Merge remote-tracking branch 'origin/released'

Conflicts:
	pixman/pixman/pixman-mmx.c

34 files changed, 494 insertions, 367 deletions

diff --git a/mesalib/src/mapi/glapi/SConscript b/mesalib/src/mapi/glapi/SConscript
index 9882806ce..4097a7fe1 100644
--- a/mesalib/src/mapi/glapi/SConscript
+++ b/mesalib/src/mapi/glapi/SConscript
@@ -46,7 +46,7 @@ for s in mapi_sources:
 #
 # Assembly sources
 #
-if env['gcc'] and env['platform'] != 'windows':
+if env['gcc'] and env['platform'] not in ('darwin', 'windows'):
     if env['machine'] == 'x86':
         env.Append(CPPDEFINES = [
             'USE_X86_ASM',
diff --git a/mesalib/src/mesa/SConscript b/mesalib/src/mesa/SConscript
index e9b1f6aaf..10a04689d 100644
--- a/mesalib/src/mesa/SConscript
+++ b/mesalib/src/mesa/SConscript
@@ -384,7 +384,7 @@ if env['gles']:
 #
 # Assembly sources
 #
-if env['gcc'] and env['platform'] != 'windows':
+if env['gcc'] and env['platform'] not in ('darwin', 'windows'):
     if env['machine'] == 'x86':
         env.Append(CPPDEFINES = [
             'USE_X86_ASM',
diff --git a/mesalib/src/mesa/drivers/dri/swrast/swrast.c b/mesalib/src/mesa/drivers/dri/swrast/swrast.c
index ff26e2769..bfac47c08 100644
--- a/mesalib/src/mesa/drivers/dri/swrast/swrast.c
+++ b/mesalib/src/mesa/drivers/dri/swrast/swrast.c
@@ -474,7 +474,7 @@ dri_create_buffer(__DRIscreen * sPriv,
     dPriv->driverPrivate = drawable;
     drawable->dPriv = dPriv;
 
-    drawable->row = malloc(MAX_WIDTH * 4);
+    drawable->row = malloc(SWRAST_MAX_WIDTH * 4);
     if (drawable->row == NULL)
 	goto drawable_fail;
 
diff --git a/mesalib/src/mesa/drivers/windows/gdi/wgl.c b/mesalib/src/mesa/drivers/windows/gdi/wgl.c
index 61850c26f..d99473bb3 100644
--- a/mesalib/src/mesa/drivers/windows/gdi/wgl.c
+++ b/mesalib/src/mesa/drivers/windows/gdi/wgl.c
@@ -33,6 +33,7 @@
 
 #include "main/config.h"
 #include "glapi/glapi.h"
+#include "swrast/swrast.h"
 #include "GL/wmesa.h"   /* protos for wmesa* functions */
 
 /*
diff --git a/mesalib/src/mesa/main/config.h b/mesalib/src/mesa/main/config.h
index 7b7740ebe..8bf741f99 100644
--- a/mesalib/src/mesa/main/config.h
+++ b/mesalib/src/mesa/main/config.h
@@ -46,9 +46,6 @@
 /** Maximum texture matrix stack depth */
 #define MAX_TEXTURE_STACK_DEPTH 10
 
-/** Maximum color matrix stack depth */
-#define MAX_COLOR_STACK_DEPTH 4
-
 /** Maximum attribute stack depth */
 #define MAX_ATTRIB_STACK_DEPTH 16
 
@@ -74,11 +71,7 @@
 #define MAX_AUX_BUFFERS 1
 
 /** Maximum order (degree) of curves */
-#ifdef AMIGA
-#   define MAX_EVAL_ORDER 12
-#else
-#   define MAX_EVAL_ORDER 30
-#endif
+#define MAX_EVAL_ORDER 30
 
 /** Maximum Name stack depth */
 #define MAX_NAME_STACK_DEPTH 64
@@ -115,7 +108,9 @@
 /** Maximum rectangular texture size - GL_NV_texture_rectangle */
 #define MAX_TEXTURE_RECT_SIZE 16384
 
-/** Maximum number of layers in a 1D or 2D array texture - GL_MESA_texture_array */
+/**
+ * Maximum number of layers in a 1D or 2D array texture - GL_MESA_texture_array
+ */
 #define MAX_ARRAY_TEXTURE_LAYERS 64
 
 /**
@@ -141,34 +136,9 @@
 #define MAX_TEXTURE_UNITS ((MAX_TEXTURE_COORD_UNITS > MAX_TEXTURE_IMAGE_UNITS) ? MAX_TEXTURE_COORD_UNITS : MAX_TEXTURE_IMAGE_UNITS)
 
 
-/** 
- * Maximum viewport/image width. Must accomodate all texture sizes too. 
- */
-
-#ifndef MAX_WIDTH
-#   define MAX_WIDTH 16384
-#endif
-/** Maximum viewport/image height */
-#ifndef MAX_HEIGHT
-#   define MAX_HEIGHT 16384
-#endif
-
-/* XXX: hack to prevent stack overflow on windows until all temporary arrays
- * [MAX_WIDTH] are allocated from the heap */
-#ifdef WIN32
-#undef MAX_TEXTURE_LEVELS
-#undef MAX_3D_TEXTURE_LEVELS
-#undef MAX_CUBE_TEXTURE_LEVELS
-#undef MAX_TEXTURE_RECT_SIZE
-#undef MAX_WIDTH
-#undef MAX_HEIGHT
-#define MAX_TEXTURE_LEVELS 13
-#define MAX_3D_TEXTURE_LEVELS 9
-#define MAX_CUBE_TEXTURE_LEVELS 13
-#define MAX_TEXTURE_RECT_SIZE 4096
-#define MAX_WIDTH 4096
-#define MAX_HEIGHT 4096
-#endif
+/** Maximum viewport size */
+#define MAX_VIEWPORT_WIDTH 16384
+#define MAX_VIEWPORT_HEIGHT 16384
 
 /** Maxmimum size for CVA.  May be overridden by the drivers.  */
 #define MAX_ARRAY_LOCK_SIZE 3000
@@ -176,14 +146,6 @@
 /** Subpixel precision for antialiasing, window coordinate snapping */
 #define SUB_PIXEL_BITS 4
 
-/** Size of histogram tables */
-#define HISTOGRAM_TABLE_SIZE 256
-
-/** Max convolution filter width */
-#define MAX_CONVOLUTION_WIDTH 9
-/** Max convolution filter height */
-#define MAX_CONVOLUTION_HEIGHT 9
-
 /** For GL_ARB_texture_compression */
 #define MAX_COMPRESSED_TEXTURE_FORMATS 25
 
@@ -280,6 +242,7 @@
 /** For GL_EXT_framebuffer_object */
 /*@{*/
 #define MAX_COLOR_ATTACHMENTS 8
+#define MAX_RENDERBUFFER_SIZE 16384
 /*@}*/
 
 /** For GL_ATI_envmap_bump - support bump mapping on first 8 units */
@@ -299,46 +262,6 @@
 /*@}*/
 
 
-/**
- * \name Mesa-specific parameters
- */
-/*@{*/
-
-
-/**
- * If non-zero use GLdouble for walking triangle edges, for better accuracy.
- */
-#define TRIANGLE_WALK_DOUBLE 0
-
-
-/**
- * Bits per depth buffer value (max is 32).
- */
-#ifndef DEFAULT_SOFTWARE_DEPTH_BITS
-#define DEFAULT_SOFTWARE_DEPTH_BITS 16
-#endif
-/** Depth buffer data type */
-#if DEFAULT_SOFTWARE_DEPTH_BITS <= 16
-#define DEFAULT_SOFTWARE_DEPTH_TYPE GLushort
-#else
-#define DEFAULT_SOFTWARE_DEPTH_TYPE GLuint
-#endif
-
-
-/**
- * Bits per stencil value: 8
- */
-#define STENCIL_BITS 8
-
-
-/**
- * For swrast, bits per color channel:  8, 16 or 32
- */
-#ifndef CHAN_BITS
-#define CHAN_BITS 8
-#endif
-
-
 /*
  * Color channel component order
  * 
diff --git a/mesalib/src/mesa/main/context.c b/mesalib/src/mesa/main/context.c
index 43e7438ad..8d48904f8 100644
--- a/mesalib/src/mesa/main/context.c
+++ b/mesalib/src/mesa/main/context.c
@@ -268,7 +268,7 @@ _mesa_initialize_visual( struct gl_config *vis,
    if (depthBits < 0 || depthBits > 32) {
       return GL_FALSE;
    }
-   if (stencilBits < 0 || stencilBits > STENCIL_BITS) {
+   if (stencilBits < 0 || stencilBits > 8) {
       return GL_FALSE;
    }
    assert(accumRedBits >= 0);
@@ -586,8 +586,8 @@ _mesa_init_constants(struct gl_context *ctx)
    ctx->Const.MaxLights = MAX_LIGHTS;
    ctx->Const.MaxShininess = 128.0;
    ctx->Const.MaxSpotExponent = 128.0;
-   ctx->Const.MaxViewportWidth = MAX_WIDTH;
-   ctx->Const.MaxViewportHeight = MAX_HEIGHT;
+   ctx->Const.MaxViewportWidth = MAX_VIEWPORT_WIDTH;
+   ctx->Const.MaxViewportHeight = MAX_VIEWPORT_HEIGHT;
 #if FEATURE_ARB_vertex_program
    init_program_limits(GL_VERTEX_PROGRAM_ARB, &ctx->Const.VertexProgram);
 #endif
@@ -608,7 +608,7 @@ _mesa_init_constants(struct gl_context *ctx)
 
 #if FEATURE_EXT_framebuffer_object
    ctx->Const.MaxColorAttachments = MAX_COLOR_ATTACHMENTS;
-   ctx->Const.MaxRenderbufferSize = MAX_WIDTH;
+   ctx->Const.MaxRenderbufferSize = MAX_RENDERBUFFER_SIZE;
 #endif
 
 #if FEATURE_ARB_vertex_shader
@@ -712,20 +712,15 @@ check_context_limits(struct gl_context *ctx)
    assert(ctx->Const.MaxCubeTextureLevels <= MAX_CUBE_TEXTURE_LEVELS);
    assert(ctx->Const.MaxTextureRectSize <= MAX_TEXTURE_RECT_SIZE);
 
-   /* make sure largest texture image is <= MAX_WIDTH in size */
-   assert((1 << (ctx->Const.MaxTextureLevels - 1)) <= MAX_WIDTH);
-   assert((1 << (ctx->Const.MaxCubeTextureLevels - 1)) <= MAX_WIDTH);
-   assert((1 << (ctx->Const.Max3DTextureLevels - 1)) <= MAX_WIDTH);
-
    /* Texture level checks */
    assert(MAX_TEXTURE_LEVELS >= MAX_3D_TEXTURE_LEVELS);
    assert(MAX_TEXTURE_LEVELS >= MAX_CUBE_TEXTURE_LEVELS);
 
    /* Max texture size should be <= max viewport size (render to texture) */
-   assert((1 << (MAX_TEXTURE_LEVELS - 1)) <= MAX_WIDTH);
-
-   assert(ctx->Const.MaxViewportWidth <= MAX_WIDTH);
-   assert(ctx->Const.MaxViewportHeight <= MAX_WIDTH);
+   assert((1 << (ctx->Const.MaxTextureLevels - 1))
+          <= ctx->Const.MaxViewportWidth);
+   assert((1 << (ctx->Const.MaxTextureLevels - 1))
+          <= ctx->Const.MaxViewportHeight);
 
    assert(ctx->Const.MaxDrawBuffers <= MAX_DRAW_BUFFERS);
 
diff --git a/mesalib/src/mesa/main/readpix.c b/mesalib/src/mesa/main/readpix.c
index 48708a6eb..0f429ab22 100644
--- a/mesalib/src/mesa/main/readpix.c
+++ b/mesalib/src/mesa/main/readpix.c
@@ -110,6 +110,7 @@ read_depth_pixels( struct gl_context *ctx,
    GLint j;
    GLubyte *dst, *map;
    int dstStride, stride;
+   GLfloat *depthValues;
 
    if (!rb)
       return;
@@ -119,8 +120,6 @@ read_depth_pixels( struct gl_context *ctx,
    ASSERT(y >= 0);
    ASSERT(x + width <= (GLint) rb->Width);
    ASSERT(y + height <= (GLint) rb->Height);
-   /* width should never be > MAX_WIDTH since we did clipping earlier */
-   ASSERT(width <= MAX_WIDTH);
 
    if (fast_read_depth_pixels(ctx, x, y, width, height, type, pixels, packing))
       return;
@@ -136,16 +135,24 @@ read_depth_pixels( struct gl_context *ctx,
       return;
    }
 
-   /* General case (slower) */
-   for (j = 0; j < height; j++, y++) {
-      GLfloat depthValues[MAX_WIDTH];
-      _mesa_unpack_float_z_row(rb->Format, width, map, depthValues);
-      _mesa_pack_depth_span(ctx, width, dst, type, depthValues, packing);
+   depthValues = (GLfloat *) malloc(width * sizeof(GLfloat));
 
-      dst += dstStride;
-      map += stride;
+   if (depthValues) {
+      /* General case (slower) */
+      for (j = 0; j < height; j++, y++) {
+         _mesa_unpack_float_z_row(rb->Format, width, map, depthValues);
+         _mesa_pack_depth_span(ctx, width, dst, type, depthValues, packing);
+
+         dst += dstStride;
+         map += stride;
+      }
+   }
+   else {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glReadPixels");
    }
 
+   free(depthValues);
+
    ctx->Driver.UnmapRenderbuffer(ctx, rb);
 }
 
@@ -163,15 +170,12 @@ read_stencil_pixels( struct gl_context *ctx,
    struct gl_framebuffer *fb = ctx->ReadBuffer;
    struct gl_renderbuffer *rb = fb->Attachment[BUFFER_STENCIL].Renderbuffer;
    GLint j;
-   GLubyte *map;
+   GLubyte *map, *stencil;
    GLint stride;
 
    if (!rb)
       return;
 
-   /* width should never be > MAX_WIDTH since we did clipping earlier */
-   ASSERT(width <= MAX_WIDTH);
-
    ctx->Driver.MapRenderbuffer(ctx, rb, x, y, width, height, GL_MAP_READ_BIT,
 			       &map, &stride);
    if (!map) {
@@ -179,19 +183,27 @@ read_stencil_pixels( struct gl_context *ctx,
       return;
    }
 
-   /* process image row by row */
-   for (j = 0; j < height; j++) {
-      GLvoid *dest;
-      GLubyte stencil[MAX_WIDTH];
+   stencil = (GLubyte *) malloc(width * sizeof(GLubyte));
 
-      _mesa_unpack_ubyte_stencil_row(rb->Format, width, map, stencil);
-      dest = _mesa_image_address2d(packing, pixels, width, height,
-                                   GL_STENCIL_INDEX, type, j, 0);
+   if (stencil) {
+      /* process image row by row */
+      for (j = 0; j < height; j++) {
+         GLvoid *dest;
 
-      _mesa_pack_stencil_span(ctx, width, type, dest, stencil, packing);
+         _mesa_unpack_ubyte_stencil_row(rb->Format, width, map, stencil);
+         dest = _mesa_image_address2d(packing, pixels, width, height,
+                                      GL_STENCIL_INDEX, type, j, 0);
 
-      map += stride;
+         _mesa_pack_stencil_span(ctx, width, type, dest, stencil, packing);
+
+         map += stride;
+      }
    }
+   else {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glReadPixels");
+   }
+
+   free(stencil);
 
    ctx->Driver.UnmapRenderbuffer(ctx, rb);
 }
@@ -378,7 +390,7 @@ fast_read_depth_stencil_pixels_separate(struct gl_context *ctx,
    struct gl_framebuffer *fb = ctx->ReadBuffer;
    struct gl_renderbuffer *depthRb = fb->Attachment[BUFFER_DEPTH].Renderbuffer;
    struct gl_renderbuffer *stencilRb = fb->Attachment[BUFFER_STENCIL].Renderbuffer;
-   GLubyte *depthMap, *stencilMap;
+   GLubyte *depthMap, *stencilMap, *stencilVals;
    int depthStride, stencilStride, i, j;
 
    if (_mesa_get_format_datatype(depthRb->Format) != GL_UNSIGNED_NORMALIZED)
@@ -399,21 +411,28 @@ fast_read_depth_stencil_pixels_separate(struct gl_context *ctx,
       return GL_TRUE;  /* don't bother trying the slow path */
    }
 
-   for (j = 0; j < height; j++) {
-      GLubyte stencilVals[MAX_WIDTH];
+   stencilVals = (GLubyte *) malloc(width * sizeof(GLubyte));
 
-      _mesa_unpack_uint_z_row(depthRb->Format, width, depthMap, dst);
-      _mesa_unpack_ubyte_stencil_row(stencilRb->Format, width,
-				     stencilMap, stencilVals);
+   if (stencilVals) {
+      for (j = 0; j < height; j++) {
+         _mesa_unpack_uint_z_row(depthRb->Format, width, depthMap, dst);
+         _mesa_unpack_ubyte_stencil_row(stencilRb->Format, width,
+                                        stencilMap, stencilVals);
 
-      for (i = 0; i < width; i++) {
-	 dst[i] = (dst[i] & 0xffffff00) | stencilVals[i];
-      }
+         for (i = 0; i < width; i++) {
+            dst[i] = (dst[i] & 0xffffff00) | stencilVals[i];
+         }
 
-      depthMap += depthStride;
-      stencilMap += stencilStride;
-      dst += dstStride / 4;
+         depthMap += depthStride;
+         stencilMap += stencilStride;
+         dst += dstStride / 4;
+      }
    }
+   else {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glReadPixels");
+   }
+
+   free(stencilVals);
 
    ctx->Driver.UnmapRenderbuffer(ctx, depthRb);
    ctx->Driver.UnmapRenderbuffer(ctx, stencilRb);
@@ -434,6 +453,9 @@ slow_read_depth_stencil_pixels_separate(struct gl_context *ctx,
    struct gl_renderbuffer *stencilRb = fb->Attachment[BUFFER_STENCIL].Renderbuffer;
    GLubyte *depthMap, *stencilMap;
    int depthStride, stencilStride, j;
+   GLubyte *stencilVals;
+   GLfloat *depthVals;
+
 
    /* The depth and stencil buffers might be separate, or a single buffer.
     * If one buffer, only map it once.
@@ -460,21 +482,29 @@ slow_read_depth_stencil_pixels_separate(struct gl_context *ctx,
       stencilStride = depthStride;
    }
 
-   for (j = 0; j < height; j++) {
-      GLubyte stencilVals[MAX_WIDTH];
-      GLfloat depthVals[MAX_WIDTH];
+   stencilVals = (GLubyte *) malloc(width * sizeof(GLubyte));
+   depthVals = (GLfloat *) malloc(width * sizeof(GLfloat));
 
-      _mesa_unpack_float_z_row(depthRb->Format, width, depthMap, depthVals);
-      _mesa_unpack_ubyte_stencil_row(stencilRb->Format, width,
-				     stencilMap, stencilVals);
+   if (stencilVals && depthVals) {
+      for (j = 0; j < height; j++) {
+         _mesa_unpack_float_z_row(depthRb->Format, width, depthMap, depthVals);
+         _mesa_unpack_ubyte_stencil_row(stencilRb->Format, width,
+                                        stencilMap, stencilVals);
 
-      _mesa_pack_depth_stencil_span(ctx, width, type, (GLuint *)dst,
-				    depthVals, stencilVals, packing);
+         _mesa_pack_depth_stencil_span(ctx, width, type, (GLuint *)dst,
+                                       depthVals, stencilVals, packing);
 
-      depthMap += depthStride;
-      stencilMap += stencilStride;
-      dst += dstStride;
+         depthMap += depthStride;
+         stencilMap += stencilStride;
+         dst += dstStride;
+      }
    }
+   else {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glReadPixels");
+   }
+
+   free(stencilVals);
+   free(depthVals);
 
    ctx->Driver.UnmapRenderbuffer(ctx, depthRb);
    if (stencilRb != depthRb) {
diff --git a/mesalib/src/mesa/main/texstore.c b/mesalib/src/mesa/main/texstore.c
index e8190c392..d368b1868 100644
--- a/mesalib/src/mesa/main/texstore.c
+++ b/mesalib/src/mesa/main/texstore.c
@@ -2797,6 +2797,15 @@ _mesa_texstore_z24_s8(TEXSTORE_PARAMS)
    }
    else if (srcFormat == GL_DEPTH_COMPONENT ||
             srcFormat == GL_STENCIL_INDEX) {
+      GLuint *depth = (GLuint *) malloc(srcWidth * sizeof(GLuint));
+      GLubyte *stencil = (GLubyte *) malloc(srcWidth * sizeof(GLubyte));
+
+      if (!depth || !stencil) {
+         free(depth);
+         free(stencil);
+         return GL_FALSE;
+      }
+
       /* In case we only upload depth we need to preserve the stencil */
       for (img = 0; img < srcDepth; img++) {
 	 GLuint *dstRow = (GLuint *) dstSlices[img];
@@ -2806,8 +2815,6 @@ _mesa_texstore_z24_s8(TEXSTORE_PARAMS)
                   srcFormat, srcType,
                   img, 0, 0);
          for (row = 0; row < srcHeight; row++) {
-            GLuint depth[MAX_WIDTH];
-	    GLubyte stencil[MAX_WIDTH];
             GLint i;
 	    GLboolean keepdepth = GL_FALSE, keepstencil = GL_FALSE;
 
@@ -2845,6 +2852,9 @@ _mesa_texstore_z24_s8(TEXSTORE_PARAMS)
             dstRow += dstRowStride / sizeof(GLuint);
          }
       }
+
+      free(depth);
+      free(stencil);
    }
    return GL_TRUE;
 }
@@ -2860,6 +2870,8 @@ _mesa_texstore_s8_z24(TEXSTORE_PARAMS)
    const GLint srcRowStride
       = _mesa_image_row_stride(srcPacking, srcWidth, srcFormat, srcType);
    GLint img, row;
+   GLuint *depth;
+   GLubyte *stencil;
 
    ASSERT(dstFormat == MESA_FORMAT_S8_Z24);
    ASSERT(srcFormat == GL_DEPTH_STENCIL_EXT ||
@@ -2868,6 +2880,15 @@ _mesa_texstore_s8_z24(TEXSTORE_PARAMS)
    ASSERT(srcFormat != GL_DEPTH_STENCIL_EXT ||
           srcType == GL_UNSIGNED_INT_24_8_EXT);
 
+   depth = (GLuint *) malloc(srcWidth * sizeof(GLuint));
+   stencil = (GLubyte *) malloc(srcWidth * sizeof(GLubyte));
+
+   if (!depth || !stencil) {
+      free(depth);
+      free(stencil);
+      return GL_FALSE;
+   }
+
    for (img = 0; img < srcDepth; img++) {
       GLuint *dstRow = (GLuint *) dstSlices[img];
       const GLubyte *src
@@ -2876,8 +2897,6 @@ _mesa_texstore_s8_z24(TEXSTORE_PARAMS)
 						srcFormat, srcType,
 						img, 0, 0);
       for (row = 0; row < srcHeight; row++) {
-	 GLuint depth[MAX_WIDTH];
-	 GLubyte stencil[MAX_WIDTH];
 	 GLint i;
 	 GLboolean keepdepth = GL_FALSE, keepstencil = GL_FALSE;
 	 
@@ -2916,6 +2935,10 @@ _mesa_texstore_s8_z24(TEXSTORE_PARAMS)
 	 dstRow += dstRowStride / sizeof(GLuint);
       }
    }
+
+   free(depth);
+   free(stencil);
+
    return GL_TRUE;
 }
 
@@ -2944,7 +2967,11 @@ _mesa_texstore_s8(TEXSTORE_PARAMS)
       const GLint srcRowStride
 	 = _mesa_image_row_stride(srcPacking, srcWidth, srcFormat, srcType);
       GLint img, row;
-      
+      GLubyte *stencil = (GLubyte *) malloc(srcWidth * sizeof(GLubyte));
+
+      if (!stencil)
+         return GL_FALSE;
+
       for (img = 0; img < srcDepth; img++) {
          GLubyte *dstRow = dstSlices[img];
          const GLubyte *src
@@ -2953,7 +2980,6 @@ _mesa_texstore_s8(TEXSTORE_PARAMS)
                                                    srcFormat, srcType,
                                                    img, 0, 0);
          for (row = 0; row < srcHeight; row++) {
-            GLubyte stencil[MAX_WIDTH];
             GLint i;
 
             /* get the 8-bit stencil values */
@@ -2971,6 +2997,7 @@ _mesa_texstore_s8(TEXSTORE_PARAMS)
          }
       }
 
+      free(stencil);
    }
 
    return GL_TRUE;
diff --git a/mesalib/src/mesa/program/prog_execute.h b/mesalib/src/mesa/program/prog_execute.h
index 6365b0741..1ae302c32 100644
--- a/mesalib/src/mesa/program/prog_execute.h
+++ b/mesalib/src/mesa/program/prog_execute.h
@@ -1,87 +1,91 @@
-/*

- * Mesa 3-D graphics library

- * Version:  7.0.3

- *

- * Copyright (C) 1999-2007  Brian Paul   All Rights Reserved.

- *

- * Permission is hereby granted, free of charge, to any person obtaining a

- * copy of this software and associated documentation files (the "Software"),

- * to deal in the Software without restriction, including without limitation

- * the rights to use, copy, modify, merge, publish, distribute, sublicense,

- * and/or sell copies of the Software, and to permit persons to whom the

- * Software is furnished to do so, subject to the following conditions:

- *

- * The above copyright notice and this permission notice shall be included

- * in all copies or substantial portions of the Software.

- *

- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS

- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL

- * BRIAN PAUL BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN

- * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN

- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

- */

-

-#ifndef PROG_EXECUTE_H

-#define PROG_EXECUTE_H

-

-#include "main/config.h"

-#include "main/mtypes.h"

-

-

-typedef void (*FetchTexelLodFunc)(struct gl_context *ctx, const GLfloat texcoord[4],

-                                  GLfloat lambda, GLuint unit, GLfloat color[4]);

-

-typedef void (*FetchTexelDerivFunc)(struct gl_context *ctx, const GLfloat texcoord[4],

-                                    const GLfloat texdx[4],

-                                    const GLfloat texdy[4],

-                                    GLfloat lodBias,

-                                    GLuint unit, GLfloat color[4]);

-

-

-/**

- * Virtual machine state used during execution of vertex/fragment programs.

- */

-struct gl_program_machine

-{

-   const struct gl_program *CurProgram;

-

-   /** Fragment Input attributes */

-   GLfloat (*Attribs)[MAX_WIDTH][4];

-   GLfloat (*DerivX)[4];

-   GLfloat (*DerivY)[4];

-   GLuint NumDeriv; /**< Max index into DerivX/Y arrays */

-   GLuint CurElement; /**< Index into Attribs arrays */

-

-   /** Vertex Input attribs */

-   GLfloat VertAttribs[VERT_ATTRIB_MAX][4];

-

-   GLfloat Temporaries[MAX_PROGRAM_TEMPS][4];

-   GLfloat Outputs[MAX_PROGRAM_OUTPUTS][4];

-   GLfloat (*EnvParams)[4]; /**< Vertex or Fragment env parameters */

-   GLuint CondCodes[4];  /**< COND_* value for x/y/z/w */

-   GLint AddressReg[MAX_PROGRAM_ADDRESS_REGS][4];

-   GLfloat SystemValues[SYSTEM_VALUE_MAX][4];

-

-   const GLubyte *Samplers;  /** Array mapping sampler var to tex unit */

-

-   GLuint CallStack[MAX_PROGRAM_CALL_DEPTH]; /**< For CAL/RET instructions */

-   GLuint StackDepth; /**< Index/ptr to top of CallStack[] */

-

-   /** Texture fetch functions */

-   FetchTexelLodFunc FetchTexelLod;

-   FetchTexelDerivFunc FetchTexelDeriv;

-};

-

-

-extern void

-_mesa_get_program_register(struct gl_context *ctx, gl_register_file file,

-                           GLuint index, GLfloat val[4]);

-

-extern GLboolean

-_mesa_execute_program(struct gl_context *ctx,

-                      const struct gl_program *program,

-                      struct gl_program_machine *machine);

-

-

-#endif /* PROG_EXECUTE_H */

+/*
+ * Mesa 3-D graphics library
+ * Version:  7.0.3
+ *
+ * Copyright (C) 1999-2007  Brian Paul   All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * BRIAN PAUL BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef PROG_EXECUTE_H
+#define PROG_EXECUTE_H
+
+#include "main/config.h"
+#include "main/mtypes.h"
+
+
+typedef void (*FetchTexelLodFunc)(struct gl_context *ctx, const GLfloat texcoord[4],
+                                  GLfloat lambda, GLuint unit, GLfloat color[4]);
+
+typedef void (*FetchTexelDerivFunc)(struct gl_context *ctx, const GLfloat texcoord[4],
+                                    const GLfloat texdx[4],
+                                    const GLfloat texdy[4],
+                                    GLfloat lodBias,
+                                    GLuint unit, GLfloat color[4]);
+
+
+/** NOTE: This must match SWRAST_MAX_WIDTH */
+#define PROG_MAX_WIDTH 16384
+
+
+/**
+ * Virtual machine state used during execution of vertex/fragment programs.
+ */
+struct gl_program_machine
+{
+   const struct gl_program *CurProgram;
+
+   /** Fragment Input attributes */
+   GLfloat (*Attribs)[PROG_MAX_WIDTH][4];
+   GLfloat (*DerivX)[4];
+   GLfloat (*DerivY)[4];
+   GLuint NumDeriv; /**< Max index into DerivX/Y arrays */
+   GLuint CurElement; /**< Index into Attribs arrays */
+
+   /** Vertex Input attribs */
+   GLfloat VertAttribs[VERT_ATTRIB_MAX][4];
+
+   GLfloat Temporaries[MAX_PROGRAM_TEMPS][4];
+   GLfloat Outputs[MAX_PROGRAM_OUTPUTS][4];
+   GLfloat (*EnvParams)[4]; /**< Vertex or Fragment env parameters */
+   GLuint CondCodes[4];  /**< COND_* value for x/y/z/w */
+   GLint AddressReg[MAX_PROGRAM_ADDRESS_REGS][4];
+   GLfloat SystemValues[SYSTEM_VALUE_MAX][4];
+
+   const GLubyte *Samplers;  /** Array mapping sampler var to tex unit */
+
+   GLuint CallStack[MAX_PROGRAM_CALL_DEPTH]; /**< For CAL/RET instructions */
+   GLuint StackDepth; /**< Index/ptr to top of CallStack[] */
+
+   /** Texture fetch functions */
+   FetchTexelLodFunc FetchTexelLod;
+   FetchTexelDerivFunc FetchTexelDeriv;
+};
+
+
+extern void
+_mesa_get_program_register(struct gl_context *ctx, gl_register_file file,
+                           GLuint index, GLfloat val[4]);
+
+extern GLboolean
+_mesa_execute_program(struct gl_context *ctx,
+                      const struct gl_program *program,
+                      struct gl_program_machine *machine);
+
+
+#endif /* PROG_EXECUTE_H */
diff --git a/mesalib/src/mesa/state_tracker/st_cb_drawpixels.c b/mesalib/src/mesa/state_tracker/st_cb_drawpixels.c
index de4c189a8..18d0e53d4 100644
--- a/mesalib/src/mesa/state_tracker/st_cb_drawpixels.c
+++ b/mesalib/src/mesa/state_tracker/st_cb_drawpixels.c
@@ -824,9 +824,10 @@ draw_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
    enum pipe_transfer_usage usage;
    struct pipe_transfer *pt;
    const GLboolean zoom = ctx->Pixel.ZoomX != 1.0 || ctx->Pixel.ZoomY != 1.0;
-   GLint skipPixels;
    ubyte *stmap;
    struct gl_pixelstore_attrib clippedUnpack = *unpack;
+   GLubyte *sValues;
+   GLuint *zValues;
 
    if (!zoom) {
       if (!_mesa_clip_drawpixels(ctx, &x, &y, &width, &height,
@@ -862,22 +863,19 @@ draw_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
    pixels = _mesa_map_pbo_source(ctx, &clippedUnpack, pixels);
    assert(pixels);
 
-   /* if width > MAX_WIDTH, have to process image in chunks */
-   skipPixels = 0;
-   while (skipPixels < width) {
-      const GLint spanX = skipPixels;
-      const GLint spanWidth = MIN2(width - skipPixels, MAX_WIDTH);
+   sValues = (GLubyte *) malloc(width * sizeof(GLubyte));
+   zValues = (GLuint *) malloc(width * sizeof(GLuint));
+
+   if (sValues && zValues) {
       GLint row;
       for (row = 0; row < height; row++) {
-         GLubyte sValues[MAX_WIDTH];
-         GLuint zValues[MAX_WIDTH];
          GLfloat *zValuesFloat = (GLfloat*)zValues;
          GLenum destType = GL_UNSIGNED_BYTE;
          const GLvoid *source = _mesa_image_address2d(&clippedUnpack, pixels,
                                                       width, height,
                                                       format, type,
-                                                      row, skipPixels);
-         _mesa_unpack_stencil_span(ctx, spanWidth, destType, sValues,
+                                                      row, 0);
+         _mesa_unpack_stencil_span(ctx, width, destType, sValues,
                                    type, source, &clippedUnpack,
                                    ctx->_ImageTransferState);
 
@@ -886,7 +884,7 @@ draw_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
                pt->resource->format == PIPE_FORMAT_Z32_FLOAT_S8X24_UINT ?
                GL_FLOAT : GL_UNSIGNED_INT;
 
-            _mesa_unpack_depth_span(ctx, spanWidth, ztype, zValues,
+            _mesa_unpack_depth_span(ctx, width, ztype, zValues,
                                     (1 << 24) - 1, type, source,
                                     &clippedUnpack);
          }
@@ -910,63 +908,63 @@ draw_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
             switch (pt->resource->format) {
             case PIPE_FORMAT_S8_UINT:
                {
-                  ubyte *dest = stmap + spanY * pt->stride + spanX;
+                  ubyte *dest = stmap + spanY * pt->stride;
                   assert(usage == PIPE_TRANSFER_WRITE);
-                  memcpy(dest, sValues, spanWidth);
+                  memcpy(dest, sValues, width);
                }
                break;
             case PIPE_FORMAT_Z24_UNORM_S8_UINT:
                if (format == GL_DEPTH_STENCIL) {
-                  uint *dest = (uint *) (stmap + spanY * pt->stride + spanX*4);
+                  uint *dest = (uint *) (stmap + spanY * pt->stride);
                   GLint k;
                   assert(usage == PIPE_TRANSFER_WRITE);
-                  for (k = 0; k < spanWidth; k++) {
+                  for (k = 0; k < width; k++) {
                      dest[k] = zValues[k] | (sValues[k] << 24);
                   }
                }
                else {
-                  uint *dest = (uint *) (stmap + spanY * pt->stride + spanX*4);
+                  uint *dest = (uint *) (stmap + spanY * pt->stride);
                   GLint k;
                   assert(usage == PIPE_TRANSFER_READ_WRITE);
-                  for (k = 0; k < spanWidth; k++) {
+                  for (k = 0; k < width; k++) {
                      dest[k] = (dest[k] & 0xffffff) | (sValues[k] << 24);
                   }
                }
                break;
             case PIPE_FORMAT_S8_UINT_Z24_UNORM:
                if (format == GL_DEPTH_STENCIL) {
-                  uint *dest = (uint *) (stmap + spanY * pt->stride + spanX*4);
+                  uint *dest = (uint *) (stmap + spanY * pt->stride);
                   GLint k;
                   assert(usage == PIPE_TRANSFER_WRITE);
-                  for (k = 0; k < spanWidth; k++) {
+                  for (k = 0; k < width; k++) {
                      dest[k] = (zValues[k] << 8) | (sValues[k] & 0xff);
                   }
                }
                else {
-                  uint *dest = (uint *) (stmap + spanY * pt->stride + spanX*4);
+                  uint *dest = (uint *) (stmap + spanY * pt->stride);
                   GLint k;
                   assert(usage == PIPE_TRANSFER_READ_WRITE);
-                  for (k = 0; k < spanWidth; k++) {
+                  for (k = 0; k < width; k++) {
                      dest[k] = (dest[k] & 0xffffff00) | (sValues[k] & 0xff);
                   }
                }
                break;
             case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
                if (format == GL_DEPTH_STENCIL) {
-                  uint *dest = (uint *) (stmap + spanY * pt->stride + spanX*4);
+                  uint *dest = (uint *) (stmap + spanY * pt->stride);
                   GLfloat *destf = (GLfloat*)dest;
                   GLint k;
                   assert(usage == PIPE_TRANSFER_WRITE);
-                  for (k = 0; k < spanWidth; k++) {
+                  for (k = 0; k < width; k++) {
                      destf[k*2] = zValuesFloat[k];
                      dest[k*2+1] = sValues[k] & 0xff;
                   }
                }
                else {
-                  uint *dest = (uint *) (stmap + spanY * pt->stride + spanX*4);
+                  uint *dest = (uint *) (stmap + spanY * pt->stride);
                   GLint k;
                   assert(usage == PIPE_TRANSFER_READ_WRITE);
-                  for (k = 0; k < spanWidth; k++) {
+                  for (k = 0; k < width; k++) {
                      dest[k*2+1] = sValues[k] & 0xff;
                   }
                }
@@ -976,8 +974,13 @@ draw_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
             }
          }
       }
-      skipPixels += spanWidth;
    }
+   else {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels()");
+   }
+
+   free(sValues);
+   free(zValues);
 
    _mesa_unmap_pbo_source(ctx, &clippedUnpack);
 
diff --git a/mesalib/src/mesa/state_tracker/st_cb_texture.c b/mesalib/src/mesa/state_tracker/st_cb_texture.c
index d887455e6..ea59ccf25 100644
--- a/mesalib/src/mesa/state_tracker/st_cb_texture.c
+++ b/mesalib/src/mesa/state_tracker/st_cb_texture.c
@@ -684,9 +684,16 @@ decompress_with_blit(struct gl_context * ctx,
       /* format translation via floats */
       GLuint row;
       enum pipe_format pformat = util_format_linear(dst_texture->format);
+      GLfloat *rgba;
+
+      rgba = (GLfloat *) malloc(width * 4 * sizeof(GLfloat));
+      if (!rgba) {
+         _mesa_error(ctx, GL_OUT_OF_MEMORY, "glGetTexImage()");
+         goto end;
+      }
+
       for (row = 0; row < height; row++) {
          const GLbitfield transferOps = 0x0; /* bypassed for glGetTexImage() */
-         GLfloat rgba[4 * MAX_WIDTH];
          GLvoid *dest = _mesa_image_address2d(&ctx->Pack, pixels, width,
                                               height, format, type, row, 0);
 
@@ -700,8 +707,11 @@ decompress_with_blit(struct gl_context * ctx,
          _mesa_pack_rgba_span_float(ctx, width, (GLfloat (*)[4]) rgba, format,
                                     type, dest, &ctx->Pack, transferOps);
       }
+
+      free(rgba);
    }
 
+end:
    _mesa_unmap_pbo_dest(ctx, &ctx->Pack);
 
    pipe->transfer_destroy(pipe, tex_xfer);
@@ -763,8 +773,6 @@ fallback_copy_texsubimage(struct gl_context *ctx,
    if (ST_DEBUG & DEBUG_FALLBACK)
       debug_printf("%s: fallback processing\n", __FUNCTION__);
 
-   assert(width <= MAX_WIDTH);
-
    if (st_fb_orientation(ctx->ReadBuffer) == Y_0_TOP) {
       srcY = strb->Base.Height - srcY - height;
    }
@@ -793,6 +801,7 @@ fallback_copy_texsubimage(struct gl_context *ctx,
       const GLboolean scaleOrBias = (ctx->Pixel.DepthScale != 1.0F ||
                                      ctx->Pixel.DepthBias != 0.0F);
       GLint row, yStep;
+      uint *data;
 
       /* determine bottom-to-top vs. top-to-bottom order for src buffer */
       if (st_fb_orientation(ctx->ReadBuffer) == Y_0_TOP) {
@@ -804,15 +813,23 @@ fallback_copy_texsubimage(struct gl_context *ctx,
          yStep = 1;
       }
 
-      /* To avoid a large temp memory allocation, do copy row by row */
-      for (row = 0; row < height; row++, srcY += yStep) {
-         uint data[MAX_WIDTH];
-         pipe_get_tile_z(pipe, src_trans, 0, srcY, width, 1, data);
-         if (scaleOrBias) {
-            _mesa_scale_and_bias_depth_uint(ctx, width, data);
+      data = (uint *) malloc(width * sizeof(uint));
+
+      if (data) {
+         /* To avoid a large temp memory allocation, do copy row by row */
+         for (row = 0; row < height; row++, srcY += yStep) {
+            pipe_get_tile_z(pipe, src_trans, 0, srcY, width, 1, data);
+            if (scaleOrBias) {
+               _mesa_scale_and_bias_depth_uint(ctx, width, data);
+            }
+            pipe_put_tile_z(pipe, stImage->transfer, 0, row, width, 1, data);
          }
-         pipe_put_tile_z(pipe, stImage->transfer, 0, row, width, 1, data);
       }
+      else {
+         _mesa_error(ctx, GL_OUT_OF_MEMORY, "glCopyTexSubImage()");
+      }
+
+      free(data);
    }
    else {
       /* RGBA format */
diff --git a/mesalib/src/mesa/state_tracker/st_extensions.c b/mesalib/src/mesa/state_tracker/st_extensions.c
index fb36a6809..33bc6ed72 100644
--- a/mesalib/src/mesa/state_tracker/st_extensions.c
+++ b/mesalib/src/mesa/state_tracker/st_extensions.c
@@ -108,6 +108,14 @@ void st_init_limits(struct st_context *st)
 
    c->MaxTextureUnits = _min(c->MaxTextureImageUnits, c->MaxTextureCoordUnits);
 
+   /* Define max viewport size and max renderbuffer size in terms of
+    * max texture size (note: max tex RECT size = max tex 2D size).
+    * If this isn't true for some hardware we'll need new PIPE_CAP_ queries.
+    */
+   c->MaxViewportWidth =
+   c->MaxViewportHeight =
+   c->MaxRenderbufferSize = c->MaxTextureRectSize;
+
    c->MaxDrawBuffers
       = _clamp(screen->get_param(screen, PIPE_CAP_MAX_RENDER_TARGETS),
               1, MAX_DRAW_BUFFERS);
diff --git a/mesalib/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/mesalib/src/mesa/state_tracker/st_glsl_to_tgsi.cpp
index f139e95fe..b0227855c 100644
--- a/mesalib/src/mesa/state_tracker/st_glsl_to_tgsi.cpp
+++ b/mesalib/src/mesa/state_tracker/st_glsl_to_tgsi.cpp
@@ -4746,8 +4746,6 @@ get_mesa_program(struct gl_context *ctx,
 {
    glsl_to_tgsi_visitor* v = new glsl_to_tgsi_visitor();
    struct gl_program *prog;
-   struct pipe_screen * screen = st_context(ctx)->pipe->screen;
-   unsigned pipe_shader_type;
    GLenum target;
    const char *target_string;
    bool progress;
@@ -4758,17 +4756,14 @@ get_mesa_program(struct gl_context *ctx,
    case GL_VERTEX_SHADER:
       target = GL_VERTEX_PROGRAM_ARB;
       target_string = "vertex";
-      pipe_shader_type = PIPE_SHADER_VERTEX;
       break;
    case GL_FRAGMENT_SHADER:
       target = GL_FRAGMENT_PROGRAM_ARB;
       target_string = "fragment";
-      pipe_shader_type = PIPE_SHADER_FRAGMENT;
       break;
    case GL_GEOMETRY_SHADER:
       target = GL_GEOMETRY_PROGRAM_NV;
       target_string = "geometry";
-      pipe_shader_type = PIPE_SHADER_GEOMETRY;
       break;
    default:
       assert(!"should not be reached");
@@ -4792,12 +4787,8 @@ get_mesa_program(struct gl_context *ctx,
    _mesa_generate_parameters_list_for_uniforms(shader_program, shader,
 					       prog->Parameters);
 
-   if (!screen->get_shader_param(screen, pipe_shader_type,
-                                 PIPE_SHADER_CAP_OUTPUT_READ)) {
-      /* Remove reads to output registers, and to varyings in vertex shaders. */
-      lower_output_reads(shader->ir);
-   }
-
+   /* Remove reads from output registers. */
+   lower_output_reads(shader->ir);
 
    /* Emit intermediate IR for main(). */
    visit_exec_list(shader->ir, v);
diff --git a/mesalib/src/mesa/swrast/s_aalinetemp.h b/mesalib/src/mesa/swrast/s_aalinetemp.h
index ba9f8abb9..a517fb697 100644
--- a/mesalib/src/mesa/swrast/s_aalinetemp.h
+++ b/mesalib/src/mesa/swrast/s_aalinetemp.h
@@ -91,7 +91,7 @@ NAME(plot)(struct gl_context *ctx, struct LineInfo *line, int ix, int iy)
    ATTRIB_LOOP_END
 #endif
 
-   if (line->span.end == MAX_WIDTH) {
+   if (line->span.end == SWRAST_MAX_WIDTH) {
       _swrast_write_rgba_span(ctx, &(line->span));
       line->span.end = 0; /* reset counter */
    }
diff --git a/mesalib/src/mesa/swrast/s_aatritemp.h b/mesalib/src/mesa/swrast/s_aatritemp.h
index 77b3ae6ec..9cdb35fd2 100644
--- a/mesalib/src/mesa/swrast/s_aatritemp.h
+++ b/mesalib/src/mesa/swrast/s_aatritemp.h
@@ -196,7 +196,7 @@
          span.array = SWRAST_CONTEXT(ctx)->SpanArrays + omp_get_thread_num();
 #endif
          /* skip over fragments with zero coverage */
-         while (startX < MAX_WIDTH) {
+         while (startX < SWRAST_MAX_WIDTH) {
             coverage = compute_coveragef(pMin, pMid, pMax, startX, iy);
             if (coverage > 0.0F)
                break;
diff --git a/mesalib/src/mesa/swrast/s_bitmap.c b/mesalib/src/mesa/swrast/s_bitmap.c
index 18f1c1866..3a2792913 100644
--- a/mesalib/src/mesa/swrast/s_bitmap.c
+++ b/mesalib/src/mesa/swrast/s_bitmap.c
@@ -123,7 +123,7 @@ _swrast_Bitmap( struct gl_context *ctx, GLint px, GLint py,
             src++;
       }
 
-      if (count + width >= MAX_WIDTH || row + 1 == height) {
+      if (count + width >= SWRAST_MAX_WIDTH || row + 1 == height) {
          /* flush the span */
          span.end = count;
          _swrast_write_rgba_span(ctx, &span);
diff --git a/mesalib/src/mesa/swrast/s_blend.c b/mesalib/src/mesa/swrast/s_blend.c
index cd6e6f036..54fffbb45 100644
--- a/mesalib/src/mesa/swrast/s_blend.c
+++ b/mesalib/src/mesa/swrast/s_blend.c
@@ -998,7 +998,7 @@ _swrast_blend_span(struct gl_context *ctx, struct gl_renderbuffer *rb, SWspan *s
    SWcontext *swrast = SWRAST_CONTEXT(ctx);
    void *rbPixels;
 
-   ASSERT(span->end <= MAX_WIDTH);
+   ASSERT(span->end <= SWRAST_MAX_WIDTH);
    ASSERT(span->arrayMask & SPAN_RGBA);
    ASSERT(!ctx->Color.ColorLogicOpEnabled);
 
diff --git a/mesalib/src/mesa/swrast/s_chan.h b/mesalib/src/mesa/swrast/s_chan.h
index 94ac8b65b..1db7fae4d 100644
--- a/mesalib/src/mesa/swrast/s_chan.h
+++ b/mesalib/src/mesa/swrast/s_chan.h
@@ -36,6 +36,14 @@
 
 
 /**
+ * Default bits per color channel:  8, 16 or 32
+ */
+#ifndef CHAN_BITS
+#define CHAN_BITS 8
+#endif
+
+
+/**
  * Color channel data type.
  */
 #if CHAN_BITS == 8
diff --git a/mesalib/src/mesa/swrast/s_context.c b/mesalib/src/mesa/swrast/s_context.c
index cc304d70c..63350b2e7 100644
--- a/mesalib/src/mesa/swrast/s_context.c
+++ b/mesalib/src/mesa/swrast/s_context.c
@@ -726,6 +726,18 @@ _swrast_CreateContext( struct gl_context *ctx )
    const GLuint maxThreads = 1;
 #endif
 
+   assert(ctx->Const.MaxViewportWidth <= SWRAST_MAX_WIDTH);
+   assert(ctx->Const.MaxViewportHeight <= SWRAST_MAX_WIDTH);
+
+   assert(ctx->Const.MaxRenderbufferSize <= SWRAST_MAX_WIDTH);
+
+   /* make sure largest texture image is <= SWRAST_MAX_WIDTH in size */
+   assert((1 << (ctx->Const.MaxTextureLevels - 1)) <= SWRAST_MAX_WIDTH);
+   assert((1 << (ctx->Const.MaxCubeTextureLevels - 1)) <= SWRAST_MAX_WIDTH);
+   assert((1 << (ctx->Const.Max3DTextureLevels - 1)) <= SWRAST_MAX_WIDTH);
+
+   assert(PROG_MAX_WIDTH == SWRAST_MAX_WIDTH);
+
    if (SWRAST_DEBUG) {
       _mesa_debug(ctx, "_swrast_CreateContext\n");
    }
@@ -790,6 +802,19 @@ _swrast_CreateContext( struct gl_context *ctx )
 
    ctx->swrast_context = swrast;
 
+   swrast->stencil_temp.buf1 = (GLubyte *) malloc(SWRAST_MAX_WIDTH * sizeof(GLubyte));
+   swrast->stencil_temp.buf2 = (GLubyte *) malloc(SWRAST_MAX_WIDTH * sizeof(GLubyte));
+   swrast->stencil_temp.buf3 = (GLubyte *) malloc(SWRAST_MAX_WIDTH * sizeof(GLubyte));
+   swrast->stencil_temp.buf4 = (GLubyte *) malloc(SWRAST_MAX_WIDTH * sizeof(GLubyte));
+
+   if (!swrast->stencil_temp.buf1 ||
+       !swrast->stencil_temp.buf2 ||
+       !swrast->stencil_temp.buf3 ||
+       !swrast->stencil_temp.buf4) {
+      _swrast_DestroyContext(ctx);
+      return GL_FALSE;
+   }
+
    return GL_TRUE;
 }
 
@@ -806,6 +831,12 @@ _swrast_DestroyContext( struct gl_context *ctx )
    if (swrast->ZoomedArrays)
       FREE( swrast->ZoomedArrays );
    FREE( swrast->TexelBuffer );
+
+   free(swrast->stencil_temp.buf1);
+   free(swrast->stencil_temp.buf2);
+   free(swrast->stencil_temp.buf3);
+   free(swrast->stencil_temp.buf4);
+
    FREE( swrast );
 
    ctx->swrast_context = 0;
diff --git a/mesalib/src/mesa/swrast/s_context.h b/mesalib/src/mesa/swrast/s_context.h
index 9388c3569..26b97f78d 100644
--- a/mesalib/src/mesa/swrast/s_context.h
+++ b/mesalib/src/mesa/swrast/s_context.h
@@ -306,6 +306,13 @@ typedef struct
    /** State used during execution of fragment programs */
    struct gl_program_machine FragProgMachine;
 
+   /** Temporary arrays for stencil operations.  To avoid large stack
+    * allocations.
+    */
+   struct {
+      GLubyte *buf1, *buf2, *buf3, *buf4;
+   } stencil_temp;
+
 } SWcontext;
 
 
diff --git a/mesalib/src/mesa/swrast/s_copypix.c b/mesalib/src/mesa/swrast/s_copypix.c
index 592d35a98..cf419c328 100644
--- a/mesalib/src/mesa/swrast/s_copypix.c
+++ b/mesalib/src/mesa/swrast/s_copypix.c
@@ -158,7 +158,7 @@ copy_rgba_pixels(struct gl_context *ctx, GLint srcx, GLint srcy,
       p = NULL;
    }
 
-   ASSERT(width < MAX_WIDTH);
+   ASSERT(width < SWRAST_MAX_WIDTH);
 
    for (row = 0; row < height; row++, sy += stepy, dy += stepy) {
       GLvoid *rgba = span.array->attribs[FRAG_ATTRIB_COL0];
@@ -246,7 +246,7 @@ copy_depth_pixels( struct gl_context *ctx, GLint srcx, GLint srcy,
 {
    struct gl_framebuffer *fb = ctx->ReadBuffer;
    struct gl_renderbuffer *readRb = fb->Attachment[BUFFER_DEPTH].Renderbuffer;
-   GLfloat *p, *tmpImage;
+   GLfloat *p, *tmpImage, *depth;
    GLint sy, dy, stepy;
    GLint j;
    const GLboolean zoom = ctx->Pixel.ZoomX != 1.0F || ctx->Pixel.ZoomY != 1.0F;
@@ -303,8 +303,13 @@ copy_depth_pixels( struct gl_context *ctx, GLint srcx, GLint srcy,
       p = NULL;
    }
 
+   depth = (GLfloat *) malloc(width * sizeof(GLfloat));
+   if (!depth) {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glCopyPixels()");
+      goto end;
+   }
+
    for (j = 0; j < height; j++, sy += stepy, dy += stepy) {
-      GLfloat depth[MAX_WIDTH];
       /* get depth values */
       if (overlapping) {
          memcpy(depth, p, width * sizeof(GLfloat));
@@ -327,6 +332,9 @@ copy_depth_pixels( struct gl_context *ctx, GLint srcx, GLint srcy,
          _swrast_write_rgba_span(ctx, &span);
    }
 
+   free(depth);
+
+end:
    if (overlapping)
       free(tmpImage);
 }
@@ -342,7 +350,7 @@ copy_stencil_pixels( struct gl_context *ctx, GLint srcx, GLint srcy,
    struct gl_renderbuffer *rb = fb->Attachment[BUFFER_STENCIL].Renderbuffer;
    GLint sy, dy, stepy;
    GLint j;
-   GLubyte *p, *tmpImage;
+   GLubyte *p, *tmpImage, *stencil;
    const GLboolean zoom = ctx->Pixel.ZoomX != 1.0F || ctx->Pixel.ZoomY != 1.0F;
    GLint overlapping;
 
@@ -392,9 +400,13 @@ copy_stencil_pixels( struct gl_context *ctx, GLint srcx, GLint srcy,
       p = NULL;
    }
 
-   for (j = 0; j < height; j++, sy += stepy, dy += stepy) {
-      GLubyte stencil[MAX_WIDTH];
+   stencil = (GLubyte *) malloc(width * sizeof(GLubyte));
+   if (!stencil) {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glCopyPixels()");
+      goto end;
+   }
 
+   for (j = 0; j < height; j++, sy += stepy, dy += stepy) {
       /* Get stencil values */
       if (overlapping) {
          memcpy(stencil, p, width * sizeof(GLubyte));
@@ -416,6 +428,9 @@ copy_stencil_pixels( struct gl_context *ctx, GLint srcx, GLint srcy,
       }
    }
 
+   free(stencil);
+
+end:
    if (overlapping)
       free(tmpImage);
 }
diff --git a/mesalib/src/mesa/swrast/s_depth.c b/mesalib/src/mesa/swrast/s_depth.c
index c90388209..26126a932 100644
--- a/mesalib/src/mesa/swrast/s_depth.c
+++ b/mesalib/src/mesa/swrast/s_depth.c
@@ -419,9 +419,15 @@ _swrast_depth_bounds_test( struct gl_context *ctx, SWspan *span )
    const GLuint count = span->end;
    GLuint i;
    GLboolean anyPass = GL_FALSE;
-   GLuint zBufferTemp[MAX_WIDTH];
+   GLuint *zBufferTemp;
    const GLuint *zBufferVals;
 
+   zBufferTemp = (GLuint *) malloc(count * sizeof(GLuint));
+   if (!zBufferTemp) {
+      /* don't generate a stream of OUT_OF_MEMORY errors here */
+      return GL_FALSE;
+   }
+
    if (span->arrayMask & SPAN_XY)
       zStart = NULL;
    else
@@ -453,6 +459,8 @@ _swrast_depth_bounds_test( struct gl_context *ctx, SWspan *span )
       }
    }
 
+   free(zBufferTemp);
+
    return anyPass;
 }
 
diff --git a/mesalib/src/mesa/swrast/s_drawpix.c b/mesalib/src/mesa/swrast/s_drawpix.c
index c19808bd4..1fa64c378 100644
--- a/mesalib/src/mesa/swrast/s_drawpix.c
+++ b/mesalib/src/mesa/swrast/s_drawpix.c
@@ -264,34 +264,35 @@ draw_stencil_pixels( struct gl_context *ctx, GLint x, GLint y,
 {
    const GLboolean zoom = ctx->Pixel.ZoomX != 1.0 || ctx->Pixel.ZoomY != 1.0;
    const GLenum destType = GL_UNSIGNED_BYTE;
-   GLint skipPixels;
+   GLint row;
+   GLubyte *values;
 
-   /* if width > MAX_WIDTH, have to process image in chunks */
-   skipPixels = 0;
-   while (skipPixels < width) {
-      const GLint spanX = x + skipPixels;
-      const GLint spanWidth = MIN2(width - skipPixels, MAX_WIDTH);
-      GLint row;
-      for (row = 0; row < height; row++) {
-         const GLint spanY = y + row;
-         GLubyte values[MAX_WIDTH];
-         const GLvoid *source = _mesa_image_address2d(unpack, pixels,
-                                                      width, height,
-                                                      GL_STENCIL_INDEX, type,
-                                                      row, skipPixels);
-         _mesa_unpack_stencil_span(ctx, spanWidth, destType, values,
-                                   type, source, unpack,
-                                   ctx->_ImageTransferState);
-         if (zoom) {
-            _swrast_write_zoomed_stencil_span(ctx, x, y, spanWidth,
-                                              spanX, spanY, values);
-         }
-         else {
-            _swrast_write_stencil_span(ctx, spanWidth, spanX, spanY, values);
-         }
+   values = (GLubyte *) malloc(width * sizeof(GLubyte));
+   if (!values) {
+      _mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels");
+      return;
+   }
+
+   for (row = 0; row < height; row++) {
+      const GLvoid *source = _mesa_image_address2d(unpack, pixels,
+                                                   width, height,
+                                                   GL_STENCIL_INDEX, type,
+                                                   row, 0);
+      _mesa_unpack_stencil_span(ctx, width, destType, values,
+                                type, source, unpack,
+                                ctx->_ImageTransferState);
+      if (zoom) {
+         _swrast_write_zoomed_stencil_span(ctx, x, y, width,
+                                           x, y, values);
+      }
+      else {
+         _swrast_write_stencil_span(ctx, width, x, y, values);
       }
-      skipPixels += spanWidth;
+
+      y++;
    }
+
+   free(values);
 }
 
 
@@ -318,7 +319,7 @@ draw_depth_pixels( struct gl_context *ctx, GLint x, GLint y,
        && ctx->DrawBuffer->Visual.depthBits == 16
        && !scaleOrBias
        && !zoom
-       && width <= MAX_WIDTH
+       && width <= SWRAST_MAX_WIDTH
        && !unpack->SwapBytes) {
       /* Special case: directly write 16-bit depth values */
       GLint row;
@@ -338,7 +339,7 @@ draw_depth_pixels( struct gl_context *ctx, GLint x, GLint y,
    else if (type == GL_UNSIGNED_INT
             && !scaleOrBias
             && !zoom
-            && width <= MAX_WIDTH
+            && width <= SWRAST_MAX_WIDTH
             && !unpack->SwapBytes) {
       /* Special case: shift 32-bit values down to Visual.depthBits */
       const GLint shift = 32 - ctx->DrawBuffer->Visual.depthBits;
@@ -366,11 +367,11 @@ draw_depth_pixels( struct gl_context *ctx, GLint x, GLint y,
       const GLuint depthMax = ctx->DrawBuffer->_DepthMax;
       GLint skipPixels = 0;
 
-      /* in case width > MAX_WIDTH do the copy in chunks */
+      /* in case width > SWRAST_MAX_WIDTH do the copy in chunks */
       while (skipPixels < width) {
-         const GLint spanWidth = MIN2(width - skipPixels, MAX_WIDTH);
+         const GLint spanWidth = MIN2(width - skipPixels, SWRAST_MAX_WIDTH);
          GLint row;
-         ASSERT(span.end <= MAX_WIDTH);
+         ASSERT(span.end <= SWRAST_MAX_WIDTH);
          for (row = 0; row < height; row++) {
             const GLvoid *zSrc = _mesa_image_address2d(unpack,
                                                       pixels, width, height,
@@ -452,9 +453,9 @@ draw_rgba_pixels( struct gl_context *ctx, GLint x, GLint y,
       /* use span array for temp color storage */
       GLfloat *rgba = (GLfloat *) span.array->attribs[FRAG_ATTRIB_COL0];
 
-      /* if the span is wider than MAX_WIDTH we have to do it in chunks */
+      /* if the span is wider than SWRAST_MAX_WIDTH we have to do it in chunks */
       while (skipPixels < width) {
-         const GLint spanWidth = MIN2(width - skipPixels, MAX_WIDTH);
+         const GLint spanWidth = MIN2(width - skipPixels, SWRAST_MAX_WIDTH);
          const GLubyte *source
             = (const GLubyte *) _mesa_image_address2d(unpack, pixels,
                                                       width, height, format,
@@ -588,15 +589,21 @@ draw_depth_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
        * Separate depth/stencil buffers, or pixel transfer ops required.
        */
       /* XXX need to handle very wide images (skippixels) */
+      GLuint *zValues;  /* 32-bit Z values */
       GLint i;
 
+      zValues = (GLuint *) malloc(width * sizeof(GLuint));
+      if (!zValues) {
+         _mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels");
+         return;
+      }
+
       for (i = 0; i < height; i++) {
          const GLuint *depthStencilSrc = (const GLuint *)
             _mesa_image_address2d(&clippedUnpack, pixels, width, height,
                                   GL_DEPTH_STENCIL_EXT, type, i, 0);
 
          if (ctx->Depth.Mask) {
-            GLuint zValues[MAX_WIDTH];  /* 32-bit Z values */
             _mesa_unpack_depth_span(ctx, width,
                                     GL_UNSIGNED_INT, /* dest type */
                                     zValues,         /* dest addr */
@@ -615,7 +622,7 @@ draw_depth_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
          }
 
          if (stencilMask != 0x0) {
-            GLubyte stencilValues[MAX_WIDTH];
+            GLubyte *stencilValues = (GLubyte *) zValues; /* re-use buffer */
             /* get stencil values, with shift/offset/mapping */
             _mesa_unpack_stencil_span(ctx, width, stencilType, stencilValues,
                                       type, depthStencilSrc, &clippedUnpack,
@@ -627,6 +634,8 @@ draw_depth_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
                _swrast_write_stencil_span(ctx, width, x, y + i, stencilValues);
          }
       }
+
+      free(zValues);
    }
 }
 
diff --git a/mesalib/src/mesa/swrast/s_lines.c b/mesalib/src/mesa/swrast/s_lines.c
index ee997b08a..2078be43b 100644
--- a/mesalib/src/mesa/swrast/s_lines.c
+++ b/mesalib/src/mesa/swrast/s_lines.c
@@ -67,7 +67,7 @@ draw_wide_line( struct gl_context *ctx, SWspan *span, GLboolean xMajor )
                                      ctx->Const.MaxLineWidth);
    GLint start;
 
-   ASSERT(span->end < MAX_WIDTH);
+   ASSERT(span->end < SWRAST_MAX_WIDTH);
 
    if (width & 1)
       start = width / 2;
diff --git a/mesalib/src/mesa/swrast/s_logic.c b/mesalib/src/mesa/swrast/s_logic.c
index e908a0efe..8791630a4 100644
--- a/mesalib/src/mesa/swrast/s_logic.c
+++ b/mesalib/src/mesa/swrast/s_logic.c
@@ -193,7 +193,7 @@ _swrast_logicop_rgba_span(struct gl_context *ctx, struct gl_renderbuffer *rb,
 {
    void *rbPixels;
 
-   ASSERT(span->end < MAX_WIDTH);
+   ASSERT(span->end < SWRAST_MAX_WIDTH);
    ASSERT(span->arrayMask & SPAN_RGBA);
 
    rbPixels = _swrast_get_dest_rgba(ctx, rb, span);
diff --git a/mesalib/src/mesa/swrast/s_masking.c b/mesalib/src/mesa/swrast/s_masking.c
index 2d962ebc5..4f262fa97 100644
--- a/mesalib/src/mesa/swrast/s_masking.c
+++ b/mesalib/src/mesa/swrast/s_masking.c
@@ -46,7 +46,7 @@ _swrast_mask_rgba_span(struct gl_context *ctx, struct gl_renderbuffer *rb,
    const GLuint n = span->end;
    void *rbPixels;
 
-   ASSERT(n < MAX_WIDTH);
+   ASSERT(n < SWRAST_MAX_WIDTH);
    ASSERT(span->arrayMask & SPAN_RGBA);
 
    rbPixels = _swrast_get_dest_rgba(ctx, rb, span);
diff --git a/mesalib/src/mesa/swrast/s_points.c b/mesalib/src/mesa/swrast/s_points.c
index 11b7ef7b1..acbdb2d42 100644
--- a/mesalib/src/mesa/swrast/s_points.c
+++ b/mesalib/src/mesa/swrast/s_points.c
@@ -439,7 +439,7 @@ large_point(struct gl_context *ctx, const SWvertex *vert)
             span.end++;
          }
       }
-      assert(span.end <= MAX_WIDTH);
+      assert(span.end <= SWRAST_MAX_WIDTH);
       _swrast_write_rgba_span(ctx, &span);
    }
 }
@@ -475,7 +475,7 @@ pixel_point(struct gl_context *ctx, const SWvertex *vert)
    span->attrStepY[FRAG_ATTRIB_WPOS][3] = 0.0F;
 
    /* check if we need to flush */
-   if (span->end >= MAX_WIDTH ||
+   if (span->end >= SWRAST_MAX_WIDTH ||
        (swrast->_RasterMask & (BLEND_BIT | LOGIC_OP_BIT | MASKING_BIT)) ||
        span->facing != swrast->PointLineFacing) {
       if (span->end > 0) {
@@ -504,7 +504,7 @@ pixel_point(struct gl_context *ctx, const SWvertex *vert)
    span->array->z[count] = (GLint) (vert->attrib[FRAG_ATTRIB_WPOS][2] + 0.5F);
 
    span->end = count + 1;
-   ASSERT(span->end <= MAX_WIDTH);
+   ASSERT(span->end <= SWRAST_MAX_WIDTH);
 }
 
 
diff --git a/mesalib/src/mesa/swrast/s_span.c b/mesalib/src/mesa/swrast/s_span.c
index 025e7b207..627ef1136 100644
--- a/mesalib/src/mesa/swrast/s_span.c
+++ b/mesalib/src/mesa/swrast/s_span.c
@@ -1164,7 +1164,7 @@ _swrast_write_rgba_span( struct gl_context *ctx, SWspan *span)
       return;
    }
 
-   ASSERT(span->end <= MAX_WIDTH);
+   ASSERT(span->end <= SWRAST_MAX_WIDTH);
 
    /* Depth bounds test */
    if (ctx->Depth.BoundsTest && fb->Visual.depthBits > 0) {
@@ -1319,7 +1319,8 @@ _swrast_write_rgba_span( struct gl_context *ctx, SWspan *span)
          /* color[fragOutput] will be written to buffer[buf] */
 
          if (rb) {
-            GLchan rgbaSave[MAX_WIDTH][4];
+            /* re-use one of the attribute array buffers for rgbaSave */
+            GLchan (*rgbaSave)[4] = (GLchan (*)[4]) span->array->attribs[0];
             struct swrast_renderbuffer *srb = swrast_renderbuffer(rb);
             GLenum colorType = srb->ColorType;
 
diff --git a/mesalib/src/mesa/swrast/s_span.h b/mesalib/src/mesa/swrast/s_span.h
index ff0fe6cd9..0763c7161 100644
--- a/mesalib/src/mesa/swrast/s_span.h
+++ b/mesalib/src/mesa/swrast/s_span.h
@@ -32,6 +32,7 @@
 #include "main/glheader.h"
 #include "main/mtypes.h"
 #include "swrast/s_chan.h"
+#include "swrast/swrast.h"
 
 
 struct gl_context;
@@ -71,24 +72,24 @@ typedef struct sw_span_arrays
    /* XXX someday look at transposing first two indexes for better memory
     * access pattern.
     */
-   GLfloat attribs[FRAG_ATTRIB_MAX][MAX_WIDTH][4];
+   GLfloat attribs[FRAG_ATTRIB_MAX][SWRAST_MAX_WIDTH][4];
 
    /** This mask indicates which fragments are alive or culled */
-   GLubyte mask[MAX_WIDTH];
+   GLubyte mask[SWRAST_MAX_WIDTH];
 
    GLenum ChanType; /**< Color channel type, GL_UNSIGNED_BYTE, GL_FLOAT */
 
    /** Attribute arrays that don't fit into attribs[] array above */
    /*@{*/
-   GLubyte rgba8[MAX_WIDTH][4];
-   GLushort rgba16[MAX_WIDTH][4];
+   GLubyte rgba8[SWRAST_MAX_WIDTH][4];
+   GLushort rgba16[SWRAST_MAX_WIDTH][4];
    GLchan (*rgba)[4];  /** either == rgba8 or rgba16 */
-   GLint   x[MAX_WIDTH];  /**< fragment X coords */
-   GLint   y[MAX_WIDTH];  /**< fragment Y coords */
-   GLuint  z[MAX_WIDTH];  /**< fragment Z coords */
-   GLuint  index[MAX_WIDTH];  /**< Color indexes */
-   GLfloat lambda[MAX_TEXTURE_COORD_UNITS][MAX_WIDTH]; /**< Texture LOD */
-   GLfloat coverage[MAX_WIDTH];  /**< Fragment coverage for AA/smoothing */
+   GLint   x[SWRAST_MAX_WIDTH];  /**< fragment X coords */
+   GLint   y[SWRAST_MAX_WIDTH];  /**< fragment Y coords */
+   GLuint  z[SWRAST_MAX_WIDTH];  /**< fragment Z coords */
+   GLuint  index[SWRAST_MAX_WIDTH];  /**< Color indexes */
+   GLfloat lambda[MAX_TEXTURE_COORD_UNITS][SWRAST_MAX_WIDTH]; /**< Texture LOD */
+   GLfloat coverage[SWRAST_MAX_WIDTH];  /**< Fragment coverage for AA/smoothing */
    /*@}*/
 } SWspanarrays;
 
diff --git a/mesalib/src/mesa/swrast/s_stencil.c b/mesalib/src/mesa/swrast/s_stencil.c
index bbfbf44cc..3423737ee 100644
--- a/mesalib/src/mesa/swrast/s_stencil.c
+++ b/mesalib/src/mesa/swrast/s_stencil.c
@@ -210,7 +210,8 @@ static GLboolean
 do_stencil_test(struct gl_context *ctx, GLuint face, GLuint n,
                 GLubyte stencil[], GLubyte mask[], GLint stride)
 {
-   GLubyte fail[MAX_WIDTH];
+   SWcontext *swrast = SWRAST_CONTEXT(ctx);
+   GLubyte *fail = swrast->stencil_temp.buf2;
    GLboolean allfail = GL_FALSE;
    GLuint i, j;
    const GLuint valueMask = ctx->Stencil.ValueMask[face];
@@ -347,6 +348,7 @@ put_s8_values(struct gl_context *ctx, struct gl_renderbuffer *rb,
 GLboolean
 _swrast_stencil_and_ztest_span(struct gl_context *ctx, SWspan *span)
 {
+   SWcontext *swrast = SWRAST_CONTEXT(ctx);
    struct gl_framebuffer *fb = ctx->DrawBuffer;
    struct gl_renderbuffer *rb = fb->Attachment[BUFFER_STENCIL].Renderbuffer;
    const GLint stencilOffset = get_stencil_offset(rb->Format);
@@ -354,7 +356,7 @@ _swrast_stencil_and_ztest_span(struct gl_context *ctx, SWspan *span)
    const GLuint face = (span->facing == 0) ? 0 : ctx->Stencil._BackFace;
    const GLuint count = span->end;
    GLubyte *mask = span->array->mask;
-   GLubyte stencilTemp[MAX_WIDTH];
+   GLubyte *stencilTemp = swrast->stencil_temp.buf1;
    GLubyte *stencilBuf;
 
    if (span->arrayMask & SPAN_XY) {
@@ -402,7 +404,10 @@ _swrast_stencil_and_ztest_span(struct gl_context *ctx, SWspan *span)
       /*
        * Perform depth buffering, then apply zpass or zfail stencil function.
        */
-      GLubyte passMask[MAX_WIDTH], failMask[MAX_WIDTH], origMask[MAX_WIDTH];
+      SWcontext *swrast = SWRAST_CONTEXT(ctx);
+      GLubyte *passMask = swrast->stencil_temp.buf2;
+      GLubyte *failMask = swrast->stencil_temp.buf3;
+      GLubyte *origMask = swrast->stencil_temp.buf4;
 
       /* save the current mask bits */
       memcpy(origMask, mask, count * sizeof(GLubyte));
@@ -488,6 +493,7 @@ void
 _swrast_write_stencil_span(struct gl_context *ctx, GLint n, GLint x, GLint y,
                            const GLubyte stencil[] )
 {
+   SWcontext *swrast = SWRAST_CONTEXT(ctx);
    struct gl_framebuffer *fb = ctx->DrawBuffer;
    struct gl_renderbuffer *rb = fb->Attachment[BUFFER_STENCIL].Renderbuffer;
    const GLuint stencilMax = (1 << fb->Visual.stencilBits) - 1;
@@ -517,7 +523,8 @@ _swrast_write_stencil_span(struct gl_context *ctx, GLint n, GLint x, GLint y,
 
    if ((stencilMask & stencilMax) != stencilMax) {
       /* need to apply writemask */
-      GLubyte destVals[MAX_WIDTH], newVals[MAX_WIDTH];
+      GLubyte *destVals = swrast->stencil_temp.buf1;
+      GLubyte *newVals = swrast->stencil_temp.buf2;
       GLint i;
 
       _mesa_unpack_ubyte_stencil_row(rb->Format, n, stencilBuf, destVals);
diff --git a/mesalib/src/mesa/swrast/s_texcombine.c b/mesalib/src/mesa/swrast/s_texcombine.c
index 1fce5c565..8fbf988b4 100644
--- a/mesalib/src/mesa/swrast/s_texcombine.c
+++ b/mesalib/src/mesa/swrast/s_texcombine.c
@@ -49,9 +49,9 @@ static inline float4_array
 get_texel_array(SWcontext *swrast, GLuint unit)
 {
 #ifdef _OPENMP
-   return (float4_array) (swrast->TexelBuffer + unit * MAX_WIDTH * 4 * omp_get_num_threads() + (MAX_WIDTH * 4 * omp_get_thread_num()));
+   return (float4_array) (swrast->TexelBuffer + unit * SWRAST_MAX_WIDTH * 4 * omp_get_num_threads() + (SWRAST_MAX_WIDTH * 4 * omp_get_thread_num()));
 #else
-   return (float4_array) (swrast->TexelBuffer + unit * MAX_WIDTH * 4);
+   return (float4_array) (swrast->TexelBuffer + unit * SWRAST_MAX_WIDTH * 4);
 #endif
 }
 
@@ -611,7 +611,7 @@ _swrast_texture_span( struct gl_context *ctx, SWspan *span )
        */
       swrast->TexelBuffer =
 	 (GLfloat *) MALLOC(ctx->Const.MaxTextureImageUnits * maxThreads *
-			    MAX_WIDTH * 4 * sizeof(GLfloat));
+			    SWRAST_MAX_WIDTH * 4 * sizeof(GLfloat));
       if (!swrast->TexelBuffer) {
 	 _mesa_error(ctx, GL_OUT_OF_MEMORY, "texture_combine");
 	 return;
@@ -625,7 +625,7 @@ _swrast_texture_span( struct gl_context *ctx, SWspan *span )
       return;
    }
 
-   ASSERT(span->end <= MAX_WIDTH);
+   ASSERT(span->end <= SWRAST_MAX_WIDTH);
 
    /*
     * Save copy of the incoming fragment colors (the GL_PRIMARY_COLOR)
diff --git a/mesalib/src/mesa/swrast/s_triangle.c b/mesalib/src/mesa/swrast/s_triangle.c
index ddb4792f7..e89a999a9 100644
--- a/mesalib/src/mesa/swrast/s_triangle.c
+++ b/mesalib/src/mesa/swrast/s_triangle.c
@@ -142,7 +142,7 @@ _swrast_culltriangle( struct gl_context *ctx,
 
 #define RENDER_SPAN( span )						\
    GLuint i;								\
-   GLubyte rgba[MAX_WIDTH][4];						\
+   GLubyte (*rgba)[4] = swrast->SpanArrays->rgba8;			\
    span.intTex[0] -= FIXED_HALF; /* off-by-one error? */		\
    span.intTex[1] -= FIXED_HALF;					\
    for (i = 0; i < span.end; i++) {					\
@@ -200,7 +200,8 @@ _swrast_culltriangle( struct gl_context *ctx,
 
 #define RENDER_SPAN( span )						\
    GLuint i;				    				\
-   GLubyte rgba[MAX_WIDTH][4];						\
+   GLubyte (*rgba)[4] = swrast->SpanArrays->rgba8;			\
+   GLubyte *mask = swrast->SpanArrays->mask;                            \
    span.intTex[0] -= FIXED_HALF; /* off-by-one error? */		\
    span.intTex[1] -= FIXED_HALF;					\
    for (i = 0; i < span.end; i++) {					\
@@ -215,17 +216,17 @@ _swrast_culltriangle( struct gl_context *ctx,
          rgba[i][BCOMP] = texture[pos+0];				\
          rgba[i][ACOMP] = 0xff;          				\
          zRow[i] = z;							\
-         span.array->mask[i] = 1;					\
+         mask[i] = 1;							\
       }									\
       else {								\
-         span.array->mask[i] = 0;					\
+         mask[i] = 0;							\
       }									\
       span.intTex[0] += span.intTexStep[0];				\
       span.intTex[1] += span.intTexStep[1];				\
       span.z += span.zStep;						\
    }									\
    _swrast_put_row(ctx, rb, GL_UNSIGNED_BYTE,                           \
-                   span.end, span.x, span.y, rgba, span.array->mask);
+                   span.end, span.x, span.y, rgba, mask);
 
 #include "s_tritemp.h"
 
diff --git a/mesalib/src/mesa/swrast/s_zoom.c b/mesalib/src/mesa/swrast/s_zoom.c
index 73bff482b..768bbbafd 100644
--- a/mesalib/src/mesa/swrast/s_zoom.c
+++ b/mesalib/src/mesa/swrast/s_zoom.c
@@ -150,7 +150,7 @@ zoom_span( struct gl_context *ctx, GLint imgX, GLint imgY, const SWspan *span,
 
    zoomedWidth = x1 - x0;
    ASSERT(zoomedWidth > 0);
-   ASSERT(zoomedWidth <= MAX_WIDTH);
+   ASSERT(zoomedWidth <= SWRAST_MAX_WIDTH);
 
    /* no pixel arrays! must be horizontal spans. */
    ASSERT((span->arrayMask & SPAN_XY) == 0);
@@ -362,7 +362,7 @@ _swrast_write_zoomed_stencil_span(struct gl_context *ctx, GLint imgX, GLint imgY
                                   GLint width, GLint spanX, GLint spanY,
                                   const GLubyte stencil[])
 {
-   GLubyte zoomedVals[MAX_WIDTH];
+   GLubyte *zoomedVals;
    GLint x0, x1, y0, y1, y;
    GLint i, zoomedWidth;
 
@@ -373,7 +373,11 @@ _swrast_write_zoomed_stencil_span(struct gl_context *ctx, GLint imgX, GLint imgY
 
    zoomedWidth = x1 - x0;
    ASSERT(zoomedWidth > 0);
-   ASSERT(zoomedWidth <= MAX_WIDTH);
+   ASSERT(zoomedWidth <= SWRAST_MAX_WIDTH);
+
+   zoomedVals = (GLubyte *) malloc(zoomedWidth * sizeof(GLubyte));
+   if (!zoomedVals)
+      return;
 
    /* zoom the span horizontally */
    for (i = 0; i < zoomedWidth; i++) {
@@ -387,6 +391,8 @@ _swrast_write_zoomed_stencil_span(struct gl_context *ctx, GLint imgX, GLint imgY
    for (y = y0; y < y1; y++) {
       _swrast_write_stencil_span(ctx, zoomedWidth, x0, y, zoomedVals);
    }
+
+   free(zoomedVals);
 }
 
 
@@ -401,7 +407,7 @@ _swrast_write_zoomed_z_span(struct gl_context *ctx, GLint imgX, GLint imgY,
 {
    struct gl_renderbuffer *rb =
       ctx->DrawBuffer->Attachment[BUFFER_DEPTH].Renderbuffer;
-   GLuint zoomedVals[MAX_WIDTH];
+   GLuint *zoomedVals;
    GLint x0, x1, y0, y1, y;
    GLint i, zoomedWidth;
 
@@ -412,7 +418,11 @@ _swrast_write_zoomed_z_span(struct gl_context *ctx, GLint imgX, GLint imgY,
 
    zoomedWidth = x1 - x0;
    ASSERT(zoomedWidth > 0);
-   ASSERT(zoomedWidth <= MAX_WIDTH);
+   ASSERT(zoomedWidth <= SWRAST_MAX_WIDTH);
+
+   zoomedVals = (GLuint *) malloc(zoomedWidth * sizeof(GLuint));
+   if (!zoomedVals)
+      return;
 
    /* zoom the span horizontally */
    for (i = 0; i < zoomedWidth; i++) {
@@ -427,4 +437,6 @@ _swrast_write_zoomed_z_span(struct gl_context *ctx, GLint imgX, GLint imgY,
       GLubyte *dst = _swrast_pixel_address(rb, x0, y);
       _mesa_pack_uint_z_row(rb->Format, zoomedWidth, zoomedVals, dst);
    }
+
+   free(zoomedVals);
 }
diff --git a/mesalib/src/mesa/swrast/swrast.h b/mesalib/src/mesa/swrast/swrast.h
index ad19eeecc..a299e6fda 100644
--- a/mesalib/src/mesa/swrast/swrast.h
+++ b/mesalib/src/mesa/swrast/swrast.h
@@ -35,6 +35,34 @@
 #include "main/mtypes.h"
 #include "swrast/s_chan.h"
 
+
+/**
+ * If non-zero use GLdouble for walking triangle edges, for better accuracy.
+ */
+#define TRIANGLE_WALK_DOUBLE 0
+
+
+/**
+ * Bits per depth buffer value (max is 32).
+ */
+#ifndef DEFAULT_SOFTWARE_DEPTH_BITS
+#define DEFAULT_SOFTWARE_DEPTH_BITS 16
+#endif
+/** Depth buffer data type */
+#if DEFAULT_SOFTWARE_DEPTH_BITS <= 16
+#define DEFAULT_SOFTWARE_DEPTH_TYPE GLushort
+#else
+#define DEFAULT_SOFTWARE_DEPTH_TYPE GLuint
+#endif
+
+
+/**
+ * Max image/surface/texture size.
+ */
+#define SWRAST_MAX_WIDTH 16384
+#define SWRAST_MAX_HEIGHT 16384
+
+
 /**
  * \struct SWvertex
  * \brief Data-structure to handle vertices in the software rasterizer.