docs: Add release notes for 10.2.2 release

Which is ready to go.
Update VERSION to 10.2.2
2014-06-24 21:30:02 -07:00 · 2014-06-24 21:26:25 -07:00 · 2014-06-23 15:04:35 -07:00 · 2014-06-23 15:04:11 -07:00 · 2014-06-23 15:01:16 -07:00 · 2014-06-23 15:01:06 -07:00
78 changed files with 796 additions and 182 deletions
--- a/2
+++ b/2
@@ -1 +1 @@
-10.2.0-rc4
+10.2.2
--- a/configure.ac
+++ b/configure.ac
@@ -1293,6 +1293,7 @@ if test "x$enable_xa" = xyes; then
    fi
    GALLIUM_STATE_TRACKERS_DIRS="xa $GALLIUM_STATE_TRACKERS_DIRS"
    enable_gallium_loader=yes
+    enable_gallium_drm_loader=yes
 fi
 AM_CONDITIONAL(HAVE_ST_XA, test "x$enable_xa" = xyes)

@@ -1323,7 +1324,7 @@ AM_CONDITIONAL(HAVE_OPENVG, test "x$enable_openvg" = xyes)
 dnl
 dnl Gallium G3DVL configuration
 dnl
-if test -n "$with_gallium_drivers" && ! echo "$with_gallium_drivers" | grep -q 'swrast'; then
+if test -n "$with_gallium_drivers" -a "x$with_gallium_drivers" != xswrast; then
    if test "x$enable_xvmc" = xauto; then
 	PKG_CHECK_EXISTS([xvmc], [enable_xvmc=yes], [enable_xvmc=no])
    fi
@@ -1672,6 +1673,10 @@ if test "x$enable_gallium_llvm" = xyes; then
 else
    MESA_LLVM=0
    LLVM_VERSION_INT=0
+
+    if test "x$enable_opencl" = xyes; then
+        AC_MSG_ERROR([cannot enable OpenCL without LLVM])
+    fi
 fi

 dnl Directory for XVMC libs
--- a/docs/index.html
+++ b/docs/index.html
@@ -16,6 +16,20 @@

 <h1>News</h1>

+<h2>June 6, 2014</h2>
+<p>
+<a href="relnotes/10.2.1.html">Mesa 10.2.1</a> is released.  This release
+only fixes a build error in the radeonsi driver that was introduced between
+10.2-rc5 and the 10.2 final release.
+</p>
+
+<h2>June 6, 2014</h2>
+<p>
+<a href="relnotes/10.2.html">Mesa 10.2</a> is released.  This is a new
+development release.  See the release notes for more information about
+the release.
+</p>
+
 <h2>April 18, 2014</h2>
 <p>
 <a href="relnotes/10.1.1.html">Mesa 10.1.1</a> is released.
--- a/docs/relnotes.html
+++ b/docs/relnotes.html
@@ -21,6 +21,8 @@ The release notes summarize what's new or changed in each Mesa release.
 </p>

 <ul>
+<li><a href="relnotes/10.2.1.html">10.2.1 release notes</a>
+<li><a href="relnotes/10.2.html">10.2 release notes</a>
 <li><a href="relnotes/10.1.1.html">10.1.1 release notes</a>
 <li><a href="relnotes/10.1.html">10.1 release notes</a>
 <li><a href="relnotes/10.0.5.html">10.0.5 release notes</a>
--- a/docs/relnotes/10.2.1.html
+++ b/docs/relnotes/10.2.1.html
@@ -0,0 +1,61 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html lang="en">
+<head>
+  <meta http-equiv="content-type" content="text/html; charset=utf-8">
+  <title>Mesa Release Notes</title>
+  <link rel="stylesheet" type="text/css" href="../mesa.css">
+</head>
+<body>
+
+<div class="header">
+  <h1>The Mesa 3D Graphics Library</h1>
+</div>
+
+<iframe src="../contents.html"></iframe>
+<div class="content">
+
+<h1>Mesa 10.2.1 Release Notes / June 6, 2014</h1>
+
+<p>
+Mesa 10.2.1 is a bug fix release which fixes bugs found since the 10.1 release.
+</p>
+<p>
+Mesa 10.2.1 implements the OpenGL 3.3 API, but the version reported by
+glGetString(GL_VERSION) or glGetIntegerv(GL_MAJOR_VERSION) /
+glGetIntegerv(GL_MINOR_VERSION) depends on the particular driver being used.
+Some drivers don't support all the features required in OpenGL 3.3.  OpenGL
+3.3 is <strong>only</strong> available if requested at context creation
+because compatibility contexts are not supported.
+</p>
+
+
+<h2>MD5 checksums</h2>
+<pre>
+96f892dae2d0bb14ac9c2113f586c909  MesaLib-10.2.1.tar.gz
+093f9b5d077e5f6061dcd7b01b7aa51a  MesaLib-10.2.1.tar.bz2
+6ab76c1608e5deed1eb8b54c62d7a48a  MesaLib-10.2.1.zip
+</pre>
+
+
+<h2>New features</h2>
+<p>None</p>
+
+<h2>Bug fixes</h2>
+
+<p>
+Mesa 10.2 had a build problem in the radeonsi driver due to an error resolving
+conflicts in a patch cherry-pick from master.  The build error is fixed.
+</p>
+
+<h2>Changes</h2>
+
+<p>Ian Romanick (3):</p>
+<ul>
+  <li>docs: Add MD5 checksum, etc. for 10.1 release</li>
+  <li>radeonsi: Fix build error introduced in 5ab9a9c</li>
+  <li>Bump version to 10.2.1</li>
+</ul>
+
+</div>
+</body>
+</html>
--- a/docs/relnotes/10.2.2.html
+++ b/docs/relnotes/10.2.2.html
@@ -0,0 +1,178 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html lang="en">
+<head>
+  <meta http-equiv="content-type" content="text/html; charset=utf-8">
+  <title>Mesa Release Notes</title>
+  <link rel="stylesheet" type="text/css" href="../mesa.css">
+</head>
+<body>
+
+<div class="header">
+  <h1>The Mesa 3D Graphics Library</h1>
+</div>
+
+<iframe src="../contents.html"></iframe>
+<div class="content">
+
+<h1>Mesa 10.2.2 Release Notes / June 24, 2014</h1>
+
+<p>
+Mesa 10.2.2 is a bug fix release which fixes bugs found since the 10.2.1 release.
+</p>
+<p>
+Mesa 10.2.2 implements the OpenGL 3.3 API, but the version reported by
+glGetString(GL_VERSION) or glGetIntegerv(GL_MAJOR_VERSION) /
+glGetIntegerv(GL_MINOR_VERSION) depends on the particular driver being used.
+Some drivers don't support all the features required in OpenGL 3.3.  OpenGL
+3.3 is <strong>only</strong> available if requested at context creation
+because compatibility contexts are not supported.
+</p>
+
+
+<h2>SHA256 checksums</h2>
+<pre>
+</pre>
+
+
+<h2>New features</h2>
+<p>None</p>
+
+<h2>Bug fixes</h2>
+
+<p>This list is likely incomplete.</p>
+
+<ul>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=54372">Bug 54372</a> - GLX_INTEL_swap_event crashes driver when swapping window buffers</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=66452">Bug 66452</a> - JUNIPER UVD accelerated playback of WMV3 streams does not work</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=74005">Bug 74005</a> - [i965 Bisected]Piglit/glx_glx-make-glxdrawable-current fails</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=77865">Bug 77865</a> - [BDW] Many Ogles3conform framebuffer_blit cases fail</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=78581">Bug 78581</a> - OpenCL: clBuildProgram prints error messages directly rather than storing them</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=79029">Bug 79029</a> - INTEL_DEBUG=shader_time is full of lies</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=79729">Bug 79729</a> - [i965] glClear on a multisample texture doesn't work</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=79907">Bug 79907</a> - Mesa 10.2.1 --enable-vdpau default=auto broken</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=80115">Bug 80115</a> - MESA_META_DRAW_BUFFERS induced GL_INVALID_VALUE errors</li>
+
+</ul>
+
+
+<h2>Changes</h2>
+
+<p>Adrian Negreanu (8):</p>
+<ul>
+  <li>add megadriver_stub_FILES</li>
+  <li>android: adapt to the megadriver mechanism</li>
+  <li>android: add libloader to libGLES_mesa and libmesa_egl_dri2</li>
+  <li>android: add src/gallium/auxiliary as include path for libmesa_dricore</li>
+  <li>android, egl: add correct drm include for libmesa_egl_dri2</li>
+  <li>android, egl: typo dri2_fallback_pixmap_surface -&gt; dri2_fallback_create_pixmap_surface</li>
+  <li>android, mesa_gen_matypes: pull in timespec POSIX definition</li>
+  <li>android, dricore: undefined reference to _mesa_streaming_load_memcpy</li>
+</ul>
+
+<p>Carl Worth (1):</p>
+<ul>
+  <li>Update VERSION to 10.2.2</li>
+</ul>
+
+<p>Daniel Manjarres (1):</p>
+<ul>
+  <li>glx: Don't crash on swap event for a Window (non-GLXWindow)</li>
+</ul>
+
+<p>Emil Velikov (3):</p>
+<ul>
+  <li>targets/xa: limit the amount of exported symbols</li>
+  <li>configure: error out when building opencl without LLVM</li>
+  <li>configure: correctly autodetect xvmc/vdpau/omx</li>
+</ul>
+
+<p>Grigori Goronzy (1):</p>
+<ul>
+  <li>radeon/uvd: disable VC-1 simple/main on UVD 2.x</li>
+</ul>
+
+<p>Iago Toral Quiroga (1):</p>
+<ul>
+  <li>mesa: Copy Geom.UsesEndPrimitive when cloning a geometry program.</li>
+</ul>
+
+<p>Ian Romanick (3):</p>
+<ul>
+  <li>docs: Add initial 10.2.1 release notes</li>
+  <li>docs: Add MD5 checksum, etc. for 10.2.1 release</li>
+  <li>meta: Respect the driver's maximum number of draw buffers</li>
+</ul>
+
+<p>Ilia Mirkin (7):</p>
+<ul>
+  <li>gk110/ir: emit saturate flag on fadd when needed</li>
+  <li>gk110/ir: fix emitting constbuf file index</li>
+  <li>gk110/ir: fix bfind emission</li>
+  <li>nv50: make sure to mark first scissor dirty after blit</li>
+  <li>nv30: plug some memory leaks on screen destroy and shader compile</li>
+  <li>nv30: avoid dangling references to deleted contexts</li>
+  <li>nv30: hack to avoid errors on unexpected color/zeta combinations</li>
+</ul>
+
+<p>Jason Ekstrand (1):</p>
+<ul>
+  <li>meta_blit: properly compute texture width for the CopyTexSubImage fallback</li>
+</ul>
+
+<p>José Fonseca (1):</p>
+<ul>
+  <li>mesa/main: Prevent sefgault on glGetIntegerv(GL_ATOMIC_COUNTER_BUFFER_BINDING).</li>
+</ul>
+
+<p>Kenneth Graunke (9):</p>
+<ul>
+  <li>i965: Don't use the head sentinel as an fs_inst in Gen4 workaround code.</li>
+  <li>i965: Invalidate live intervals when inserting Gen4 SEND workarounds.</li>
+  <li>i965/vec4: Fix dead code elimination for VGRFs of size &gt; 1.</li>
+  <li>i965: Add missing MOCS setup for 3DSTATE_INDEX_BUFFER on Broadwell.</li>
+  <li>i965: Drop Broadwell perf_debugs about missing MOCS that aren't missing.</li>
+  <li>i965: Add missing newlines to a few perf_debug messages.</li>
+  <li>i965/vec4: Use the sampler for pull constant loads on Broadwell.</li>
+  <li>i965: Use 8x4 aligned rectangles for HiZ operations on Broadwell.</li>
+  <li>i965: Save meta stencil blit programs in the context.</li>
+</ul>
+
+<p>Kristian Høgsberg (1):</p>
+<ul>
+  <li>mesa: Remove glClear optimization based on drawable size</li>
+</ul>
+
+<p>Michel Dänzer (1):</p>
+<ul>
+  <li>configure: Only check for OpenCL without LLVM when the latter is certain</li>
+</ul>
+
+<p>Neil Roberts (1):</p>
+<ul>
+  <li>i965: Set the fast clear color value for texture surfaces</li>
+</ul>
+
+<p>Tom Stellard (2):</p>
+<ul>
+  <li>clover: Prevent Clang from printing number of errors and warnings to stderr.</li>
+  <li>clover: Don't use llvm's global context</li>
+</ul>
+
+<p>Ville Syrjälä (1):</p>
+<ul>
+  <li>i915: Fix gen2 texblend setup</li>
+</ul>
+
+
+</div>
+</body>
+</html>
--- a/docs/relnotes/10.2.html
+++ b/docs/relnotes/10.2.html
@@ -14,7 +14,7 @@
 <iframe src="../contents.html"></iframe>
 <div class="content">

-<h1>Mesa 10.2 Release Notes / TBD</h1>
+<h1>Mesa 10.2 Release Notes / June 6, 2014</h1>

 <p>
 Mesa 10.2 is a new development release.
@@ -33,7 +33,9 @@ because compatibility contexts are not supported.

 <h2>MD5 checksums</h2>
 <pre>
-TBD.
+c87bfb6dd5cbcf1fdef42e5ccd972581  MesaLib-10.2.0.tar.gz
+7aaba90bd7169a94ae2fe83febdec963  MesaLib-10.2.0.tar.bz2
+58b203aca15dadc25ab4d1126db1052b  MesaLib-10.2.0.zip
 </pre>


--- a/src/egl/drivers/dri2/Android.mk
+++ b/src/egl/drivers/dri2/Android.mk
@@ -40,8 +40,12 @@ LOCAL_C_INCLUDES := \
 	$(MESA_TOP)/src/mapi \
 	$(MESA_TOP)/src/egl/main \
 	$(MESA_TOP)/src/loader \
+	$(DRM_TOP)/include/drm \
 	$(DRM_GRALLOC_TOP)

+LOCAL_STATIC_LIBRARIES := \
+	libloader
+
 LOCAL_MODULE := libmesa_egl_dri2

 include $(MESA_COMMON_MK)
--- a/src/egl/drivers/dri2/platform_android.c
+++ b/src/egl/drivers/dri2/platform_android.c
@@ -638,7 +638,7 @@ droid_log(EGLint level, const char *msg)
 static struct dri2_egl_display_vtbl droid_display_vtbl = {
   .authenticate = NULL,
   .create_window_surface = droid_create_window_surface,
-   .create_pixmap_surface = dri2_fallback_pixmap_surface,
+   .create_pixmap_surface = dri2_fallback_create_pixmap_surface,
   .create_pbuffer_surface = droid_create_pbuffer_surface,
   .destroy_surface = droid_destroy_surface,
   .create_image = droid_create_image_khr,
--- a/src/egl/main/Android.mk
+++ b/src/egl/main/Android.mk
@@ -154,11 +154,14 @@ LOCAL_STATIC_LIBRARIES := \
 	libmesa_glsl \
 	libmesa_glsl_utils \
 	libmesa_gallium \
-	libloader \
 	$(LOCAL_STATIC_LIBRARIES)

 endif # MESA_BUILD_GALLIUM

+LOCAL_STATIC_LIBRARIES := \
+	$(LOCAL_STATIC_LIBRARIES) \
+	libloader
+
 LOCAL_MODULE := libGLES_mesa
 LOCAL_MODULE_PATH := $(TARGET_OUT_SHARED_LIBRARIES)/egl

--- a/src/egl/main/eglapi.c
+++ b/src/egl/main/eglapi.c
@@ -524,8 +524,12 @@ eglMakeCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read,
   if (!context && ctx != EGL_NO_CONTEXT)
      RETURN_EGL_ERROR(disp, EGL_BAD_CONTEXT, EGL_FALSE);
   if (!draw_surf || !read_surf) {
-      /* surfaces may be NULL if surfaceless */
-      if (!disp->Extensions.KHR_surfaceless_context)
+      /* From the EGL 1.4 (20130211) spec:
+       *
+       *    To release the current context without assigning a new one, set ctx
+       *    to EGL_NO_CONTEXT and set draw and read to EGL_NO_SURFACE.
+       */
+      if (!disp->Extensions.KHR_surfaceless_context && ctx != EGL_NO_CONTEXT)
         RETURN_EGL_ERROR(disp, EGL_BAD_SURFACE, EGL_FALSE);

      if ((!draw_surf && draw != EGL_NO_SURFACE) ||
@@ -567,6 +571,10 @@ _eglCreateWindowSurfaceCommon(_EGLDisplay *disp, EGLConfig config,
   EGLSurface ret;

   _EGL_CHECK_CONFIG(disp, conf, EGL_NO_SURFACE, drv);
+
+   if (native_window == NULL)
+      RETURN_EGL_ERROR(disp, EGL_BAD_NATIVE_WINDOW, EGL_NO_SURFACE);
+
   surf = drv->API.CreateWindowSurface(drv, disp, conf, native_window,
                                       attrib_list);
   ret = (surf) ? _eglLinkSurface(surf) : EGL_NO_SURFACE;
--- a/src/gallium/drivers/llvmpipe/lp_rast.c
+++ b/src/gallium/drivers/llvmpipe/lp_rast.c
@@ -312,9 +312,15 @@ lp_rast_shade_tile(struct lp_rasterizer_task *task,

         /* color buffer */
         for (i = 0; i < scene->fb.nr_cbufs; i++){
-            stride[i] = scene->cbufs[i].stride;
-            color[i] = lp_rast_get_unswizzled_color_block_pointer(task, i, tile_x + x,
-                                                                  tile_y + y, inputs->layer);
+            if (scene->fb.cbufs[i]) {
+               stride[i] = scene->cbufs[i].stride;
+               color[i] = lp_rast_get_unswizzled_color_block_pointer(task, i, tile_x + x,
+                                                                     tile_y + y, inputs->layer);
+            }
+            else {
+               stride[i] = 0;
+               color[i] = NULL;
+            }
         }

         /* depth buffer */
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
@@ -287,10 +287,12 @@ CodeEmitterGK110::emitPredicate(const Instruction *i)
 void
 CodeEmitterGK110::setCAddress14(const ValueRef& src)
 {
-   const int32_t addr = src.get()->asSym()->reg.data.offset / 4;
+   const Storage& res = src.get()->asSym()->reg;
+   const int32_t addr = res.data.offset / 4;

   code[0] |= (addr & 0x01ff) << 23;
   code[1] |= (addr & 0x3e00) >> 9;
+   code[1] |= res.fileIndex << 5;
 }

 void
@@ -413,7 +415,6 @@ CodeEmitterGK110::emitForm_21(const Instruction *i, uint32_t opc2,
      case FILE_MEMORY_CONST:
         code[1] &= (s == 2) ? ~(0x4 << 28) : ~(0x8 << 28);
         setCAddress14(i->src(s));
-         code[1] |= i->getSrc(s)->reg.fileIndex << 5;
         break;
      case FILE_IMMEDIATE:
         setShortImmediate(i, s);
@@ -555,6 +556,7 @@ CodeEmitterGK110::emitFADD(const Instruction *i)
      RND_(2a, F);
      ABS_(31, 0);
      NEG_(33, 0);
+      SAT_(35);

      if (code[0] & 0x1) {
         modNegAbsF32_3b(i, 1);
@@ -633,7 +635,7 @@ CodeEmitterGK110::emitISAD(const Instruction *i)
 {
   assert(i->dType == TYPE_S32 || i->dType == TYPE_U32);

-   emitForm_21(i, 0x1fc, 0xb74);
+   emitForm_21(i, 0x1f4, 0xb74);

   if (i->dType == TYPE_S32)
      code[1] |= 1 << 19;
@@ -711,7 +713,7 @@ CodeEmitterGK110::emitEXTBF(const Instruction *i)
 void
 CodeEmitterGK110::emitBFIND(const Instruction *i)
 {
-   emitForm_21(i, 0x618, 0xc18);
+   emitForm_C(i, 0x218, 0x2);

   if (i->dType == TYPE_S32)
      code[1] |= 0x80000;
@@ -952,7 +954,7 @@ CodeEmitterGK110::emitSLCT(const CmpInstruction *i)
      FTZ_(32);
      emitCondCode(cc, 0x33, 0xf);
   } else {
-      emitForm_21(i, 0x1a4, 0xb20);
+      emitForm_21(i, 0x1a0, 0xb20);
      emitCondCode(cc, 0x34, 0x7);
   }
 }
@@ -967,7 +969,7 @@ void CodeEmitterGK110::emitSELP(const Instruction *i)

 void CodeEmitterGK110::emitTEXBAR(const Instruction *i)
 {
-   code[0] = 0x00000002 | (i->subOp << 23);
+   code[0] = 0x0000003e | (i->subOp << 23);
   code[1] = 0x77000000;

   emitPredicate(i);
@@ -1204,7 +1206,7 @@ CodeEmitterGK110::emitFlow(const Instruction *i)
   case OP_PRECONT:  code[1] = 0x15800000; mask = 2; break;
   case OP_PRERET:   code[1] = 0x13800000; mask = 2; break;

-   case OP_QUADON:  code[1] = 0x1b000000; mask = 0; break;
+   case OP_QUADON:  code[1] = 0x1b800000; mask = 0; break;
   case OP_QUADPOP: code[1] = 0x1c000000; mask = 0; break;
   case OP_BRKPT:   code[1] = 0x00000000; mask = 0; break;
   default:
@@ -1326,7 +1328,8 @@ CodeEmitterGK110::emitOUT(const Instruction *i)
 void
 CodeEmitterGK110::emitInterpMode(const Instruction *i)
 {
-   code[1] |= i->ipa << 21; // TODO: INTERP_SAMPLEID
+   code[1] |= (i->ipa & 0x3) << 21; // TODO: INTERP_SAMPLEID
+   code[1] |= (i->ipa & 0xc) << (19 - 2);
 }

 void
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
@@ -2199,7 +2199,6 @@ Converter::handleInstruction(const struct tgsi_full_instruction *insn)
   case TGSI_OPCODE_IMUL_HI:
   case TGSI_OPCODE_UMUL_HI:
   case TGSI_OPCODE_OR:
-   case TGSI_OPCODE_POW:
   case TGSI_OPCODE_SHL:
   case TGSI_OPCODE_ISHR:
   case TGSI_OPCODE_USHR:
@@ -2254,6 +2253,11 @@ Converter::handleInstruction(const struct tgsi_full_instruction *insn)
      FOR_EACH_DST_ENABLED_CHANNEL(0, c, tgsi)
         mkOp1(OP_MOV, TYPE_U32, dst0[c], fetchSrc(0, c));
      break;
+   case TGSI_OPCODE_POW:
+      val0 = mkOp2v(op, TYPE_F32, getScratch(), fetchSrc(0, 0), fetchSrc(1, 0));
+      FOR_EACH_DST_ENABLED_CHANNEL(0, c, tgsi)
+         mkOp1(OP_MOV, TYPE_F32, dst0[c], val0);
+      break;
   case TGSI_OPCODE_EX2:
   case TGSI_OPCODE_LG2:
      val0 = mkOp1(op, TYPE_F32, getScratch(), fetchSrc(0, 0))->getDef(0);
@@ -2453,7 +2457,12 @@ Converter::handleInstruction(const struct tgsi_full_instruction *insn)
      break;
   case TGSI_OPCODE_KILL_IF:
      val0 = new_LValue(func, FILE_PREDICATE);
+      mask = 0;
      for (c = 0; c < 4; ++c) {
+         const int s = tgsi.getSrc(0).getSwizzle(c);
+         if (mask & (1 << s))
+            continue;
+         mask |= 1 << s;
         mkCmp(OP_SET, CC_LT, TYPE_F32, val0, TYPE_F32, fetchSrc(0, c), zero);
         mkOp(OP_DISCARD, TYPE_NONE, NULL)->setPredicate(CC_P, val0);
      }
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
@@ -1279,8 +1279,11 @@ NV50LoweringPreSSA::checkPredicate(Instruction *insn)
   Value *pred = insn->getPredicate();
   Value *cdst;

-   if (!pred || pred->reg.file == FILE_FLAGS)
+   // FILE_PREDICATE will simply be changed to FLAGS on conversion to SSA
+   if (!pred ||
+       pred->reg.file == FILE_FLAGS || pred->reg.file == FILE_PREDICATE)
      return;
+
   cdst = bld.getSSA(1, FILE_FLAGS);

   bld.mkCmp(OP_SET, CC_NEU, insn->dType, cdst, insn->dType, bld.loadImm(NULL, 0), pred);
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -561,8 +561,9 @@ ConstantFolding::expr(Instruction *i,
      if (i->src(0).getImmediate(src0))
         expr(i, src0, *i->getSrc(1)->asImm());
   } else {
-      i->op = OP_MOV;
+      i->op = i->saturate ? OP_SAT : OP_MOV; /* SAT handled by unary() */
   }
+   i->subOp = 0;
 }

 void
@@ -612,6 +613,7 @@ ConstantFolding::unary(Instruction *i, const ImmediateValue &imm)
   switch (i->op) {
   case OP_NEG: res.data.f32 = -imm.reg.data.f32; break;
   case OP_ABS: res.data.f32 = fabsf(imm.reg.data.f32); break;
+   case OP_SAT: res.data.f32 = CLAMP(imm.reg.data.f32, 0.0f, 1.0f); break;
   case OP_RCP: res.data.f32 = 1.0f / imm.reg.data.f32; break;
   case OP_RSQ: res.data.f32 = 1.0f / sqrtf(imm.reg.data.f32); break;
   case OP_LG2: res.data.f32 = log2f(imm.reg.data.f32); break;
@@ -922,6 +924,7 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, int s)

   case OP_ABS:
   case OP_NEG:
+   case OP_SAT:
   case OP_LG2:
   case OP_RCP:
   case OP_SQRT:
--- a/src/gallium/drivers/nouveau/nv30/nv30_context.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_context.c
@@ -165,6 +165,9 @@ nv30_context_destroy(struct pipe_context *pipe)
   if (nv30->draw)
      draw_destroy(nv30->draw);

+   if (nv30->screen->base.pushbuf->user_priv == &nv30->bufctx)
+      nv30->screen->base.pushbuf->user_priv = NULL;
+
   nouveau_bufctx_del(&nv30->bufctx);

   if (nv30->screen->cur_ctx == nv30)
--- a/src/gallium/drivers/nouveau/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
@@ -325,6 +325,12 @@ nv30_screen_destroy(struct pipe_screen *pscreen)
      nouveau_fence_ref(NULL, &screen->base.fence.current);
   }

+   nouveau_bo_ref(NULL, &screen->notify);
+
+   nouveau_heap_destroy(&screen->query_heap);
+   nouveau_heap_destroy(&screen->vp_exec_heap);
+   nouveau_heap_destroy(&screen->vp_data_heap);
+
   nouveau_object_del(&screen->query);
   nouveau_object_del(&screen->fence);
   nouveau_object_del(&screen->ntfy);
--- a/src/gallium/drivers/nouveau/nv30/nv30_state.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_state.c
@@ -23,6 +23,7 @@
 *
 */

+#include "util/u_format.h"
 #include "util/u_helpers.h"
 #include "util/u_inlines.h"

@@ -360,6 +361,22 @@ nv30_set_framebuffer_state(struct pipe_context *pipe,

    nv30->framebuffer = *fb;
    nv30->dirty |= NV30_NEW_FRAMEBUFFER;
+
+   /* Hardware can't handle different swizzled-ness or different blocksizes
+    * for zs and cbufs. If both are supplied and something doesn't match,
+    * blank out the zs for now so that at least *some* rendering can occur.
+    */
+    if (fb->nr_cbufs > 0 && fb->zsbuf) {
+       struct nv30_miptree *color_mt = nv30_miptree(fb->cbufs[0]->texture);
+       struct nv30_miptree *zeta_mt = nv30_miptree(fb->zsbuf->texture);
+
+       if (color_mt->swizzled != zeta_mt->swizzled ||
+           (util_format_get_blocksize(fb->zsbuf->format) > 2) !=
+           (util_format_get_blocksize(fb->cbufs[0]->format) > 2)) {
+          nv30->framebuffer.zsbuf = NULL;
+          debug_printf("Mismatched color and zeta formats, ignoring zeta.\n");
+       }
+    }
 }

 static void
--- a/src/gallium/drivers/nouveau/nv30/nvfx_fragprog.c
+++ b/src/gallium/drivers/nouveau/nv30/nvfx_fragprog.c
@@ -1225,6 +1225,7 @@ out:
   if(fpc)
   {
      FREE(fpc->r_temp);
+      FREE(fpc->r_imm);
      util_dynarray_fini(&fpc->if_stack);
      util_dynarray_fini(&fpc->label_relocs);
      util_dynarray_fini(&fpc->imm_data);
--- a/src/gallium/drivers/nouveau/nv50/nv50_context.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_context.c
@@ -122,12 +122,9 @@ nv50_destroy(struct pipe_context *pipe)
 {
   struct nv50_context *nv50 = nv50_context(pipe);

-   if (nv50_context_screen(nv50)->cur_ctx == nv50) {
-      nv50->base.pushbuf->kick_notify = NULL;
+   if (nv50_context_screen(nv50)->cur_ctx == nv50)
      nv50_context_screen(nv50)->cur_ctx = NULL;
-      nouveau_pushbuf_bufctx(nv50->base.pushbuf, NULL);
-   }
-   /* need to flush before destroying the bufctx */
+   nouveau_pushbuf_bufctx(nv50->base.pushbuf, NULL);
   nouveau_pushbuf_kick(nv50->base.pushbuf, nv50->base.pushbuf->channel);

   nv50_context_unreference_resources(nv50);
--- a/src/gallium/drivers/nouveau/nv50/nv50_state_validate.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_state_validate.c
@@ -400,6 +400,10 @@ nv50_switch_pipe_context(struct nv50_context *ctx_to)
   ctx_to->viewports_dirty = ~0;
   ctx_to->scissors_dirty = ~0;

+   ctx_to->constbuf_dirty[0] =
+   ctx_to->constbuf_dirty[1] =
+   ctx_to->constbuf_dirty[2] = (1 << NV50_MAX_PIPE_CONSTBUFS) - 1;
+
   if (!ctx_to->vertex)
      ctx_to->dirty &= ~(NV50_NEW_VERTEX | NV50_NEW_ARRAYS);

--- a/src/gallium/drivers/nouveau/nv50/nv50_surface.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_surface.c
@@ -288,6 +288,14 @@ nv50_clear_render_target(struct pipe_context *pipe,

   PUSH_REFN(push, bo, mt->base.domain | NOUVEAU_BO_WR);

+   BEGIN_NV04(push, NV50_3D(SCREEN_SCISSOR_HORIZ), 2);
+   PUSH_DATA (push, ( width << 16) | dstx);
+   PUSH_DATA (push, (height << 16) | dsty);
+   BEGIN_NV04(push, NV50_3D(SCISSOR_HORIZ(0)), 2);
+   PUSH_DATA (push, 8192 << 16);
+   PUSH_DATA (push, 8192 << 16);
+   nv50->scissors_dirty |= 1;
+
   BEGIN_NV04(push, NV50_3D(RT_CONTROL), 1);
   PUSH_DATA (push, 1);
   BEGIN_NV04(push, NV50_3D(RT_ADDRESS_HIGH(0)), 5);
@@ -325,7 +333,7 @@ nv50_clear_render_target(struct pipe_context *pipe,
                 (z << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT));
   }

-   nv50->dirty |= NV50_NEW_FRAMEBUFFER;
+   nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR;
 }

 static void
@@ -364,6 +372,14 @@ nv50_clear_depth_stencil(struct pipe_context *pipe,

   PUSH_REFN(push, bo, mt->base.domain | NOUVEAU_BO_WR);

+   BEGIN_NV04(push, NV50_3D(SCREEN_SCISSOR_HORIZ), 2);
+   PUSH_DATA (push, ( width << 16) | dstx);
+   PUSH_DATA (push, (height << 16) | dsty);
+   BEGIN_NV04(push, NV50_3D(SCISSOR_HORIZ(0)), 2);
+   PUSH_DATA (push, 8192 << 16);
+   PUSH_DATA (push, 8192 << 16);
+   nv50->scissors_dirty |= 1;
+
   BEGIN_NV04(push, NV50_3D(ZETA_ADDRESS_HIGH), 5);
   PUSH_DATAh(push, bo->offset + sf->offset);
   PUSH_DATA (push, bo->offset + sf->offset);
@@ -390,7 +406,7 @@ nv50_clear_depth_stencil(struct pipe_context *pipe,
                 (z << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT));
   }

-   nv50->dirty |= NV50_NEW_FRAMEBUFFER;
+   nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR;
 }

 void
@@ -1090,6 +1106,7 @@ nv50_blitctx_post_blit(struct nv50_blitctx *blit)
       NV50_NEW_RASTERIZER | NV50_NEW_ZSA | NV50_NEW_BLEND |
       NV50_NEW_TEXTURES | NV50_NEW_SAMPLERS |
       NV50_NEW_VERTPROG | NV50_NEW_GMTYPROG | NV50_NEW_FRAGPROG);
+   nv50->scissors_dirty |= 1;

   nv50->base.pipe.set_min_samples(&nv50->base.pipe, blit->saved.min_samples);
 }
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_context.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_context.c
@@ -123,11 +123,12 @@ nvc0_destroy(struct pipe_context *pipe)
 {
   struct nvc0_context *nvc0 = nvc0_context(pipe);

-   if (nvc0->screen->cur_ctx == nvc0) {
-      nvc0->base.pushbuf->kick_notify = NULL;
+   if (nvc0->screen->cur_ctx == nvc0)
      nvc0->screen->cur_ctx = NULL;
-      nouveau_pushbuf_bufctx(nvc0->base.pushbuf, NULL);
-   }
+   /* Unset bufctx, we don't want to revalidate any resources after the flush.
+    * Other contexts will always set their bufctx again on action calls.
+    */
+   nouveau_pushbuf_bufctx(nvc0->base.pushbuf, NULL);
   nouveau_pushbuf_kick(nvc0->base.pushbuf, nvc0->base.pushbuf->channel);

   nvc0_context_unreference_resources(nvc0);
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
@@ -133,17 +133,12 @@ static int
 nvc0_fp_assign_output_slots(struct nv50_ir_prog_info *info)
 {
   unsigned count = info->prop.fp.numColourResults * 4;
-   unsigned i, c, ci;
+   unsigned i, c;

-   for (i = 0, ci = 0; i < info->numOutputs; ++i) {
-      if (info->out[i].sn == TGSI_SEMANTIC_COLOR) {
+   for (i = 0; i < info->numOutputs; ++i)
+      if (info->out[i].sn == TGSI_SEMANTIC_COLOR)
         for (c = 0; c < 4; ++c)
-            info->out[i].slot[c] = ci * 4 + c;
-         ci++;
-      }
-   }
-
-   assert(ci == info->prop.fp.numColourResults);
+            info->out[i].slot[c] = info->out[i].si * 4 + c;

   if (info->io.sampleMask < PIPE_MAX_SHADER_OUTPUTS)
      info->out[info->io.sampleMask].slot[0] = count++;
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
@@ -171,7 +171,7 @@ nvc0_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
   case PIPE_CAP_VERTEX_ELEMENT_SRC_OFFSET_4BYTE_ALIGNED_ONLY:
      return 0;
   case PIPE_CAP_COMPUTE:
-      return (class_3d >= NVE4_3D_CLASS) ? 1 : 0;
+      return (class_3d == NVE4_3D_CLASS) ? 1 : 0;
   case PIPE_CAP_PREFER_BLIT_BASED_TEXTURE_TRANSFER:
      return 1;
   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
@@ -211,7 +211,7 @@ nvc0_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
   case PIPE_SHADER_FRAGMENT:
      break;
   case PIPE_SHADER_COMPUTE:
-      if (class_3d < NVE4_3D_CLASS)
+      if (class_3d != NVE4_3D_CLASS)
         return 0;
      break;
   default:
@@ -514,9 +514,10 @@ nvc0_screen_init_compute(struct nvc0_screen *screen)
         return nvc0_screen_compute_setup(screen, screen->base.pushbuf);
      return 0;
   case 0xe0:
+      return nve4_screen_compute_setup(screen, screen->base.pushbuf);
   case 0xf0:
   case 0x100:
-      return nve4_screen_compute_setup(screen, screen->base.pushbuf);
+      return 0;
   default:
      return -1;
   }
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
@@ -531,6 +531,7 @@ nvc0_switch_pipe_context(struct nvc0_context *ctx_to)
   for (s = 0; s < 5; ++s) {
      ctx_to->samplers_dirty[s] = ~0;
      ctx_to->textures_dirty[s] = ~0;
+      ctx_to->constbuf_dirty[s] = (1 << NVC0_MAX_PIPE_CONSTBUFS) - 1;
   }

   if (!ctx_to->vertex)
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_surface.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_surface.c
@@ -543,9 +543,22 @@ nvc0_blitter_make_vp(struct nvc0_blitter *blit)
      0x03f01c46, 0x0a7e0080, /* export b96 o[0x80] $r0:$r1:$r2 */
      0x00001de7, 0x80000000, /* exit */
   };
+   static const uint32_t code_gk110[] =
+   {
+      0x00000000, 0x08000000, /* sched */
+      0x401ffc12, 0x7ec7fc00, /* ld b64 $r4d a[0x80] 0x0 0x0 */
+      0x481ffc02, 0x7ecbfc00, /* ld b96 $r0t a[0x90] 0x0 0x0 */
+      0x381ffc12, 0x7f07fc00, /* st b64 a[0x70] $r4d 0x0 0x0 */
+      0x401ffc02, 0x7f0bfc00, /* st b96 a[0x80] $r0t 0x0 0x0 */
+      0x001c003c, 0x18000000, /* exit */
+   };

   blit->vp.type = PIPE_SHADER_VERTEX;
   blit->vp.translated = TRUE;
+   if (blit->screen->base.class_3d >= NVF0_3D_CLASS) {
+      blit->vp.code = (uint32_t *)code_gk110; /* const_cast */
+      blit->vp.code_size = sizeof(code_gk110);
+   } else
   if (blit->screen->base.class_3d >= NVE4_3D_CLASS) {
      blit->vp.code = (uint32_t *)code_nve4; /* const_cast */
      blit->vp.code_size = sizeof(code_nve4);
--- a/src/gallium/drivers/r600/r600_blit.c
+++ b/src/gallium/drivers/r600/r600_blit.c
@@ -789,7 +789,8 @@ static bool do_hardware_msaa_resolve(struct pipe_context *ctx,
 	    info->src.box.width == dst_width &&
 	    info->src.box.height == dst_height &&
 	    info->src.box.depth == 1 &&
-	    dst->surface.level[info->dst.level].mode >= RADEON_SURF_MODE_1D) {
+	    dst->surface.level[info->dst.level].mode >= RADEON_SURF_MODE_1D &&
+	    (!dst->cmask.size || !dst->dirty_level_mask) /* dst cannot be fast-cleared */) {
 		r600_blitter_begin(ctx, R600_COLOR_RESOLVE);
 		util_blitter_custom_resolve_color(rctx->blitter,
 						  info->dst.resource, info->dst.level,
--- a/src/gallium/drivers/radeon/r600_texture.c
+++ b/src/gallium/drivers/radeon/r600_texture.c
@@ -1235,6 +1235,9 @@ void evergreen_do_fast_color_clear(struct r600_common_context *rctx,
 {
 	int i;

+	if (rctx->current_render_cond)
+		return;
+
 	for (i = 0; i < fb->nr_cbufs; i++) {
 		struct r600_texture *tex;
 		unsigned clear_bit = PIPE_CLEAR_COLOR0 << i;
--- a/src/gallium/drivers/radeon/radeon_video.c
+++ b/src/gallium/drivers/radeon/radeon_video.c
@@ -242,7 +242,10 @@ int rvid_get_video_param(struct pipe_screen *screen,
 		switch (param) {
 		case PIPE_VIDEO_CAP_SUPPORTED:
 			/* no support for MPEG4 */
-			return codec != PIPE_VIDEO_FORMAT_MPEG4;
+			return codec != PIPE_VIDEO_FORMAT_MPEG4 &&
+			       /* FIXME: VC-1 simple/main profile is broken */
+			       profile != PIPE_VIDEO_PROFILE_VC1_SIMPLE &&
+			       profile != PIPE_VIDEO_PROFILE_VC1_MAIN;
 		case PIPE_VIDEO_CAP_PREFERS_INTERLACED:
 		case PIPE_VIDEO_CAP_SUPPORTS_INTERLACED:
 			/* and MPEG2 only with shaders */
--- a/src/gallium/drivers/radeonsi/si_blit.c
+++ b/src/gallium/drivers/radeonsi/si_blit.c
@@ -689,7 +689,8 @@ static bool do_hardware_msaa_resolve(struct pipe_context *ctx,
 	    info->src.box.height == dst_height &&
 	    info->src.box.depth == 1 &&
 	    dst->surface.level[info->dst.level].mode >= RADEON_SURF_MODE_1D &&
-	    !(dst->surface.flags & RADEON_SURF_SCANOUT)) {
+	    !(dst->surface.flags & RADEON_SURF_SCANOUT) &&
+	    (!dst->cmask.size || !dst->dirty_level_mask) /* dst cannot be fast-cleared */) {
 		si_blitter_begin(ctx, SI_COLOR_RESOLVE);
 		util_blitter_custom_resolve_color(sctx->blitter,
 						  info->dst.resource, info->dst.level,
--- a/src/gallium/state_trackers/clover/llvm/invocation.cpp
+++ b/src/gallium/state_trackers/clover/llvm/invocation.cpp
@@ -117,12 +117,13 @@ namespace {
 #endif

   llvm::Module *
-   compile(const std::string &source, const std::string &name,
-           const std::string &triple, const std::string &processor,
-           const std::string &opts, clang::LangAS::Map& address_spaces) {
+   compile(llvm::LLVMContext &llvm_ctx, const std::string &source,
+           const std::string &name, const std::string &triple,
+           const std::string &processor, const std::string &opts,
+           clang::LangAS::Map& address_spaces) {

      clang::CompilerInstance c;
-      clang::EmitLLVMOnlyAction act(&llvm::getGlobalContext());
+      clang::EmitLLVMOnlyAction act(&llvm_ctx);
      std::string log;
      llvm::raw_string_ostream s_log(log);
      std::string libclc_path = LIBCLC_LIBEXECDIR + processor + "-"
@@ -187,6 +188,11 @@ namespace {
      c.getLangOpts().NoBuiltin = true;
      c.getTargetOpts().Triple = triple;
      c.getTargetOpts().CPU = processor;
+
+      // This is a workaround for a Clang bug which causes the number
+      // of warnings and errors to be printed to stderr.
+      // http://www.llvm.org/bugs/show_bug.cgi?id=19735
+      c.getDiagnosticOpts().ShowCarets = false;
 #if HAVE_LLVM <= 0x0301
      c.getInvocation().setLangDefaults(clang::IK_OpenCL);
 #else
@@ -394,10 +400,12 @@ clover::compile_program_llvm(const compat::string &source,
                      target.size() - processor_str_len - 1);
   clang::LangAS::Map address_spaces;

+   llvm::LLVMContext llvm_ctx;
+
   // The input file name must have the .cl extension in order for the
   // CompilerInvocation class to recognize it as an OpenCL source file.
-   llvm::Module *mod = compile(source, "input.cl", triple, processor, opts,
-                                                                address_spaces);
+   llvm::Module *mod = compile(llvm_ctx, source, "input.cl", triple, processor,
+                               opts, address_spaces);

   find_kernels(mod, kernels);

--- a/src/gallium/targets/xa/Makefile.am
+++ b/src/gallium/targets/xa/Makefile.am
@@ -66,6 +66,9 @@ libxatracker_la_LDFLAGS = \
 	$(GC_SECTIONS) \
 	$(LD_NO_UNDEFINED)

+libxatracker_la_LDFLAGS += \
+	-Wl,--version-script=$(top_srcdir)/src/gallium/targets/xa/xa.sym
+
 if HAVE_MESA_LLVM
 libxatracker_la_LIBADD += $(LLVM_LIBS)
 libxatracker_la_LDFLAGS += $(LLVM_LDFLAGS)
--- a/src/gallium/targets/xa/xa.sym
+++ b/src/gallium/targets/xa/xa.sym
@@ -0,0 +1,38 @@
+{
+	global:
+		xa_composite_allocation;
+		xa_composite_check_accelerated;
+		xa_composite_done;
+		xa_composite_prepare;
+		xa_composite_rect;
+		xa_context_create;
+		xa_context_default;
+		xa_context_destroy;
+		xa_context_flush;
+		xa_copy;
+		xa_copy_done;
+		xa_copy_prepare;
+		xa_fence_get;
+		xa_fence_wait;
+		xa_fence_destroy;
+		xa_format_check_supported;
+		xa_solid;
+		xa_solid_done;
+		xa_solid_prepare;
+		xa_surface_create;
+		xa_surface_dma;
+		xa_surface_format;
+		xa_surface_from_handle;
+		xa_surface_handle;
+		xa_surface_map;
+		xa_surface_redefine;
+		xa_surface_ref;
+		xa_surface_unmap;
+		xa_surface_unref;
+		xa_tracker_create;
+		xa_tracker_destroy;
+		xa_tracker_version;
+		xa_yuv_planar_blit;
+	local:
+		*;
+};
--- a/src/glsl/ast_to_hir.cpp
+++ b/src/glsl/ast_to_hir.cpp
@@ -3652,11 +3652,15 @@ ast_declarator_list::hir(exec_list *instructions,
       * instruction stream.
       */
      exec_list initializer_instructions;
+
+      /* Examine var name here since var may get deleted in the next call */
+      bool var_is_gl_id = (strncmp(var->name, "gl_", 3) == 0);
+
      ir_variable *earlier =
         get_variable_being_redeclared(var, decl->get_location(), state,
                                       false /* allow_all_redeclarations */);
      if (earlier != NULL) {
-         if (strncmp(var->name, "gl_", 3) == 0 &&
+         if (var_is_gl_id &&
             earlier->data.how_declared == ir_var_declared_in_block) {
            _mesa_glsl_error(&loc, state,
                             "`%s' has already been redeclared using "
--- a/src/glx/dri2.c
+++ b/src/glx/dri2.c
@@ -131,10 +131,14 @@ DRI2WireToEvent(Display *dpy, XEvent *event, xEvent *wire)
      aevent->msc = ((CARD64)awire->msc_hi << 32) | awire->msc_lo;

      glxDraw = GetGLXDrawable(dpy, pdraw->drawable);
-      if (awire->sbc < glxDraw->lastEventSbc)
-	 glxDraw->eventSbcWrap += 0x100000000;
-      glxDraw->lastEventSbc = awire->sbc;
-      aevent->sbc = awire->sbc + glxDraw->eventSbcWrap;
+      if (glxDraw != NULL) {
+         if (awire->sbc < glxDraw->lastEventSbc)
+            glxDraw->eventSbcWrap += 0x100000000;
+         glxDraw->lastEventSbc = awire->sbc;
+         aevent->sbc = awire->sbc + glxDraw->eventSbcWrap;
+      } else {
+         aevent->sbc = awire->sbc;
+      }

      return True;
   }
--- a/src/glx/glxext.c
+++ b/src/glx/glxext.c
@@ -249,6 +249,10 @@ glx_display_free(struct glx_display *priv)
   if (priv->dri2Display)
      (*priv->dri2Display->destroyDisplay) (priv->dri2Display);
   priv->dri2Display = NULL;
+
+   if (priv->dri3Display)
+      (*priv->dri3Display->destroyDisplay) (priv->dri3Display);
+   priv->dri3Display = NULL;
 #endif

   free((char *) priv);
--- a/src/mapi/glapi/glapi_dispatch.c
+++ b/src/mapi/glapi/glapi_dispatch.c
@@ -87,6 +87,63 @@
 /* those link to libglapi.a should provide the entry points */
 #define _GLAPI_SKIP_PROTO_ENTRY_POINTS
 #endif
+
+/* These prototypes are necessary because GLES1 library builds will create
+ * dispatch functions for them.  We can't directly include GLES/gl.h because
+ * it would conflict the previously-included GL/gl.h.  Since GLES1 ABI is not
+ * expected to every add more functions, the path of least resistance is to
+ * just duplicate the prototypes for the functions that aren't already in
+ * desktop OpenGL.
+ */
+#include <GLES/glplatform.h>
+
+GL_API void GL_APIENTRY glClearDepthf (GLclampf depth);
+GL_API void GL_APIENTRY glClipPlanef (GLenum plane, const GLfloat *equation);
+GL_API void GL_APIENTRY glFrustumf (GLfloat left, GLfloat right, GLfloat bottom, GLfloat top, GLfloat zNear, GLfloat zFar);
+GL_API void GL_APIENTRY glGetClipPlanef (GLenum pname, GLfloat eqn[4]);
+GL_API void GL_APIENTRY glOrthof (GLfloat left, GLfloat right, GLfloat bottom, GLfloat top, GLfloat zNear, GLfloat zFar);
+
+GL_API void GL_APIENTRY glAlphaFuncx (GLenum func, GLclampx ref);
+GL_API void GL_APIENTRY glClearColorx (GLclampx red, GLclampx green, GLclampx blue, GLclampx alpha);
+GL_API void GL_APIENTRY glClearDepthx (GLclampx depth);
+GL_API void GL_APIENTRY glClipPlanex (GLenum plane, const GLfixed *equation);
+GL_API void GL_APIENTRY glColor4x (GLfixed red, GLfixed green, GLfixed blue, GLfixed alpha);
+GL_API void GL_APIENTRY glDepthRangex (GLclampx zNear, GLclampx zFar);
+GL_API void GL_APIENTRY glFogx (GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glFogxv (GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glFrustumx (GLfixed left, GLfixed right, GLfixed bottom, GLfixed top, GLfixed zNear, GLfixed zFar);
+GL_API void GL_APIENTRY glGetClipPlanex (GLenum pname, GLfixed eqn[4]);
+GL_API void GL_APIENTRY glGetFixedv (GLenum pname, GLfixed *params);
+GL_API void GL_APIENTRY glGetLightxv (GLenum light, GLenum pname, GLfixed *params);
+GL_API void GL_APIENTRY glGetMaterialxv (GLenum face, GLenum pname, GLfixed *params);
+GL_API void GL_APIENTRY glGetTexEnvxv (GLenum env, GLenum pname, GLfixed *params);
+GL_API void GL_APIENTRY glGetTexParameterxv (GLenum target, GLenum pname, GLfixed *params);
+GL_API void GL_APIENTRY glLightModelx (GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glLightModelxv (GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glLightx (GLenum light, GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glLightxv (GLenum light, GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glLineWidthx (GLfixed width);
+GL_API void GL_APIENTRY glLoadMatrixx (const GLfixed *m);
+GL_API void GL_APIENTRY glMaterialx (GLenum face, GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glMaterialxv (GLenum face, GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glMultMatrixx (const GLfixed *m);
+GL_API void GL_APIENTRY glMultiTexCoord4x (GLenum target, GLfixed s, GLfixed t, GLfixed r, GLfixed q);
+GL_API void GL_APIENTRY glNormal3x (GLfixed nx, GLfixed ny, GLfixed nz);
+GL_API void GL_APIENTRY glOrthox (GLfixed left, GLfixed right, GLfixed bottom, GLfixed top, GLfixed zNear, GLfixed zFar);
+GL_API void GL_APIENTRY glPointParameterx (GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glPointParameterxv (GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glPointSizex (GLfixed size);
+GL_API void GL_APIENTRY glPolygonOffsetx (GLfixed factor, GLfixed units);
+GL_API void GL_APIENTRY glRotatex (GLfixed angle, GLfixed x, GLfixed y, GLfixed z);
+GL_API void GL_APIENTRY glSampleCoveragex (GLclampx value, GLboolean invert);
+GL_API void GL_APIENTRY glScalex (GLfixed x, GLfixed y, GLfixed z);
+GL_API void GL_APIENTRY glTexEnvx (GLenum target, GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glTexEnvxv (GLenum target, GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glTexParameterx (GLenum target, GLenum pname, GLfixed param);
+GL_API void GL_APIENTRY glTexParameterxv (GLenum target, GLenum pname, const GLfixed *params);
+GL_API void GL_APIENTRY glTranslatex (GLfixed x, GLfixed y, GLfixed z);
+GL_API void GL_APIENTRY glPointSizePointerOES (GLenum type, GLsizei stride, const GLvoid *pointer);
+
 #include "glapi/glapitemp.h"

 #endif /* USE_X86_ASM */
--- a/src/mesa/Android.libmesa_dricore.mk
+++ b/src/mesa/Android.libmesa_dricore.mk
@@ -47,10 +47,16 @@ ifeq ($(TARGET_ARCH),x86)
 endif # x86
 endif # MESA_ENABLE_ASM

+ifeq ($(ARCH_X86_HAVE_SSE4_1),true)
+LOCAL_SRC_FILES += \
+	$(SRCDIR)main/streaming-load-memcpy.c
+endif
+
 LOCAL_C_INCLUDES := \
 	$(call intermediates-dir-for STATIC_LIBRARIES,libmesa_program,,) \
 	$(MESA_TOP)/src/mapi \
-	$(MESA_TOP)/src/glsl
+	$(MESA_TOP)/src/glsl \
+	$(MESA_TOP)/src/gallium/auxiliary

 LOCAL_WHOLE_STATIC_LIBRARIES := \
 	libmesa_program
--- a/src/mesa/Android.libmesa_glsl_utils.mk
+++ b/src/mesa/Android.libmesa_glsl_utils.mk
@@ -56,6 +56,7 @@ include $(CLEAR_VARS)

 LOCAL_MODULE := libmesa_glsl_utils
 LOCAL_IS_HOST_MODULE := true
+LOCAL_CFLAGS := -D_POSIX_C_SOURCE=199309L

 LOCAL_C_INCLUDES := \
 	$(MESA_TOP)/src/glsl \
--- a/src/mesa/Android.mesa_gen_matypes.mk
+++ b/src/mesa/Android.mesa_gen_matypes.mk
@@ -33,6 +33,7 @@ include $(CLEAR_VARS)

 LOCAL_MODULE := mesa_gen_matypes
 LOCAL_IS_HOST_MODULE := true
+LOCAL_CFLAGS := -D_POSIX_C_SOURCE=199309L

 LOCAL_C_INCLUDES := \
 	$(MESA_TOP)/src/mapi \
--- a/src/mesa/drivers/common/meta.c
+++ b/src/mesa/drivers/common/meta.c
@@ -801,7 +801,7 @@ _mesa_meta_begin(struct gl_context *ctx, GLbitfield state)
      int buf, real_color_buffers = 0;
      memset(save->ColorDrawBuffers, 0, sizeof(save->ColorDrawBuffers));

-      for (buf = 0; buf < MAX_DRAW_BUFFERS; buf++) {
+      for (buf = 0; buf < ctx->Const.MaxDrawBuffers; buf++) {
         int buf_index = ctx->DrawBuffer->_ColorDrawBufferIndexes[buf];
         if (buf_index == -1)
            continue;
@@ -1213,7 +1213,7 @@ _mesa_meta_end(struct gl_context *ctx)
      _mesa_BindRenderbuffer(GL_RENDERBUFFER, save->RenderbufferName);

   if (state & MESA_META_DRAW_BUFFERS) {
-      _mesa_DrawBuffers(MAX_DRAW_BUFFERS, save->ColorDrawBuffers);
+      _mesa_DrawBuffers(ctx->Const.MaxDrawBuffers, save->ColorDrawBuffers);
   }

   ctx->Meta->SaveStackDepth--;
--- a/src/mesa/drivers/common/meta.h
+++ b/src/mesa/drivers/common/meta.h
@@ -270,7 +270,7 @@ struct blit_state
 struct fb_tex_blit_state
 {
   GLint baseLevelSave, maxLevelSave;
-   GLuint sampler, samplerSave;
+   GLuint sampler, samplerSave, stencilSamplingSave;
   GLuint tempTex;
 };

@@ -407,7 +407,7 @@ _mesa_meta_fb_tex_blit_begin(const struct gl_context *ctx,
                             struct fb_tex_blit_state *blit);

 extern void
-_mesa_meta_fb_tex_blit_end(const struct gl_context *ctx, GLenum target,
+_mesa_meta_fb_tex_blit_end(struct gl_context *ctx, GLenum target,
                           struct fb_tex_blit_state *blit);

 extern GLboolean
--- a/src/mesa/drivers/common/meta_blit.c
+++ b/src/mesa/drivers/common/meta_blit.c
@@ -273,7 +273,7 @@ setup_glsl_msaa_blit_shader(struct gl_context *ctx,
                                   samples);
         } else {
            ralloc_asprintf_append(&sample_resolve,
-                                   "   out_color = sample_%d_0 / %f;\n",
+                                   "   gl_FragColor = sample_%d_0 / %f;\n",
                                   samples, (float)samples);
         }
      }
@@ -405,7 +405,7 @@ blitframebuffer_texture(struct gl_context *ctx,
      }
   } else {
      GLenum tex_base_format;
-      int srcW = abs(srcY1 - srcY0);
+      int srcW = abs(srcX1 - srcX0);
      int srcH = abs(srcY1 - srcY0);
      /* Fall back to doing a CopyTexSubImage to get the destination
       * renderbuffer into a texture.
@@ -444,6 +444,7 @@ blitframebuffer_texture(struct gl_context *ctx,

   fb_tex_blit.baseLevelSave = texObj->BaseLevel;
   fb_tex_blit.maxLevelSave = texObj->MaxLevel;
+   fb_tex_blit.stencilSamplingSave = texObj->StencilSampling;

   if (glsl_version) {
      setup_glsl_blit_framebuffer(ctx, blit, rb, target);
@@ -574,7 +575,7 @@ _mesa_meta_fb_tex_blit_begin(const struct gl_context *ctx,
 }

 void
-_mesa_meta_fb_tex_blit_end(const struct gl_context *ctx, GLenum target,
+_mesa_meta_fb_tex_blit_end(struct gl_context *ctx, GLenum target,
                           struct fb_tex_blit_state *blit)
 {
   /* Restore texture object state, the texture binding will
@@ -583,6 +584,16 @@ _mesa_meta_fb_tex_blit_end(const struct gl_context *ctx, GLenum target,
   if (target != GL_TEXTURE_RECTANGLE_ARB) {
      _mesa_TexParameteri(target, GL_TEXTURE_BASE_LEVEL, blit->baseLevelSave);
      _mesa_TexParameteri(target, GL_TEXTURE_MAX_LEVEL, blit->maxLevelSave);
+
+      if (ctx->Extensions.ARB_stencil_texturing) {
+         const struct gl_texture_object *texObj =
+            _mesa_get_current_tex_object(ctx, target);
+
+         if (texObj->StencilSampling != blit->stencilSamplingSave)
+            _mesa_TexParameteri(target, GL_DEPTH_STENCIL_TEXTURE_MODE,
+                                blit->stencilSamplingSave ?
+                                   GL_STENCIL_INDEX : GL_DEPTH_COMPONENT);
+      }
   }

   _mesa_BindSampler(ctx->Texture.CurrentUnit, blit->samplerSave);
--- a/src/mesa/drivers/dri/Android.mk
+++ b/src/mesa/drivers/dri/Android.mk
@@ -43,6 +43,7 @@ MESA_DRI_C_INCLUDES := \

 MESA_DRI_WHOLE_STATIC_LIBRARIES := \
 	libmesa_glsl \
+	libmegadriver_stub \
 	libmesa_dri_common \
 	libmesa_dricore

--- a/src/mesa/drivers/dri/common/Android.mk
+++ b/src/mesa/drivers/dri/common/Android.mk
@@ -86,3 +86,20 @@ $(intermediates)/xmlpool/options.h: $$(PRIVATE_SCRIPT) $$(PRIVATE_TEMPLATE_HEADE

 include $(MESA_COMMON_MK)
 include $(BUILD_STATIC_LIBRARY)
+
+#
+# Build libmegadriver_stub
+#
+
+include $(CLEAR_VARS)
+include $(LOCAL_PATH)/Makefile.sources
+
+LOCAL_MODULE := libmegadriver_stub
+LOCAL_MODULE_CLASS := STATIC_LIBRARIES
+LOCAL_C_INCLUDES := \
+    $(MESA_DRI_C_INCLUDES)
+
+LOCAL_SRC_FILES := $(megadriver_stub_FILES)
+
+include $(MESA_COMMON_MK)
+include $(BUILD_STATIC_LIBRARY)
--- a/src/mesa/drivers/dri/common/Makefile.am
+++ b/src/mesa/drivers/dri/common/Makefile.am
@@ -42,7 +42,7 @@ libdricommon_la_SOURCES = $(DRI_COMMON_FILES)
 libdri_test_stubs_la_SOURCES = $(test_stubs_FILES)
 libdri_test_stubs_la_CFLAGS = $(AM_CFLAGS) -DNO_MAIN

-libmegadriver_stub_la_SOURCES = megadriver_stub.c
+libmegadriver_stub_la_SOURCES = $(megadriver_stub_FILES)

 sysconf_DATA = drirc

--- a/src/mesa/drivers/dri/common/Makefile.sources
+++ b/src/mesa/drivers/dri/common/Makefile.sources
@@ -14,3 +14,6 @@ mesa_dri_common_INCLUDES := \

 test_stubs_FILES := \
 	dri_test.c
+
+megadriver_stub_FILES := \
+	megadriver_stub.c
--- a/src/mesa/drivers/dri/i915/i830_texblend.c
+++ b/src/mesa/drivers/dri/i915/i830_texblend.c
@@ -445,7 +445,7 @@ i830EmitTextureBlend(struct i830_context *i830)
   I830_ACTIVESTATE(i830, I830_UPLOAD_TEXBLEND_ALL, false);

   if (ctx->Texture._MaxEnabledTexImageUnit != -1) {
-      for (unit = 0; unit < ctx->Texture._MaxEnabledTexImageUnit; unit++)
+      for (unit = 0; unit <= ctx->Texture._MaxEnabledTexImageUnit; unit++)
         if (ctx->Texture.Unit[unit]._Current)
            emit_texblend(i830, unit, blendunit++,
                          unit == ctx->Texture._MaxEnabledTexImageUnit);
--- a/src/mesa/drivers/dri/i915/intel_context.c
+++ b/src/mesa/drivers/dri/i915/intel_context.c
@@ -507,7 +507,7 @@ intelInitContext(struct intel_context *intel,

   _mesa_meta_init(ctx);

-   intel->hw_stencil = mesaVis->stencilBits && mesaVis->depthBits == 24;
+   intel->hw_stencil = mesaVis && mesaVis->stencilBits && mesaVis->depthBits == 24;
   intel->hw_stipple = 1;

   intel->RenderIndex = ~0;
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -1115,6 +1115,9 @@ struct brw_context

   struct brw_cache cache;

+   /** IDs for meta stencil blit shader programs. */
+   unsigned meta_stencil_blit_programs[2];
+
   /* Whether a meta-operation is in progress. */
   bool meta_in_progress;

--- a/src/mesa/drivers/dri/i965/brw_defines.h
+++ b/src/mesa/drivers/dri/i965/brw_defines.h
@@ -606,6 +606,7 @@
 #define BRW_TEXCOORDMODE_CUBE            3
 #define BRW_TEXCOORDMODE_CLAMP_BORDER    4
 #define BRW_TEXCOORDMODE_MIRROR_ONCE     5
+#define GEN8_TEXCOORDMODE_HALF_BORDER    6

 #define BRW_THREAD_PRIORITY_NORMAL   0
 #define BRW_THREAD_PRIORITY_HIGH     1
@@ -1694,7 +1695,7 @@ enum brw_message_target {
 /* GEN7/DW1: */
 # define GEN7_SF_DEPTH_BUFFER_SURFACE_FORMAT_SHIFT	12
 /* GEN7/DW2: */
-# define HSW_SF_LINE_STIPPLE_ENABLE			14
+# define HSW_SF_LINE_STIPPLE_ENABLE			(1 << 14)

 # define GEN8_SF_SMOOTH_POINT_ENABLE                    (1 << 13)

--- a/src/mesa/drivers/dri/i965/brw_device_info.c
+++ b/src/mesa/drivers/dri/i965/brw_device_info.c
@@ -192,33 +192,44 @@ static const struct brw_device_info brw_device_info_hsw_gt3 = {
   },
 };

-/* Thread counts and URB limits are placeholders, and may not be accurate. */
 #define GEN8_FEATURES                               \
   .gen = 8,                                        \
   .has_hiz_and_separate_stencil = true,            \
   .must_use_separate_stencil = true,               \
   .has_llc = true,                                 \
   .has_pln = true,                                 \
-   .max_vs_threads = 280,                           \
-   .max_gs_threads = 256,                           \
-   .max_wm_threads = 408,                           \
-   .urb = {                                         \
-      .size = 128,                                  \
-      .min_vs_entries = 64,                         \
-      .max_vs_entries = 1664,                       \
-      .max_gs_entries = 640,                        \
-   }
+   .max_vs_threads = 504,                           \
+   .max_gs_threads = 504,                           \
+   .max_wm_threads = 384                            \

 static const struct brw_device_info brw_device_info_bdw_gt1 = {
   GEN8_FEATURES, .gt = 1,
+   .urb = {
+      .size = 192,
+      .min_vs_entries = 64,
+      .max_vs_entries = 2560,
+      .max_gs_entries = 960,
+   }
 };

 static const struct brw_device_info brw_device_info_bdw_gt2 = {
   GEN8_FEATURES, .gt = 2,
+   .urb = {
+      .size = 384,
+      .min_vs_entries = 64,
+      .max_vs_entries = 2560,
+      .max_gs_entries = 960,
+   }
 };

 static const struct brw_device_info brw_device_info_bdw_gt3 = {
   GEN8_FEATURES, .gt = 3,
+   .urb = {
+      .size = 384,
+      .min_vs_entries = 64,
+      .max_vs_entries = 2560,
+      .max_gs_entries = 960,
+   }
 };

 /* Thread counts and URB limits are placeholders, and may not be accurate.
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -2406,7 +2406,7 @@ fs_visitor::insert_gen4_pre_send_dependency_workarounds(fs_inst *inst)
    * program.
    */
   for (fs_inst *scan_inst = (fs_inst *)inst->prev;
-        scan_inst != NULL;
+        !scan_inst->is_head_sentinel();
        scan_inst = (fs_inst *)scan_inst->prev) {

      /* If we hit control flow, assume that there *are* outstanding
@@ -2533,6 +2533,8 @@ fs_visitor::insert_gen4_send_dependency_workarounds()
   if (brw->gen != 4 || brw->is_g4x)
      return;

+   bool progress = false;
+
   /* Note that we're done with register allocation, so GRF fs_regs always
    * have a .reg_offset of 0.
    */
@@ -2543,8 +2545,12 @@ fs_visitor::insert_gen4_send_dependency_workarounds()
      if (inst->mlen != 0 && inst->dst.file == GRF) {
         insert_gen4_pre_send_dependency_workarounds(inst);
         insert_gen4_post_send_dependency_workarounds(inst);
+         progress = true;
      }
   }
+
+   if (progress)
+      invalidate_live_intervals();
 }

 /**
--- a/src/mesa/drivers/dri/i965/brw_fs_register_coalesce.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_register_coalesce.cpp
@@ -77,21 +77,40 @@ is_coalesce_candidate(const fs_inst *inst, const int *virtual_grf_sizes)

 static bool
 can_coalesce_vars(brw::fs_live_variables *live_intervals,
-                  const exec_list *instructions, const fs_inst *inst, int ip,
+                  const exec_list *instructions, const fs_inst *inst,
                  int var_to, int var_from)
 {
   if (!live_intervals->vars_interfere(var_from, var_to))
      return true;

-   assert(ip >= live_intervals->start[var_to]);
+   /* We know that the live ranges of A (var_from) and B (var_to)
+    * interfere because of the ->vars_interfere() call above. If the end
+    * of B's live range is after the end of A's range, then we know two
+    * things:
+    *  - the start of B's live range must be in A's live range (since we
+    *    already know the two ranges interfere, this is the only remaining
+    *    possibility)
+    *  - the interference isn't of the form we're looking for (where B is
+    *    entirely inside A)
+    */
+   if (live_intervals->end[var_to] > live_intervals->end[var_from])
+      return false;

-   fs_inst *scan_inst;
-   for (scan_inst = (fs_inst *)inst->next;
-        !scan_inst->is_tail_sentinel() && ip <= live_intervals->end[var_to];
-        scan_inst = (fs_inst *)scan_inst->next, ip++) {
-      if (scan_inst->opcode == BRW_OPCODE_WHILE)
+   int scan_ip = -1;
+
+   foreach_list(n, instructions) {
+      fs_inst *scan_inst = (fs_inst *)n;
+      scan_ip++;
+
+      if (scan_inst->is_control_flow())
         return false;

+      if (scan_ip <= live_intervals->start[var_to])
+         continue;
+
+      if (scan_ip > live_intervals->end[var_to])
+         break;
+
      if (scan_inst->dst.equals(inst->dst) ||
          scan_inst->dst.equals(inst->src[0]))
         return false;
@@ -114,11 +133,9 @@ fs_visitor::register_coalesce()
   fs_inst *mov[MAX_SAMPLER_MESSAGE_SIZE];
   int var_to[MAX_SAMPLER_MESSAGE_SIZE];
   int var_from[MAX_SAMPLER_MESSAGE_SIZE];
-   int ip = -1;

   foreach_list(node, &this->instructions) {
      fs_inst *inst = (fs_inst *)node;
-      ip++;

      if (!is_coalesce_candidate(inst, virtual_grf_sizes))
         continue;
@@ -157,7 +174,7 @@ fs_visitor::register_coalesce()
         var_to[i] = live_intervals->var_from_vgrf[reg_to] + reg_to_offset[i];
         var_from[i] = live_intervals->var_from_vgrf[reg_from] + i;

-         if (!can_coalesce_vars(live_intervals, &instructions, inst, ip,
+         if (!can_coalesce_vars(live_intervals, &instructions, inst,
                                var_to[i], var_from[i])) {
            can_coalesce = false;
            reg_from = -1;
--- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
@@ -221,15 +221,18 @@ fs_visitor::emit_lrp(const fs_reg &dst, const fs_reg &x, const fs_reg &y,
       !y.is_valid_3src() ||
       !a.is_valid_3src()) {
      /* We can't use the LRP instruction.  Emit x*(1-a) + y*a. */
+      fs_reg y_times_a           = fs_reg(this, glsl_type::float_type);
      fs_reg one_minus_a         = fs_reg(this, glsl_type::float_type);
+      fs_reg x_times_one_minus_a = fs_reg(this, glsl_type::float_type);
+
+      emit(MUL(y_times_a, y, a));

      fs_reg negative_a = a;
      negative_a.negate = !a.negate;
-
      emit(ADD(one_minus_a, negative_a, fs_reg(1.0f)));
-      fs_inst *mul = emit(MUL(reg_null_f, y, a));
-      mul->writes_accumulator = true;
-      emit(MAC(dst, x, one_minus_a));
+      emit(MUL(x_times_one_minus_a, x, one_minus_a));
+
+      emit(ADD(dst, x_times_one_minus_a, y_times_a));
   } else {
      /* The LRP instruction actually does op1 * op0 + op2 * (1 - op0), so
       * we need to reorder the operands.
@@ -1480,15 +1483,28 @@ fs_visitor::rescale_texcoord(ir_texture *ir, fs_reg coordinate,
 	 return coordinate;
      }

-      scale_x = fs_reg(UNIFORM, uniforms);
-      scale_y = fs_reg(UNIFORM, uniforms + 1);
-
      GLuint index = _mesa_add_state_reference(params,
 					       (gl_state_index *)tokens);
-      stage_prog_data->param[uniforms++] =
-         &prog->Parameters->ParameterValues[index][0].f;
-      stage_prog_data->param[uniforms++] =
-         &prog->Parameters->ParameterValues[index][1].f;
+      /* Try to find existing copies of the texrect scale uniforms. */
+      for (unsigned i = 0; i < uniforms; i++) {
+         if (stage_prog_data->param[i] ==
+             &prog->Parameters->ParameterValues[index][0].f) {
+            scale_x = fs_reg(UNIFORM, i);
+            scale_y = fs_reg(UNIFORM, i + 1);
+            break;
+         }
+      }
+
+      /* If we didn't already set them up, do so now. */
+      if (scale_x.file == BAD_FILE) {
+         scale_x = fs_reg(UNIFORM, uniforms);
+         scale_y = fs_reg(UNIFORM, uniforms + 1);
+
+         stage_prog_data->param[uniforms++] =
+            &prog->Parameters->ParameterValues[index][0].f;
+         stage_prog_data->param[uniforms++] =
+            &prog->Parameters->ParameterValues[index][1].f;
+      }
   }

   /* The 965 requires the EU to do the normalization of GL rectangle
--- a/src/mesa/drivers/dri/i965/brw_meta_stencil_blit.c
+++ b/src/mesa/drivers/dri/i965/brw_meta_stencil_blit.c
@@ -272,28 +272,30 @@ setup_coord_transform(GLuint prog, const struct blit_dims *dims)
 }

 static GLuint
-setup_program(struct gl_context *ctx, bool msaa_tex)
+setup_program(struct brw_context *brw, bool msaa_tex)
 {
+   struct gl_context *ctx = &brw->ctx;
   struct blit_state *blit = &ctx->Meta->Blit;
-   static GLuint prog_cache[] = { 0, 0 };
   const char *fs_source;
   const struct sampler_and_fetch *sampler = &samplers[msaa_tex];

   _mesa_meta_setup_vertex_objects(&blit->VAO, &blit->VBO, true, 2, 2, 0);

-   if (prog_cache[msaa_tex]) {
-      _mesa_UseProgram(prog_cache[msaa_tex]);
-      return prog_cache[msaa_tex];
+   GLuint *prog_id = &brw->meta_stencil_blit_programs[msaa_tex];
+
+   if (*prog_id) {
+      _mesa_UseProgram(*prog_id);
+      return *prog_id;
   }
  
   fs_source = ralloc_asprintf(NULL, fs_tmpl, sampler->sampler,
                               sampler->fetch);
   _mesa_meta_compile_and_link_program(ctx, vs_source, fs_source,
                                       "i965 stencil blit",
-                                       &prog_cache[msaa_tex]);
+                                       prog_id);
   ralloc_free(fs_source);

-   return prog_cache[msaa_tex];
+   return *prog_id;
 }

 /**
@@ -391,6 +393,7 @@ set_read_rb_tex_image(struct gl_context *ctx, struct fb_tex_blit_state *blit,

   blit->baseLevelSave = tex_obj->BaseLevel;
   blit->maxLevelSave = tex_obj->MaxLevel;
+   blit->stencilSamplingSave = tex_obj->StencilSampling;
   blit->sampler = _mesa_meta_setup_sampler(ctx, tex_obj, *target,
                                            GL_NEAREST, level);
 }
@@ -426,7 +429,7 @@ brw_meta_stencil_blit(struct brw_context *brw,
   _mesa_TexParameteri(target, GL_DEPTH_STENCIL_TEXTURE_MODE,
                       GL_STENCIL_INDEX);

-   prog = setup_program(ctx, target != GL_TEXTURE_2D);
+   prog = setup_program(brw, target != GL_TEXTURE_2D);
   setup_bounding_rect(prog, orig_dims);
   setup_drawing_rect(prog, &dims);
   setup_coord_transform(prog, orig_dims);
--- a/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp
+++ b/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp
@@ -870,8 +870,7 @@ fs_instruction_scheduler::calculate_deps()
      } else if (inst->dst.is_accumulator() && gen6plus) {
         add_dep(last_accumulator_write, n);
         last_accumulator_write = n;
-      } else if (inst->dst.file != BAD_FILE &&
-                 !inst->dst.is_null()) {
+      } else if (inst->dst.file != BAD_FILE) {
 	 add_barrier_deps(n);
      }

@@ -998,8 +997,7 @@ fs_instruction_scheduler::calculate_deps()
         }
      } else if (inst->dst.is_accumulator() && gen6plus) {
         last_accumulator_write = n;
-      } else if (inst->dst.file != BAD_FILE &&
-                 !inst->dst.is_null()) {
+      } else if (inst->dst.file != BAD_FILE) {
 	 add_barrier_deps(n);
      }

@@ -1115,8 +1113,7 @@ vec4_instruction_scheduler::calculate_deps()
      } else if (inst->dst.is_accumulator() && gen6plus) {
         add_dep(last_accumulator_write, n);
         last_accumulator_write = n;
-      } else if (inst->dst.file != BAD_FILE &&
-                 !inst->dst.is_null()) {
+      } else if (inst->dst.file != BAD_FILE) {
         add_barrier_deps(n);
      }

@@ -1208,8 +1205,7 @@ vec4_instruction_scheduler::calculate_deps()
         last_fixed_grf_write = n;
      } else if (inst->dst.is_accumulator() && gen6plus) {
         last_accumulator_write = n;
-      } else if (inst->dst.file != BAD_FILE &&
-                 !inst->dst.is_null()) {
+      } else if (inst->dst.file != BAD_FILE) {
         add_barrier_deps(n);
      }

--- a/src/mesa/drivers/dri/i965/brw_state.h
+++ b/src/mesa/drivers/dri/i965/brw_state.h
@@ -243,7 +243,8 @@ void gen7_upload_3dstate_so_decl_list(struct brw_context *brw,
 void gen8_init_vtable_surface_functions(struct brw_context *brw);

 /* brw_wm_sampler_state.c */
-uint32_t translate_wrap_mode(GLenum wrap, bool using_nearest);
+uint32_t translate_wrap_mode(struct brw_context *brw,
+                             GLenum wrap, bool using_nearest);
 void upload_default_color(struct brw_context *brw,
 			  struct gl_sampler_object *sampler,
 			  int unit,
--- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
@@ -464,7 +464,8 @@ vec4_visitor::dead_code_eliminate()
         }

         if (inst->dst.file == scan_inst->dst.file &&
-             inst->dst.reg == scan_inst->dst.reg) {
+             inst->dst.reg == scan_inst->dst.reg &&
+             inst->dst.reg_offset == scan_inst->dst.reg_offset) {
            int new_writemask = scan_inst->dst.writemask & ~dead_channels;

            progress = try_eliminate_instruction(scan_inst, new_writemask, brw) ||
--- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
@@ -1171,13 +1171,17 @@ vec4_visitor::emit_lrp(const dst_reg &dst,
      /* Earlier generations don't support three source operations, so we
       * need to emit x*(1-a) + y*a.
       */
-      dst_reg one_minus_a   = dst_reg(this, glsl_type::vec4_type);
-      one_minus_a.writemask = dst.writemask;
+      dst_reg y_times_a           = dst_reg(this, glsl_type::vec4_type);
+      dst_reg one_minus_a         = dst_reg(this, glsl_type::vec4_type);
+      dst_reg x_times_one_minus_a = dst_reg(this, glsl_type::vec4_type);
+      y_times_a.writemask           = dst.writemask;
+      one_minus_a.writemask         = dst.writemask;
+      x_times_one_minus_a.writemask = dst.writemask;

+      emit(MUL(y_times_a, y, a));
      emit(ADD(one_minus_a, negate(a), src_reg(1.0f)));
-      vec4_instruction *mul = emit(MUL(dst_null_f(), y, a));
-      mul->writes_accumulator = true;
-      emit(MAC(dst, x, src_reg(one_minus_a)));
+      emit(MUL(x_times_one_minus_a, x, src_reg(one_minus_a)));
+      emit(ADD(dst, src_reg(x_times_one_minus_a), src_reg(y_times_a)));
   }
 }

--- a/src/mesa/drivers/dri/i965/brw_wm.c
+++ b/src/mesa/drivers/dri/i965/brw_wm.c
@@ -352,7 +352,8 @@ brw_populate_sampler_prog_key_data(struct gl_context *ctx,
         if (alpha_depth || (brw->gen < 8 && !brw->is_haswell))
            key->swizzles[s] = brw_get_texture_swizzle(ctx, t);

-	 if (sampler->MinFilter != GL_NEAREST &&
+	 if (brw->gen < 8 &&
+             sampler->MinFilter != GL_NEAREST &&
 	     sampler->MagFilter != GL_NEAREST) {
 	    if (sampler->WrapS == GL_CLAMP)
 	       key->gl_clamp_mask[0] |= 1 << s;
--- a/src/mesa/drivers/dri/i965/brw_wm_sampler_state.c
+++ b/src/mesa/drivers/dri/i965/brw_wm_sampler_state.c
@@ -46,7 +46,7 @@


 uint32_t
-translate_wrap_mode(GLenum wrap, bool using_nearest)
+translate_wrap_mode(struct brw_context *brw, GLenum wrap, bool using_nearest)
 {
   switch( wrap ) {
   case GL_REPEAT:
@@ -55,9 +55,16 @@ translate_wrap_mode(GLenum wrap, bool using_nearest)
      /* GL_CLAMP is the weird mode where coordinates are clamped to
       * [0.0, 1.0], so linear filtering of coordinates outside of
       * [0.0, 1.0] give you half edge texel value and half border
-       * color.  The fragment shader will clamp the coordinates, and
-       * we set clamp_border here, which gets the result desired.  We
-       * just use clamp(_to_edge) for nearest, because for nearest
+       * color.
+       *
+       * Gen8+ supports this natively.
+       */
+      if (brw->gen >= 8)
+         return GEN8_TEXCOORDMODE_HALF_BORDER;
+
+      /* On Gen4-7.5, we clamp the coordinates in the fragment shader
+       * and set clamp_border here, which gets the result desired.
+       * We just use clamp(_to_edge) for nearest, because for nearest
       * clamping to 1.0 gives border color instead of the desired
       * edge texels.
       */
@@ -276,11 +283,11 @@ static void brw_update_sampler_state(struct brw_context *brw,
      }
   }

-   sampler->ss1.r_wrap_mode = translate_wrap_mode(gl_sampler->WrapR,
+   sampler->ss1.r_wrap_mode = translate_wrap_mode(brw, gl_sampler->WrapR,
 						  using_nearest);
-   sampler->ss1.s_wrap_mode = translate_wrap_mode(gl_sampler->WrapS,
+   sampler->ss1.s_wrap_mode = translate_wrap_mode(brw, gl_sampler->WrapS,
 						  using_nearest);
-   sampler->ss1.t_wrap_mode = translate_wrap_mode(gl_sampler->WrapT,
+   sampler->ss1.t_wrap_mode = translate_wrap_mode(brw, gl_sampler->WrapT,
 						  using_nearest);

   if (brw->gen >= 6 &&
--- a/src/mesa/drivers/dri/i965/gen6_clip_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_clip_state.c
@@ -106,7 +106,7 @@ upload_clip_state(struct brw_context *brw)
         dw2 &= ~GEN6_CLIP_GB_TEST;
         if (brw->gen >= 8) {
            perf_debug("Disabling GB clipping due to lack of Gen8 viewport "
-                       "clipping setup code.  This should be fixed.");
+                       "clipping setup code.  This should be fixed.\n");
         }
         break;
      }
@@ -116,7 +116,7 @@ upload_clip_state(struct brw_context *brw)
   if (ctx->RasterDiscard) {
      dw2 |= GEN6_CLIP_MODE_REJECT_ALL;
      perf_debug("Rasterizer discard is currently implemented via the clipper; "
-                 "%s be faster.", brw->gen >= 7 ? "using the SOL unit may" :
+                 "%s be faster.\n", brw->gen >= 7 ? "using the SOL unit may" :
                 "having the GS not write primitives would likely");
   }

--- a/src/mesa/drivers/dri/i965/gen7_sampler_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sampler_state.c
@@ -103,11 +103,11 @@ gen7_update_sampler_state(struct brw_context *brw, int unit, int ss_index,
      }
   }

-   sampler->ss3.r_wrap_mode = translate_wrap_mode(gl_sampler->WrapR,
+   sampler->ss3.r_wrap_mode = translate_wrap_mode(brw, gl_sampler->WrapR,
 						  using_nearest);
-   sampler->ss3.s_wrap_mode = translate_wrap_mode(gl_sampler->WrapS,
+   sampler->ss3.s_wrap_mode = translate_wrap_mode(brw, gl_sampler->WrapS,
 						  using_nearest);
-   sampler->ss3.t_wrap_mode = translate_wrap_mode(gl_sampler->WrapT,
+   sampler->ss3.t_wrap_mode = translate_wrap_mode(brw, gl_sampler->WrapT,
 						  using_nearest);

   /* Cube-maps on 965 and later must use the same wrap mode for all 3
--- a/src/mesa/drivers/dri/i965/gen7_wm_surface_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_wm_surface_state.c
@@ -337,6 +337,8 @@ gen7_update_texture_surface(struct gl_context *ctx,
              /* mip count */
              (intelObj->_MaxLevel - tObj->BaseLevel));

+   surf[7] = mt->fast_clear_color_value;
+
   if (brw->is_haswell) {
      /* Handling GL_ALPHA as a surface format override breaks 1.30+ style
       * texturing functions that return a float, as our code generation always
@@ -351,7 +353,7 @@ gen7_update_texture_surface(struct gl_context *ctx,

      const bool need_scs_green_to_blue = for_gather && tex_format == BRW_SURFACEFORMAT_R32G32_FLOAT_LD;

-      surf[7] =
+      surf[7] |=
         SET_FIELD(brw_swizzle_to_scs(GET_SWZ(swizzle, 0), need_scs_green_to_blue), GEN7_SURFACE_SCS_R) |
         SET_FIELD(brw_swizzle_to_scs(GET_SWZ(swizzle, 1), need_scs_green_to_blue), GEN7_SURFACE_SCS_G) |
         SET_FIELD(brw_swizzle_to_scs(GET_SWZ(swizzle, 2), need_scs_green_to_blue), GEN7_SURFACE_SCS_B) |
--- a/src/mesa/drivers/dri/i965/gen8_depth_state.c
+++ b/src/mesa/drivers/dri/i965/gen8_depth_state.c
@@ -225,6 +225,13 @@ gen8_hiz_exec(struct brw_context *brw, struct intel_mipmap_tree *mt,
   assert(mt->first_level == 0);
   assert(mt->logical_depth0 >= 1);

+   /* If we're operating on LOD 0, align to 8x4 to meet the alignment
+    * requirements for most HiZ operations.  Otherwise, use the actual size
+    * to allow the hardware to calculate the miplevel offsets correctly.
+    */
+   uint32_t surface_width  = ALIGN(mt->logical_width0,  level == 0 ? 8 : 1);
+   uint32_t surface_height = ALIGN(mt->logical_height0, level == 0 ? 4 : 1);
+
   /* The basic algorithm is:
    * - If needed, emit 3DSTATE_{DEPTH,HIER_DEPTH,STENCIL}_BUFFER and
    *   3DSTATE_CLEAR_PARAMS packets to set up the relevant buffers.
@@ -239,14 +246,19 @@ gen8_hiz_exec(struct brw_context *brw, struct intel_mipmap_tree *mt,
                      true, /* depth writes */
                      NULL, false, 0, /* no stencil for now */
                      true, /* hiz */
-                      mt->logical_width0,
-                      mt->logical_height0,
+                      surface_width,
+                      surface_height,
                      mt->logical_depth0,
                      level,
                      layer); /* min_array_element */

-   unsigned rect_width = minify(mt->logical_width0, level);
-   unsigned rect_height = minify(mt->logical_height0, level);
+   /* Depth buffer clears and HiZ resolves must use an 8x4 aligned rectangle.
+    * Note that intel_miptree_level_enable_hiz disables HiZ for miplevels > 0
+    * which aren't 8x4 aligned, so expanding the size is safe - it'll just
+    * draw into empty padding space.
+    */
+   unsigned rect_width = ALIGN(minify(mt->logical_width0, level), 8);
+   unsigned rect_height = ALIGN(minify(mt->logical_height0, level), 4);

   BEGIN_BATCH(4);
   OUT_BATCH(_3DSTATE_DRAWING_RECTANGLE << 16 | (4 - 2));
--- a/src/mesa/drivers/dri/i965/gen8_draw_upload.c
+++ b/src/mesa/drivers/dri/i965/gen8_draw_upload.c
@@ -94,8 +94,6 @@ gen8_emit_vertices(struct brw_context *brw)
   if (brw->vb.nr_buffers) {
      assert(brw->vb.nr_buffers <= 33);

-      perf_debug("Missing MOCS setup for 3DSTATE_VERTEX_BUFFERS.");
-
      BEGIN_BATCH(1 + 4*brw->vb.nr_buffers);
      OUT_BATCH((_3DSTATE_VERTEX_BUFFERS << 16) | (4*brw->vb.nr_buffers - 1));
      for (unsigned i = 0; i < brw->vb.nr_buffers; i++) {
@@ -213,11 +211,9 @@ gen8_emit_index_buffer(struct brw_context *brw)
   if (index_buffer == NULL)
      return;

-   perf_debug("Missing MOCS setup for 3DSTATE_INDEX_BUFFER.");
-
   BEGIN_BATCH(5);
   OUT_BATCH(CMD_INDEX_BUFFER << 16 | (5 - 2));
-   OUT_BATCH(brw_get_index_type(index_buffer->type) << 8);
+   OUT_BATCH(brw_get_index_type(index_buffer->type) << 8 | BDW_MOCS_WB);
   OUT_RELOC64(brw->ib.bo, I915_GEM_DOMAIN_VERTEX, 0, 0);
   OUT_BATCH(brw->ib.bo->size);
   ADVANCE_BATCH();
--- a/src/mesa/drivers/dri/i965/gen8_misc_state.c
+++ b/src/mesa/drivers/dri/i965/gen8_misc_state.c
@@ -31,8 +31,6 @@
 */
 static void upload_state_base_address(struct brw_context *brw)
 {
-   perf_debug("Missing MOCS setup for STATE_BASE_ADDRESS.");
-
   BEGIN_BATCH(16);
   OUT_BATCH(CMD_STATE_BASE_ADDRESS << 16 | (16 - 2));
   /* General state base address: stateless DP read/write requests */
--- a/src/mesa/drivers/dri/i965/gen8_surface_state.c
+++ b/src/mesa/drivers/dri/i965/gen8_surface_state.c
@@ -207,9 +207,11 @@ gen8_update_texture_surface(struct gl_context *ctx,
      (firstImage->_BaseFormat == GL_DEPTH_COMPONENT ||
       firstImage->_BaseFormat == GL_DEPTH_STENCIL);

+   surf[7] = mt->fast_clear_color_value;
+
   const int swizzle =
      unlikely(alpha_depth) ? SWIZZLE_XYZW : brw_get_texture_swizzle(ctx, tObj);
-   surf[7] =
+   surf[7] |=
      SET_FIELD(brw_swizzle_to_scs(GET_SWZ(swizzle, 0), false), GEN7_SURFACE_SCS_R) |
      SET_FIELD(brw_swizzle_to_scs(GET_SWZ(swizzle, 1), false), GEN7_SURFACE_SCS_G) |
      SET_FIELD(brw_swizzle_to_scs(GET_SWZ(swizzle, 2), false), GEN7_SURFACE_SCS_B) |
--- a/src/mesa/drivers/dri/i965/gen8_vec4_generator.cpp
+++ b/src/mesa/drivers/dri/i965/gen8_vec4_generator.cpp
@@ -443,14 +443,14 @@ gen8_vec4_generator::generate_pull_constant_load(vec4_instruction *inst,
   gen8_instruction *send = next_inst(BRW_OPCODE_SEND);
   gen8_set_dst(brw, send, dst);
   gen8_set_src0(brw, send, offset);
-   gen8_set_dp_message(brw, send, GEN7_SFID_DATAPORT_DATA_CACHE,
-                       surf_index,
-                       GEN6_DATAPORT_READ_MESSAGE_OWORD_DUAL_BLOCK_READ,
-                       0,      /* message control */
-                       1,      /* mlen */
-                       1,      /* rlen */
-                       false,  /* no header */
-                       false); /* EOT */
+   gen8_set_sampler_message(brw, send,
+                            surf_index,
+                            0, /* The LD message ignores the sampler unit. */
+                            GEN5_SAMPLER_MESSAGE_SAMPLE_LD,
+                            1,      /* rlen */
+                            1,      /* mlen */
+                            false,  /* no header */
+                            BRW_SAMPLER_SIMD_MODE_SIMD4X2);

   brw_mark_surface_used(&prog_data->base, surf_index);
 }
--- a/src/mesa/main/clear.c
+++ b/src/mesa/main/clear.c
@@ -180,11 +180,6 @@ _mesa_Clear( GLbitfield mask )
      return;
   }

-   if (ctx->DrawBuffer->Width == 0 || ctx->DrawBuffer->Height == 0 ||
-       ctx->DrawBuffer->_Xmin >= ctx->DrawBuffer->_Xmax ||
-       ctx->DrawBuffer->_Ymin >= ctx->DrawBuffer->_Ymax)
-      return;
-
   if (ctx->RasterDiscard)
      return;

--- a/src/mesa/main/get.c
+++ b/src/mesa/main/get.c
@@ -847,6 +847,16 @@ find_custom_value(struct gl_context *ctx, const struct value_desc *d, union valu
      v->value_int = ctx->Array.VAO->IndexBufferObj->Name;
      break;

+   /* ARB_vertex_array_bgra */
+   case GL_COLOR_ARRAY_SIZE:
+      array = &ctx->Array.VAO->VertexAttrib[VERT_ATTRIB_COLOR0];
+      v->value_int = array->Format == GL_BGRA ? GL_BGRA : array->Size;
+      break;
+   case GL_SECONDARY_COLOR_ARRAY_SIZE:
+      array = &ctx->Array.VAO->VertexAttrib[VERT_ATTRIB_COLOR1];
+      v->value_int = array->Format == GL_BGRA ? GL_BGRA : array->Size;
+      break;
+
   /* ARB_copy_buffer */
   case GL_COPY_READ_BUFFER:
      v->value_int = ctx->CopyReadBuffer->Name;
@@ -995,7 +1005,11 @@ find_custom_value(struct gl_context *ctx, const struct value_desc *d, union valu
      break;
   /* GL_ARB_shader_atomic_counters */
   case GL_ATOMIC_COUNTER_BUFFER_BINDING:
-      v->value_int = ctx->AtomicBuffer->Name;
+      if (ctx->AtomicBuffer) {
+         v->value_int = ctx->AtomicBuffer->Name;
+      } else {
+         v->value_int = 0;
+      }
      break;
   /* GL_ARB_draw_indirect */
   case GL_DRAW_INDIRECT_BUFFER_BINDING:
--- a/src/mesa/main/get_hash_generator.py
+++ b/src/mesa/main/get_hash_generator.py
@@ -52,7 +52,7 @@ def print_header():
          (prime_factor, prime_step)

 def print_params(params):
-   print "static struct value_desc values[] = {"
+   print "static const struct value_desc values[] = {"
   for p in params:
      print "    { %s, %s }," % (p[0], p[1])

--- a/src/mesa/main/get_hash_params.py
+++ b/src/mesa/main/get_hash_params.py
@@ -199,7 +199,7 @@ descriptor=[
  [ "NORMAL_ARRAY_TYPE", "ARRAY_ENUM(VertexAttrib[VERT_ATTRIB_NORMAL].Type), NO_EXTRA" ],
  [ "NORMAL_ARRAY_STRIDE", "ARRAY_INT(VertexAttrib[VERT_ATTRIB_NORMAL].Stride), NO_EXTRA" ],
  [ "COLOR_ARRAY", "ARRAY_BOOL(VertexAttrib[VERT_ATTRIB_COLOR0].Enabled), NO_EXTRA" ],
-  [ "COLOR_ARRAY_SIZE", "ARRAY_INT(VertexAttrib[VERT_ATTRIB_COLOR0].Size), NO_EXTRA" ],
+  [ "COLOR_ARRAY_SIZE", "LOC_CUSTOM, TYPE_INT, 0, NO_EXTRA" ],
  [ "COLOR_ARRAY_TYPE", "ARRAY_ENUM(VertexAttrib[VERT_ATTRIB_COLOR0].Type), NO_EXTRA" ],
  [ "COLOR_ARRAY_STRIDE", "ARRAY_INT(VertexAttrib[VERT_ATTRIB_COLOR0].Stride), NO_EXTRA" ],
  [ "TEXTURE_COORD_ARRAY", "LOC_CUSTOM, TYPE_BOOLEAN, offsetof(struct gl_client_array, Enabled), NO_EXTRA" ],
@@ -552,7 +552,7 @@ descriptor=[
  [ "SECONDARY_COLOR_ARRAY", "ARRAY_BOOL(VertexAttrib[VERT_ATTRIB_COLOR1].Enabled), NO_EXTRA" ],
  [ "SECONDARY_COLOR_ARRAY_TYPE", "ARRAY_ENUM(VertexAttrib[VERT_ATTRIB_COLOR1].Type), NO_EXTRA" ],
  [ "SECONDARY_COLOR_ARRAY_STRIDE", "ARRAY_INT(VertexAttrib[VERT_ATTRIB_COLOR1].Stride), NO_EXTRA" ],
-  [ "SECONDARY_COLOR_ARRAY_SIZE", "ARRAY_INT(VertexAttrib[VERT_ATTRIB_COLOR1].Size), NO_EXTRA" ],
+  [ "SECONDARY_COLOR_ARRAY_SIZE", "LOC_CUSTOM, TYPE_INT, 0, NO_EXTRA" ],

 # GL_EXT_fog_coord
  [ "CURRENT_FOG_COORDINATE", "CONTEXT_FLOAT(Current.Attrib[VERT_ATTRIB_FOG][0]), extra_flush_current" ],
--- a/src/mesa/program/program.c
+++ b/src/mesa/program/program.c
@@ -552,6 +552,7 @@ _mesa_clone_program(struct gl_context *ctx, const struct gl_program *prog)
         gpc->InputType = gp->InputType;
         gpc->Invocations = gp->Invocations;
         gpc->OutputType = gp->OutputType;
+         gpc->UsesEndPrimitive = gp->UsesEndPrimitive;
      }
      break;
   default:
--- a/src/mesa/state_tracker/st_program.c
+++ b/src/mesa/state_tracker/st_program.c
@@ -679,32 +679,36 @@ st_translate_fragment_program(struct st_context *st,
         outputsWritten &= ~(1 << FRAG_RESULT_STENCIL);
      }

+      if (outputsWritten & BITFIELD64_BIT(FRAG_RESULT_SAMPLE_MASK)) {
+         fs_output_semantic_name[fs_num_outputs] = TGSI_SEMANTIC_SAMPLEMASK;
+         fs_output_semantic_index[fs_num_outputs] = 0;
+         outputMapping[FRAG_RESULT_SAMPLE_MASK] = fs_num_outputs;
+         fs_num_outputs++;
+         outputsWritten &= ~(1 << FRAG_RESULT_SAMPLE_MASK);
+      }
+
      /* handle remaining outputs (color) */
      for (attr = 0; attr < FRAG_RESULT_MAX; attr++) {
         if (outputsWritten & BITFIELD64_BIT(attr)) {
-            int semantic = TGSI_SEMANTIC_COLOR;
            switch (attr) {
            case FRAG_RESULT_DEPTH:
            case FRAG_RESULT_STENCIL:
+            case FRAG_RESULT_SAMPLE_MASK:
               /* handled above */
               assert(0);
               break;
            case FRAG_RESULT_COLOR:
-               write_all = GL_TRUE;
-               break;
-            case FRAG_RESULT_SAMPLE_MASK:
-               semantic = TGSI_SEMANTIC_SAMPLEMASK;
+               write_all = GL_TRUE; /* fallthrough */
+            default:
+               assert(attr == FRAG_RESULT_COLOR ||
+                      (FRAG_RESULT_DATA0 <= attr && attr < FRAG_RESULT_MAX));
+               fs_output_semantic_name[fs_num_outputs] = TGSI_SEMANTIC_COLOR;
+               fs_output_semantic_index[fs_num_outputs] = numColors;
+               outputMapping[attr] = fs_num_outputs;
+               numColors++;
               break;
            }

-            assert(attr == FRAG_RESULT_COLOR ||
-                   attr == FRAG_RESULT_SAMPLE_MASK ||
-                   (FRAG_RESULT_DATA0 <= attr && attr < FRAG_RESULT_MAX));
-            fs_output_semantic_name[fs_num_outputs] = semantic;
-            fs_output_semantic_index[fs_num_outputs] = numColors;
-            outputMapping[attr] = fs_num_outputs;
-            numColors++;
-
            fs_num_outputs++;
         }
      }