[Mesa-dev] [PATCH 1/5] drm-uapi: Update headers from nouveau/linux-5.6
James Jones
jajones at nvidia.com
Wed Feb 5 20:52:43 UTC 2020
Copy latest drm_fourcc.h from nouveau/linux-5.6
XXX - Update this with final commit ID/info
commit: d8a841ff4f4cbb31dd0dfd037399421969837730
Author: James Jones <jajones at nvidia.com>
Date: Tue Aug 6 17:10:10 2019 -0700
drm: Generalized NV Block Linear DRM format mod
Signed-off-by: James Jones <jajones at nvidia.com>
---
include/drm-uapi/drm_fourcc.h | 135 +++++++++++++++++++++++++++++++---
1 file changed, 126 insertions(+), 9 deletions(-)
diff --git a/include/drm-uapi/drm_fourcc.h b/include/drm-uapi/drm_fourcc.h
index 2376d36ea57..56217e2f39e 100644
--- a/include/drm-uapi/drm_fourcc.h
+++ b/include/drm-uapi/drm_fourcc.h
@@ -69,7 +69,7 @@ extern "C" {
#define fourcc_code(a, b, c, d) ((__u32)(a) | ((__u32)(b) << 8) | \
((__u32)(c) << 16) | ((__u32)(d) << 24))
-#define DRM_FORMAT_BIG_ENDIAN (1<<31) /* format is big endian instead of little endian */
+#define DRM_FORMAT_BIG_ENDIAN (1U<<31) /* format is big endian instead of little endian */
/* Reserve 0 for the invalid format specifier */
#define DRM_FORMAT_INVALID 0
@@ -410,6 +410,17 @@ extern "C" {
#define I915_FORMAT_MOD_Y_TILED_CCS fourcc_mod_code(INTEL, 4)
#define I915_FORMAT_MOD_Yf_TILED_CCS fourcc_mod_code(INTEL, 5)
+/*
+ * Intel color control surfaces (CCS) for Gen-12 render compression.
+ *
+ * The main surface is Y-tiled 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
+ * Y-tile widths.
+ */
+#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS fourcc_mod_code(INTEL, 6)
+
/*
* Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
*
@@ -497,7 +508,113 @@ extern "C" {
#define DRM_FORMAT_MOD_NVIDIA_TEGRA_TILED fourcc_mod_code(NVIDIA, 1)
/*
- * 16Bx2 Block Linear layout, used by desktop GPUs, and Tegra K1 and later
+ * Generalized Block Linear layout, used by desktop GPUs starting with NV50/G80,
+ * and Tegra GPUs starting with Tegra K1.
+ *
+ * Pixels are arranged in Groups of Bytes (GOBs). GOB size and layout varies
+ * based on the architecture generation. GOBs themselves are then arranged in
+ * 3D blocks, with the block dimensions (in terms of GOBs) always being a power
+ * of two, and hence expressible as their log2 equivalent (E.g., "2" represents
+ * a block depth or height of "4").
+ *
+ * Chapter 20 "Pixel Memory Formats" of the Tegra X1 TRM describes this format
+ * in full detail.
+ *
+ * Macro
+ * Bits Param Description
+ * ---- ----- -----------------------------------------------------------------
+ *
+ * 3:0 h log2(height) of each block, in GOBs. Placed here for
+ * compatibility with the existing
+ * DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK()-based modifiers.
+ *
+ * 4:4 - Must be 1, to indicate block-linear layout. Necessary for
+ * compatibility with the existing
+ * DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK()-based modifiers.
+ *
+ * 8:5 - Reserved (To support 3D-surfaces with variable log2(depth) block
+ * size). Must be zero.
+ *
+ * Note there is no log2(width) parameter. Some portions of the
+ * hardware support a block width of two gobs, but it is impractical
+ * to use due to lack of support elsewhere, and has no known
+ * benefits.
+ *
+ * 11:9 - Reserved (To support 2D-array textures with variable array stride
+ * in blocks, specified via log2(tile width in blocks)). Must be
+ * zero.
+ *
+ * 19:12 k Page Kind. This value directly maps to a field in the page
+ * tables of all GPUs >= NV50. It affects the exact layout of bits
+ * in memory and can be derived from the tuple
+ *
+ * (format, GPU model, compression type, samples per pixel)
+ *
+ * Where compression type is defined below. If GPU model were
+ * implied by the format modifier, format, or memory buffer, page
+ * kind would not need to be included in the modifier itself, but
+ * since the modifier should define the layout of the associated
+ * memory buffer independent from any device or other context, it
+ * must be included here.
+ *
+ * 21:20 g GOB Height and Page Kind Generation. The height of a GOB changed
+ * starting with Fermi GPUs. Additionally, the mapping between page
+ * kind and bit layout has changed at various points.
+ *
+ * 0 = Gob Height 8, Fermi - Volta, Tegra K1+ Page Kind mapping
+ * 1 = Gob Height 4, G80 - GT2XX Page Kind mapping
+ * 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
+ *
+ * 25:23 c Lossless Framebuffer Compression type.
+ *
+ * 0 = none
+ * 1 = ROP/3D, layout 1, exact compression format implied by Page
+ * Kind field
+ * 2 = ROP/3D, layout 2, exact compression format implied by Page
+ * Kind field
+ * 3 = CDE horizontal
+ * 4 = CDE vertical
+ * 5 = Reserved for future use
+ * 6 = Reserved for future use
+ * 7 = Reserved for future use
+ *
+ * 55:25 - 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 | \
+ ((h) & 0xf) | \
+ (((k) & 0xff) << 12) | \
+ (((g) & 0x3) << 20) | \
+ (((s) & 0x1) << 22) | \
+ (((c) & 0x7) << 23)))
+
+/* To grandfather in prior block linear format modifiers to the above layout,
+ * the page kind "0", which corresponds to "pitch/linear" and hence is unusable
+ * with block-linear layouts, is remapped within drivers to the value 0xfe,
+ * which corresponds to the "generic" kind used for simple single-sample
+ * uncompressed color formats on Fermi - Volta GPUs.
+ */
+static inline __u64
+drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
+{
+ if (!(modifier & 0x10) || (modifier & (0xff << 12)))
+ return modifier;
+ else
+ return modifier | (0xfe << 12);
+}
+
+/*
+ * 16Bx2 Block Linear layout, used by Tegra K1 and later
*
* Pixels are arranged in 64x8 Groups Of Bytes (GOBs). GOBs are then stacked
* vertically by a power of 2 (1 to 32 GOBs) to form a block.
@@ -518,20 +635,20 @@ extern "C" {
* in full detail.
*/
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(v) \
- fourcc_mod_code(NVIDIA, 0x10 | ((v) & 0xf))
+ DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 0, 0, 0, (v))
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_ONE_GOB \
- fourcc_mod_code(NVIDIA, 0x10)
+ DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0)
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_TWO_GOB \
- fourcc_mod_code(NVIDIA, 0x11)
+ DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1)
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_FOUR_GOB \
- fourcc_mod_code(NVIDIA, 0x12)
+ DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2)
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_EIGHT_GOB \
- fourcc_mod_code(NVIDIA, 0x13)
+ DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3)
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_SIXTEEN_GOB \
- fourcc_mod_code(NVIDIA, 0x14)
+ DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4)
#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_THIRTYTWO_GOB \
- fourcc_mod_code(NVIDIA, 0x15)
+ DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5)
/*
* Some Broadcom modifiers take parameters, for example the number of
--
2.17.1
More information about the mesa-dev
mailing list