1/* 2 * Copyright 2013 Advanced Micro Devices, Inc. 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 * on the rights to use, copy, modify, merge, publish, distribute, sub 8 * license, and/or sell copies of the Software, and to permit persons to whom 9 * the 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 NON-INFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHOR(S) AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM, 19 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 20 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 21 * USE OR OTHER DEALINGS IN THE SOFTWARE. 22 * 23 * Authors: Marek Olšák <maraeo@gmail.com> 24 */ 25 26/** 27 * This file contains helpers for writing commands to commands streams. 28 */ 29 30#ifndef R600_CS_H 31#define R600_CS_H 32 33#include "r600_pipe_common.h" 34#include "r600d_common.h" 35 36/** 37 * Return true if there is enough memory in VRAM and GTT for the buffers 38 * added so far. 39 * 40 * \param vram VRAM memory size not added to the buffer list yet 41 * \param gtt GTT memory size not added to the buffer list yet 42 */ 43static inline bool 44radeon_cs_memory_below_limit(struct r600_common_screen *screen, 45 struct radeon_cmdbuf *cs, 46 uint64_t vram, uint64_t gtt) 47{ 48 vram += (uint64_t)cs->used_vram_kb * 1024; 49 gtt += (uint64_t)cs->used_gart_kb * 1024; 50 51 /* Anything that goes above the VRAM size should go to GTT. */ 52 if (vram > (uint64_t)screen->info.vram_size_kb * 1024) 53 gtt += vram - (uint64_t)screen->info.vram_size_kb * 1024; 54 55 /* Now we just need to check if we have enough GTT. */ 56 return gtt < (uint64_t)screen->info.gart_size_kb * 1024 * 0.7; 57} 58 59/** 60 * Add a buffer to the buffer list for the given command stream (CS). 61 * 62 * All buffers used by a CS must be added to the list. This tells the kernel 63 * driver which buffers are used by GPU commands. Other buffers can 64 * be swapped out (not accessible) during execution. 65 * 66 * The buffer list becomes empty after every context flush and must be 67 * rebuilt. 68 */ 69static inline unsigned radeon_add_to_buffer_list(struct r600_common_context *rctx, 70 struct r600_ring *ring, 71 struct r600_resource *rbo, 72 unsigned usage) 73{ 74 assert(usage); 75 return rctx->ws->cs_add_buffer( 76 &ring->cs, rbo->buf, 77 usage | RADEON_USAGE_SYNCHRONIZED, 78 rbo->domains) * 4; 79} 80 81/** 82 * Same as above, but also checks memory usage and flushes the context 83 * accordingly. 84 * 85 * When this SHOULD NOT be used: 86 * 87 * - if r600_context_add_resource_size has been called for the buffer 88 * followed by *_need_cs_space for checking the memory usage 89 * 90 * - if r600_need_dma_space has been called for the buffer 91 * 92 * - when emitting state packets and draw packets (because preceding packets 93 * can't be re-emitted at that point) 94 * 95 * - if shader resource "enabled_mask" is not up-to-date or there is 96 * a different constraint disallowing a context flush 97 */ 98static inline unsigned 99radeon_add_to_buffer_list_check_mem(struct r600_common_context *rctx, 100 struct r600_ring *ring, 101 struct r600_resource *rbo, 102 unsigned usage, 103 bool check_mem) 104{ 105 if (check_mem && 106 !radeon_cs_memory_below_limit(rctx->screen, &ring->cs, 107 rctx->vram + rbo->vram_usage, 108 rctx->gtt + rbo->gart_usage)) 109 ring->flush(rctx, PIPE_FLUSH_ASYNC, NULL); 110 111 return radeon_add_to_buffer_list(rctx, ring, rbo, usage); 112} 113 114static inline void r600_emit_reloc(struct r600_common_context *rctx, 115 struct r600_ring *ring, struct r600_resource *rbo, 116 unsigned usage) 117{ 118 struct radeon_cmdbuf *cs = &ring->cs; 119 bool has_vm = ((struct r600_common_screen*)rctx->b.screen)->info.r600_has_virtual_memory; 120 unsigned reloc = radeon_add_to_buffer_list(rctx, ring, rbo, usage); 121 122 if (!has_vm) { 123 radeon_emit(cs, PKT3(PKT3_NOP, 0, 0)); 124 radeon_emit(cs, reloc); 125 } 126} 127 128static inline void radeon_set_config_reg_seq(struct radeon_cmdbuf *cs, unsigned reg, unsigned num) 129{ 130 assert(reg < R600_CONTEXT_REG_OFFSET); 131 assert(cs->current.cdw + 2 + num <= cs->current.max_dw); 132 radeon_emit(cs, PKT3(PKT3_SET_CONFIG_REG, num, 0)); 133 radeon_emit(cs, (reg - R600_CONFIG_REG_OFFSET) >> 2); 134} 135 136static inline void radeon_set_config_reg(struct radeon_cmdbuf *cs, unsigned reg, unsigned value) 137{ 138 radeon_set_config_reg_seq(cs, reg, 1); 139 radeon_emit(cs, value); 140} 141 142static inline void radeon_set_context_reg_seq(struct radeon_cmdbuf *cs, unsigned reg, unsigned num) 143{ 144 assert(reg >= R600_CONTEXT_REG_OFFSET); 145 assert(cs->current.cdw + 2 + num <= cs->current.max_dw); 146 radeon_emit(cs, PKT3(PKT3_SET_CONTEXT_REG, num, 0)); 147 radeon_emit(cs, (reg - R600_CONTEXT_REG_OFFSET) >> 2); 148} 149 150static inline void radeon_set_context_reg(struct radeon_cmdbuf *cs, unsigned reg, unsigned value) 151{ 152 radeon_set_context_reg_seq(cs, reg, 1); 153 radeon_emit(cs, value); 154} 155 156static inline void radeon_set_context_reg_idx(struct radeon_cmdbuf *cs, 157 unsigned reg, unsigned idx, 158 unsigned value) 159{ 160 assert(reg >= R600_CONTEXT_REG_OFFSET); 161 assert(cs->current.cdw + 3 <= cs->current.max_dw); 162 radeon_emit(cs, PKT3(PKT3_SET_CONTEXT_REG, 1, 0)); 163 radeon_emit(cs, (reg - R600_CONTEXT_REG_OFFSET) >> 2 | (idx << 28)); 164 radeon_emit(cs, value); 165} 166 167static inline void radeon_set_sh_reg_seq(struct radeon_cmdbuf *cs, unsigned reg, unsigned num) 168{ 169 assert(reg >= SI_SH_REG_OFFSET && reg < SI_SH_REG_END); 170 assert(cs->current.cdw + 2 + num <= cs->current.max_dw); 171 radeon_emit(cs, PKT3(PKT3_SET_SH_REG, num, 0)); 172 radeon_emit(cs, (reg - SI_SH_REG_OFFSET) >> 2); 173} 174 175static inline void radeon_set_sh_reg(struct radeon_cmdbuf *cs, unsigned reg, unsigned value) 176{ 177 radeon_set_sh_reg_seq(cs, reg, 1); 178 radeon_emit(cs, value); 179} 180 181static inline void radeon_set_uconfig_reg_seq(struct radeon_cmdbuf *cs, unsigned reg, unsigned num) 182{ 183 assert(reg >= CIK_UCONFIG_REG_OFFSET && reg < CIK_UCONFIG_REG_END); 184 assert(cs->current.cdw + 2 + num <= cs->current.max_dw); 185 radeon_emit(cs, PKT3(PKT3_SET_UCONFIG_REG, num, 0)); 186 radeon_emit(cs, (reg - CIK_UCONFIG_REG_OFFSET) >> 2); 187} 188 189static inline void radeon_set_uconfig_reg(struct radeon_cmdbuf *cs, unsigned reg, unsigned value) 190{ 191 radeon_set_uconfig_reg_seq(cs, reg, 1); 192 radeon_emit(cs, value); 193} 194 195static inline void radeon_set_uconfig_reg_idx(struct radeon_cmdbuf *cs, 196 unsigned reg, unsigned idx, 197 unsigned value) 198{ 199 assert(reg >= CIK_UCONFIG_REG_OFFSET && reg < CIK_UCONFIG_REG_END); 200 assert(cs->current.cdw + 3 <= cs->current.max_dw); 201 radeon_emit(cs, PKT3(PKT3_SET_UCONFIG_REG, 1, 0)); 202 radeon_emit(cs, (reg - CIK_UCONFIG_REG_OFFSET) >> 2 | (idx << 28)); 203 radeon_emit(cs, value); 204} 205 206#endif 207