1/* 2 * Copyright 2012 Advanced Micro Devices, Inc. 3 * All Rights Reserved. 4 * 5 * Permission is hereby granted, free of charge, to any person obtaining a 6 * copy of this software and associated documentation files (the "Software"), 7 * to deal in the Software without restriction, including without limitation 8 * on the rights to use, copy, modify, merge, publish, distribute, sub 9 * license, and/or sell copies of the Software, and to permit persons to whom 10 * the Software is furnished to do so, subject to the following conditions: 11 * 12 * The above copyright notice and this permission notice (including the next 13 * paragraph) shall be included in all copies or substantial portions of the 14 * Software. 15 * 16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 18 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL 19 * THE AUTHOR(S) AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM, 20 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 21 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 22 * USE OR OTHER DEALINGS IN THE SOFTWARE. 23 */ 24 25#include "si_pipe.h" 26#include "si_build_pm4.h" 27#include "sid.h" 28#include "util/u_memory.h" 29 30static void si_pm4_cmd_begin(struct si_pm4_state *state, unsigned opcode) 31{ 32 if (!state->max_dw) 33 state->max_dw = ARRAY_SIZE(state->pm4); 34 assert(state->ndw < state->max_dw); 35 assert(opcode <= 254); 36 state->last_opcode = opcode; 37 state->last_pm4 = state->ndw++; 38} 39 40void si_pm4_cmd_add(struct si_pm4_state *state, uint32_t dw) 41{ 42 if (!state->max_dw) 43 state->max_dw = ARRAY_SIZE(state->pm4); 44 assert(state->ndw < state->max_dw); 45 state->pm4[state->ndw++] = dw; 46 state->last_opcode = 255; /* invalid opcode */ 47} 48 49static void si_pm4_cmd_end(struct si_pm4_state *state, bool predicate) 50{ 51 unsigned count; 52 count = state->ndw - state->last_pm4 - 2; 53 state->pm4[state->last_pm4] = PKT3(state->last_opcode, count, predicate); 54} 55 56static void si_pm4_set_reg_custom(struct si_pm4_state *state, unsigned reg, uint32_t val, 57 unsigned opcode, unsigned idx) 58{ 59 reg >>= 2; 60 61 if (!state->max_dw) 62 state->max_dw = ARRAY_SIZE(state->pm4); 63 64 assert(state->ndw + 2 <= state->max_dw); 65 66 if (opcode != state->last_opcode || reg != (state->last_reg + 1)) { 67 si_pm4_cmd_begin(state, opcode); 68 state->pm4[state->ndw++] = reg | (idx << 28); 69 } 70 71 assert(reg <= UINT16_MAX); 72 state->last_reg = reg; 73 state->pm4[state->ndw++] = val; 74 si_pm4_cmd_end(state, false); 75} 76 77void si_pm4_set_reg(struct si_pm4_state *state, unsigned reg, uint32_t val) 78{ 79 unsigned opcode; 80 81 SI_CHECK_SHADOWED_REGS(reg, 1); 82 83 if (reg >= SI_CONFIG_REG_OFFSET && reg < SI_CONFIG_REG_END) { 84 opcode = PKT3_SET_CONFIG_REG; 85 reg -= SI_CONFIG_REG_OFFSET; 86 87 } else if (reg >= SI_SH_REG_OFFSET && reg < SI_SH_REG_END) { 88 opcode = PKT3_SET_SH_REG; 89 reg -= SI_SH_REG_OFFSET; 90 91 } else if (reg >= SI_CONTEXT_REG_OFFSET && reg < SI_CONTEXT_REG_END) { 92 opcode = PKT3_SET_CONTEXT_REG; 93 reg -= SI_CONTEXT_REG_OFFSET; 94 95 } else if (reg >= CIK_UCONFIG_REG_OFFSET && reg < CIK_UCONFIG_REG_END) { 96 opcode = PKT3_SET_UCONFIG_REG; 97 reg -= CIK_UCONFIG_REG_OFFSET; 98 99 } else { 100 PRINT_ERR("Invalid register offset %08x!\n", reg); 101 return; 102 } 103 104 si_pm4_set_reg_custom(state, reg, val, opcode, 0); 105} 106 107void si_pm4_set_reg_idx3(struct si_pm4_state *state, unsigned reg, uint32_t val) 108{ 109 SI_CHECK_SHADOWED_REGS(reg, 1); 110 111 si_pm4_set_reg_custom(state, reg - SI_SH_REG_OFFSET, val, PKT3_SET_SH_REG_INDEX, 3); 112} 113 114void si_pm4_clear_state(struct si_pm4_state *state) 115{ 116 state->ndw = 0; 117} 118 119void si_pm4_free_state(struct si_context *sctx, struct si_pm4_state *state, unsigned idx) 120{ 121 if (!state) 122 return; 123 124 if (idx != ~0) { 125 if (sctx->emitted.array[idx] == state) 126 sctx->emitted.array[idx] = NULL; 127 128 if (sctx->queued.array[idx] == state) { 129 sctx->queued.array[idx] = NULL; 130 sctx->dirty_states &= ~BITFIELD_BIT(idx); 131 } 132 } 133 134 FREE(state); 135} 136 137void si_pm4_emit(struct si_context *sctx, struct si_pm4_state *state) 138{ 139 struct radeon_cmdbuf *cs = &sctx->gfx_cs; 140 141 if (state->is_shader) { 142 radeon_add_to_buffer_list(sctx, &sctx->gfx_cs, ((struct si_shader*)state)->bo, 143 RADEON_USAGE_READ | RADEON_PRIO_SHADER_BINARY); 144 } 145 146 radeon_begin(cs); 147 radeon_emit_array(state->pm4, state->ndw); 148 radeon_end(); 149 150 if (state->atom.emit) 151 state->atom.emit(sctx); 152} 153 154void si_pm4_reset_emitted(struct si_context *sctx, bool first_cs) 155{ 156 if (!first_cs && sctx->shadowed_regs) { 157 /* Only dirty states that contain buffers, so that they are 158 * added to the buffer list on the next draw call. 159 */ 160 for (unsigned i = 0; i < SI_NUM_STATES; i++) { 161 struct si_pm4_state *state = sctx->queued.array[i]; 162 163 if (state && state->is_shader) { 164 sctx->emitted.array[i] = NULL; 165 sctx->dirty_states |= 1 << i; 166 } 167 } 168 return; 169 } 170 171 memset(&sctx->emitted, 0, sizeof(sctx->emitted)); 172 173 for (unsigned i = 0; i < SI_NUM_STATES; i++) { 174 if (sctx->queued.array[i]) 175 sctx->dirty_states |= BITFIELD_BIT(i); 176 } 177} 178