Merge remote-tracking branch 'origin/released'

* origin/released:
  mesa xkbcomp git update 19 Jul 2013

28 files changed, 965 insertions, 344 deletions

diff --git a/mesalib/configure.ac b/mesalib/configure.ac
index 0026613cc..35f6797ee 100644
--- a/mesalib/configure.ac
+++ b/mesalib/configure.ac
@@ -100,6 +100,7 @@ AC_MSG_RESULT([$acv_mesa_CLANG])
 
 dnl If we're using GCC, make sure that it is at least version 3.3.0.  Older
 dnl versions are explictly not supported.
+GEN_ASM_OFFSETS=no
 if test "x$GCC" = xyes -a "x$acv_mesa_CLANG" = xno; then
     AC_MSG_CHECKING([whether gcc version is sufficient])
     major=0
@@ -117,7 +118,12 @@ if test "x$GCC" = xyes -a "x$acv_mesa_CLANG" = xno; then
     else
         AC_MSG_RESULT([yes])
     fi
+
+    if test "x$cross_compiling" = xyes; then
+        GEN_ASM_OFFSETS=yes
+    fi
 fi
+AM_CONDITIONAL([GEN_ASM_OFFSETS], test "x$GEN_ASM_OFFSETS" = xyes)
 
 dnl Make sure the pkg-config macros are defined
 m4_ifndef([PKG_PROG_PKG_CONFIG],
@@ -438,7 +444,7 @@ test "x$enable_asm" = xno && AC_MSG_RESULT([no])
 # disable if cross compiling on x86/x86_64 since we must run gen_matypes
 if test "x$enable_asm" = xyes && test "x$cross_compiling" = xyes; then
     case "$host_cpu" in
-    i?86 | x86_64)
+    i?86 | x86_64 | amd64)
         enable_asm=no
         AC_MSG_RESULT([no, cross compiling])
         ;;
@@ -449,7 +455,7 @@ if test "x$enable_asm" = xyes; then
     case "$host_cpu" in
     i?86)
         case "$host_os" in
-        linux* | *freebsd* | dragonfly* | *netbsd*)
+        linux* | *freebsd* | dragonfly* | *netbsd* | openbsd*)
             test "x$enable_64bit" = xyes && asm_arch=x86_64 || asm_arch=x86
             ;;
         gnu*)
@@ -457,9 +463,9 @@ if test "x$enable_asm" = xyes; then
             ;;
         esac
         ;;
-    x86_64)
+    x86_64|amd64)
         case "$host_os" in
-        linux* | *freebsd* | dragonfly* | *netbsd*)
+        linux* | *freebsd* | dragonfly* | *netbsd* | openbsd*)
             test "x$enable_32bit" = xyes && asm_arch=x86 || asm_arch=x86_64
             ;;
         esac
@@ -478,7 +484,7 @@ if test "x$enable_asm" = xyes; then
         DEFINES="$DEFINES -DUSE_X86_ASM -DUSE_MMX_ASM -DUSE_3DNOW_ASM -DUSE_SSE_ASM"
         AC_MSG_RESULT([yes, x86])
         ;;
-    x86_64)
+    x86_64|amd64)
         DEFINES="$DEFINES -DUSE_X86_64_ASM"
         AC_MSG_RESULT([yes, x86_64])
         ;;
@@ -966,7 +972,7 @@ if test "x$enable_dri" = xyes; then
         DEFINES="$DEFINES -DHAVE_ALIAS"
 
         case "$host_cpu" in
-        x86_64)
+        x86_64|amd64)
             if test "x$DRI_DIRS" = "xyes"; then
                 DRI_DIRS="i915 i965 nouveau r200 radeon swrast"
             fi
@@ -985,7 +991,7 @@ if test "x$enable_dri" = xyes; then
             ;;
         esac
         ;;
-    freebsd* | dragonfly* | *netbsd*)
+    freebsd* | dragonfly* | *netbsd* | openbsd*)
         DEFINES="$DEFINES -DHAVE_PTHREAD -DUSE_EXTERNAL_DXTN_LIB=1"
         DEFINES="$DEFINES -DHAVE_ALIAS"
 
@@ -1573,7 +1579,7 @@ if test "x$with_gallium_drivers" = x; then
 fi
 if test "x$enable_gallium_llvm" = xauto; then
     case "$host_cpu" in
-    i*86|x86_64) enable_gallium_llvm=yes;;
+    i*86|x86_64|amd64) enable_gallium_llvm=yes;;
     esac
 fi
 if test "x$enable_gallium_llvm" = xyes; then
@@ -1605,14 +1611,14 @@ if test "x$enable_gallium_llvm" = xyes; then
         fi
 
         LLVM_COMPONENTS="engine bitwriter"
-        if $LLVM_CONFIG --components | grep -q '\<mcjit\>'; then
+        if $LLVM_CONFIG --components | grep -qw 'mcjit'; then
             LLVM_COMPONENTS="${LLVM_COMPONENTS} mcjit"
         fi
 
         if test "x$enable_opencl" = xyes; then
             LLVM_COMPONENTS="${LLVM_COMPONENTS} ipo linker instrumentation"
             # LLVM 3.3 >= 177971 requires IRReader
-            if $LLVM_CONFIG --components | grep -q '\<irreader\>'; then
+            if $LLVM_CONFIG --components | grep -qw 'irreader'; then
                 LLVM_COMPONENTS="${LLVM_COMPONENTS} irreader"
             fi
         fi
@@ -1705,7 +1711,7 @@ gallium_check_st() {
 gallium_require_llvm() {
     if test "x$MESA_LLVM" = x0; then
         case "$host_cpu" in
-        i*86|x86_64) AC_MSG_ERROR([LLVM is required to build $1 on x86 and x86_64]);;
+        i*86|x86_64|amd64) AC_MSG_ERROR([LLVM is required to build $1 on x86 and x86_64]);;
         esac
     fi
 }
@@ -1727,7 +1733,7 @@ radeon_llvm_check() {
     if test "$LLVM_VERSION_INT" -lt "${LLVM_REQUIRED_VERSION_MAJOR}0${LLVM_REQUIRED_VERSION_MINOR}"; then
         AC_MSG_ERROR([LLVM $LLVM_REQUIRED_VERSION_MAJOR.$LLVM_REQUIRED_VERSION_MINOR or newer is required for r600g and radeonsi.])
     fi
-    if test true && $LLVM_CONFIG --targets-built | grep -qv '\<R600\>' ; then
+    if test true && $LLVM_CONFIG --targets-built | grep -qvw 'R600' ; then
         AC_MSG_ERROR([LLVM R600 Target not enabled.  You can enable it when building the LLVM
                       sources with the --enable-experimental-targets=R600
                       configure flag])
diff --git a/mesalib/docs/index.html b/mesalib/docs/index.html
index d85081d50..f0c51703f 100644
--- a/mesalib/docs/index.html
+++ b/mesalib/docs/index.html
@@ -16,6 +16,12 @@
 
 <h1>News</h1>
 
+<h2>July 17, 2013</h2>
+<p>
+<a href="relnotes/9.1.5.html">Mesa 9.1.5</a> is released.
+This is a bug fix release.
+</p>
+
 <h2>July 1, 2013</h2>
 <p>
 <a href="relnotes/9.1.4.html">Mesa 9.1.4</a> is released.
diff --git a/mesalib/docs/relnotes.html b/mesalib/docs/relnotes.html
index bc5ad3c20..3d391c061 100644
--- a/mesalib/docs/relnotes.html
+++ b/mesalib/docs/relnotes.html
@@ -22,6 +22,7 @@ The release notes summarize what's new or changed in each Mesa release.
 
 <ul>
 <li><a href="relnotes/9.2.html">9.2 release notes</a>
+<li><a href="relnotes/9.1.5.html">9.1.5 release notes</a>
 <li><a href="relnotes/9.1.4.html">9.1.4 release notes</a>
 <li><a href="relnotes/9.1.3.html">9.1.3 release notes</a>
 <li><a href="relnotes/9.1.2.html">9.1.2 release notes</a>
diff --git a/mesalib/docs/relnotes/9.1.5.html b/mesalib/docs/relnotes/9.1.5.html
new file mode 100644
index 000000000..fcc47c4f4
--- /dev/null
+++ b/mesalib/docs/relnotes/9.1.5.html
@@ -0,0 +1,138 @@
+<!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 9.1.5 Release Notes / July 17, 2013</h1>
+
+<p>
+Mesa 9.1.5 is a bug fix release which fixes bugs found since the 9.1.4 release.
+</p>
+<p>
+Mesa 9.1 implements the OpenGL 3.1 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 3.1.  OpenGL
+3.1 is <strong>only</strong> available if requested at context creation
+because GL_ARB_compatibility is not supported.
+</p>
+
+<h2>MD5 checksums</h2>
+<pre>
+TBD
+</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=58384">Bug 58384</a> - [i965 Bisected]Oglc max_values(advanced.fragmentProgram.GL_MAX_PROGRAM_ENV_PARAMETERS_ARB) segfault</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=62647">Bug 62647</a> - Wrong rendering of Dota 2 on Wine (apitrace attached) - Intel IVB HD4000</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=63674">Bug 63674</a> - [IVB]frozen at the first frame when run Unigine-heaven 4.0</li>
+
+<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=65910">Bug 65910</a> - Killing weston-launch causes segv in desktop-shell</li>
+
+</ul>
+
+<h2>Changes</h2>
+<p>The full set of changes can be viewed by using the following GIT command:</p>
+
+<pre>
+  git log mesa-9.1.4..mesa-9.1.5
+</pre>
+
+<p>Anuj Phogat (1):</p>
+<ul>
+  <li>mesa: Return ZeroVec/dummyReg instead of NULL pointer</li>
+</ul>
+
+<p>Brian Paul (1):</p>
+<ul>
+  <li>svga: check for NaN shader immediates</li>
+</ul>
+
+<p>Carl Worth (3):</p>
+<ul>
+  <li>cherry-ignore: Ignore previously backported patch</li>
+  <li>cherry-ignore: Drop two patches which we've decided not to include</li>
+  <li>mesa: Bump version to 9.1.5</li>
+</ul>
+
+<p>Chris Forbes (1):</p>
+<ul>
+  <li>i965: fix alpha test for MRT</li>
+</ul>
+
+<p>Christoph Bumiller (1):</p>
+<ul>
+  <li>r600g: x/y coordinates must be divided by block dim in dma blit</li>
+</ul>
+
+<p>Eric Anholt (1):</p>
+<ul>
+  <li>ra: Fix register spilling.</li>
+</ul>
+
+<p>Ian Romanick (6):</p>
+<ul>
+  <li>docs: Add 9.1.4 release md5sums</li>
+  <li>glsl: Add a gl_shader_program parameter to _mesa_uniform_{merge,split}_location_offset</li>
+  <li>glsl: Add gl_shader_program::UniformLocationBaseScale</li>
+  <li>glsl: Generate smaller values for uniform locations</li>
+  <li>i965: Be more careful with the interleaved user array upload optimization</li>
+  <li>glsl: Move all var decls to the front of the IR list in reverse order</li>
+</ul>
+
+<p>Kenneth Graunke (1):</p>
+<ul>
+  <li>glsl/builtins: Fix ARB_texture_cube_map_array built-in availability.</li>
+</ul>
+
+<p>Kristian Høgsberg (1):</p>
+<ul>
+  <li>wayland: Handle global_remove event as well</li>
+</ul>
+
+<p>Matt Turner (1):</p>
+<ul>
+  <li>register_allocate: Fix the type of best_benefit.</li>
+</ul>
+
+<p>Paul Berry (1):</p>
+<ul>
+  <li>glsl ES: Fix magnitude of gl_MaxVertexUniformVectors.</li>
+</ul>
+
+<p>Richard Sandiford (3):</p>
+<ul>
+  <li>st/xlib Fix XIMage bytes-per-pixel calculation</li>
+  <li>st/xlib: Fix XImage stride calculation</li>
+  <li>st/dri/sw: Fix pitch calculation in drisw_update_tex_buffer</li>
+</ul>
+
+<p>Vinson Lee (1):</p>
+<ul>
+  <li>swrast: Fix memory leak.</li>
+</ul>
+
+</div>
+</body>
+</html>
diff --git a/mesalib/include/GL/internal/dri_interface.h b/mesalib/include/GL/internal/dri_interface.h
index add2fe60c..279e9f003 100644
--- a/mesalib/include/GL/internal/dri_interface.h
+++ b/mesalib/include/GL/internal/dri_interface.h
@@ -556,6 +556,8 @@ struct __DRIuseInvalidateExtensionRec {
 #define __DRI_ATTRIB_RGBA_BIT			0x01	
 #define __DRI_ATTRIB_COLOR_INDEX_BIT		0x02
 #define __DRI_ATTRIB_LUMINANCE_BIT		0x04
+#define __DRI_ATTRIB_FLOAT_BIT			0x08
+#define __DRI_ATTRIB_UNSIGNED_FLOAT_BIT		0x10
 
 /* __DRI_ATTRIB_CONFIG_CAVEAT */
 #define __DRI_ATTRIB_SLOW_BIT			0x01
diff --git a/mesalib/m4/ax_prog_flex.m4 b/mesalib/m4/ax_prog_flex.m4
index 117f8fe67..82fbc30c3 100644
--- a/mesalib/m4/ax_prog_flex.m4
+++ b/mesalib/m4/ax_prog_flex.m4
@@ -53,7 +53,7 @@ AC_DEFUN([AX_PROG_FLEX], [
   AC_REQUIRE([AC_PROG_EGREP])
 
   AC_CACHE_CHECK([if flex is the lexer generator],[ax_cv_prog_flex],[
-    AS_IF([$LEX --version 2>/dev/null | $EGREP -q '^flex '],
+    AS_IF([$LEX --version 2>/dev/null | $EGREP -q '^\<flex\>'],
       [ax_cv_prog_flex=yes], [ax_cv_prog_flex=no])
   ])
   AS_IF([test "$ax_cv_prog_flex" = "yes"],
diff --git a/mesalib/src/gallium/auxiliary/util/u_format_s3tc.c b/mesalib/src/gallium/auxiliary/util/u_format_s3tc.c
index 35e3d3445..fd628157b 100644
--- a/mesalib/src/gallium/auxiliary/util/u_format_s3tc.c
+++ b/mesalib/src/gallium/auxiliary/util/u_format_s3tc.c
@@ -27,6 +27,7 @@
 #include "u_math.h"
 #include "u_format.h"
 #include "u_format_s3tc.h"
+#include "u_format_srgb.h"
 
 
 #if defined(_WIN32) || defined(WIN32)
@@ -247,7 +248,7 @@ util_format_dxtn_rgb_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
                                         const uint8_t *src_row, unsigned src_stride,
                                         unsigned width, unsigned height,
                                         util_format_dxtn_fetch_t fetch,
-                                        unsigned block_size)
+                                        unsigned block_size, boolean srgb)
 {
    const unsigned bw = 4, bh = 4, comps = 4;
    unsigned x, y, i, j;
@@ -258,6 +259,11 @@ util_format_dxtn_rgb_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
             for(i = 0; i < bw; ++i) {
                uint8_t *dst = dst_row + (y + j)*dst_stride/sizeof(*dst_row) + (x + i)*comps;
                fetch(0, src, i, j, dst);
+               if (srgb) {
+                  dst[0] = util_format_srgb_to_linear_8unorm(dst[0]);
+                  dst[1] = util_format_srgb_to_linear_8unorm(dst[1]);
+                  dst[2] = util_format_srgb_to_linear_8unorm(dst[2]);
+               }
             }
          }
          src += block_size;
@@ -274,7 +280,8 @@ util_format_dxt1_rgb_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
                                            src_row, src_stride,
                                            width, height,
-                                           util_format_dxt1_rgb_fetch, 8);
+                                           util_format_dxt1_rgb_fetch,
+                                           8, FALSE);
 }
 
 void
@@ -285,7 +292,8 @@ util_format_dxt1_rgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
                                            src_row, src_stride,
                                            width, height,
-                                           util_format_dxt1_rgba_fetch, 8);
+                                           util_format_dxt1_rgba_fetch,
+                                           8, FALSE);
 }
 
 void
@@ -296,7 +304,8 @@ util_format_dxt3_rgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
                                            src_row, src_stride,
                                            width, height,
-                                           util_format_dxt3_rgba_fetch, 16);
+                                           util_format_dxt3_rgba_fetch,
+                                           16, FALSE);
 }
 
 void
@@ -307,7 +316,8 @@ util_format_dxt5_rgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
                                            src_row, src_stride,
                                            width, height,
-                                           util_format_dxt5_rgba_fetch, 16);
+                                           util_format_dxt5_rgba_fetch,
+                                           16, FALSE);
 }
 
 static INLINE void
@@ -315,7 +325,7 @@ util_format_dxtn_rgb_unpack_rgba_float(float *dst_row, unsigned dst_stride,
                                        const uint8_t *src_row, unsigned src_stride,
                                        unsigned width, unsigned height,
                                        util_format_dxtn_fetch_t fetch,
-                                       unsigned block_size)
+                                       unsigned block_size, boolean srgb)
 {
    unsigned x, y, i, j;
    for(y = 0; y < height; y += 4) {
@@ -326,9 +336,16 @@ util_format_dxtn_rgb_unpack_rgba_float(float *dst_row, unsigned dst_stride,
                float *dst = dst_row + (y + j)*dst_stride/sizeof(*dst_row) + (x + i)*4;
                uint8_t tmp[4];
                fetch(0, src, i, j, tmp);
-               dst[0] = ubyte_to_float(tmp[0]);
-               dst[1] = ubyte_to_float(tmp[1]);
-               dst[2] = ubyte_to_float(tmp[2]);
+               if (srgb) {
+                  dst[0] = util_format_srgb_8unorm_to_linear_float(tmp[0]);
+                  dst[1] = util_format_srgb_8unorm_to_linear_float(tmp[1]);
+                  dst[2] = util_format_srgb_8unorm_to_linear_float(tmp[2]);
+               }
+               else {
+                  dst[0] = ubyte_to_float(tmp[0]);
+                  dst[1] = ubyte_to_float(tmp[1]);
+                  dst[2] = ubyte_to_float(tmp[2]);
+               }
                dst[3] = ubyte_to_float(tmp[3]);
             }
          }
@@ -346,7 +363,8 @@ util_format_dxt1_rgb_unpack_rgba_float(float *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
                                           src_row, src_stride,
                                           width, height,
-                                          util_format_dxt1_rgb_fetch, 8);
+                                          util_format_dxt1_rgb_fetch,
+                                          8, FALSE);
 }
 
 void
@@ -357,7 +375,8 @@ util_format_dxt1_rgba_unpack_rgba_float(float *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
                                           src_row, src_stride,
                                           width, height,
-                                          util_format_dxt1_rgba_fetch, 8);
+                                          util_format_dxt1_rgba_fetch,
+                                          8, FALSE);
 }
 
 void
@@ -368,7 +387,8 @@ util_format_dxt3_rgba_unpack_rgba_float(float *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
                                           src_row, src_stride,
                                           width, height,
-                                          util_format_dxt3_rgba_fetch, 16);
+                                          util_format_dxt3_rgba_fetch,
+                                          16, FALSE);
 }
 
 void
@@ -379,7 +399,8 @@ util_format_dxt5_rgba_unpack_rgba_float(float *dst_row, unsigned dst_stride,
    util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
                                           src_row, src_stride,
                                           width, height,
-                                          util_format_dxt5_rgba_fetch, 16);
+                                          util_format_dxt5_rgba_fetch,
+                                          16, FALSE);
 }
 
 
@@ -387,29 +408,52 @@ util_format_dxt5_rgba_unpack_rgba_float(float *dst_row, unsigned dst_stride,
  * Block compression.
  */
 
-void
-util_format_dxt1_rgb_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
-                                      const uint8_t *src, unsigned src_stride,
-                                      unsigned width, unsigned height)
+static INLINE void
+util_format_dxtn_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
+                                  const uint8_t *src, unsigned src_stride,
+                                  unsigned width, unsigned height,
+                                  enum util_format_dxtn format,
+                                  unsigned block_size, boolean srgb)
 {
-   const unsigned bw = 4, bh = 4, bytes_per_block = 8;
+   const unsigned bw = 4, bh = 4, comps = 4;
    unsigned x, y, i, j, k;
    for(y = 0; y < height; y += bh) {
       uint8_t *dst = dst_row;
       for(x = 0; x < width; x += bw) {
-         uint8_t tmp[4][4][3];  /* [bh][bw][comps] */
+         uint8_t tmp[4][4][4];  /* [bh][bw][comps] */
          for(j = 0; j < bh; ++j) {
             for(i = 0; i < bw; ++i) {
+               uint8_t src_tmp;
                for(k = 0; k < 3; ++k) {
-                  tmp[j][i][k] = src[(y + j)*src_stride/sizeof(*src) + (x + i)*4 + k];
+                  src_tmp = src[(y + j)*src_stride/sizeof(*src) + (x+i)*comps + k];
+                  if (srgb) {
+                     tmp[j][i][k] = util_format_linear_to_srgb_8unorm(src_tmp);
+                  }
+                  else {
+                     tmp[j][i][k] = src_tmp;
+                  }
                }
+               /* for sake of simplicity there's an unneeded 4th component for dxt1_rgb */
+               tmp[j][i][3] = src[(y + j)*src_stride/sizeof(*src) + (x+i)*comps + 3];
             }
          }
-         util_format_dxtn_pack(3, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT1_RGB, dst, 0);
-         dst += bytes_per_block;
+         /* even for dxt1_rgb have 4 src comps */
+         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], format, dst, 0);
+         dst += block_size;
       }
       dst_row += dst_stride / sizeof(*dst_row);
    }
+
+}
+
+void
+util_format_dxt1_rgb_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
+                                      const uint8_t *src, unsigned src_stride,
+                                      unsigned width, unsigned height)
+{
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src, src_stride,
+                                     width, height, UTIL_FORMAT_DXT1_RGB,
+                                     8, FALSE);
 }
 
 void
@@ -417,24 +461,9 @@ util_format_dxt1_rgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
                                        const uint8_t *src, unsigned src_stride,
                                        unsigned width, unsigned height)
 {
-   const unsigned bw = 4, bh = 4, comps = 4, bytes_per_block = 8;
-   unsigned x, y, i, j, k;
-   for(y = 0; y < height; y += bh) {
-      uint8_t *dst = dst_row;
-      for(x = 0; x < width; x += bw) {
-         uint8_t tmp[4][4][4];  /* [bh][bw][comps] */
-         for(j = 0; j < bh; ++j) {
-            for(i = 0; i < bw; ++i) {
-               for(k = 0; k < comps; ++k) {
-                  tmp[j][i][k] = src[(y + j)*src_stride/sizeof(*src) + (x + i)*comps + k];
-               }
-            }
-         }
-         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT1_RGBA, dst, 0);
-         dst += bytes_per_block;
-      }
-      dst_row += dst_stride / sizeof(*dst_row);
-   }
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src, src_stride,
+                                     width, height, UTIL_FORMAT_DXT1_RGBA,
+                                     8, FALSE);
 }
 
 void
@@ -442,24 +471,9 @@ util_format_dxt3_rgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
                                        const uint8_t *src, unsigned src_stride,
                                        unsigned width, unsigned height)
 {
-   const unsigned bw = 4, bh = 4, comps = 4, bytes_per_block = 16;
-   unsigned x, y, i, j, k;
-   for(y = 0; y < height; y += bh) {
-      uint8_t *dst = dst_row;
-      for(x = 0; x < width; x += bw) {
-         uint8_t tmp[4][4][4];  /* [bh][bw][comps] */
-         for(j = 0; j < bh; ++j) {
-            for(i = 0; i < bw; ++i) {
-               for(k = 0; k < comps; ++k) {
-                  tmp[j][i][k] = src[(y + j)*src_stride/sizeof(*src) + (x + i)*comps + k];
-               }
-            }
-         }
-         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT3_RGBA, dst, 0);
-         dst += bytes_per_block;
-      }
-      dst_row += dst_stride / sizeof(*dst_row);
-   }
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src, src_stride,
+                                     width, height, UTIL_FORMAT_DXT3_RGBA,
+                                     16, FALSE);
 }
 
 void
@@ -467,73 +481,65 @@ util_format_dxt5_rgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride,
                                        const uint8_t *src, unsigned src_stride,
                                        unsigned width, unsigned height)
 {
-   const unsigned bw = 4, bh = 4, comps = 4, bytes_per_block = 16;
-   unsigned x, y, i, j, k;
-
-   for(y = 0; y < height; y += bh) {
-      uint8_t *dst = dst_row;
-      for(x = 0; x < width; x += bw) {
-         uint8_t tmp[4][4][4];  /* [bh][bw][comps] */
-         for(j = 0; j < bh; ++j) {
-            for(i = 0; i < bw; ++i) {
-               for(k = 0; k < comps; ++k) {
-                  tmp[j][i][k] = src[(y + j)*src_stride/sizeof(*src) + (x + i)*comps + k];
-               }
-            }
-         }
-         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT5_RGBA, dst, 0);
-         dst += bytes_per_block;
-      }
-      dst_row += dst_stride / sizeof(*dst_row);
-   }
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src, src_stride,
+                                     width, height, UTIL_FORMAT_DXT5_RGBA,
+                                     16, FALSE);
 }
 
-void
-util_format_dxt1_rgb_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride,
-                                     const float *src, unsigned src_stride,
-                                     unsigned width, unsigned height)
+static INLINE void
+util_format_dxtn_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride,
+                                 const float *src, unsigned src_stride,
+                                 unsigned width, unsigned height,
+                                 enum util_format_dxtn format,
+                                 unsigned block_size, boolean srgb)
 {
    unsigned x, y, i, j, k;
    for(y = 0; y < height; y += 4) {
       uint8_t *dst = dst_row;
       for(x = 0; x < width; x += 4) {
-         uint8_t tmp[4][4][3];
+         uint8_t tmp[4][4][4];
          for(j = 0; j < 4; ++j) {
             for(i = 0; i < 4; ++i) {
+               float src_tmp;
                for(k = 0; k < 3; ++k) {
-                  tmp[j][i][k] = float_to_ubyte(src[(y + j)*src_stride/sizeof(*src) + (x+i)*4 + k]);
+                  src_tmp = src[(y + j)*src_stride/sizeof(*src) + (x+i)*4 + k];
+                  if (srgb) {
+                     tmp[j][i][k] = util_format_linear_float_to_srgb_8unorm(src_tmp);
+                  }
+                  else {
+                     tmp[j][i][k] = float_to_ubyte(src_tmp);
+                  }
                }
+               /* for sake of simplicity there's an unneeded 4th component for dxt1_rgb */
+               src_tmp = src[(y + j)*src_stride/sizeof(*src) + (x+i)*4 + 3];
+               tmp[j][i][3] = float_to_ubyte(src_tmp);
             }
          }
-         util_format_dxtn_pack(3, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT1_RGB, dst, 0);
-         dst += 8;
+         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], format, dst, 0);
+         dst += block_size;
       }
       dst_row += 4*dst_stride/sizeof(*dst_row);
    }
 }
 
 void
+util_format_dxt1_rgb_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride,
+                                     const float *src, unsigned src_stride,
+                                     unsigned width, unsigned height)
+{
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src, src_stride,
+                                    width, height, UTIL_FORMAT_DXT1_RGB,
+                                    8, FALSE);
+}
+
+void
 util_format_dxt1_rgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride,
                                       const float *src, unsigned src_stride,
                                       unsigned width, unsigned height)
 {
-   unsigned x, y, i, j, k;
-   for(y = 0; y < height; y += 4) {
-      uint8_t *dst = dst_row;
-      for(x = 0; x < width; x += 4) {
-         uint8_t tmp[4][4][4];
-         for(j = 0; j < 4; ++j) {
-            for(i = 0; i < 4; ++i) {
-               for(k = 0; k < 4; ++k) {
-                  tmp[j][i][k] = float_to_ubyte(src[(y + j)*src_stride/sizeof(*src) + (x+i)*4 + k]);
-               }
-            }
-         }
-         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT1_RGBA, dst, 0);
-         dst += 8;
-      }
-      dst_row += 4*dst_stride/sizeof(*dst_row);
-   }
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src, src_stride,
+                                    width, height, UTIL_FORMAT_DXT1_RGBA,
+                                    8, FALSE);
 }
 
 void
@@ -541,23 +547,9 @@ util_format_dxt3_rgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride,
                                       const float *src, unsigned src_stride,
                                       unsigned width, unsigned height)
 {
-   unsigned x, y, i, j, k;
-   for(y = 0; y < height; y += 4) {
-      uint8_t *dst = dst_row;
-      for(x = 0; x < width; x += 4) {
-         uint8_t tmp[4][4][4];
-         for(j = 0; j < 4; ++j) {
-            for(i = 0; i < 4; ++i) {
-               for(k = 0; k < 4; ++k) {
-                  tmp[j][i][k] = float_to_ubyte(src[(y + j)*src_stride/sizeof(*src) + (x+i)*4 + k]);
-               }
-            }
-         }
-         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT3_RGBA, dst, 0);
-         dst += 16;
-      }
-      dst_row += 4*dst_stride/sizeof(*dst_row);
-   }
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src, src_stride,
+                                    width, height, UTIL_FORMAT_DXT3_RGBA,
+                                    16, FALSE);
 }
 
 void
@@ -565,173 +557,245 @@ util_format_dxt5_rgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride,
                                       const float *src, unsigned src_stride,
                                       unsigned width, unsigned height)
 {
-   unsigned x, y, i, j, k;
-   for(y = 0; y < height; y += 4) {
-      uint8_t *dst = dst_row;
-      for(x = 0; x < width; x += 4) {
-         uint8_t tmp[4][4][4];
-         for(j = 0; j < 4; ++j) {
-            for(i = 0; i < 4; ++i) {
-               for(k = 0; k < 4; ++k) {
-                  tmp[j][i][k] = float_to_ubyte(src[(y + j)*src_stride/sizeof(*src) + (x+i)*4 + k]);
-               }
-            }
-         }
-         util_format_dxtn_pack(4, 4, 4, &tmp[0][0][0], UTIL_FORMAT_DXT5_RGBA, dst, 0);
-         dst += 16;
-      }
-      dst_row += 4*dst_stride/sizeof(*dst_row);
-   }
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src, src_stride,
+                                    width, height, UTIL_FORMAT_DXT5_RGBA,
+                                    16, FALSE);
 }
 
 
 /*
  * SRGB variants.
- *
- * FIXME: shunts to RGB for now
  */
 
 void
-util_format_dxt1_srgb_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgb_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt1_rgb_unpack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   uint8_t tmp[4];
+   util_format_dxt1_rgb_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_to_linear_8unorm(tmp[0]);
+   dst[1] = util_format_srgb_to_linear_8unorm(tmp[1]);
+   dst[2] = util_format_srgb_to_linear_8unorm(tmp[2]);
+   dst[3] = 255;
 }
 
 void
-util_format_dxt1_srgb_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgba_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt1_rgb_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   uint8_t tmp[4];
+   util_format_dxt1_rgba_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_to_linear_8unorm(tmp[0]);
+   dst[1] = util_format_srgb_to_linear_8unorm(tmp[1]);
+   dst[2] = util_format_srgb_to_linear_8unorm(tmp[2]);
+   dst[3] = tmp[3];
 }
 
 void
-util_format_dxt1_srgb_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt3_srgba_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt1_rgb_fetch_rgba_8unorm(dst, src, i, j);
+   uint8_t tmp[4];
+   util_format_dxt3_rgba_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_to_linear_8unorm(tmp[0]);
+   dst[1] = util_format_srgb_to_linear_8unorm(tmp[1]);
+   dst[2] = util_format_srgb_to_linear_8unorm(tmp[2]);
+   dst[3] = tmp[3];
 }
 
 void
-util_format_dxt1_srgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt5_srgba_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt1_rgba_unpack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   uint8_t tmp[4];
+   util_format_dxt5_rgba_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_to_linear_8unorm(tmp[0]);
+   dst[1] = util_format_srgb_to_linear_8unorm(tmp[1]);
+   dst[2] = util_format_srgb_to_linear_8unorm(tmp[2]);
+   dst[3] = tmp[3];
 }
 
 void
-util_format_dxt1_srgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgb_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt1_rgba_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   uint8_t tmp[4];
+   util_format_dxt1_rgb_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_8unorm_to_linear_float(tmp[0]);
+   dst[1] = util_format_srgb_8unorm_to_linear_float(tmp[1]);
+   dst[2] = util_format_srgb_8unorm_to_linear_float(tmp[2]);
+   dst[3] = 1.0f;
 }
 
 void
-util_format_dxt1_srgba_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt1_srgba_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt1_rgba_fetch_rgba_8unorm(dst, src, i, j);
+   uint8_t tmp[4];
+   util_format_dxt1_rgba_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_8unorm_to_linear_float(tmp[0]);
+   dst[1] = util_format_srgb_8unorm_to_linear_float(tmp[1]);
+   dst[2] = util_format_srgb_8unorm_to_linear_float(tmp[2]);
+   dst[3] = ubyte_to_float(tmp[3]);
 }
 
 void
-util_format_dxt3_srgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt3_srgba_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt3_rgba_unpack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   uint8_t tmp[4];
+   util_format_dxt3_rgba_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_8unorm_to_linear_float(tmp[0]);
+   dst[1] = util_format_srgb_8unorm_to_linear_float(tmp[1]);
+   dst[2] = util_format_srgb_8unorm_to_linear_float(tmp[2]);
+   dst[3] = ubyte_to_float(tmp[3]);
 }
 
 void
-util_format_dxt3_srgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt5_srgba_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
 {
-   util_format_dxt3_rgba_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   uint8_t tmp[4];
+   util_format_dxt5_rgba_fetch(0, src, i, j, tmp);
+   dst[0] = util_format_srgb_8unorm_to_linear_float(tmp[0]);
+   dst[1] = util_format_srgb_8unorm_to_linear_float(tmp[1]);
+   dst[2] = util_format_srgb_8unorm_to_linear_float(tmp[2]);
+   dst[3] = ubyte_to_float(tmp[3]);
 }
 
 void
-util_format_dxt3_srgba_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt1_srgb_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt3_rgba_fetch_rgba_8unorm(dst, src, i, j);
+   util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
+                                           src_row, src_stride,
+                                           width, height,
+                                           util_format_dxt1_rgb_fetch,
+                                           8, TRUE);
 }
 
 void
-util_format_dxt5_srgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt5_rgba_unpack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
+                                           src_row, src_stride,
+                                           width, height,
+                                           util_format_dxt1_rgba_fetch,
+                                           8, TRUE);
 }
 
 void
-util_format_dxt5_srgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt3_srgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt5_rgba_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
+                                           src_row, src_stride,
+                                           width, height,
+                                           util_format_dxt3_rgba_fetch,
+                                           16, TRUE);
 }
 
 void
-util_format_dxt5_srgba_fetch_rgba_8unorm(uint8_t *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt5_srgba_unpack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt5_rgba_fetch_rgba_8unorm(dst, src, i, j);
+   util_format_dxtn_rgb_unpack_rgba_8unorm(dst_row, dst_stride,
+                                           src_row, src_stride,
+                                           width, height,
+                                           util_format_dxt5_rgba_fetch,
+                                           16, TRUE);
 }
 
 void
 util_format_dxt1_srgb_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt1_rgb_unpack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
+                                          src_row, src_stride,
+                                          width, height,
+                                          util_format_dxt1_rgb_fetch,
+                                          8, TRUE);
 }
 
 void
-util_format_dxt1_srgb_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgba_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt1_rgb_pack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
+                                          src_row, src_stride,
+                                          width, height,
+                                          util_format_dxt1_rgba_fetch,
+                                          8, TRUE);
 }
 
 void
-util_format_dxt1_srgb_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt3_srgba_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt1_rgb_fetch_rgba_float(dst, src, i, j);
+   util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
+                                          src_row, src_stride,
+                                          width, height,
+                                          util_format_dxt3_rgba_fetch,
+                                          16, TRUE);
 }
 
 void
-util_format_dxt1_srgba_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt5_srgba_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt1_rgba_unpack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_rgb_unpack_rgba_float(dst_row, dst_stride,
+                                          src_row, src_stride,
+                                          width, height,
+                                          util_format_dxt5_rgba_fetch,
+                                          16, TRUE);
 }
 
 void
-util_format_dxt1_srgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgb_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt1_rgba_pack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride,
+                                     width, height, UTIL_FORMAT_DXT1_RGB,
+                                     8, TRUE);
 }
 
 void
-util_format_dxt1_srgba_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt1_srgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt1_rgba_fetch_rgba_float(dst, src, i, j);
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride,
+                                     width, height, UTIL_FORMAT_DXT1_RGBA,
+                                     8, TRUE);
 }
 
 void
-util_format_dxt3_srgba_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt3_srgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt3_rgba_unpack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride,
+                                     width, height, UTIL_FORMAT_DXT3_RGBA,
+                                     16, TRUE);
 }
 
 void
-util_format_dxt3_srgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt5_srgba_pack_rgba_8unorm(uint8_t *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt3_rgba_pack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_pack_rgba_8unorm(dst_row, dst_stride, src_row, src_stride,
+                                     width, height, UTIL_FORMAT_DXT5_RGBA,
+                                     16, TRUE);
 }
 
 void
-util_format_dxt3_srgba_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt1_srgb_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt3_rgba_fetch_rgba_float(dst, src, i, j);
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src_row, src_stride,
+                                    width, height, UTIL_FORMAT_DXT1_RGB,
+                                    8, TRUE);
 }
 
 void
-util_format_dxt5_srgba_unpack_rgba_float(float *dst_row, unsigned dst_stride, const uint8_t *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt1_srgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt5_rgba_unpack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src_row, src_stride,
+                                    width, height, UTIL_FORMAT_DXT1_RGBA,
+                                    8, TRUE);
 }
 
 void
-util_format_dxt5_srgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
+util_format_dxt3_srgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt5_rgba_pack_rgba_float(dst_row, dst_stride, src_row, src_stride, width, height);
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src_row, src_stride,
+                                    width, height, UTIL_FORMAT_DXT3_RGBA,
+                                    16, TRUE);
 }
 
 void
-util_format_dxt5_srgba_fetch_rgba_float(float *dst, const uint8_t *src, unsigned i, unsigned j)
+util_format_dxt5_srgba_pack_rgba_float(uint8_t *dst_row, unsigned dst_stride, const float *src_row, unsigned src_stride, unsigned width, unsigned height)
 {
-   util_format_dxt5_rgba_fetch_rgba_float(dst, src, i, j);
+   util_format_dxtn_pack_rgba_float(dst_row, dst_stride, src_row, src_stride,
+                                    width, height, UTIL_FORMAT_DXT5_RGBA,
+                                    16, TRUE);
 }
 
diff --git a/mesalib/src/gallium/auxiliary/util/u_format_srgb.h b/mesalib/src/gallium/auxiliary/util/u_format_srgb.h
index 43213fbeb..82ed9575d 100644
--- a/mesalib/src/gallium/auxiliary/util/u_format_srgb.h
+++ b/mesalib/src/gallium/auxiliary/util/u_format_srgb.h
@@ -83,6 +83,11 @@ util_format_srgb_8unorm_to_linear_float(uint8_t x)
 }
 
 
+/*
+ * XXX These 2 functions probably don't make a lot of sense (but lots
+ * of potential callers which most likely all don't make sense neither)
+ */
+
 /**
  * Convert a 8bit normalized value from linear to srgb.
  */
diff --git a/mesalib/src/glsl/ast.h b/mesalib/src/glsl/ast.h
index ff603b352..5f2d5b1e4 100644
--- a/mesalib/src/glsl/ast.h
+++ b/mesalib/src/glsl/ast.h
@@ -417,6 +417,12 @@ struct ast_type_qualifier {
 	  */
 	 unsigned explicit_index:1;
 
+         /**
+          * Flag set if GL_ARB_shading_language_420pack "binding" layout
+          * qualifier is used.
+          */
+         unsigned explicit_binding:1;
+
          /** \name Layout qualifiers for GL_AMD_conservative_depth */
          /** \{ */
          unsigned depth_any:1;
@@ -441,6 +447,9 @@ struct ast_type_qualifier {
       unsigned i;
    } flags;
 
+   /** Precision of the type (highp/medium/lowp). */
+   unsigned precision:2;
+
    /**
     * Location specified via GL_ARB_explicit_attrib_location layout
     *
@@ -457,11 +466,34 @@ struct ast_type_qualifier {
    int index;
 
    /**
+    * Binding specified via GL_ARB_shading_language_420pack's "binding" keyword.
+    *
+    * \note
+    * This field is only valid if \c explicit_binding is set.
+    */
+   int binding;
+
+   /**
     * Return true if and only if an interpolation qualifier is present.
     */
    bool has_interpolation() const;
 
    /**
+    * Return whether a layout qualifier is present.
+    */
+   bool has_layout() const;
+
+   /**
+    * Return whether a storage qualifier is present.
+    */
+   bool has_storage() const;
+
+   /**
+    * Return whether an auxiliary storage qualifier is present.
+    */
+   bool has_auxiliary_storage() const;
+
+   /**
     * \brief Return string representation of interpolation qualifier.
     *
     * If an interpolation qualifier is present, then return that qualifier's
@@ -522,8 +554,8 @@ public:
    ast_type_specifier(const ast_type_specifier *that, bool is_array,
                       ast_expression *array_size)
       : ast_node(), type_name(that->type_name), structure(that->structure),
-        is_array(is_array), array_size(array_size), precision(that->precision),
-        is_precision_statement(that->is_precision_statement)
+        is_array(is_array), array_size(array_size),
+        default_precision(that->default_precision)
    {
       /* empty */
    }
@@ -531,8 +563,8 @@ public:
    /** Construct a type specifier from a type name */
    ast_type_specifier(const char *name) 
       : type_name(name), structure(NULL),
-	is_array(false), array_size(NULL), precision(ast_precision_none),
-	is_precision_statement(false)
+	is_array(false), array_size(NULL),
+	default_precision(ast_precision_none)
    {
       /* empty */
    }
@@ -540,8 +572,8 @@ public:
    /** Construct a type specifier from a structure definition */
    ast_type_specifier(ast_struct_specifier *s)
       : type_name(s->name), structure(s),
-	is_array(false), array_size(NULL), precision(ast_precision_none),
-	is_precision_statement(false)
+	is_array(false), array_size(NULL),
+	default_precision(ast_precision_none)
    {
       /* empty */
    }
@@ -560,9 +592,8 @@ public:
    bool is_array;
    ast_expression *array_size;
 
-   unsigned precision:2;
-
-   bool is_precision_statement;
+   /** For precision statements, this is the given precision; otherwise none. */
+   unsigned default_precision:2;
 };
 
 
diff --git a/mesalib/src/glsl/ast_to_hir.cpp b/mesalib/src/glsl/ast_to_hir.cpp
index 28ccf7288..bfd5fda8f 100644
--- a/mesalib/src/glsl/ast_to_hir.cpp
+++ b/mesalib/src/glsl/ast_to_hir.cpp
@@ -1850,6 +1850,84 @@ validate_matrix_layout_for_type(struct _mesa_glsl_parse_state *state,
    }
 }
 
+static bool
+validate_binding_qualifier(struct _mesa_glsl_parse_state *state,
+                           YYLTYPE *loc,
+                           ir_variable *var,
+                           const ast_type_qualifier *qual)
+{
+   if (var->mode != ir_var_uniform) {
+      _mesa_glsl_error(loc, state,
+                       "the \"binding\" qualifier only applies to uniforms.\n");
+      return false;
+   }
+
+   if (qual->binding < 0) {
+      _mesa_glsl_error(loc, state, "binding values must be >= 0.\n");
+      return false;
+   }
+
+   const struct gl_context *const ctx = state->ctx;
+   unsigned elements = var->type->is_array() ? var->type->length : 1;
+   unsigned max_index = qual->binding + elements - 1;
+
+   if (var->type->is_interface()) {
+      /* UBOs.  From page 60 of the GLSL 4.20 specification:
+       * "If the binding point for any uniform block instance is less than zero,
+       *  or greater than or equal to the implementation-dependent maximum
+       *  number of uniform buffer bindings, a compilation error will occur.
+       *  When the binding identifier is used with a uniform block instanced as
+       *  an array of size N, all elements of the array from binding through
+       *  binding + N – 1 must be within this range."
+       *
+       * The implementation-dependent maximum is GL_MAX_UNIFORM_BUFFER_BINDINGS.
+       */
+      if (max_index >= ctx->Const.MaxUniformBufferBindings) {
+         _mesa_glsl_error(loc, state, "layout(binding = %d) for %d UBOs exceeds "
+                          "the maximum number of UBO binding points (%d).\n",
+                          qual->binding, elements,
+                          ctx->Const.MaxUniformBufferBindings);
+         return false;
+      }
+   } else if (var->type->is_sampler() ||
+              (var->type->is_array() && var->type->fields.array->is_sampler())) {
+      /* Samplers.  From page 63 of the GLSL 4.20 specification:
+       * "If the binding is less than zero, or greater than or equal to the
+       *  implementation-dependent maximum supported number of units, a
+       *  compilation error will occur. When the binding identifier is used
+       *  with an array of size N, all elements of the array from binding
+       *  through binding + N - 1 must be within this range."
+       */
+      unsigned limit;
+      switch (state->target) {
+      case vertex_shader:
+         limit = ctx->Const.VertexProgram.MaxTextureImageUnits;
+         break;
+      case geometry_shader:
+         limit = ctx->Const.GeometryProgram.MaxTextureImageUnits;
+         break;
+      case fragment_shader:
+         limit = ctx->Const.FragmentProgram.MaxTextureImageUnits;
+         break;
+      }
+
+      if (max_index >= limit) {
+         _mesa_glsl_error(loc, state, "layout(binding = %d) for %d samplers "
+                          "exceeds the maximum number of texture image units "
+                          "(%d).\n", qual->binding, elements, limit);
+
+         return false;
+      }
+   } else {
+      _mesa_glsl_error(loc, state,
+                       "the \"binding\" qualifier only applies to uniform "
+                       "blocks, samplers, or arrays of samplers.\n");
+      return false;
+   }
+
+   return true;
+}
+
 static void
 apply_type_qualifier_to_variable(const struct ast_type_qualifier *qual,
 				 ir_variable *var,
@@ -2080,11 +2158,11 @@ apply_type_qualifier_to_variable(const struct ast_type_qualifier *qual,
 			  "explicit index requires explicit location\n");
    }
 
-   /* Does the declaration use the 'layout' keyword?
-    */
-   const bool uses_layout = qual->flags.q.pixel_center_integer
-      || qual->flags.q.origin_upper_left
-      || qual->flags.q.explicit_location; /* no need for index since it relies on location */
+   if (qual->flags.q.explicit_binding &&
+       validate_binding_qualifier(state, loc, var, qual)) {
+      var->explicit_binding = true;
+      var->binding = qual->binding;
+   }
 
    /* Does the declaration use the deprecated 'attribute' or 'varying'
     * keywords?
@@ -2115,7 +2193,7 @@ apply_type_qualifier_to_variable(const struct ast_type_qualifier *qual,
    const bool relaxed_layout_qualifier_checking =
       state->ARB_fragment_coord_conventions_enable;
 
-   if (uses_layout && uses_deprecated_qualifier) {
+   if (qual->has_layout() && uses_deprecated_qualifier) {
       if (relaxed_layout_qualifier_checking) {
 	 _mesa_glsl_warning(loc, state,
 			    "`layout' qualifier may not be used with "
@@ -2544,6 +2622,12 @@ ast_declarator_list::hir(exec_list *instructions,
 			     type_name);
 	 }
       }
+
+      if (this->type->qualifier.precision != ast_precision_none &&
+          this->type->specifier->structure != NULL) {
+         _mesa_glsl_error(&loc, state, "Precision qualifiers can't be applied "
+                          "to structures.\n");
+      }
    }
 
    foreach_list_typed (ast_declaration, decl, link, &this->declarations) {
@@ -2846,7 +2930,7 @@ ast_declarator_list::hir(exec_list *instructions,
 
       /* Precision qualifiers exists only in GLSL versions 1.00 and >= 1.30.
        */
-      if (this->type->specifier->precision != ast_precision_none) {
+      if (this->type->qualifier.precision != ast_precision_none) {
          state->check_precision_qualifiers_allowed(&loc);
       }
 
@@ -2864,9 +2948,10 @@ ast_declarator_list::hir(exec_list *instructions,
        * From page 87 of the GLSL ES spec:
        *    "RESOLUTION: Allow sampler types to take a precision qualifier."
        */
-      if (this->type->specifier->precision != ast_precision_none
+      if (this->type->qualifier.precision != ast_precision_none
           && !var->type->is_float()
           && !var->type->is_integer()
+          && !var->type->is_record()
           && !(var->type->is_sampler() && state->es_shader)
           && !(var->type->is_array()
                && (var->type->fields.array->is_float()
@@ -3958,22 +4043,11 @@ ir_rvalue *
 ast_type_specifier::hir(exec_list *instructions,
 			  struct _mesa_glsl_parse_state *state)
 {
-   if (!this->is_precision_statement && this->structure == NULL)
+   if (this->default_precision == ast_precision_none && this->structure == NULL)
       return NULL;
 
    YYLTYPE loc = this->get_location();
 
-   if (this->precision != ast_precision_none
-       && !state->check_precision_qualifiers_allowed(&loc)) {
-      return NULL;
-   }
-   if (this->precision != ast_precision_none
-       && this->structure != NULL) {
-      _mesa_glsl_error(&loc, state,
-                       "precision qualifiers do not apply to structures");
-      return NULL;
-   }
-
    /* If this is a precision statement, check that the type to which it is
     * applied is either float or int.
     *
@@ -3984,10 +4058,16 @@ ast_type_specifier::hir(exec_list *instructions,
     *    field can be either int or float [...].  Any other types or
     *    qualifiers will result in an error.
     */
-   if (this->is_precision_statement) {
-      assert(this->precision != ast_precision_none);
-      assert(this->structure == NULL); /* The check for structures was
-                                        * performed above. */
+   if (this->default_precision != ast_precision_none) {
+      if (!state->check_precision_qualifiers_allowed(&loc))
+         return NULL;
+
+      if (this->structure != NULL) {
+         _mesa_glsl_error(&loc, state,
+                          "precision qualifiers do not apply to structures");
+         return NULL;
+      }
+
       if (this->is_array) {
          _mesa_glsl_error(&loc, state,
                           "default precision statements do not apply to "
@@ -4307,6 +4387,13 @@ ast_interface_block::hir(exec_list *instructions,
                                    var_mode);
          var->interface_type = block_type;
 
+         /* Propagate the "binding" keyword into this UBO's fields;
+          * the UBO declaration itself doesn't get an ir_variable unless it
+          * has an instance name.  This is ugly.
+          */
+         var->explicit_binding = this->layout.flags.q.explicit_binding;
+         var->binding = this->layout.binding;
+
          state->symbols->add_variable(var);
          instructions->push_tail(var);
       }
diff --git a/mesalib/src/glsl/ast_type.cpp b/mesalib/src/glsl/ast_type.cpp
index be84550da..275b2a1d0 100644
--- a/mesalib/src/glsl/ast_type.cpp
+++ b/mesalib/src/glsl/ast_type.cpp
@@ -56,6 +56,42 @@ bool ast_type_qualifier::has_interpolation() const
           || this->flags.q.noperspective;
 }
 
+bool
+ast_type_qualifier::has_layout() const
+{
+   return this->flags.q.origin_upper_left
+          || this->flags.q.pixel_center_integer
+          || this->flags.q.depth_any
+          || this->flags.q.depth_greater
+          || this->flags.q.depth_less
+          || this->flags.q.depth_unchanged
+          || this->flags.q.std140
+          || this->flags.q.shared
+          || this->flags.q.column_major
+          || this->flags.q.row_major
+          || this->flags.q.packed
+          || this->flags.q.explicit_location
+          || this->flags.q.explicit_index
+          || this->flags.q.explicit_binding;
+}
+
+bool
+ast_type_qualifier::has_storage() const
+{
+   return this->flags.q.constant
+          || this->flags.q.attribute
+          || this->flags.q.varying
+          || this->flags.q.in
+          || this->flags.q.out
+          || this->flags.q.uniform;
+}
+
+bool
+ast_type_qualifier::has_auxiliary_storage() const
+{
+   return this->flags.q.centroid;
+}
+
 const char*
 ast_type_qualifier::interpolation_string() const
 {
@@ -110,6 +146,9 @@ ast_type_qualifier::merge_qualifier(YYLTYPE *loc,
    if (q.flags.q.explicit_index)
       this->index = q.index;
 
+   if (q.flags.q.explicit_binding)
+      this->binding = q.binding;
+
    return true;
 }
 
diff --git a/mesalib/src/glsl/builtin_compiler/Makefile.am b/mesalib/src/glsl/builtin_compiler/Makefile.am
index 823d546e1..5f1a995c3 100644
--- a/mesalib/src/glsl/builtin_compiler/Makefile.am
+++ b/mesalib/src/glsl/builtin_compiler/Makefile.am
@@ -65,6 +65,8 @@ AM_CXXFLAGS = $(AM_CFLAGS)
 include ../Makefile.sources
 
 noinst_PROGRAMS = builtin_compiler
+
+if !CROSS_COMPILING
 noinst_LTLIBRARIES = libglslcore.la libglcpp.la
 
 libglcpp_la_SOURCES =					\
@@ -74,6 +76,7 @@ libglcpp_la_SOURCES =					\
 libglslcore_la_SOURCES =				\
 	$(BUILTIN_COMPILER_GENERATED_CXX_FILES)		\
 	$(LIBGLSL_FILES)
+endif
 
 builtin_compiler_SOURCES = \
 	$(top_srcdir)/src/mesa/main/hash_table.c	\
@@ -82,4 +85,14 @@ builtin_compiler_SOURCES = \
 	$(top_srcdir)/src/mesa/program/symbol_table.c	\
 	$(BUILTIN_COMPILER_CXX_FILES)			\
 	$(GLSL_COMPILER_CXX_FILES)
+
+if CROSS_COMPILING
+builtin_compiler_SOURCES += \
+	$(LIBGLCPP_GENERATED_FILES) \
+	$(LIBGLCPP_FILES) \
+	$(BUILTIN_COMPILER_GENERATED_CXX_FILES) \
+	$(LIBGLSL_FILES)
+builtin_compiler_CPPFLAGS = $(AM_CPPFLAGS)
+else
 builtin_compiler_LDADD = libglslcore.la libglcpp.la
+endif
diff --git a/mesalib/src/glsl/glsl_lexer.ll b/mesalib/src/glsl/glsl_lexer.ll
index e66ce7bee..dbc8154e4 100644
--- a/mesalib/src/glsl/glsl_lexer.ll
+++ b/mesalib/src/glsl/glsl_lexer.ll
@@ -366,7 +366,8 @@ layout		{
 		      || yyextra->ARB_conservative_depth_enable
 		      || yyextra->ARB_explicit_attrib_location_enable
 		      || yyextra->ARB_uniform_buffer_object_enable
-		      || yyextra->ARB_fragment_coord_conventions_enable) {
+		      || yyextra->ARB_fragment_coord_conventions_enable
+                      || yyextra->ARB_shading_language_420pack_enable) {
 		      return LAYOUT_TOK;
 		   } else {
 		      yylval->identifier = strdup(yytext);
diff --git a/mesalib/src/glsl/glsl_parser.yy b/mesalib/src/glsl/glsl_parser.yy
index b8f3df90e..cbd94b41f 100644
--- a/mesalib/src/glsl/glsl_parser.yy
+++ b/mesalib/src/glsl/glsl_parser.yy
@@ -162,6 +162,7 @@ static void yyerror(YYLTYPE *loc, _mesa_glsl_parse_state *st, const char *msg)
 %type <node> simple_statement
 %type <n> precision_qualifier
 %type <type_qualifier> type_qualifier
+%type <type_qualifier> auxiliary_storage_qualifier
 %type <type_qualifier> storage_qualifier
 %type <type_qualifier> interpolation_qualifier
 %type <type_qualifier> layout_qualifier
@@ -169,7 +170,6 @@ static void yyerror(YYLTYPE *loc, _mesa_glsl_parse_state *st, const char *msg)
 %type <type_qualifier> interface_block_layout_qualifier
 %type <type_qualifier> interface_qualifier
 %type <type_specifier> type_specifier
-%type <type_specifier> type_specifier_no_prec
 %type <type_specifier> type_specifier_nonarray
 %type <identifier> basic_type_specifier_nonarray
 %type <fully_specified_type> fully_specified_type
@@ -180,7 +180,7 @@ static void yyerror(YYLTYPE *loc, _mesa_glsl_parse_state *st, const char *msg)
 %type <parameter_declarator> parameter_declarator
 %type <parameter_declarator> parameter_declaration
 %type <type_qualifier> parameter_qualifier
-%type <type_qualifier> parameter_type_qualifier
+%type <type_qualifier> parameter_direction_qualifier
 %type <type_specifier> parameter_type_specifier
 %type <function_definition> function_definition
 %type <compound_statement> compound_statement_no_new_scope
@@ -790,10 +790,9 @@ declaration:
    {
       $$ = $1;
    }
-   | PRECISION precision_qualifier type_specifier_no_prec ';'
+   | PRECISION precision_qualifier type_specifier ';'
    {
-      $3->precision = $2;
-      $3->is_precision_statement = true;
+      $3->default_precision = $2;
       $$ = $3;
    }
    | interface_block
@@ -864,29 +863,11 @@ parameter_declarator:
    ;
 
 parameter_declaration:
-   parameter_type_qualifier parameter_qualifier parameter_declarator
-   {
-      $1.flags.i |= $2.flags.i;
-
-      $$ = $3;
-      $$->type->qualifier = $1;
-   }
-   | parameter_qualifier parameter_declarator
+   parameter_qualifier parameter_declarator
    {
       $$ = $2;
       $$->type->qualifier = $1;
    }
-   | parameter_type_qualifier parameter_qualifier parameter_type_specifier
-   {
-      void *ctx = state;
-      $1.flags.i |= $2.flags.i;
-
-      $$ = new(ctx) ast_parameter_declarator();
-      $$->set_location(yylloc);
-      $$->type = new(ctx) ast_fully_specified_type();
-      $$->type->qualifier = $1;
-      $$->type->specifier = $3;
-   }
    | parameter_qualifier parameter_type_specifier
    {
       void *ctx = state;
@@ -903,7 +884,40 @@ parameter_qualifier:
    {
       memset(& $$, 0, sizeof($$));
    }
-   | IN_TOK
+   | CONST_TOK parameter_qualifier
+   {
+      if ($2.flags.q.constant)
+         _mesa_glsl_error(&@1, state, "duplicate const qualifier.\n");
+
+      $$ = $2;
+      $$.flags.q.constant = 1;
+   }
+   | parameter_direction_qualifier parameter_qualifier
+   {
+      if (($1.flags.q.in || $1.flags.q.out) && ($2.flags.q.in || $2.flags.q.out))
+         _mesa_glsl_error(&@1, state, "duplicate in/out/inout qualifier\n");
+
+      if (!state->ARB_shading_language_420pack_enable && $2.flags.q.constant)
+         _mesa_glsl_error(&@1, state, "const must be specified before "
+                          "in/out/inout.\n");
+
+      $$ = $1;
+      $$.merge_qualifier(&@1, state, $2);
+   }
+   | precision_qualifier parameter_qualifier
+   {
+      if ($2.precision != ast_precision_none)
+         _mesa_glsl_error(&@1, state, "Duplicate precision qualifier.\n");
+
+      if (!state->ARB_shading_language_420pack_enable && $2.flags.i != 0)
+         _mesa_glsl_error(&@1, state, "Precision qualifiers must come last.\n");
+
+      $$ = $2;
+      $$.precision = $1;
+   }
+
+parameter_direction_qualifier:
+   IN_TOK
    {
       memset(& $$, 0, sizeof($$));
       $$.flags.q.in = 1;
@@ -1240,6 +1254,12 @@ layout_qualifier_id:
          }
       }
 
+      if (state->ARB_shading_language_420pack_enable &&
+          strcmp("binding", $1) == 0) {
+         $$.flags.q.explicit_binding = 1;
+         $$.binding = $3;
+      }
+
       /* If the identifier didn't match any known layout identifiers,
        * emit an error.
        */
@@ -1305,45 +1325,154 @@ interpolation_qualifier:
    }
    ;
 
-parameter_type_qualifier:
-   CONST_TOK
+type_qualifier:
+   /* Single qualifiers */
+   INVARIANT
    {
       memset(& $$, 0, sizeof($$));
-      $$.flags.q.constant = 1;
+      $$.flags.q.invariant = 1;
    }
-   ;
-
-type_qualifier:
-   storage_qualifier
+   | auxiliary_storage_qualifier
+   | storage_qualifier
+   | interpolation_qualifier
    | layout_qualifier
-   | layout_qualifier storage_qualifier
+   | precision_qualifier
+   {
+      memset(&$$, 0, sizeof($$));
+      $$.precision = $1;
+   }
+
+   /* Multiple qualifiers:
+    * In GLSL 4.20, these can be specified in any order.  In earlier versions,
+    * they appear in this order (see GLSL 1.50 section 4.7 & comments below):
+    *
+    *    invariant interpolation auxiliary storage precision  ...or...
+    *    layout storage precision
+    *
+    * Each qualifier's rule ensures that the accumulated qualifiers on the right
+    * side don't contain any that must appear on the left hand side.
+    * For example, when processing a storage qualifier, we check that there are
+    * no auxiliary, interpolation, layout, or invariant qualifiers to the right.
+    */
+   | INVARIANT type_qualifier
+   {
+      if ($2.flags.q.invariant)
+         _mesa_glsl_error(&@1, state, "Duplicate \"invariant\" qualifier.\n");
+
+      if ($2.has_layout()) {
+         _mesa_glsl_error(&@1, state,
+                          "\"invariant\" cannot be used with layout(...).\n");
+      }
+
+      $$ = $2;
+      $$.flags.q.invariant = 1;
+   }
+   | interpolation_qualifier type_qualifier
+   {
+      /* Section 4.3 of the GLSL 1.40 specification states:
+       * "...qualified with one of these interpolation qualifiers"
+       *
+       * GLSL 1.30 claims to allow "one or more", but insists that:
+       * "These interpolation qualifiers may only precede the qualifiers in,
+       *  centroid in, out, or centroid out in a declaration."
+       *
+       * ...which means that e.g. smooth can't precede smooth, so there can be
+       * only one after all, and the 1.40 text is a clarification, not a change.
+       */
+      if ($2.has_interpolation())
+         _mesa_glsl_error(&@1, state, "Duplicate interpolation qualifier.\n");
+
+      if ($2.has_layout()) {
+         _mesa_glsl_error(&@1, state, "Interpolation qualifiers cannot be used "
+                          "with layout(...).\n");
+      }
+
+      if (!state->ARB_shading_language_420pack_enable && $2.flags.q.invariant) {
+         _mesa_glsl_error(&@1, state, "Interpolation qualifiers must come "
+                          "after \"invariant\".\n");
+      }
+
+      $$ = $1;
+      $$.merge_qualifier(&@1, state, $2);
+   }
+   | layout_qualifier type_qualifier
    {
+      /* The GLSL 1.50 grammar indicates that a layout(...) declaration can be
+       * used standalone or immediately before a storage qualifier.  It cannot
+       * be used with interpolation qualifiers or invariant.  There does not
+       * appear to be any text indicating that it must come before the storage
+       * qualifier, but always seems to in examples.
+       */
+      if (!state->ARB_shading_language_420pack_enable && $2.has_layout())
+         _mesa_glsl_error(&@1, state, "Duplicate layout(...) qualifiers.\n");
+
+      if ($2.flags.q.invariant)
+         _mesa_glsl_error(&@1, state, "layout(...) cannot be used with "
+                          "the \"invariant\" qualifier\n");
+
+      if ($2.has_interpolation()) {
+         _mesa_glsl_error(&@1, state, "layout(...) cannot be used with "
+                          "interpolation qualifiers.\n");
+      }
+
       $$ = $1;
-      $$.flags.i |= $2.flags.i;
+      $$.merge_qualifier(&@1, state, $2);
    }
-   | interpolation_qualifier
-   | interpolation_qualifier storage_qualifier
+   | auxiliary_storage_qualifier type_qualifier
    {
+      if ($2.has_auxiliary_storage()) {
+         _mesa_glsl_error(&@1, state,
+                          "Duplicate auxiliary storage qualifier (centroid).\n");
+      }
+
+      if (!state->ARB_shading_language_420pack_enable &&
+          ($2.flags.q.invariant || $2.has_interpolation() || $2.has_layout())) {
+         _mesa_glsl_error(&@1, state, "Auxiliary storage qualifiers must come "
+                          "just before storage qualifiers.\n");
+      }
       $$ = $1;
       $$.flags.i |= $2.flags.i;
    }
-   | INVARIANT storage_qualifier
+   | storage_qualifier type_qualifier
    {
-      $$ = $2;
-      $$.flags.q.invariant = 1;
+      /* Section 4.3 of the GLSL 1.20 specification states:
+       * "Variable declarations may have a storage qualifier specified..."
+       *  1.30 clarifies this to "may have one storage qualifier".
+       */
+      if ($2.has_storage())
+         _mesa_glsl_error(&@1, state, "Duplicate storage qualifier.\n");
+
+      if (!state->ARB_shading_language_420pack_enable &&
+          ($2.flags.q.invariant || $2.has_interpolation() || $2.has_layout() ||
+           $2.has_auxiliary_storage())) {
+         _mesa_glsl_error(&@1, state, "Storage qualifiers must come after "
+                          "invariant, interpolation, layout and auxiliary "
+                          "storage qualifiers.\n");
+      }
+
+      $$ = $1;
+      $$.merge_qualifier(&@1, state, $2);
    }
-   | INVARIANT interpolation_qualifier storage_qualifier
+   | precision_qualifier type_qualifier
    {
+      if ($2.precision != ast_precision_none)
+         _mesa_glsl_error(&@1, state, "Duplicate precision qualifier.\n");
+
+      if (!state->ARB_shading_language_420pack_enable && $2.flags.i != 0)
+         _mesa_glsl_error(&@1, state, "Precision qualifiers must come last.\n");
+
       $$ = $2;
-      $$.flags.i |= $3.flags.i;
-      $$.flags.q.invariant = 1;
+      $$.precision = $1;
    }
-   | INVARIANT
+   ;
+
+auxiliary_storage_qualifier:
+   CENTROID
    {
       memset(& $$, 0, sizeof($$));
-      $$.flags.q.invariant = 1;
+      $$.flags.q.centroid = 1;
    }
-   ;
+   /* TODO: "sample" and "patch" also go here someday. */
 
 storage_qualifier:
    CONST_TOK
@@ -1361,12 +1490,6 @@ storage_qualifier:
       memset(& $$, 0, sizeof($$));
       $$.flags.q.varying = 1;
    }
-   | CENTROID VARYING
-   {
-      memset(& $$, 0, sizeof($$));
-      $$.flags.q.centroid = 1;
-      $$.flags.q.varying = 1;
-   }
    | IN_TOK
    {
       memset(& $$, 0, sizeof($$));
@@ -1377,16 +1500,6 @@ storage_qualifier:
       memset(& $$, 0, sizeof($$));
       $$.flags.q.out = 1;
    }
-   | CENTROID IN_TOK
-   {
-      memset(& $$, 0, sizeof($$));
-      $$.flags.q.centroid = 1; $$.flags.q.in = 1;
-   }
-   | CENTROID OUT_TOK
-   {
-      memset(& $$, 0, sizeof($$));
-      $$.flags.q.centroid = 1; $$.flags.q.out = 1;
-   }
    | UNIFORM
    {
       memset(& $$, 0, sizeof($$));
@@ -1395,18 +1508,6 @@ storage_qualifier:
    ;
 
 type_specifier:
-   type_specifier_no_prec
-   {
-      $$ = $1;
-   }
-   | precision_qualifier type_specifier_no_prec
-   {
-      $$ = $2;
-      $$->precision = $1;
-   }
-   ;
-
-type_specifier_no_prec:
    type_specifier_nonarray
    | type_specifier_nonarray '[' ']'
    {
diff --git a/mesalib/src/glsl/ir.h b/mesalib/src/glsl/ir.h
index 1f0dc0906..7ac291cf4 100644
--- a/mesalib/src/glsl/ir.h
+++ b/mesalib/src/glsl/ir.h
@@ -471,6 +471,14 @@ public:
    unsigned explicit_index:1;
 
    /**
+    * Was an initial binding explicitly set in the shader?
+    *
+    * If so, constant_value contains an integer ir_constant representing the
+    * initial binding point.
+    */
+   unsigned explicit_binding:1;
+
+   /**
     * Does this variable have an initializer?
     *
     * This is used by the linker to cross-validiate initializers of global
@@ -528,6 +536,13 @@ public:
    int index;
 
    /**
+    * Initial binding point for a sampler or UBO.
+    *
+    * For array types, this represents the binding point for the first element.
+    */
+   int binding;
+
+   /**
     * Built-in state that backs this uniform
     *
     * Once set at variable creation, \c state_slots must remain invariant.
diff --git a/mesalib/src/glsl/ir_clone.cpp b/mesalib/src/glsl/ir_clone.cpp
index 5b42935f8..9d4178de8 100644
--- a/mesalib/src/glsl/ir_clone.cpp
+++ b/mesalib/src/glsl/ir_clone.cpp
@@ -50,11 +50,13 @@ ir_variable::clone(void *mem_ctx, struct hash_table *ht) const
    var->interpolation = this->interpolation;
    var->location = this->location;
    var->index = this->index;
+   var->binding = this->binding;
    var->warn_extension = this->warn_extension;
    var->origin_upper_left = this->origin_upper_left;
    var->pixel_center_integer = this->pixel_center_integer;
    var->explicit_location = this->explicit_location;
    var->explicit_index = this->explicit_index;
+   var->explicit_binding = this->explicit_binding;
    var->has_initializer = this->has_initializer;
    var->depth_layout = this->depth_layout;
 
diff --git a/mesalib/src/glsl/ir_optimization.h b/mesalib/src/glsl/ir_optimization.h
index fad6f1bfe..2c1479ff4 100644
--- a/mesalib/src/glsl/ir_optimization.h
+++ b/mesalib/src/glsl/ir_optimization.h
@@ -61,7 +61,7 @@ enum lower_packing_builtins_op {
    LOWER_UNPACK_SNORM_4x8               = 0x0200,
 
    LOWER_PACK_UNORM_4x8                 = 0x0400,
-   LOWER_UNPACK_UNORM_4x8               = 0x0800,
+   LOWER_UNPACK_UNORM_4x8               = 0x0800
 };
 
 bool do_common_optimization(exec_list *ir, bool linked,
diff --git a/mesalib/src/glsl/link_uniform_initializers.cpp b/mesalib/src/glsl/link_uniform_initializers.cpp
index 54d9bf1f5..3f6671047 100644
--- a/mesalib/src/glsl/link_uniform_initializers.cpp
+++ b/mesalib/src/glsl/link_uniform_initializers.cpp
@@ -82,6 +82,56 @@ copy_constant_to_storage(union gl_constant_value *storage,
 }
 
 void
+set_uniform_binding(void *mem_ctx, gl_shader_program *prog,
+                    const char *name, const glsl_type *type, int binding)
+{
+   struct gl_uniform_storage *const storage =
+      get_storage(prog->UniformStorage, prog->NumUserUniformStorage, name);
+
+   if (storage == NULL) {
+      assert(storage != NULL);
+      return;
+   }
+
+   if (storage->type->is_sampler()) {
+      unsigned elements = MAX2(storage->array_elements, 1);
+
+      /* From section 4.4.4 of the GLSL 4.20 specification:
+       * "If the binding identifier is used with an array, the first element
+       *  of the array takes the specified unit and each subsequent element
+       *  takes the next consecutive unit."
+       */
+      for (unsigned int i = 0; i < elements; i++) {
+         storage->storage[i].i = binding + i;
+      }
+
+      for (int sh = 0; sh < MESA_SHADER_TYPES; sh++) {
+         gl_shader *shader = prog->_LinkedShaders[sh];
+
+         if (shader && storage->sampler[sh].active) {
+            for (unsigned i = 0; i < elements; i++) {
+               unsigned index = storage->sampler[sh].index + i;
+
+               shader->SamplerUnits[index] = storage->storage[i].i;
+            }
+         }
+      }
+   } else if (storage->block_index != -1) {
+      /* This is a field of a UBO.  val is the binding index. */
+      for (int i = 0; i < MESA_SHADER_TYPES; i++) {
+         int stage_index = prog->UniformBlockStageIndex[i][storage->block_index];
+
+         if (stage_index != -1) {
+            struct gl_shader *sh = prog->_LinkedShaders[i];
+            sh->UniformBlocks[stage_index].Binding = binding;
+         }
+      }
+   }
+
+   storage->initialized = true;
+}
+
+void
 set_uniform_initializer(void *mem_ctx, gl_shader_program *prog,
 			const char *name, const glsl_type *type,
 			ir_constant *val)
@@ -136,20 +186,6 @@ set_uniform_initializer(void *mem_ctx, gl_shader_program *prog,
 
 	 idx += elements;
       }
-
-      if (base_type == GLSL_TYPE_SAMPLER) {
-         for (int sh = 0; sh < MESA_SHADER_TYPES; sh++) {
-            gl_shader *shader = prog->_LinkedShaders[sh];
-
-            if (shader && storage->sampler[sh].active) {
-               for (unsigned i = 0; i < storage->array_elements; i++) {
-                  unsigned index = storage->sampler[sh].index + i;
-
-                  shader->SamplerUnits[index] = storage->storage[i].i;
-               }
-            }
-	 }
-      }
    } else {
       copy_constant_to_storage(storage->storage,
 			       val,
@@ -187,14 +223,19 @@ link_set_uniform_initializers(struct gl_shader_program *prog)
       foreach_list(node, shader->ir) {
 	 ir_variable *const var = ((ir_instruction *) node)->as_variable();
 
-	 if (!var || var->mode != ir_var_uniform || !var->constant_value)
+	 if (!var || var->mode != ir_var_uniform)
 	    continue;
 
 	 if (!mem_ctx)
 	    mem_ctx = ralloc_context(NULL);
 
-	 linker::set_uniform_initializer(mem_ctx, prog, var->name,
-					 var->type, var->constant_value);
+         if (var->explicit_binding) {
+            linker::set_uniform_binding(mem_ctx, prog, var->name,
+                                        var->type, var->binding);
+         } else if (var->constant_value) {
+            linker::set_uniform_initializer(mem_ctx, prog, var->name,
+                                            var->type, var->constant_value);
+         }
       }
    }
 
diff --git a/mesalib/src/glsl/linker.cpp b/mesalib/src/glsl/linker.cpp
index ba97ade25..ac010cfbb 100644
--- a/mesalib/src/glsl/linker.cpp
+++ b/mesalib/src/glsl/linker.cpp
@@ -541,6 +541,25 @@ cross_validate_globals(struct gl_shader_program *prog,
 	       existing->explicit_location = true;
 	    }
 
+            /* From the GLSL 4.20 specification:
+             * "A link error will result if two compilation units in a program
+             *  specify different integer-constant bindings for the same
+             *  opaque-uniform name.  However, it is not an error to specify a
+             *  binding on some but not all declarations for the same name"
+             */
+            if (var->explicit_binding) {
+               if (existing->explicit_binding &&
+                   var->binding != existing->binding) {
+                  linker_error(prog, "explicit bindings for %s "
+                               "`%s' have differing values\n",
+                               mode_string(var), var->name);
+                  return false;
+               }
+
+               existing->binding = var->binding;
+               existing->explicit_binding = true;
+            }
+
 	    /* Validate layout qualifiers for gl_FragDepth.
 	     *
 	     * From the AMD/ARB_conservative_depth specs:
@@ -1147,7 +1166,7 @@ update_array_sizes(struct gl_shader_program *prog)
 	    }
 	 }
 
-	 if (size + 1 != var->type->fields.array->length) {
+	 if (size + 1 != var->type->length) {
 	    /* If this is a built-in uniform (i.e., it's backed by some
 	     * fixed-function state), adjust the number of state slots to
 	     * match the new array size.  The number of slots per array entry
diff --git a/mesalib/src/mapi/glapi/gen/ARB_framebuffer_object.xml b/mesalib/src/mapi/glapi/gen/ARB_framebuffer_object.xml
index 87eda93eb..7c547c167 100644
--- a/mesalib/src/mapi/glapi/gen/ARB_framebuffer_object.xml
+++ b/mesalib/src/mapi/glapi/gen/ARB_framebuffer_object.xml
@@ -149,7 +149,7 @@
     <function name="BindRenderbuffer" es2="2.0" offset="assign">
         <param name="target" type="GLenum"/>
         <param name="renderbuffer" type="GLuint"/>
-	<glx rop="4316"/>
+        <glx rop="235"/>
     </function>
 
     <function name="DeleteRenderbuffers"
@@ -199,7 +199,7 @@
     <function name="BindFramebuffer" es2="2.0" offset="assign">
         <param name="target" type="GLenum"/>
         <param name="framebuffer" type="GLuint"/>
-	<glx rop="4319"/>
+        <glx rop="236"/>
     </function>
 
     <function name="DeleteFramebuffers"
diff --git a/mesalib/src/mapi/glapi/gen/EXT_framebuffer_object.xml b/mesalib/src/mapi/glapi/gen/EXT_framebuffer_object.xml
index 85a05f6ed..16c82a4a2 100644
--- a/mesalib/src/mapi/glapi/gen/EXT_framebuffer_object.xml
+++ b/mesalib/src/mapi/glapi/gen/EXT_framebuffer_object.xml
@@ -78,9 +78,10 @@
 	<return type="GLboolean"/>
     </function>
 
-    <function name="BindRenderbufferEXT" alias="BindRenderbuffer">
+    <function name="BindRenderbufferEXT" offset="assign">
         <param name="target" type="GLenum"/>
         <param name="renderbuffer" type="GLuint"/>
+        <glx rop="4316"/>
     </function>
 
     <function name="DeleteRenderbuffersEXT" alias="DeleteRenderbuffers">
@@ -111,9 +112,10 @@
 	<return type="GLboolean"/>
     </function>
 
-    <function name="BindFramebufferEXT" alias="BindFramebuffer">
+    <function name="BindFramebufferEXT" offset="assign">
         <param name="target" type="GLenum"/>
         <param name="framebuffer" type="GLuint"/>
+        <glx rop="4319"/>
     </function>
 
     <function name="DeleteFramebuffersEXT" alias="DeleteFramebuffers">
diff --git a/mesalib/src/mesa/drivers/dri/common/utils.c b/mesalib/src/mesa/drivers/dri/common/utils.c
index ac0773b0d..c9fc21891 100644
--- a/mesalib/src/mesa/drivers/dri/common/utils.c
+++ b/mesalib/src/mesa/drivers/dri/common/utils.c
@@ -366,7 +366,6 @@ static const struct { unsigned int attrib, offset; } attribMap[] = {
     __ATTRIB(__DRI_ATTRIB_TRANSPARENT_GREEN_VALUE,	transparentGreen),
     __ATTRIB(__DRI_ATTRIB_TRANSPARENT_BLUE_VALUE,	transparentBlue),
     __ATTRIB(__DRI_ATTRIB_TRANSPARENT_ALPHA_VALUE,	transparentAlpha),
-    __ATTRIB(__DRI_ATTRIB_FLOAT_MODE,			floatMode),
     __ATTRIB(__DRI_ATTRIB_RED_MASK,			redMask),
     __ATTRIB(__DRI_ATTRIB_GREEN_MASK,			greenMask),
     __ATTRIB(__DRI_ATTRIB_BLUE_MASK,			blueMask),
@@ -418,11 +417,6 @@ driGetConfigAttribIndex(const __DRIconfig *config,
         /* XXX no return value??? */
 	break;
 
-    case __DRI_ATTRIB_FLOAT_MODE:
-        /* this field is not int-sized */
-        *value = config->modes.floatMode;
-        break;
-
     default:
         /* any other int-sized field */
 	*value = *(unsigned int *)
diff --git a/mesalib/src/mesa/main/fbobject.c b/mesalib/src/mesa/main/fbobject.c
index f59fdb12d..a29f1ab13 100644
--- a/mesalib/src/mesa/main/fbobject.c
+++ b/mesalib/src/mesa/main/fbobject.c
@@ -1155,6 +1155,13 @@ _mesa_BindRenderbuffer(GLenum target, GLuint renderbuffer)
 }
 
 
+void GLAPIENTRY
+_mesa_BindRenderbufferEXT(GLenum target, GLuint renderbuffer)
+{
+    _mesa_BindRenderbuffer(target, renderbuffer);
+}
+
+
 /**
  * If the given renderbuffer is anywhere attached to the framebuffer, detach
  * the renderbuffer.
@@ -2025,6 +2032,13 @@ _mesa_BindFramebuffer(GLenum target, GLuint framebuffer)
    }
 }
 
+void GLAPIENTRY
+_mesa_BindFramebufferEXT(GLenum target, GLuint framebuffer)
+{
+    _mesa_BindFramebuffer(target, framebuffer);
+}
+
+
 
 void GLAPIENTRY
 _mesa_DeleteFramebuffers(GLsizei n, const GLuint *framebuffers)
diff --git a/mesalib/src/mesa/main/fbobject.h b/mesalib/src/mesa/main/fbobject.h
index 4066ea65b..0a2a5cc59 100644
--- a/mesalib/src/mesa/main/fbobject.h
+++ b/mesalib/src/mesa/main/fbobject.h
@@ -120,6 +120,9 @@ extern void GLAPIENTRY
 _mesa_BindRenderbuffer(GLenum target, GLuint renderbuffer);
 
 extern void GLAPIENTRY
+_mesa_BindRenderbufferEXT(GLenum target, GLuint renderbuffer);
+
+extern void GLAPIENTRY
 _mesa_DeleteRenderbuffers(GLsizei n, const GLuint *renderbuffers);
 
 extern void GLAPIENTRY
@@ -152,6 +155,9 @@ extern void GLAPIENTRY
 _mesa_BindFramebuffer(GLenum target, GLuint framebuffer);
 
 extern void GLAPIENTRY
+_mesa_BindFramebufferEXT(GLenum target, GLuint framebuffer);
+
+extern void GLAPIENTRY
 _mesa_DeleteFramebuffers(GLsizei n, const GLuint *framebuffers);
 
 extern void GLAPIENTRY
diff --git a/mesalib/src/mesa/main/mtypes.h b/mesalib/src/mesa/main/mtypes.h
index ea139ea58..aba7d845b 100644
--- a/mesalib/src/mesa/main/mtypes.h
+++ b/mesalib/src/mesa/main/mtypes.h
@@ -3283,7 +3283,7 @@ enum mesa_debug_source {
    MESA_DEBUG_SOURCE_THIRD_PARTY,
    MESA_DEBUG_SOURCE_APPLICATION,
    MESA_DEBUG_SOURCE_OTHER,
-   MESA_DEBUG_SOURCE_COUNT,
+   MESA_DEBUG_SOURCE_COUNT
 };
 
 enum mesa_debug_type {
@@ -3293,14 +3293,14 @@ enum mesa_debug_type {
    MESA_DEBUG_TYPE_PORTABILITY,
    MESA_DEBUG_TYPE_PERFORMANCE,
    MESA_DEBUG_TYPE_OTHER,
-   MESA_DEBUG_TYPE_COUNT,
+   MESA_DEBUG_TYPE_COUNT
 };
 
 enum mesa_debug_severity {
    MESA_DEBUG_SEVERITY_LOW,
    MESA_DEBUG_SEVERITY_MEDIUM,
    MESA_DEBUG_SEVERITY_HIGH,
-   MESA_DEBUG_SEVERITY_COUNT,
+   MESA_DEBUG_SEVERITY_COUNT
 };
 
 /** @} */
@@ -3353,7 +3353,7 @@ typedef enum
    API_OPENGLES,
    API_OPENGLES2,
    API_OPENGL_CORE,
-   API_OPENGL_LAST = API_OPENGL_CORE,
+   API_OPENGL_LAST = API_OPENGL_CORE
 } gl_api;
 
 /**
diff --git a/mesalib/src/mesa/state_tracker/st_extensions.c b/mesalib/src/mesa/state_tracker/st_extensions.c
index 32348ef73..d01942967 100644
--- a/mesalib/src/mesa/state_tracker/st_extensions.c
+++ b/mesalib/src/mesa/state_tracker/st_extensions.c
@@ -615,6 +615,7 @@ void st_init_extensions(struct st_context *st)
       ctx->Extensions.ARB_shader_bit_encoding = GL_TRUE;
       ctx->Extensions.ARB_shading_language_packing = GL_TRUE;
       ctx->Extensions.OES_depth_texture_cube_map = GL_TRUE;
+      ctx->Extensions.ARB_shading_language_420pack = GL_TRUE;
    } else {
       /* Optional integer support for GLSL 1.2. */
       if (screen->get_shader_param(screen, PIPE_SHADER_VERTEX,
diff --git a/mesalib/src/mesa/x86/Makefile.am b/mesalib/src/mesa/x86/Makefile.am
index 21ce3607a..167857684 100644
--- a/mesalib/src/mesa/x86/Makefile.am
+++ b/mesalib/src/mesa/x86/Makefile.am
@@ -33,7 +33,17 @@ gen_matypes_SOURCES = gen_matypes.c
 BUILT_SOURCES = matypes.h
 CLEANFILES = matypes.h
 
+if GEN_ASM_OFFSETS
+
+matypes.h: $(gen_matypes_SOURCES)
+	$(AM_V_GEN)$(COMPILE) $< -DASM_OFFSETS -S -o - | \
+		sed -n '/^->/{s:^->::;/[$$]/{s:^:#define :;s:[$$]::};p}' > $@
+
+else
+
 matypes.h: gen_matypes
 	$(AM_V_GEN)./gen_matypes > $@
 
 endif
+
+endif
diff --git a/mesalib/src/mesa/x86/gen_matypes.c b/mesalib/src/mesa/x86/gen_matypes.c
index 80ee61aa8..1e904aa0b 100644
--- a/mesalib/src/mesa/x86/gen_matypes.c
+++ b/mesalib/src/mesa/x86/gen_matypes.c
@@ -52,7 +52,7 @@ do {									\
    printf( "\n" );							\
    printf( "/* ====================================================="	\
 	   "========\n" );						\
-   printf( " * Offsets for %s\n", x );					\
+   printf( " * Offsets for " x "\n" );					\
    printf( " */\n" );							\
    printf( "\n" );							\
 } while (0)
@@ -61,20 +61,43 @@ do {									\
 do {									\
    printf( "\n" );							\
    printf( "/*\n" );							\
-   printf( " * Flags for %s\n", x );					\
+   printf( " * Flags for " x "\n" );					\
    printf( " */\n" );							\
    printf( "\n" );							\
 } while (0)
 
-#define OFFSET( s, t, m )						\
-   printf( "#define %s\t%lu\n", s, (unsigned long) offsetof( t, m ) );
+#ifdef ASM_OFFSETS
 
-#define SIZEOF( s, t )							\
-   printf( "#define %s\t%lu\n", s, (unsigned long) sizeof(t) );
+/*
+ * Format the asm output in a special way that we can manipulate
+ * after the fact and turn into the final header for the target.
+ */
+
+#define DEFINE_UL( s, ul )						\
+   __asm__ __volatile__ ( "\n->" s " %0" : : "i" (ul) )
+
+#define DEFINE( s, d )							\
+   DEFINE_UL( s, d )
+
+#define printf( x )							\
+   __asm__ __volatile__ ( "\n->" x )
+
+#else
+
+#define DEFINE_UL( s, ul )						\
+   printf( "#define %s\t%lu\n", s, (unsigned long) (ul) );
 
 #define DEFINE( s, d )							\
    printf( "#define %s\t0x%" PRIx64 "\n", s, (uint64_t) d );
 
+#endif
+
+#define OFFSET( s, t, m )						\
+   DEFINE_UL( s, offsetof( t, m ) )
+
+#define SIZEOF( s, t )							\
+   DEFINE_UL( s, sizeof(t) )
+
 
 
 int main( int argc, char **argv )