1/* 2 * Copyright © 2014 Broadcom 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice (including the next 12 * paragraph) shall be included in all copies or substantial portions of the 13 * Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS 21 * IN THE SOFTWARE. 22 */ 23 24/** @file vc4_tiling.c 25 * 26 * Handles information about the VC4 tiling formats, and loading and storing 27 * from them. 28 * 29 * Texture mipmap levels on VC4 are (with the exception of 32-bit RGBA raster 30 * textures for scanout) stored as groups of microtiles. If the texture is at 31 * least 4x4 microtiles (utiles), then those microtiles are arranged in a sort 32 * of Hilbert-fractal-ish layout (T), otherwise the microtiles are in raster 33 * order (LT). 34 * 35 * Specifically, the T format has: 36 * 37 * - 64b utiles of pixels in a raster-order grid according to cpp. It's 4x4 38 * pixels at 32 bit depth. 39 * 40 * - 1k subtiles made of a 4x4 raster-order grid of 64b utiles (so usually 41 * 16x16 pixels). 42 * 43 * - 4k tiles made of a 2x2 grid of 1k subtiles (so usually 32x32 pixels). On 44 * even 4k tile rows, they're arranged as (BL, TL, TR, BR), and on odd rows 45 * they're (TR, BR, BL, TL), where bottom left is start of memory. 46 * 47 * - an image made of 4k tiles in rows either left-to-right (even rows of 4k 48 * tiles) or right-to-left (odd rows of 4k tiles). 49 */ 50 51#include "vc4_screen.h" 52#include "vc4_context.h" 53#include "vc4_tiling.h" 54 55/** 56 * The texture unit decides what tiling format a particular miplevel is using 57 * this function, so we lay out our miptrees accordingly. 58 */ 59bool 60vc4_size_is_lt(uint32_t width, uint32_t height, int cpp) 61{ 62 return (width <= 4 * vc4_utile_width(cpp) || 63 height <= 4 * vc4_utile_height(cpp)); 64} 65 66/** 67 * Takes a utile x and y (and the number of utiles of width of the image) and 68 * returns the offset to the utile within a VC4_TILING_FORMAT_TF image. 69 */ 70static uint32_t 71t_utile_address(uint32_t utile_x, uint32_t utile_y, 72 uint32_t utile_stride) 73{ 74 /* T images have to be aligned to 8 utiles (4x4 subtiles, which are 75 * 2x2 in a 4k tile). 76 */ 77 assert(!(utile_stride & 7)); 78 uint32_t tile_stride = utile_stride >> 3; 79 /* 4k tile offsets. */ 80 uint32_t tile_x = utile_x >> 3; 81 uint32_t tile_y = utile_y >> 3; 82 bool odd_tile_y = tile_y & 1; 83 84 /* Odd lines of 4k tiles go right-to-left. */ 85 if (odd_tile_y) 86 tile_x = tile_stride - tile_x - 1; 87 88 uint32_t tile_offset = 4096 * (tile_y * tile_stride + tile_x); 89 90 uint32_t stile_x = (utile_x >> 2) & 1; 91 uint32_t stile_y = (utile_y >> 2) & 1; 92 uint32_t stile_index = (stile_y << 1) + stile_x; 93 static const uint32_t odd_stile_map[4] = {2, 1, 3, 0}; 94 static const uint32_t even_stile_map[4] = {0, 3, 1, 2}; 95 96 uint32_t stile_offset = 1024 * (odd_tile_y ? 97 odd_stile_map[stile_index] : 98 even_stile_map[stile_index]); 99 100 /* This function no longer handles the utile offset within a subtile. 101 * Walking subtiles is the job of the LT image handler. 102 */ 103 assert(!(utile_x & 3) && !(utile_y & 3)); 104 105#if 0 106 fprintf(stderr, "utile %d,%d -> %d + %d + %d (stride %d,%d) = %d\n", 107 utile_x, utile_y, 108 tile_offset, stile_offset, utile_offset, 109 utile_stride, tile_stride, 110 tile_offset + stile_offset + utile_offset); 111#endif 112 113 return tile_offset + stile_offset; 114} 115 116/** 117 * Loads or stores a T texture image by breaking it down into subtiles 118 * (1024-byte, 4x4-utile) sub-images that we can use the LT tiling functions 119 * on. 120 */ 121static inline void 122vc4_t_image_helper(void *gpu, uint32_t gpu_stride, 123 void *cpu, uint32_t cpu_stride, 124 int cpp, const struct pipe_box *box, 125 bool to_cpu) 126{ 127 uint32_t utile_w = vc4_utile_width(cpp); 128 uint32_t utile_h = vc4_utile_height(cpp); 129 uint32_t utile_w_shift = ffs(utile_w) - 1; 130 uint32_t utile_h_shift = ffs(utile_h) - 1; 131 uint32_t stile_w = 4 * utile_w; 132 uint32_t stile_h = 4 * utile_h; 133 assert(stile_w * stile_h * cpp == 1024); 134 uint32_t utile_stride = gpu_stride / cpp / utile_w; 135 uint32_t x1 = box->x; 136 uint32_t y1 = box->y; 137 uint32_t x2 = box->x + box->width; 138 uint32_t y2 = box->y + box->height; 139 struct pipe_box partial_box; 140 uint32_t gpu_lt_stride = stile_w * cpp; 141 142 for (uint32_t y = y1; y < y2; y = align(y + 1, stile_h)) { 143 partial_box.y = y & (stile_h - 1); 144 partial_box.height = MIN2(y2 - y, stile_h - partial_box.y); 145 146 uint32_t cpu_offset = 0; 147 for (uint32_t x = x1; x < x2; x = align(x + 1, stile_w)) { 148 partial_box.x = x & (stile_w - 1); 149 partial_box.width = MIN2(x2 - x, 150 stile_w - partial_box.x); 151 152 /* The dst offset we want is the start of this 153 * subtile 154 */ 155 uint32_t gpu_offset = 156 t_utile_address((x >> utile_w_shift) & ~0x3, 157 (y >> utile_h_shift) & ~0x3, 158 utile_stride); 159 160 if (to_cpu) { 161 vc4_load_lt_image(cpu + cpu_offset, 162 cpu_stride, 163 gpu + gpu_offset, 164 gpu_lt_stride, 165 cpp, &partial_box); 166 } else { 167 vc4_store_lt_image(gpu + gpu_offset, 168 gpu_lt_stride, 169 cpu + cpu_offset, 170 cpu_stride, 171 cpp, &partial_box); 172 } 173 174 cpu_offset += partial_box.width * cpp; 175 } 176 cpu += cpu_stride * partial_box.height; 177 } 178} 179 180static void 181vc4_store_t_image(void *dst, uint32_t dst_stride, 182 void *src, uint32_t src_stride, 183 int cpp, const struct pipe_box *box) 184{ 185 vc4_t_image_helper(dst, dst_stride, 186 src, src_stride, 187 cpp, box, false); 188} 189 190static void 191vc4_load_t_image(void *dst, uint32_t dst_stride, 192 void *src, uint32_t src_stride, 193 int cpp, const struct pipe_box *box) 194{ 195 vc4_t_image_helper(src, src_stride, 196 dst, dst_stride, 197 cpp, box, true); 198} 199 200/** 201 * Loads pixel data from the start (microtile-aligned) box in \p src to the 202 * start of \p dst according to the given tiling format. 203 */ 204void 205vc4_load_tiled_image(void *dst, uint32_t dst_stride, 206 void *src, uint32_t src_stride, 207 uint8_t tiling_format, int cpp, 208 const struct pipe_box *box) 209{ 210 if (tiling_format == VC4_TILING_FORMAT_LT) { 211 vc4_load_lt_image(dst, dst_stride, 212 src, src_stride, 213 cpp, box); 214 } else { 215 assert(tiling_format == VC4_TILING_FORMAT_T); 216 vc4_load_t_image(dst, dst_stride, 217 src, src_stride, 218 cpp, box); 219 } 220} 221 222/** 223 * Stores pixel data from the start of \p src into a (microtile-aligned) box in 224 * \p dst according to the given tiling format. 225 */ 226void 227vc4_store_tiled_image(void *dst, uint32_t dst_stride, 228 void *src, uint32_t src_stride, 229 uint8_t tiling_format, int cpp, 230 const struct pipe_box *box) 231{ 232 if (tiling_format == VC4_TILING_FORMAT_LT) { 233 vc4_store_lt_image(dst, dst_stride, 234 src, src_stride, 235 cpp, box); 236 } else { 237 assert(tiling_format == VC4_TILING_FORMAT_T); 238 vc4_store_t_image(dst, dst_stride, 239 src, src_stride, 240 cpp, box); 241 } 242} 243 244