vpx_convolve_copy_neon: fix unaligned loads w/w==4

Fixes a -fsanitize=undefined warning:

vpx_dsp/arm/vpx_convolve_copy_neon.c:29:26: runtime error: load of
misaligned address 0xffffa8242bea for type 'const uint32_t' (aka 'const
unsigned int'), which requires 4 byte alignment
0xffffa8242bea: note: pointer points here
 88 81  7d 7d 7d 7d 7d 81 81 7d  81 80 87 97 a8 ab a0 91 ...
              ^
    #0 0xb0447c in vpx_convolve_copy_neon
       vpx_dsp/arm/vpx_convolve_copy_neon.c:29:26
    #1 0x12285c8 in inter_predictor vp9/common/vp9_reconinter.h:29:3
    #2 0x1228430 in dec_build_inter_predictors
       vp9/decoder/vp9_decodeframe.c
    ...

Change-Id: Iaec4ac2a400b6e6db72d12e5a7acb316262b12a7

diff --git a/vpx_dsp/arm/vpx_convolve_copy_neon.c b/vpx_dsp/arm/vpx_convolve_copy_neon.c
index 361ec8a..bea7c98 100644 (file)
--- a/vpx_dsp/arm/vpx_convolve_copy_neon.c
+++ b/vpx_dsp/arm/vpx_convolve_copy_neon.c
@@ -9,6 +9,7 @@
  */
 
 #include <arm_neon.h>
+#include <string.h>
 
 #include "./vpx_dsp_rtcd.h"
 #include "vpx/vpx_integer.h"
@@ -26,10 +27,10 @@ void vpx_convolve_copy_neon(const uint8_t *src, ptrdiff_t src_stride,
 
   if (w < 8) {  // copy4
     do {
-      *(uint32_t *)dst = *(const uint32_t *)src;
+      memcpy(dst, src, 4);
       src += src_stride;
       dst += dst_stride;
-      *(uint32_t *)dst = *(const uint32_t *)src;
+      memcpy(dst, src, 4);
       src += src_stride;
       dst += dst_stride;
       h -= 2;