diff options
Diffstat (limited to 'include/uapi/drm/drm_fourcc.h')
| -rw-r--r-- | include/uapi/drm/drm_fourcc.h | 877 |
1 files changed, 858 insertions, 19 deletions
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 490143500a50..e527b24bd824 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -54,16 +54,52 @@ extern "C" { * Format modifiers may change any property of the buffer, including the number * of planes and/or the required allocation size. Format modifiers are * vendor-namespaced, and as such the relationship between a fourcc code and a - * modifier is specific to the modifer being used. For example, some modifiers + * modifier is specific to the modifier being used. For example, some modifiers * may preserve meaning - such as number of planes - from the fourcc code, * whereas others may not. * + * Modifiers must uniquely encode buffer layout. In other words, a buffer must + * match only a single modifier. A modifier must not be a subset of layouts of + * another modifier. For instance, it's incorrect to encode pitch alignment in + * a modifier: a buffer may match a 64-pixel aligned modifier and a 32-pixel + * aligned modifier. That said, modifiers can have implicit minimal + * requirements. + * + * For modifiers where the combination of fourcc code and modifier can alias, + * a canonical pair needs to be defined and used by all drivers. Preferred + * combinations are also encouraged where all combinations might lead to + * confusion and unnecessarily reduced interoperability. An example for the + * latter is AFBC, where the ABGR layouts are preferred over ARGB layouts. + * + * There are two kinds of modifier users: + * + * - Kernel and user-space drivers: for drivers it's important that modifiers + * don't alias, otherwise two drivers might support the same format but use + * different aliases, preventing them from sharing buffers in an efficient + * format. + * - Higher-level programs interfacing with KMS/GBM/EGL/Vulkan/etc: these users + * see modifiers as opaque tokens they can check for equality and intersect. + * These users mustn't need to know to reason about the modifier value + * (i.e. they are not expected to extract information out of the modifier). + * * Vendors should document their modifier usage in as much detail as * possible, to ensure maximum compatibility across devices, drivers and * applications. * * The authoritative list of format modifier codes is found in * `include/uapi/drm/drm_fourcc.h` + * + * Open Source User Waiver + * ----------------------- + * + * Because this is the authoritative source for pixel formats and modifiers + * referenced by GL, Vulkan extensions and other standards and hence used both + * by open source and closed source driver stacks, the usual requirement for an + * upstream in-kernel or open source userspace user does not apply. + * + * To ensure, as much as feasible, compatibility across stacks and avoid + * confusion with incompatible enumerations stakeholders for all relevant driver + * stacks should approve additions. */ #define fourcc_code(a, b, c, d) ((__u32)(a) | ((__u32)(b) << 8) | \ @@ -75,12 +111,42 @@ extern "C" { #define DRM_FORMAT_INVALID 0 /* color index */ +#define DRM_FORMAT_C1 fourcc_code('C', '1', ' ', ' ') /* [7:0] C0:C1:C2:C3:C4:C5:C6:C7 1:1:1:1:1:1:1:1 eight pixels/byte */ +#define DRM_FORMAT_C2 fourcc_code('C', '2', ' ', ' ') /* [7:0] C0:C1:C2:C3 2:2:2:2 four pixels/byte */ +#define DRM_FORMAT_C4 fourcc_code('C', '4', ' ', ' ') /* [7:0] C0:C1 4:4 two pixels/byte */ #define DRM_FORMAT_C8 fourcc_code('C', '8', ' ', ' ') /* [7:0] C */ -/* 8 bpp Red */ +/* 1 bpp Darkness (inverse relationship between channel value and brightness) */ +#define DRM_FORMAT_D1 fourcc_code('D', '1', ' ', ' ') /* [7:0] D0:D1:D2:D3:D4:D5:D6:D7 1:1:1:1:1:1:1:1 eight pixels/byte */ + +/* 2 bpp Darkness (inverse relationship between channel value and brightness) */ +#define DRM_FORMAT_D2 fourcc_code('D', '2', ' ', ' ') /* [7:0] D0:D1:D2:D3 2:2:2:2 four pixels/byte */ + +/* 4 bpp Darkness (inverse relationship between channel value and brightness) */ +#define DRM_FORMAT_D4 fourcc_code('D', '4', ' ', ' ') /* [7:0] D0:D1 4:4 two pixels/byte */ + +/* 8 bpp Darkness (inverse relationship between channel value and brightness) */ +#define DRM_FORMAT_D8 fourcc_code('D', '8', ' ', ' ') /* [7:0] D */ + +/* 1 bpp Red (direct relationship between channel value and brightness) */ +#define DRM_FORMAT_R1 fourcc_code('R', '1', ' ', ' ') /* [7:0] R0:R1:R2:R3:R4:R5:R6:R7 1:1:1:1:1:1:1:1 eight pixels/byte */ + +/* 2 bpp Red (direct relationship between channel value and brightness) */ +#define DRM_FORMAT_R2 fourcc_code('R', '2', ' ', ' ') /* [7:0] R0:R1:R2:R3 2:2:2:2 four pixels/byte */ + +/* 4 bpp Red (direct relationship between channel value and brightness) */ +#define DRM_FORMAT_R4 fourcc_code('R', '4', ' ', ' ') /* [7:0] R0:R1 4:4 two pixels/byte */ + +/* 8 bpp Red (direct relationship between channel value and brightness) */ #define DRM_FORMAT_R8 fourcc_code('R', '8', ' ', ' ') /* [7:0] R */ -/* 16 bpp Red */ +/* 10 bpp Red (direct relationship between channel value and brightness) */ +#define DRM_FORMAT_R10 fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */ + +/* 12 bpp Red (direct relationship between channel value and brightness) */ +#define DRM_FORMAT_R12 fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */ + +/* 16 bpp Red (direct relationship between channel value and brightness) */ #define DRM_FORMAT_R16 fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */ /* 16 bpp RG */ @@ -144,8 +210,19 @@ extern "C" { #define DRM_FORMAT_RGBA1010102 fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */ #define DRM_FORMAT_BGRA1010102 fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */ +/* 48 bpp RGB */ +#define DRM_FORMAT_RGB161616 fourcc_code('R', 'G', '4', '8') /* [47:0] R:G:B 16:16:16 little endian */ +#define DRM_FORMAT_BGR161616 fourcc_code('B', 'G', '4', '8') /* [47:0] B:G:R 16:16:16 little endian */ + +/* 64 bpp RGB */ +#define DRM_FORMAT_XRGB16161616 fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */ +#define DRM_FORMAT_XBGR16161616 fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */ + +#define DRM_FORMAT_ARGB16161616 fourcc_code('A', 'R', '4', '8') /* [63:0] A:R:G:B 16:16:16:16 little endian */ +#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 */ @@ -155,6 +232,26 @@ 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: + */ +#define DRM_FORMAT_AXBXGXRX106106106106 fourcc_code('A', 'B', '1', '0') /* [63:0] A:x:B:x:G:x:R:x 10:6:10:6:10:6:10:6 little endian */ + /* packed YCbCr */ #define DRM_FORMAT_YUYV fourcc_code('Y', 'U', 'Y', 'V') /* [31:0] Cr0:Y1:Cb0:Y0 8:8:8:8 little endian */ #define DRM_FORMAT_YVYU fourcc_code('Y', 'V', 'Y', 'U') /* [31:0] Cb0:Y1:Cr0:Y0 8:8:8:8 little endian */ @@ -162,7 +259,9 @@ extern "C" { #define DRM_FORMAT_VYUY fourcc_code('V', 'Y', 'U', 'Y') /* [31:0] Y1:Cb0:Y0:Cr0 8:8:8:8 little endian */ #define DRM_FORMAT_AYUV fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */ +#define DRM_FORMAT_AVUY8888 fourcc_code('A', 'V', 'U', 'Y') /* [31:0] A:Cr:Cb:Y 8:8:8:8 little endian */ #define DRM_FORMAT_XYUV8888 fourcc_code('X', 'Y', 'U', 'V') /* [31:0] X:Y:Cb:Cr 8:8:8:8 little endian */ +#define DRM_FORMAT_XVUY8888 fourcc_code('X', 'V', 'U', 'Y') /* [31:0] X:Cr:Cb:Y 8:8:8:8 little endian */ #define DRM_FORMAT_VUY888 fourcc_code('V', 'U', '2', '4') /* [23:0] Cr:Cb:Y 8:8:8 little endian */ #define DRM_FORMAT_VUY101010 fourcc_code('V', 'U', '3', '0') /* Y followed by U then V, 10:10:10. Non-linear modifier only */ @@ -236,6 +335,14 @@ extern "C" { #define DRM_FORMAT_NV61 fourcc_code('N', 'V', '6', '1') /* 2x1 subsampled Cb:Cr plane */ #define DRM_FORMAT_NV24 fourcc_code('N', 'V', '2', '4') /* non-subsampled Cr:Cb plane */ #define DRM_FORMAT_NV42 fourcc_code('N', 'V', '4', '2') /* non-subsampled Cb:Cr plane */ +/* + * 2 plane YCbCr + * index 0 = Y plane, [39:0] Y3:Y2:Y1:Y0 little endian + * index 1 = Cr:Cb plane, [39:0] Cr1:Cb1:Cr0:Cb0 little endian + */ +#define DRM_FORMAT_NV15 fourcc_code('N', 'V', '1', '5') /* 2x2 subsampled Cr:Cb plane */ +#define DRM_FORMAT_NV20 fourcc_code('N', 'V', '2', '0') /* 2x1 subsampled Cr:Cb plane */ +#define DRM_FORMAT_NV30 fourcc_code('N', 'V', '3', '0') /* non-subsampled Cr:Cb plane */ /* * 2 plane YCbCr MSB aligned @@ -265,6 +372,65 @@ extern "C" { */ #define DRM_FORMAT_P016 fourcc_code('P', '0', '1', '6') /* 2x2 subsampled Cr:Cb plane 16 bits per channel */ +/* 2 plane YCbCr420. + * 3 10 bit components and 2 padding bits packed into 4 bytes. + * index 0 = Y plane, [31:0] x:Y2:Y1:Y0 2:10:10:10 little endian + * index 1 = Cr:Cb plane, [63:0] x:Cr2:Cb2:Cr1:x:Cb1:Cr0:Cb0 [2:10:10:10:2:10:10:10] little endian + */ +#define DRM_FORMAT_P030 fourcc_code('P', '0', '3', '0') /* 2x2 subsampled Cr:Cb plane 10 bits per channel packed */ + +/* 3 plane non-subsampled (444) YCbCr + * 16 bits per component, but only 10 bits are used and 6 bits are padded + * index 0: Y plane, [15:0] Y:x [10:6] little endian + * index 1: Cb plane, [15:0] Cb:x [10:6] little endian + * index 2: Cr plane, [15:0] Cr:x [10:6] little endian + */ +#define DRM_FORMAT_Q410 fourcc_code('Q', '4', '1', '0') + +/* 3 plane non-subsampled (444) YCrCb + * 16 bits per component, but only 10 bits are used and 6 bits are padded + * index 0: Y plane, [15:0] Y:x [10:6] little endian + * index 1: Cr plane, [15:0] Cr:x [10:6] little endian + * index 2: Cb plane, [15:0] Cb:x [10:6] little endian + */ +#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 @@ -298,7 +464,6 @@ extern "C" { */ /* Vendor Ids: */ -#define DRM_FORMAT_MOD_NONE 0 #define DRM_FORMAT_MOD_VENDOR_NONE 0 #define DRM_FORMAT_MOD_VENDOR_INTEL 0x01 #define DRM_FORMAT_MOD_VENDOR_AMD 0x02 @@ -309,11 +474,20 @@ extern "C" { #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07 #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 /* add more to the end as needed */ #define DRM_FORMAT_RESERVED ((1ULL << 56) - 1) +#define fourcc_mod_get_vendor(modifier) \ + (((modifier) >> 56) & 0xff) + +#define fourcc_mod_is_vendor(modifier, vendor) \ + (fourcc_mod_get_vendor(modifier) == DRM_FORMAT_MOD_VENDOR_## vendor) + #define fourcc_mod_code(vendor, val) \ ((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | ((val) & 0x00ffffffffffffffULL)) @@ -323,8 +497,33 @@ extern "C" { * When adding a new token please document the layout with a code comment, * similar to the fourcc codes above. drm_fourcc.h is considered the * authoritative source for all of these. + * + * Generic modifier names: + * + * DRM_FORMAT_MOD_GENERIC_* definitions are used to provide vendor-neutral names + * for layouts which are common across multiple vendors. To preserve + * compatibility, in cases where a vendor-specific definition already exists and + * a generic name for it is desired, the common name is a purely symbolic alias + * and must use the same numerical value as the original definition. + * + * Note that generic names should only be used for modifiers which describe + * generic layouts (such as pixel re-ordering), which may have + * independently-developed support across multiple vendors. + * + * In future cases where a generic layout is identified before merging with a + * vendor-specific modifier, a new 'GENERIC' vendor or modifier using vendor + * 'NONE' could be considered. This should only be for obvious, exceptional + * cases to avoid polluting the 'GENERIC' namespace with modifiers which only + * apply to a single vendor. + * + * Generic names should not be used for cases where multiple hardware vendors + * have implementations of the same standardised compression scheme (such as + * AFBC). In those cases, all implementations should use the same format + * modifier(s), reflecting the vendor of the standard. */ +#define DRM_FORMAT_MOD_GENERIC_16_16_TILE DRM_FORMAT_MOD_SAMSUNG_16_16_TILE + /* * Invalid Modifier * @@ -344,6 +543,16 @@ extern "C" { */ #define DRM_FORMAT_MOD_LINEAR fourcc_mod_code(NONE, 0) +/* + * Deprecated: use DRM_FORMAT_MOD_LINEAR instead + * + * The "none" format modifier doesn't actually mean that the modifier is + * implicit, instead it means that the layout is linear. Whether modifiers are + * used is out-of-band information carried in an API-specific way (e.g. in a + * flag for drm_mode_fb_cmd2). + */ +#define DRM_FORMAT_MOD_NONE 0 + /* Intel framebuffer modifiers */ /* @@ -387,7 +596,7 @@ extern "C" { * This is a tiled layout using 4Kb tiles in row-major layout. * Within the tile pixels are laid out in 16 256 byte units / sub-tiles which * are arranged in four groups (two wide, two high) with column-major layout. - * Each group therefore consits out of four 256 byte units, which are also laid + * Each group therefore consists out of four 256 byte units, which are also laid * out as 2x2 column-major. * 256 byte units are made out of four 64 byte blocks of pixels, producing * either a square block or a 2:1 unit. @@ -441,6 +650,140 @@ extern "C" { #define I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS fourcc_mod_code(INTEL, 7) /* + * Intel Color Control Surface with Clear Color (CCS) for Gen-12 render + * compression. + * + * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear + * and at index 1. The clear color is stored at index 2, and the pitch should + * be 64 bytes aligned. The clear color structure is 256 bits. The first 128 bits + * represents Raw Clear Color Red, Green, Blue and Alpha color each represented + * by 32 bits. The raw clear color is consumed by the 3d engine and generates + * the converted clear color of size 64 bits. The first 32 bits store the Lower + * Converted Clear Color value and the next 32 bits store the Higher Converted + * Clear Color value when applicable. The Converted Clear Color values are + * consumed by the DE. The last 64 bits are used to store Color Discard Enable + * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line + * corresponds to an area of 4x1 tiles in the main surface. The main surface + * pitch is required to be a multiple of 4 tile widths. + */ +#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8) + +/* + * Intel Tile 4 layout + * + * This is a tiled layout using 4KB tiles in a row-major layout. It has the same + * shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It + * only differs from Tile Y at the 256B granularity in between. At this + * granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape + * of 64B x 8 rows. + */ +#define I915_FORMAT_MOD_4_TILED fourcc_mod_code(INTEL, 9) + +/* + * Intel color control surfaces (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * outside of the GEM object in a reserved memory area dedicated for the + * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The + * main surface pitch is required to be a multiple of four Tile 4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS fourcc_mod_code(INTEL, 10) + +/* + * Intel color control surfaces (CCS) for DG2 media compression. + * + * 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 RC/RC_CC/MC compressible GEM objects. The main surface + * pitch is required to be a multiple of four Tile 4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_MC_CCS fourcc_mod_code(INTEL, 11) + +/* + * Intel Color Control Surface with Clear Color (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * outside of the GEM object in a reserved memory area dedicated for the + * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The + * main surface pitch is required to be a multiple of four Tile 4 widths. The + * clear color is stored at plane index 1 and the pitch should be 64 bytes + * aligned. The format of the 256 bits of clear color data matches the one used + * for the I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description + * for details. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12) + +/* + * Intel Color Control Surfaces (CCS) for display ver. 14 render compression. + * + * The main surface is tile4 and at plane index 0, the CCS is linear and + * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in + * main surface. In other words, 4 bits in CCS map to a main surface cache + * line pair. The main surface pitch is required to be a multiple of four + * tile4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS fourcc_mod_code(INTEL, 13) + +/* + * Intel Color Control Surfaces (CCS) for display ver. 14 media compression + * + * The main surface is tile4 and at plane index 0, the CCS is linear and + * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in + * main surface. In other words, 4 bits in CCS map to a main surface cache + * line pair. The main surface pitch is required to be a multiple of four + * tile4 widths. For semi-planar formats like NV12, CCS planes follow the + * Y and UV planes i.e., planes 0 and 1 are used for Y and UV surfaces, + * planes 2 and 3 for the respective CCS. + */ +#define I915_FORMAT_MOD_4_TILED_MTL_MC_CCS fourcc_mod_code(INTEL, 14) + +/* + * Intel Color Control Surface with Clear Color (CCS) for display ver. 14 render + * compression. + * + * The main surface is tile4 and is at plane index 0 whereas CCS is linear + * and at index 1. The clear color is stored at index 2, and the pitch should + * be ignored. The clear color structure is 256 bits. The first 128 bits + * represents Raw Clear Color Red, Green, Blue and Alpha color each represented + * by 32 bits. The raw clear color is consumed by the 3d engine and generates + * the converted clear color of size 64 bits. The first 32 bits store the Lower + * Converted Clear Color value and the next 32 bits store the Higher Converted + * Clear Color value when applicable. The Converted Clear Color values are + * consumed by the DE. The last 64 bits are used to store Color Discard Enable + * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line + * corresponds to an area of 4x1 tiles in the main surface. The main surface + * pitch is required to be a multiple of 4 tile widths. + */ +#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) + +/* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * * Macroblocks are laid in a Z-shape, and each pixel data is following the @@ -477,6 +820,28 @@ extern "C" { */ #define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) +/* + * Qualcomm Tiled Format + * + * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_TILED3 fourcc_mod_code(QCOM, 3) + +/* + * Qualcomm Alternate Tiled Format + * + * Alternate tiled format typically only used within GMEM. + * Implementation may be platform and base-format specific. + */ +#define DRM_FORMAT_MOD_QCOM_TILED2 fourcc_mod_code(QCOM, 2) + + /* Vivante framebuffer modifiers */ /* @@ -517,6 +882,35 @@ extern "C" { */ #define DRM_FORMAT_MOD_VIVANTE_SPLIT_SUPER_TILED fourcc_mod_code(VIVANTE, 4) +/* + * Vivante TS (tile-status) buffer modifiers. They can be combined with all of + * the color buffer tiling modifiers defined above. When TS is present it's a + * separate buffer containing the clear/compression status of each tile. The + * modifiers are defined as VIVANTE_MOD_TS_c_s, where c is the color buffer + * tile size in bytes covered by one entry in the status buffer and s is the + * number of status bits per entry. + * We reserve the top 8 bits of the Vivante modifier space for tile status + * clear/compression modifiers, as future cores might add some more TS layout + * variations. + */ +#define VIVANTE_MOD_TS_64_4 (1ULL << 48) +#define VIVANTE_MOD_TS_64_2 (2ULL << 48) +#define VIVANTE_MOD_TS_128_4 (3ULL << 48) +#define VIVANTE_MOD_TS_256_4 (4ULL << 48) +#define VIVANTE_MOD_TS_MASK (0xfULL << 48) + +/* + * Vivante compression modifiers. Those depend on a TS modifier being present + * as the TS bits get reinterpreted as compression tags instead of simple + * clear markers when compression is enabled. + */ +#define VIVANTE_MOD_COMP_DEC400 (1ULL << 52) +#define VIVANTE_MOD_COMP_MASK (0xfULL << 52) + +/* Masking out the extension bits will yield the base modifier. */ +#define VIVANTE_MOD_EXT_MASK (VIVANTE_MOD_TS_MASK | \ + VIVANTE_MOD_COMP_MASK) + /* NVIDIA frame buffer modifiers */ /* @@ -585,14 +979,20 @@ 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. * @@ -607,7 +1007,7 @@ 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 | \ @@ -615,6 +1015,7 @@ 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, @@ -729,6 +1130,10 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) * and UV. Some SAND-using hardware stores UV in a separate tiled * image from Y to reduce the column height, which is not supported * with these modifiers. + * + * The DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT modifier is also + * supported for DRM_FORMAT_P030 where the columns remain as 128 bytes + * wide, but as this is a 10 bpp format that translates to 96 pixels. */ #define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \ @@ -786,10 +1191,10 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) */ /* - * The top 4 bits (out of the 56 bits alloted for specifying vendor specific - * modifiers) denote the category for modifiers. Currently we have only two - * categories of modifiers ie AFBC and MISC. We can have a maximum of sixteen - * different categories. + * The top 4 bits (out of the 56 bits allotted for specifying vendor specific + * modifiers) denote the category for modifiers. Currently we have three + * categories of modifiers ie AFBC, MISC and AFRC. We can have a maximum of + * sixteen different categories. */ #define DRM_FORMAT_MOD_ARM_CODE(__type, __val) \ fourcc_mod_code(ARM, ((__u64)(__type) << 52) | ((__val) & 0x000fffffffffffffULL)) @@ -892,6 +1297,121 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) */ #define AFBC_FORMAT_MOD_BCH (1ULL << 11) +/* AFBC uncompressed storage mode + * + * Indicates that the buffer is using AFBC uncompressed storage mode. + * In this mode all superblock payloads in the buffer use the uncompressed + * storage mode, which is usually only used for data which cannot be compressed. + * The buffer layout is the same as for AFBC buffers without USM set, this only + * affects the storage mode of the individual superblocks. Note that even a + * buffer without USM set may use uncompressed storage mode for some or all + * superblocks, USM just guarantees it for all. + */ +#define AFBC_FORMAT_MOD_USM (1ULL << 12) + +/* + * Arm Fixed-Rate Compression (AFRC) modifiers + * + * AFRC is a proprietary fixed rate image compression protocol and format, + * designed to provide guaranteed bandwidth and memory footprint + * reductions in graphics and media use-cases. + * + * AFRC buffers consist of one or more planes, with the same components + * and meaning as an uncompressed buffer using the same pixel format. + * + * Within each plane, the pixel/luma/chroma values are grouped into + * "coding unit" blocks which are individually compressed to a + * fixed size (in bytes). All coding units within a given plane of a buffer + * store the same number of values, and have the same compressed size. + * + * The coding unit size is configurable, allowing different rates of compression. + * + * The start of each AFRC buffer plane must be aligned to an alignment granule which + * depends on the coding unit size. + * + * Coding Unit Size Plane Alignment + * ---------------- --------------- + * 16 bytes 1024 bytes + * 24 bytes 512 bytes + * 32 bytes 2048 bytes + * + * Coding units are grouped into paging tiles. AFRC buffer dimensions must be aligned + * to a multiple of the paging tile dimensions. + * The dimensions of each paging tile depend on whether the buffer is optimised for + * scanline (SCAN layout) or rotated (ROT layout) access. + * + * Layout Paging Tile Width Paging Tile Height + * ------ ----------------- ------------------ + * SCAN 16 coding units 4 coding units + * ROT 8 coding units 8 coding units + * + * The dimensions of each coding unit depend on the number of components + * in the compressed plane and whether the buffer is optimised for + * scanline (SCAN layout) or rotated (ROT layout) access. + * + * Number of Components in Plane Layout Coding Unit Width Coding Unit Height + * ----------------------------- --------- ----------------- ------------------ + * 1 SCAN 16 samples 4 samples + * Example: 16x4 luma samples in a 'Y' plane + * 16x4 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer + * ----------------------------- --------- ----------------- ------------------ + * 1 ROT 8 samples 8 samples + * Example: 8x8 luma samples in a 'Y' plane + * 8x8 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer + * ----------------------------- --------- ----------------- ------------------ + * 2 DONT CARE 8 samples 4 samples + * Example: 8x4 chroma pairs in the 'UV' plane of a semi-planar YUV buffer + * ----------------------------- --------- ----------------- ------------------ + * 3 DONT CARE 4 samples 4 samples + * Example: 4x4 pixels in an RGB buffer without alpha + * ----------------------------- --------- ----------------- ------------------ + * 4 DONT CARE 4 samples 4 samples + * Example: 4x4 pixels in an RGB buffer with alpha + */ + +#define DRM_FORMAT_MOD_ARM_TYPE_AFRC 0x02 + +#define DRM_FORMAT_MOD_ARM_AFRC(__afrc_mode) \ + DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_AFRC, __afrc_mode) + +/* + * AFRC coding unit size modifier. + * + * Indicates the number of bytes used to store each compressed coding unit for + * one or more planes in an AFRC encoded buffer. The coding unit size for chrominance + * is the same for both Cb and Cr, which may be stored in separate planes. + * + * AFRC_FORMAT_MOD_CU_SIZE_P0 indicates the number of bytes used to store + * each compressed coding unit in the first plane of the buffer. For RGBA buffers + * this is the only plane, while for semi-planar and fully-planar YUV buffers, + * this corresponds to the luma plane. + * + * AFRC_FORMAT_MOD_CU_SIZE_P12 indicates the number of bytes used to store + * each compressed coding unit in the second and third planes in the buffer. + * For semi-planar and fully-planar YUV buffers, this corresponds to the chroma plane(s). + * + * For single-plane buffers, AFRC_FORMAT_MOD_CU_SIZE_P0 must be specified + * and AFRC_FORMAT_MOD_CU_SIZE_P12 must be zero. + * For semi-planar and fully-planar buffers, both AFRC_FORMAT_MOD_CU_SIZE_P0 and + * AFRC_FORMAT_MOD_CU_SIZE_P12 must be specified. + */ +#define AFRC_FORMAT_MOD_CU_SIZE_MASK 0xf +#define AFRC_FORMAT_MOD_CU_SIZE_16 (1ULL) +#define AFRC_FORMAT_MOD_CU_SIZE_24 (2ULL) +#define AFRC_FORMAT_MOD_CU_SIZE_32 (3ULL) + +#define AFRC_FORMAT_MOD_CU_SIZE_P0(__afrc_cu_size) (__afrc_cu_size) +#define AFRC_FORMAT_MOD_CU_SIZE_P12(__afrc_cu_size) ((__afrc_cu_size) << 4) + +/* + * AFRC scanline memory layout. + * + * Indicates if the buffer uses the scanline-optimised layout + * for an AFRC encoded buffer, otherwise, it uses the rotation-optimised layout. + * The memory layout is the same for all planes. + */ +#define AFRC_FORMAT_MOD_LAYOUT_SCAN (1ULL << 8) + /* * Arm 16x16 Block U-Interleaved modifier * @@ -916,6 +1436,325 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) */ #define DRM_FORMAT_MOD_ALLWINNER_TILED fourcc_mod_code(ALLWINNER, 1) +/* + * Amlogic Video Framebuffer Compression modifiers + * + * Amlogic uses a proprietary lossless image compression protocol and format + * for their hardware video codec accelerators, either video decoders or + * video input encoders. + * + * It considerably reduces memory bandwidth while writing and reading + * frames in memory. + * + * The underlying storage is considered to be 3 components, 8bit or 10-bit + * per component YCbCr 420, single plane : + * - DRM_FORMAT_YUV420_8BIT + * - DRM_FORMAT_YUV420_10BIT + * + * The first 8 bits of the mode defines the layout, then the following 8 bits + * defines the options changing the layout. + * + * Not all combinations are valid, and different SoCs may support different + * combinations of layout and options. + */ +#define __fourcc_mod_amlogic_layout_mask 0xff +#define __fourcc_mod_amlogic_options_shift 8 +#define __fourcc_mod_amlogic_options_mask 0xff + +#define DRM_FORMAT_MOD_AMLOGIC_FBC(__layout, __options) \ + fourcc_mod_code(AMLOGIC, \ + ((__layout) & __fourcc_mod_amlogic_layout_mask) | \ + (((__options) & __fourcc_mod_amlogic_options_mask) \ + << __fourcc_mod_amlogic_options_shift)) + +/* Amlogic FBC Layouts */ + +/* + * Amlogic FBC Basic Layout + * + * The basic layout is composed of: + * - a body content organized in 64x32 superblocks with 4096 bytes per + * superblock in default mode. + * - a 32 bytes per 128x64 header block + * + * This layout is transferrable between Amlogic SoCs supporting this modifier. + */ +#define AMLOGIC_FBC_LAYOUT_BASIC (1ULL) + +/* + * Amlogic FBC Scatter Memory layout + * + * Indicates the header contains IOMMU references to the compressed + * frames content to optimize memory access and layout. + * + * In this mode, only the header memory address is needed, thus the + * content memory organization is tied to the current producer + * execution and cannot be saved/dumped neither transferrable between + * Amlogic SoCs supporting this modifier. + * + * Due to the nature of the layout, these buffers are not expected to + * be accessible by the user-space clients, but only accessible by the + * hardware producers and consumers. + * + * The user-space clients should expect a failure while trying to mmap + * the DMA-BUF handle returned by the producer. + */ +#define AMLOGIC_FBC_LAYOUT_SCATTER (2ULL) + +/* Amlogic FBC Layout Options Bit Mask */ + +/* + * Amlogic FBC Memory Saving mode + * + * Indicates the storage is packed when pixel size is multiple of word + * boundaries, i.e. 8bit should be stored in this mode to save allocation + * memory. + * + * This mode reduces body layout to 3072 bytes per 64x32 superblock with + * the basic layout and 3200 bytes per 64x32 superblock combined with + * the scatter layout. + */ +#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 + * + * Memory layout: + * + * without DCC: + * - main surface + * + * with DCC & without DCC_RETILE: + * - main surface in plane 0 + * - DCC surface in plane 1 (RB-aligned, pipe-aligned if DCC_PIPE_ALIGN is set) + * + * with DCC & DCC_RETILE: + * - main surface in plane 0 + * - displayable DCC surface in plane 1 (not RB-aligned & not pipe-aligned) + * - pipe-aligned DCC surface in plane 2 (RB-aligned & pipe-aligned) + * + * For multi-plane formats the above surfaces get merged into one plane for + * each format plane, based on the required alignment only. + * + * Bits Parameter Notes + * ----- ------------------------ --------------------------------------------- + * + * 7:0 TILE_VERSION Values are AMD_FMT_MOD_TILE_VER_* + * 12:8 TILE Values are AMD_FMT_MOD_TILE_<version>_* + * 13 DCC + * 14 DCC_RETILE + * 15 DCC_PIPE_ALIGN + * 16 DCC_INDEPENDENT_64B + * 17 DCC_INDEPENDENT_128B + * 19:18 DCC_MAX_COMPRESSED_BLOCK Values are AMD_FMT_MOD_DCC_BLOCK_* + * 20 DCC_CONSTANT_ENCODE + * 23:21 PIPE_XOR_BITS Only for some chips + * 26:24 BANK_XOR_BITS Only for some chips + * 29:27 PACKERS Only for some chips + * 32:30 RB Only for some chips + * 35:33 PIPE Only for some chips + * 55:36 - Reserved for future use, must be zero + */ +#define AMD_FMT_MOD fourcc_mod_code(AMD, 0) + +#define IS_AMD_FMT_MOD(val) (((val) >> 56) == DRM_FORMAT_MOD_VENDOR_AMD) + +/* Reserve 0 for GFX8 and older */ +#define AMD_FMT_MOD_TILE_VER_GFX9 1 +#define AMD_FMT_MOD_TILE_VER_GFX10 2 +#define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3 +#define AMD_FMT_MOD_TILE_VER_GFX11 4 +#define AMD_FMT_MOD_TILE_VER_GFX12 5 + +/* + * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical + * version. + */ +#define AMD_FMT_MOD_TILE_GFX9_64K_S 9 + +/* + * 64K_D for non-32 bpp is the same for GFX9/GFX10/GFX10_RBPLUS and hence has + * GFX9 as canonical version. + * + * 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 +#define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31 + +/* Gfx12 swizzle modes: + * 0 - LINEAR + * 1 - 256B_2D - 2D block dimensions + * 2 - 4KB_2D + * 3 - 64KB_2D + * 4 - 256KB_2D + * 5 - 4KB_3D - 3D block dimensions + * 6 - 64KB_3D + * 7 - 256KB_3D + */ +#define AMD_FMT_MOD_TILE_GFX12_256B_2D 1 +#define AMD_FMT_MOD_TILE_GFX12_4K_2D 2 +#define AMD_FMT_MOD_TILE_GFX12_64K_2D 3 +#define AMD_FMT_MOD_TILE_GFX12_256K_2D 4 + +#define AMD_FMT_MOD_DCC_BLOCK_64B 0 +#define AMD_FMT_MOD_DCC_BLOCK_128B 1 +#define AMD_FMT_MOD_DCC_BLOCK_256B 2 + +#define AMD_FMT_MOD_TILE_VERSION_SHIFT 0 +#define AMD_FMT_MOD_TILE_VERSION_MASK 0xFF +#define AMD_FMT_MOD_TILE_SHIFT 8 +#define AMD_FMT_MOD_TILE_MASK 0x1F + +/* Whether DCC compression is enabled. */ +#define AMD_FMT_MOD_DCC_SHIFT 13 +#define AMD_FMT_MOD_DCC_MASK 0x1 + +/* + * Whether to include two DCC surfaces, one which is rb & pipe aligned, and + * one which is not-aligned. + */ +#define AMD_FMT_MOD_DCC_RETILE_SHIFT 14 +#define AMD_FMT_MOD_DCC_RETILE_MASK 0x1 + +/* Only set if DCC_RETILE = false */ +#define AMD_FMT_MOD_DCC_PIPE_ALIGN_SHIFT 15 +#define AMD_FMT_MOD_DCC_PIPE_ALIGN_MASK 0x1 + +#define AMD_FMT_MOD_DCC_INDEPENDENT_64B_SHIFT 16 +#define AMD_FMT_MOD_DCC_INDEPENDENT_64B_MASK 0x1 +#define AMD_FMT_MOD_DCC_INDEPENDENT_128B_SHIFT 17 +#define AMD_FMT_MOD_DCC_INDEPENDENT_128B_MASK 0x1 +#define AMD_FMT_MOD_DCC_MAX_COMPRESSED_BLOCK_SHIFT 18 +#define AMD_FMT_MOD_DCC_MAX_COMPRESSED_BLOCK_MASK 0x3 + +/* + * DCC supports embedding some clear colors directly in the DCC surface. + * However, on older GPUs the rendering HW ignores the embedded clear color + * and prefers the driver provided color. This necessitates doing a fastclear + * eliminate operation before a process transfers control. + * + * If this bit is set that means the fastclear eliminate is not needed for these + * embeddable colors. + */ +#define AMD_FMT_MOD_DCC_CONSTANT_ENCODE_SHIFT 20 +#define AMD_FMT_MOD_DCC_CONSTANT_ENCODE_MASK 0x1 + +/* + * The below fields are for accounting for per GPU differences. These are only + * relevant for GFX9 and later and if the tile field is *_X/_T. + * + * PIPE_XOR_BITS = always needed + * BANK_XOR_BITS = only for TILE_VER_GFX9 + * PACKERS = only for TILE_VER_GFX10_RBPLUS + * RB = only for TILE_VER_GFX9 & DCC + * PIPE = only for TILE_VER_GFX9 & DCC & (DCC_RETILE | DCC_PIPE_ALIGN) + */ +#define AMD_FMT_MOD_PIPE_XOR_BITS_SHIFT 21 +#define AMD_FMT_MOD_PIPE_XOR_BITS_MASK 0x7 +#define AMD_FMT_MOD_BANK_XOR_BITS_SHIFT 24 +#define AMD_FMT_MOD_BANK_XOR_BITS_MASK 0x7 +#define AMD_FMT_MOD_PACKERS_SHIFT 27 +#define AMD_FMT_MOD_PACKERS_MASK 0x7 +#define AMD_FMT_MOD_RB_SHIFT 30 +#define AMD_FMT_MOD_RB_MASK 0x7 +#define AMD_FMT_MOD_PIPE_SHIFT 33 +#define AMD_FMT_MOD_PIPE_MASK 0x7 + +#define AMD_FMT_MOD_SET(field, value) \ + ((__u64)(value) << AMD_FMT_MOD_##field##_SHIFT) +#define AMD_FMT_MOD_GET(field, value) \ + (((value) >> AMD_FMT_MOD_##field##_SHIFT) & AMD_FMT_MOD_##field##_MASK) +#define AMD_FMT_MOD_CLEAR(field) \ + (~((__u64)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT)) + #if defined(__cplusplus) } #endif |