1/* 2 * Copyright 2010 Jerome Glisse <glisse@freedesktop.org> 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: 24 * Jerome Glisse 25 */ 26#include "r600_pipe.h" 27#include "evergreend.h" 28#include "util/u_memory.h" 29#include "util/u_math.h" 30 31void evergreen_dma_copy_buffer(struct r600_context *rctx, 32 struct pipe_resource *dst, 33 struct pipe_resource *src, 34 uint64_t dst_offset, 35 uint64_t src_offset, 36 uint64_t size) 37{ 38 struct radeon_cmdbuf *cs = &rctx->b.dma.cs; 39 unsigned i, ncopy, csize, sub_cmd, shift; 40 struct r600_resource *rdst = (struct r600_resource*)dst; 41 struct r600_resource *rsrc = (struct r600_resource*)src; 42 43 /* Mark the buffer range of destination as valid (initialized), 44 * so that transfer_map knows it should wait for the GPU when mapping 45 * that range. */ 46 util_range_add(&rdst->b.b, &rdst->valid_buffer_range, dst_offset, 47 dst_offset + size); 48 49 dst_offset += rdst->gpu_address; 50 src_offset += rsrc->gpu_address; 51 52 /* see if we use dword or byte copy */ 53 if (!(dst_offset % 4) && !(src_offset % 4) && !(size % 4)) { 54 size >>= 2; 55 sub_cmd = EG_DMA_COPY_DWORD_ALIGNED; 56 shift = 2; 57 } else { 58 sub_cmd = EG_DMA_COPY_BYTE_ALIGNED; 59 shift = 0; 60 } 61 ncopy = (size / EG_DMA_COPY_MAX_SIZE) + !!(size % EG_DMA_COPY_MAX_SIZE); 62 63 r600_need_dma_space(&rctx->b, ncopy * 5, rdst, rsrc); 64 for (i = 0; i < ncopy; i++) { 65 csize = size < EG_DMA_COPY_MAX_SIZE ? size : EG_DMA_COPY_MAX_SIZE; 66 /* emit reloc before writing cs so that cs is always in consistent state */ 67 radeon_add_to_buffer_list(&rctx->b, &rctx->b.dma, rsrc, RADEON_USAGE_READ); 68 radeon_add_to_buffer_list(&rctx->b, &rctx->b.dma, rdst, RADEON_USAGE_WRITE); 69 radeon_emit(cs, DMA_PACKET(DMA_PACKET_COPY, sub_cmd, csize)); 70 radeon_emit(cs, dst_offset & 0xffffffff); 71 radeon_emit(cs, src_offset & 0xffffffff); 72 radeon_emit(cs, (dst_offset >> 32UL) & 0xff); 73 radeon_emit(cs, (src_offset >> 32UL) & 0xff); 74 dst_offset += csize << shift; 75 src_offset += csize << shift; 76 size -= csize; 77 } 78} 79 80/* The max number of bytes to copy per packet. */ 81#define CP_DMA_MAX_BYTE_COUNT ((1 << 21) - 8) 82 83void evergreen_cp_dma_clear_buffer(struct r600_context *rctx, 84 struct pipe_resource *dst, uint64_t offset, 85 unsigned size, uint32_t clear_value, 86 enum r600_coherency coher) 87{ 88 struct radeon_cmdbuf *cs = &rctx->b.gfx.cs; 89 90 assert(size); 91 assert(rctx->screen->b.has_cp_dma); 92 93 /* Mark the buffer range of destination as valid (initialized), 94 * so that transfer_map knows it should wait for the GPU when mapping 95 * that range. */ 96 util_range_add(dst, &r600_resource(dst)->valid_buffer_range, offset, 97 offset + size); 98 99 offset += r600_resource(dst)->gpu_address; 100 101 /* Flush the cache where the resource is bound. */ 102 rctx->b.flags |= r600_get_flush_flags(coher) | 103 R600_CONTEXT_WAIT_3D_IDLE; 104 105 while (size) { 106 unsigned sync = 0; 107 unsigned byte_count = MIN2(size, CP_DMA_MAX_BYTE_COUNT); 108 unsigned reloc; 109 110 r600_need_cs_space(rctx, 111 10 + (rctx->b.flags ? R600_MAX_FLUSH_CS_DWORDS : 0) + 112 R600_MAX_PFP_SYNC_ME_DWORDS, FALSE, 0); 113 114 /* Flush the caches for the first copy only. */ 115 if (rctx->b.flags) { 116 r600_flush_emit(rctx); 117 } 118 119 /* Do the synchronization after the last copy, so that all data is written to memory. */ 120 if (size == byte_count) { 121 sync = PKT3_CP_DMA_CP_SYNC; 122 } 123 124 /* This must be done after r600_need_cs_space. */ 125 reloc = radeon_add_to_buffer_list(&rctx->b, &rctx->b.gfx, 126 (struct r600_resource*)dst, RADEON_USAGE_WRITE | 127 RADEON_PRIO_CP_DMA); 128 129 radeon_emit(cs, PKT3(PKT3_CP_DMA, 4, 0)); 130 radeon_emit(cs, clear_value); /* DATA [31:0] */ 131 radeon_emit(cs, sync | PKT3_CP_DMA_SRC_SEL(2)); /* CP_SYNC [31] | SRC_SEL[30:29] */ 132 radeon_emit(cs, offset); /* DST_ADDR_LO [31:0] */ 133 radeon_emit(cs, (offset >> 32) & 0xff); /* DST_ADDR_HI [7:0] */ 134 radeon_emit(cs, byte_count); /* COMMAND [29:22] | BYTE_COUNT [20:0] */ 135 136 radeon_emit(cs, PKT3(PKT3_NOP, 0, 0)); 137 radeon_emit(cs, reloc); 138 139 size -= byte_count; 140 offset += byte_count; 141 } 142 143 /* CP DMA is executed in ME, but index buffers are read by PFP. 144 * This ensures that ME (CP DMA) is idle before PFP starts fetching 145 * indices. If we wanted to execute CP DMA in PFP, this packet 146 * should precede it. 147 */ 148 if (coher == R600_COHERENCY_SHADER) 149 r600_emit_pfp_sync_me(rctx); 150} 151