summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/gen7_renderclear.c
blob: 21f08e53889c39a1b52d6f48dd8e4d52676b801c (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
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2019 Intel Corporation
 */

#include "gen7_renderclear.h"
#include "i915_drv.h"
#include "intel_gpu_commands.h"

#define GT3_INLINE_DATA_DELAYS 0x1E00
#define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS))

struct cb_kernel {
	const void *data;
	u32 size;
};

#define CB_KERNEL(name) { .data = (name), .size = sizeof(name) }

#include "ivb_clear_kernel.c"
static const struct cb_kernel cb_kernel_ivb = CB_KERNEL(ivb_clear_kernel);

#include "hsw_clear_kernel.c"
static const struct cb_kernel cb_kernel_hsw = CB_KERNEL(hsw_clear_kernel);

struct batch_chunk {
	struct i915_vma *vma;
	u32 offset;
	u32 *start;
	u32 *end;
	u32 max_items;
};

struct batch_vals {
	u32 max_threads;
	u32 state_start;
	u32 surface_start;
	u32 surface_height;
	u32 surface_width;
	u32 size;
};

static int num_primitives(const struct batch_vals *bv)
{
	/*
	 * We need to saturate the GPU with work in order to dispatch
	 * a shader on every HW thread, and clear the thread-local registers.
	 * In short, we have to dispatch work faster than the shaders can
	 * run in order to fill the EU and occupy each HW thread.
	 */
	return bv->max_threads;
}

static void
batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv)
{
	if (IS_HASWELL(i915)) {
		switch (INTEL_INFO(i915)->gt) {
		default:
		case 1:
			bv->max_threads = 70;
			break;
		case 2:
			bv->max_threads = 140;
			break;
		case 3:
			bv->max_threads = 280;
			break;
		}
		bv->surface_height = 16 * 16;
		bv->surface_width = 32 * 2 * 16;
	} else {
		switch (INTEL_INFO(i915)->gt) {
		default:
		case 1: /* including vlv */
			bv->max_threads = 36;
			break;
		case 2:
			bv->max_threads = 128;
			break;
		}
		bv->surface_height = 16 * 8;
		bv->surface_width = 32 * 16;
	}
	bv->state_start = round_up(SZ_1K + num_primitives(bv) * 64, SZ_4K);
	bv->surface_start = bv->state_start + SZ_4K;
	bv->size = bv->surface_start + bv->surface_height * bv->surface_width;
}

static void batch_init(struct batch_chunk *bc,
		       struct i915_vma *vma,
		       u32 *start, u32 offset, u32 max_bytes)
{
	bc->vma = vma;
	bc->offset = offset;
	bc->start = start + bc->offset / sizeof(*bc->start);
	bc->end = bc->start;
	bc->max_items = max_bytes / sizeof(*bc->start);
}

static u32 batch_offset(const struct batch_chunk *bc, u32 *cs)
{
	return (cs - bc->start) * sizeof(*bc->start) + bc->offset;
}

static u32 batch_addr(const struct batch_chunk *bc)
{
	return bc->vma->node.start;
}

static void batch_add(struct batch_chunk *bc, const u32 d)
{
	GEM_BUG_ON((bc->end - bc->start) >= bc->max_items);
	*bc->end++ = d;
}

static u32 *batch_alloc_items(struct batch_chunk *bc, u32 align, u32 items)
{
	u32 *map;

	if (align) {
		u32 *end = PTR_ALIGN(bc->end, align);

		memset32(bc->end, 0, end - bc->end);
		bc->end = end;
	}

	map = bc->end;
	bc->end += items;

	return map;
}

static u32 *batch_alloc_bytes(struct batch_chunk *bc, u32 align, u32 bytes)
{
	GEM_BUG_ON(!IS_ALIGNED(bytes, sizeof(*bc->start)));
	return batch_alloc_items(bc, align, bytes / sizeof(*bc->start));
}

static u32
gen7_fill_surface_state(struct batch_chunk *state,
			const u32 dst_offset,
			const struct batch_vals *bv)
{
	u32 surface_h = bv->surface_height;
	u32 surface_w = bv->surface_width;
	u32 *cs = batch_alloc_items(state, 32, 8);
	u32 offset = batch_offset(state, cs);

#define SURFACE_2D 1
#define SURFACEFORMAT_B8G8R8A8_UNORM 0x0C0
#define RENDER_CACHE_READ_WRITE 1

	*cs++ = SURFACE_2D << 29 |
		(SURFACEFORMAT_B8G8R8A8_UNORM << 18) |
		(RENDER_CACHE_READ_WRITE << 8);

	*cs++ = batch_addr(state) + dst_offset;

	*cs++ = ((surface_h / 4 - 1) << 16) | (surface_w / 4 - 1);
	*cs++ = surface_w;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
#define SHADER_CHANNELS(r, g, b, a) \
	(((r) << 25) | ((g) << 22) | ((b) << 19) | ((a) << 16))
	*cs++ = SHADER_CHANNELS(4, 5, 6, 7);
	batch_advance(state, cs);

	return offset;
}

static u32
gen7_fill_binding_table(struct batch_chunk *state,
			const struct batch_vals *bv)
{
	u32 surface_start =
		gen7_fill_surface_state(state, bv->surface_start, bv);
	u32 *cs = batch_alloc_items(state, 32, 8);
	u32 offset = batch_offset(state, cs);

	*cs++ = surface_start - state->offset;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	batch_advance(state, cs);

	return offset;
}

static u32
gen7_fill_kernel_data(struct batch_chunk *state,
		      const u32 *data,
		      const u32 size)
{
	return batch_offset(state,
			    memcpy(batch_alloc_bytes(state, 64, size),
				   data, size));
}

static u32
gen7_fill_interface_descriptor(struct batch_chunk *state,
			       const struct batch_vals *bv,
			       const struct cb_kernel *kernel,
			       unsigned int count)
{
	u32 kernel_offset =
		gen7_fill_kernel_data(state, kernel->data, kernel->size);
	u32 binding_table = gen7_fill_binding_table(state, bv);
	u32 *cs = batch_alloc_items(state, 32, 8 * count);
	u32 offset = batch_offset(state, cs);

	*cs++ = kernel_offset;
	*cs++ = (1 << 7) | (1 << 13);
	*cs++ = 0;
	*cs++ = (binding_table - state->offset) | 1;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;

	/* 1 - 63dummy idds */
	memset32(cs, 0x00, (count - 1) * 8);
	batch_advance(state, cs + (count - 1) * 8);

	return offset;
}

static void
gen7_emit_state_base_address(struct batch_chunk *batch,
			     u32 surface_state_base)
{
	u32 *cs = batch_alloc_items(batch, 0, 10);

	*cs++ = STATE_BASE_ADDRESS | (10 - 2);
	/* general */
	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
	/* surface */
	*cs++ = (batch_addr(batch) + surface_state_base) | BASE_ADDRESS_MODIFY;
	/* dynamic */
	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
	/* indirect */
	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
	/* instruction */
	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;

	/* general/dynamic/indirect/instruction access Bound */
	*cs++ = 0;
	*cs++ = BASE_ADDRESS_MODIFY;
	*cs++ = 0;
	*cs++ = BASE_ADDRESS_MODIFY;
	batch_advance(batch, cs);
}

static void
gen7_emit_vfe_state(struct batch_chunk *batch,
		    const struct batch_vals *bv,
		    u32 urb_size, u32 curbe_size,
		    u32 mode)
{
	u32 threads = bv->max_threads - 1;
	u32 *cs = batch_alloc_items(batch, 32, 8);

	*cs++ = MEDIA_VFE_STATE | (8 - 2);

	/* scratch buffer */
	*cs++ = 0;

	/* number of threads & urb entries for GPGPU vs Media Mode */
	*cs++ = threads << 16 | 1 << 8 | mode << 2;

	*cs++ = 0;

	/* urb entry size & curbe size in 256 bits unit */
	*cs++ = urb_size << 16 | curbe_size;

	/* scoreboard */
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;
	batch_advance(batch, cs);
}

static void
gen7_emit_interface_descriptor_load(struct batch_chunk *batch,
				    const u32 interface_descriptor,
				    unsigned int count)
{
	u32 *cs = batch_alloc_items(batch, 8, 4);

	*cs++ = MEDIA_INTERFACE_DESCRIPTOR_LOAD | (4 - 2);
	*cs++ = 0;
	*cs++ = count * 8 * sizeof(*cs);

	/*
	 * interface descriptor address - it is relative to the dynamics base
	 * address
	 */
	*cs++ = interface_descriptor;
	batch_advance(batch, cs);
}

static void
gen7_emit_media_object(struct batch_chunk *batch,
		       unsigned int media_object_index)
{
	unsigned int x_offset = (media_object_index % 16) * 64;
	unsigned int y_offset = (media_object_index / 16) * 16;
	unsigned int pkt = 6 + 3;
	u32 *cs;

	cs = batch_alloc_items(batch, 8, pkt);

	*cs++ = MEDIA_OBJECT | (pkt - 2);

	/* interface descriptor offset */
	*cs++ = 0;

	/* without indirect data */
	*cs++ = 0;
	*cs++ = 0;

	/* scoreboard */
	*cs++ = 0;
	*cs++ = 0;

	/* inline */
	*cs++ = y_offset << 16 | x_offset;
	*cs++ = 0;
	*cs++ = GT3_INLINE_DATA_DELAYS;

	batch_advance(batch, cs);
}

static void gen7_emit_pipeline_flush(struct batch_chunk *batch)
{
	u32 *cs = batch_alloc_items(batch, 0, 4);

	*cs++ = GFX_OP_PIPE_CONTROL(4);
	*cs++ = PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
		PIPE_CONTROL_DEPTH_CACHE_FLUSH |
		PIPE_CONTROL_DC_FLUSH_ENABLE |
		PIPE_CONTROL_CS_STALL;
	*cs++ = 0;
	*cs++ = 0;

	batch_advance(batch, cs);
}

static void gen7_emit_pipeline_invalidate(struct batch_chunk *batch)
{
	u32 *cs = batch_alloc_items(batch, 0, 10);

	/* ivb: Stall before STATE_CACHE_INVALIDATE */
	*cs++ = GFX_OP_PIPE_CONTROL(5);
	*cs++ = PIPE_CONTROL_STALL_AT_SCOREBOARD |
		PIPE_CONTROL_CS_STALL;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;

	*cs++ = GFX_OP_PIPE_CONTROL(5);
	*cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE;
	*cs++ = 0;
	*cs++ = 0;
	*cs++ = 0;

	batch_advance(batch, cs);
}

static void emit_batch(struct i915_vma * const vma,
		       u32 *start,
		       const struct batch_vals *bv)
{
	struct drm_i915_private *i915 = vma->vm->i915;
	const unsigned int desc_count = 1;
	const unsigned int urb_size = 1;
	struct batch_chunk cmds, state;
	u32 descriptors;
	unsigned int i;

	batch_init(&cmds, vma, start, 0, bv->state_start);
	batch_init(&state, vma, start, bv->state_start, SZ_4K);

	descriptors = gen7_fill_interface_descriptor(&state, bv,
						     IS_HASWELL(i915) ?
						     &cb_kernel_hsw :
						     &cb_kernel_ivb,
						     desc_count);

	/* Reset inherited context registers */
	gen7_emit_pipeline_flush(&cmds);
	gen7_emit_pipeline_invalidate(&cmds);
	batch_add(&cmds, MI_LOAD_REGISTER_IMM(2));
	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_0_GEN7));
	batch_add(&cmds, 0xffff0000 |
			((IS_IVB_GT1(i915) || IS_VALLEYVIEW(i915)) ?
			 HIZ_RAW_STALL_OPT_DISABLE :
			 0));
	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_1));
	batch_add(&cmds, 0xffff0000 | PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
	gen7_emit_pipeline_invalidate(&cmds);
	gen7_emit_pipeline_flush(&cmds);

	/* Switch to the media pipeline and our base address */
	gen7_emit_pipeline_invalidate(&cmds);
	batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
	batch_add(&cmds, MI_NOOP);
	gen7_emit_pipeline_invalidate(&cmds);

	gen7_emit_pipeline_flush(&cmds);
	gen7_emit_state_base_address(&cmds, descriptors);
	gen7_emit_pipeline_invalidate(&cmds);

	/* Set the clear-residual kernel state */
	gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
	gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count);

	/* Execute the kernel on all HW threads */
	for (i = 0; i < num_primitives(bv); i++)
		gen7_emit_media_object(&cmds, i);

	batch_add(&cmds, MI_BATCH_BUFFER_END);
}

int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
			    struct i915_vma * const vma)
{
	struct batch_vals bv;
	u32 *batch;

	batch_get_defaults(engine->i915, &bv);
	if (!vma)
		return bv.size;

	GEM_BUG_ON(vma->obj->base.size < bv.size);

	batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
	if (IS_ERR(batch))
		return PTR_ERR(batch);

	emit_batch(vma, memset(batch, 0, bv.size), &bv);

	i915_gem_object_flush_map(vma->obj);
	__i915_gem_object_release_map(vma->obj);

	return 0;
}