@@ -222,7 +222,7 @@ extern "C" {
#define DRM_FORMAT_ABGR16161616 fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */
/*
- * Floating point 64bpp RGB
+ * Half-Floating point - 16b/component
* IEEE 754-2008 binary16 half-precision float
* [15:0] sign:exponent:mantissa 1:5:10
*/
@@ -232,6 +232,20 @@ extern "C" {
#define DRM_FORMAT_ARGB16161616F fourcc_code('A', 'R', '4', 'H') /* [63:0] A:R:G:B 16:16:16:16 little endian */
#define DRM_FORMAT_ABGR16161616F fourcc_code('A', 'B', '4', 'H') /* [63:0] A:B:G:R 16:16:16:16 little endian */
+#define DRM_FORMAT_R16F fourcc_code('R', ' ', ' ', 'H') /* [15:0] R 16 little endian */
+#define DRM_FORMAT_GR1616F fourcc_code('G', 'R', ' ', 'H') /* [31:0] G:R 16:16 little endian */
+#define DRM_FORMAT_BGR161616F fourcc_code('B', 'G', 'R', 'H') /* [47:0] B:G:R 16:16:16 little endian */
+
+/*
+ * Floating point - 32b/component
+ * IEEE 754-2008 binary32 float
+ * [31:0] sign:exponent:mantissa 1:8:23
+ */
+#define DRM_FORMAT_R32F fourcc_code('R', ' ', ' ', 'F') /* [31:0] R 32 little endian */
+#define DRM_FORMAT_GR3232F fourcc_code('G', 'R', ' ', 'F') /* [63:0] R:G 32:32 little endian */
+#define DRM_FORMAT_BGR323232F fourcc_code('B', 'G', 'R', 'F') /* [95:0] R:G:B 32:32:32 little endian */
+#define DRM_FORMAT_ABGR32323232F fourcc_code('A', 'B', '8', 'F') /* [127:0] R:G:B:A 32:32:32:32 little endian */
+
/*
* RGBA format with 10-bit components packed in 64-bit per pixel, with 6 bits
* of unused padding per component:
@@ -381,6 +395,42 @@ extern "C" {
*/
#define DRM_FORMAT_Q401 fourcc_code('Q', '4', '0', '1')
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^6=64. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [6:10] little endian
+ * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian
+ * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian
+ */
+#define DRM_FORMAT_S010 fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S210 fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S410 fourcc_code('S', '4', '1', '0') /* non-subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^4=16. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [4:12] little endian
+ * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian
+ * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian
+ */
+#define DRM_FORMAT_S012 fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S212 fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S412 fourcc_code('S', '4', '1', '2') /* non-subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+
+/*
+ * 3 plane YCbCr
+ * index 0 = Y plane, [15:0] Y little endian
+ * index 1 = Cr plane, [15:0] Cr little endian
+ * index 2 = Cb plane, [15:0] Cb little endian
+ */
+#define DRM_FORMAT_S016 fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S216 fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S416 fourcc_code('S', '4', '1', '6') /* non-subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+
/*
* 3 plane YCbCr
* index 0: Y plane, [7:0] Y
@@ -489,6 +539,8 @@ extern "C" {
#define DRM_FORMAT_MOD_VENDOR_ARM 0x08
#define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09
#define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a
+#define DRM_FORMAT_MOD_VENDOR_MTK 0x0b
+#define DRM_FORMAT_MOD_VENDOR_APPLE 0x0c
#define DRM_FORMAT_MOD_VENDOR_MIPI 0x0b
#define DRM_FORMAT_MOD_VENDOR_RPI 0x0c
@@ -772,6 +824,31 @@ extern "C" {
*/
#define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS_CC fourcc_mod_code(INTEL, 15)
+/*
+ * Intel Color Control Surfaces (CCS) for graphics ver. 20 unified compression
+ * on integrated graphics
+ *
+ * The main surface is Tile 4 and at plane index 0. For semi-planar formats
+ * like NV12, the Y and UV planes are Tile 4 and are located at plane indices
+ * 0 and 1, respectively. The CCS for all planes are stored outside of the
+ * GEM object in a reserved memory area dedicated for the storage of the
+ * CCS data for all compressible GEM objects.
+ */
+#define I915_FORMAT_MOD_4_TILED_LNL_CCS fourcc_mod_code(INTEL, 16)
+
+/*
+ * Intel Color Control Surfaces (CCS) for graphics ver. 20 unified compression
+ * on discrete graphics
+ *
+ * The main surface is Tile 4 and at plane index 0. For semi-planar formats
+ * like NV12, the Y and UV planes are Tile 4 and are located at plane indices
+ * 0 and 1, respectively. The CCS for all planes are stored outside of the
+ * GEM object in a reserved memory area dedicated for the storage of the
+ * CCS data for all compressible GEM objects. The GEM object must be stored in
+ * contiguous memory with a size aligned to 64KB
+ */
+#define I915_FORMAT_MOD_4_TILED_BMG_CCS fourcc_mod_code(INTEL, 17)
+
/*
* IPU3 Bayer packing layout
*
@@ -780,7 +857,7 @@ extern "C" {
* the 6 most significant bits in the last byte unused. The format is little
* endian.
*/
-#define IPU3_FORMAT_MOD_PACKED fourcc_mod_code(INTEL, 13)
+#define IPU3_FORMAT_MOD_PACKED fourcc_mod_code(INTEL, 18)
/*
* Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
@@ -978,14 +1055,20 @@ extern "C" {
* 2 = Gob Height 8, Turing+ Page Kind mapping
* 3 = Reserved for future use.
*
- * 22:22 s Sector layout. On Tegra GPUs prior to Xavier, there is a further
- * bit remapping step that occurs at an even lower level than the
- * page kind and block linear swizzles. This causes the layout of
- * surfaces mapped in those SOC's GPUs to be incompatible with the
- * equivalent mapping on other GPUs in the same system.
- *
- * 0 = Tegra K1 - Tegra Parker/TX2 Layout.
- * 1 = Desktop GPU and Tegra Xavier+ Layout
+ * 22:22 s Sector layout. There is a further bit remapping step that occurs
+ * 26:27 at an even lower level than the page kind and block linear
+ * swizzles. This causes the bit arrangement of surfaces in memory
+ * to differ subtly, and prevents direct sharing of surfaces between
+ * GPUs with different layouts.
+ *
+ * 0 = Tegra K1 - Tegra Parker/TX2 Layout
+ * 1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout
+ * 2 = GB20x(Blackwell 2)+ 8 bpp surface layout
+ * 3 = GB20x(Blackwell 2)+ 16 bpp surface layout
+ * 4 = Reserved for future use.
+ * 5 = Reserved for future use.
+ * 6 = Reserved for future use.
+ * 7 = Reserved for future use.
*
* 25:23 c Lossless Framebuffer Compression type.
*
@@ -1000,7 +1083,7 @@ extern "C" {
* 6 = Reserved for future use
* 7 = Reserved for future use
*
- * 55:25 - Reserved for future use. Must be zero.
+ * 55:28 - Reserved for future use. Must be zero.
*/
#define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \
fourcc_mod_code(NVIDIA, (0x10 | \
@@ -1008,6 +1091,7 @@ extern "C" {
(((k) & 0xff) << 12) | \
(((g) & 0x3) << 20) | \
(((s) & 0x1) << 22) | \
+ (((s) & 0x6) << 25) | \
(((c) & 0x7) << 23)))
/* To grandfather in prior block linear format modifiers to the above layout,
@@ -1508,6 +1592,90 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
*/
#define AMLOGIC_FBC_OPTION_MEM_SAVING (1ULL << 0)
+/* MediaTek modifiers
+ * Bits Parameter Notes
+ * ----- ------------------------ ---------------------------------------------
+ * 7: 0 TILE LAYOUT Values are MTK_FMT_MOD_TILE_*
+ * 15: 8 COMPRESSION Values are MTK_FMT_MOD_COMPRESS_*
+ * 23:16 10 BIT LAYOUT Values are MTK_FMT_MOD_10BIT_LAYOUT_*
+ *
+ */
+
+#define DRM_FORMAT_MOD_MTK(__flags) fourcc_mod_code(MTK, __flags)
+
+/*
+ * MediaTek Tiled Modifier
+ * The lowest 8 bits of the modifier is used to specify the tiling
+ * layout. Only the 16L_32S tiling is used for now, but we define an
+ * "untiled" version and leave room for future expansion.
+ */
+#define MTK_FMT_MOD_TILE_MASK 0xf
+#define MTK_FMT_MOD_TILE_NONE 0x0
+#define MTK_FMT_MOD_TILE_16L32S 0x1
+
+/*
+ * Bits 8-15 specify compression options
+ */
+#define MTK_FMT_MOD_COMPRESS_MASK (0xf << 8)
+#define MTK_FMT_MOD_COMPRESS_NONE (0x0 << 8)
+#define MTK_FMT_MOD_COMPRESS_V1 (0x1 << 8)
+
+/*
+ * Bits 16-23 specify how the bits of 10 bit formats are
+ * stored out in memory
+ */
+#define MTK_FMT_MOD_10BIT_LAYOUT_MASK (0xf << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_PACKED (0x0 << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_LSBTILED (0x1 << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_LSBRASTER (0x2 << 16)
+
+/* alias for the most common tiling format */
+#define DRM_FORMAT_MOD_MTK_16L_32S_TILE DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S)
+
+/*
+ * Apple GPU-tiled layouts.
+ *
+ * Apple GPUs support nonlinear tilings with optional lossless compression.
+ *
+ * GPU-tiled images are divided into 16KiB tiles:
+ *
+ * Bytes per pixel Tile size
+ * --------------- ---------
+ * 1 128x128
+ * 2 128x64
+ * 4 64x64
+ * 8 64x32
+ * 16 32x32
+ *
+ * Tiles are raster-order. Pixels within a tile are interleaved (Morton order).
+ *
+ * Compressed images pad the body to 128-bytes and are immediately followed by a
+ * metadata section. The metadata section rounds the image dimensions to
+ * powers-of-two and contains 8 bytes for each 16x16 compression subtile.
+ * Subtiles are interleaved (Morton order).
+ *
+ * All images are 128-byte aligned.
+ *
+ * These layouts fundamentally do not have meaningful strides. No matter how we
+ * specify strides for these layouts, userspace unaware of Apple image layouts
+ * will be unable to use correctly the specified stride for any purpose.
+ * Userspace aware of the image layouts do not use strides. The most "correct"
+ * convention would be setting the image stride to 0. Unfortunately, some
+ * software assumes the stride is at least (width * bytes per pixel). We
+ * therefore require that stride equals (width * bytes per pixel). Since the
+ * stride is arbitrary here, we pick the simplest convention.
+ *
+ * Although containing two sections, compressed image layouts are treated in
+ * software as a single plane. This is modelled after AFBC, a similar
+ * scheme. Attempting to separate the sections to be "explicit" in DRM would
+ * only generate more confusion, as software does not treat the image this way.
+ *
+ * For detailed information on the hardware image layouts, see
+ * https://docs.mesa3d.org/drivers/asahi.html#image-layouts
+ */
+#define DRM_FORMAT_MOD_APPLE_GPU_TILED fourcc_mod_code(APPLE, 1)
+#define DRM_FORMAT_MOD_APPLE_GPU_TILED_COMPRESSED fourcc_mod_code(APPLE, 2)
+
/*
* AMD modifiers
*
@@ -1571,6 +1739,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
* 64K_D_2D on GFX12 is identical to 64K_D on GFX11.
*/
#define AMD_FMT_MOD_TILE_GFX9_64K_D 10
+#define AMD_FMT_MOD_TILE_GFX9_4K_D_X 22
#define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25
#define AMD_FMT_MOD_TILE_GFX9_64K_D_X 26
#define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27