aboutsummaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers/dri/intel/intel_span.c
blob: 3645720c060b9780fee5cdfb10c6130af3d2e9b7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
/**************************************************************************
 * 
 * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
 * Copyright 2011 Intel Corporation
 * All Rights Reserved.
 * 
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sub license, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 * 
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 * 
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
 * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 * 
 * Authors:
 *     Chad Versace <chad@chad-versace.us>
 *
 **************************************************************************/

#include <stdbool.h>
#include <stdint.h>
#include "main/glheader.h"
#include "main/macros.h"
#include "main/mtypes.h"
#include "main/colormac.h"
#include "main/renderbuffer.h"

#include "intel_buffers.h"
#include "intel_fbo.h"
#include "intel_mipmap_tree.h"
#include "intel_screen.h"
#include "intel_span.h"
#include "intel_regions.h"
#include "intel_tex.h"

#include "swrast/swrast.h"
#include "swrast/s_renderbuffer.h"

/**
 * \brief Get pointer offset into stencil buffer.
 *
 * The stencil buffer is W tiled. Since the GTT is incapable of W fencing, we
 * must decode the tile's layout in software.
 *
 * See
 *   - PRM, 2011 Sandy Bridge, Volume 1, Part 2, Section 4.5.2.1 W-Major Tile
 *     Format.
 *   - PRM, 2011 Sandy Bridge, Volume 1, Part 2, Section 4.5.3 Tiling Algorithm
 *
 * Even though the returned offset is always positive, the return type is
 * signed due to
 *    commit e8b1c6d6f55f5be3bef25084fdd8b6127517e137
 *    mesa: Fix return type of  _mesa_get_format_bytes() (#37351)
 */
intptr_t
intel_offset_S8(uint32_t stride, uint32_t x, uint32_t y)
{
   uint32_t tile_size = 4096;
   uint32_t tile_width = 64;
   uint32_t tile_height = 64;
   uint32_t row_size = 64 * stride;

   uint32_t tile_x = x / tile_width;
   uint32_t tile_y = y / tile_height;

   /* The byte's address relative to the tile's base addres. */
   uint32_t byte_x = x % tile_width;
   uint32_t byte_y = y % tile_height;

   uintptr_t u = tile_y * row_size
               + tile_x * tile_size
               + 512 * (byte_x / 8)
               +  64 * (byte_y / 8)
               +  32 * ((byte_y / 4) % 2)
               +  16 * ((byte_x / 4) % 2)
               +   8 * ((byte_y / 2) % 2)
               +   4 * ((byte_x / 2) % 2)
               +   2 * (byte_y % 2)
               +   1 * (byte_x % 2);

   /*
    * Errata for Gen5:
    *
    * An additional offset is needed which is not documented in the PRM.
    *
    * if ((byte_x / 8) % 2 == 1) {
    *    if ((byte_y / 8) % 2) == 0) {
    *       u += 64;
    *    } else {
    *       u -= 64;
    *    }
    * }
    *
    * The offset is expressed more tersely as
    * u += ((int) x & 0x8) * (8 - (((int) y & 0x8) << 1));
    */

   return u;
}


/**
 * Resolve all buffers that will be mapped by intelSpanRenderStart().
 *
 * Resolve the depth buffer of each enabled texture and of the read and draw
 * buffers.
 *
 * (Note: In the future this will also perform MSAA resolves.)
 */
static void
intel_span_resolve_buffers(struct intel_context *intel)
{
   struct gl_context *ctx = &intel->ctx;
   struct intel_renderbuffer *draw_irb;
   struct intel_renderbuffer *read_irb;
   struct intel_texture_object *tex_obj;

   /* Resolve depth buffer of each enabled texture. */
   for (int i = 0; i < ctx->Const.MaxTextureImageUnits; i++) {
      if (!ctx->Texture.Unit[i]._ReallyEnabled)
	 continue;
      tex_obj = intel_texture_object(ctx->Texture.Unit[i]._Current);
      intel_finalize_mipmap_tree(intel, i);
      if (!tex_obj || !tex_obj->mt)
	 continue;
      intel_miptree_all_slices_resolve_depth(intel, tex_obj->mt);
   }

   /* Resolve each attached depth buffer. */
   draw_irb = intel_get_renderbuffer(ctx->DrawBuffer, BUFFER_DEPTH);
   read_irb = intel_get_renderbuffer(ctx->ReadBuffer, BUFFER_DEPTH);
   if (draw_irb)
      intel_renderbuffer_resolve_depth(intel, draw_irb);
   if (read_irb != draw_irb && read_irb)
      intel_renderbuffer_resolve_depth(intel, read_irb);
}

/**
 * Map the regions needed by intelSpanRenderStart().
 */
static void
intel_span_map_buffers(struct intel_context *intel)
{
   struct gl_context *ctx = &intel->ctx;
   struct intel_texture_object *tex_obj;

   for (int i = 0; i < ctx->Const.MaxTextureImageUnits; i++) {
      if (!ctx->Texture.Unit[i]._ReallyEnabled)
	 continue;
      tex_obj = intel_texture_object(ctx->Texture.Unit[i]._Current);
      intel_finalize_mipmap_tree(intel, i);
      intel_tex_map_images(intel, tex_obj,
			   GL_MAP_READ_BIT | GL_MAP_WRITE_BIT);
   }

   _swrast_map_renderbuffers(ctx);
}

/**
 * Prepare for software rendering.  Map current read/draw framebuffers'
 * renderbuffes and all currently bound texture objects.
 *
 * Old note: Moved locking out to get reasonable span performance.
 */
void
intelSpanRenderStart(struct gl_context * ctx)
{
   struct intel_context *intel = intel_context(ctx);

   intel_flush(ctx);
   intel_prepare_render(intel);
   intel_span_resolve_buffers(intel);
   intel_flush(ctx);
   intel_span_map_buffers(intel);
}

/**
 * Called when done software rendering.  Unmap the buffers we mapped in
 * the above function.
 */
void
intelSpanRenderFinish(struct gl_context * ctx)
{
   struct intel_context *intel = intel_context(ctx);
   GLuint i;

   _swrast_flush(ctx);

   for (i = 0; i < ctx->Const.MaxTextureImageUnits; i++) {
      if (ctx->Texture.Unit[i]._ReallyEnabled) {
         struct gl_texture_object *texObj = ctx->Texture.Unit[i]._Current;
         intel_tex_unmap_images(intel, intel_texture_object(texObj));
      }
   }

   _swrast_unmap_renderbuffers(ctx);
}


void
intelInitSpanFuncs(struct gl_context * ctx)
{
   struct swrast_device_driver *swdd = _swrast_GetDeviceDriverReference(ctx);
   swdd->SpanRenderStart = intelSpanRenderStart;
   swdd->SpanRenderFinish = intelSpanRenderFinish;
}

void
intel_map_vertex_shader_textures(struct gl_context *ctx)
{
   struct intel_context *intel = intel_context(ctx);
   int i;

   if (ctx->VertexProgram._Current == NULL)
      return;

   for (i = 0; i < ctx->Const.MaxTextureImageUnits; i++) {
      if (ctx->Texture.Unit[i]._ReallyEnabled &&
	  ctx->VertexProgram._Current->Base.TexturesUsed[i] != 0) {
         struct gl_texture_object *texObj = ctx->Texture.Unit[i]._Current;

         intel_tex_map_images(intel, intel_texture_object(texObj),
                              GL_MAP_READ_BIT | GL_MAP_WRITE_BIT);
      }
   }
}

void
intel_unmap_vertex_shader_textures(struct gl_context *ctx)
{
   struct intel_context *intel = intel_context(ctx);
   int i;

   if (ctx->VertexProgram._Current == NULL)
      return;

   for (i = 0; i < ctx->Const.MaxTextureImageUnits; i++) {
      if (ctx->Texture.Unit[i]._ReallyEnabled &&
	  ctx->VertexProgram._Current->Base.TexturesUsed[i] != 0) {
         struct gl_texture_object *texObj = ctx->Texture.Unit[i]._Current;

         intel_tex_unmap_images(intel, intel_texture_object(texObj));
      }
   }
}