util: fix pwetty on big-endian

Cairo always uses native byte order for rendering.

Hence if the byte order of the frame buffer differs from the byte order
of the CPU, the frame buffer contents need to be byteswapped twice: once
before rendering, to convert to native byte order, and a second time
after rendering, to restore the frame buffer format's byte order.

Note that byte swapping is not done for ARGB32 formats, as for these
formats, byte order only affects the order of the red, green, and blue
channels, which we do not care about here.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
v5:
  - Add Reviewed-by,

v4:
  - No changes,

v3:
  - Wrap byteswap_buffer{16,32}() implementation inside #if HAVE_CAIRO
    to avoid defined-but-not-used compiler warnings,

v2:
  - RGB30 is untested.

tests/util/pattern.c

@@ -79,10 +79,12 @@ static inline uint32_t swap32(uint32_t x)
 #define cpu_to_be16(x)			(x)
 #define cpu_to_le16(x)			swap16(x)
 #define cpu_to_le32(x)			swap32(x)
+#define fb_foreign_endian(format)	(!((format) & DRM_FORMAT_BIG_ENDIAN))
 #else
 #define cpu_to_be16(x)			swap16(x)
 #define cpu_to_le16(x)			(x)
 #define cpu_to_le32(x)			(x)
+#define fb_foreign_endian(format)	((format) & DRM_FORMAT_BIG_ENDIAN)
 #endif
 
 #define cpu_to_fb16(x)	(fb_be ? cpu_to_be16(x) : cpu_to_le16(x))
@@ -1290,6 +1292,32 @@ static void fill_smpte(const struct util_format_info *info, void *planes[3],
 	}
 }
 
+#if HAVE_CAIRO
+static void byteswap_buffer16(void *mem, unsigned int width, unsigned int height,
+			      unsigned int stride)
+{
+	unsigned int x, y;
+
+	for (y = 0; y < height; ++y) {
+		for (x = 0; x < width; ++x)
+			((uint16_t *)mem)[x] = swap16(((uint16_t *)mem)[x]);
+		mem += stride;
+	}
+}
+
+static void byteswap_buffer32(void *mem, unsigned int width, unsigned int height,
+			      unsigned int stride)
+{
+	unsigned int x, y;
+
+	for (y = 0; y < height; ++y) {
+		for (x = 0; x < width; ++x)
+			((uint32_t *)mem)[x] = swap32(((uint32_t *)mem)[x]);
+		mem += stride;
+	}
+}
+#endif
+
 static void make_pwetty(void *data, unsigned int width, unsigned int height,
 			unsigned int stride, uint32_t format)
 {
@@ -1297,6 +1325,8 @@ static void make_pwetty(void *data, unsigned int width, unsigned int height,
 	cairo_surface_t *surface;
 	cairo_t *cr;
 	cairo_format_t cairo_format;
+	bool swap16 = false;
+	bool swap32 = false;
 
 	/* we can ignore the order of R,G,B channels */
 	switch (format) {
@@ -1309,6 +1339,7 @@ static void make_pwetty(void *data, unsigned int width, unsigned int height,
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_BGR565:
 		cairo_format = CAIRO_FORMAT_RGB16_565;
+		swap16 = fb_foreign_endian(format);
 		break;
 #if CAIRO_VERSION_MAJOR > 1 || (CAIRO_VERSION_MAJOR == 1 && CAIRO_VERSION_MINOR >= 12)
 	case DRM_FORMAT_ARGB2101010:
@@ -1316,12 +1347,19 @@ static void make_pwetty(void *data, unsigned int width, unsigned int height,
 	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_XBGR2101010:
 		cairo_format = CAIRO_FORMAT_RGB30;
+		swap32 = fb_foreign_endian(format);
 		break;
 #endif
 	default:
 		return;
 	}
 
+	/* Cairo uses native byte order, so we may have to byteswap before... */
+	if (swap16)
+		byteswap_buffer16(data, width, height, stride);
+	if (swap32)
+		byteswap_buffer32(data, width, height, stride);
+
 	surface = cairo_image_surface_create_for_data(data,
 						      cairo_format,
 						      width, height,
@@ -1357,6 +1395,12 @@ static void make_pwetty(void *data, unsigned int width, unsigned int height,
 		}
 
 	cairo_destroy(cr);
+
+	/* ... and after */
+	if (swap16)
+		byteswap_buffer16(data, width, height, stride);
+	if (swap32)
+		byteswap_buffer32(data, width, height, stride);
 #endif
 }