docs: Update 11.0.0 release notes

Signed-off-by: Emil Velikov <emil.l.velikov@gmail.com>
Update version to 11.0.0(final)
2015-09-12 13:06:25 +01:00 · 2015-09-12 10:21:51 +01:00 · 2015-09-11 19:47:09 +01:00 · 2015-09-11 19:46:16 +01:00 · 2015-09-11 19:43:42 +01:00 · 2015-09-11 19:19:32 +01:00
45 changed files with 628 additions and 250 deletions
--- a/Android.common.mk
+++ b/Android.common.mk
@@ -42,6 +42,7 @@ LOCAL_CFLAGS += \
 	-DANDROID_VERSION=0x0$(MESA_ANDROID_MAJOR_VERSION)0$(MESA_ANDROID_MINOR_VERSION)

 LOCAL_CFLAGS += \
+	-D__STDC_LIMIT_MACROS \
 	-DHAVE___BUILTIN_EXPECT \
 	-DHAVE___BUILTIN_FFS \
 	-DHAVE___BUILTIN_FFSLL \
@@ -70,7 +71,7 @@ endif

 ifeq ($(MESA_ENABLE_LLVM),true)
 LOCAL_CFLAGS += \
-	-DHAVE_LLVM=0x0305 -DLLVM_VERSION_PATCH=2 \
+	-DHAVE_LLVM=0x0305 -DMESA_LLVM_VERSION_PATCH=2 \
 	-D__STDC_CONSTANT_MACROS \
 	-D__STDC_FORMAT_MACROS \
 	-D__STDC_LIMIT_MACROS
--- a/2
+++ b/2
@@ -1 +1 @@
-11.0.0-rc3
+11.0.0
--- a/docs/relnotes/11.0.0.html
+++ b/docs/relnotes/11.0.0.html
@@ -14,7 +14,7 @@
 <iframe src="../contents.html"></iframe>
 <div class="content">

-<h1>Mesa 11.0.0 Release Notes / TBD</h1>
+<h1>Mesa 11.0.0 Release Notes / September 12, 2015</h1>

 <p>
 Mesa 11.0.0 is a new development release.
@@ -83,13 +83,175 @@ Note: some of the new features are only available with certain drivers.
 <li>EGL 1.5 on r600, radeonsi, nv50, nvc0</li>
 </ul>

+
 <h2>Bug fixes</h2>

-TBD.
+<p>This list is likely incomplete.</p>
+
+<ul>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=51658">Bug 51658</a> - r200 (&amp; possibly radeon) DRI fixes for gnome shell on Mesa 8.0.3</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=65525">Bug 65525</a> - [llvmpipe] lp_scene.h:210:lp_scene_alloc: Assertion `size &lt;= (64 * 1024)' failed.</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=66346">Bug 66346</a> - shader_query.cpp:49: error: invalid conversion from 'void*' to 'GLuint'</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=73512">Bug 73512</a> - [clover] mesa.icd. should contain full path</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=73528">Bug 73528</a> - Deferred lighting in Second Life causes system hiccups and screen flickering</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=74329">Bug 74329</a> - Please expose OES_texture_float and OES_texture_half_float on the ES3 context</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=80500">Bug 80500</a> - Flickering shadows in unreleased title trace</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=82186">Bug 82186</a> - [r600g] BARTS GPU lockup with minecraft shaders</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=84225">Bug 84225</a> - Allow constant-index-expression sampler array indexing with GLSL-ES &lt; 300</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=84677">Bug 84677</a> - Triangle disappears with glPolygonMode GL_LINE</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=85252">Bug 85252</a> - Segfault in compiler while processing ternary operator with void arguments</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=89131">Bug 89131</a> - [Bisected] Graphical corruption in Weston,  shows old framebuffer pieces</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90000">Bug 90000</a> - [i965 Bisected NIR] Piglit/gglean_fragprog1-z-write_test fail</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90073">Bug 90073</a> - Leaks in xcb_dri3_open_reply_fds() and get_render_node_from_id_path_tag</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90249">Bug 90249</a> - Fails to build egl_dri2 on osx</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90310">Bug 90310</a> - Fails to build gallium_dri.so at linking stage with clang because of multiple redefinitions</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90347">Bug 90347</a> - [NVE0+] Failure to insert texbar under some circumstances (causing bad colors in Terasology)</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90466">Bug 90466</a> - arm: linker error ndefined reference to `nir_metadata_preserve'</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90520">Bug 90520</a> - Register spilling clobbers registers used elsewhere in the shader</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90537">Bug 90537</a> - radeonsi bo/va conflict on RADEON_GEM_VA (rscreen-&gt;ws-&gt;buffer_from_handle returns NULL)</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90547">Bug 90547</a> - [BDW/BSW/SKL Bisected]Piglit/glean&#64;vertprog1-rsq_test_2_(reciprocal_square_root_of_negative_value) fais</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90580">Bug 90580</a> - [HSW bisected] integer multiplication bug</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90600">Bug 90600</a> - IOError: [Errno 2] No such file or directory: 'gl_API.xml'</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90621">Bug 90621</a> - Mesa fail to build from git</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90629">Bug 90629</a> - [i965] SIMD16 dual_source_blend assertion `src[i].file != GRF || src[i].width == dst.width' failed</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90691">Bug 90691</a> - [BSW]Piglit/spec/nv_conditional_render/dlist fails intermittently</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90728">Bug 90728</a> - dvd playback with vlc and vdpau causes segmentation fault</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90734">Bug 90734</a> - glBufferSubData is corrupting data when buffer is &gt; 32k</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90748">Bug 90748</a> - [BDW Bisected]dEQP-GLES3.functional.fbo.completeness.renderable.texture.depth.rg_half_float_oes fails</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90749">Bug 90749</a> - [BDW Bisected]dEQP-GLES3.functional.rasterization.fbo.rbo_multisample_max.primitives.lines_wide fails</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90751">Bug 90751</a> - [BDW Bisected]dEQP-GLES3.functional.fbo.completeness.renderable.texture.stencil.stencil_index8 fails</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90797">Bug 90797</a> - [ALL bisected] Mesa change cause performance case manhattan fail.</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90817">Bug 90817</a> - swrast fails to load with certain remote X servers</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90830">Bug 90830</a> - [bsw bisected regression] GPU hang for spec.arb_gpu_shader5.execution.sampler_array_indexing.vs-nonzero-base</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90839">Bug 90839</a> - [10.5.5/10.6 regression, bisected] PBO glDrawPixels no longer using blit fastpath</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90873">Bug 90873</a> - Kernel hang, TearFree On, Mate desktop environment</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90887">Bug 90887</a> - PhiMovesPass in register allocator broken</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90895">Bug 90895</a> - [IVB/HSW/BDW/BSW Bisected] GLB2.7 Egypt, GfxBench3.0 T-Rex &amp; ALU and many SynMark cases performance reduced by 10-23%</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90902">Bug 90902</a> - [bsw][regression] dEQP: &quot;Found invalid pixel values&quot;</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90903">Bug 90903</a> - egl_dri2.c:dri2_load fails to load libglapi on osx</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90904">Bug 90904</a> - OSX: EXC_BAD_ACCESS when using translate_sse + gallium + softpipe/llvmpipe</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90905">Bug 90905</a> - mesa: Finish subdir-objects transition</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=90925">Bug 90925</a> - &quot;high fidelity&quot;: Segfault in _mesa_program_resource_find_name</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91022">Bug 91022</a> - [g45 g965 bisected] assertions generated from textureGrad cube samplers fix</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91047">Bug 91047</a> - [SNB Bisected] Messed up Fog in Super Smash Bros. Melee in Dolphin</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91056">Bug 91056</a> - The Bard's Tale (2005, native)  has rendering issues</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91077">Bug 91077</a> - dri2_glx.c:1186: undefined reference to `loader_open_device'</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91099">Bug 91099</a> - [llvmpipe] piglit glsl-max-varyings &gt;max_varying_components regression</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91101">Bug 91101</a> - [softpipe] piglit glsl-1.50&#64;execution&#64;geometry&#64;max-input-components regression</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91117">Bug 91117</a> - Nimbus (running in wine) has rendering issues, objects are semi-transparent</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91124">Bug 91124</a> - Civilization V (in Wine) has rendering issues: text missing, menu bar corrupted</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91173">Bug 91173</a> - Oddworld: Stranger's Wrath HD: disfigured models in wrong colors</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91193">Bug 91193</a> - [290x] Dota2 reborn ingame rendering breaks with git-af4b9c7</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91222">Bug 91222</a> - lp_test_format regression on CentOS 7</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91226">Bug 91226</a> - Crash in glLinkProgram (NEW)</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91231">Bug 91231</a> - [NV92] Psychonauts (native) segfaults on start when DRI3 enabled</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91254">Bug 91254</a> - (regresion) video using VA-API on Intel slow and freeze system with mesa 10.6 or 10.6.1</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91290">Bug 91290</a> - SIGSEGV glcpp/glcpp-parse.y:1077</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91292">Bug 91292</a> - [BDW+] glVertexAttribDivisor not working in combination with glPolygonMode</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91337">Bug 91337</a> - OSMesaGetProcAdress(&quot;OSMesaPixelStore&quot;) returns nil</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91418">Bug 91418</a> - Visual Studio 2015 vsnprintf build error</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91425">Bug 91425</a> - [regression, bisected] Piglit spec/ext_packed_float/ getteximage-invalid-format-for-packed-type fails</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91441">Bug 91441</a> - make check DispatchSanity_test.GL30 regression</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91444">Bug 91444</a> - regression bisected radeonsi: don't change pipe_resource in resource_copy_region</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91461">Bug 91461</a> - gl_TessLevel* writes have no effect for all but the last TCS invocation</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91513">Bug 91513</a> - [IVB/HSW/BDW/SKL Bisected] Lightsmark performance reduced by 7%-10%</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91526">Bug 91526</a> - World of Warcraft (on Wine) has UI corruption with nouveau</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91544">Bug 91544</a> - [i965, regression, bisected] regression of several tests in 93977d3a151675946c03e</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91551">Bug 91551</a> - DXTn compressed normal maps produce severe artifacts on all NV5x and NVDx chipsets</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91570">Bug 91570</a> - Upgrading mesa to 10.6 causes segfault in OpenGL applications with GeForce4 MX 440 / AGP 8X</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91591">Bug 91591</a> - rounding.h:102:2: error: #error &quot;Unsupported or undefined LONG_BIT&quot;</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91610">Bug 91610</a> - [BSW] GPU hang for spec.shaders.point-vertex-id gl_instanceid divisor</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91673">Bug 91673</a> - Segfault when calling glTexSubImage2D on storage texture to bound FBO</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91726">Bug 91726</a> - R600 asserts in tgsi_cmp/make_src_for_op3</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91847">Bug 91847</a> - glGenerateTextureMipmap not working (no errors) unless glActiveTexture(GL_TEXTURE1) is called before</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91857">Bug 91857</a> - Mesa 10.6.3 linker is slow</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91881">Bug 91881</a> - regression: GPU lockups since mesa-11.0.0_rc1 on RV620 (r600) driver</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91890">Bug 91890</a> - [nve7] witcher2: blurry image &amp; DATA_ERRORs (class 0xa097 mthd 0x2380/0x238c)</li>
+
+</ul>
+

 <h2>Changes</h2>

-TBD.
+<li>Removed the EGL loader from the Linux SCons build.</li>

 </div>
 </body>
--- a/src/gallium/auxiliary/Makefile.am
+++ b/src/gallium/auxiliary/Makefile.am
@@ -38,18 +38,23 @@ libgallium_la_SOURCES += \

 endif

-indices/u_indices_gen.c: $(srcdir)/indices/u_indices_gen.py
-	$(AM_V_at)$(MKDIR_P) indices
-	$(AM_V_GEN) $(PYTHON2) $< > $@
+MKDIR_GEN = $(AM_V_at)$(MKDIR_P) $(@D)
+PYTHON_GEN =  $(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS)

-indices/u_unfilled_gen.c: $(srcdir)/indices/u_unfilled_gen.py
-	$(AM_V_at)$(MKDIR_P) indices
-	$(AM_V_GEN) $(PYTHON2) $< > $@
+indices/u_indices_gen.c: indices/u_indices_gen.py
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/indices/u_indices_gen.py > $@

-util/u_format_table.c: $(srcdir)/util/u_format_table.py $(srcdir)/util/u_format_pack.py $(srcdir)/util/u_format_parse.py $(srcdir)/util/u_format.csv
-	$(AM_V_at)$(MKDIR_P) util
-	$(AM_V_GEN) $(PYTHON2) $(srcdir)/util/u_format_table.py $(srcdir)/util/u_format.csv > $@
+indices/u_unfilled_gen.c: indices/u_unfilled_gen.py
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/indices/u_unfilled_gen.py > $@

+util/u_format_table.c: util/u_format_table.py \
+                       util/u_format_pack.py \
+                       util/u_format_parse.py \
+                       util/u_format.csv
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/util/u_format_table.py $(srcdir)/util/u_format.csv > $@

 noinst_LTLIBRARIES += libgalliumvl_stub.la
 libgalliumvl_stub_la_SOURCES = \
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp
@@ -884,7 +884,7 @@ CodeEmitterNV50::emitINTERP(const Instruction *i)
   defId(i->def(0), 2);
   srcAddr8(i->src(0), 16);

-   if (i->getInterpMode() == NV50_IR_INTERP_FLAT) {
+   if (i->encSize != 8 && i->getInterpMode() == NV50_IR_INTERP_FLAT) {
      code[0] |= 1 << 8;
   } else {
      if (i->op == OP_PINTERP) {
@@ -896,10 +896,11 @@ CodeEmitterNV50::emitINTERP(const Instruction *i)
   }

   if (i->encSize == 8) {
-      code[1] =
-         (code[0] & (3 << 24)) >> (24 - 16) |
-         (code[0] & (1 <<  8)) << (18 -  8);
-      code[0] &= ~0x03000100;
+      if (i->getInterpMode() == NV50_IR_INTERP_FLAT)
+         code[1] = 4 << 16;
+      else
+         code[1] = (code[0] & (3 << 24)) >> (24 - 16);
+      code[0] &= ~0x03000000;
      code[0] |= 1;
      emitFlagsRd(i);
   }
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
@@ -202,7 +202,10 @@ NV50LegalizePostRA::visit(Function *fn)
   Program *prog = fn->getProgram();

   r63 = new_LValue(fn, FILE_GPR);
-   r63->reg.data.id = 63;
+   if (prog->maxGPR < 63)
+      r63->reg.data.id = 63;
+   else
+      r63->reg.data.id = 127;

   // this is actually per-program, but we can do it all on visiting main()
   std::list<Instruction *> *outWrites =
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -2602,6 +2602,10 @@ NV50PostRaConstantFolding::visit(BasicBlock *bb)
             !isFloatType(i->dType))
            break;

+         if (i->getDef(0)->reg.data.id >= 64 ||
+             i->getSrc(0)->reg.data.id >= 64)
+            break;
+
         def = i->getSrc(1)->getInsn();
         if (def->op == OP_MOV && def->src(0).getFile() == FILE_IMMEDIATE) {
            vtmp = i->getSrc(1);
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp
@@ -411,7 +411,7 @@ int ImmediateValue::print(char *buf, size_t size, DataType ty) const
   case TYPE_U64:
   case TYPE_S64:
   default:
-      PRINT("0x%016"PRIx64, reg.data.u64);
+      PRINT("0x%016" PRIx64, reg.data.u64);
      break;
   }
   return pos;
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
@@ -25,6 +25,7 @@

 #include <stack>
 #include <limits>
+#include <tr1/unordered_map>

 namespace nv50_ir {

@@ -222,6 +223,7 @@ private:
   private:
      virtual bool visit(BasicBlock *);
      inline bool needNewElseBlock(BasicBlock *b, BasicBlock *p);
+      inline void splitEdges(BasicBlock *b);
   };

   class ArgumentMovesPass : public Pass {
@@ -345,28 +347,55 @@ RegAlloc::PhiMovesPass::needNewElseBlock(BasicBlock *b, BasicBlock *p)
   return (n == 2);
 }

-// For each operand of each PHI in b, generate a new value by inserting a MOV
-// at the end of the block it is coming from and replace the operand with its
-// result. This eliminates liveness conflicts and enables us to let values be
-// copied to the right register if such a conflict exists nonetheless.
+struct PhiMapHash {
+   size_t operator()(const std::pair<Instruction *, BasicBlock *>& val) const {
+      return std::tr1::hash<Instruction*>()(val.first) * 31 +
+         std::tr1::hash<BasicBlock*>()(val.second);
+   }
+};
+
+typedef std::tr1::unordered_map<
+   std::pair<Instruction *, BasicBlock *>, Value *, PhiMapHash> PhiMap;
+
+// Critical edges need to be split up so that work can be inserted along
+// specific edge transitions. Unfortunately manipulating incident edges into a
+// BB invalidates all the PHI nodes since their sources are implicitly ordered
+// by incident edge order.
 //
-// These MOVs are also crucial in making sure the live intervals of phi srces
-// are extended until the end of the loop, since they are not included in the
-// live-in sets.
-bool
-RegAlloc::PhiMovesPass::visit(BasicBlock *bb)
+// TODO: Make it so that that is not the case, and PHI nodes store pointers to
+// the original BBs.
+void
+RegAlloc::PhiMovesPass::splitEdges(BasicBlock *bb)
 {
-   Instruction *phi, *mov;
   BasicBlock *pb, *pn;
-
+   Instruction *phi;
+   Graph::EdgeIterator ei;
   std::stack<BasicBlock *> stack;
+   int j = 0;

-   for (Graph::EdgeIterator ei = bb->cfg.incident(); !ei.end(); ei.next()) {
+   for (ei = bb->cfg.incident(); !ei.end(); ei.next()) {
      pb = BasicBlock::get(ei.getNode());
      assert(pb);
      if (needNewElseBlock(bb, pb))
         stack.push(pb);
   }
+
+   // No critical edges were found, no need to perform any work.
+   if (stack.empty())
+      return;
+
+   // We're about to, potentially, reorder the inbound edges. This means that
+   // we need to hold on to the (phi, bb) -> src mapping, and fix up the phi
+   // nodes after the graph has been modified.
+   PhiMap phis;
+
+   j = 0;
+   for (ei = bb->cfg.incident(); !ei.end(); ei.next(), j++) {
+      pb = BasicBlock::get(ei.getNode());
+      for (phi = bb->getPhi(); phi && phi->op == OP_PHI; phi = phi->next)
+         phis.insert(std::make_pair(std::make_pair(phi, pb), phi->getSrc(j)));
+   }
+
   while (!stack.empty()) {
      pb = stack.top();
      pn = new BasicBlock(func);
@@ -379,12 +408,47 @@ RegAlloc::PhiMovesPass::visit(BasicBlock *bb)
      assert(pb->getExit()->op != OP_CALL);
      if (pb->getExit()->asFlow()->target.bb == bb)
         pb->getExit()->asFlow()->target.bb = pn;
+
+      for (phi = bb->getPhi(); phi && phi->op == OP_PHI; phi = phi->next) {
+         PhiMap::iterator it = phis.find(std::make_pair(phi, pb));
+         assert(it != phis.end());
+         phis.insert(std::make_pair(std::make_pair(phi, pn), it->second));
+         phis.erase(it);
+      }
   }

+   // Now go through and fix up all of the phi node sources.
+   j = 0;
+   for (ei = bb->cfg.incident(); !ei.end(); ei.next(), j++) {
+      pb = BasicBlock::get(ei.getNode());
+      for (phi = bb->getPhi(); phi && phi->op == OP_PHI; phi = phi->next) {
+         PhiMap::const_iterator it = phis.find(std::make_pair(phi, pb));
+         assert(it != phis.end());
+
+         phi->setSrc(j, it->second);
+      }
+   }
+}
+
+// For each operand of each PHI in b, generate a new value by inserting a MOV
+// at the end of the block it is coming from and replace the operand with its
+// result. This eliminates liveness conflicts and enables us to let values be
+// copied to the right register if such a conflict exists nonetheless.
+//
+// These MOVs are also crucial in making sure the live intervals of phi srces
+// are extended until the end of the loop, since they are not included in the
+// live-in sets.
+bool
+RegAlloc::PhiMovesPass::visit(BasicBlock *bb)
+{
+   Instruction *phi, *mov;
+
+   splitEdges(bb);
+
   // insert MOVs (phi->src(j) should stem from j-th in-BB)
   int j = 0;
   for (Graph::EdgeIterator ei = bb->cfg.incident(); !ei.end(); ei.next()) {
-      pb = BasicBlock::get(ei.getNode());
+      BasicBlock *pb = BasicBlock::get(ei.getNode());
      if (!pb->isTerminated())
         pb->insertTail(new_FlowInstruction(func, OP_BRA, bb));

--- a/src/gallium/drivers/nouveau/nouveau_buffer.c
+++ b/src/gallium/drivers/nouveau/nouveau_buffer.c
@@ -206,8 +206,8 @@ nouveau_transfer_write(struct nouveau_context *nv, struct nouveau_transfer *tx,
      nv->copy_data(nv, buf->bo, buf->offset + base, buf->domain,
                    tx->bo, tx->offset + offset, NOUVEAU_BO_GART, size);
   else
-   if ((buf->base.bind & PIPE_BIND_CONSTANT_BUFFER) && nv->push_cb && can_cb)
-      nv->push_cb(nv, buf->bo, buf->domain, buf->offset, buf->base.width0,
+   if (nv->push_cb && can_cb)
+      nv->push_cb(nv, buf,
                  base, size / 4, (const uint32_t *)data);
   else
      nv->push_data(nv, buf->bo, buf->offset + base, buf->domain, size, data);
--- a/src/gallium/drivers/nouveau/nouveau_buffer.h
+++ b/src/gallium/drivers/nouveau/nouveau_buffer.h
@@ -41,6 +41,8 @@ struct nv04_resource {
   uint8_t status;
   uint8_t domain;

+   uint16_t cb_bindings[6]; /* per-shader per-slot bindings */
+
   struct nouveau_fence *fence;
   struct nouveau_fence *fence_wr;

--- a/src/gallium/drivers/nouveau/nouveau_context.h
+++ b/src/gallium/drivers/nouveau/nouveau_context.h
@@ -6,6 +6,8 @@

 #define NOUVEAU_MAX_SCRATCH_BUFS 4

+struct nv04_resource;
+
 struct nouveau_context {
   struct pipe_context pipe;
   struct nouveau_screen *screen;
@@ -23,8 +25,7 @@ struct nouveau_context {
                     unsigned, const void *);
   /* base, size refer to the whole constant buffer */
   void (*push_cb)(struct nouveau_context *,
-                   struct nouveau_bo *, unsigned domain,
-                   unsigned base, unsigned size,
+                   struct nv04_resource *,
                   unsigned offset, unsigned words, const uint32_t *);

   /* @return: @ref reduced by nr of references found in context */
--- a/src/gallium/drivers/nouveau/nv30/nv30_miptree.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_miptree.c
@@ -149,14 +149,50 @@ static void
 nv30_resource_resolve(struct nv30_context *nv30,
                      const struct pipe_blit_info *info)
 {
+   struct nv30_miptree *src_mt = nv30_miptree(info->src.resource);
   struct nv30_rect src, dst;
+   unsigned x, x0, x1, y, y1, w, h;

   define_rect(info->src.resource, 0, info->src.box.z, info->src.box.x,
      info->src.box.y, info->src.box.width, info->src.box.height, &src);
   define_rect(info->dst.resource, 0, info->dst.box.z, info->dst.box.x,
      info->dst.box.y, info->dst.box.width, info->dst.box.height, &dst);

-   nv30_transfer_rect(nv30, BILINEAR, &src, &dst);
+   x0 = src.x0;
+   x1 = src.x1;
+   y1 = src.y1;
+
+   /* On nv3x we must use sifm which is restricted to 1024x1024 tiles */
+   for (y = src.y0; y < y1; y += h) {
+      h = y1 - y;
+      if (h > 1024)
+         h = 1024;
+
+      src.y0 = 0;
+      src.y1 = h;
+      src.h = h;
+
+      dst.y1 = dst.y0 + (h >> src_mt->ms_y);
+      dst.h = h >> src_mt->ms_y;
+
+      for (x = x0; x < x1; x += w) {
+         w = x1 - x;
+         if (w > 1024)
+            w = 1024;
+
+         src.offset = y * src.pitch + x * src.cpp;
+         src.x0 = 0;
+         src.x1 = w;
+         src.w = w;
+
+         dst.offset = (y >> src_mt->ms_y) * dst.pitch +
+                      (x >> src_mt->ms_x) * dst.cpp;
+         dst.x1 = dst.x0 + (w >> src_mt->ms_x);
+         dst.w = w >> src_mt->ms_x;
+
+         nv30_transfer_rect(nv30, BILINEAR, &src, &dst);
+      }
+   }
 }

 void
--- a/src/gallium/drivers/nouveau/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
@@ -319,8 +319,9 @@ nv30_screen_is_format_supported(struct pipe_screen *pscreen,
                                unsigned sample_count,
                                unsigned bindings)
 {
-   if (sample_count > 4)
+   if (sample_count > nv30_screen(pscreen)->max_sample_count)
      return false;
+
   if (!(0x00000017 & (1 << sample_count)))
      return false;

@@ -450,6 +451,23 @@ nv30_screen_create(struct nouveau_device *dev)
      return NULL;
   }

+   /*
+    * Some modern apps try to use msaa without keeping in mind the
+    * restrictions on videomem of older cards. Resulting in dmesg saying:
+    * [ 1197.850642] nouveau E[soffice.bin[3785]] fail ttm_validate
+    * [ 1197.850648] nouveau E[soffice.bin[3785]] validating bo list
+    * [ 1197.850654] nouveau E[soffice.bin[3785]] validate: -12
+    *
+    * Because we are running out of video memory, after which the program
+    * using the msaa visual freezes, and eventually the entire system freezes.
+    *
+    * To work around this we do not allow msaa visauls by default and allow
+    * the user to override this via NV30_MAX_MSAA.
+    */
+   screen->max_sample_count = debug_get_num_option("NV30_MAX_MSAA", 0);
+   if (screen->max_sample_count > 4)
+      screen->max_sample_count = 4;
+
   pscreen = &screen->base.base;
   pscreen->destroy = nv30_screen_destroy;
   pscreen->get_param = nv30_screen_get_param;
--- a/src/gallium/drivers/nouveau/nv30/nv30_screen.h
+++ b/src/gallium/drivers/nouveau/nv30/nv30_screen.h
@@ -38,6 +38,8 @@ struct nv30_screen {
   /*XXX: nvfx state */
   struct nouveau_heap *vp_exec_heap;
   struct nouveau_heap *vp_data_heap;
+
+   unsigned max_sample_count;
 };

 static inline struct nv30_screen *
--- a/src/gallium/drivers/nouveau/nv30/nv30_transfer.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_transfer.c
@@ -371,7 +371,7 @@ nv30_transfer_rect_blit(XFER_ARGS)
 static bool
 nv30_transfer_sifm(XFER_ARGS)
 {
-   if (!src->pitch || (src->w | src->h) > 1024 || src->w < 2 || src->h < 2)
+   if (!src->pitch || src->w > 1024 || src->h > 1024 || src->w < 2 || src->h < 2)
      return false;

   if (src->d > 1 || dst->d > 1)
@@ -381,7 +381,7 @@ nv30_transfer_sifm(XFER_ARGS)
      return false;

   if (!dst->pitch) {
-      if ((dst->w | dst->h) > 2048 || dst->w < 2 || dst->h < 2)
+      if (dst->w > 2048 || dst->h > 2048 || dst->w < 2 || dst->h < 2)
         return false;
   } else {
      if (dst->domain != NOUVEAU_BO_VRAM)
--- a/src/gallium/drivers/nouveau/nv50/nv50_formats.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_formats.c
@@ -203,8 +203,10 @@ const struct nv50_format nv50_format_table[PIPE_FORMAT_COUNT] =
   F3B(B5G6R5_UNORM, B5G6R5_UNORM, C2, C1, C0, xx, UNORM, 5_6_5, TD),
   C4B(B5G5R5A1_UNORM, BGR5_A1_UNORM, C2, C1, C0, C3, UNORM, 5_5_5_1, TD),
   F3B(B5G5R5X1_UNORM, BGR5_X1_UNORM, C2, C1, C0, xx, UNORM, 5_5_5_1, TD),
+#if NOUVEAU_DRIVER != 0xc0
   C4B(B4G4R4A4_UNORM, NONE, C2, C1, C0, C3, UNORM, 4_4_4_4, T),
   F3B(B4G4R4X4_UNORM, NONE, C2, C1, C0, xx, UNORM, 4_4_4_4, T),
+#endif
   F3B(R9G9B9E5_FLOAT, NONE, C0, C1, C2, xx, FLOAT, 9_9_9_E5, T),

   C4A(R10G10B10A2_UNORM, RGB10_A2_UNORM, C0, C1, C2, C3, UNORM, 10_10_10_2,
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_context.h
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_context.h
@@ -299,10 +299,10 @@ nve4_p2mf_push_linear(struct nouveau_context *nv,
                      struct nouveau_bo *dst, unsigned offset, unsigned domain,
                      unsigned size, const void *data);
 void
-nvc0_cb_push(struct nouveau_context *,
-             struct nouveau_bo *bo, unsigned domain,
-             unsigned base, unsigned size,
-             unsigned offset, unsigned words, const uint32_t *data);
+nvc0_cb_bo_push(struct nouveau_context *,
+                struct nouveau_bo *bo, unsigned domain,
+                unsigned base, unsigned size,
+                unsigned offset, unsigned words, const uint32_t *data);

 /* nvc0_vbo.c */
 void nvc0_draw_vbo(struct pipe_context *, const struct pipe_draw_info *);
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
@@ -449,7 +449,7 @@ nvc0_fp_gen_header(struct nvc0_program *fp, struct nv50_ir_prog_info *info)

   for (i = 0; i < info->numOutputs; ++i) {
      if (info->out[i].sn == TGSI_SEMANTIC_COLOR)
-         fp->hdr[18] |= info->out[i].mask << info->out[i].slot[0];
+         fp->hdr[18] |= 0xf << info->out[i].slot[0];
   }

   fp->fp.early_z = info->prop.fp.earlyFragTests;
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_state.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_state.c
@@ -831,6 +831,8 @@ nvc0_set_constant_buffer(struct pipe_context *pipe, uint shader, uint index,
   }
   nvc0->constbuf_dirty[s] |= 1 << i;

+   if (nvc0->constbuf[s][i].u.buf)
+      nv04_resource(nvc0->constbuf[s][i].u.buf)->cb_bindings[s] &= ~(1 << i);
   pipe_resource_reference(&nvc0->constbuf[s][i].u.buf, res);

   nvc0->constbuf[s][i].user = (cb && cb->user_buffer) ? true : false;
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
@@ -440,7 +440,7 @@ nvc0_constbufs_validate(struct nvc0_context *nvc0)
               BEGIN_NVC0(push, NVC0_3D(CB_BIND(s)), 1);
               PUSH_DATA (push, (0 << 4) | 1);
            }
-            nvc0_cb_push(&nvc0->base, bo, NV_VRAM_DOMAIN(&nvc0->screen->base),
+            nvc0_cb_bo_push(&nvc0->base, bo, NV_VRAM_DOMAIN(&nvc0->screen->base),
                         base, nvc0->state.uniform_buffer_bound[s],
                         0, (size + 3) / 4,
                         nvc0->constbuf[s][0].u.data);
@@ -458,6 +458,7 @@ nvc0_constbufs_validate(struct nvc0_context *nvc0)
               BCTX_REFN(nvc0->bufctx_3d, CB(s, i), res, RD);

               nvc0->cb_dirty = 1; /* Force cache flush for UBO. */
+               res->cb_bindings[s] |= 1 << i;
            } else {
               BEGIN_NVC0(push, NVC0_3D(CB_BIND(s)), 1);
               PUSH_DATA (push, (i << 4) | 0);
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_transfer.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_transfer.c
@@ -506,11 +506,48 @@ nvc0_miptree_transfer_unmap(struct pipe_context *pctx,
 }

 /* This happens rather often with DTD9/st. */
-void
+static void
 nvc0_cb_push(struct nouveau_context *nv,
-             struct nouveau_bo *bo, unsigned domain,
-             unsigned base, unsigned size,
+             struct nv04_resource *res,
             unsigned offset, unsigned words, const uint32_t *data)
+{
+   struct nvc0_context *nvc0 = nvc0_context(&nv->pipe);
+   struct nvc0_constbuf *cb = NULL;
+   int s;
+
+   /* Go through all the constbuf binding points of this buffer and try to
+    * find one which contains the region to be updated.
+    */
+   for (s = 0; s < 6 && !cb; s++) {
+      uint16_t bindings = res->cb_bindings[s];
+      while (bindings) {
+         int i = ffs(bindings) - 1;
+         uint32_t cb_offset = nvc0->constbuf[s][i].offset;
+
+         bindings &= ~(1 << i);
+         if (cb_offset <= offset &&
+             cb_offset + nvc0->constbuf[s][i].size >= offset + words * 4) {
+            cb = &nvc0->constbuf[s][i];
+            break;
+         }
+      }
+   }
+
+   if (cb) {
+      nvc0_cb_bo_push(nv, res->bo, res->domain,
+                      res->offset + cb->offset, cb->size,
+                      offset - cb->offset, words, data);
+   } else {
+      nv->push_data(nv, res->bo, res->offset + offset, res->domain,
+                    words * 4, data);
+   }
+}
+
+void
+nvc0_cb_bo_push(struct nouveau_context *nv,
+                struct nouveau_bo *bo, unsigned domain,
+                unsigned base, unsigned size,
+                unsigned offset, unsigned words, const uint32_t *data)
 {
   struct nouveau_pushbuf *push = nv->pushbuf;

@@ -520,6 +557,9 @@ nvc0_cb_push(struct nouveau_context *nv,
   assert(!(offset & 3));
   size = align(size, 0x100);

+   assert(offset < size);
+   assert(offset + words * 4 <= size);
+
   BEGIN_NVC0(push, NVC0_3D(CB_SIZE), 3);
   PUSH_DATA (push, size);
   PUSH_DATAh(push, bo->offset + base);
--- a/src/gallium/drivers/r600/evergreen_state.c
+++ b/src/gallium/drivers/r600/evergreen_state.c
@@ -1853,7 +1853,7 @@ static void evergreen_emit_vertex_buffers(struct r600_context *rctx,
 		radeon_emit(cs, PKT3(PKT3_SET_RESOURCE, 8, 0) | pkt_flags);
 		radeon_emit(cs, (resource_offset + buffer_index) * 8);
 		radeon_emit(cs, va); /* RESOURCEi_WORD0 */
-		radeon_emit(cs, rbuffer->buf->size - vb->buffer_offset - 1); /* RESOURCEi_WORD1 */
+		radeon_emit(cs, rbuffer->b.b.width0 - vb->buffer_offset - 1); /* RESOURCEi_WORD1 */
 		radeon_emit(cs, /* RESOURCEi_WORD2 */
 				 S_030008_ENDIAN_SWAP(r600_endian_swap(32)) |
 				 S_030008_STRIDE(vb->stride) |
@@ -1923,7 +1923,7 @@ static void evergreen_emit_constant_buffers(struct r600_context *rctx,
 		radeon_emit(cs, PKT3(PKT3_SET_RESOURCE, 8, 0) | pkt_flags);
 		radeon_emit(cs, (buffer_id_base + buffer_index) * 8);
 		radeon_emit(cs, va); /* RESOURCEi_WORD0 */
-		radeon_emit(cs, rbuffer->buf->size - cb->buffer_offset - 1); /* RESOURCEi_WORD1 */
+		radeon_emit(cs, rbuffer->b.b.width0 - cb->buffer_offset - 1); /* RESOURCEi_WORD1 */
 		radeon_emit(cs, /* RESOURCEi_WORD2 */
 			    S_030008_ENDIAN_SWAP(gs_ring_buffer ? ENDIAN_NONE : r600_endian_swap(32)) |
 			    S_030008_STRIDE(gs_ring_buffer ? 4 : 16) |
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -141,7 +141,7 @@ int r600_pipe_shader_create(struct pipe_context *ctx,
 	bool dump = r600_can_dump_shader(&rctx->screen->b, sel->tokens);
 	unsigned use_sb = !(rctx->screen->b.debug_flags & DBG_NO_SB);
 	unsigned sb_disasm = use_sb || (rctx->screen->b.debug_flags & DBG_SB_DISASM);
-	unsigned export_shader = key.vs.as_es;
+	unsigned export_shader;

 	shader->shader.bc.isa = rctx->isa;

@@ -220,6 +220,7 @@ int r600_pipe_shader_create(struct pipe_context *ctx,
 		}
 		break;
 	case TGSI_PROCESSOR_VERTEX:
+		export_shader = key.vs.as_es;
 		if (rctx->b.chip_class >= EVERGREEN) {
 			if (export_shader)
 				evergreen_update_es_state(ctx, shader);
@@ -1830,8 +1831,6 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
 	ctx.shader = shader;
 	ctx.native_integers = true;

-	shader->vs_as_gs_a = key.vs.as_gs_a;
-	shader->vs_as_es = key.vs.as_es;

 	r600_bytecode_init(ctx.bc, rscreen->b.chip_class, rscreen->b.family,
 			   rscreen->has_compressed_msaa_texturing);
@@ -1844,9 +1843,14 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
 	shader->processor_type = ctx.type;
 	ctx.bc->type = shader->processor_type;

-	ring_outputs = key.vs.as_es || (ctx.type == TGSI_PROCESSOR_GEOMETRY);
+	if (ctx.type == TGSI_PROCESSOR_VERTEX) {
+		shader->vs_as_gs_a = key.vs.as_gs_a;
+		shader->vs_as_es = key.vs.as_es;
+	}

-	if (key.vs.as_es) {
+	ring_outputs = shader->vs_as_es || ctx.type == TGSI_PROCESSOR_GEOMETRY;
+
+	if (shader->vs_as_es) {
 		ctx.gs_for_vs = &rctx->gs_shader->current->shader;
 	} else {
 		ctx.gs_for_vs = NULL;
@@ -1866,7 +1870,8 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
 	shader->nr_ps_color_exports = 0;
 	shader->nr_ps_max_color_exports = 0;

-	shader->two_side = key.ps.color_two_side;
+	if (ctx.type == TGSI_PROCESSOR_FRAGMENT)
+		shader->two_side = key.ps.color_two_side;

 	/* register allocations */
 	/* Values [0,127] correspond to GPR[0..127].
@@ -2270,7 +2275,7 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
 	convert_edgeflag_to_int(&ctx);

 	if (ring_outputs) {
-		if (key.vs.as_es)
+		if (shader->vs_as_es)
 			emit_gs_ring_writes(&ctx, FALSE);
 	} else {
 		/* Export output */
--- a/src/gallium/drivers/r600/r600_state.c
+++ b/src/gallium/drivers/r600/r600_state.c
@@ -1007,7 +1007,7 @@ static void r600_init_color_surface(struct r600_context *rctx,

 		/* CMASK. */
 		if (!rctx->dummy_cmask ||
-		    rctx->dummy_cmask->buf->size < cmask.size ||
+		    rctx->dummy_cmask->b.b.width0 < cmask.size ||
 		    rctx->dummy_cmask->buf->alignment % cmask.alignment != 0) {
 			struct pipe_transfer *transfer;
 			void *ptr;
@@ -1025,7 +1025,7 @@ static void r600_init_color_surface(struct r600_context *rctx,

 		/* FMASK. */
 		if (!rctx->dummy_fmask ||
-		    rctx->dummy_fmask->buf->size < fmask.size ||
+		    rctx->dummy_fmask->b.b.width0 < fmask.size ||
 		    rctx->dummy_fmask->buf->alignment % fmask.alignment != 0) {
 			pipe_resource_reference((struct pipe_resource**)&rctx->dummy_fmask, NULL);
 			rctx->dummy_fmask = r600_buffer_create_helper(rscreen, fmask.size, fmask.alignment);
@@ -1694,7 +1694,7 @@ static void r600_emit_vertex_buffers(struct r600_context *rctx, struct r600_atom
 		radeon_emit(cs, PKT3(PKT3_SET_RESOURCE, 7, 0));
 		radeon_emit(cs, (320 + buffer_index) * 7);
 		radeon_emit(cs, offset); /* RESOURCEi_WORD0 */
-		radeon_emit(cs, rbuffer->buf->size - offset - 1); /* RESOURCEi_WORD1 */
+		radeon_emit(cs, rbuffer->b.b.width0 - offset - 1); /* RESOURCEi_WORD1 */
 		radeon_emit(cs, /* RESOURCEi_WORD2 */
 				 S_038008_ENDIAN_SWAP(r600_endian_swap(32)) |
 				 S_038008_STRIDE(vb->stride));
@@ -1743,7 +1743,7 @@ static void r600_emit_constant_buffers(struct r600_context *rctx,
 		radeon_emit(cs, PKT3(PKT3_SET_RESOURCE, 7, 0));
 		radeon_emit(cs, (buffer_id_base + buffer_index) * 7);
 		radeon_emit(cs, offset); /* RESOURCEi_WORD0 */
-		radeon_emit(cs, rbuffer->buf->size - offset - 1); /* RESOURCEi_WORD1 */
+		radeon_emit(cs, rbuffer->b.b.width0 - offset - 1); /* RESOURCEi_WORD1 */
 		radeon_emit(cs, /* RESOURCEi_WORD2 */
 			    S_038008_ENDIAN_SWAP(gs_ring_buffer ? ENDIAN_NONE : r600_endian_swap(32)) |
 			    S_038008_STRIDE(gs_ring_buffer ? 4 : 16));
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -195,9 +195,7 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen, void *
 	r600_target = radeon_llvm_get_r600_target(triple);
 	sctx->tm = LLVMCreateTargetMachine(r600_target, triple,
 					   r600_get_llvm_processor_name(sscreen->b.family),
-					   sctx->b.chip_class >= VI ?
-						   "+DumpCode" :
-						   "+DumpCode,+vgpr-spilling",
+					   "+DumpCode,+vgpr-spilling",
 					   LLVMCodeGenLevelDefault,
 					   LLVMRelocDefault,
 					   LLVMCodeModelDefault);
--- a/src/gallium/state_trackers/clover/llvm/invocation.cpp
+++ b/src/gallium/state_trackers/clover/llvm/invocation.cpp
@@ -465,7 +465,7 @@ namespace {
            const bool is_write_only = access_qual == "write_only";
            const bool is_read_only = access_qual == "read_only";

-            typename module::argument::type marg_type;
+            enum module::argument::type marg_type;
            if (is_image2d && is_read_only) {
               marg_type = module::argument::image2d_rd;
            } else if (is_image2d && is_write_only) {
--- a/src/gallium/winsys/amdgpu/drm/amdgpu_winsys.c
+++ b/src/gallium/winsys/amdgpu/drm/amdgpu_winsys.c
@@ -110,7 +110,7 @@ static boolean do_winsys_init(struct amdgpu_winsys *ws)
   struct amdgpu_heap_info vram, gtt;
   struct drm_amdgpu_info_hw_ip dma = {}, uvd = {}, vce = {};
   uint32_t vce_version = 0, vce_feature = 0;
-   int r;
+   int r, i, j;

   /* Query hardware and driver information. */
   r = amdgpu_query_gpu_info(ws->dev, &ws->amdinfo);
@@ -248,7 +248,6 @@ static boolean do_winsys_init(struct amdgpu_winsys *ws)
   ws->info.vram_size = vram.heap_size;
   /* convert the shader clock from KHz to MHz */
   ws->info.max_sclk = ws->amdinfo.max_engine_clk / 1000;
-   ws->info.max_compute_units = 1; /* TODO */
   ws->info.max_se = ws->amdinfo.num_shader_engines;
   ws->info.max_sh_per_se = ws->amdinfo.num_shader_arrays_per_engine;
   ws->info.has_uvd = uvd.available_rings != 0;
@@ -263,6 +262,18 @@ static boolean do_winsys_init(struct amdgpu_winsys *ws)
   ws->info.r600_virtual_address = TRUE;
   ws->info.r600_has_dma = dma.available_rings != 0;

+   /* Guess what the maximum compute unit number is by looking at the mask
+    * of enabled CUs.
+    */
+   for (i = 0; i < ws->info.max_se; i++)
+      for (j = 0; j < ws->info.max_sh_per_se; j++) {
+         unsigned max = util_last_bit(ws->amdinfo.cu_bitmap[i][j]);
+
+         if (ws->info.max_compute_units < max)
+            ws->info.max_compute_units = max;
+      }
+   ws->info.max_compute_units *= ws->info.max_se * ws->info.max_sh_per_se;
+
   memcpy(ws->info.si_tile_mode_array, ws->amdinfo.gb_tile_mode,
          sizeof(ws->amdinfo.gb_tile_mode));
   ws->info.si_tile_mode_array_valid = TRUE;
--- a/src/glsl/Android.gen.mk
+++ b/src/glsl/Android.gen.mk
@@ -29,18 +29,7 @@ endif

 intermediates := $(call local-generated-sources-dir)

-sources := \
-	glsl_lexer.cpp \
-	glsl_parser.cpp \
-	glcpp/glcpp-lex.c \
-	glcpp/glcpp-parse.c \
-	nir/nir_builder_opcodes.h \
-	nir/nir_constant_expressions.c \
-	nir/nir_opcodes.c \
-	nir/nir_opcodes.h \
-	nir/nir_opt_algebraic.c
-
-LOCAL_SRC_FILES := $(filter-out $(sources), $(LOCAL_SRC_FILES))
+LOCAL_SRC_FILES := $(LOCAL_SRC_FILES)

 LOCAL_C_INCLUDES += \
 	$(intermediates)/glcpp \
@@ -51,8 +40,10 @@ LOCAL_C_INCLUDES += \
 LOCAL_EXPORT_C_INCLUDE_DIRS += \
 	$(intermediates)/nir

-sources := $(addprefix $(intermediates)/, $(sources))
-LOCAL_GENERATED_SOURCES += $(sources)
+LOCAL_GENERATED_SOURCES += $(addprefix $(intermediates)/, \
+	$(LIBGLCPP_GENERATED_FILES) \
+	$(NIR_GENERATED_FILES) \
+	$(LIBGLSL_GENERATED_CXX_FILES))

 define local-l-or-ll-to-c-or-cpp
 	@mkdir -p $(dir $@)
@@ -102,8 +93,7 @@ $(intermediates)/nir/nir_builder_opcodes.h: $(nir_builder_opcodes_deps)
 nir_constant_expressions_gen := $(LOCAL_PATH)/nir/nir_constant_expressions.py
 nir_constant_expressions_deps := \
 	$(LOCAL_PATH)/nir/nir_opcodes.py \
-	$(LOCAL_PATH)/nir/nir_constant_expressions.py \
-	$(LOCAL_PATH)/nir/nir_constant_expressions.h
+	$(LOCAL_PATH)/nir/nir_constant_expressions.py

 $(intermediates)/nir/nir_constant_expressions.c: $(nir_constant_expressions_deps)
 	@mkdir -p $(dir $@)
--- a/src/glsl/Makefile.am
+++ b/src/glsl/Makefile.am
@@ -140,13 +140,16 @@ libglsl_la_SOURCES =					\
 	glsl_parser.cpp					\
 	glsl_parser.h					\
 	$(LIBGLSL_FILES)				\
-	$(NIR_FILES)
+	$(NIR_FILES)					\
+	$(NIR_GENERATED_FILES)
+

 libnir_la_SOURCES =					\
 	glsl_types.cpp					\
 	builtin_types.cpp				\
 	glsl_symbol_table.cpp				\
-	$(NIR_FILES)
+	$(NIR_FILES)					\
+	$(NIR_GENERATED_FILES)

 glsl_compiler_SOURCES = \
 	$(GLSL_COMPILER_CXX_FILES)
@@ -197,19 +200,23 @@ am__v_YACC_ = $(am__v_YACC_$(AM_DEFAULT_VERBOSITY))
 am__v_YACC_0 = @echo "  YACC    " $@;
 am__v_YACC_1 =

+MKDIR_GEN = $(AM_V_at)$(MKDIR_P) $(@D)
+YACC_GEN = $(AM_V_YACC)$(YACC) $(YFLAGS)
+LEX_GEN = $(AM_V_LEX)$(LEX) $(LFLAGS)
+
 glsl_parser.cpp glsl_parser.h: glsl_parser.yy
-	$(AM_V_YACC) $(YACC) $(YFLAGS) -o $@ -p "_mesa_glsl_" --defines=$(builddir)/glsl_parser.h $<
+	$(YACC_GEN) -o $@ -p "_mesa_glsl_" --defines=$(builddir)/glsl_parser.h $(srcdir)/glsl_parser.yy

 glsl_lexer.cpp: glsl_lexer.ll
-	$(AM_V_LEX) $(LEX) $(LFLAGS) -o $@ $<
+	$(LEX_GEN) -o $@ $(srcdir)/glsl_lexer.ll

 glcpp/glcpp-parse.c glcpp/glcpp-parse.h: glcpp/glcpp-parse.y
-	$(AM_V_at)$(MKDIR_P) glcpp
-	$(AM_V_YACC) $(YACC) $(YFLAGS) -o $@ -p "glcpp_parser_" --defines=$(builddir)/glcpp/glcpp-parse.h $<
+	$(MKDIR_GEN)
+	$(YACC_GEN) -o $@ -p "glcpp_parser_" --defines=$(builddir)/glcpp/glcpp-parse.h $(srcdir)/glcpp/glcpp-parse.y

 glcpp/glcpp-lex.c: glcpp/glcpp-lex.l
-	$(AM_V_at)$(MKDIR_P) glcpp
-	$(AM_V_LEX) $(LEX) $(LFLAGS) -o $@ $<
+	$(MKDIR_GEN)
+	$(LEX_GEN) -o $@ $(srcdir)/glcpp/glcpp-lex.l

 # Only the parsers (specifically the header files generated at the same time)
 # need to be in BUILT_SOURCES. Though if we list the parser headers YACC is
@@ -222,11 +229,7 @@ BUILT_SOURCES =						\
 	glsl_lexer.cpp					\
 	glcpp/glcpp-parse.c				\
 	glcpp/glcpp-lex.c				\
-	nir/nir_builder_opcodes.h				\
-	nir/nir_constant_expressions.c			\
-	nir/nir_opcodes.c				\
-	nir/nir_opcodes.h				\
-	nir/nir_opt_algebraic.c
+	$(NIR_GENERATED_FILES)
 CLEANFILES =						\
 	glcpp/glcpp-parse.h				\
 	glsl_parser.h					\
@@ -239,22 +242,24 @@ dist-hook:
 	$(RM) glcpp/tests/*.out
 	$(RM) glcpp/tests/subtest*/*.out

-nir/nir_builder_opcodes.h: nir/nir_opcodes.py nir/nir_builder_opcodes_h.py
-	$(AM_V_at)$(MKDIR_P) nir
-	$(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/nir/nir_builder_opcodes_h.py > $@
+PYTHON_GEN = $(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS)

-nir/nir_constant_expressions.c: nir/nir_opcodes.py nir/nir_constant_expressions.py nir/nir_constant_expressions.h
-	$(AM_V_at)$(MKDIR_P) nir
-	$(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/nir/nir_constant_expressions.py > $@
+nir/nir_builder_opcodes.h: nir/nir_opcodes.py nir/nir_builder_opcodes_h.py
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/nir/nir_builder_opcodes_h.py > $@
+
+nir/nir_constant_expressions.c: nir/nir_opcodes.py nir/nir_constant_expressions.py
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/nir/nir_constant_expressions.py > $@

 nir/nir_opcodes.h: nir/nir_opcodes.py nir/nir_opcodes_h.py
-	$(AM_V_at)$(MKDIR_P) nir
-	$(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/nir/nir_opcodes_h.py > $@
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/nir/nir_opcodes_h.py > $@

 nir/nir_opcodes.c: nir/nir_opcodes.py nir/nir_opcodes_c.py
-	$(AM_V_at)$(MKDIR_P) nir
-	$(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/nir/nir_opcodes_c.py > $@
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/nir/nir_opcodes_c.py > $@

 nir/nir_opt_algebraic.c: nir/nir_opt_algebraic.py nir/nir_algebraic.py
-	$(AM_V_at)$(MKDIR_P) nir
-	$(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/nir/nir_opt_algebraic.py > $@
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/nir/nir_opt_algebraic.py > $@
--- a/src/glsl/Makefile.sources
+++ b/src/glsl/Makefile.sources
@@ -69,8 +69,7 @@ NIR_FILES = \
 	nir/nir_vla.h \
 	nir/nir_worklist.c \
 	nir/nir_worklist.h \
-	nir/nir_types.cpp \
-	$(NIR_GENERATED_FILES)
+	nir/nir_types.cpp

 # libglsl

--- a/src/glsl/opt_constant_propagation.cpp
+++ b/src/glsl/opt_constant_propagation.cpp
@@ -40,6 +40,7 @@
 #include "ir_basic_block.h"
 #include "ir_optimization.h"
 #include "glsl_types.h"
+#include "util/hash_table.h"

 namespace {

@@ -95,7 +96,8 @@ public:
      killed_all = false;
      mem_ctx = ralloc_context(0);
      this->acp = new(mem_ctx) exec_list;
-      this->kills = new(mem_ctx) exec_list;
+      this->kills = _mesa_hash_table_create(mem_ctx, _mesa_hash_pointer,
+                                            _mesa_key_pointer_equal);
   }
   ~ir_constant_propagation_visitor()
   {
@@ -123,7 +125,7 @@ public:
    * List of kill_entry: The masks of variables whose values were
    * killed in this block.
    */
-   exec_list *kills;
+   hash_table *kills;

   bool progress;

@@ -263,11 +265,12 @@ ir_constant_propagation_visitor::visit_enter(ir_function_signature *ir)
    * main() at link time, so they're irrelevant to us.
    */
   exec_list *orig_acp = this->acp;
-   exec_list *orig_kills = this->kills;
+   hash_table *orig_kills = this->kills;
   bool orig_killed_all = this->killed_all;

   this->acp = new(mem_ctx) exec_list;
-   this->kills = new(mem_ctx) exec_list;
+   this->kills = _mesa_hash_table_create(mem_ctx, _mesa_hash_pointer,
+                                         _mesa_key_pointer_equal);
   this->killed_all = false;

   visit_list_elements(this, &ir->body);
@@ -352,11 +355,12 @@ void
 ir_constant_propagation_visitor::handle_if_block(exec_list *instructions)
 {
   exec_list *orig_acp = this->acp;
-   exec_list *orig_kills = this->kills;
+   hash_table *orig_kills = this->kills;
   bool orig_killed_all = this->killed_all;

   this->acp = new(mem_ctx) exec_list;
-   this->kills = new(mem_ctx) exec_list;
+   this->kills = _mesa_hash_table_create(mem_ctx, _mesa_hash_pointer,
+                                         _mesa_key_pointer_equal);
   this->killed_all = false;

   /* Populate the initial acp with a constant of the original */
@@ -370,12 +374,14 @@ ir_constant_propagation_visitor::handle_if_block(exec_list *instructions)
      orig_acp->make_empty();
   }

-   exec_list *new_kills = this->kills;
+   hash_table *new_kills = this->kills;
   this->kills = orig_kills;
   this->acp = orig_acp;
   this->killed_all = this->killed_all || orig_killed_all;

-   foreach_in_list(kill_entry, k, new_kills) {
+   hash_entry *htk;
+   hash_table_foreach(new_kills, htk) {
+      kill_entry *k = (kill_entry *) htk->data;
      kill(k->var, k->write_mask);
   }
 }
@@ -397,7 +403,7 @@ ir_visitor_status
 ir_constant_propagation_visitor::visit_enter(ir_loop *ir)
 {
   exec_list *orig_acp = this->acp;
-   exec_list *orig_kills = this->kills;
+   hash_table *orig_kills = this->kills;
   bool orig_killed_all = this->killed_all;

   /* FINISHME: For now, the initial acp for loops is totally empty.
@@ -405,7 +411,8 @@ ir_constant_propagation_visitor::visit_enter(ir_loop *ir)
    * cloned minus the killed entries after the first run through.
    */
   this->acp = new(mem_ctx) exec_list;
-   this->kills = new(mem_ctx) exec_list;
+   this->kills = _mesa_hash_table_create(mem_ctx, _mesa_hash_pointer,
+                                         _mesa_key_pointer_equal);
   this->killed_all = false;

   visit_list_elements(this, &ir->body_instructions);
@@ -414,12 +421,14 @@ ir_constant_propagation_visitor::visit_enter(ir_loop *ir)
      orig_acp->make_empty();
   }

-   exec_list *new_kills = this->kills;
+   hash_table *new_kills = this->kills;
   this->kills = orig_kills;
   this->acp = orig_acp;
   this->killed_all = this->killed_all || orig_killed_all;

-   foreach_in_list(kill_entry, k, new_kills) {
+   hash_entry *htk;
+   hash_table_foreach(new_kills, htk) {
+      kill_entry *k = (kill_entry *) htk->data;
      kill(k->var, k->write_mask);
   }

@@ -448,14 +457,15 @@ ir_constant_propagation_visitor::kill(ir_variable *var, unsigned write_mask)
   /* Add this writemask of the variable to the list of killed
    * variables in this block.
    */
-   foreach_in_list(kill_entry, entry, this->kills) {
-      if (entry->var == var) {
-	 entry->write_mask |= write_mask;
-	 return;
-      }
+   hash_entry *kill_hash_entry = _mesa_hash_table_search(this->kills, var);
+   if (kill_hash_entry) {
+      kill_entry *entry = (kill_entry *) kill_hash_entry->data;
+      entry->write_mask |= write_mask;
+      return;
   }
   /* Not already in the list.  Make new entry. */
-   this->kills->push_tail(new(this->mem_ctx) kill_entry(var, write_mask));
+   _mesa_hash_table_insert(this->kills, var,
+                           new(this->mem_ctx) kill_entry(var, write_mask));
 }

 /**
--- a/src/glsl/opt_constant_variable.cpp
+++ b/src/glsl/opt_constant_variable.cpp
@@ -36,11 +36,11 @@
 #include "ir_visitor.h"
 #include "ir_optimization.h"
 #include "glsl_types.h"
+#include "util/hash_table.h"

 namespace {

 struct assignment_entry {
-   exec_node link;
   int assignment_count;
   ir_variable *var;
   ir_constant *constval;
@@ -54,31 +54,32 @@ public:
   virtual ir_visitor_status visit_enter(ir_assignment *);
   virtual ir_visitor_status visit_enter(ir_call *);

-   exec_list list;
+   struct hash_table *ht;
 };

 } /* unnamed namespace */

 static struct assignment_entry *
-get_assignment_entry(ir_variable *var, exec_list *list)
+get_assignment_entry(ir_variable *var, struct hash_table *ht)
 {
+   struct hash_entry *hte = _mesa_hash_table_search(ht, var);
   struct assignment_entry *entry;

-   foreach_list_typed(struct assignment_entry, entry, link, list) {
-      if (entry->var == var)
-	 return entry;
+   if (hte) {
+      entry = (struct assignment_entry *) hte->data;
+   } else {
+      entry = (struct assignment_entry *) calloc(1, sizeof(*entry));
+      entry->var = var;
+      _mesa_hash_table_insert(ht, var, entry);
   }

-   entry = (struct assignment_entry *)calloc(1, sizeof(*entry));
-   entry->var = var;
-   list->push_head(&entry->link);
   return entry;
 }

 ir_visitor_status
 ir_constant_variable_visitor::visit(ir_variable *ir)
 {
-   struct assignment_entry *entry = get_assignment_entry(ir, &this->list);
+   struct assignment_entry *entry = get_assignment_entry(ir, this->ht);
   entry->our_scope = true;
   return visit_continue;
 }
@@ -97,7 +98,7 @@ ir_constant_variable_visitor::visit_enter(ir_assignment *ir)
   ir_constant *constval;
   struct assignment_entry *entry;

-   entry = get_assignment_entry(ir->lhs->variable_referenced(), &this->list);
+   entry = get_assignment_entry(ir->lhs->variable_referenced(), this->ht);
   assert(entry);
   entry->assignment_count++;

@@ -150,7 +151,7 @@ ir_constant_variable_visitor::visit_enter(ir_call *ir)
 	 struct assignment_entry *entry;

 	 assert(var);
-	 entry = get_assignment_entry(var, &this->list);
+	 entry = get_assignment_entry(var, this->ht);
 	 entry->assignment_count++;
      }
   }
@@ -161,7 +162,7 @@ ir_constant_variable_visitor::visit_enter(ir_call *ir)
      struct assignment_entry *entry;

      assert(var);
-      entry = get_assignment_entry(var, &this->list);
+      entry = get_assignment_entry(var, this->ht);
      entry->assignment_count++;
   }

@@ -177,20 +178,22 @@ do_constant_variable(exec_list *instructions)
   bool progress = false;
   ir_constant_variable_visitor v;

+   v.ht = _mesa_hash_table_create(NULL, _mesa_hash_pointer,
+                                  _mesa_key_pointer_equal);
   v.run(instructions);

-   while (!v.list.is_empty()) {
-
-      struct assignment_entry *entry;
-      entry = exec_node_data(struct assignment_entry, v.list.head, link);
+   struct hash_entry *hte;
+   hash_table_foreach(v.ht, hte) {
+      struct assignment_entry *entry = (struct assignment_entry *) hte->data;

      if (entry->assignment_count == 1 && entry->constval && entry->our_scope) {
 	 entry->var->constant_value = entry->constval;
 	 progress = true;
      }
-      entry->link.remove();
+      hte->data = NULL;
      free(entry);
   }
+   _mesa_hash_table_destroy(v.ht, NULL);

   return progress;
 }
--- a/src/mapi/Makefile.am
+++ b/src/mapi/Makefile.am
@@ -50,19 +50,14 @@ AM_CPPFLAGS =							\

 include Makefile.sources

+MKDIR_GEN = $(AM_V_at)$(MKDIR_P) $(@D)
+PYTHON_GEN = $(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS)
+
 glapi_gen_mapi_deps := \
 	mapi_abi.py \
 	$(wildcard glapi/gen/*.xml) \
 	$(wildcard glapi/gen/*.py)

-# $(1): path to an XML file
-# $(2): name of the printer
-define glapi_gen_mapi
-@$(MKDIR_P) $(dir $@)
-$(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/mapi_abi.py \
-	--mode lib --printer $(2) $(1) > $@
-endef
-
 if HAVE_SHARED_GLAPI
 BUILT_SOURCES += shared-glapi/glapi_mapi_tmp.h

@@ -93,7 +88,9 @@ shared_glapi_test_LDADD = \
 endif

 shared-glapi/glapi_mapi_tmp.h : glapi/gen/gl_and_es_API.xml $(glapi_gen_mapi_deps)
-	$(call glapi_gen_mapi,$<,shared-glapi)
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/mapi_abi.py --mode lib --printer shared-glapi \
+		$(srcdir)/glapi/gen/gl_and_es_API.xml > $@

 if HAVE_OPENGL
 noinst_LTLIBRARIES = glapi/libglapi.la
@@ -185,7 +182,9 @@ endif
 endif

 es1api/glapi_mapi_tmp.h: glapi/gen/gl_and_es_API.xml $(glapi_gen_mapi_deps)
-	$(call glapi_gen_mapi,$<,es1api)
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/mapi_abi.py --mode lib --printer es1api \
+		$(srcdir)/glapi/gen/gl_and_es_API.xml > $@

 if HAVE_OPENGL_ES2
 TESTS += es2api/ABI-check
@@ -229,6 +228,8 @@ endif
 endif

 es2api/glapi_mapi_tmp.h: glapi/gen/gl_and_es_API.xml $(glapi_gen_mapi_deps)
-	$(call glapi_gen_mapi,$<,es2api)
+	$(MKDIR_GEN)
+	$(PYTHON_GEN) $(srcdir)/mapi_abi.py --mode lib --printer es2api \
+		$(srcdir)/glapi/gen/gl_and_es_API.xml > $@

 include $(top_srcdir)/install-lib-links.mk
--- a/src/mapi/glapi/gen/Makefile.am
+++ b/src/mapi/glapi/gen/Makefile.am
@@ -20,7 +20,7 @@ XORG_INDENT_FLAGS = -linux -bad -bap -blf -bli0 -cbi0 -cdw -nce -cs -i4 -lc80 -p

 MESA_DIR = $(top_builddir)/src/mesa
 MESA_GLAPI_DIR = $(top_builddir)/src/mapi/glapi
-MESA_MAPI_DIR = $(top_builddir)/src/mapi
+MESA_MAPI_DIR = $(top_srcdir)/src/mapi
 MESA_GLX_DIR = $(top_builddir)/src/glx

 MESA_GLAPI_OUTPUTS = \
@@ -209,7 +209,7 @@ COMMON = $(API_XML) \

 COMMON_GLX = $(COMMON) glX_API.xml glX_XML.py glX_proto_common.py

-PYTHON_GEN = $(AM_V_GEN) $(PYTHON2) $(PYTHON_FLAGS)
+PYTHON_GEN = $(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS)

 ######################################################################

@@ -241,65 +241,65 @@ $(XORG_GLAPI_DIR)/%.h: $(MESA_GLAPI_DIR)/%.h
 ######################################################################

 $(MESA_GLAPI_DIR)/glapi_mapi_tmp.h: $(MESA_MAPI_DIR)/mapi_abi.py $(COMMON)
-	$(PYTHON_GEN) $< \
+	$(PYTHON_GEN) $(MESA_MAPI_DIR)/mapi_abi.py \
 		--printer glapi --mode lib $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_GLAPI_DIR)/glprocs.h: gl_procs.py $(COMMON)
-	$(PYTHON_GEN) $< -c -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_procs.py -c -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_GLAPI_DIR)/glapitemp.h: gl_apitemp.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_apitemp.py -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_GLAPI_DIR)/glapitable.h: gl_table.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_table.py -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_GLAPI_DIR)/glapi_gentable.c: gl_gentable.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_gentable.py -f $(srcdir)/gl_and_es_API.xml > $@

 ######################################################################

 $(MESA_GLAPI_DIR)/glapi_x86.S: gl_x86_asm.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_x86_asm.py -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_GLAPI_DIR)/glapi_x86-64.S: gl_x86-64_asm.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_x86-64_asm.py -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_GLAPI_DIR)/glapi_sparc.S: gl_SPARC_asm.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_SPARC_asm.py -f $(srcdir)/gl_and_es_API.xml > $@

 ######################################################################

 $(MESA_DIR)/main/enums.c: gl_enums.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_enums.py -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_DIR)/main/api_exec.c: gl_genexec.py apiexec.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/gl_genexec.py -f $(srcdir)/gl_and_es_API.xml > $@

 $(MESA_DIR)/main/dispatch.h: gl_table.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml -m remap_table > $@
+	$(PYTHON_GEN) $(srcdir)/gl_table.py -f $(srcdir)/gl_and_es_API.xml -m remap_table > $@

 $(MESA_DIR)/main/remap_helper.h: remap_helper.py $(COMMON)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_and_es_API.xml > $@
+	$(PYTHON_GEN) $(srcdir)/remap_helper.py -f $(srcdir)/gl_and_es_API.xml > $@

 ######################################################################

 $(MESA_GLX_DIR)/indirect.c: glX_proto_send.py $(COMMON_GLX)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_API.xml -m proto \
+	$(PYTHON_GEN) $(srcdir)/glX_proto_send.py -f $(srcdir)/gl_API.xml -m proto \
 	  | $(INDENT) $(INDENT_FLAGS) > $@

 $(MESA_GLX_DIR)/indirect.h: glX_proto_send.py $(COMMON_GLX)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_API.xml -m init_h > $@
+	$(PYTHON_GEN) $(srcdir)/glX_proto_send.py -f $(srcdir)/gl_API.xml -m init_h > $@

 $(MESA_GLX_DIR)/indirect_init.c: glX_proto_send.py $(COMMON_GLX)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_API.xml -m init_c > $@
+	$(PYTHON_GEN) $(srcdir)/glX_proto_send.py -f $(srcdir)/gl_API.xml -m init_c > $@

 $(MESA_GLX_DIR)/indirect_size.h $(XORG_GLX_DIR)/indirect_size.h: glX_proto_size.py $(COMMON_GLX)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_API.xml -m size_h --only-set \
+	$(PYTHON_GEN) $(srcdir)/glX_proto_size.py -f $(srcdir)/gl_API.xml -m size_h --only-set \
 	    --header-tag _INDIRECT_SIZE_H_ \
 	  | $(INDENT) $(INDENT_FLAGS) > $@

 $(MESA_GLX_DIR)/indirect_size.c: glX_proto_size.py $(COMMON_GLX)
-	$(PYTHON_GEN) $< -f $(srcdir)/gl_API.xml -m size_c --only-set \
+	$(PYTHON_GEN) $(srcdir)/glX_proto_size.py -f $(srcdir)/gl_API.xml -m size_c --only-set \
 	  | $(INDENT) $(INDENT_FLAGS) > $@

 ######################################################################
--- a/src/mesa/Makefile.am
+++ b/src/mesa/Makefile.am
@@ -90,37 +90,24 @@ CLEANFILES = \
 	program/program_parse.tab.h \
 	main/git_sha1.h.tmp

-GET_HASH_GEN = main/get_hash_generator.py
+PYTHON_GEN = $(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS)

-main/get_hash.h: ../mapi/glapi/gen/gl_and_es_API.xml main/get_hash_params.py 	\
-		 $(GET_HASH_GEN)
-	$(AM_V_GEN)set -e;						\
-	$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/$(GET_HASH_GEN)		\
-		-f $< > $@.tmp;						\
-	mv $@.tmp $@;
+main/get_hash.h: ../mapi/glapi/gen/gl_and_es_API.xml main/get_hash_params.py \
+                 main/get_hash_generator.py
+	$(PYTHON_GEN) $(srcdir)/main/get_hash_generator.py \
+		-f $(srcdir)/../mapi/glapi/gen/gl_and_es_API.xml > $@

-main/format_info.h: main/formats.csv                                    \
+main/format_info.h: main/formats.csv \
                    main/format_parser.py main/format_info.py
-	$(AM_V_GEN)set -e;						\
-	$(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/main/format_info.py        \
-                   $< > $@.tmp;                                         \
-	mv $@.tmp $@;
+	$(PYTHON_GEN) $(srcdir)/main/format_info.py $(srcdir)/main/formats.csv > $@

-main/format_pack.c: main/format_pack.py main/formats.csv		\
+main/format_pack.c: main/format_pack.py main/formats.csv \
                    main/format_parser.py
-	$(AM_V_GEN)set -e;						\
-	$(PYTHON2) $(PYTHON_FLAGS)					\
-			$(srcdir)/main/format_pack.py			\
-			$(srcdir)/main/formats.csv			\
-		| $(INDENT) $(INDENT_FLAGS) > $@;
+	$(PYTHON_GEN) $(srcdir)/main/format_pack.py $(srcdir)/main/formats.csv > $@

 main/format_unpack.c: main/format_unpack.py main/formats.csv	\
                      main/format_parser.py
-	$(AM_V_GEN)set -e;						\
-	$(PYTHON2) $(PYTHON_FLAGS)					\
-			$(srcdir)/main/format_unpack.py			\
-			$(srcdir)/main/formats.csv			\
-		| $(INDENT) $(INDENT_FLAGS) > $@;
+	$(PYTHON_GEN) $(srcdir)/main/format_unpack.py $(srcdir)/main/formats.csv > $@

 main/formats.c: main/format_info.h

@@ -201,13 +188,17 @@ libmesa_sse41_la_CFLAGS = $(AM_CFLAGS) $(SSE41_CFLAGS)
 pkgconfigdir = $(libdir)/pkgconfig
 pkgconfig_DATA = gl.pc

+MKDIR_GEN = $(AM_V_at)$(MKDIR_P) $(@D)
+YACC_GEN = $(AM_V_GEN)$(YACC) $(YFLAGS)
+LEX_GEN = $(AM_V_GEN)$(LEX) $(LFLAGS)
+
 program/lex.yy.c: program/program_lexer.l
-	$(AM_V_at)$(MKDIR_P) program
-	$(AM_V_GEN) $(LEX) --never-interactive --outfile=$@ $<
+	$(MKDIR_GEN)
+	$(LEX_GEN) -o $@ $(srcdir)/program/program_lexer.l

 program/program_parse.tab.c program/program_parse.tab.h: program/program_parse.y
-	$(AM_V_at)$(MKDIR_P) program
-	$(AM_V_GEN) $(YACC) -p "_mesa_program_" -v -d --output=program/program_parse.tab.c $<
+	$(MKDIR_GEN)
+	$(YACC_GEN) -o $@ -p "_mesa_program_" --defines=$(builddir)/program/program_parse.tab.h $(srcdir)/program/program_parse.y

 if GEN_ASM_OFFSETS
 matypes.h: $(gen_matypes_SOURCES)
--- a/src/mesa/drivers/common/meta_generate_mipmap.c
+++ b/src/mesa/drivers/common/meta_generate_mipmap.c
@@ -163,7 +163,6 @@ _mesa_meta_GenerateMipmap(struct gl_context *ctx, GLenum target,
   const GLuint maxLevel = texObj->MaxLevel;
   const GLint maxLevelSave = texObj->MaxLevel;
   const GLboolean genMipmapSave = texObj->GenerateMipmap;
-   const GLuint currentTexUnitSave = ctx->Texture.CurrentUnit;
   const GLboolean use_glsl_version = ctx->Extensions.ARB_vertex_shader &&
                                      ctx->Extensions.ARB_fragment_shader;
   GLenum faceTarget;
@@ -202,8 +201,12 @@ _mesa_meta_GenerateMipmap(struct gl_context *ctx, GLenum target,
   samplerSave = ctx->Texture.Unit[ctx->Texture.CurrentUnit].Sampler ?
      ctx->Texture.Unit[ctx->Texture.CurrentUnit].Sampler->Name : 0;

-   if (currentTexUnitSave != 0)
-      _mesa_BindTexture(target, texObj->Name);
+   /* We may have been called from glGenerateTextureMipmap with CurrentUnit
+    * still set to 0, so we don't know when we can skip binding the texture.
+    * Assume that _mesa_BindTexture will be fast if we're rebinding the same
+    * texture.
+    */
+   _mesa_BindTexture(target, texObj->Name);

   if (!mipmap->Sampler) {
      _mesa_GenSamplers(1, &mipmap->Sampler);
--- a/src/mesa/drivers/dri/common/xmlpool/Makefile.am
+++ b/src/mesa/drivers/dri/common/xmlpool/Makefile.am
@@ -67,7 +67,7 @@ CLEANFILES = \
 	$(MOS)

 # Default target options.h
-options.h: LOCALEDIR := .
+LOCALEDIR := .
 options.h: t_options.h $(MOS)
 	$(AM_V_GEN) $(PYTHON2) $(PYTHON_FLAGS) $(srcdir)/gen_xmlpool.py $(srcdir)/t_options.h $(LOCALEDIR) $(LANGS) > options.h

--- a/src/mesa/drivers/dri/i965/brw_blorp_blit.cpp
+++ b/src/mesa/drivers/dri/i965/brw_blorp_blit.cpp
@@ -215,6 +215,10 @@ brw_blorp_copytexsubimage(struct brw_context *brw,
   struct intel_renderbuffer *src_irb = intel_renderbuffer(src_rb);
   struct intel_texture_image *intel_image = intel_texture_image(dst_image);

+   /* No pixel transfer operations (zoom, bias, mapping), just a blit */
+   if (brw->ctx._ImageTransferState)
+      return false;
+
   /* Sync up the state of window system buffers.  We need to do this before
    * we go looking at the src renderbuffer's miptree.
    */
--- a/src/mesa/drivers/dri/i965/brw_context.c
+++ b/src/mesa/drivers/dri/i965/brw_context.c
@@ -323,6 +323,15 @@ brw_initialize_context_constants(struct brw_context *brw)

   ctx->Const.StripTextureBorder = true;

+   ctx->Const.MaxUniformBlockSize = 65536;
+   for (int i = 0; i < MESA_SHADER_STAGES; i++) {
+      struct gl_program_constants *prog = &ctx->Const.Program[i];
+      prog->MaxUniformBlocks = 12;
+      prog->MaxCombinedUniformComponents =
+         prog->MaxUniformComponents +
+         ctx->Const.MaxUniformBlockSize / 4 * prog->MaxUniformBlocks;
+   }
+
   ctx->Const.MaxDualSourceDrawBuffers = 1;
   ctx->Const.MaxDrawBuffers = BRW_MAX_DRAW_BUFFERS;
   ctx->Const.Program[MESA_SHADER_FRAGMENT].MaxTextureImageUnits = max_samplers;
--- a/src/mesa/drivers/dri/i965/brw_fs_vector_splitting.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_vector_splitting.cpp
@@ -43,6 +43,7 @@
 #include "glsl/ir_visitor.h"
 #include "glsl/ir_rvalue_visitor.h"
 #include "glsl/glsl_types.h"
+#include "util/hash_table.h"

 static bool debug = false;

@@ -72,7 +73,8 @@ public:
   ir_vector_reference_visitor(void)
   {
      this->mem_ctx = ralloc_context(NULL);
-      this->variable_list.make_empty();
+      this->ht = _mesa_hash_table_create(mem_ctx, _mesa_hash_pointer,
+                                         _mesa_key_pointer_equal);
   }

   ~ir_vector_reference_visitor(void)
@@ -89,7 +91,7 @@ public:
   variable_entry *get_variable_entry(ir_variable *var);

   /* List of variable_entry */
-   exec_list variable_list;
+   struct hash_table *ht;

   void *mem_ctx;
 };
@@ -119,13 +121,12 @@ ir_vector_reference_visitor::get_variable_entry(ir_variable *var)
      break;
   }

-   foreach_in_list(variable_entry, entry, &variable_list) {
-      if (entry->var == var)
-	 return entry;
-   }
+   struct hash_entry *hte = _mesa_hash_table_search(ht, var);
+   if (hte)
+      return (struct variable_entry *) hte->data;

   variable_entry *entry = new(mem_ctx) variable_entry(var);
-   this->variable_list.push_tail(entry);
+   _mesa_hash_table_insert(ht, var, entry);
   return entry;
 }

@@ -195,9 +196,9 @@ ir_vector_reference_visitor::visit_enter(ir_function_signature *ir)

 class ir_vector_splitting_visitor : public ir_rvalue_visitor {
 public:
-   ir_vector_splitting_visitor(exec_list *vars)
+   ir_vector_splitting_visitor(struct hash_table *vars)
   {
-      this->variable_list = vars;
+      this->ht = vars;
   }

   virtual ir_visitor_status visit_leave(ir_assignment *);
@@ -205,7 +206,7 @@ public:
   void handle_rvalue(ir_rvalue **rvalue);
   variable_entry *get_splitting_entry(ir_variable *var);

-   exec_list *variable_list;
+   struct hash_table *ht;
 };

 variable_entry *
@@ -216,13 +217,8 @@ ir_vector_splitting_visitor::get_splitting_entry(ir_variable *var)
   if (!var->type->is_vector())
      return NULL;

-   foreach_in_list(variable_entry, entry, variable_list) {
-      if (entry->var == var) {
-	 return entry;
-      }
-   }
-
-   return NULL;
+   struct hash_entry *hte = _mesa_hash_table_search(ht, var);
+   return hte ? (struct variable_entry *) hte->data : NULL;
 }

 void
@@ -329,12 +325,15 @@ ir_vector_splitting_visitor::visit_leave(ir_assignment *ir)
 bool
 brw_do_vector_splitting(exec_list *instructions)
 {
+   struct hash_entry *hte;
+
   ir_vector_reference_visitor refs;

   visit_list_elements(&refs, instructions);

   /* Trim out variables we can't split. */
-   foreach_in_list_safe(variable_entry, entry, &refs.variable_list) {
+   hash_table_foreach(refs.ht, hte) {
+      struct variable_entry *entry = (struct variable_entry *) hte->data;
      if (debug) {
 	 fprintf(stderr, "vector %s@%p: whole_access %d\n",
                 entry->var->name, (void *) entry->var,
@@ -342,11 +341,11 @@ brw_do_vector_splitting(exec_list *instructions)
      }

      if (entry->whole_vector_access) {
-	 entry->remove();
+         _mesa_hash_table_remove(refs.ht, hte);
      }
   }

-   if (refs.variable_list.is_empty())
+   if (refs.ht->entries == 0)
      return false;

   void *mem_ctx = ralloc_context(NULL);
@@ -354,7 +353,8 @@ brw_do_vector_splitting(exec_list *instructions)
   /* Replace the decls of the vectors to be split with their split
    * components.
    */
-   foreach_in_list(variable_entry, entry, &refs.variable_list) {
+   hash_table_foreach(refs.ht, hte) {
+      struct variable_entry *entry = (struct variable_entry *) hte->data;
      const struct glsl_type *type;
      type = glsl_type::get_instance(entry->var->type->base_type, 1, 1);

@@ -378,7 +378,7 @@ brw_do_vector_splitting(exec_list *instructions)
      entry->var->remove();
   }

-   ir_vector_splitting_visitor split(&refs.variable_list);
+   ir_vector_splitting_visitor split(refs.ht);
   visit_list_elements(&split, instructions);

   ralloc_free(mem_ctx);
--- a/src/mesa/drivers/dri/i965/intel_tex_copy.c
+++ b/src/mesa/drivers/dri/i965/intel_tex_copy.c
@@ -55,6 +55,10 @@ intel_copy_texsubimage(struct brw_context *brw,
   const GLenum internalFormat = intelImage->base.Base.InternalFormat;
   bool ret;

+   /* No pixel transfer operations (zoom, bias, mapping), just a blit */
+   if (brw->ctx._ImageTransferState)
+      return false;
+
   intel_prepare_render(brw);

   /* glCopyTexSubImage() can be called on a multisampled renderbuffer (if
--- a/src/mesa/state_tracker/st_extensions.c
+++ b/src/mesa/state_tracker/st_extensions.c
@@ -873,8 +873,13 @@ void st_init_extensions(struct pipe_screen *screen,

   consts->MaxViewports = screen->get_param(screen, PIPE_CAP_MAX_VIEWPORTS);
   if (consts->MaxViewports >= 16) {
-      consts->ViewportBounds.Min = -16384.0;
-      consts->ViewportBounds.Max = 16384.0;
+      if (glsl_feature_level >= 400) {
+         consts->ViewportBounds.Min = -32768.0;
+         consts->ViewportBounds.Max = 32767.0;
+      } else {
+         consts->ViewportBounds.Min = -16384.0;
+         consts->ViewportBounds.Max = 16383.0;
+      }
      extensions->ARB_viewport_array = GL_TRUE;
      extensions->ARB_fragment_layer_viewport = GL_TRUE;
      if (extensions->AMD_vertex_shader_layer)
--- a/src/mesa/state_tracker/st_format.c
+++ b/src/mesa/state_tracker/st_format.c
@@ -1270,46 +1270,40 @@ static const struct format_mapping format_map[] = {
   /* 32-bit float formats */
   {
      { GL_RGBA32F_ARB, 0 },
-      { PIPE_FORMAT_R32G32B32A32_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+      { PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_RGB32F_ARB, 0 },
      { PIPE_FORMAT_R32G32B32_FLOAT, PIPE_FORMAT_R32G32B32X32_FLOAT,
-        PIPE_FORMAT_R32G32B32A32_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+        PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_LUMINANCE_ALPHA32F_ARB, 0 },
-      { PIPE_FORMAT_L32A32_FLOAT, PIPE_FORMAT_R32G32B32A32_FLOAT,
-        PIPE_FORMAT_L16A16_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+      { PIPE_FORMAT_L32A32_FLOAT, PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_ALPHA32F_ARB, 0 },
      { PIPE_FORMAT_A32_FLOAT, PIPE_FORMAT_L32A32_FLOAT,
-        PIPE_FORMAT_R32G32B32A32_FLOAT, PIPE_FORMAT_A16_FLOAT,
-        PIPE_FORMAT_L16A16_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+        PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_INTENSITY32F_ARB, 0 },
      { PIPE_FORMAT_I32_FLOAT, PIPE_FORMAT_L32A32_FLOAT,
-        PIPE_FORMAT_R32G32B32A32_FLOAT, PIPE_FORMAT_I16_FLOAT,
-        PIPE_FORMAT_L16A16_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+        PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_LUMINANCE32F_ARB, 0 },
      { PIPE_FORMAT_L32_FLOAT, PIPE_FORMAT_L32A32_FLOAT,
-        PIPE_FORMAT_R32G32B32A32_FLOAT, PIPE_FORMAT_L16_FLOAT,
-        PIPE_FORMAT_L16A16_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+        PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_R32F, 0 },
      { PIPE_FORMAT_R32_FLOAT, PIPE_FORMAT_R32G32_FLOAT,
-        PIPE_FORMAT_R32G32B32A32_FLOAT, PIPE_FORMAT_R16_FLOAT,
-        PIPE_FORMAT_R16G16_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+        PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },
   {
      { GL_RG32F, 0 },
-      { PIPE_FORMAT_R32G32_FLOAT, PIPE_FORMAT_R32G32B32A32_FLOAT,
-        PIPE_FORMAT_R16G16_FLOAT, PIPE_FORMAT_R16G16B16A16_FLOAT, 0 }
+      { PIPE_FORMAT_R32G32_FLOAT, PIPE_FORMAT_R32G32B32A32_FLOAT, 0 }
   },

   /* R, RG formats */
--- a/src/util/Makefile.am
+++ b/src/util/Makefile.am
@@ -52,5 +52,7 @@ BUILT_SOURCES = $(MESA_UTIL_GENERATED_FILES)
 CLEANFILES = $(BUILT_SOURCES)
 EXTRA_DIST = format_srgb.py SConscript

-format_srgb.c: $(srcdir)/format_srgb.py
-	$(AM_V_GEN) $(PYTHON2) $< > $@
+PYTHON_GEN = $(AM_V_GEN)$(PYTHON2) $(PYTHON_FLAGS)
+
+format_srgb.c: format_srgb.py
+	$(PYTHON_GEN) $(srcdir)/format_srgb.py > $@