swscale/aarch64: Fix rgb24toyv12 only works with aligned width

Since c0666d8b, rgb24toyv12 is broken for width non-aligned to 16.
Add a simple wrapper to handle the non-aligned part.

Co-authored-by: johzzy <hellojinqiang@gmail.com>
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>

libswscale/aarch64/rgb2rgb.c

@@ -27,9 +27,30 @@
 #include "libswscale/swscale.h"
 #include "libswscale/swscale_internal.h"
 
+// Only handle width aligned to 16
 void ff_rgb24toyv12_neon(const uint8_t *src, uint8_t *ydst, uint8_t *udst,
                          uint8_t *vdst, int width, int height, int lumStride,
                          int chromStride, int srcStride, int32_t *rgb2yuv);
+
+static void rgb24toyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst,
+                        uint8_t *vdst, int width, int height, int lumStride,
+                        int chromStride, int srcStride, int32_t *rgb2yuv)
+{
+    int width_align = width & (~15);
+
+    if (width_align > 0)
+        ff_rgb24toyv12_neon(src, ydst, udst, vdst, width_align, height,
+                lumStride, chromStride, srcStride, rgb2yuv);
+    if (width_align < width) {
+        src += width_align * 3;
+        ydst += width_align;
+        udst += width_align / 2;
+        vdst += width_align / 2;
+        ff_rgb24toyv12_c(src, ydst, udst, vdst, width - width_align, height,
+                lumStride, chromStride, srcStride, rgb2yuv);
+    }
+}
+
 void ff_interleave_bytes_neon(const uint8_t *src1, const uint8_t *src2,
                               uint8_t *dest, int width, int height,
                               int src1Stride, int src2Stride, int dstStride);
@@ -42,7 +63,7 @@ av_cold void rgb2rgb_init_aarch64(void)
     int cpu_flags = av_get_cpu_flags();
 
     if (have_neon(cpu_flags)) {
-        ff_rgb24toyv12  = ff_rgb24toyv12_neon;
+        ff_rgb24toyv12  = rgb24toyv12;
         interleaveBytes = ff_interleave_bytes_neon;
         deinterleaveBytes = ff_deinterleave_bytes_neon;
     }

tests/checkasm/sw_rgb.c

@@ -129,7 +129,7 @@ static int cmp_off_by_n(const uint8_t *ref, const uint8_t *test, size_t n, int a
 
 static void check_rgb24toyv12(struct SwsContext *ctx)
 {
-    static const int input_sizes[] = {16, 128, 512, MAX_LINE_SIZE, -MAX_LINE_SIZE};
+    static const int input_sizes[] = {2, 16, 128, 540, MAX_LINE_SIZE, -MAX_LINE_SIZE};
 
     LOCAL_ALIGNED_32(uint8_t, src, [BUFSIZE * 3]);
     LOCAL_ALIGNED_32(uint8_t, buf_y_0, [BUFSIZE]);