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
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
|
#ifndef _INTEL_RINGBUFFER_H_
#define _INTEL_RINGBUFFER_H_
#include <linux/hashtable.h>
#include "i915_gem_batch_pool.h"
#include "i915_gem_request.h"
#include "i915_gem_timeline.h"
#define I915_CMD_HASH_ORDER 9
/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
* but keeps the logic simple. Indeed, the whole purpose of this macro is just
* to give some inclination as to some of the magic values used in the various
* workarounds!
*/
#define CACHELINE_BYTES 64
#define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(uint32_t))
/*
* Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
* Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
* Gen4+ BSpec "vol1c Memory Interface and Command Stream" / 5.3.4.5 "Ring Buffer Use"
*
* "If the Ring Buffer Head Pointer and the Tail Pointer are on the same
* cacheline, the Head Pointer must not be greater than the Tail
* Pointer."
*/
#define I915_RING_FREE_SPACE 64
struct intel_hw_status_page {
struct i915_vma *vma;
u32 *page_addr;
u32 ggtt_offset;
};
#define I915_READ_TAIL(engine) I915_READ(RING_TAIL((engine)->mmio_base))
#define I915_WRITE_TAIL(engine, val) I915_WRITE(RING_TAIL((engine)->mmio_base), val)
#define I915_READ_START(engine) I915_READ(RING_START((engine)->mmio_base))
#define I915_WRITE_START(engine, val) I915_WRITE(RING_START((engine)->mmio_base), val)
#define I915_READ_HEAD(engine) I915_READ(RING_HEAD((engine)->mmio_base))
#define I915_WRITE_HEAD(engine, val) I915_WRITE(RING_HEAD((engine)->mmio_base), val)
#define I915_READ_CTL(engine) I915_READ(RING_CTL((engine)->mmio_base))
#define I915_WRITE_CTL(engine, val) I915_WRITE(RING_CTL((engine)->mmio_base), val)
#define I915_READ_IMR(engine) I915_READ(RING_IMR((engine)->mmio_base))
#define I915_WRITE_IMR(engine, val) I915_WRITE(RING_IMR((engine)->mmio_base), val)
#define I915_READ_MODE(engine) I915_READ(RING_MI_MODE((engine)->mmio_base))
#define I915_WRITE_MODE(engine, val) I915_WRITE(RING_MI_MODE((engine)->mmio_base), val)
/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
* do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
*/
#define gen8_semaphore_seqno_size sizeof(uint64_t)
#define GEN8_SEMAPHORE_OFFSET(__from, __to) \
(((__from) * I915_NUM_ENGINES + (__to)) * gen8_semaphore_seqno_size)
#define GEN8_SIGNAL_OFFSET(__ring, to) \
(dev_priv->semaphore->node.start + \
GEN8_SEMAPHORE_OFFSET((__ring)->id, (to)))
#define GEN8_WAIT_OFFSET(__ring, from) \
(dev_priv->semaphore->node.start + \
GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
enum intel_engine_hangcheck_action {
ENGINE_IDLE = 0,
ENGINE_WAIT,
ENGINE_ACTIVE_SEQNO,
ENGINE_ACTIVE_HEAD,
ENGINE_ACTIVE_SUBUNITS,
ENGINE_WAIT_KICK,
ENGINE_DEAD,
};
static inline const char *
hangcheck_action_to_str(const enum intel_engine_hangcheck_action a)
{
switch (a) {
case ENGINE_IDLE:
return "idle";
case ENGINE_WAIT:
return "wait";
case ENGINE_ACTIVE_SEQNO:
return "active seqno";
case ENGINE_ACTIVE_HEAD:
return "active head";
case ENGINE_ACTIVE_SUBUNITS:
return "active subunits";
case ENGINE_WAIT_KICK:
return "wait kick";
case ENGINE_DEAD:
return "dead";
}
return "unknown";
}
#define I915_MAX_SLICES 3
#define I915_MAX_SUBSLICES 3
#define instdone_slice_mask(dev_priv__) \
(INTEL_GEN(dev_priv__) == 7 ? \
1 : INTEL_INFO(dev_priv__)->sseu.slice_mask)
#define instdone_subslice_mask(dev_priv__) \
(INTEL_GEN(dev_priv__) == 7 ? \
1 : INTEL_INFO(dev_priv__)->sseu.subslice_mask)
#define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \
for ((slice__) = 0, (subslice__) = 0; \
(slice__) < I915_MAX_SLICES; \
(subslice__) = ((subslice__) + 1) < I915_MAX_SUBSLICES ? (subslice__) + 1 : 0, \
(slice__) += ((subslice__) == 0)) \
for_each_if((BIT(slice__) & instdone_slice_mask(dev_priv__)) && \
(BIT(subslice__) & instdone_subslice_mask(dev_priv__)))
struct intel_instdone {
u32 instdone;
/* The following exist only in the RCS engine */
u32 slice_common;
u32 sampler[I915_MAX_SLICES][I915_MAX_SUBSLICES];
u32 row[I915_MAX_SLICES][I915_MAX_SUBSLICES];
};
struct intel_engine_hangcheck {
u64 acthd;
u32 seqno;
enum intel_engine_hangcheck_action action;
unsigned long action_timestamp;
int deadlock;
struct intel_instdone instdone;
bool stalled;
};
struct intel_ring {
struct i915_vma *vma;
void *vaddr;
struct intel_engine_cs *engine;
struct list_head request_list;
u32 head;
u32 tail;
int space;
int size;
int effective_size;
/** We track the position of the requests in the ring buffer, and
* when each is retired we increment last_retired_head as the GPU
* must have finished processing the request and so we know we
* can advance the ringbuffer up to that position.
*
* last_retired_head is set to -1 after the value is consumed so
* we can detect new retirements.
*/
u32 last_retired_head;
};
struct i915_gem_context;
struct drm_i915_reg_table;
/*
* we use a single page to load ctx workarounds so all of these
* values are referred in terms of dwords
*
* struct i915_wa_ctx_bb:
* offset: specifies batch starting position, also helpful in case
* if we want to have multiple batches at different offsets based on
* some criteria. It is not a requirement at the moment but provides
* an option for future use.
* size: size of the batch in DWORDS
*/
struct i915_ctx_workarounds {
struct i915_wa_ctx_bb {
u32 offset;
u32 size;
} indirect_ctx, per_ctx;
struct i915_vma *vma;
};
struct drm_i915_gem_request;
struct intel_render_state;
struct intel_engine_cs {
struct drm_i915_private *i915;
const char *name;
enum intel_engine_id {
RCS = 0,
BCS,
VCS,
VCS2, /* Keep instances of the same type engine together. */
VECS
} id;
#define _VCS(n) (VCS + (n))
unsigned int exec_id;
enum intel_engine_hw_id {
RCS_HW = 0,
VCS_HW,
BCS_HW,
VECS_HW,
VCS2_HW
} hw_id;
enum intel_engine_hw_id guc_id; /* XXX same as hw_id? */
u32 mmio_base;
unsigned int irq_shift;
struct intel_ring *buffer;
struct intel_timeline *timeline;
struct intel_render_state *render_state;
/* Rather than have every client wait upon all user interrupts,
* with the herd waking after every interrupt and each doing the
* heavyweight seqno dance, we delegate the task (of being the
* bottom-half of the user interrupt) to the first client. After
* every interrupt, we wake up one client, who does the heavyweight
* coherent seqno read and either goes back to sleep (if incomplete),
* or wakes up all the completed clients in parallel, before then
* transferring the bottom-half status to the next client in the queue.
*
* Compared to walking the entire list of waiters in a single dedicated
* bottom-half, we reduce the latency of the first waiter by avoiding
* a context switch, but incur additional coherent seqno reads when
* following the chain of request breadcrumbs. Since it is most likely
* that we have a single client waiting on each seqno, then reducing
* the overhead of waking that client is much preferred.
*/
struct intel_breadcrumbs {
struct task_struct __rcu *irq_seqno_bh; /* bh for interrupts */
bool irq_posted;
spinlock_t lock; /* protects the lists of requests; irqsafe */
struct rb_root waiters; /* sorted by retirement, priority */
struct rb_root signals; /* sorted by retirement */
struct intel_wait *first_wait; /* oldest waiter by retirement */
struct task_struct *signaler; /* used for fence signalling */
struct drm_i915_gem_request *first_signal;
struct timer_list fake_irq; /* used after a missed interrupt */
struct timer_list hangcheck; /* detect missed interrupts */
unsigned long timeout;
bool irq_enabled : 1;
bool rpm_wakelock : 1;
} breadcrumbs;
/*
* A pool of objects to use as shadow copies of client batch buffers
* when the command parser is enabled. Prevents the client from
* modifying the batch contents after software parsing.
*/
struct i915_gem_batch_pool batch_pool;
struct intel_hw_status_page status_page;
struct i915_ctx_workarounds wa_ctx;
struct i915_vma *scratch;
u32 irq_keep_mask; /* always keep these interrupts */
u32 irq_enable_mask; /* bitmask to enable ring interrupt */
void (*irq_enable)(struct intel_engine_cs *engine);
void (*irq_disable)(struct intel_engine_cs *engine);
int (*init_hw)(struct intel_engine_cs *engine);
void (*reset_hw)(struct intel_engine_cs *engine,
struct drm_i915_gem_request *req);
int (*context_pin)(struct intel_engine_cs *engine,
struct i915_gem_context *ctx);
void (*context_unpin)(struct intel_engine_cs *engine,
struct i915_gem_context *ctx);
int (*request_alloc)(struct drm_i915_gem_request *req);
int (*init_context)(struct drm_i915_gem_request *req);
int (*emit_flush)(struct drm_i915_gem_request *request,
u32 mode);
#define EMIT_INVALIDATE BIT(0)
#define EMIT_FLUSH BIT(1)
#define EMIT_BARRIER (EMIT_INVALIDATE | EMIT_FLUSH)
int (*emit_bb_start)(struct drm_i915_gem_request *req,
u64 offset, u32 length,
unsigned int dispatch_flags);
#define I915_DISPATCH_SECURE BIT(0)
#define I915_DISPATCH_PINNED BIT(1)
#define I915_DISPATCH_RS BIT(2)
void (*emit_breadcrumb)(struct drm_i915_gem_request *req,
u32 *out);
int emit_breadcrumb_sz;
/* Pass the request to the hardware queue (e.g. directly into
* the legacy ringbuffer or to the end of an execlist).
*
* This is called from an atomic context with irqs disabled; must
* be irq safe.
*/
void (*submit_request)(struct drm_i915_gem_request *req);
/* Call when the priority on a request has changed and it and its
* dependencies may need rescheduling. Note the request itself may
* not be ready to run!
*
* Called under the struct_mutex.
*/
void (*schedule)(struct drm_i915_gem_request *request,
int priority);
/* Some chipsets are not quite as coherent as advertised and need
* an expensive kick to force a true read of the up-to-date seqno.
* However, the up-to-date seqno is not always required and the last
* seen value is good enough. Note that the seqno will always be
* monotonic, even if not coherent.
*/
|