Merge remote-tracking branch 'origin/released'

Conflicts:
	apps/xwininfo/configure.ac
	apps/xwininfo/xwininfo.c
	libX11/configure.ac
	libX11/specs/libX11/AppC.xml
	libX11/specs/libX11/AppD.xml
	libX11/specs/libX11/CH03.xml
	libX11/specs/libX11/CH04.xml
	libX11/specs/libX11/CH05.xml
	libX11/specs/libX11/CH06.xml
	libX11/specs/libX11/CH07.xml
	libX11/specs/libX11/CH08.xml
	libX11/specs/libX11/CH09.xml
	libX11/specs/libX11/CH11.xml
	libX11/specs/libX11/CH12.xml
	libX11/specs/libX11/CH13.xml
	libX11/specs/libX11/CH14.xml
	libX11/specs/libX11/CH15.xml
	libX11/specs/libX11/CH16.xml
	libxcb/configure.ac
	libxcb/src/c_client.py
	libxcb/src/xcb_auth.c
	libxcb/src/xcb_util.c
	mesalib/common.py
	mesalib/configs/linux-dri
	mesalib/docs/GL3.txt
	mesalib/docs/download.html
	mesalib/docs/install.html
	mesalib/include/GL/internal/dri_interface.h
	mesalib/scons/custom.py
	mesalib/scons/gallium.py
	mesalib/src/gallium/auxiliary/util/u_math.h
	mesalib/src/gallium/auxiliary/util/u_vbuf_mgr.c
	mesalib/src/glsl/ast_function.cpp
	mesalib/src/glsl/ast_to_hir.cpp
	mesalib/src/glsl/glcpp/glcpp-parse.y
	mesalib/src/glsl/glsl_parser_extras.cpp
	mesalib/src/glsl/glsl_parser_extras.h
	mesalib/src/glsl/ir.cpp
	mesalib/src/glsl/ir.h
	mesalib/src/glsl/ir_clone.cpp
	mesalib/src/glsl/ir_print_visitor.cpp
	mesalib/src/glsl/ir_validate.cpp
	mesalib/src/glsl/linker.cpp
	mesalib/src/glsl/main.cpp
	mesalib/src/glsl/opt_tree_grafting.cpp
	mesalib/src/mapi/glapi/gen/Makefile
	mesalib/src/mapi/glapi/gen/gl_XML.py
	mesalib/src/mapi/glapi/gen/gl_table.py
	mesalib/src/mapi/glapi/glapi_mapi_tmp.h
	mesalib/src/mapi/glapi/glapi_sparc.S
	mesalib/src/mapi/glapi/glapi_x86-64.S
	mesalib/src/mapi/glapi/glapi_x86.S
	mesalib/src/mapi/glapi/glapitemp.h
	mesalib/src/mapi/glapi/glprocs.h
	mesalib/src/mapi/mapi/u_thread.c
	mesalib/src/mapi/mapi/u_thread.h
	mesalib/src/mesa/SConscript
	mesalib/src/mesa/drivers/common/driverfuncs.c
	mesalib/src/mesa/drivers/windows/gldirect/dglcontext.c
	mesalib/src/mesa/main/api_arrayelt.c
	mesalib/src/mesa/main/bufferobj.c
	mesalib/src/mesa/main/compiler.h
	mesalib/src/mesa/main/dd.h
	mesalib/src/mesa/main/dlist.c
	mesalib/src/mesa/main/enums.c
	mesalib/src/mesa/main/es_generator.py
	mesalib/src/mesa/main/fbobject.c
	mesalib/src/mesa/main/imports.h
	mesalib/src/mesa/main/mtypes.h
	mesalib/src/mesa/main/pbo.c
	mesalib/src/mesa/main/remap_helper.h
	mesalib/src/mesa/main/shared.c
	mesalib/src/mesa/main/texgetimage.c
	mesalib/src/mesa/main/teximage.c
	mesalib/src/mesa/main/uniforms.c
	mesalib/src/mesa/program/ir_to_mesa.cpp
	mesalib/src/mesa/program/prog_optimize.c
	mesalib/src/mesa/program/register_allocate.c
	mesalib/src/mesa/program/register_allocate.h
	mesalib/src/mesa/sources.mak
	mesalib/src/mesa/state_tracker/st_cb_bufferobjects.c
	mesalib/src/mesa/state_tracker/st_cb_texture.c
	mesalib/src/mesa/state_tracker/st_texture.h
	mesalib/src/mesa/swrast/s_context.c
	mesalib/src/mesa/tnl/t_draw.c
	mesalib/src/mesa/vbo/vbo_exec_array.c
	mesalib/src/mesa/vbo/vbo_save_api.c
	pixman/pixman/pixman-arm-common.h
	pixman/pixman/pixman-fast-path.c
	pixman/pixman/pixman-inlines.h
	pixman/test/Makefile.am
	pixman/test/utils.c
	pixman/test/utils.h
	xorg-server/configure.ac
	xorg-server/fb/fbblt.c
	xorg-server/hw/xquartz/darwin.c
	xorg-server/xkeyboard-config/symbols/de

18 files changed, 2383 insertions, 2177 deletions

diff --git a/pixman/pixman/Makefile.am b/pixman/pixman/Makefile.am
index acc273145..44e6b17e4 100644
--- a/pixman/pixman/Makefile.am
+++ b/pixman/pixman/Makefile.am
@@ -1,129 +1,129 @@
-lib_LTLIBRARIES = libpixman-1.la

-libpixman_1_la_LDFLAGS = -version-info $(LT_VERSION_INFO) -no-undefined @PTHREAD_LDFLAGS@ 

-libpixman_1_la_LIBADD = @PTHREAD_LIBS@ @DEP_LIBS@ -lm

-libpixman_1_la_SOURCES =			\

-	pixman.h				\

-	pixman-accessor.h			\

-	pixman-access.c				\

-	pixman-access-accessors.c		\

-	pixman-cpu.c				\

-	pixman-gradient-walker.c		\

-	pixman-region16.c			\

-	pixman-region32.c			\

-	pixman-compiler.h			\

-	pixman-private.h			\

-	pixman-image.c				\

-	pixman-implementation.c			\

-	pixman-combine32.c			\

-	pixman-combine32.h			\

-	pixman-combine64.c			\

-	pixman-combine64.h			\

-	pixman-general.c			\

-	pixman.c				\

-	pixman-noop.c				\

-	pixman-fast-path.c			\

-	pixman-fast-path.h			\

-	pixman-solid-fill.c			\

-	pixman-conical-gradient.c		\

-	pixman-linear-gradient.c		\

-	pixman-radial-gradient.c		\

-	pixman-bits-image.c			\

-	pixman-utils.c				\

-	pixman-edge.c				\

-	pixman-edge-accessors.c			\

-	pixman-edge-imp.h			\

-	pixman-trap.c				\

-	pixman-timer.c				\

-	pixman-matrix.c

-

-libpixmanincludedir = $(includedir)/pixman-1

-libpixmaninclude_HEADERS = pixman.h pixman-version.h

-noinst_LTLIBRARIES = 

-

-BUILT_SOURCES = pixman-combine32.h pixman-combine32.c pixman-combine64.h pixman-combine64.c

-

-pixman-combine32.c : pixman-combine.c.template pixman-combine32.h make-combine.pl

-	$(PERL) $(srcdir)/make-combine.pl 8 < $(srcdir)/pixman-combine.c.template > $@ || ($(RM) $@; exit 1)

-pixman-combine32.h : pixman-combine.h.template make-combine.pl

-	$(PERL) $(srcdir)/make-combine.pl 8 < $(srcdir)/pixman-combine.h.template > $@ || ($(RM) $@; exit 1)

-

-pixman-combine64.c : pixman-combine.c.template pixman-combine64.h make-combine.pl

-	$(PERL) $(srcdir)/make-combine.pl 16 < $(srcdir)/pixman-combine.c.template > $@ || ($(RM) $@; exit 1)

-pixman-combine64.h : pixman-combine.h.template make-combine.pl

-	$(PERL) $(srcdir)/make-combine.pl 16 < $(srcdir)/pixman-combine.h.template > $@ || ($(RM) $@; exit 1)

-

-EXTRA_DIST = Makefile.win32 pixman-combine.c.template make-combine.pl pixman-region.c \

-	pixman-combine.h.template solaris-hwcap.mapfile

-CLEANFILES = pixman-combine32.c pixman-combine64.c pixman-combine32.h pixman-combine64.h

-

-# mmx code

-if USE_MMX

-noinst_LTLIBRARIES += libpixman-mmx.la

-libpixman_mmx_la_SOURCES = \

-	pixman-mmx.c

-libpixman_mmx_la_CFLAGS = $(DEP_CFLAGS) $(MMX_CFLAGS)

-libpixman_mmx_la_LIBADD = $(DEP_LIBS)

-libpixman_1_la_LDFLAGS += $(MMX_LDFLAGS)

-libpixman_1_la_LIBADD += libpixman-mmx.la

-

-ASM_CFLAGS_mmx=$(MMX_CFLAGS)

-endif

-

-# vmx code

-if USE_VMX

-noinst_LTLIBRARIES += libpixman-vmx.la

-libpixman_vmx_la_SOURCES = \

-	pixman-vmx.c \

-	pixman-combine32.h

-libpixman_vmx_la_CFLAGS = $(DEP_CFLAGS) $(VMX_CFLAGS)

-libpixman_vmx_la_LIBADD = $(DEP_LIBS)

-libpixman_1_la_LIBADD += libpixman-vmx.la

-

-ASM_CFLAGS_vmx=$(VMX_CFLAGS)

-endif

-

-# sse2 code

-if USE_SSE2

-noinst_LTLIBRARIES += libpixman-sse2.la

-libpixman_sse2_la_SOURCES = \

-	pixman-sse2.c

-libpixman_sse2_la_CFLAGS = $(DEP_CFLAGS) $(SSE2_CFLAGS)

-libpixman_sse2_la_LIBADD = $(DEP_LIBS)

-libpixman_1_la_LDFLAGS += $(SSE2_LDFLAGS)

-libpixman_1_la_LIBADD += libpixman-sse2.la

-

-ASM_CFLAGS_sse2=$(SSE2_CFLAGS)

-endif

-

-# arm simd code

-if USE_ARM_SIMD

-noinst_LTLIBRARIES += libpixman-arm-simd.la

-libpixman_arm_simd_la_SOURCES = \

-	pixman-arm-simd.c	\

-	pixman-arm-common.h	\

-	pixman-arm-simd-asm.S

-libpixman_arm_simd_la_CFLAGS = $(DEP_CFLAGS)

-libpixman_arm_simd_la_LIBADD = $(DEP_LIBS)

-libpixman_1_la_LIBADD += libpixman-arm-simd.la

-

-ASM_CFLAGS_arm_simd=

-endif

-

-# arm neon code

-if USE_ARM_NEON

-noinst_LTLIBRARIES += libpixman-arm-neon.la

-libpixman_arm_neon_la_SOURCES = \

-        pixman-arm-neon.c	\

-        pixman-arm-common.h	\

-        pixman-arm-neon-asm.S	\

-		pixman-arm-neon-asm-bilinear.S \

-        pixman-arm-neon-asm.h

-libpixman_arm_neon_la_CFLAGS = $(DEP_CFLAGS)

-libpixman_arm_neon_la_LIBADD = $(DEP_LIBS)

-libpixman_1_la_LIBADD += libpixman-arm-neon.la

-

-ASM_CFLAGS_arm_neon=

-endif

-

-.c.s : $(libpixmaninclude_HEADERS) $(BUILT_SOURCES)

-	$(CC) $(CFLAGS) $(ASM_CFLAGS_$(@:pixman-%.s=%)) $(ASM_CFLAGS_$(@:pixman-arm-%.s=arm_%)) -DHAVE_CONFIG_H -I$(srcdir) -I$(builddir) -I$(top_builddir) -S -o $@ $<

+lib_LTLIBRARIES = libpixman-1.la
+libpixman_1_la_LDFLAGS = -version-info $(LT_VERSION_INFO) -no-undefined @PTHREAD_LDFLAGS@ 
+libpixman_1_la_LIBADD = @PTHREAD_LIBS@ @DEP_LIBS@ -lm
+libpixman_1_la_SOURCES =			\
+	pixman.h				\
+	pixman-accessor.h			\
+	pixman-access.c				\
+	pixman-access-accessors.c		\
+	pixman-cpu.c				\
+	pixman-gradient-walker.c		\
+	pixman-region16.c			\
+	pixman-region32.c			\
+	pixman-compiler.h			\
+	pixman-private.h			\
+	pixman-image.c				\
+	pixman-implementation.c			\
+	pixman-combine32.c			\
+	pixman-combine32.h			\
+	pixman-combine64.c			\
+	pixman-combine64.h			\
+	pixman-general.c			\
+	pixman.c				\
+	pixman-noop.c				\
+	pixman-fast-path.c			\
+	pixman-solid-fill.c			\
+	pixman-conical-gradient.c		\
+	pixman-linear-gradient.c		\
+	pixman-radial-gradient.c		\
+	pixman-bits-image.c			\
+	pixman-utils.c				\
+	pixman-edge.c				\
+	pixman-edge-accessors.c			\
+	pixman-edge-imp.h			\
+	pixman-inlines.h			\
+	pixman-trap.c				\
+	pixman-timer.c				\
+	pixman-matrix.c
+
+libpixmanincludedir = $(includedir)/pixman-1
+libpixmaninclude_HEADERS = pixman.h pixman-version.h
+noinst_LTLIBRARIES = 
+
+BUILT_SOURCES = pixman-combine32.h pixman-combine32.c pixman-combine64.h pixman-combine64.c
+
+pixman-combine32.c : pixman-combine.c.template pixman-combine32.h make-combine.pl
+	$(PERL) $(srcdir)/make-combine.pl 8 < $(srcdir)/pixman-combine.c.template > $@ || ($(RM) $@; exit 1)
+pixman-combine32.h : pixman-combine.h.template make-combine.pl
+	$(PERL) $(srcdir)/make-combine.pl 8 < $(srcdir)/pixman-combine.h.template > $@ || ($(RM) $@; exit 1)
+
+pixman-combine64.c : pixman-combine.c.template pixman-combine64.h make-combine.pl
+	$(PERL) $(srcdir)/make-combine.pl 16 < $(srcdir)/pixman-combine.c.template > $@ || ($(RM) $@; exit 1)
+pixman-combine64.h : pixman-combine.h.template make-combine.pl
+	$(PERL) $(srcdir)/make-combine.pl 16 < $(srcdir)/pixman-combine.h.template > $@ || ($(RM) $@; exit 1)
+
+EXTRA_DIST = Makefile.win32 pixman-combine.c.template make-combine.pl pixman-region.c \
+	pixman-combine.h.template solaris-hwcap.mapfile
+CLEANFILES = pixman-combine32.c pixman-combine64.c pixman-combine32.h pixman-combine64.h
+
+# mmx code
+if USE_MMX
+noinst_LTLIBRARIES += libpixman-mmx.la
+libpixman_mmx_la_SOURCES = \
+	pixman-mmx.c
+libpixman_mmx_la_CFLAGS = $(DEP_CFLAGS) $(MMX_CFLAGS)
+libpixman_mmx_la_LIBADD = $(DEP_LIBS)
+libpixman_1_la_LDFLAGS += $(MMX_LDFLAGS)
+libpixman_1_la_LIBADD += libpixman-mmx.la
+
+ASM_CFLAGS_mmx=$(MMX_CFLAGS)
+endif
+
+# vmx code
+if USE_VMX
+noinst_LTLIBRARIES += libpixman-vmx.la
+libpixman_vmx_la_SOURCES = \
+	pixman-vmx.c \
+	pixman-combine32.h
+libpixman_vmx_la_CFLAGS = $(DEP_CFLAGS) $(VMX_CFLAGS)
+libpixman_vmx_la_LIBADD = $(DEP_LIBS)
+libpixman_1_la_LIBADD += libpixman-vmx.la
+
+ASM_CFLAGS_vmx=$(VMX_CFLAGS)
+endif
+
+# sse2 code
+if USE_SSE2
+noinst_LTLIBRARIES += libpixman-sse2.la
+libpixman_sse2_la_SOURCES = \
+	pixman-sse2.c
+libpixman_sse2_la_CFLAGS = $(DEP_CFLAGS) $(SSE2_CFLAGS)
+libpixman_sse2_la_LIBADD = $(DEP_LIBS)
+libpixman_1_la_LDFLAGS += $(SSE2_LDFLAGS)
+libpixman_1_la_LIBADD += libpixman-sse2.la
+
+ASM_CFLAGS_sse2=$(SSE2_CFLAGS)
+endif
+
+# arm simd code
+if USE_ARM_SIMD
+noinst_LTLIBRARIES += libpixman-arm-simd.la
+libpixman_arm_simd_la_SOURCES = \
+	pixman-arm-simd.c	\
+	pixman-arm-common.h	\
+	pixman-arm-simd-asm.S
+libpixman_arm_simd_la_CFLAGS = $(DEP_CFLAGS)
+libpixman_arm_simd_la_LIBADD = $(DEP_LIBS)
+libpixman_1_la_LIBADD += libpixman-arm-simd.la
+
+ASM_CFLAGS_arm_simd=
+endif
+
+# arm neon code
+if USE_ARM_NEON
+noinst_LTLIBRARIES += libpixman-arm-neon.la
+libpixman_arm_neon_la_SOURCES = \
+        pixman-arm-neon.c	\
+        pixman-arm-common.h	\
+        pixman-arm-neon-asm.S	\
+		pixman-arm-neon-asm-bilinear.S \
+        pixman-arm-neon-asm.h
+libpixman_arm_neon_la_CFLAGS = $(DEP_CFLAGS)
+libpixman_arm_neon_la_LIBADD = $(DEP_LIBS)
+libpixman_1_la_LIBADD += libpixman-arm-neon.la
+
+ASM_CFLAGS_arm_neon=
+endif
+
+.c.s : $(libpixmaninclude_HEADERS) $(BUILT_SOURCES)
+	$(CC) $(CFLAGS) $(ASM_CFLAGS_$(@:pixman-%.s=%)) $(ASM_CFLAGS_$(@:pixman-arm-%.s=arm_%)) -DHAVE_CONFIG_H -I$(srcdir) -I$(builddir) -I$(top_builddir) -S -o $@ $<
diff --git a/pixman/pixman/pixman-arm-common.h b/pixman/pixman/pixman-arm-common.h
index de1fd4872..c15af540a 100644
--- a/pixman/pixman/pixman-arm-common.h
+++ b/pixman/pixman/pixman-arm-common.h
@@ -26,7 +26,7 @@
 #ifndef PIXMAN_ARM_COMMON_H

 #define PIXMAN_ARM_COMMON_H

 

-#include "pixman-fast-path.h"

+#include "pixman-inlines.h"

 

 /* Define some macros which can expand into proxy functions between

  * ARM assembly optimized functions and the rest of pixman fast path API.

diff --git a/pixman/pixman/pixman-arm-simd.c b/pixman/pixman/pixman-arm-simd.c
index 45981a6b0..3d19bfac1 100644
--- a/pixman/pixman/pixman-arm-simd.c
+++ b/pixman/pixman/pixman-arm-simd.c
@@ -1,432 +1,432 @@
-/*

- * Copyright © 2008 Mozilla Corporation

- *

- * Permission to use, copy, modify, distribute, and sell this software and its

- * documentation for any purpose is hereby granted without fee, provided that

- * the above copyright notice appear in all copies and that both that

- * copyright notice and this permission notice appear in supporting

- * documentation, and that the name of Mozilla Corporation not be used in

- * advertising or publicity pertaining to distribution of the software without

- * specific, written prior permission.  Mozilla Corporation makes no

- * representations about the suitability of this software for any purpose.  It

- * is provided "as is" without express or implied warranty.

- *

- * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS

- * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND

- * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY

- * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES

- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN

- * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING

- * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS

- * SOFTWARE.

- *

- * Author:  Jeff Muizelaar (jeff@infidigm.net)

- *

- */

-#ifdef HAVE_CONFIG_H

-#include <config.h>

-#endif

-

-#include "pixman-private.h"

-#include "pixman-arm-common.h"

-#include "pixman-fast-path.h"

-

-#if 0 /* This code was moved to 'pixman-arm-simd-asm.S' */

-

-void

-pixman_composite_add_8_8_asm_armv6 (int32_t  width,

-				    int32_t  height,

-				    uint8_t *dst_line,

-				    int32_t  dst_stride,

-				    uint8_t *src_line,

-				    int32_t  src_stride)

-{

-    uint8_t *dst, *src;

-    int32_t w;

-    uint8_t s, d;

-

-    while (height--)

-    {

-	dst = dst_line;

-	dst_line += dst_stride;

-	src = src_line;

-	src_line += src_stride;

-	w = width;

-

-	/* ensure both src and dst are properly aligned before doing 32 bit reads

-	 * we'll stay in this loop if src and dst have differing alignments

-	 */

-	while (w && (((unsigned long)dst & 3) || ((unsigned long)src & 3)))

-	{

-	    s = *src;

-	    d = *dst;

-	    asm ("uqadd8 %0, %1, %2" : "+r" (d) : "r" (s));

-	    *dst = d;

-

-	    dst++;

-	    src++;

-	    w--;

-	}

-

-	while (w >= 4)

-	{

-	    asm ("uqadd8 %0, %1, %2"

-		 : "=r" (*(uint32_t*)dst)

-		 : "r" (*(uint32_t*)src), "r" (*(uint32_t*)dst));

-	    dst += 4;

-	    src += 4;

-	    w -= 4;

-	}

-

-	while (w)

-	{

-	    s = *src;

-	    d = *dst;

-	    asm ("uqadd8 %0, %1, %2" : "+r" (d) : "r" (s));

-	    *dst = d;

-

-	    dst++;

-	    src++;

-	    w--;

-	}

-    }

-

-}

-

-void

-pixman_composite_over_8888_8888_asm_armv6 (int32_t   width,

-                                           int32_t   height,

-                                           uint32_t *dst_line,

-                                           int32_t   dst_stride,

-                                           uint32_t *src_line,

-                                           int32_t   src_stride)

-{

-    uint32_t    *dst;

-    uint32_t    *src;

-    int32_t w;

-    uint32_t component_half = 0x800080;

-    uint32_t upper_component_mask = 0xff00ff00;

-    uint32_t alpha_mask = 0xff;

-

-    while (height--)

-    {

-	dst = dst_line;

-	dst_line += dst_stride;

-	src = src_line;

-	src_line += src_stride;

-	w = width;

-

-/* #define inner_branch */

-	asm volatile (

-	    "cmp %[w], #0\n\t"

-	    "beq 2f\n\t"

-	    "1:\n\t"

-	    /* load src */

-	    "ldr r5, [%[src]], #4\n\t"

-#ifdef inner_branch

-	    /* We can avoid doing the multiplication in two cases: 0x0 or 0xff.

-	     * The 0x0 case also allows us to avoid doing an unecessary data

-	     * write which is more valuable so we only check for that

-	     */

-	    "cmp r5, #0\n\t"

-	    "beq 3f\n\t"

-

-	    /* = 255 - alpha */

-	    "sub r8, %[alpha_mask], r5, lsr #24\n\t"

-

-	    "ldr r4, [%[dest]] \n\t"

-

-#else

-	    "ldr r4, [%[dest]] \n\t"

-

-	    /* = 255 - alpha */

-	    "sub r8, %[alpha_mask], r5, lsr #24\n\t"

-#endif

-	    "uxtb16 r6, r4\n\t"

-	    "uxtb16 r7, r4, ror #8\n\t"

-

-	    /* multiply by 257 and divide by 65536 */

-	    "mla r6, r6, r8, %[component_half]\n\t"

-	    "mla r7, r7, r8, %[component_half]\n\t"

-

-	    "uxtab16 r6, r6, r6, ror #8\n\t"

-	    "uxtab16 r7, r7, r7, ror #8\n\t"

-

-	    /* recombine the 0xff00ff00 bytes of r6 and r7 */

-	    "and r7, r7, %[upper_component_mask]\n\t"

-	    "uxtab16 r6, r7, r6, ror #8\n\t"

-

-	    "uqadd8 r5, r6, r5\n\t"

-

-#ifdef inner_branch

-	    "3:\n\t"

-

-#endif

-	    "str r5, [%[dest]], #4\n\t"

-	    /* increment counter and jmp to top */

-	    "subs	%[w], %[w], #1\n\t"

-	    "bne	1b\n\t"

-	    "2:\n\t"

-	    : [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src)

-	    : [component_half] "r" (component_half), [upper_component_mask] "r" (upper_component_mask),

-	      [alpha_mask] "r" (alpha_mask)

-	    : "r4", "r5", "r6", "r7", "r8", "cc", "memory"

-	    );

-    }

-}

-

-void

-pixman_composite_over_8888_n_8888_asm_armv6 (int32_t   width,

-                                             int32_t   height,

-                                             uint32_t *dst_line,

-                                             int32_t   dst_stride,

-                                             uint32_t *src_line,

-                                             int32_t   src_stride,

-                                             uint32_t  mask)

-{

-    uint32_t *dst;

-    uint32_t *src;

-    int32_t w;

-    uint32_t component_half = 0x800080;

-    uint32_t alpha_mask = 0xff;

-

-    mask = (mask) >> 24;

-

-    while (height--)

-    {

-	dst = dst_line;

-	dst_line += dst_stride;

-	src = src_line;

-	src_line += src_stride;

-	w = width;

-

-/* #define inner_branch */

-	asm volatile (

-	    "cmp %[w], #0\n\t"

-	    "beq 2f\n\t"

-	    "1:\n\t"

-	    /* load src */

-	    "ldr r5, [%[src]], #4\n\t"

-#ifdef inner_branch

-	    /* We can avoid doing the multiplication in two cases: 0x0 or 0xff.

-	     * The 0x0 case also allows us to avoid doing an unecessary data

-	     * write which is more valuable so we only check for that

-	     */

-	    "cmp r5, #0\n\t"

-	    "beq 3f\n\t"

-

-#endif

-	    "ldr r4, [%[dest]] \n\t"

-

-	    "uxtb16 r6, r5\n\t"

-	    "uxtb16 r7, r5, ror #8\n\t"

-

-	    /* multiply by alpha (r8) then by 257 and divide by 65536 */

-	    "mla r6, r6, %[mask_alpha], %[component_half]\n\t"

-	    "mla r7, r7, %[mask_alpha], %[component_half]\n\t"

-

-	    "uxtab16 r6, r6, r6, ror #8\n\t"

-	    "uxtab16 r7, r7, r7, ror #8\n\t"

-

-	    "uxtb16 r6, r6, ror #8\n\t"

-	    "uxtb16 r7, r7, ror #8\n\t"

-

-	    /* recombine */

-	    "orr r5, r6, r7, lsl #8\n\t"

-

-	    "uxtb16 r6, r4\n\t"

-	    "uxtb16 r7, r4, ror #8\n\t"

-

-	    /* 255 - alpha */

-	    "sub r8, %[alpha_mask], r5, lsr #24\n\t"

-

-	    /* multiply by alpha (r8) then by 257 and divide by 65536 */

-	    "mla r6, r6, r8, %[component_half]\n\t"

-	    "mla r7, r7, r8, %[component_half]\n\t"

-

-	    "uxtab16 r6, r6, r6, ror #8\n\t"

-	    "uxtab16 r7, r7, r7, ror #8\n\t"

-

-	    "uxtb16 r6, r6, ror #8\n\t"

-	    "uxtb16 r7, r7, ror #8\n\t"

-

-	    /* recombine */

-	    "orr r6, r6, r7, lsl #8\n\t"

-

-	    "uqadd8 r5, r6, r5\n\t"

-

-#ifdef inner_branch

-	    "3:\n\t"

-

-#endif

-	    "str r5, [%[dest]], #4\n\t"

-	    /* increment counter and jmp to top */

-	    "subs	%[w], %[w], #1\n\t"

-	    "bne	1b\n\t"

-	    "2:\n\t"

-	    : [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src)

-	    : [component_half] "r" (component_half), [mask_alpha] "r" (mask),

-	      [alpha_mask] "r" (alpha_mask)

-	    : "r4", "r5", "r6", "r7", "r8", "r9", "cc", "memory"

-	    );

-    }

-}

-

-void

-pixman_composite_over_n_8_8888_asm_armv6 (int32_t   width,

-                                          int32_t   height,

-                                          uint32_t *dst_line,

-                                          int32_t   dst_stride,

-                                          uint32_t  src,

-                                          int32_t   unused,

-                                          uint8_t  *mask_line,

-                                          int32_t   mask_stride)

-{

-    uint32_t  srca;

-    uint32_t *dst;

-    uint8_t  *mask;

-    int32_t w;

-

-    srca = src >> 24;

-

-    uint32_t component_mask = 0xff00ff;

-    uint32_t component_half = 0x800080;

-

-    uint32_t src_hi = (src >> 8) & component_mask;

-    uint32_t src_lo = src & component_mask;

-

-    while (height--)

-    {

-	dst = dst_line;

-	dst_line += dst_stride;

-	mask = mask_line;

-	mask_line += mask_stride;

-	w = width;

-

-/* #define inner_branch */

-	asm volatile (

-	    "cmp %[w], #0\n\t"

-	    "beq 2f\n\t"

-	    "1:\n\t"

-	    /* load mask */

-	    "ldrb r5, [%[mask]], #1\n\t"

-#ifdef inner_branch

-	    /* We can avoid doing the multiplication in two cases: 0x0 or 0xff.

-	     * The 0x0 case also allows us to avoid doing an unecessary data

-	     * write which is more valuable so we only check for that

-	     */

-	    "cmp r5, #0\n\t"

-	    "beq 3f\n\t"

-

-#endif

-	    "ldr r4, [%[dest]] \n\t"

-

-	    /* multiply by alpha (r8) then by 257 and divide by 65536 */

-	    "mla r6, %[src_lo], r5, %[component_half]\n\t"

-	    "mla r7, %[src_hi], r5, %[component_half]\n\t"

-

-	    "uxtab16 r6, r6, r6, ror #8\n\t"

-	    "uxtab16 r7, r7, r7, ror #8\n\t"

-

-	    "uxtb16 r6, r6, ror #8\n\t"

-	    "uxtb16 r7, r7, ror #8\n\t"

-

-	    /* recombine */

-	    "orr r5, r6, r7, lsl #8\n\t"

-

-	    "uxtb16 r6, r4\n\t"

-	    "uxtb16 r7, r4, ror #8\n\t"

-

-	    /* we could simplify this to use 'sub' if we were

-	     * willing to give up a register for alpha_mask

-	     */

-	    "mvn r8, r5\n\t"

-	    "mov r8, r8, lsr #24\n\t"

-

-	    /* multiply by alpha (r8) then by 257 and divide by 65536 */

-	    "mla r6, r6, r8, %[component_half]\n\t"

-	    "mla r7, r7, r8, %[component_half]\n\t"

-

-	    "uxtab16 r6, r6, r6, ror #8\n\t"

-	    "uxtab16 r7, r7, r7, ror #8\n\t"

-

-	    "uxtb16 r6, r6, ror #8\n\t"

-	    "uxtb16 r7, r7, ror #8\n\t"

-

-	    /* recombine */

-	    "orr r6, r6, r7, lsl #8\n\t"

-

-	    "uqadd8 r5, r6, r5\n\t"

-

-#ifdef inner_branch

-	    "3:\n\t"

-

-#endif

-	    "str r5, [%[dest]], #4\n\t"

-	    /* increment counter and jmp to top */

-	    "subs	%[w], %[w], #1\n\t"

-	    "bne	1b\n\t"

-	    "2:\n\t"

-	    : [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src), [mask] "+r" (mask)

-	    : [component_half] "r" (component_half),

-	      [src_hi] "r" (src_hi), [src_lo] "r" (src_lo)

-	    : "r4", "r5", "r6", "r7", "r8", "cc", "memory");

-    }

-}

-

-#endif

-

-PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, add_8_8,

-                                   uint8_t, 1, uint8_t, 1)

-PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, over_8888_8888,

-                                   uint32_t, 1, uint32_t, 1)

-

-PIXMAN_ARM_BIND_FAST_PATH_SRC_N_DST (SKIP_ZERO_MASK, armv6, over_8888_n_8888,

-                                     uint32_t, 1, uint32_t, 1)

-

-PIXMAN_ARM_BIND_FAST_PATH_N_MASK_DST (SKIP_ZERO_SRC, armv6, over_n_8_8888,

-                                      uint8_t, 1, uint32_t, 1)

-

-PIXMAN_ARM_BIND_SCALED_NEAREST_SRC_DST (armv6, 0565_0565, SRC,

-                                        uint16_t, uint16_t)

-PIXMAN_ARM_BIND_SCALED_NEAREST_SRC_DST (armv6, 8888_8888, SRC,

-                                        uint32_t, uint32_t)

-

-static const pixman_fast_path_t arm_simd_fast_paths[] =

-{

-    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, a8r8g8b8, armv6_composite_over_8888_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, x8r8g8b8, armv6_composite_over_8888_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, a8b8g8r8, armv6_composite_over_8888_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, x8b8g8r8, armv6_composite_over_8888_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, a8r8g8b8, armv6_composite_over_8888_n_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, x8r8g8b8, armv6_composite_over_8888_n_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, solid, a8b8g8r8, armv6_composite_over_8888_n_8888),

-    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, solid, x8b8g8r8, armv6_composite_over_8888_n_8888),

-

-    PIXMAN_STD_FAST_PATH (ADD, a8, null, a8, armv6_composite_add_8_8),

-

-    PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8r8g8b8, armv6_composite_over_n_8_8888),

-    PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8r8g8b8, armv6_composite_over_n_8_8888),

-    PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8b8g8r8, armv6_composite_over_n_8_8888),

-    PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8b8g8r8, armv6_composite_over_n_8_8888),

-

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, r5g6b5, r5g6b5, armv6_0565_0565),

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, b5g6r5, b5g6r5, armv6_0565_0565),

-

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8r8g8b8, a8r8g8b8, armv6_8888_8888),

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8r8g8b8, x8r8g8b8, armv6_8888_8888),

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, x8r8g8b8, x8r8g8b8, armv6_8888_8888),

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8b8g8r8, a8b8g8r8, armv6_8888_8888),

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8b8g8r8, x8b8g8r8, armv6_8888_8888),

-    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, x8b8g8r8, x8b8g8r8, armv6_8888_8888),

-

-    { PIXMAN_OP_NONE },

-};

-

-pixman_implementation_t *

-_pixman_implementation_create_arm_simd (pixman_implementation_t *fallback)

-{

-    pixman_implementation_t *imp = _pixman_implementation_create (fallback, arm_simd_fast_paths);

-

-    return imp;

-}

+/*
+ * Copyright © 2008 Mozilla Corporation
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that
+ * copyright notice and this permission notice appear in supporting
+ * documentation, and that the name of Mozilla Corporation not be used in
+ * advertising or publicity pertaining to distribution of the software without
+ * specific, written prior permission.  Mozilla Corporation makes no
+ * representations about the suitability of this software for any purpose.  It
+ * is provided "as is" without express or implied warranty.
+ *
+ * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS
+ * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+ * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
+ * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
+ * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
+ * SOFTWARE.
+ *
+ * Author:  Jeff Muizelaar (jeff@infidigm.net)
+ *
+ */
+#ifdef HAVE_CONFIG_H
+#include <config.h>
+#endif
+
+#include "pixman-private.h"
+#include "pixman-arm-common.h"
+#include "pixman-inlines.h"
+
+#if 0 /* This code was moved to 'pixman-arm-simd-asm.S' */
+
+void
+pixman_composite_add_8_8_asm_armv6 (int32_t  width,
+				    int32_t  height,
+				    uint8_t *dst_line,
+				    int32_t  dst_stride,
+				    uint8_t *src_line,
+				    int32_t  src_stride)
+{
+    uint8_t *dst, *src;
+    int32_t w;
+    uint8_t s, d;
+
+    while (height--)
+    {
+	dst = dst_line;
+	dst_line += dst_stride;
+	src = src_line;
+	src_line += src_stride;
+	w = width;
+
+	/* ensure both src and dst are properly aligned before doing 32 bit reads
+	 * we'll stay in this loop if src and dst have differing alignments
+	 */
+	while (w && (((unsigned long)dst & 3) || ((unsigned long)src & 3)))
+	{
+	    s = *src;
+	    d = *dst;
+	    asm ("uqadd8 %0, %1, %2" : "+r" (d) : "r" (s));
+	    *dst = d;
+
+	    dst++;
+	    src++;
+	    w--;
+	}
+
+	while (w >= 4)
+	{
+	    asm ("uqadd8 %0, %1, %2"
+		 : "=r" (*(uint32_t*)dst)
+		 : "r" (*(uint32_t*)src), "r" (*(uint32_t*)dst));
+	    dst += 4;
+	    src += 4;
+	    w -= 4;
+	}
+
+	while (w)
+	{
+	    s = *src;
+	    d = *dst;
+	    asm ("uqadd8 %0, %1, %2" : "+r" (d) : "r" (s));
+	    *dst = d;
+
+	    dst++;
+	    src++;
+	    w--;
+	}
+    }
+
+}
+
+void
+pixman_composite_over_8888_8888_asm_armv6 (int32_t   width,
+                                           int32_t   height,
+                                           uint32_t *dst_line,
+                                           int32_t   dst_stride,
+                                           uint32_t *src_line,
+                                           int32_t   src_stride)
+{
+    uint32_t    *dst;
+    uint32_t    *src;
+    int32_t w;
+    uint32_t component_half = 0x800080;
+    uint32_t upper_component_mask = 0xff00ff00;
+    uint32_t alpha_mask = 0xff;
+
+    while (height--)
+    {
+	dst = dst_line;
+	dst_line += dst_stride;
+	src = src_line;
+	src_line += src_stride;
+	w = width;
+
+/* #define inner_branch */
+	asm volatile (
+	    "cmp %[w], #0\n\t"
+	    "beq 2f\n\t"
+	    "1:\n\t"
+	    /* load src */
+	    "ldr r5, [%[src]], #4\n\t"
+#ifdef inner_branch
+	    /* We can avoid doing the multiplication in two cases: 0x0 or 0xff.
+	     * The 0x0 case also allows us to avoid doing an unecessary data
+	     * write which is more valuable so we only check for that
+	     */
+	    "cmp r5, #0\n\t"
+	    "beq 3f\n\t"
+
+	    /* = 255 - alpha */
+	    "sub r8, %[alpha_mask], r5, lsr #24\n\t"
+
+	    "ldr r4, [%[dest]] \n\t"
+
+#else
+	    "ldr r4, [%[dest]] \n\t"
+
+	    /* = 255 - alpha */
+	    "sub r8, %[alpha_mask], r5, lsr #24\n\t"
+#endif
+	    "uxtb16 r6, r4\n\t"
+	    "uxtb16 r7, r4, ror #8\n\t"
+
+	    /* multiply by 257 and divide by 65536 */
+	    "mla r6, r6, r8, %[component_half]\n\t"
+	    "mla r7, r7, r8, %[component_half]\n\t"
+
+	    "uxtab16 r6, r6, r6, ror #8\n\t"
+	    "uxtab16 r7, r7, r7, ror #8\n\t"
+
+	    /* recombine the 0xff00ff00 bytes of r6 and r7 */
+	    "and r7, r7, %[upper_component_mask]\n\t"
+	    "uxtab16 r6, r7, r6, ror #8\n\t"
+
+	    "uqadd8 r5, r6, r5\n\t"
+
+#ifdef inner_branch
+	    "3:\n\t"
+
+#endif
+	    "str r5, [%[dest]], #4\n\t"
+	    /* increment counter and jmp to top */
+	    "subs	%[w], %[w], #1\n\t"
+	    "bne	1b\n\t"
+	    "2:\n\t"
+	    : [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src)
+	    : [component_half] "r" (component_half), [upper_component_mask] "r" (upper_component_mask),
+	      [alpha_mask] "r" (alpha_mask)
+	    : "r4", "r5", "r6", "r7", "r8", "cc", "memory"
+	    );
+    }
+}
+
+void
+pixman_composite_over_8888_n_8888_asm_armv6 (int32_t   width,
+                                             int32_t   height,
+                                             uint32_t *dst_line,
+                                             int32_t   dst_stride,
+                                             uint32_t *src_line,
+                                             int32_t   src_stride,
+                                             uint32_t  mask)
+{
+    uint32_t *dst;
+    uint32_t *src;
+    int32_t w;
+    uint32_t component_half = 0x800080;
+    uint32_t alpha_mask = 0xff;
+
+    mask = (mask) >> 24;
+
+    while (height--)
+    {
+	dst = dst_line;
+	dst_line += dst_stride;
+	src = src_line;
+	src_line += src_stride;
+	w = width;
+
+/* #define inner_branch */
+	asm volatile (
+	    "cmp %[w], #0\n\t"
+	    "beq 2f\n\t"
+	    "1:\n\t"
+	    /* load src */
+	    "ldr r5, [%[src]], #4\n\t"
+#ifdef inner_branch
+	    /* We can avoid doing the multiplication in two cases: 0x0 or 0xff.
+	     * The 0x0 case also allows us to avoid doing an unecessary data
+	     * write which is more valuable so we only check for that
+	     */
+	    "cmp r5, #0\n\t"
+	    "beq 3f\n\t"
+
+#endif
+	    "ldr r4, [%[dest]] \n\t"
+
+	    "uxtb16 r6, r5\n\t"
+	    "uxtb16 r7, r5, ror #8\n\t"
+
+	    /* multiply by alpha (r8) then by 257 and divide by 65536 */
+	    "mla r6, r6, %[mask_alpha], %[component_half]\n\t"
+	    "mla r7, r7, %[mask_alpha], %[component_half]\n\t"
+
+	    "uxtab16 r6, r6, r6, ror #8\n\t"
+	    "uxtab16 r7, r7, r7, ror #8\n\t"
+
+	    "uxtb16 r6, r6, ror #8\n\t"
+	    "uxtb16 r7, r7, ror #8\n\t"
+
+	    /* recombine */
+	    "orr r5, r6, r7, lsl #8\n\t"
+
+	    "uxtb16 r6, r4\n\t"
+	    "uxtb16 r7, r4, ror #8\n\t"
+
+	    /* 255 - alpha */
+	    "sub r8, %[alpha_mask], r5, lsr #24\n\t"
+
+	    /* multiply by alpha (r8) then by 257 and divide by 65536 */
+	    "mla r6, r6, r8, %[component_half]\n\t"
+	    "mla r7, r7, r8, %[component_half]\n\t"
+
+	    "uxtab16 r6, r6, r6, ror #8\n\t"
+	    "uxtab16 r7, r7, r7, ror #8\n\t"
+
+	    "uxtb16 r6, r6, ror #8\n\t"
+	    "uxtb16 r7, r7, ror #8\n\t"
+
+	    /* recombine */
+	    "orr r6, r6, r7, lsl #8\n\t"
+
+	    "uqadd8 r5, r6, r5\n\t"
+
+#ifdef inner_branch
+	    "3:\n\t"
+
+#endif
+	    "str r5, [%[dest]], #4\n\t"
+	    /* increment counter and jmp to top */
+	    "subs	%[w], %[w], #1\n\t"
+	    "bne	1b\n\t"
+	    "2:\n\t"
+	    : [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src)
+	    : [component_half] "r" (component_half), [mask_alpha] "r" (mask),
+	      [alpha_mask] "r" (alpha_mask)
+	    : "r4", "r5", "r6", "r7", "r8", "r9", "cc", "memory"
+	    );
+    }
+}
+
+void
+pixman_composite_over_n_8_8888_asm_armv6 (int32_t   width,
+                                          int32_t   height,
+                                          uint32_t *dst_line,
+                                          int32_t   dst_stride,
+                                          uint32_t  src,
+                                          int32_t   unused,
+                                          uint8_t  *mask_line,
+                                          int32_t   mask_stride)
+{
+    uint32_t  srca;
+    uint32_t *dst;
+    uint8_t  *mask;
+    int32_t w;
+
+    srca = src >> 24;
+
+    uint32_t component_mask = 0xff00ff;
+    uint32_t component_half = 0x800080;
+
+    uint32_t src_hi = (src >> 8) & component_mask;
+    uint32_t src_lo = src & component_mask;
+
+    while (height--)
+    {
+	dst = dst_line;
+	dst_line += dst_stride;
+	mask = mask_line;
+	mask_line += mask_stride;
+	w = width;
+
+/* #define inner_branch */
+	asm volatile (
+	    "cmp %[w], #0\n\t"
+	    "beq 2f\n\t"
+	    "1:\n\t"
+	    /* load mask */
+	    "ldrb r5, [%[mask]], #1\n\t"
+#ifdef inner_branch
+	    /* We can avoid doing the multiplication in two cases: 0x0 or 0xff.
+	     * The 0x0 case also allows us to avoid doing an unecessary data
+	     * write which is more valuable so we only check for that
+	     */
+	    "cmp r5, #0\n\t"
+	    "beq 3f\n\t"
+
+#endif
+	    "ldr r4, [%[dest]] \n\t"
+
+	    /* multiply by alpha (r8) then by 257 and divide by 65536 */
+	    "mla r6, %[src_lo], r5, %[component_half]\n\t"
+	    "mla r7, %[src_hi], r5, %[component_half]\n\t"
+
+	    "uxtab16 r6, r6, r6, ror #8\n\t"
+	    "uxtab16 r7, r7, r7, ror #8\n\t"
+
+	    "uxtb16 r6, r6, ror #8\n\t"
+	    "uxtb16 r7, r7, ror #8\n\t"
+
+	    /* recombine */
+	    "orr r5, r6, r7, lsl #8\n\t"
+
+	    "uxtb16 r6, r4\n\t"
+	    "uxtb16 r7, r4, ror #8\n\t"
+
+	    /* we could simplify this to use 'sub' if we were
+	     * willing to give up a register for alpha_mask
+	     */
+	    "mvn r8, r5\n\t"
+	    "mov r8, r8, lsr #24\n\t"
+
+	    /* multiply by alpha (r8) then by 257 and divide by 65536 */
+	    "mla r6, r6, r8, %[component_half]\n\t"
+	    "mla r7, r7, r8, %[component_half]\n\t"
+
+	    "uxtab16 r6, r6, r6, ror #8\n\t"
+	    "uxtab16 r7, r7, r7, ror #8\n\t"
+
+	    "uxtb16 r6, r6, ror #8\n\t"
+	    "uxtb16 r7, r7, ror #8\n\t"
+
+	    /* recombine */
+	    "orr r6, r6, r7, lsl #8\n\t"
+
+	    "uqadd8 r5, r6, r5\n\t"
+
+#ifdef inner_branch
+	    "3:\n\t"
+
+#endif
+	    "str r5, [%[dest]], #4\n\t"
+	    /* increment counter and jmp to top */
+	    "subs	%[w], %[w], #1\n\t"
+	    "bne	1b\n\t"
+	    "2:\n\t"
+	    : [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src), [mask] "+r" (mask)
+	    : [component_half] "r" (component_half),
+	      [src_hi] "r" (src_hi), [src_lo] "r" (src_lo)
+	    : "r4", "r5", "r6", "r7", "r8", "cc", "memory");
+    }
+}
+
+#endif
+
+PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, add_8_8,
+                                   uint8_t, 1, uint8_t, 1)
+PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, over_8888_8888,
+                                   uint32_t, 1, uint32_t, 1)
+
+PIXMAN_ARM_BIND_FAST_PATH_SRC_N_DST (SKIP_ZERO_MASK, armv6, over_8888_n_8888,
+                                     uint32_t, 1, uint32_t, 1)
+
+PIXMAN_ARM_BIND_FAST_PATH_N_MASK_DST (SKIP_ZERO_SRC, armv6, over_n_8_8888,
+                                      uint8_t, 1, uint32_t, 1)
+
+PIXMAN_ARM_BIND_SCALED_NEAREST_SRC_DST (armv6, 0565_0565, SRC,
+                                        uint16_t, uint16_t)
+PIXMAN_ARM_BIND_SCALED_NEAREST_SRC_DST (armv6, 8888_8888, SRC,
+                                        uint32_t, uint32_t)
+
+static const pixman_fast_path_t arm_simd_fast_paths[] =
+{
+    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, a8r8g8b8, armv6_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, x8r8g8b8, armv6_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, a8b8g8r8, armv6_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, x8b8g8r8, armv6_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, a8r8g8b8, armv6_composite_over_8888_n_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, x8r8g8b8, armv6_composite_over_8888_n_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, solid, a8b8g8r8, armv6_composite_over_8888_n_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, solid, x8b8g8r8, armv6_composite_over_8888_n_8888),
+
+    PIXMAN_STD_FAST_PATH (ADD, a8, null, a8, armv6_composite_add_8_8),
+
+    PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8r8g8b8, armv6_composite_over_n_8_8888),
+    PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8r8g8b8, armv6_composite_over_n_8_8888),
+    PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8b8g8r8, armv6_composite_over_n_8_8888),
+    PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8b8g8r8, armv6_composite_over_n_8_8888),
+
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, r5g6b5, r5g6b5, armv6_0565_0565),
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, b5g6r5, b5g6r5, armv6_0565_0565),
+
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8r8g8b8, a8r8g8b8, armv6_8888_8888),
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8r8g8b8, x8r8g8b8, armv6_8888_8888),
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, x8r8g8b8, x8r8g8b8, armv6_8888_8888),
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8b8g8r8, a8b8g8r8, armv6_8888_8888),
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, a8b8g8r8, x8b8g8r8, armv6_8888_8888),
+    PIXMAN_ARM_SIMPLE_NEAREST_FAST_PATH (SRC, x8b8g8r8, x8b8g8r8, armv6_8888_8888),
+
+    { PIXMAN_OP_NONE },
+};
+
+pixman_implementation_t *
+_pixman_implementation_create_arm_simd (pixman_implementation_t *fallback)
+{
+    pixman_implementation_t *imp = _pixman_implementation_create (fallback, arm_simd_fast_paths);
+
+    return imp;
+}
diff --git a/pixman/pixman/pixman-bits-image.c b/pixman/pixman/pixman-bits-image.c
index 40ccaa8bd..f540c76e1 100644
--- a/pixman/pixman/pixman-bits-image.c
+++ b/pixman/pixman/pixman-bits-image.c
@@ -1,1581 +1,1463 @@
-/*

- * Copyright © 2000 Keith Packard, member of The XFree86 Project, Inc.

- *             2005 Lars Knoll & Zack Rusin, Trolltech

- *             2008 Aaron Plattner, NVIDIA Corporation

- * Copyright © 2000 SuSE, Inc.

- * Copyright © 2007, 2009 Red Hat, Inc.

- * Copyright © 2008 André Tupinambá <andrelrt@gmail.com>

- *

- * Permission to use, copy, modify, distribute, and sell this software and its

- * documentation for any purpose is hereby granted without fee, provided that

- * the above copyright notice appear in all copies and that both that

- * copyright notice and this permission notice appear in supporting

- * documentation, and that the name of Keith Packard not be used in

- * advertising or publicity pertaining to distribution of the software without

- * specific, written prior permission.  Keith Packard makes no

- * representations about the suitability of this software for any purpose.  It

- * is provided "as is" without express or implied warranty.

- *

- * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS

- * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND

- * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY

- * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES

- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN

- * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING

- * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS

- * SOFTWARE.

- */

-

-#ifdef HAVE_CONFIG_H

-#include <config.h>

-#endif

-#include <stdio.h>

-#include <stdlib.h>

-#include <string.h>

-#include "pixman-private.h"

-#include "pixman-combine32.h"

-

-/*

- * By default, just evaluate the image at 32bpp and expand.  Individual image

- * types can plug in a better scanline getter if they want to. For example

- * we  could produce smoother gradients by evaluating them at higher color

- * depth, but that's a project for the future.

- */

-static void

-_pixman_image_get_scanline_generic_64 (pixman_image_t * image,

-                                       int              x,

-                                       int              y,

-                                       int              width,

-                                       uint32_t *       buffer,

-                                       const uint32_t * mask)

-{

-    uint32_t *mask8 = NULL;

-

-    /* Contract the mask image, if one exists, so that the 32-bit fetch

-     * function can use it.

-     */

-    if (mask)

-    {

-	mask8 = pixman_malloc_ab (width, sizeof(uint32_t));

-	if (!mask8)

-	    return;

-

-	pixman_contract (mask8, (uint64_t *)mask, width);

-    }

-

-    /* Fetch the source image into the first half of buffer. */

-    image->bits.get_scanline_32 (image, x, y, width, (uint32_t*)buffer, mask8);

-

-    /* Expand from 32bpp to 64bpp in place. */

-    pixman_expand ((uint64_t *)buffer, buffer, PIXMAN_a8r8g8b8, width);

-

-    free (mask8);

-}

-

-/* Fetch functions */

-

-static force_inline uint32_t

-fetch_pixel_no_alpha (bits_image_t *image,

-		      int x, int y, pixman_bool_t check_bounds)

-{

-    if (check_bounds &&

-	(x < 0 || x >= image->width || y < 0 || y >= image->height))

-    {

-	return 0;

-    }

-

-    return image->fetch_pixel_32 (image, x, y);

-}

-

-typedef uint32_t (* get_pixel_t) (bits_image_t *image,

-				  int x, int y, pixman_bool_t check_bounds);

-

-static force_inline void

-repeat (pixman_repeat_t repeat, int size, int *coord)

-{

-    switch (repeat)

-    {

-    case PIXMAN_REPEAT_NORMAL:

-	*coord = MOD (*coord, size);

-	break;

-

-    case PIXMAN_REPEAT_PAD:

-	*coord = CLIP (*coord, 0, size - 1);

-	break;

-

-    case PIXMAN_REPEAT_REFLECT:

-	*coord = MOD (*coord, size * 2);

-

-	if (*coord >= size)

-	    *coord = size * 2 - *coord - 1;

-	break;

-

-    case PIXMAN_REPEAT_NONE:

-	break;

-

-    default:

-        break;

-    }

-}

-

-static force_inline uint32_t

-bits_image_fetch_pixel_nearest (bits_image_t   *image,

-				pixman_fixed_t  x,

-				pixman_fixed_t  y,

-				get_pixel_t	get_pixel)

-{

-    int x0 = pixman_fixed_to_int (x - pixman_fixed_e);

-    int y0 = pixman_fixed_to_int (y - pixman_fixed_e);

-

-    if (image->common.repeat != PIXMAN_REPEAT_NONE)

-    {

-	repeat (image->common.repeat, image->width, &x0);

-	repeat (image->common.repeat, image->height, &y0);

-

-	return get_pixel (image, x0, y0, FALSE);

-    }

-    else

-    {

-	return get_pixel (image, x0, y0, TRUE);

-    }

-}

-

-#if SIZEOF_LONG > 4

-

-static force_inline uint32_t

-bilinear_interpolation (uint32_t tl, uint32_t tr,

-			uint32_t bl, uint32_t br,

-			int distx, int disty)

-{

-    uint64_t distxy, distxiy, distixy, distixiy;

-    uint64_t tl64, tr64, bl64, br64;

-    uint64_t f, r;

-

-    distxy = distx * disty;

-    distxiy = distx * (256 - disty);

-    distixy = (256 - distx) * disty;

-    distixiy = (256 - distx) * (256 - disty);

-

-    /* Alpha and Blue */

-    tl64 = tl & 0xff0000ff;

-    tr64 = tr & 0xff0000ff;

-    bl64 = bl & 0xff0000ff;

-    br64 = br & 0xff0000ff;

-

-    f = tl64 * distixiy + tr64 * distxiy + bl64 * distixy + br64 * distxy;

-    r = f & 0x0000ff0000ff0000ull;

-

-    /* Red and Green */

-    tl64 = tl;

-    tl64 = ((tl64 << 16) & 0x000000ff00000000ull) | (tl64 & 0x0000ff00ull);

-

-    tr64 = tr;

-    tr64 = ((tr64 << 16) & 0x000000ff00000000ull) | (tr64 & 0x0000ff00ull);

-

-    bl64 = bl;

-    bl64 = ((bl64 << 16) & 0x000000ff00000000ull) | (bl64 & 0x0000ff00ull);

-

-    br64 = br;

-    br64 = ((br64 << 16) & 0x000000ff00000000ull) | (br64 & 0x0000ff00ull);

-

-    f = tl64 * distixiy + tr64 * distxiy + bl64 * distixy + br64 * distxy;

-    r |= ((f >> 16) & 0x000000ff00000000ull) | (f & 0xff000000ull);

-

-    return (uint32_t)(r >> 16);

-}

-

-#else

-

-static force_inline uint32_t

-bilinear_interpolation (uint32_t tl, uint32_t tr,

-			uint32_t bl, uint32_t br,

-			int distx, int disty)

-{

-    int distxy, distxiy, distixy, distixiy;

-    uint32_t f, r;

-

-    distxy = distx * disty;

-    distxiy = (distx << 8) - distxy;	/* distx * (256 - disty) */

-    distixy = (disty << 8) - distxy;	/* disty * (256 - distx) */

-    distixiy =

-	256 * 256 - (disty << 8) -

-	(distx << 8) + distxy;		/* (256 - distx) * (256 - disty) */

-

-    /* Blue */

-    r = (tl & 0x000000ff) * distixiy + (tr & 0x000000ff) * distxiy

-      + (bl & 0x000000ff) * distixy  + (br & 0x000000ff) * distxy;

-

-    /* Green */

-    f = (tl & 0x0000ff00) * distixiy + (tr & 0x0000ff00) * distxiy

-      + (bl & 0x0000ff00) * distixy  + (br & 0x0000ff00) * distxy;

-    r |= f & 0xff000000;

-

-    tl >>= 16;

-    tr >>= 16;

-    bl >>= 16;

-    br >>= 16;

-    r >>= 16;

-

-    /* Red */

-    f = (tl & 0x000000ff) * distixiy + (tr & 0x000000ff) * distxiy

-      + (bl & 0x000000ff) * distixy  + (br & 0x000000ff) * distxy;

-    r |= f & 0x00ff0000;

-

-    /* Alpha */

-    f = (tl & 0x0000ff00) * distixiy + (tr & 0x0000ff00) * distxiy

-      + (bl & 0x0000ff00) * distixy  + (br & 0x0000ff00) * distxy;

-    r |= f & 0xff000000;

-

-    return r;

-}

-

-#endif

-

-static force_inline uint32_t

-bits_image_fetch_pixel_bilinear (bits_image_t   *image,

-				 pixman_fixed_t  x,

-				 pixman_fixed_t  y,

-				 get_pixel_t	 get_pixel)

-{

-    pixman_repeat_t repeat_mode = image->common.repeat;

-    int width = image->width;

-    int height = image->height;

-    int x1, y1, x2, y2;

-    uint32_t tl, tr, bl, br;

-    int32_t distx, disty;

-

-    x1 = x - pixman_fixed_1 / 2;

-    y1 = y - pixman_fixed_1 / 2;

-

-    distx = (x1 >> 8) & 0xff;

-    disty = (y1 >> 8) & 0xff;

-

-    x1 = pixman_fixed_to_int (x1);

-    y1 = pixman_fixed_to_int (y1);

-    x2 = x1 + 1;

-    y2 = y1 + 1;

-

-    if (repeat_mode != PIXMAN_REPEAT_NONE)

-    {

-	repeat (repeat_mode, width, &x1);

-	repeat (repeat_mode, height, &y1);

-	repeat (repeat_mode, width, &x2);

-	repeat (repeat_mode, height, &y2);

-

-	tl = get_pixel (image, x1, y1, FALSE);

-	bl = get_pixel (image, x1, y2, FALSE);

-	tr = get_pixel (image, x2, y1, FALSE);

-	br = get_pixel (image, x2, y2, FALSE);

-    }

-    else

-    {

-	tl = get_pixel (image, x1, y1, TRUE);

-	tr = get_pixel (image, x2, y1, TRUE);

-	bl = get_pixel (image, x1, y2, TRUE);

-	br = get_pixel (image, x2, y2, TRUE);

-    }

-

-    return bilinear_interpolation (tl, tr, bl, br, distx, disty);

-}

-

-static void

-bits_image_fetch_bilinear_no_repeat_8888 (pixman_image_t * ima,

-					  int              offset,

-					  int              line,

-					  int              width,

-					  uint32_t *       buffer,

-					  const uint32_t * mask)

-{

-    bits_image_t *bits = &ima->bits;

-    pixman_fixed_t x_top, x_bottom, x;

-    pixman_fixed_t ux_top, ux_bottom, ux;

-    pixman_vector_t v;

-    uint32_t top_mask, bottom_mask;

-    uint32_t *top_row;

-    uint32_t *bottom_row;

-    uint32_t *end;

-    uint32_t zero[2] = { 0, 0 };

-    uint32_t one = 1;

-    int y, y1, y2;

-    int disty;

-    int mask_inc;

-    int w;

-

-    /* reference point is the center of the pixel */

-    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;

-    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;

-    v.vector[2] = pixman_fixed_1;

-

-    if (!pixman_transform_point_3d (bits->common.transform, &v))

-	return;

-

-    ux = ux_top = ux_bottom = bits->common.transform->matrix[0][0];

-    x = x_top = x_bottom = v.vector[0] - pixman_fixed_1/2;

-

-    y = v.vector[1] - pixman_fixed_1/2;

-    disty = (y >> 8) & 0xff;

-

-    /* Load the pointers to the first and second lines from the source

-     * image that bilinear code must read.

-     *

-     * The main trick in this code is about the check if any line are

-     * outside of the image;

-     *

-     * When I realize that a line (any one) is outside, I change

-     * the pointer to a dummy area with zeros. Once I change this, I

-     * must be sure the pointer will not change, so I set the

-     * variables to each pointer increments inside the loop.

-     */

-    y1 = pixman_fixed_to_int (y);

-    y2 = y1 + 1;

-

-    if (y1 < 0 || y1 >= bits->height)

-    {

-	top_row = zero;

-	x_top = 0;

-	ux_top = 0;

-    }

-    else

-    {

-	top_row = bits->bits + y1 * bits->rowstride;

-	x_top = x;

-	ux_top = ux;

-    }

-

-    if (y2 < 0 || y2 >= bits->height)

-    {

-	bottom_row = zero;

-	x_bottom = 0;

-	ux_bottom = 0;

-    }

-    else

-    {

-	bottom_row = bits->bits + y2 * bits->rowstride;

-	x_bottom = x;

-	ux_bottom = ux;

-    }

-

-    /* Instead of checking whether the operation uses the mast in

-     * each loop iteration, verify this only once and prepare the

-     * variables to make the code smaller inside the loop.

-     */

-    if (!mask)

-    {

-        mask_inc = 0;

-        mask = &one;

-    }

-    else

-    {

-        /* If have a mask, prepare the variables to check it */

-        mask_inc = 1;

-    }

-

-    /* If both are zero, then the whole thing is zero */

-    if (top_row == zero && bottom_row == zero)

-    {

-	memset (buffer, 0, width * sizeof (uint32_t));

-	return;

-    }

-    else if (bits->format == PIXMAN_x8r8g8b8)

-    {

-	if (top_row == zero)

-	{

-	    top_mask = 0;

-	    bottom_mask = 0xff000000;

-	}

-	else if (bottom_row == zero)

-	{

-	    top_mask = 0xff000000;

-	    bottom_mask = 0;

-	}

-	else

-	{

-	    top_mask = 0xff000000;

-	    bottom_mask = 0xff000000;

-	}

-    }

-    else

-    {

-	top_mask = 0;

-	bottom_mask = 0;

-    }

-

-    end = buffer + width;

-

-    /* Zero fill to the left of the image */

-    while (buffer < end && x < pixman_fixed_minus_1)

-    {

-	*buffer++ = 0;

-	x += ux;

-	x_top += ux_top;

-	x_bottom += ux_bottom;

-	mask += mask_inc;

-    }

-

-    /* Left edge

-     */

-    while (buffer < end && x < 0)

-    {

-	uint32_t tr, br;

-	int32_t distx;

-

-	tr = top_row[pixman_fixed_to_int (x_top) + 1] | top_mask;

-	br = bottom_row[pixman_fixed_to_int (x_bottom) + 1] | bottom_mask;

-

-	distx = (x >> 8) & 0xff;

-

-	*buffer++ = bilinear_interpolation (0, tr, 0, br, distx, disty);

-

-	x += ux;

-	x_top += ux_top;

-	x_bottom += ux_bottom;

-	mask += mask_inc;

-    }

-

-    /* Main part */

-    w = pixman_int_to_fixed (bits->width - 1);

-

-    while (buffer < end  &&  x < w)

-    {

-	if (*mask)

-	{

-	    uint32_t tl, tr, bl, br;

-	    int32_t distx;

-

-	    tl = top_row [pixman_fixed_to_int (x_top)] | top_mask;

-	    tr = top_row [pixman_fixed_to_int (x_top) + 1] | top_mask;

-	    bl = bottom_row [pixman_fixed_to_int (x_bottom)] | bottom_mask;

-	    br = bottom_row [pixman_fixed_to_int (x_bottom) + 1] | bottom_mask;

-

-	    distx = (x >> 8) & 0xff;

-

-	    *buffer = bilinear_interpolation (tl, tr, bl, br, distx, disty);

-	}

-

-	buffer++;

-	x += ux;

-	x_top += ux_top;

-	x_bottom += ux_bottom;

-	mask += mask_inc;

-    }

-

-    /* Right Edge */

-    w = pixman_int_to_fixed (bits->width);

-    while (buffer < end  &&  x < w)

-    {

-	if (*mask)

-	{

-	    uint32_t tl, bl;

-	    int32_t distx;

-

-	    tl = top_row [pixman_fixed_to_int (x_top)] | top_mask;

-	    bl = bottom_row [pixman_fixed_to_int (x_bottom)] | bottom_mask;

-

-	    distx = (x >> 8) & 0xff;

-

-	    *buffer = bilinear_interpolation (tl, 0, bl, 0, distx, disty);

-	}

-

-	buffer++;

-	x += ux;

-	x_top += ux_top;

-	x_bottom += ux_bottom;

-	mask += mask_inc;

-    }

-

-    /* Zero fill to the left of the image */

-    while (buffer < end)

-	*buffer++ = 0;

-}

-

-static force_inline uint32_t

-bits_image_fetch_pixel_convolution (bits_image_t   *image,

-				    pixman_fixed_t  x,

-				    pixman_fixed_t  y,

-				    get_pixel_t     get_pixel)

-{

-    pixman_fixed_t *params = image->common.filter_params;

-    int x_off = (params[0] - pixman_fixed_1) >> 1;

-    int y_off = (params[1] - pixman_fixed_1) >> 1;

-    int32_t cwidth = pixman_fixed_to_int (params[0]);

-    int32_t cheight = pixman_fixed_to_int (params[1]);

-    int32_t srtot, sgtot, sbtot, satot;

-    int32_t i, j, x1, x2, y1, y2;

-    pixman_repeat_t repeat_mode = image->common.repeat;

-    int width = image->width;

-    int height = image->height;

-

-    params += 2;

-

-    x1 = pixman_fixed_to_int (x - pixman_fixed_e - x_off);

-    y1 = pixman_fixed_to_int (y - pixman_fixed_e - y_off);

-    x2 = x1 + cwidth;

-    y2 = y1 + cheight;

-

-    srtot = sgtot = sbtot = satot = 0;

-

-    for (i = y1; i < y2; ++i)

-    {

-	for (j = x1; j < x2; ++j)

-	{

-	    int rx = j;

-	    int ry = i;

-

-	    pixman_fixed_t f = *params;

-

-	    if (f)

-	    {

-		uint32_t pixel;

-

-		if (repeat_mode != PIXMAN_REPEAT_NONE)

-		{

-		    repeat (repeat_mode, width, &rx);

-		    repeat (repeat_mode, height, &ry);

-

-		    pixel = get_pixel (image, rx, ry, FALSE);

-		}

-		else

-		{

-		    pixel = get_pixel (image, rx, ry, TRUE);

-		}

-

-		srtot += RED_8 (pixel) * f;

-		sgtot += GREEN_8 (pixel) * f;

-		sbtot += BLUE_8 (pixel) * f;

-		satot += ALPHA_8 (pixel) * f;

-	    }

-

-	    params++;

-	}

-    }

-

-    satot >>= 16;

-    srtot >>= 16;

-    sgtot >>= 16;

-    sbtot >>= 16;

-

-    satot = CLIP (satot, 0, 0xff);

-    srtot = CLIP (srtot, 0, 0xff);

-    sgtot = CLIP (sgtot, 0, 0xff);

-    sbtot = CLIP (sbtot, 0, 0xff);

-

-    return ((satot << 24) | (srtot << 16) | (sgtot <<  8) | (sbtot));

-}

-

-static force_inline uint32_t

-bits_image_fetch_pixel_filtered (bits_image_t *image,

-				 pixman_fixed_t x,

-				 pixman_fixed_t y,

-				 get_pixel_t    get_pixel)

-{

-    switch (image->common.filter)

-    {

-    case PIXMAN_FILTER_NEAREST:

-    case PIXMAN_FILTER_FAST:

-	return bits_image_fetch_pixel_nearest (image, x, y, get_pixel);

-	break;

-

-    case PIXMAN_FILTER_BILINEAR:

-    case PIXMAN_FILTER_GOOD:

-    case PIXMAN_FILTER_BEST:

-	return bits_image_fetch_pixel_bilinear (image, x, y, get_pixel);

-	break;

-

-    case PIXMAN_FILTER_CONVOLUTION:

-	return bits_image_fetch_pixel_convolution (image, x, y, get_pixel);

-	break;

-

-    default:

-        break;

-    }

-

-    return 0;

-}

-

-static void

-bits_image_fetch_affine_no_alpha (pixman_image_t * image,

-				  int              offset,

-				  int              line,

-				  int              width,

-				  uint32_t *       buffer,

-				  const uint32_t * mask)

-{

-    pixman_fixed_t x, y;

-    pixman_fixed_t ux, uy;

-    pixman_vector_t v;

-    int i;

-

-    /* reference point is the center of the pixel */

-    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;

-    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;

-    v.vector[2] = pixman_fixed_1;

-

-    if (image->common.transform)

-    {

-	if (!pixman_transform_point_3d (image->common.transform, &v))

-	    return;

-

-	ux = image->common.transform->matrix[0][0];

-	uy = image->common.transform->matrix[1][0];

-    }

-    else

-    {

-	ux = pixman_fixed_1;

-	uy = 0;

-    }

-

-    x = v.vector[0];

-    y = v.vector[1];

-

-    for (i = 0; i < width; ++i)

-    {

-	if (!mask || mask[i])

-	{

-	    buffer[i] = bits_image_fetch_pixel_filtered (

-		&image->bits, x, y, fetch_pixel_no_alpha);

-	}

-

-	x += ux;

-	y += uy;

-    }

-}

-

-/* General fetcher */

-static force_inline uint32_t

-fetch_pixel_general (bits_image_t *image, int x, int y, pixman_bool_t check_bounds)

-{

-    uint32_t pixel;

-

-    if (check_bounds &&

-	(x < 0 || x >= image->width || y < 0 || y >= image->height))

-    {

-	return 0;

-    }

-

-    pixel = image->fetch_pixel_32 (image, x, y);

-

-    if (image->common.alpha_map)

-    {

-	uint32_t pixel_a;

-

-	x -= image->common.alpha_origin_x;

-	y -= image->common.alpha_origin_y;

-

-	if (x < 0 || x >= image->common.alpha_map->width ||

-	    y < 0 || y >= image->common.alpha_map->height)

-	{

-	    pixel_a = 0;

-	}

-	else

-	{

-	    pixel_a = image->common.alpha_map->fetch_pixel_32 (

-		image->common.alpha_map, x, y);

-

-	    pixel_a = ALPHA_8 (pixel_a);

-	}

-

-	pixel &= 0x00ffffff;

-	pixel |= (pixel_a << 24);

-    }

-

-    return pixel;

-}

-

-static void

-bits_image_fetch_general (pixman_image_t * image,

-			  int              offset,

-			  int              line,

-			  int              width,

-			  uint32_t *       buffer,

-			  const uint32_t * mask)

-{

-    pixman_fixed_t x, y, w;

-    pixman_fixed_t ux, uy, uw;

-    pixman_vector_t v;

-    int i;

-

-    /* reference point is the center of the pixel */

-    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;

-    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;

-    v.vector[2] = pixman_fixed_1;

-

-    if (image->common.transform)

-    {

-	if (!pixman_transform_point_3d (image->common.transform, &v))

-	    return;

-

-	ux = image->common.transform->matrix[0][0];

-	uy = image->common.transform->matrix[1][0];

-	uw = image->common.transform->matrix[2][0];

-    }

-    else

-    {

-	ux = pixman_fixed_1;

-	uy = 0;

-	uw = 0;

-    }

-

-    x = v.vector[0];

-    y = v.vector[1];

-    w = v.vector[2];

-

-    for (i = 0; i < width; ++i)

-    {

-	pixman_fixed_t x0, y0;

-

-	if (!mask || mask[i])

-	{

-	    if (w != 0)

-	    {

-		x0 = ((pixman_fixed_48_16_t)x << 16) / w;

-		y0 = ((pixman_fixed_48_16_t)y << 16) / w;

-	    }

-	    else

-	    {

-		x0 = 0;

-		y0 = 0;

-	    }

-

-	    buffer[i] = bits_image_fetch_pixel_filtered (

-		&image->bits, x0, y0, fetch_pixel_general);

-	}

-

-	x += ux;

-	y += uy;

-	w += uw;

-    }

-}

-

-static const uint8_t zero[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };

-

-typedef uint32_t (* convert_pixel_t) (const uint8_t *row, int x);

-

-static force_inline void

-bits_image_fetch_bilinear_affine (pixman_image_t * image,

-				  int              offset,

-				  int              line,

-				  int              width,

-				  uint32_t *       buffer,

-				  const uint32_t * mask,

-

-				  convert_pixel_t	convert_pixel,

-				  pixman_format_code_t	format,

-				  pixman_repeat_t	repeat_mode)

-{

-    pixman_fixed_t x, y;

-    pixman_fixed_t ux, uy;

-    pixman_vector_t v;

-    bits_image_t *bits = &image->bits;

-    int i;

-

-    /* reference point is the center of the pixel */

-    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;

-    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;

-    v.vector[2] = pixman_fixed_1;

-

-    if (!pixman_transform_point_3d (image->common.transform, &v))

-	return;

-

-    ux = image->common.transform->matrix[0][0];

-    uy = image->common.transform->matrix[1][0];

-

-    x = v.vector[0];

-    y = v.vector[1];

-

-    for (i = 0; i < width; ++i)

-    {

-	int x1, y1, x2, y2;

-	uint32_t tl, tr, bl, br;

-	int32_t distx, disty;

-	int width = image->bits.width;

-	int height = image->bits.height;

-	const uint8_t *row1;

-	const uint8_t *row2;

-

-	if (mask && !mask[i])

-	    goto next;

-

-	x1 = x - pixman_fixed_1 / 2;

-	y1 = y - pixman_fixed_1 / 2;

-

-	distx = (x1 >> 8) & 0xff;

-	disty = (y1 >> 8) & 0xff;

-

-	y1 = pixman_fixed_to_int (y1);

-	y2 = y1 + 1;

-	x1 = pixman_fixed_to_int (x1);

-	x2 = x1 + 1;

-

-	if (repeat_mode != PIXMAN_REPEAT_NONE)

-	{

-	    uint32_t mask;

-

-	    mask = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;

-

-	    repeat (repeat_mode, width, &x1);

-	    repeat (repeat_mode, height, &y1);

-	    repeat (repeat_mode, width, &x2);

-	    repeat (repeat_mode, height, &y2);

-

-	    row1 = (uint8_t *)bits->bits + bits->rowstride * 4 * y1;

-	    row2 = (uint8_t *)bits->bits + bits->rowstride * 4 * y2;

-

-	    tl = convert_pixel (row1, x1) | mask;

-	    tr = convert_pixel (row1, x2) | mask;

-	    bl = convert_pixel (row2, x1) | mask;

-	    br = convert_pixel (row2, x2) | mask;

-	}

-	else

-	{

-	    uint32_t mask1, mask2;

-	    int bpp;

-

-	    /* Note: PIXMAN_FORMAT_BPP() returns an unsigned value,

-	     * which means if you use it in expressions, those

-	     * expressions become unsigned themselves. Since

-	     * the variables below can be negative in some cases,

-	     * that will lead to crashes on 64 bit architectures.

-	     *

-	     * So this line makes sure bpp is signed

-	     */

-	    bpp = PIXMAN_FORMAT_BPP (format);

-

-	    if (x1 >= width || x2 < 0 || y1 >= height || y2 < 0)

-	    {

-		buffer[i] = 0;

-		goto next;

-	    }

-

-	    if (y2 == 0)

-	    {

-		row1 = zero;

-		mask1 = 0;

-	    }

-	    else

-	    {

-		row1 = (uint8_t *)bits->bits + bits->rowstride * 4 * y1;

-		row1 += bpp / 8 * x1;

-

-		mask1 = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;

-	    }

-

-	    if (y1 == height - 1)

-	    {

-		row2 = zero;

-		mask2 = 0;

-	    }

-	    else

-	    {

-		row2 = (uint8_t *)bits->bits + bits->rowstride * 4 * y2;

-		row2 += bpp / 8 * x1;

-

-		mask2 = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;

-	    }

-

-	    if (x2 == 0)

-	    {

-		tl = 0;

-		bl = 0;

-	    }

-	    else

-	    {

-		tl = convert_pixel (row1, 0) | mask1;

-		bl = convert_pixel (row2, 0) | mask2;

-	    }

-

-	    if (x1 == width - 1)

-	    {

-		tr = 0;

-		br = 0;

-	    }

-	    else

-	    {

-		tr = convert_pixel (row1, 1) | mask1;

-		br = convert_pixel (row2, 1) | mask2;

-	    }

-	}

-

-	buffer[i] = bilinear_interpolation (

-	    tl, tr, bl, br, distx, disty);

-

-    next:

-	x += ux;

-	y += uy;

-    }

-}

-

-static force_inline void

-bits_image_fetch_nearest_affine (pixman_image_t * image,

-				 int              offset,

-				 int              line,

-				 int              width,

-				 uint32_t *       buffer,

-				 const uint32_t * mask,

-				 

-				 convert_pixel_t	convert_pixel,

-				 pixman_format_code_t	format,

-				 pixman_repeat_t	repeat_mode)

-{

-    pixman_fixed_t x, y;

-    pixman_fixed_t ux, uy;

-    pixman_vector_t v;

-    bits_image_t *bits = &image->bits;

-    int i;

-

-    /* reference point is the center of the pixel */

-    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;

-    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;

-    v.vector[2] = pixman_fixed_1;

-

-    if (!pixman_transform_point_3d (image->common.transform, &v))

-	return;

-

-    ux = image->common.transform->matrix[0][0];

-    uy = image->common.transform->matrix[1][0];

-

-    x = v.vector[0];

-    y = v.vector[1];

-

-    for (i = 0; i < width; ++i)

-    {

-	int width, height, x0, y0;

-	const uint8_t *row;

-

-	if (mask && !mask[i])

-	    goto next;

-	

-	width = image->bits.width;

-	height = image->bits.height;

-	x0 = pixman_fixed_to_int (x - pixman_fixed_e);

-	y0 = pixman_fixed_to_int (y - pixman_fixed_e);

-

-	if (repeat_mode == PIXMAN_REPEAT_NONE &&

-	    (y0 < 0 || y0 >= height || x0 < 0 || x0 >= width))

-	{

-	    buffer[i] = 0;

-	}

-	else

-	{

-	    uint32_t mask = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;

-

-	    if (repeat_mode != PIXMAN_REPEAT_NONE)

-	    {

-		repeat (repeat_mode, width, &x0);

-		repeat (repeat_mode, height, &y0);

-	    }

-

-	    row = (uint8_t *)bits->bits + bits->rowstride * 4 * y0;

-

-	    buffer[i] = convert_pixel (row, x0) | mask;

-	}

-

-    next:

-	x += ux;

-	y += uy;

-    }

-}

-

-static force_inline uint32_t

-convert_a8r8g8b8 (const uint8_t *row, int x)

-{

-    return *(((uint32_t *)row) + x);

-}

-

-static force_inline uint32_t

-convert_x8r8g8b8 (const uint8_t *row, int x)

-{

-    return *(((uint32_t *)row) + x);

-}

-

-static force_inline uint32_t

-convert_a8 (const uint8_t *row, int x)

-{

-    return *(row + x) << 24;

-}

-

-static force_inline uint32_t

-convert_r5g6b5 (const uint8_t *row, int x)

-{

-    return CONVERT_0565_TO_0888 (*((uint16_t *)row + x));

-}

-

-#define MAKE_BILINEAR_FETCHER(name, format, repeat_mode)		\

-    static void								\

-    bits_image_fetch_bilinear_affine_ ## name (pixman_image_t *image,	\

-					       int              offset,	\

-					       int              line,	\

-					       int              width,	\

-					       uint32_t *       buffer,	\

-					       const uint32_t * mask)	\

-    {									\

-	bits_image_fetch_bilinear_affine (image, offset, line,		\

-					  width, buffer, mask,		\

-					  convert_ ## format,		\

-					  PIXMAN_ ## format,		\

-					  repeat_mode);			\

-    }

-

-#define MAKE_NEAREST_FETCHER(name, format, repeat_mode)			\

-    static void								\

-    bits_image_fetch_nearest_affine_ ## name (pixman_image_t *image,	\

-					      int              offset,	\

-					      int              line,	\

-					      int              width,	\

-					      uint32_t *       buffer,	\

-					      const uint32_t * mask)	\

-    {									\

-	bits_image_fetch_nearest_affine (image, offset, line,		\

-					 width, buffer, mask,		\

-					 convert_ ## format,		\

-					 PIXMAN_ ## format,		\

-					 repeat_mode);			\

-    }

-

-#define MAKE_FETCHERS(name, format, repeat_mode)			\

-    MAKE_NEAREST_FETCHER (name, format, repeat_mode)			\

-    MAKE_BILINEAR_FETCHER (name, format, repeat_mode)

-

-MAKE_FETCHERS (pad_a8r8g8b8,     a8r8g8b8, PIXMAN_REPEAT_PAD)

-MAKE_FETCHERS (none_a8r8g8b8,    a8r8g8b8, PIXMAN_REPEAT_NONE)

-MAKE_FETCHERS (reflect_a8r8g8b8, a8r8g8b8, PIXMAN_REPEAT_REFLECT)

-MAKE_FETCHERS (normal_a8r8g8b8,  a8r8g8b8, PIXMAN_REPEAT_NORMAL)

-MAKE_FETCHERS (pad_x8r8g8b8,     x8r8g8b8, PIXMAN_REPEAT_PAD)

-MAKE_FETCHERS (none_x8r8g8b8,    x8r8g8b8, PIXMAN_REPEAT_NONE)

-MAKE_FETCHERS (reflect_x8r8g8b8, x8r8g8b8, PIXMAN_REPEAT_REFLECT)

-MAKE_FETCHERS (normal_x8r8g8b8,  x8r8g8b8, PIXMAN_REPEAT_NORMAL)

-MAKE_FETCHERS (pad_a8,           a8,       PIXMAN_REPEAT_PAD)

-MAKE_FETCHERS (none_a8,          a8,       PIXMAN_REPEAT_NONE)

-MAKE_FETCHERS (reflect_a8,	 a8,       PIXMAN_REPEAT_REFLECT)

-MAKE_FETCHERS (normal_a8,	 a8,       PIXMAN_REPEAT_NORMAL)

-MAKE_FETCHERS (pad_r5g6b5,       r5g6b5,   PIXMAN_REPEAT_PAD)

-MAKE_FETCHERS (none_r5g6b5,      r5g6b5,   PIXMAN_REPEAT_NONE)

-MAKE_FETCHERS (reflect_r5g6b5,   r5g6b5,   PIXMAN_REPEAT_REFLECT)

-MAKE_FETCHERS (normal_r5g6b5,    r5g6b5,   PIXMAN_REPEAT_NORMAL)

-

-static void

-bits_image_fetch_solid_32 (pixman_image_t * image,

-                           int              x,

-                           int              y,

-                           int              width,

-                           uint32_t *       buffer,

-                           const uint32_t * mask)

-{

-    uint32_t color;

-    uint32_t *end;

-

-    color = image->bits.fetch_pixel_32 (&image->bits, 0, 0);

-

-    end = buffer + width;

-    while (buffer < end)

-	*(buffer++) = color;

-}

-

-static void

-bits_image_fetch_solid_64 (pixman_image_t * image,

-                           int              x,

-                           int              y,

-                           int              width,

-                           uint32_t *       b,

-                           const uint32_t * unused)

-{

-    uint64_t color;

-    uint64_t *buffer = (uint64_t *)b;

-    uint64_t *end;

-

-    color = image->bits.fetch_pixel_64 (&image->bits, 0, 0);

-

-    end = buffer + width;

-    while (buffer < end)

-	*(buffer++) = color;

-}

-

-static void

-bits_image_fetch_untransformed_repeat_none (bits_image_t *image,

-                                            pixman_bool_t wide,

-                                            int           x,

-                                            int           y,

-                                            int           width,

-                                            uint32_t *    buffer)

-{

-    uint32_t w;

-

-    if (y < 0 || y >= image->height)

-    {

-	memset (buffer, 0, width * (wide? 8 : 4));

-	return;

-    }

-

-    if (x < 0)

-    {

-	w = MIN (width, -x);

-

-	memset (buffer, 0, w * (wide ? 8 : 4));

-

-	width -= w;

-	buffer += w * (wide? 2 : 1);

-	x += w;

-    }

-

-    if (x < image->width)

-    {

-	w = MIN (width, image->width - x);

-

-	if (wide)

-	    image->fetch_scanline_64 ((pixman_image_t *)image, x, y, w, buffer, NULL);

-	else

-	    image->fetch_scanline_32 ((pixman_image_t *)image, x, y, w, buffer, NULL);

-

-	width -= w;

-	buffer += w * (wide? 2 : 1);

-	x += w;

-    }

-

-    memset (buffer, 0, width * (wide ? 8 : 4));

-}

-

-static void

-bits_image_fetch_untransformed_repeat_normal (bits_image_t *image,

-                                              pixman_bool_t wide,

-                                              int           x,

-                                              int           y,

-                                              int           width,

-                                              uint32_t *    buffer)

-{

-    uint32_t w;

-

-    while (y < 0)

-	y += image->height;

-

-    while (y >= image->height)

-	y -= image->height;

-

-    while (width)

-    {

-	while (x < 0)

-	    x += image->width;

-	while (x >= image->width)

-	    x -= image->width;

-

-	w = MIN (width, image->width - x);

-

-	if (wide)

-	    image->fetch_scanline_64 ((pixman_image_t *)image, x, y, w, buffer, NULL);

-	else

-	    image->fetch_scanline_32 ((pixman_image_t *)image, x, y, w, buffer, NULL);

-

-	buffer += w * (wide? 2 : 1);

-	x += w;

-	width -= w;

-    }

-}

-

-static void

-bits_image_fetch_untransformed_32 (pixman_image_t * image,

-                                   int              x,

-                                   int              y,

-                                   int              width,

-                                   uint32_t *       buffer,

-                                   const uint32_t * mask)

-{

-    if (image->common.repeat == PIXMAN_REPEAT_NONE)

-    {

-	bits_image_fetch_untransformed_repeat_none (

-	    &image->bits, FALSE, x, y, width, buffer);

-    }

-    else

-    {

-	bits_image_fetch_untransformed_repeat_normal (

-	    &image->bits, FALSE, x, y, width, buffer);

-    }

-}

-

-static void

-bits_image_fetch_untransformed_64 (pixman_image_t * image,

-                                   int              x,

-                                   int              y,

-                                   int              width,

-                                   uint32_t *       buffer,

-                                   const uint32_t * unused)

-{

-    if (image->common.repeat == PIXMAN_REPEAT_NONE)

-    {

-	bits_image_fetch_untransformed_repeat_none (

-	    &image->bits, TRUE, x, y, width, buffer);

-    }

-    else

-    {

-	bits_image_fetch_untransformed_repeat_normal (

-	    &image->bits, TRUE, x, y, width, buffer);

-    }

-}

-

-typedef struct

-{

-    pixman_format_code_t	format;

-    uint32_t			flags;

-    fetch_scanline_t		fetch_32;

-    fetch_scanline_t		fetch_64;

-} fetcher_info_t;

-

-static const fetcher_info_t fetcher_info[] =

-{

-    { PIXMAN_solid,

-      FAST_PATH_NO_ALPHA_MAP,

-      bits_image_fetch_solid_32,

-      bits_image_fetch_solid_64

-    },

-

-    { PIXMAN_any,

-      (FAST_PATH_NO_ALPHA_MAP			|

-       FAST_PATH_ID_TRANSFORM			|

-       FAST_PATH_NO_CONVOLUTION_FILTER		|

-       FAST_PATH_NO_PAD_REPEAT			|

-       FAST_PATH_NO_REFLECT_REPEAT),

-      bits_image_fetch_untransformed_32,

-      bits_image_fetch_untransformed_64

-    },

-

-#define FAST_BILINEAR_FLAGS						\

-    (FAST_PATH_NO_ALPHA_MAP		|				\

-     FAST_PATH_NO_ACCESSORS		|				\

-     FAST_PATH_HAS_TRANSFORM		|				\

-     FAST_PATH_AFFINE_TRANSFORM		|				\

-     FAST_PATH_X_UNIT_POSITIVE		|				\

-     FAST_PATH_Y_UNIT_ZERO		|				\

-     FAST_PATH_NONE_REPEAT		|				\

-     FAST_PATH_BILINEAR_FILTER)

-

-    { PIXMAN_a8r8g8b8,

-      FAST_BILINEAR_FLAGS,

-      bits_image_fetch_bilinear_no_repeat_8888,

-      _pixman_image_get_scanline_generic_64

-    },

-

-    { PIXMAN_x8r8g8b8,

-      FAST_BILINEAR_FLAGS,

-      bits_image_fetch_bilinear_no_repeat_8888,

-      _pixman_image_get_scanline_generic_64

-    },

-

-#define GENERAL_BILINEAR_FLAGS						\

-    (FAST_PATH_NO_ALPHA_MAP		|				\

-     FAST_PATH_NO_ACCESSORS		|				\

-     FAST_PATH_HAS_TRANSFORM		|				\

-     FAST_PATH_AFFINE_TRANSFORM		|				\

-     FAST_PATH_BILINEAR_FILTER)

-

-#define GENERAL_NEAREST_FLAGS						\

-    (FAST_PATH_NO_ALPHA_MAP		|				\

-     FAST_PATH_NO_ACCESSORS		|				\

-     FAST_PATH_HAS_TRANSFORM		|				\

-     FAST_PATH_AFFINE_TRANSFORM		|				\

-     FAST_PATH_NEAREST_FILTER)

-

-#define BILINEAR_AFFINE_FAST_PATH(name, format, repeat)			\

-    { PIXMAN_ ## format,						\

-      GENERAL_BILINEAR_FLAGS | FAST_PATH_ ## repeat ## _REPEAT,		\

-      bits_image_fetch_bilinear_affine_ ## name,			\

-      _pixman_image_get_scanline_generic_64				\

-    },

-

-#define NEAREST_AFFINE_FAST_PATH(name, format, repeat)			\

-    { PIXMAN_ ## format,						\

-      GENERAL_NEAREST_FLAGS | FAST_PATH_ ## repeat ## _REPEAT,		\

-      bits_image_fetch_nearest_affine_ ## name,			\

-      _pixman_image_get_scanline_generic_64				\

-    },

-

-#define AFFINE_FAST_PATHS(name, format, repeat)				\

-    BILINEAR_AFFINE_FAST_PATH(name, format, repeat)			\

-    NEAREST_AFFINE_FAST_PATH(name, format, repeat)

-    

-    AFFINE_FAST_PATHS (pad_a8r8g8b8, a8r8g8b8, PAD)

-    AFFINE_FAST_PATHS (none_a8r8g8b8, a8r8g8b8, NONE)

-    AFFINE_FAST_PATHS (reflect_a8r8g8b8, a8r8g8b8, REFLECT)

-    AFFINE_FAST_PATHS (normal_a8r8g8b8, a8r8g8b8, NORMAL)

-    AFFINE_FAST_PATHS (pad_x8r8g8b8, x8r8g8b8, PAD)

-    AFFINE_FAST_PATHS (none_x8r8g8b8, x8r8g8b8, NONE)

-    AFFINE_FAST_PATHS (reflect_x8r8g8b8, x8r8g8b8, REFLECT)

-    AFFINE_FAST_PATHS (normal_x8r8g8b8, x8r8g8b8, NORMAL)

-    AFFINE_FAST_PATHS (pad_a8, a8, PAD)

-    AFFINE_FAST_PATHS (none_a8, a8, NONE)

-    AFFINE_FAST_PATHS (reflect_a8, a8, REFLECT)

-    AFFINE_FAST_PATHS (normal_a8, a8, NORMAL)

-    AFFINE_FAST_PATHS (pad_r5g6b5, r5g6b5, PAD)

-    AFFINE_FAST_PATHS (none_r5g6b5, r5g6b5, NONE)

-    AFFINE_FAST_PATHS (reflect_r5g6b5, r5g6b5, REFLECT)

-    AFFINE_FAST_PATHS (normal_r5g6b5, r5g6b5, NORMAL)

-

-    /* Affine, no alpha */

-    { PIXMAN_any,

-      (FAST_PATH_NO_ALPHA_MAP | FAST_PATH_HAS_TRANSFORM | FAST_PATH_AFFINE_TRANSFORM),

-      bits_image_fetch_affine_no_alpha,

-      _pixman_image_get_scanline_generic_64

-    },

-

-    /* General */

-    { PIXMAN_any, 0, bits_image_fetch_general, _pixman_image_get_scanline_generic_64 },

-

-    { PIXMAN_null },

-};

-

-static void

-bits_image_property_changed (pixman_image_t *image)

-{

-    uint32_t flags = image->common.flags;

-    pixman_format_code_t format = image->common.extended_format_code;

-    const fetcher_info_t *info;

-

-    _pixman_bits_image_setup_accessors (&image->bits);

-

-    info = fetcher_info;

-    while (info->format != PIXMAN_null)

-    {

-	if ((info->format == format || info->format == PIXMAN_any)	&&

-	    (info->flags & flags) == info->flags)

-	{

-	    image->bits.get_scanline_32 = info->fetch_32;

-	    image->bits.get_scanline_64 = info->fetch_64;

-	    break;

-	}

-

-	info++;

-    }

-}

-

-static uint32_t *

-src_get_scanline_narrow (pixman_iter_t *iter, const uint32_t *mask)

-{

-    iter->image->bits.get_scanline_32 (

-	iter->image, iter->x, iter->y++, iter->width, iter->buffer, mask);

-

-    return iter->buffer;

-}

-

-static uint32_t *

-src_get_scanline_wide (pixman_iter_t *iter, const uint32_t *mask)

-{

-    iter->image->bits.get_scanline_64 (

-	iter->image, iter->x, iter->y++, iter->width, iter->buffer, mask);

-

-    return iter->buffer;

-}

-

-void

-_pixman_bits_image_src_iter_init (pixman_image_t *image, pixman_iter_t *iter)

-{

-    if (iter->flags & ITER_NARROW)

-	iter->get_scanline = src_get_scanline_narrow;

-    else

-	iter->get_scanline = src_get_scanline_wide;

-}

-

-static uint32_t *

-dest_get_scanline_narrow (pixman_iter_t *iter, const uint32_t *mask)

-{

-    pixman_image_t *image  = iter->image;

-    int             x      = iter->x;

-    int             y      = iter->y;

-    int             width  = iter->width;

-    uint32_t *	    buffer = iter->buffer;

-

-    image->bits.fetch_scanline_32 (image, x, y, width, buffer, mask);

-    if (image->common.alpha_map)

-    {

-	x -= image->common.alpha_origin_x;

-	y -= image->common.alpha_origin_y;

-

-	image->common.alpha_map->fetch_scanline_32 (

-	    (pixman_image_t *)image->common.alpha_map,

-	    x, y, width, buffer, mask);

-    }

-

-    return iter->buffer;

-}

-

-static uint32_t *

-dest_get_scanline_wide (pixman_iter_t *iter, const uint32_t *mask)

-{

-    bits_image_t *  image  = &iter->image->bits;

-    int             x      = iter->x;

-    int             y      = iter->y;

-    int             width  = iter->width;

-    uint32_t *	    buffer = iter->buffer;

-

-    image->fetch_scanline_64 (

-	(pixman_image_t *)image, x, y, width, buffer, mask);

-    if (image->common.alpha_map)

-    {

-	x -= image->common.alpha_origin_x;

-	y -= image->common.alpha_origin_y;

-

-	image->common.alpha_map->fetch_scanline_64 (

-	    (pixman_image_t *)image->common.alpha_map, x, y, width, buffer, mask);

-    }

-

-    return iter->buffer;

-}

-

-static void

-dest_write_back_narrow (pixman_iter_t *iter)

-{

-    bits_image_t *  image  = &iter->image->bits;

-    int             x      = iter->x;

-    int             y      = iter->y;

-    int             width  = iter->width;

-    const uint32_t *buffer = iter->buffer;

-

-    image->store_scanline_32 (image, x, y, width, buffer);

-

-    if (image->common.alpha_map)

-    {

-	x -= image->common.alpha_origin_x;

-	y -= image->common.alpha_origin_y;

-

-	image->common.alpha_map->store_scanline_32 (

-	    image->common.alpha_map, x, y, width, buffer);

-    }

-

-    iter->y++;

-}

-

-static void

-dest_write_back_wide (pixman_iter_t *iter)

-{

-    bits_image_t *  image  = &iter->image->bits;

-    int             x      = iter->x;

-    int             y      = iter->y;

-    int             width  = iter->width;

-    const uint32_t *buffer = iter->buffer;

-

-    image->store_scanline_64 (image, x, y, width, buffer);

-

-    if (image->common.alpha_map)

-    {

-	x -= image->common.alpha_origin_x;

-	y -= image->common.alpha_origin_y;

-

-	image->common.alpha_map->store_scanline_64 (

-	    image->common.alpha_map, x, y, width, buffer);

-    }

-

-    iter->y++;

-}

-

-void

-_pixman_bits_image_dest_iter_init (pixman_image_t *image, pixman_iter_t *iter)

-{

-    if (iter->flags & ITER_NARROW)

-    {

-	if ((iter->flags & (ITER_IGNORE_RGB | ITER_IGNORE_ALPHA)) ==

-	    (ITER_IGNORE_RGB | ITER_IGNORE_ALPHA))

-	{

-	    iter->get_scanline = _pixman_iter_get_scanline_noop;

-	}

-	else

-	{

-	    iter->get_scanline = dest_get_scanline_narrow;

-	}

-	

-	iter->write_back = dest_write_back_narrow;

-    }

-    else

-    {

-	iter->get_scanline = dest_get_scanline_wide;

-	iter->write_back = dest_write_back_wide;

-    }

-}

-

-static uint32_t *

-create_bits (pixman_format_code_t format,

-             int                  width,

-             int                  height,

-             int *                rowstride_bytes)

-{

-    int stride;

-    int buf_size;

-    int bpp;

-

-    /* what follows is a long-winded way, avoiding any possibility of integer

-     * overflows, of saying:

-     * stride = ((width * bpp + 0x1f) >> 5) * sizeof (uint32_t);

-     */

-

-    bpp = PIXMAN_FORMAT_BPP (format);

-    if (pixman_multiply_overflows_int (width, bpp))

-	return NULL;

-

-    stride = width * bpp;

-    if (pixman_addition_overflows_int (stride, 0x1f))

-	return NULL;

-

-    stride += 0x1f;

-    stride >>= 5;

-

-    stride *= sizeof (uint32_t);

-

-    if (pixman_multiply_overflows_int (height, stride))

-	return NULL;

-

-    buf_size = height * stride;

-

-    if (rowstride_bytes)

-	*rowstride_bytes = stride;

-

-    return calloc (buf_size, 1);

-}

-

-PIXMAN_EXPORT pixman_image_t *

-pixman_image_create_bits (pixman_format_code_t format,

-                          int                  width,

-                          int                  height,

-                          uint32_t *           bits,

-                          int                  rowstride_bytes)

-{

-    pixman_image_t *image;

-    uint32_t *free_me = NULL;

-

-    /* must be a whole number of uint32_t's

-     */

-    return_val_if_fail (

-	bits == NULL || (rowstride_bytes % sizeof (uint32_t)) == 0, NULL);

-

-    return_val_if_fail (PIXMAN_FORMAT_BPP (format) >= PIXMAN_FORMAT_DEPTH (format), NULL);

-

-    if (!bits && width && height)

-    {

-	free_me = bits = create_bits (format, width, height, &rowstride_bytes);

-	if (!bits)

-	    return NULL;

-    }

-

-    image = _pixman_image_allocate ();

-

-    if (!image)

-    {

-	if (free_me)

-	    free (free_me);

-

-	return NULL;

-    }

-

-    image->type = BITS;

-    image->bits.format = format;

-    image->bits.width = width;

-    image->bits.height = height;

-    image->bits.bits = bits;

-    image->bits.free_me = free_me;

-    image->bits.read_func = NULL;

-    image->bits.write_func = NULL;

-

-    /* The rowstride is stored in number of uint32_t */

-    image->bits.rowstride = rowstride_bytes / (int) sizeof (uint32_t);

-

-    image->bits.indexed = NULL;

-

-    image->common.property_changed = bits_image_property_changed;

-

-    _pixman_image_reset_clip_region (image);

-

-    return image;

-}

+/*
+ * Copyright © 2000 Keith Packard, member of The XFree86 Project, Inc.
+ *             2005 Lars Knoll & Zack Rusin, Trolltech
+ *             2008 Aaron Plattner, NVIDIA Corporation
+ * Copyright © 2000 SuSE, Inc.
+ * Copyright © 2007, 2009 Red Hat, Inc.
+ * Copyright © 2008 André Tupinambá <andrelrt@gmail.com>
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that
+ * copyright notice and this permission notice appear in supporting
+ * documentation, and that the name of Keith Packard not be used in
+ * advertising or publicity pertaining to distribution of the software without
+ * specific, written prior permission.  Keith Packard makes no
+ * representations about the suitability of this software for any purpose.  It
+ * is provided "as is" without express or implied warranty.
+ *
+ * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS
+ * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+ * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
+ * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
+ * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
+ * SOFTWARE.
+ */
+
+#ifdef HAVE_CONFIG_H
+#include <config.h>
+#endif
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "pixman-private.h"
+#include "pixman-combine32.h"
+#include "pixman-inlines.h"
+
+/*
+ * By default, just evaluate the image at 32bpp and expand.  Individual image
+ * types can plug in a better scanline getter if they want to. For example
+ * we  could produce smoother gradients by evaluating them at higher color
+ * depth, but that's a project for the future.
+ */
+static void
+_pixman_image_get_scanline_generic_64 (pixman_image_t * image,
+                                       int              x,
+                                       int              y,
+                                       int              width,
+                                       uint32_t *       buffer,
+                                       const uint32_t * mask)
+{
+    uint32_t *mask8 = NULL;
+
+    /* Contract the mask image, if one exists, so that the 32-bit fetch
+     * function can use it.
+     */
+    if (mask)
+    {
+	mask8 = pixman_malloc_ab (width, sizeof(uint32_t));
+	if (!mask8)
+	    return;
+
+	pixman_contract (mask8, (uint64_t *)mask, width);
+    }
+
+    /* Fetch the source image into the first half of buffer. */
+    image->bits.get_scanline_32 (image, x, y, width, (uint32_t*)buffer, mask8);
+
+    /* Expand from 32bpp to 64bpp in place. */
+    pixman_expand ((uint64_t *)buffer, buffer, PIXMAN_a8r8g8b8, width);
+
+    free (mask8);
+}
+
+/* Fetch functions */
+
+static force_inline uint32_t
+fetch_pixel_no_alpha (bits_image_t *image,
+		      int x, int y, pixman_bool_t check_bounds)
+{
+    if (check_bounds &&
+	(x < 0 || x >= image->width || y < 0 || y >= image->height))
+    {
+	return 0;
+    }
+
+    return image->fetch_pixel_32 (image, x, y);
+}
+
+typedef uint32_t (* get_pixel_t) (bits_image_t *image,
+				  int x, int y, pixman_bool_t check_bounds);
+
+static force_inline uint32_t
+bits_image_fetch_pixel_nearest (bits_image_t   *image,
+				pixman_fixed_t  x,
+				pixman_fixed_t  y,
+				get_pixel_t	get_pixel)
+{
+    int x0 = pixman_fixed_to_int (x - pixman_fixed_e);
+    int y0 = pixman_fixed_to_int (y - pixman_fixed_e);
+
+    if (image->common.repeat != PIXMAN_REPEAT_NONE)
+    {
+	repeat (image->common.repeat, &x0, image->width);
+	repeat (image->common.repeat, &y0, image->height);
+
+	return get_pixel (image, x0, y0, FALSE);
+    }
+    else
+    {
+	return get_pixel (image, x0, y0, TRUE);
+    }
+}
+
+static force_inline uint32_t
+bits_image_fetch_pixel_bilinear (bits_image_t   *image,
+				 pixman_fixed_t  x,
+				 pixman_fixed_t  y,
+				 get_pixel_t	 get_pixel)
+{
+    pixman_repeat_t repeat_mode = image->common.repeat;
+    int width = image->width;
+    int height = image->height;
+    int x1, y1, x2, y2;
+    uint32_t tl, tr, bl, br;
+    int32_t distx, disty;
+
+    x1 = x - pixman_fixed_1 / 2;
+    y1 = y - pixman_fixed_1 / 2;
+
+    distx = (x1 >> 8) & 0xff;
+    disty = (y1 >> 8) & 0xff;
+
+    x1 = pixman_fixed_to_int (x1);
+    y1 = pixman_fixed_to_int (y1);
+    x2 = x1 + 1;
+    y2 = y1 + 1;
+
+    if (repeat_mode != PIXMAN_REPEAT_NONE)
+    {
+	repeat (repeat_mode, &x1, width);
+	repeat (repeat_mode, &y1, height);
+	repeat (repeat_mode, &x2, width);
+	repeat (repeat_mode, &y2, height);
+
+	tl = get_pixel (image, x1, y1, FALSE);
+	bl = get_pixel (image, x1, y2, FALSE);
+	tr = get_pixel (image, x2, y1, FALSE);
+	br = get_pixel (image, x2, y2, FALSE);
+    }
+    else
+    {
+	tl = get_pixel (image, x1, y1, TRUE);
+	tr = get_pixel (image, x2, y1, TRUE);
+	bl = get_pixel (image, x1, y2, TRUE);
+	br = get_pixel (image, x2, y2, TRUE);
+    }
+
+    return bilinear_interpolation (tl, tr, bl, br, distx, disty);
+}
+
+static void
+bits_image_fetch_bilinear_no_repeat_8888 (pixman_image_t * ima,
+					  int              offset,
+					  int              line,
+					  int              width,
+					  uint32_t *       buffer,
+					  const uint32_t * mask)
+{
+    bits_image_t *bits = &ima->bits;
+    pixman_fixed_t x_top, x_bottom, x;
+    pixman_fixed_t ux_top, ux_bottom, ux;
+    pixman_vector_t v;
+    uint32_t top_mask, bottom_mask;
+    uint32_t *top_row;
+    uint32_t *bottom_row;
+    uint32_t *end;
+    uint32_t zero[2] = { 0, 0 };
+    uint32_t one = 1;
+    int y, y1, y2;
+    int disty;
+    int mask_inc;
+    int w;
+
+    /* reference point is the center of the pixel */
+    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;
+    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;
+    v.vector[2] = pixman_fixed_1;
+
+    if (!pixman_transform_point_3d (bits->common.transform, &v))
+	return;
+
+    ux = ux_top = ux_bottom = bits->common.transform->matrix[0][0];
+    x = x_top = x_bottom = v.vector[0] - pixman_fixed_1/2;
+
+    y = v.vector[1] - pixman_fixed_1/2;
+    disty = (y >> 8) & 0xff;
+
+    /* Load the pointers to the first and second lines from the source
+     * image that bilinear code must read.
+     *
+     * The main trick in this code is about the check if any line are
+     * outside of the image;
+     *
+     * When I realize that a line (any one) is outside, I change
+     * the pointer to a dummy area with zeros. Once I change this, I
+     * must be sure the pointer will not change, so I set the
+     * variables to each pointer increments inside the loop.
+     */
+    y1 = pixman_fixed_to_int (y);
+    y2 = y1 + 1;
+
+    if (y1 < 0 || y1 >= bits->height)
+    {
+	top_row = zero;
+	x_top = 0;
+	ux_top = 0;
+    }
+    else
+    {
+	top_row = bits->bits + y1 * bits->rowstride;
+	x_top = x;
+	ux_top = ux;
+    }
+
+    if (y2 < 0 || y2 >= bits->height)
+    {
+	bottom_row = zero;
+	x_bottom = 0;
+	ux_bottom = 0;
+    }
+    else
+    {
+	bottom_row = bits->bits + y2 * bits->rowstride;
+	x_bottom = x;
+	ux_bottom = ux;
+    }
+
+    /* Instead of checking whether the operation uses the mast in
+     * each loop iteration, verify this only once and prepare the
+     * variables to make the code smaller inside the loop.
+     */
+    if (!mask)
+    {
+        mask_inc = 0;
+        mask = &one;
+    }
+    else
+    {
+        /* If have a mask, prepare the variables to check it */
+        mask_inc = 1;
+    }
+
+    /* If both are zero, then the whole thing is zero */
+    if (top_row == zero && bottom_row == zero)
+    {
+	memset (buffer, 0, width * sizeof (uint32_t));
+	return;
+    }
+    else if (bits->format == PIXMAN_x8r8g8b8)
+    {
+	if (top_row == zero)
+	{
+	    top_mask = 0;
+	    bottom_mask = 0xff000000;
+	}
+	else if (bottom_row == zero)
+	{
+	    top_mask = 0xff000000;
+	    bottom_mask = 0;
+	}
+	else
+	{
+	    top_mask = 0xff000000;
+	    bottom_mask = 0xff000000;
+	}
+    }
+    else
+    {
+	top_mask = 0;
+	bottom_mask = 0;
+    }
+
+    end = buffer + width;
+
+    /* Zero fill to the left of the image */
+    while (buffer < end && x < pixman_fixed_minus_1)
+    {
+	*buffer++ = 0;
+	x += ux;
+	x_top += ux_top;
+	x_bottom += ux_bottom;
+	mask += mask_inc;
+    }
+
+    /* Left edge
+     */
+    while (buffer < end && x < 0)
+    {
+	uint32_t tr, br;
+	int32_t distx;
+
+	tr = top_row[pixman_fixed_to_int (x_top) + 1] | top_mask;
+	br = bottom_row[pixman_fixed_to_int (x_bottom) + 1] | bottom_mask;
+
+	distx = (x >> 8) & 0xff;
+
+	*buffer++ = bilinear_interpolation (0, tr, 0, br, distx, disty);
+
+	x += ux;
+	x_top += ux_top;
+	x_bottom += ux_bottom;
+	mask += mask_inc;
+    }
+
+    /* Main part */
+    w = pixman_int_to_fixed (bits->width - 1);
+
+    while (buffer < end  &&  x < w)
+    {
+	if (*mask)
+	{
+	    uint32_t tl, tr, bl, br;
+	    int32_t distx;
+
+	    tl = top_row [pixman_fixed_to_int (x_top)] | top_mask;
+	    tr = top_row [pixman_fixed_to_int (x_top) + 1] | top_mask;
+	    bl = bottom_row [pixman_fixed_to_int (x_bottom)] | bottom_mask;
+	    br = bottom_row [pixman_fixed_to_int (x_bottom) + 1] | bottom_mask;
+
+	    distx = (x >> 8) & 0xff;
+
+	    *buffer = bilinear_interpolation (tl, tr, bl, br, distx, disty);
+	}
+
+	buffer++;
+	x += ux;
+	x_top += ux_top;
+	x_bottom += ux_bottom;
+	mask += mask_inc;
+    }
+
+    /* Right Edge */
+    w = pixman_int_to_fixed (bits->width);
+    while (buffer < end  &&  x < w)
+    {
+	if (*mask)
+	{
+	    uint32_t tl, bl;
+	    int32_t distx;
+
+	    tl = top_row [pixman_fixed_to_int (x_top)] | top_mask;
+	    bl = bottom_row [pixman_fixed_to_int (x_bottom)] | bottom_mask;
+
+	    distx = (x >> 8) & 0xff;
+
+	    *buffer = bilinear_interpolation (tl, 0, bl, 0, distx, disty);
+	}
+
+	buffer++;
+	x += ux;
+	x_top += ux_top;
+	x_bottom += ux_bottom;
+	mask += mask_inc;
+    }
+
+    /* Zero fill to the left of the image */
+    while (buffer < end)
+	*buffer++ = 0;
+}
+
+static force_inline uint32_t
+bits_image_fetch_pixel_convolution (bits_image_t   *image,
+				    pixman_fixed_t  x,
+				    pixman_fixed_t  y,
+				    get_pixel_t     get_pixel)
+{
+    pixman_fixed_t *params = image->common.filter_params;
+    int x_off = (params[0] - pixman_fixed_1) >> 1;
+    int y_off = (params[1] - pixman_fixed_1) >> 1;
+    int32_t cwidth = pixman_fixed_to_int (params[0]);
+    int32_t cheight = pixman_fixed_to_int (params[1]);
+    int32_t srtot, sgtot, sbtot, satot;
+    int32_t i, j, x1, x2, y1, y2;
+    pixman_repeat_t repeat_mode = image->common.repeat;
+    int width = image->width;
+    int height = image->height;
+
+    params += 2;
+
+    x1 = pixman_fixed_to_int (x - pixman_fixed_e - x_off);
+    y1 = pixman_fixed_to_int (y - pixman_fixed_e - y_off);
+    x2 = x1 + cwidth;
+    y2 = y1 + cheight;
+
+    srtot = sgtot = sbtot = satot = 0;
+
+    for (i = y1; i < y2; ++i)
+    {
+	for (j = x1; j < x2; ++j)
+	{
+	    int rx = j;
+	    int ry = i;
+
+	    pixman_fixed_t f = *params;
+
+	    if (f)
+	    {
+		uint32_t pixel;
+
+		if (repeat_mode != PIXMAN_REPEAT_NONE)
+		{
+		    repeat (repeat_mode, &rx, width);
+		    repeat (repeat_mode, &ry, height);
+
+		    pixel = get_pixel (image, rx, ry, FALSE);
+		}
+		else
+		{
+		    pixel = get_pixel (image, rx, ry, TRUE);
+		}
+
+		srtot += RED_8 (pixel) * f;
+		sgtot += GREEN_8 (pixel) * f;
+		sbtot += BLUE_8 (pixel) * f;
+		satot += ALPHA_8 (pixel) * f;
+	    }
+
+	    params++;
+	}
+    }
+
+    satot >>= 16;
+    srtot >>= 16;
+    sgtot >>= 16;
+    sbtot >>= 16;
+
+    satot = CLIP (satot, 0, 0xff);
+    srtot = CLIP (srtot, 0, 0xff);
+    sgtot = CLIP (sgtot, 0, 0xff);
+    sbtot = CLIP (sbtot, 0, 0xff);
+
+    return ((satot << 24) | (srtot << 16) | (sgtot <<  8) | (sbtot));
+}
+
+static force_inline uint32_t
+bits_image_fetch_pixel_filtered (bits_image_t *image,
+				 pixman_fixed_t x,
+				 pixman_fixed_t y,
+				 get_pixel_t    get_pixel)
+{
+    switch (image->common.filter)
+    {
+    case PIXMAN_FILTER_NEAREST:
+    case PIXMAN_FILTER_FAST:
+	return bits_image_fetch_pixel_nearest (image, x, y, get_pixel);
+	break;
+
+    case PIXMAN_FILTER_BILINEAR:
+    case PIXMAN_FILTER_GOOD:
+    case PIXMAN_FILTER_BEST:
+	return bits_image_fetch_pixel_bilinear (image, x, y, get_pixel);
+	break;
+
+    case PIXMAN_FILTER_CONVOLUTION:
+	return bits_image_fetch_pixel_convolution (image, x, y, get_pixel);
+	break;
+
+    default:
+        break;
+    }
+
+    return 0;
+}
+
+static void
+bits_image_fetch_affine_no_alpha (pixman_image_t * image,
+				  int              offset,
+				  int              line,
+				  int              width,
+				  uint32_t *       buffer,
+				  const uint32_t * mask)
+{
+    pixman_fixed_t x, y;
+    pixman_fixed_t ux, uy;
+    pixman_vector_t v;
+    int i;
+
+    /* reference point is the center of the pixel */
+    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;
+    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;
+    v.vector[2] = pixman_fixed_1;
+
+    if (image->common.transform)
+    {
+	if (!pixman_transform_point_3d (image->common.transform, &v))
+	    return;
+
+	ux = image->common.transform->matrix[0][0];
+	uy = image->common.transform->matrix[1][0];
+    }
+    else
+    {
+	ux = pixman_fixed_1;
+	uy = 0;
+    }
+
+    x = v.vector[0];
+    y = v.vector[1];
+
+    for (i = 0; i < width; ++i)
+    {
+	if (!mask || mask[i])
+	{
+	    buffer[i] = bits_image_fetch_pixel_filtered (
+		&image->bits, x, y, fetch_pixel_no_alpha);
+	}
+
+	x += ux;
+	y += uy;
+    }
+}
+
+/* General fetcher */
+static force_inline uint32_t
+fetch_pixel_general (bits_image_t *image, int x, int y, pixman_bool_t check_bounds)
+{
+    uint32_t pixel;
+
+    if (check_bounds &&
+	(x < 0 || x >= image->width || y < 0 || y >= image->height))
+    {
+	return 0;
+    }
+
+    pixel = image->fetch_pixel_32 (image, x, y);
+
+    if (image->common.alpha_map)
+    {
+	uint32_t pixel_a;
+
+	x -= image->common.alpha_origin_x;
+	y -= image->common.alpha_origin_y;
+
+	if (x < 0 || x >= image->common.alpha_map->width ||
+	    y < 0 || y >= image->common.alpha_map->height)
+	{
+	    pixel_a = 0;
+	}
+	else
+	{
+	    pixel_a = image->common.alpha_map->fetch_pixel_32 (
+		image->common.alpha_map, x, y);
+
+	    pixel_a = ALPHA_8 (pixel_a);
+	}
+
+	pixel &= 0x00ffffff;
+	pixel |= (pixel_a << 24);
+    }
+
+    return pixel;
+}
+
+static void
+bits_image_fetch_general (pixman_image_t * image,
+			  int              offset,
+			  int              line,
+			  int              width,
+			  uint32_t *       buffer,
+			  const uint32_t * mask)
+{
+    pixman_fixed_t x, y, w;
+    pixman_fixed_t ux, uy, uw;
+    pixman_vector_t v;
+    int i;
+
+    /* reference point is the center of the pixel */
+    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;
+    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;
+    v.vector[2] = pixman_fixed_1;
+
+    if (image->common.transform)
+    {
+	if (!pixman_transform_point_3d (image->common.transform, &v))
+	    return;
+
+	ux = image->common.transform->matrix[0][0];
+	uy = image->common.transform->matrix[1][0];
+	uw = image->common.transform->matrix[2][0];
+    }
+    else
+    {
+	ux = pixman_fixed_1;
+	uy = 0;
+	uw = 0;
+    }
+
+    x = v.vector[0];
+    y = v.vector[1];
+    w = v.vector[2];
+
+    for (i = 0; i < width; ++i)
+    {
+	pixman_fixed_t x0, y0;
+
+	if (!mask || mask[i])
+	{
+	    if (w != 0)
+	    {
+		x0 = ((pixman_fixed_48_16_t)x << 16) / w;
+		y0 = ((pixman_fixed_48_16_t)y << 16) / w;
+	    }
+	    else
+	    {
+		x0 = 0;
+		y0 = 0;
+	    }
+
+	    buffer[i] = bits_image_fetch_pixel_filtered (
+		&image->bits, x0, y0, fetch_pixel_general);
+	}
+
+	x += ux;
+	y += uy;
+	w += uw;
+    }
+}
+
+static const uint8_t zero[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+
+typedef uint32_t (* convert_pixel_t) (const uint8_t *row, int x);
+
+static force_inline void
+bits_image_fetch_bilinear_affine (pixman_image_t * image,
+				  int              offset,
+				  int              line,
+				  int              width,
+				  uint32_t *       buffer,
+				  const uint32_t * mask,
+
+				  convert_pixel_t	convert_pixel,
+				  pixman_format_code_t	format,
+				  pixman_repeat_t	repeat_mode)
+{
+    pixman_fixed_t x, y;
+    pixman_fixed_t ux, uy;
+    pixman_vector_t v;
+    bits_image_t *bits = &image->bits;
+    int i;
+
+    /* reference point is the center of the pixel */
+    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;
+    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;
+    v.vector[2] = pixman_fixed_1;
+
+    if (!pixman_transform_point_3d (image->common.transform, &v))
+	return;
+
+    ux = image->common.transform->matrix[0][0];
+    uy = image->common.transform->matrix[1][0];
+
+    x = v.vector[0];
+    y = v.vector[1];
+
+    for (i = 0; i < width; ++i)
+    {
+	int x1, y1, x2, y2;
+	uint32_t tl, tr, bl, br;
+	int32_t distx, disty;
+	int width = image->bits.width;
+	int height = image->bits.height;
+	const uint8_t *row1;
+	const uint8_t *row2;
+
+	if (mask && !mask[i])
+	    goto next;
+
+	x1 = x - pixman_fixed_1 / 2;
+	y1 = y - pixman_fixed_1 / 2;
+
+	distx = (x1 >> 8) & 0xff;
+	disty = (y1 >> 8) & 0xff;
+
+	y1 = pixman_fixed_to_int (y1);
+	y2 = y1 + 1;
+	x1 = pixman_fixed_to_int (x1);
+	x2 = x1 + 1;
+
+	if (repeat_mode != PIXMAN_REPEAT_NONE)
+	{
+	    uint32_t mask;
+
+	    mask = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;
+
+	    repeat (repeat_mode, &x1, width);
+	    repeat (repeat_mode, &y1, height);
+	    repeat (repeat_mode, &x2, width);
+	    repeat (repeat_mode, &y2, height);
+
+	    row1 = (uint8_t *)bits->bits + bits->rowstride * 4 * y1;
+	    row2 = (uint8_t *)bits->bits + bits->rowstride * 4 * y2;
+
+	    tl = convert_pixel (row1, x1) | mask;
+	    tr = convert_pixel (row1, x2) | mask;
+	    bl = convert_pixel (row2, x1) | mask;
+	    br = convert_pixel (row2, x2) | mask;
+	}
+	else
+	{
+	    uint32_t mask1, mask2;
+	    int bpp;
+
+	    /* Note: PIXMAN_FORMAT_BPP() returns an unsigned value,
+	     * which means if you use it in expressions, those
+	     * expressions become unsigned themselves. Since
+	     * the variables below can be negative in some cases,
+	     * that will lead to crashes on 64 bit architectures.
+	     *
+	     * So this line makes sure bpp is signed
+	     */
+	    bpp = PIXMAN_FORMAT_BPP (format);
+
+	    if (x1 >= width || x2 < 0 || y1 >= height || y2 < 0)
+	    {
+		buffer[i] = 0;
+		goto next;
+	    }
+
+	    if (y2 == 0)
+	    {
+		row1 = zero;
+		mask1 = 0;
+	    }
+	    else
+	    {
+		row1 = (uint8_t *)bits->bits + bits->rowstride * 4 * y1;
+		row1 += bpp / 8 * x1;
+
+		mask1 = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;
+	    }
+
+	    if (y1 == height - 1)
+	    {
+		row2 = zero;
+		mask2 = 0;
+	    }
+	    else
+	    {
+		row2 = (uint8_t *)bits->bits + bits->rowstride * 4 * y2;
+		row2 += bpp / 8 * x1;
+
+		mask2 = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;
+	    }
+
+	    if (x2 == 0)
+	    {
+		tl = 0;
+		bl = 0;
+	    }
+	    else
+	    {
+		tl = convert_pixel (row1, 0) | mask1;
+		bl = convert_pixel (row2, 0) | mask2;
+	    }
+
+	    if (x1 == width - 1)
+	    {
+		tr = 0;
+		br = 0;
+	    }
+	    else
+	    {
+		tr = convert_pixel (row1, 1) | mask1;
+		br = convert_pixel (row2, 1) | mask2;
+	    }
+	}
+
+	buffer[i] = bilinear_interpolation (
+	    tl, tr, bl, br, distx, disty);
+
+    next:
+	x += ux;
+	y += uy;
+    }
+}
+
+static force_inline void
+bits_image_fetch_nearest_affine (pixman_image_t * image,
+				 int              offset,
+				 int              line,
+				 int              width,
+				 uint32_t *       buffer,
+				 const uint32_t * mask,
+				 
+				 convert_pixel_t	convert_pixel,
+				 pixman_format_code_t	format,
+				 pixman_repeat_t	repeat_mode)
+{
+    pixman_fixed_t x, y;
+    pixman_fixed_t ux, uy;
+    pixman_vector_t v;
+    bits_image_t *bits = &image->bits;
+    int i;
+
+    /* reference point is the center of the pixel */
+    v.vector[0] = pixman_int_to_fixed (offset) + pixman_fixed_1 / 2;
+    v.vector[1] = pixman_int_to_fixed (line) + pixman_fixed_1 / 2;
+    v.vector[2] = pixman_fixed_1;
+
+    if (!pixman_transform_point_3d (image->common.transform, &v))
+	return;
+
+    ux = image->common.transform->matrix[0][0];
+    uy = image->common.transform->matrix[1][0];
+
+    x = v.vector[0];
+    y = v.vector[1];
+
+    for (i = 0; i < width; ++i)
+    {
+	int width, height, x0, y0;
+	const uint8_t *row;
+
+	if (mask && !mask[i])
+	    goto next;
+	
+	width = image->bits.width;
+	height = image->bits.height;
+	x0 = pixman_fixed_to_int (x - pixman_fixed_e);
+	y0 = pixman_fixed_to_int (y - pixman_fixed_e);
+
+	if (repeat_mode == PIXMAN_REPEAT_NONE &&
+	    (y0 < 0 || y0 >= height || x0 < 0 || x0 >= width))
+	{
+	    buffer[i] = 0;
+	}
+	else
+	{
+	    uint32_t mask = PIXMAN_FORMAT_A (format)? 0 : 0xff000000;
+
+	    if (repeat_mode != PIXMAN_REPEAT_NONE)
+	    {
+		repeat (repeat_mode, &x0, width);
+		repeat (repeat_mode, &y0, height);
+	    }
+
+	    row = (uint8_t *)bits->bits + bits->rowstride * 4 * y0;
+
+	    buffer[i] = convert_pixel (row, x0) | mask;
+	}
+
+    next:
+	x += ux;
+	y += uy;
+    }
+}
+
+static force_inline uint32_t
+convert_a8r8g8b8 (const uint8_t *row, int x)
+{
+    return *(((uint32_t *)row) + x);
+}
+
+static force_inline uint32_t
+convert_x8r8g8b8 (const uint8_t *row, int x)
+{
+    return *(((uint32_t *)row) + x);
+}
+
+static force_inline uint32_t
+convert_a8 (const uint8_t *row, int x)
+{
+    return *(row + x) << 24;
+}
+
+static force_inline uint32_t
+convert_r5g6b5 (const uint8_t *row, int x)
+{
+    return CONVERT_0565_TO_0888 (*((uint16_t *)row + x));
+}
+
+#define MAKE_BILINEAR_FETCHER(name, format, repeat_mode)		\
+    static void								\
+    bits_image_fetch_bilinear_affine_ ## name (pixman_image_t *image,	\
+					       int              offset,	\
+					       int              line,	\
+					       int              width,	\
+					       uint32_t *       buffer,	\
+					       const uint32_t * mask)	\
+    {									\
+	bits_image_fetch_bilinear_affine (image, offset, line,		\
+					  width, buffer, mask,		\
+					  convert_ ## format,		\
+					  PIXMAN_ ## format,		\
+					  repeat_mode);			\
+    }
+
+#define MAKE_NEAREST_FETCHER(name, format, repeat_mode)			\
+    static void								\
+    bits_image_fetch_nearest_affine_ ## name (pixman_image_t *image,	\
+					      int              offset,	\
+					      int              line,	\
+					      int              width,	\
+					      uint32_t *       buffer,	\
+					      const uint32_t * mask)	\
+    {									\
+	bits_image_fetch_nearest_affine (image, offset, line,		\
+					 width, buffer, mask,		\
+					 convert_ ## format,		\
+					 PIXMAN_ ## format,		\
+					 repeat_mode);			\
+    }
+
+#define MAKE_FETCHERS(name, format, repeat_mode)			\
+    MAKE_NEAREST_FETCHER (name, format, repeat_mode)			\
+    MAKE_BILINEAR_FETCHER (name, format, repeat_mode)
+
+MAKE_FETCHERS (pad_a8r8g8b8,     a8r8g8b8, PIXMAN_REPEAT_PAD)
+MAKE_FETCHERS (none_a8r8g8b8,    a8r8g8b8, PIXMAN_REPEAT_NONE)
+MAKE_FETCHERS (reflect_a8r8g8b8, a8r8g8b8, PIXMAN_REPEAT_REFLECT)
+MAKE_FETCHERS (normal_a8r8g8b8,  a8r8g8b8, PIXMAN_REPEAT_NORMAL)
+MAKE_FETCHERS (pad_x8r8g8b8,     x8r8g8b8, PIXMAN_REPEAT_PAD)
+MAKE_FETCHERS (none_x8r8g8b8,    x8r8g8b8, PIXMAN_REPEAT_NONE)
+MAKE_FETCHERS (reflect_x8r8g8b8, x8r8g8b8, PIXMAN_REPEAT_REFLECT)
+MAKE_FETCHERS (normal_x8r8g8b8,  x8r8g8b8, PIXMAN_REPEAT_NORMAL)
+MAKE_FETCHERS (pad_a8,           a8,       PIXMAN_REPEAT_PAD)
+MAKE_FETCHERS (none_a8,          a8,       PIXMAN_REPEAT_NONE)
+MAKE_FETCHERS (reflect_a8,	 a8,       PIXMAN_REPEAT_REFLECT)
+MAKE_FETCHERS (normal_a8,	 a8,       PIXMAN_REPEAT_NORMAL)
+MAKE_FETCHERS (pad_r5g6b5,       r5g6b5,   PIXMAN_REPEAT_PAD)
+MAKE_FETCHERS (none_r5g6b5,      r5g6b5,   PIXMAN_REPEAT_NONE)
+MAKE_FETCHERS (reflect_r5g6b5,   r5g6b5,   PIXMAN_REPEAT_REFLECT)
+MAKE_FETCHERS (normal_r5g6b5,    r5g6b5,   PIXMAN_REPEAT_NORMAL)
+
+static void
+bits_image_fetch_solid_32 (pixman_image_t * image,
+                           int              x,
+                           int              y,
+                           int              width,
+                           uint32_t *       buffer,
+                           const uint32_t * mask)
+{
+    uint32_t color;
+    uint32_t *end;
+
+    color = image->bits.fetch_pixel_32 (&image->bits, 0, 0);
+
+    end = buffer + width;
+    while (buffer < end)
+	*(buffer++) = color;
+}
+
+static void
+bits_image_fetch_solid_64 (pixman_image_t * image,
+                           int              x,
+                           int              y,
+                           int              width,
+                           uint32_t *       b,
+                           const uint32_t * unused)
+{
+    uint64_t color;
+    uint64_t *buffer = (uint64_t *)b;
+    uint64_t *end;
+
+    color = image->bits.fetch_pixel_64 (&image->bits, 0, 0);
+
+    end = buffer + width;
+    while (buffer < end)
+	*(buffer++) = color;
+}
+
+static void
+bits_image_fetch_untransformed_repeat_none (bits_image_t *image,
+                                            pixman_bool_t wide,
+                                            int           x,
+                                            int           y,
+                                            int           width,
+                                            uint32_t *    buffer)
+{
+    uint32_t w;
+
+    if (y < 0 || y >= image->height)
+    {
+	memset (buffer, 0, width * (wide? 8 : 4));
+	return;
+    }
+
+    if (x < 0)
+    {
+	w = MIN (width, -x);
+
+	memset (buffer, 0, w * (wide ? 8 : 4));
+
+	width -= w;
+	buffer += w * (wide? 2 : 1);
+	x += w;
+    }
+
+    if (x < image->width)
+    {
+	w = MIN (width, image->width - x);
+
+	if (wide)
+	    image->fetch_scanline_64 ((pixman_image_t *)image, x, y, w, buffer, NULL);
+	else
+	    image->fetch_scanline_32 ((pixman_image_t *)image, x, y, w, buffer, NULL);
+
+	width -= w;
+	buffer += w * (wide? 2 : 1);
+	x += w;
+    }
+
+    memset (buffer, 0, width * (wide ? 8 : 4));
+}
+
+static void
+bits_image_fetch_untransformed_repeat_normal (bits_image_t *image,
+                                              pixman_bool_t wide,
+                                              int           x,
+                                              int           y,
+                                              int           width,
+                                              uint32_t *    buffer)
+{
+    uint32_t w;
+
+    while (y < 0)
+	y += image->height;
+
+    while (y >= image->height)
+	y -= image->height;
+
+    while (width)
+    {
+	while (x < 0)
+	    x += image->width;
+	while (x >= image->width)
+	    x -= image->width;
+
+	w = MIN (width, image->width - x);
+
+	if (wide)
+	    image->fetch_scanline_64 ((pixman_image_t *)image, x, y, w, buffer, NULL);
+	else
+	    image->fetch_scanline_32 ((pixman_image_t *)image, x, y, w, buffer, NULL);
+
+	buffer += w * (wide? 2 : 1);
+	x += w;
+	width -= w;
+    }
+}
+
+static void
+bits_image_fetch_untransformed_32 (pixman_image_t * image,
+                                   int              x,
+                                   int              y,
+                                   int              width,
+                                   uint32_t *       buffer,
+                                   const uint32_t * mask)
+{
+    if (image->common.repeat == PIXMAN_REPEAT_NONE)
+    {
+	bits_image_fetch_untransformed_repeat_none (
+	    &image->bits, FALSE, x, y, width, buffer);
+    }
+    else
+    {
+	bits_image_fetch_untransformed_repeat_normal (
+	    &image->bits, FALSE, x, y, width, buffer);
+    }
+}
+
+static void
+bits_image_fetch_untransformed_64 (pixman_image_t * image,
+                                   int              x,
+                                   int              y,
+                                   int              width,
+                                   uint32_t *       buffer,
+                                   const uint32_t * unused)
+{
+    if (image->common.repeat == PIXMAN_REPEAT_NONE)
+    {
+	bits_image_fetch_untransformed_repeat_none (
+	    &image->bits, TRUE, x, y, width, buffer);
+    }
+    else
+    {
+	bits_image_fetch_untransformed_repeat_normal (
+	    &image->bits, TRUE, x, y, width, buffer);
+    }
+}
+
+typedef struct
+{
+    pixman_format_code_t	format;
+    uint32_t			flags;
+    fetch_scanline_t		fetch_32;
+    fetch_scanline_t		fetch_64;
+} fetcher_info_t;
+
+static const fetcher_info_t fetcher_info[] =
+{
+    { PIXMAN_solid,
+      FAST_PATH_NO_ALPHA_MAP,
+      bits_image_fetch_solid_32,
+      bits_image_fetch_solid_64
+    },
+
+    { PIXMAN_any,
+      (FAST_PATH_NO_ALPHA_MAP			|
+       FAST_PATH_ID_TRANSFORM			|
+       FAST_PATH_NO_CONVOLUTION_FILTER		|
+       FAST_PATH_NO_PAD_REPEAT			|
+       FAST_PATH_NO_REFLECT_REPEAT),
+      bits_image_fetch_untransformed_32,
+      bits_image_fetch_untransformed_64
+    },
+
+#define FAST_BILINEAR_FLAGS						\
+    (FAST_PATH_NO_ALPHA_MAP		|				\
+     FAST_PATH_NO_ACCESSORS		|				\
+     FAST_PATH_HAS_TRANSFORM		|				\
+     FAST_PATH_AFFINE_TRANSFORM		|				\
+     FAST_PATH_X_UNIT_POSITIVE		|				\
+     FAST_PATH_Y_UNIT_ZERO		|				\
+     FAST_PATH_NONE_REPEAT		|				\
+     FAST_PATH_BILINEAR_FILTER)
+
+    { PIXMAN_a8r8g8b8,
+      FAST_BILINEAR_FLAGS,
+      bits_image_fetch_bilinear_no_repeat_8888,
+      _pixman_image_get_scanline_generic_64
+    },
+
+    { PIXMAN_x8r8g8b8,
+      FAST_BILINEAR_FLAGS,
+      bits_image_fetch_bilinear_no_repeat_8888,
+      _pixman_image_get_scanline_generic_64
+    },
+
+#define GENERAL_BILINEAR_FLAGS						\
+    (FAST_PATH_NO_ALPHA_MAP		|				\
+     FAST_PATH_NO_ACCESSORS		|				\
+     FAST_PATH_HAS_TRANSFORM		|				\
+     FAST_PATH_AFFINE_TRANSFORM		|				\
+     FAST_PATH_BILINEAR_FILTER)
+
+#define GENERAL_NEAREST_FLAGS						\
+    (FAST_PATH_NO_ALPHA_MAP		|				\
+     FAST_PATH_NO_ACCESSORS		|				\
+     FAST_PATH_HAS_TRANSFORM		|				\
+     FAST_PATH_AFFINE_TRANSFORM		|				\
+     FAST_PATH_NEAREST_FILTER)
+
+#define BILINEAR_AFFINE_FAST_PATH(name, format, repeat)			\
+    { PIXMAN_ ## format,						\
+      GENERAL_BILINEAR_FLAGS | FAST_PATH_ ## repeat ## _REPEAT,		\
+      bits_image_fetch_bilinear_affine_ ## name,			\
+      _pixman_image_get_scanline_generic_64				\
+    },
+
+#define NEAREST_AFFINE_FAST_PATH(name, format, repeat)			\
+    { PIXMAN_ ## format,						\
+      GENERAL_NEAREST_FLAGS | FAST_PATH_ ## repeat ## _REPEAT,		\
+      bits_image_fetch_nearest_affine_ ## name,			\
+      _pixman_image_get_scanline_generic_64				\
+    },
+
+#define AFFINE_FAST_PATHS(name, format, repeat)				\
+    BILINEAR_AFFINE_FAST_PATH(name, format, repeat)			\
+    NEAREST_AFFINE_FAST_PATH(name, format, repeat)
+    
+    AFFINE_FAST_PATHS (pad_a8r8g8b8, a8r8g8b8, PAD)
+    AFFINE_FAST_PATHS (none_a8r8g8b8, a8r8g8b8, NONE)
+    AFFINE_FAST_PATHS (reflect_a8r8g8b8, a8r8g8b8, REFLECT)
+    AFFINE_FAST_PATHS (normal_a8r8g8b8, a8r8g8b8, NORMAL)
+    AFFINE_FAST_PATHS (pad_x8r8g8b8, x8r8g8b8, PAD)
+    AFFINE_FAST_PATHS (none_x8r8g8b8, x8r8g8b8, NONE)
+    AFFINE_FAST_PATHS (reflect_x8r8g8b8, x8r8g8b8, REFLECT)
+    AFFINE_FAST_PATHS (normal_x8r8g8b8, x8r8g8b8, NORMAL)
+    AFFINE_FAST_PATHS (pad_a8, a8, PAD)
+    AFFINE_FAST_PATHS (none_a8, a8, NONE)
+    AFFINE_FAST_PATHS (reflect_a8, a8, REFLECT)
+    AFFINE_FAST_PATHS (normal_a8, a8, NORMAL)
+    AFFINE_FAST_PATHS (pad_r5g6b5, r5g6b5, PAD)
+    AFFINE_FAST_PATHS (none_r5g6b5, r5g6b5, NONE)
+    AFFINE_FAST_PATHS (reflect_r5g6b5, r5g6b5, REFLECT)
+    AFFINE_FAST_PATHS (normal_r5g6b5, r5g6b5, NORMAL)
+
+    /* Affine, no alpha */
+    { PIXMAN_any,
+      (FAST_PATH_NO_ALPHA_MAP | FAST_PATH_HAS_TRANSFORM | FAST_PATH_AFFINE_TRANSFORM),
+      bits_image_fetch_affine_no_alpha,
+      _pixman_image_get_scanline_generic_64
+    },
+
+    /* General */
+    { PIXMAN_any, 0, bits_image_fetch_general, _pixman_image_get_scanline_generic_64 },
+
+    { PIXMAN_null },
+};
+
+static void
+bits_image_property_changed (pixman_image_t *image)
+{
+    uint32_t flags = image->common.flags;
+    pixman_format_code_t format = image->common.extended_format_code;
+    const fetcher_info_t *info;
+
+    _pixman_bits_image_setup_accessors (&image->bits);
+
+    info = fetcher_info;
+    while (info->format != PIXMAN_null)
+    {
+	if ((info->format == format || info->format == PIXMAN_any)	&&
+	    (info->flags & flags) == info->flags)
+	{
+	    image->bits.get_scanline_32 = info->fetch_32;
+	    image->bits.get_scanline_64 = info->fetch_64;
+	    break;
+	}
+
+	info++;
+    }
+}
+
+static uint32_t *
+src_get_scanline_narrow (pixman_iter_t *iter, const uint32_t *mask)
+{
+    iter->image->bits.get_scanline_32 (
+	iter->image, iter->x, iter->y++, iter->width, iter->buffer, mask);
+
+    return iter->buffer;
+}
+
+static uint32_t *
+src_get_scanline_wide (pixman_iter_t *iter, const uint32_t *mask)
+{
+    iter->image->bits.get_scanline_64 (
+	iter->image, iter->x, iter->y++, iter->width, iter->buffer, mask);
+
+    return iter->buffer;
+}
+
+void
+_pixman_bits_image_src_iter_init (pixman_image_t *image, pixman_iter_t *iter)
+{
+    if (iter->flags & ITER_NARROW)
+	iter->get_scanline = src_get_scanline_narrow;
+    else
+	iter->get_scanline = src_get_scanline_wide;
+}
+
+static uint32_t *
+dest_get_scanline_narrow (pixman_iter_t *iter, const uint32_t *mask)
+{
+    pixman_image_t *image  = iter->image;
+    int             x      = iter->x;
+    int             y      = iter->y;
+    int             width  = iter->width;
+    uint32_t *	    buffer = iter->buffer;
+
+    image->bits.fetch_scanline_32 (image, x, y, width, buffer, mask);
+    if (image->common.alpha_map)
+    {
+	x -= image->common.alpha_origin_x;
+	y -= image->common.alpha_origin_y;
+
+	image->common.alpha_map->fetch_scanline_32 (
+	    (pixman_image_t *)image->common.alpha_map,
+	    x, y, width, buffer, mask);
+    }
+
+    return iter->buffer;
+}
+
+static uint32_t *
+dest_get_scanline_wide (pixman_iter_t *iter, const uint32_t *mask)
+{
+    bits_image_t *  image  = &iter->image->bits;
+    int             x      = iter->x;
+    int             y      = iter->y;
+    int             width  = iter->width;
+    uint32_t *	    buffer = iter->buffer;
+
+    image->fetch_scanline_64 (
+	(pixman_image_t *)image, x, y, width, buffer, mask);
+    if (image->common.alpha_map)
+    {
+	x -= image->common.alpha_origin_x;
+	y -= image->common.alpha_origin_y;
+
+	image->common.alpha_map->fetch_scanline_64 (
+	    (pixman_image_t *)image->common.alpha_map, x, y, width, buffer, mask);
+    }
+
+    return iter->buffer;
+}
+
+static void
+dest_write_back_narrow (pixman_iter_t *iter)
+{
+    bits_image_t *  image  = &iter->image->bits;
+    int             x      = iter->x;
+    int             y      = iter->y;
+    int             width  = iter->width;
+    const uint32_t *buffer = iter->buffer;
+
+    image->store_scanline_32 (image, x, y, width, buffer);
+
+    if (image->common.alpha_map)
+    {
+	x -= image->common.alpha_origin_x;
+	y -= image->common.alpha_origin_y;
+
+	image->common.alpha_map->store_scanline_32 (
+	    image->common.alpha_map, x, y, width, buffer);
+    }
+
+    iter->y++;
+}
+
+static void
+dest_write_back_wide (pixman_iter_t *iter)
+{
+    bits_image_t *  image  = &iter->image->bits;
+    int             x      = iter->x;
+    int             y      = iter->y;
+    int             width  = iter->width;
+    const uint32_t *buffer = iter->buffer;
+
+    image->store_scanline_64 (image, x, y, width, buffer);
+
+    if (image->common.alpha_map)
+    {
+	x -= image->common.alpha_origin_x;
+	y -= image->common.alpha_origin_y;
+
+	image->common.alpha_map->store_scanline_64 (
+	    image->common.alpha_map, x, y, width, buffer);
+    }
+
+    iter->y++;
+}
+
+void
+_pixman_bits_image_dest_iter_init (pixman_image_t *image, pixman_iter_t *iter)
+{
+    if (iter->flags & ITER_NARROW)
+    {
+	if ((iter->flags & (ITER_IGNORE_RGB | ITER_IGNORE_ALPHA)) ==
+	    (ITER_IGNORE_RGB | ITER_IGNORE_ALPHA))
+	{
+	    iter->get_scanline = _pixman_iter_get_scanline_noop;
+	}
+	else
+	{
+	    iter->get_scanline = dest_get_scanline_narrow;
+	}
+	
+	iter->write_back = dest_write_back_narrow;
+    }
+    else
+    {
+	iter->get_scanline = dest_get_scanline_wide;
+	iter->write_back = dest_write_back_wide;
+    }
+}
+
+static uint32_t *
+create_bits (pixman_format_code_t format,
+             int                  width,
+             int                  height,
+             int *		  rowstride_bytes)
+{
+    int stride;
+    size_t buf_size;
+    int bpp;
+
+    /* what follows is a long-winded way, avoiding any possibility of integer
+     * overflows, of saying:
+     * stride = ((width * bpp + 0x1f) >> 5) * sizeof (uint32_t);
+     */
+
+    bpp = PIXMAN_FORMAT_BPP (format);
+    if (_pixman_multiply_overflows_int (width, bpp))
+	return NULL;
+
+    stride = width * bpp;
+    if (_pixman_addition_overflows_int (stride, 0x1f))
+	return NULL;
+
+    stride += 0x1f;
+    stride >>= 5;
+
+    stride *= sizeof (uint32_t);
+
+    if (_pixman_multiply_overflows_size (height, stride))
+	return NULL;
+
+    buf_size = height * stride;
+
+    if (rowstride_bytes)
+	*rowstride_bytes = stride;
+
+    return calloc (buf_size, 1);
+}
+
+PIXMAN_EXPORT pixman_image_t *
+pixman_image_create_bits (pixman_format_code_t format,
+                          int                  width,
+                          int                  height,
+                          uint32_t *           bits,
+                          int                  rowstride_bytes)
+{
+    pixman_image_t *image;
+    uint32_t *free_me = NULL;
+
+    /* must be a whole number of uint32_t's
+     */
+    return_val_if_fail (
+	bits == NULL || (rowstride_bytes % sizeof (uint32_t)) == 0, NULL);
+
+    return_val_if_fail (PIXMAN_FORMAT_BPP (format) >= PIXMAN_FORMAT_DEPTH (format), NULL);
+
+    if (!bits && width && height)
+    {
+	free_me = bits = create_bits (format, width, height, &rowstride_bytes);
+	if (!bits)
+	    return NULL;
+    }
+
+    image = _pixman_image_allocate ();
+
+    if (!image)
+    {
+	if (free_me)
+	    free (free_me);
+
+	return NULL;
+    }
+
+    image->type = BITS;
+    image->bits.format = format;
+    image->bits.width = width;
+    image->bits.height = height;
+    image->bits.bits = bits;
+    image->bits.free_me = free_me;
+    image->bits.read_func = NULL;
+    image->bits.write_func = NULL;
+
+    /* The rowstride is stored in number of uint32_t */
+    image->bits.rowstride = rowstride_bytes / (int) sizeof (uint32_t);
+
+    image->bits.indexed = NULL;
+
+    image->common.property_changed = bits_image_property_changed;
+
+    _pixman_image_reset_clip_region (image);
+
+    return image;
+}
diff --git a/pixman/pixman/pixman-fast-path.c b/pixman/pixman/pixman-fast-path.c
index 71d13da78..ad05493ca 100644
--- a/pixman/pixman/pixman-fast-path.c
+++ b/pixman/pixman/pixman-fast-path.c
@@ -30,7 +30,7 @@
 #include <stdlib.h>

 #include "pixman-private.h"

 #include "pixman-combine32.h"

-#include "pixman-fast-path.h"

+#include "pixman-inlines.h"

 

 static force_inline uint32_t

 fetch_24 (uint8_t *a)

diff --git a/pixman/pixman/pixman-fast-path.h b/pixman/pixman/pixman-inlines.h
index 64a3b3fdf..664d4a1a6 100644
--- a/pixman/pixman/pixman-fast-path.h
+++ b/pixman/pixman/pixman-inlines.h
@@ -81,6 +81,97 @@ repeat (pixman_repeat_t repeat, int *c, int size)
     return TRUE;

 }

 

+#if SIZEOF_LONG > 4

+

+static force_inline uint32_t

+bilinear_interpolation (uint32_t tl, uint32_t tr,

+			uint32_t bl, uint32_t br,

+			int distx, int disty)

+{

+    uint64_t distxy, distxiy, distixy, distixiy;

+    uint64_t tl64, tr64, bl64, br64;

+    uint64_t f, r;

+

+    distxy = distx * disty;

+    distxiy = distx * (256 - disty);

+    distixy = (256 - distx) * disty;

+    distixiy = (256 - distx) * (256 - disty);

+

+    /* Alpha and Blue */

+    tl64 = tl & 0xff0000ff;

+    tr64 = tr & 0xff0000ff;

+    bl64 = bl & 0xff0000ff;

+    br64 = br & 0xff0000ff;

+

+    f = tl64 * distixiy + tr64 * distxiy + bl64 * distixy + br64 * distxy;

+    r = f & 0x0000ff0000ff0000ull;

+

+    /* Red and Green */

+    tl64 = tl;

+    tl64 = ((tl64 << 16) & 0x000000ff00000000ull) | (tl64 & 0x0000ff00ull);

+

+    tr64 = tr;

+    tr64 = ((tr64 << 16) & 0x000000ff00000000ull) | (tr64 & 0x0000ff00ull);

+

+    bl64 = bl;

+    bl64 = ((bl64 << 16) & 0x000000ff00000000ull) | (bl64 & 0x0000ff00ull);

+

+    br64 = br;

+    br64 = ((br64 << 16) & 0x000000ff00000000ull) | (br64 & 0x0000ff00ull);

+

+    f = tl64 * distixiy + tr64 * distxiy + bl64 * distixy + br64 * distxy;

+    r |= ((f >> 16) & 0x000000ff00000000ull) | (f & 0xff000000ull);

+

+    return (uint32_t)(r >> 16);

+}

+

+#else

+

+static force_inline uint32_t

+bilinear_interpolation (uint32_t tl, uint32_t tr,

+			uint32_t bl, uint32_t br,

+			int distx, int disty)

+{

+    int distxy, distxiy, distixy, distixiy;

+    uint32_t f, r;

+

+    distxy = distx * disty;

+    distxiy = (distx << 8) - distxy;	/* distx * (256 - disty) */

+    distixy = (disty << 8) - distxy;	/* disty * (256 - distx) */

+    distixiy =

+	256 * 256 - (disty << 8) -

+	(distx << 8) + distxy;		/* (256 - distx) * (256 - disty) */

+

+    /* Blue */

+    r = (tl & 0x000000ff) * distixiy + (tr & 0x000000ff) * distxiy

+      + (bl & 0x000000ff) * distixy  + (br & 0x000000ff) * distxy;

+

+    /* Green */

+    f = (tl & 0x0000ff00) * distixiy + (tr & 0x0000ff00) * distxiy

+      + (bl & 0x0000ff00) * distixy  + (br & 0x0000ff00) * distxy;

+    r |= f & 0xff000000;

+

+    tl >>= 16;

+    tr >>= 16;

+    bl >>= 16;

+    br >>= 16;

+    r >>= 16;

+

+    /* Red */

+    f = (tl & 0x000000ff) * distixiy + (tr & 0x000000ff) * distxiy

+      + (bl & 0x000000ff) * distixy  + (br & 0x000000ff) * distxy;

+    r |= f & 0x00ff0000;

+

+    /* Alpha */

+    f = (tl & 0x0000ff00) * distixiy + (tr & 0x0000ff00) * distxiy

+      + (bl & 0x0000ff00) * distixy  + (br & 0x0000ff00) * distxy;

+    r |= f & 0xff000000;

+

+    return r;

+}

+

+#endif

+

 /*

  * For each scanline fetched from source image with PAD repeat:

  * - calculate how many pixels need to be padded on the left side

diff --git a/pixman/pixman/pixman-noop.c b/pixman/pixman/pixman-noop.c
index 4f8c3a18e..906a491f5 100644
--- a/pixman/pixman/pixman-noop.c
+++ b/pixman/pixman/pixman-noop.c
@@ -28,7 +28,7 @@
 #include <stdlib.h>
 #include "pixman-private.h"
 #include "pixman-combine32.h"
-#include "pixman-fast-path.h"
+#include "pixman-inlines.h"
 
 static void
 noop_composite (pixman_implementation_t *imp,
diff --git a/pixman/pixman/pixman-private.h b/pixman/pixman/pixman-private.h
index 6a3935e4d..a25897d77 100644
--- a/pixman/pixman/pixman-private.h
+++ b/pixman/pixman/pixman-private.h
@@ -691,10 +691,13 @@ void *
 pixman_malloc_abc (unsigned int a, unsigned int b, unsigned int c);
 
 pixman_bool_t
-pixman_multiply_overflows_int (unsigned int a, unsigned int b);
+_pixman_multiply_overflows_size (size_t a, size_t b);
 
 pixman_bool_t
-pixman_addition_overflows_int (unsigned int a, unsigned int b);
+_pixman_multiply_overflows_int (unsigned int a, unsigned int b);
+
+pixman_bool_t
+_pixman_addition_overflows_int (unsigned int a, unsigned int b);
 
 /* Compositing utilities */
 void
diff --git a/pixman/pixman/pixman-region.c b/pixman/pixman/pixman-region.c
index 142493b77..47beb5238 100644
--- a/pixman/pixman/pixman-region.c
+++ b/pixman/pixman/pixman-region.c
@@ -102,7 +102,11 @@
 
 static const box_type_t PREFIX (_empty_box_) = { 0, 0, 0, 0 };
 static const region_data_type_t PREFIX (_empty_data_) = { 0, 0 };
+#if defined (__llvm__) && !defined (__clang__)
+static const volatile region_data_type_t PREFIX (_broken_data_) = { 0, 0 };
+#else
 static const region_data_type_t PREFIX (_broken_data_) = { 0, 0 };
+#endif
 
 static box_type_t *pixman_region_empty_box =
     (box_type_t *)&PREFIX (_empty_box_);
@@ -2086,6 +2090,40 @@ PIXMAN_EXPORT PREFIX (_inverse) (region_type_t *new_reg,  /* Destination region
     return TRUE;
 }
 
+/* In time O(log n), locate the first box whose y2 is greater than y.
+ * Return @end if no such box exists.
+ */
+static box_type_t *
+find_box_for_y (box_type_t *begin, box_type_t *end, int y)
+{
+    box_type_t *mid;
+
+    if (end == begin)
+	return end;
+
+    if (end - begin == 1)
+    {
+	if (begin->y2 > y)
+	    return begin;
+	else
+	    return end;
+    }
+
+    mid = begin + (end - begin) / 2;
+    if (mid->y2 > y)
+    {
+	/* If no box is found in [begin, mid], the function
+	 * will return @mid, which is then known to be the
+	 * correct answer.
+	 */
+	return find_box_for_y (begin, mid, y);
+    }
+    else
+    {
+	return find_box_for_y (mid, end, y);
+    }
+}
+
 /*
  *   rect_in(region, rect)
  *   This routine takes a pointer to a region and a pointer to a box
@@ -2102,7 +2140,6 @@ PIXMAN_EXPORT PREFIX (_inverse) (region_type_t *new_reg,  /* Destination region
  *   partially in the region) or is outside the region (we reached a band
  *   that doesn't overlap the box at all and part_in is false)
  */
-
 pixman_region_overlap_t
 PIXMAN_EXPORT PREFIX (_contains_rectangle) (region_type_t *  region,
                                             box_type_t *     prect)
@@ -2139,12 +2176,15 @@ PIXMAN_EXPORT PREFIX (_contains_rectangle) (region_type_t *  region,
 
     /* can stop when both part_out and part_in are TRUE, or we reach prect->y2 */
     for (pbox = PIXREGION_BOXPTR (region), pbox_end = pbox + numRects;
-         pbox != pbox_end;
-         pbox++)
+	 pbox != pbox_end;
+	 pbox++)
     {
-
-        if (pbox->y2 <= y)
-	    continue;   /* getting up to speed or skipping remainder of band */
+	/* getting up to speed or skipping remainder of band */
+	if (pbox->y2 <= y)
+	{
+	    if ((pbox = find_box_for_y (pbox, pbox_end, y)) == pbox_end)
+		break;
+	}
 
         if (pbox->y1 > y)
         {
@@ -2342,13 +2382,13 @@ PREFIX (_contains_point) (region_type_t * region,
         return(TRUE);
     }
 
-    for (pbox = PIXREGION_BOXPTR (region), pbox_end = pbox + numRects;
-	 pbox != pbox_end;
-	 pbox++)
-    {
-        if (y >= pbox->y2)
-	    continue;           /* not there yet */
+    pbox = PIXREGION_BOXPTR (region);
+    pbox_end = pbox + numRects;
 
+    pbox = find_box_for_y (pbox, pbox_end, y);
+
+    for (;pbox != pbox_end; pbox++)
+    {
         if ((y < pbox->y1) || (x < pbox->x1))
 	    break;              /* missed it */
 
diff --git a/pixman/pixman/pixman-sse2.c b/pixman/pixman/pixman-sse2.c
index 3d51c2fda..6689c53a2 100644
--- a/pixman/pixman/pixman-sse2.c
+++ b/pixman/pixman/pixman-sse2.c
@@ -34,7 +34,7 @@
 #include <emmintrin.h> /* for SSE2 intrinsics */
 #include "pixman-private.h"
 #include "pixman-combine32.h"
-#include "pixman-fast-path.h"
+#include "pixman-inlines.h"
 
 static __m128i mask_0080;
 static __m128i mask_00ff;
diff --git a/pixman/pixman/pixman-utils.c b/pixman/pixman/pixman-utils.c
index cb4e62199..49e3488aa 100644
--- a/pixman/pixman/pixman-utils.c
+++ b/pixman/pixman/pixman-utils.c
@@ -31,15 +31,19 @@
 #include "pixman-private.h"
 
 pixman_bool_t
-pixman_multiply_overflows_int (unsigned int a,
-                               unsigned int b)
+_pixman_multiply_overflows_size (size_t a, size_t b)
+{
+    return a >= SIZE_MAX / b;
+}
+
+pixman_bool_t
+_pixman_multiply_overflows_int (unsigned int a, unsigned int b)
 {
     return a >= INT32_MAX / b;
 }
 
 pixman_bool_t
-pixman_addition_overflows_int (unsigned int a,
-                               unsigned int b)
+_pixman_addition_overflows_int (unsigned int a, unsigned int b)
 {
     return a > INT32_MAX - b;
 }
diff --git a/pixman/test/Makefile.am b/pixman/test/Makefile.am
index d785c2c2e..eca692236 100644
--- a/pixman/test/Makefile.am
+++ b/pixman/test/Makefile.am
@@ -15,6 +15,7 @@ TESTPROGRAMS =			\
 	scaling-crash-test	\

 	scaling-helpers-test	\

 	gradient-crash-test	\

+	region-contains-test	\

 	alphamap		\

 	stress-test		\

 	composite-traps-test	\

@@ -26,6 +27,7 @@ TESTPROGRAMS =			\
 pdf_op_test_SOURCES = pdf-op-test.c utils.c utils.h

 region_test_SOURCES = region-test.c utils.c utils.h

 blitters_test_SOURCES = blitters-test.c utils.c utils.h

+region_contains_test_SOURCES = region-contains-test.c utils.c utils.h

 composite_traps_test_SOURCES = composite-traps-test.c utils.c utils.h

 scaling_test_SOURCES = scaling-test.c utils.c utils.h

 affine_test_SOURCES = affine-test.c utils.c utils.h

diff --git a/pixman/test/Makefile.win32 b/pixman/test/Makefile.win32
index c71afe187..a62b6fc35 100644
--- a/pixman/test/Makefile.win32
+++ b/pixman/test/Makefile.win32
@@ -35,6 +35,7 @@ SOURCES =			\
 	scaling-test.c		\
 	affine-test.c		\
 	composite.c		\
+	lowlevel-blt-bench.c	\
 	utils.c
 
 TESTS =						\
@@ -56,6 +57,8 @@ TESTS =						\
 	$(CFG_VAR)/affine-test.exe		\
 	$(CFG_VAR)/composite.exe
 
+BENCHMARKS =					\
+	$(CFG_VAR)/lowlevel-blt-bench.exe
 
 OBJECTS     = $(patsubst %.c, $(CFG_VAR)/%.obj, $(SOURCES))
 
@@ -66,7 +69,7 @@ $(CFG_VAR)/%.obj: %.c
 $(CFG_VAR)/%.exe: $(CFG_VAR)/%.obj
 	$(LINK) /NOLOGO /OUT:$@ $< $(CFG_VAR)/utils.obj $(TEST_LDADD)
 
-all: $(OBJECTS) $(TESTS)
+all: $(OBJECTS) $(TESTS) $(BENCHMARKS)
 	@exit 0
 
 clean:
diff --git a/pixman/test/lowlevel-blt-bench.c b/pixman/test/lowlevel-blt-bench.c
index d58587d51..099e434f0 100644
--- a/pixman/test/lowlevel-blt-bench.c
+++ b/pixman/test/lowlevel-blt-bench.c
@@ -22,16 +22,13 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
-#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif
+#define PIXMAN_USE_INTERNAL_API
+#include <pixman.h>
 
-#include "pixman-private.h"
 #include "utils.h"
 
 #define SOLID_FLAG 1
diff --git a/pixman/test/region-contains-test.c b/pixman/test/region-contains-test.c
new file mode 100644
index 000000000..d761c4bdf
--- /dev/null
+++ b/pixman/test/region-contains-test.c
@@ -0,0 +1,169 @@
+#include <assert.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "utils.h"
+
+static void
+make_random_region (pixman_region32_t *region)
+{
+    int n_boxes;
+
+    pixman_region32_init (region);
+
+    n_boxes = lcg_rand_n (64);
+    while (n_boxes--)
+    {
+	int32_t x1, y1, x2, y2;
+
+	x1 = (int32_t)lcg_rand_u32();
+	y1 = (int32_t)lcg_rand_u32();
+	x2 = (int32_t)lcg_rand_u32();
+	y2 = (int32_t)lcg_rand_u32();
+
+	pixman_region32_union_rect (region, region, x1, y1, x2, y2);
+    }
+}
+
+static void
+print_box (pixman_box32_t *box)
+{
+    printf ("    %d %d %d %d\n", box->x1, box->y1, box->x2, box->y2);
+}
+
+static int32_t
+random_coord (pixman_region32_t *region, pixman_bool_t x)
+{
+    pixman_box32_t *b, *bb;
+    int n_boxes;
+    int begin, end;
+
+    if (lcg_rand_n (14))
+    {
+	bb = pixman_region32_rectangles (region, &n_boxes);
+	if (n_boxes == 0)
+	    goto use_extent;
+	b = bb + lcg_rand_n (n_boxes);
+    }
+    else
+    {
+    use_extent:
+	b = pixman_region32_extents (region);
+	n_boxes = 1;
+    }
+
+    if (x)
+    {
+	begin = b->x1;
+	end = b->x2;
+    }
+    else
+    {
+	begin = b->y1;
+	end = b->y2;
+    }
+
+    switch (lcg_rand_n (5))
+    {
+    case 0:
+	return begin - lcg_rand_u32();
+    case 1:
+	return end + lcg_rand_u32 ();
+    case 2:
+	return end;
+    case 3:
+	return begin;
+    default:
+	return (begin + end) / 2;
+    }
+    return 0;
+}
+
+static uint32_t
+compute_crc32_u32 (uint32_t crc32, uint32_t v)
+{
+    if (!is_little_endian())
+    {
+	v = ((v & 0xff000000) >> 24)	|
+	    ((v & 0x00ff0000) >> 8)	|
+	    ((v & 0x0000ff00) << 8)	|
+	    ((v & 0x000000ff) << 24);
+    }
+
+    return compute_crc32 (crc32, &v, sizeof (int32_t));
+}
+
+static uint32_t
+crc32_box32 (uint32_t crc32, pixman_box32_t *box)
+{
+    crc32 = compute_crc32_u32 (crc32, box->x1);
+    crc32 = compute_crc32_u32 (crc32, box->y1);
+    crc32 = compute_crc32_u32 (crc32, box->x2);
+    crc32 = compute_crc32_u32 (crc32, box->y2);
+
+    return crc32;
+}
+
+static uint32_t
+test_region_contains_rectangle (int i, int verbose)
+{
+    pixman_box32_t box;
+    pixman_box32_t rbox = { 0, 0, 0, 0 };
+    pixman_region32_t region;
+    uint32_t r, r1, r2, r3, r4, crc32;
+
+    lcg_srand (i);
+
+    make_random_region (&region);
+
+    box.x1 = random_coord (&region, TRUE);
+    box.x2 = box.x1 + lcg_rand_u32 ();
+    box.y1 = random_coord (&region, FALSE);
+    box.y2 = box.y1 + lcg_rand_u32 ();
+
+    if (verbose)
+    {
+	int n_rects;
+	pixman_box32_t *boxes;
+
+	boxes = pixman_region32_rectangles (&region, &n_rects);
+
+	printf ("region:\n");
+	while (n_rects--)
+	    print_box (boxes++);
+	printf ("box:\n");
+	print_box (&box);
+    }
+
+    crc32 = 0;
+
+    r1 = pixman_region32_contains_point (&region, box.x1, box.y1, &rbox);
+    crc32 = crc32_box32 (crc32, &rbox);
+    r2 = pixman_region32_contains_point (&region, box.x1, box.y2, &rbox);
+    crc32 = crc32_box32 (crc32, &rbox);
+    r3 = pixman_region32_contains_point (&region, box.x2, box.y1, &rbox);
+    crc32 = crc32_box32 (crc32, &rbox);
+    r4 = pixman_region32_contains_point (&region, box.x2, box.y2, &rbox);
+    crc32 = crc32_box32 (crc32, &rbox);
+
+    r = pixman_region32_contains_rectangle (&region, &box);
+    r = (i << 8) | (r << 4) | (r1 << 3) | (r2 << 2) | (r3 << 1) | (r4 << 0);
+
+    crc32 = compute_crc32_u32 (crc32, r);
+
+    if (verbose)
+	printf ("results: %d %d %d %d %d\n", (r & 0xf0) >> 4, r1, r2, r3, r4);
+
+    pixman_region32_fini (&region);
+
+    return crc32;
+}
+
+int
+main (int argc, const char *argv[])
+{
+    return fuzzer_test_main ("region_contains",
+			     1000000,
+			     0x86311506,
+			     test_region_contains_rectangle,
+			     argc, argv);
+}
diff --git a/pixman/test/scaling-helpers-test.c b/pixman/test/scaling-helpers-test.c
index c1861389b..a38cac544 100644
--- a/pixman/test/scaling-helpers-test.c
+++ b/pixman/test/scaling-helpers-test.c
@@ -4,7 +4,7 @@
 #include <stdio.h>
 #include <assert.h>
 #include "utils.h"
-#include "pixman-fast-path.h"
+#include "pixman-inlines.h"
 
 /* A trivial reference implementation for
  * 'bilinear_pad_repeat_get_scanline_bounds'
diff --git a/pixman/test/utils.c b/pixman/test/utils.c
index 06c5e5128..da494cf59 100644
--- a/pixman/test/utils.c
+++ b/pixman/test/utils.c
@@ -130,6 +130,14 @@ compute_crc32 (uint32_t    in_crc32,
     return (crc32 ^ 0xFFFFFFFF);

 }

 

+pixman_bool_t

+is_little_endian (void)

+{

+    volatile uint16_t endian_check_var = 0x1234;

+

+    return (*(volatile uint8_t *)&endian_check_var == 0x34);

+}

+

 /* perform endian conversion of pixel data

  */

 void

@@ -142,8 +150,7 @@ image_endian_swap (pixman_image_t *img)
     int i, j;

 

     /* swap bytes only on big endian systems */

-    volatile uint16_t endian_check_var = 0x1234;

-    if (*(volatile uint8_t *)&endian_check_var != 0x12)

+    if (is_little_endian())

 	return;

 

     if (bpp == 8)

diff --git a/pixman/test/utils.h b/pixman/test/utils.h
index 8f0e0c0e5..9b4d984f7 100644
--- a/pixman/test/utils.h
+++ b/pixman/test/utils.h
@@ -44,10 +44,14 @@ lcg_rand_N (int max)
 static inline uint32_t

 lcg_rand_u32 (void)

 {

-    uint32_t lo = lcg_rand();

-    uint32_t hi = lcg_rand();

-

-    return (hi << 16) | lo;

+    /* This uses the 10/11 most significant bits from the 3 lcg results

+     * (and mixes them with the low from the adjacent one).

+     */

+    uint32_t lo = lcg_rand() >> -(32 - 15 - 11 * 2);

+    uint32_t mid = lcg_rand() << (32 - 15 - 11 * 1);

+    uint32_t hi = lcg_rand() << (32 - 15 - 11 * 0);

+

+    return (hi ^ mid ^ lo);

 }

 

 /* CRC 32 computation

@@ -57,6 +61,10 @@ compute_crc32 (uint32_t    in_crc32,
 	       const void *buf,

 	       size_t      buf_len);

 

+/* Returns TRUE if running on a little endian system */

+pixman_bool_t

+is_little_endian (void);

+

 /* perform endian conversion of pixel data

  */

 void