL);
 }
 
-static void r600_setup_txq_cube_array_constants(struct r600_context *rctx, int shader_type)
-{
-	struct r600_textures_info *samplers = &rctx->samplers[shader_type];
-	int bits;
-	uint32_t array_size;
-	struct pipe_constant_buffer cb;
-	int i;
-
-	if (!samplers->views.dirty_txq_constants)
-		return;
-
-	samplers->views.dirty_txq_constants = FALSE;
-
-	bits = util_last_bit(samplers->views.enabled_mask);
-	array_size = bits * sizeof(uint32_t) * 4;
-	samplers->txq_constants = realloc(samplers->txq_constants, array_size);
-	memset(samplers->txq_constants, 0, array_size);
-	for (i = 0; i < bits; i++)
-		if (samplers->views.enabled_mask & (1 << i))
-			samplers->txq_constants[i] = samplers->views.views[i]->base.texture->array_size / 6;
-
-	cb.buffer = NULL;
-	cb.user_buffer = samplers->txq_constants;
-	cb.buffer_offset = 0;
-	cb.buffer_size = array_size;
-	rctx->b.b.set_constant_buffer(&rctx->b.b, shader_type, R600_TXQ_CONST_BUFFER, &cb);
-	pipe_resource_reference(&cb.buffer, NULL);
-}
-
 /* set sample xy locations as array of fragment shader constants */
 void r600_set_sample_locations_constant_buffer(struct r600_context *rctx)
 {
@@ -1175,7 +1154,7 @@ static bool r600_update_derived_state(struct r600_context *rctx)
 	struct pipe_context * ctx = (struct pipe_context*)rctx;
 	bool ps_dirty = false, vs_dirty = false, gs_dirty = false;
 	bool blend_disable;
-
+	bool need_buf_const;
 	if (!rctx->blitter->running) {
 		unsigned i;
 
@@ -1296,29 +1275,35 @@ static bool r600_update_derived_state(struct r600_context *rctx)
 
 	/* on R600 we stuff masks + txq info into one constant buffer */
 	/* on evergreen we only need a txq info one */
-	if (rctx->b.chip_class < EVERGREEN) {
-		if (rctx->ps_shader && rctx->ps_shader->current->shader.uses_tex_buffers)
-			r600_setup_buffer_constants(rctx, PIPE_SHADER_FRAGMENT);
-		if (rctx->vs_shader && rctx->vs_shader->current->shader.uses_tex_buffers)
-			r600_setup_buffer_constants(rctx, PIPE_SHADER_VERTEX);
-		if (rctx->gs_shader && rctx->gs_shader->current->shader.uses_tex_buffers)
-			r600_setup_buffer_constants(rctx, PIPE_SHADER_GEOMETRY);
-	} else {
-		if (rctx->ps_shader && rctx->ps_shader->current->shader.uses_tex_buffers)
-			eg_setup_buffer_constants(rctx, PIPE_SHADER_FRAGMENT);
-		if (rctx->vs_shader && rctx->vs_shader->current->shader.uses_tex_buffers)
-			eg_setup_buffer_constants(rctx, PIPE_SHADER_VERTEX);
-		if (rctx->gs_shader && rctx->gs_shader->current->shader.uses_tex_buffers)
-			eg_setup_buffer_constants(rctx, PIPE_SHADER_GEOMETRY);
+	if (rctx->ps_shader) {
+		need_buf_const = rctx->ps_shader->current->shader.uses_tex_buffers || rctx->ps_shader->current->shader.has_txq_cube_array_z_comp;
+		if (need_buf_const) {
+			if (rctx->b.chip_class < EVERGREEN)
+				r600_setup_buffer_constants(rctx, PIPE_SHADER_FRAGMENT);
+			else
+				eg_setup_buffer_constants(rctx, PIPE_SHADER_FRAGMENT);
+		}
 	}
 
+	if (rctx->vs_shader) {
+		need_buf_const = rctx->vs_shader->current->shader.uses_tex_buffers || rctx->vs_shader->current->shader.has_txq_cube_array_z_comp;
+		if (need_buf_const) {
+			if (rctx->b.chip_class < EVERGREEN)
+				r600_setup_buffer_constants(rctx, PIPE_SHADER_VERTEX);
+			else
+				eg_setup_buffer_constants(rctx, PIPE_SHADER_VERTEX);
+		}
+	}
 
-	if (rctx->ps_shader && rctx->ps_shader->current->shader.has_txq_cube_array_z_comp)
-		r600_setup_txq_cube_array_constants(rctx, PIPE_SHADER_FRAGMENT);
-	if (rctx->vs_shader && rctx->vs_shader->current->shader.has_txq_cube_array_z_comp)
-		r600_setup_txq_cube_array_constants(rctx, PIPE_SHADER_VERTEX);
-	if (rctx->gs_shader && rctx->gs_shader->current->shader.has_txq_cube_array_z_comp)
-		r600_setup_txq_cube_array_constants(rctx, PIPE_SHADER_GEOMETRY);
+	if (rctx->gs_shader) {
+		need_buf_const = rctx->gs_shader->current->shader.uses_tex_buffers || rctx->gs_shader->current->shader.has_txq_cube_array_z_comp;
+		if (need_buf_const) {
+			if (rctx->b.chip_class < EVERGREEN)
+				r600_setup_buffer_constants(rctx, PIPE_SHADER_GEOMETRY);
+			else
+				eg_setup_buffer_constants(rctx, PIPE_SHADER_GEOMETRY);
+		}
+	}
 
 	if (rctx->b.chip_class < EVERGREEN && rctx->ps_shader && rctx->vs_shader) {
 		if (!r600_adjust_gprs(rctx)) {

src/gallium/state_trackers/wgl/opengl32.def

@@ -367,7 +367,6 @@ EXPORTS
 	wglUseFontBitmapsW
 	wglUseFontOutlinesA
 	wglUseFontOutlinesW
-	wglGetExtensionsStringARB
 	DrvCopyContext
 	DrvCreateContext
 	DrvCreateLayerContext

src/gallium/targets/d3dadapter9/Makefile.am

@@ -62,7 +62,7 @@ d3dadapter9_la_LDFLAGS = \
 	-shrext .so \
 	-module \
 	-no-undefined \
-	-version-number $(NINE_MAJOR):$(NINE_MINOR) \
+	-version-number $(NINE_MAJOR):$(NINE_MINOR):$(NINE_TINY) \
 	$(GC_SECTIONS) \
 	$(LD_NO_UNDEFINED)
 

src/gallium/targets/d3dadapter9/d3d.pc.in

@@ -6,6 +6,6 @@ moduledir=@D3D_DRIVER_INSTALL_DIR@
 
 Name: d3d
 Description: Native D3D driver modules
-Version: @VERSION@
+Version: @NINE_VERSION@
 Requires.private: @DRI_PC_REQ_PRIV@
 Cflags: -I${includedir}

src/glsl/lower_const_arrays_to_uniforms.cpp

@@ -49,6 +49,7 @@ public:
    {
       instructions = insts;
       progress = false;
+      index = 0;
    }
 
    bool run()
@@ -62,6 +63,7 @@ public:
 private:
    exec_list *instructions;
    bool progress;
+   unsigned index;
 };
 
 void
@@ -70,14 +72,20 @@ lower_const_array_visitor::handle_rvalue(ir_rvalue **rvalue)
    if (!*rvalue)
       return;
 
-   ir_constant *con = (*rvalue)->as_constant();
+   ir_dereference_array *dra = (*rvalue)->as_dereference_array();
+   if (!dra)
+      return;
+
+   ir_constant *con = dra->array->as_constant();
    if (!con || !con->type->is_array())
       return;
 
    void *mem_ctx = ralloc_parent(con);
 
+   char *uniform_name = ralloc_asprintf(mem_ctx, "constarray__%d", index++);
+
    ir_variable *uni =
-      new(mem_ctx) ir_variable(con->type, "constarray", ir_var_uniform);
+      new(mem_ctx) ir_variable(con->type, uniform_name, ir_var_uniform);
    uni->constant_initializer = con;
    uni->constant_value = con;
    uni->data.has_initializer = true;
@@ -87,7 +95,8 @@ lower_const_array_visitor::handle_rvalue(ir_rvalue **rvalue)
    uni->data.max_array_access = uni->type->length - 1;
    instructions->push_head(uni);
 
-   *rvalue = new(mem_ctx) ir_dereference_variable(uni);
+   ir_dereference_variable *varref = new(mem_ctx) ir_dereference_variable(uni);
+   *rvalue = new(mem_ctx) ir_dereference_array(varref, dra->array_index);
 
    progress = true;
 }

src/mapi/glapi/SConscript

@@ -16,6 +16,7 @@ if env['platform'] == 'windows':
     env.Append(CPPDEFINES = [
         '_GDI32_', # prevent gl* being declared __declspec(dllimport) in MS headers
         'BUILD_GL32', # declare gl* as __declspec(dllexport) in Mesa headers
+        'KHRONOS_DLL_EXPORTS', # declare gl* as __declspec(dllexport) in Khronos headers
     ])
     if env['gles']:
         env.Append(CPPDEFINES = ['_GLAPI_DLL_EXPORTS'])

src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp

@@ -3354,6 +3354,7 @@ vec4_visitor::move_uniform_array_access_to_pull_constants()
 {
    int pull_constant_loc[this->uniforms];
    memset(pull_constant_loc, -1, sizeof(pull_constant_loc));
+   bool nested_reladdr;
 
    /* Walk through and find array access of uniforms.  Put a copy of that
     * uniform in the pull constant buffer.
@@ -3361,44 +3362,51 @@ vec4_visitor::move_uniform_array_access_to_pull_constants()
     * Note that we don't move constant-indexed accesses to arrays.  No
     * testing has been done of the performance impact of this choice.
     */
-   foreach_block_and_inst_safe(block, vec4_instruction, inst, cfg) {
-      for (int i = 0 ; i < 3; i++) {
-	 if (inst->src[i].file != UNIFORM || !inst->src[i].reladdr)
-	    continue;
+   do {
+      nested_reladdr = false;
 
-	 int uniform = inst->src[i].reg;
+      foreach_block_and_inst_safe(block, vec4_instruction, inst, cfg) {
+         for (int i = 0 ; i < 3; i++) {
+            if (inst->src[i].file != UNIFORM || !inst->src[i].reladdr)
+               continue;
 
-	 /* If this array isn't already present in the pull constant buffer,
-	  * add it.
-	  */
-	 if (pull_constant_loc[uniform] == -1) {
-	    const gl_constant_value **values =
-               &stage_prog_data->param[uniform * 4];
+            int uniform = inst->src[i].reg;
 
-	    pull_constant_loc[uniform] = stage_prog_data->nr_pull_params / 4;
+            if (inst->src[i].reladdr->reladdr)
+               nested_reladdr = true;  /* will need another pass */
 
-	    assert(uniform < uniform_array_size);
-	    for (int j = 0; j < uniform_size[uniform] * 4; j++) {
-	       stage_prog_data->pull_param[stage_prog_data->nr_pull_params++]
-                  = values[j];
-	    }
-	 }
+            /* If this array isn't already present in the pull constant buffer,
+             * add it.
+             */
+            if (pull_constant_loc[uniform] == -1) {
+               const gl_constant_value **values =
+                  &stage_prog_data->param[uniform * 4];
 
-	 /* Set up the annotation tracking for new generated instructions. */
-	 base_ir = inst->ir;
-	 current_annotation = inst->annotation;
+               pull_constant_loc[uniform] = stage_prog_data->nr_pull_params / 4;
 
-	 dst_reg temp = dst_reg(this, glsl_type::vec4_type);
+               assert(uniform < uniform_array_size);
+               for (int j = 0; j < uniform_size[uniform] * 4; j++) {
+                  stage_prog_data->pull_param[stage_prog_data->nr_pull_params++]
+                     = values[j];
+               }
+            }
 
-	 emit_pull_constant_load(block, inst, temp, inst->src[i],
-				 pull_constant_loc[uniform]);
+            /* Set up the annotation tracking for new generated instructions. */
+            base_ir = inst->ir;
+            current_annotation = inst->annotation;
 
-	 inst->src[i].file = temp.file;
-	 inst->src[i].reg = temp.reg;
-	 inst->src[i].reg_offset = temp.reg_offset;
-	 inst->src[i].reladdr = NULL;
+            dst_reg temp = dst_reg(this, glsl_type::vec4_type);
+
+            emit_pull_constant_load(block, inst, temp, inst->src[i],
+                                    pull_constant_loc[uniform]);
+
+            inst->src[i].file = temp.file;
+            inst->src[i].reg = temp.reg;
+            inst->src[i].reg_offset = temp.reg_offset;
+            inst->src[i].reladdr = NULL;
+         }
       }
-   }
+   } while (nested_reladdr);
 
    /* Now there are no accesses of the UNIFORM file with a reladdr, so
     * no need to track them as larger-than-vec4 objects.  This will be

src/mesa/drivers/dri/i965/gen6_sf_state.c

@@ -129,6 +129,20 @@ get_attr_override(const struct brw_vue_map *vue_map, int urb_entry_read_offset,
 }
 
 
+static bool
+is_drawing_points(const struct brw_context *brw)
+{
+   /* Determine if the primitives *reaching the SF* are points */
+   if (brw->geometry_program) {
+      /* BRW_NEW_GEOMETRY_PROGRAM */
+      return brw->geometry_program->OutputType == GL_POINTS;
+   } else {
+      /* BRW_NEW_PRIMITIVE */
+      return brw->primitive == _3DPRIM_POINTLIST;
+   }
+}
+
+
 /**
  * Create the mapping from the FS inputs we produce to the previous pipeline
  * stage (GS or VS) outputs they source from.
@@ -149,6 +163,23 @@ calculate_attr_overrides(const struct brw_context *brw,
    /* _NEW_LIGHT */
    bool shade_model_flat = brw->ctx.Light.ShadeModel == GL_FLAT;
 
+   /* From the Ivybridge PRM, Vol 2 Part 1, 3DSTATE_SBE,
+    * description of dw10 Point Sprite Texture Coordinate Enable:
+    *
+    * "This field must be programmed to zero when non-point primitives
+    * are rendered."
+    *
+    * The SandyBridge PRM doesn't explicitly say that point sprite enables
+    * must be programmed to zero when rendering non-point primitives, but
+    * the IvyBridge PRM does, and if we don't, we get garbage.
+    *
+    * This is not required on Haswell, as the hardware ignores this state
+    * when drawing non-points -- although we do still need to be careful to
+    * correctly set the attr overrides.
+    */
+   /* BRW_NEW_PRIMITIVE | BRW_NEW_GEOMETRY_PROGRAM */
+   bool drawing_points = is_drawing_points(brw);
+
    /* Initialize all the attr_overrides to 0.  In the loop below we'll modify
     * just the ones that correspond to inputs used by the fs.
     */
@@ -167,18 +198,20 @@ calculate_attr_overrides(const struct brw_context *brw,
 
       /* _NEW_POINT */
       bool point_sprite = false;
-      if (brw->ctx.Point.PointSprite &&
-	  (attr >= VARYING_SLOT_TEX0 && attr <= VARYING_SLOT_TEX7) &&
-	  brw->ctx.Point.CoordReplace[attr - VARYING_SLOT_TEX0]) {
-         point_sprite = true;
+      if (drawing_points) {
+         if (brw->ctx.Point.PointSprite &&
+             (attr >= VARYING_SLOT_TEX0 && attr <= VARYING_SLOT_TEX7) &&
+             brw->ctx.Point.CoordReplace[attr - VARYING_SLOT_TEX0]) {
+            point_sprite = true;
+         }
+
+         if (attr == VARYING_SLOT_PNTC)
+            point_sprite = true;
+
+         if (point_sprite)
+            *point_sprite_enables |= (1 << input_index);
       }
 
-      if (attr == VARYING_SLOT_PNTC)
-         point_sprite = true;
-
-      if (point_sprite)
-	 *point_sprite_enables |= (1 << input_index);
-
       /* flat shading */
       if (interp_qualifier == INTERP_QUALIFIER_FLAT ||
           (shade_model_flat && is_gl_Color &&
@@ -410,7 +443,9 @@ const struct brw_tracked_state gen6_sf_state = {
 		_NEW_POINT |
                 _NEW_MULTISAMPLE),
       .brw   = (BRW_NEW_CONTEXT |
-		BRW_NEW_FRAGMENT_PROGRAM |
+                BRW_NEW_FRAGMENT_PROGRAM |
+                BRW_NEW_GEOMETRY_PROGRAM |
+                BRW_NEW_PRIMITIVE |
                 BRW_NEW_VUE_MAP_GEOM_OUT),
       .cache = CACHE_NEW_WM_PROG
    },

src/mesa/drivers/dri/i965/gen7_sf_state.c

@@ -92,7 +92,9 @@ const struct brw_tracked_state gen7_sbe_state = {
 		_NEW_POINT |
 		_NEW_PROGRAM),
       .brw   = (BRW_NEW_CONTEXT |
-		BRW_NEW_FRAGMENT_PROGRAM |
+                BRW_NEW_FRAGMENT_PROGRAM |
+                BRW_NEW_GEOMETRY_PROGRAM |
+                BRW_NEW_PRIMITIVE |
                 BRW_NEW_VUE_MAP_GEOM_OUT),
       .cache = CACHE_NEW_WM_PROG
    },

src/mesa/main/get_hash_params.py

@@ -627,7 +627,7 @@ descriptor=[
 # == GL_CURRENT_MATRIX_NV
   [ "CURRENT_MATRIX_ARB", "LOC_CUSTOM, TYPE_MATRIX, 0, extra_ARB_vertex_program_ARB_fragment_program" ],
 # == GL_CURRENT_MATRIX_NV
-  [ "TRANSPOSE_CURRENT_MATRIX_ARB", "LOC_CUSTOM, TYPE_MATRIX, 0, extra_ARB_vertex_program_ARB_fragment_program" ],
+  [ "TRANSPOSE_CURRENT_MATRIX_ARB", "LOC_CUSTOM, TYPE_MATRIX_T, 0, extra_ARB_vertex_program_ARB_fragment_program" ],
 # == GL_PROGRAM_ERROR_POSITION_NV
   [ "PROGRAM_ERROR_POSITION_ARB", "CONTEXT_INT(Program.ErrorPos), extra_ARB_vertex_program_ARB_fragment_program" ],