summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/xe/xe_ring_ops.c
blob: c4edffcd4a320666d576d950ab15dc614545a053 (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
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2022 Intel Corporation
 */

#include "xe_ring_ops.h"

#include <generated/xe_wa_oob.h>

#include "instructions/xe_mi_commands.h"
#include "regs/xe_engine_regs.h"
#include "regs/xe_gpu_commands.h"
#include "regs/xe_gt_regs.h"
#include "regs/xe_lrc_layout.h"
#include "xe_exec_queue_types.h"
#include "xe_gt.h"
#include "xe_lrc.h"
#include "xe_macros.h"
#include "xe_sched_job.h"
#include "xe_vm_types.h"
#include "xe_vm.h"
#include "xe_wa.h"

/*
 * 3D-related flags that can't be set on _engines_ that lack access to the 3D
 * pipeline (i.e., CCS engines).
 */
#define PIPE_CONTROL_3D_ENGINE_FLAGS (\
		PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | \
		PIPE_CONTROL_DEPTH_CACHE_FLUSH | \
		PIPE_CONTROL_TILE_CACHE_FLUSH | \
		PIPE_CONTROL_DEPTH_STALL | \
		PIPE_CONTROL_STALL_AT_SCOREBOARD | \
		PIPE_CONTROL_PSD_SYNC | \
		PIPE_CONTROL_AMFS_FLUSH | \
		PIPE_CONTROL_VF_CACHE_INVALIDATE | \
		PIPE_CONTROL_GLOBAL_SNAPSHOT_RESET)

/* 3D-related flags that can't be set on _platforms_ that lack a 3D pipeline */
#define PIPE_CONTROL_3D_ARCH_FLAGS ( \
		PIPE_CONTROL_3D_ENGINE_FLAGS | \
		PIPE_CONTROL_INDIRECT_STATE_DISABLE | \
		PIPE_CONTROL_FLUSH_ENABLE | \
		PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE | \
		PIPE_CONTROL_DC_FLUSH_ENABLE)

static u32 preparser_disable(bool state)
{
	return MI_ARB_CHECK | BIT(8) | state;
}

static int emit_aux_table_inv(struct xe_gt *gt, struct xe_reg reg,
			      u32 *dw, int i)
{
	dw[i++] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1) | MI_LRI_MMIO_REMAP_EN;
	dw[i++] = reg.addr + gt->mmio.adj_offset;
	dw[i++] = AUX_INV;
	dw[i++] = MI_NOOP;

	return i;
}

static int emit_user_interrupt(u32 *dw, int i)
{
	dw[i++] = MI_USER_INTERRUPT;
	dw[i++] = MI_ARB_ON_OFF | MI_ARB_ENABLE;
	dw[i++] = MI_ARB_CHECK;

	return i;
}

static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i)
{
	dw[i++] = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
	dw[i++] = addr;
	dw[i++] = 0;
	dw[i++] = value;

	return i;
}

static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb,
			       u32 *dw, int i)
{
	dw[i++] = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW |
		(invalidate_tlb ? MI_INVALIDATE_TLB : 0);
	dw[i++] = addr | MI_FLUSH_DW_USE_GTT;
	dw[i++] = 0;
	dw[i++] = value;

	return i;
}

static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i)
{
	dw[i++] = MI_BATCH_BUFFER_START | ppgtt_flag | XE_INSTR_NUM_DW(3);
	dw[i++] = lower_32_bits(batch_addr);
	dw[i++] = upper_32_bits(batch_addr);

	return i;
}

static int emit_flush_invalidate(u32 flag, u32 *dw, int i)
{
	dw[i] = MI_FLUSH_DW;
	dw[i] |= flag;
	dw[i++] |= MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW |
		MI_FLUSH_DW_STORE_INDEX;

	dw[i++] = LRC_PPHWSP_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT;
	dw[i++] = 0;
	dw[i++] = ~0U;

	return i;
}

static int
emit_pipe_control(u32 *dw, int i, u32 bit_group_0, u32 bit_group_1, u32 offset, u32 value)
{
	dw[i++] = GFX_OP_PIPE_CONTROL(6) | bit_group_0;
	dw[i++] = bit_group_1;
	dw[i++] = offset;
	dw[i++] = 0;
	dw[i++] = value;
	dw[i++] = 0;

	return i;
}

static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
				int i)
{
	u32 flags = PIPE_CONTROL_CS_STALL |
		PIPE_CONTROL_COMMAND_CACHE_INVALIDATE |
		PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE |
		PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
		PIPE_CONTROL_VF_CACHE_INVALIDATE |
		PIPE_CONTROL_CONST_CACHE_INVALIDATE |
		PIPE_CONTROL_STATE_CACHE_INVALIDATE |
		PIPE_CONTROL_QW_WRITE |
		PIPE_CONTROL_STORE_DATA_INDEX;

	if (invalidate_tlb)
		flags |= PIPE_CONTROL_TLB_INVALIDATE;

	flags &= ~mask_flags;

	return emit_pipe_control(dw, i, 0, flags, LRC_PPHWSP_SCRATCH_ADDR, 0);
}

static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
				       u32 *dw, int i)
{
	dw[i++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(1);
	dw[i++] = lower_32_bits(addr);
	dw[i++] = upper_32_bits(addr);
	dw[i++] = lower_32_bits(value);
	dw[i++] = upper_32_bits(value);

	return i;
}

static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
{
	struct xe_gt *gt = job->q->gt;
	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
	u32 flags;

	flags = (PIPE_CONTROL_CS_STALL |
		 PIPE_CONTROL_TILE_CACHE_FLUSH |
		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
		 PIPE_CONTROL_DC_FLUSH_ENABLE |
		 PIPE_CONTROL_FLUSH_ENABLE);

	if (XE_WA(gt, 1409600907))
		flags |= PIPE_CONTROL_DEPTH_STALL;

	if (lacks_render)
		flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
	else if (job->q->class == XE_ENGINE_CLASS_COMPUTE)
		flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;

	return emit_pipe_control(dw, i, PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags, 0, 0);
}

static int emit_pipe_control_to_ring_end(struct xe_hw_engine *hwe, u32 *dw, int i)
{
	if (hwe->class != XE_ENGINE_CLASS_RENDER)
		return i;

	if (XE_WA(hwe->gt, 16020292621))
		i = emit_pipe_control(dw, i, 0, PIPE_CONTROL_LRI_POST_SYNC,
				      RING_NOPID(hwe->mmio_base).addr, 0);

	return i;
}

static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw,
			      int i)
{
	u32 flags = PIPE_CONTROL_CS_STALL | PIPE_CONTROL_GLOBAL_GTT_IVB |
		    PIPE_CONTROL_QW_WRITE;

	if (!stall_only)
		flags |= PIPE_CONTROL_FLUSH_ENABLE;

	return emit_pipe_control(dw, i, 0, flags, addr, value);
}

static u32 get_ppgtt_flag(struct xe_sched_job *job)
{
	return job->q->vm ? BIT(8) : 0;
}

/* for engines that don't require any special HW handling (no EUs, no aux inval, etc) */
static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc,
				    u64 batch_addr, u32 seqno)
{
	u32 dw[MAX_JOB_SIZE_DW], i = 0;
	u32 ppgtt_flag = get_ppgtt_flag(job);
	struct xe_vm *vm = job->q->vm;
	struct xe_gt *gt = job->q->gt;

	if (vm && vm->batch_invalidate_tlb) {
		dw[i++] = preparser_disable(true);
		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
					seqno, true, dw, i);
		dw[i++] = preparser_disable(false);
	} else {
		i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
					seqno, dw, i);
	}

	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);

	if (job->user_fence.used)
		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
						job->user_fence.value,
						dw, i);

	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);

	i = emit_user_interrupt(dw, i);

	xe_gt_assert(gt, i <= MAX_JOB_SIZE_DW);

	xe_lrc_write_ring(lrc, dw, i * sizeof(*dw));
}

static bool has_aux_ccs(struct xe_device *xe)
{
	/*
	 * PVC is a special case that has no compression of either type
	 * (FlatCCS or AuxCCS).  Also, AuxCCS is no longer used from Xe2
	 * onward, so any future platforms with no FlatCCS will not have
	 * AuxCCS either.
	 */
	if (GRAPHICS_VER(xe) >= 20 || xe->info.platform == XE_PVC)
		return false;

	return !xe->info.has_flat_ccs;
}

static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
				   u64 batch_addr, u32 seqno)
{
	u32 dw[MAX_JOB_SIZE_DW], i = 0;
	u32 ppgtt_flag = get_ppgtt_flag(job);
	struct xe_gt *gt = job->q->gt;
	struct xe_device *xe = gt_to_xe(gt);
	bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
	struct xe_vm *vm = job->q->vm;

	dw[i++] = preparser_disable(true);

	/* hsdes: 1809175790 */
	if (has_aux_ccs(xe)) {
		if (decode)
			i = emit_aux_table_inv(gt, VD0_AUX_INV, dw, i);
		else
			i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i);
	}

	if (vm && vm->batch_invalidate_tlb)
		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
					seqno, true, dw, i);

	dw[i++] = preparser_disable(false);

	if (!vm || !vm->batch_invalidate_tlb)
		i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
					seqno, dw, i);

	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);

	if (job->user_fence.used)
		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
						job->user_fence.value,
						dw, i);

	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);

	i = emit_user_interrupt(dw, i);

	xe_gt_assert(gt, i <= MAX_JOB_SIZE_DW);

	xe_lrc_write_ring(lrc, dw, i * sizeof(*dw));
}

static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
					    struct xe_lrc *lrc,
					    u64 batch_addr, u32 seqno)
{
	u32 dw[MAX_JOB_SIZE_DW], i = 0;
	u32 ppgtt_flag = get_ppgtt_flag(job);
	struct xe_gt *gt = job->q->gt;
	struct xe_device *xe = gt_to_xe(gt);
	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
	struct xe_vm *vm = job->q->vm;
	u32 mask_flags = 0;

	dw[i++] = preparser_disable(true);
	if (lacks_render)
		mask_flags = PIPE_CONTROL_3D_ARCH_FLAGS;
	else if (job->q->class == XE_ENGINE_CLASS_COMPUTE)
		mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS;

	/* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */
	i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i);

	/* hsdes: 1809175790 */
	if (has_aux_ccs(xe))
		i = emit_aux_table_inv(gt, CCS_AUX_INV, dw, i);

	dw[i++] = preparser_disable(false);

	i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
				seqno, dw, i);

	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);

	i = emit_render_cache_flush(job, dw, i);

	if (job->user_fence.used)
		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
						job->user_fence.value,
						dw, i);

	i = emit_pipe_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, lacks_render, dw, i);

	i = emit_user_interrupt(dw, i);

	i = emit_pipe_control_to_ring_end(job->q->hwe, dw, i);

	xe_gt_assert(gt, i <= MAX_JOB_SIZE_DW);

	xe_lrc_write_ring(lrc, dw, i * sizeof(*dw));
}

static void emit_migration_job_gen12(struct xe_sched_job *job,
				     struct xe_lrc *lrc, u32 seqno)
{
	u32 dw[MAX_JOB_SIZE_DW], i = 0;

	i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
				seqno, dw, i);

	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */

	i = emit_bb_start(job->batch_addr[0], BIT(8), dw, i);

	/* XXX: Do we need this? Leaving for now. */
	dw[i++] = preparser_disable(true);
	i = emit_flush_invalidate(0, dw, i);
	dw[i++] = preparser_disable(false);

	i = emit_bb_start(job->batch_addr[1], BIT(8), dw, i);

	dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | job->migrate_flush_flags |
		MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW;
	dw[i++] = xe_lrc_seqno_ggtt_addr(lrc) | MI_FLUSH_DW_USE_GTT;
	dw[i++] = 0;
	dw[i++] = seqno; /* value */

	i = emit_user_interrupt(dw, i);

	xe_gt_assert(job->q->gt, i <= MAX_JOB_SIZE_DW);

	xe_lrc_write_ring(lrc, dw, i * sizeof(*dw));
}

static void emit_job_gen12_gsc(struct xe_sched_job *job)
{
	struct xe_gt *gt = job->q->gt;

	xe_gt_assert(gt, job->q->width <= 1); /* no parallel submission for GSCCS */

	__emit_job_gen12_simple(job, job->q->lrc,
				job->batch_addr[0],
				xe_sched_job_seqno(job));
}

static void emit_job_gen12_copy(struct xe_sched_job *job)
{
	int i;

	if (xe_sched_job_is_migration(job->q)) {
		emit_migration_job_gen12(job, job->q->lrc,
					 xe_sched_job_seqno(job));
		return;
	}

	for (i = 0; i < job->q->width; ++i)
		__emit_job_gen12_simple(job, job->q->lrc + i,
				        job->batch_addr[i],
				        xe_sched_job_seqno(job));
}

static void emit_job_gen12_video(struct xe_sched_job *job)
{
	int i;

	/* FIXME: Not doing parallel handshake for now */
	for (i = 0; i < job->q->width; ++i)
		__emit_job_gen12_video(job, job->q->lrc + i,
				       job->batch_addr[i],
				       xe_sched_job_seqno(job));
}

static void emit_job_gen12_render_compute(struct xe_sched_job *job)
{
	int i;

	for (i = 0; i < job->q->width; ++i)
		__emit_job_gen12_render_compute(job, job->q->lrc + i,
						job->batch_addr[i],
						xe_sched_job_seqno(job));
}

static const struct xe_ring_ops ring_ops_gen12_gsc = {
	.emit_job = emit_job_gen12_gsc,
};

static const struct xe_ring_ops ring_ops_gen12_copy = {
	.emit_job = emit_job_gen12_copy,
};

static const struct xe_ring_ops ring_ops_gen12_video = {
	.emit_job = emit_job_gen12_video,
};

static const struct xe_ring_ops ring_ops_gen12_render_compute = {
	.emit_job = emit_job_gen12_render_compute,
};

const struct xe_ring_ops *
xe_ring_ops_get(struct xe_gt *gt, enum xe_engine_class class)
{
	switch (class) {
	case XE_ENGINE_CLASS_OTHER:
		return &ring_ops_gen12_gsc;
	case XE_ENGINE_CLASS_COPY:
		return &ring_ops_gen12_copy;
	case XE_ENGINE_CLASS_VIDEO_DECODE:
	case XE_ENGINE_CLASS_VIDEO_ENHANCE:
		return &ring_ops_gen12_video;
	case XE_ENGINE_CLASS_RENDER:
	case XE_ENGINE_CLASS_COMPUTE:
		return &ring_ops_gen12_render_compute;
	default:
		return NULL;
	}
}