[Mesa-dev] [PATCH] i965/tiled_memcpy: realign rgba8_copy_aligned_dst stack in 32-bit builds

[Scott D Phillips]

When building intel_tiled_memcpy for i686, the stack will only be
4-byte aligned. This isn't sufficient for SSE temporaries which
require 16-byte alignment.  Use the force_align_arg_pointer
function attribute in that case to ensure sufficient alignment.
---
 src/mesa/drivers/dri/i965/intel_tiled_memcpy.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c b/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
index 69306828d72..bd8bafbd2d7 100644
--- a/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
+++ b/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
@@ -42,6 +42,12 @@
 #include <emmintrin.h>
 #endif
 
+#if defined(__GNUC__) && defined(__i386__) && (defined(__SSSE3__) || defined(__SSE2__))
+#define REALIGN __attribute__((force_align_arg_pointer))
+#else
+#define REALIGN
+#endif
+
 #define FILE_DEBUG_FLAG DEBUG_TEXTURE
 
 #define ALIGN_DOWN(a, b) ROUND_DOWN_TO(a, b)
@@ -156,7 +162,7 @@ rgba8_copy_16_aligned_src(void *dst, const void *src)
 /**
  * Copy RGBA to BGRA - swap R and B, with the destination 16-byte aligned.
  */
-static inline void *
+static REALIGN inline void *
 rgba8_copy_aligned_dst(void *dst, const void *src, size_t bytes)
 {
    assert(bytes == 0 || !(((uintptr_t)dst) & 0xf));
-- 
2.14.3