Skip to contentSkip to conversation

Big-endian fixes

RFC PATCH Superseded Geert Uytterhoeven 3 participants 5 messages Mar 7, 2022 – Mar 8, 2022

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore
#3 lore raw

RFC PATCH 2/2 util: Fix 32 bpp patterns on big-endian

In reply to Geert Uytterhoeven

DRM formats are defined to be little-endian, unless the DRM_FORMAT_BIG_ENDIAN flag is set. Hence writes of multi-byte pixel values need to take endianness into account.

Introduce a cpu_to_le32() helper to convert 32-bit values from CPU-endian to little-endian, and use them in the various pattern fill functions for 32-bit formats.

---
Works now with Linux' drm_fb_xrgb8888_to_rgb332_line(), which uses le32_to_cpu() to read pixel values from memory.

---
 tests/util/pattern.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)
tests/util/pattern.c +21 -9
index 42d75d700700dc3d..48677ea6d25b2676 100644
@@ -61,6 +61,18 @@ struct color_yuv {
 	  .u = MAKE_YUV_601_U(r, g, b), \
 	  .v = MAKE_YUV_601_V(r, g, b) }
 
+#if defined(__BIG_ENDIAN__) || defined(__sparc__) || defined(__mc68000__) || defined(__MIPSEB__)
+static inline uint32_t cpu_to_le32(uint32_t x)
+{
+	return ((x & 0x000000ffU) << 24) |
+	       ((x & 0x0000ff00U) <<  8) |
+	       ((x & 0x00ff0000U) >>  8) |
+	       ((x & 0xff000000U) >> 24);
+}
+#else
+#define cpu_to_le32(x)	(x)
+#endif
+
 /* This function takes 8-bit color values */
 static inline uint32_t shiftcolor8(const struct util_color_component *comp,
 				  uint32_t value)
@@ -520,26 +532,26 @@ static void fill_smpte_rgb32(const struct util_rgb_info *rgb, void *mem,
 
 	for (y = 0; y < height * 6 / 9; ++y) {
 		for (x = 0; x < width; ++x)
-			((uint32_t *)mem)[x] = colors_top[x * 7 / width];
+			((uint32_t *)mem)[x] = cpu_to_le32(colors_top[x * 7 / width]);
 		mem += stride;
 	}
 
 	for (; y < height * 7 / 9; ++y) {
 		for (x = 0; x < width; ++x)
-			((uint32_t *)mem)[x] = colors_middle[x * 7 / width];
+			((uint32_t *)mem)[x] = cpu_to_le32(colors_middle[x * 7 / width]);
 		mem += stride;
 	}
 
 	for (; y < height; ++y) {
 		for (x = 0; x < width * 5 / 7; ++x)
 			((uint32_t *)mem)[x] =
-				colors_bottom[x * 4 / (width * 5 / 7)];
+				cpu_to_le32(colors_bottom[x * 4 / (width * 5 / 7)]);
 		for (; x < width * 6 / 7; ++x)
 			((uint32_t *)mem)[x] =
-				colors_bottom[(x - width * 5 / 7) * 3
-					      / (width / 7) + 4];
+				cpu_to_le32(colors_bottom[(x - width * 5 / 7) * 3
+							  / (width / 7) + 4]);
 		for (; x < width; ++x)
-			((uint32_t *)mem)[x] = colors_bottom[7];
+			((uint32_t *)mem)[x] = cpu_to_le32(colors_bottom[7]);
 		mem += stride;
 	}
 }
@@ -1017,7 +1029,7 @@ static void fill_tiles_rgb32(const struct util_format_info *info, void *mem,
 					  (rgb32 >> 8) & 0xff, rgb32 & 0xff,
 					  alpha);
 
-			((uint32_t *)mem)[x] = color;
+			((uint32_t *)mem)[x] = cpu_to_le32(color);
 		}
 		mem += stride;
 	}
@@ -1164,7 +1176,7 @@ static void fill_gradient_rgb32(const struct util_rgb_info *rgb,
 
 		for (j = 0; j < width / 2; j++) {
 			uint32_t value = MAKE_RGBA10(rgb, j & 0x3ff, j & 0x3ff, j & 0x3ff, 0);
-			row[2*j] = row[2*j+1] = value;
+			row[2*j] = row[2*j+1] = cpu_to_le32(value);
 		}
 		mem += stride;
 	}
@@ -1174,7 +1186,7 @@ static void fill_gradient_rgb32(const struct util_rgb_info *rgb,
 
 		for (j = 0; j < width / 2; j++) {
 			uint32_t value = MAKE_RGBA10(rgb, j & 0x3fc, j & 0x3fc, j & 0x3fc, 0);
-			row[2*j] = row[2*j+1] = value;
+			row[2*j] = row[2*j+1] = cpu_to_le32(value);
 		}
 		mem += stride;
 	}
Signature · 1 line
2.25.1
#1 lore raw

RFC PATCH 1/2 intel: Improve checks for big-endian

In reply to Geert Uytterhoeven

- sparc64-linux-gnu-gcc does not define __BIG_ENDIAN__ or SPARC, but does define __sparc__, hence replace the check for SPARC by a check for __sparc__,
- powerpc{,64,64}-linux-gnu-gcc does not define __ppc__ or __ppc64__, but does define __BIG_ENDIAN__. powerpc64le-linux-gnu-gcc does not define __ppc__ or __ppc64__, but does define __LITTLE_ENDIAN__.
Hence remove the checks for __ppc__ and __ppc64__.
- mips{,64}-linux-gnu{,abi64}-gcc does not define __BIG_ENDIAN__, but does define __MIPSEB__, so add a check for the latter,
- m68k-linux-gnu-gcc does not define __BIG_ENDIAN__, but does define

    __mc68000__, so add a check for the latter,
  - hppa{,64}-linux-gnu-gcc defines __BIG_ENDIAN__, and thus should work
    out-of-the-box.

---
Untested due to lack of hardware.

---
 intel/uthash.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
intel/uthash.h +1 -1
index 45d1f9fc12a1d6f9..0f5480be6e8ca033 100644
@@ -648,7 +648,7 @@ do {
 #define MUR_PLUS2_ALIGNED(p) (((unsigned long)p & 3UL) == 2UL)
 #define MUR_PLUS3_ALIGNED(p) (((unsigned long)p & 3UL) == 3UL)
 #define WP(p) ((uint32_t*)((unsigned long)(p) & ~3UL))
-#if (defined(__BIG_ENDIAN__) || defined(SPARC) || defined(__ppc__) || defined(__ppc64__))
+#if (defined(__BIG_ENDIAN__) || defined(__sparc__) || defined(__mc68000__) || defined(__MIPSEB__))
 #define MUR_THREE_ONE(p) ((((*WP(p))&0x00ffffff) << 8) | (((*(WP(p)+1))&0xff000000) >> 24))
 #define MUR_TWO_TWO(p)   ((((*WP(p))&0x0000ffff) <<16) | (((*(WP(p)+1))&0xffff0000) >> 16))
 #define MUR_ONE_THREE(p) ((((*WP(p))&0x000000ff) <<24) | (((*(WP(p)+1))&0xffffff00) >>  8))
Signature · 1 line
2.25.1
#0 lore raw

cover Big-endian fixes

Hi all,

When starting to use modetest, I was a bit surprised to discover the default XR24 format wasn't displayed correctly on my work-in-progress Atari DRM driver, which runs on a big-endian system.

This RFC patch series fixes some endianness issues in libdrm. It has been tested on ARAnyM using a work-in-progress Atari DRM driver, which can now display the XR24 format by converting XRGB8888 to RGB332.

Overview:
- Patch 1 improves the existing endianness checks in a header file for the Intel driver,
- Patch 2 fixes the display of 32 bpp patterns on big-endian systems.

Futher endian fixes may be needed. Note that I also have a variant of patch 2 for 16 bpp, which works with the Atari DRM driver converting RGB565 to RGB332. But I want to get real 16 bpp working in the Atari DRM driver first, as that uses a 16-bit big endian format. And what about 24 bpp?

Please refer to [1] for more information.

Thanks for your comments!

[1] "[PATCH v2 00/10] drm: Add support for low-color frame buffer formats"

    https://lore.kernel.org/r/[email protected]

Geert Uytterhoeven (2):
intel: Improve checks for big-endian
util: Fix 32 bpp patterns on big-endian

 intel/uthash.h       |  2 +-
 tests/util/pattern.c | 30 +++++++++++++++++++++---------
 2 files changed, 22 insertions(+), 10 deletions(-)
Signature · 12 lines
2.25.1

Gr{oetje,eeting}s,

						Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
							    -- Linus Torvalds
Acked-by on v1 2/2
#4 lore raw

Re: [PATCH RFC libdrm 2/2] util: Fix 32 bpp patterns on big-endian

In reply to Geert Uytterhoeven
Quoted 7 lines · On Mon, 7 Mar 2022 21:53:42 +0100 Geert Uytterhoeven <[email protected]>…

DRM formats are defined to be little-endian, unless the DRM_FORMAT_BIG_ENDIAN flag is set. Hence writes of multi-byte pixel values need to take endianness into account.

Introduce a cpu_to_le32() helper to convert 32-bit values from CPU-endian to little-endian, and use them in the various pattern fill functions for 32-bit formats.

Hi Geert,

FWIW, this explanation matches my understanding, so it sounds correct to me. That's all I can say. I guess that means

?

Thanks,
pq

Quoted 29 lines

---
Works now with Linux' drm_fb_xrgb8888_to_rgb332_line(), which uses le32_to_cpu() to read pixel values from memory.

---
 tests/util/pattern.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)
tests/util/pattern.c +11 -0
index 42d75d700700dc3d..48677ea6d25b2676 100644
@@ -61,6 +61,18 @@ struct color_yuv {
 	  .u = MAKE_YUV_601_U(r, g, b), \
 	  .v = MAKE_YUV_601_V(r, g, b) }
 
+#if defined(__BIG_ENDIAN__) || defined(__sparc__) || defined(__mc68000__) || defined(__MIPSEB__)
+static inline uint32_t cpu_to_le32(uint32_t x)
+{
+	return ((x & 0x000000ffU) << 24) |
+	       ((x & 0x0000ff00U) <<  8) |
+	       ((x & 0x00ff0000U) >>  8) |
+	       ((x & 0xff000000U) >> 24);
+}
+#else
+#define cpu_to_le32(x)	(x)
+#endif
#2 lore raw

Re: [PATCH RFC libdrm 1/2] intel: Improve checks for big-endian

In reply to Geert Uytterhoeven
Quoted 11 lines · Geert Uytterhoeven

- sparc64-linux-gnu-gcc does not define __BIG_ENDIAN__ or SPARC, but does define __sparc__, hence replace the check for SPARC by a check for __sparc__,
- powerpc{,64,64}-linux-gnu-gcc does not define __ppc__ or __ppc64__, but does define __BIG_ENDIAN__. powerpc64le-linux-gnu-gcc does not define __ppc__ or __ppc64__, but does define __LITTLE_ENDIAN__.
Hence remove the checks for __ppc__ and __ppc64__.
- mips{,64}-linux-gnu{,abi64}-gcc does not define __BIG_ENDIAN__, but does define __MIPSEB__, so add a check for the latter,
- m68k-linux-gnu-gcc does not define __BIG_ENDIAN__, but does define

Quoted 3 lines
     __mc68000__, so add a check for the latter,
   - hppa{,64}-linux-gnu-gcc defines __BIG_ENDIAN__, and thus should work
     out-of-the-box.

FWIW there's also __ARM_BIG_ENDIAN for arm-* and aarch64-* targets in BE mode, if you want to flesh out the list even more. In principle there's also "__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__" which should supposedly be consistent across platforms, but I don't know if that's even more of a specific GCC-ism.

Robin.

Quoted 20 lines

---
Untested due to lack of hardware.

---
  intel/uthash.h | 2 +-
  1 file changed, 1 insertion(+), 1 deletion(-)
intel/uthash.h +1 -1
index 45d1f9fc12a1d6f9..0f5480be6e8ca033 100644
@@ -648,7 +648,7 @@ do {
  #define MUR_PLUS2_ALIGNED(p) (((unsigned long)p & 3UL) == 2UL)
  #define MUR_PLUS3_ALIGNED(p) (((unsigned long)p & 3UL) == 3UL)
  #define WP(p) ((uint32_t*)((unsigned long)(p) & ~3UL))
-#if (defined(__BIG_ENDIAN__) || defined(SPARC) || defined(__ppc__) || defined(__ppc64__))
+#if (defined(__BIG_ENDIAN__) || defined(__sparc__) || defined(__mc68000__) || defined(__MIPSEB__))
  #define MUR_THREE_ONE(p) ((((*WP(p))&0x00ffffff) << 8) | (((*(WP(p)+1))&0xff000000) >> 24))
  #define MUR_TWO_TWO(p)   ((((*WP(p))&0x0000ffff) <<16) | (((*(WP(p)+1))&0xffff0000) >> 16))
  #define MUR_ONE_THREE(p) ((((*WP(p))&0x000000ff) <<24) | (((*(WP(p)+1))&0xffffff00) >>  8))