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
|
/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2019 Intel Corporation
*/
#include "gem/i915_gem_context.h"
#include "gem/i915_gem_pm.h"
#include "i915_drv.h"
#include "i915_globals.h"
#include "intel_context.h"
#include "intel_engine.h"
#include "intel_engine_pm.h"
#include "intel_ring.h"
static struct i915_global_context {
struct i915_global base;
struct kmem_cache *slab_ce;
} global;
static struct intel_context *intel_context_alloc(void)
{
return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL);
}
void intel_context_free(struct intel_context *ce)
{
kmem_cache_free(global.slab_ce, ce);
}
struct intel_context *
intel_context_create(struct intel_engine_cs *engine)
{
struct intel_context *ce;
ce = intel_context_alloc();
if (!ce)
return ERR_PTR(-ENOMEM);
intel_context_init(ce, engine);
return ce;
}
int intel_context_alloc_state(struct intel_context *ce)
{
int err = 0;
if (mutex_lock_interruptible(&ce->pin_mutex))
return -EINTR;
if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
if (intel_context_is_banned(ce)) {
err = -EIO;
goto unlock;
}
err = ce->ops->alloc(ce);
if (unlikely(err))
goto unlock;
set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
}
unlock:
mutex_unlock(&ce->pin_mutex);
return err;
}
static int intel_context_active_acquire(struct intel_context *ce)
{
int err;
__i915_active_acquire(&ce->active);
if (intel_context_is_barrier(ce))
return 0;
/* Preallocate tracking nodes */
err = i915_active_acquire_preallocate_barrier(&ce->active,
ce->engine);
if (err)
i915_active_release(&ce->active);
return err;
}
static void intel_context_active_release(struct intel_context *ce)
{
/* Nodes preallocated in intel_context_active() */
i915_active_acquire_barrier(&ce->active);
i915_active_release(&ce->active);
}
int __intel_context_do_pin(struct intel_context *ce)
{
int err;
if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
err = intel_context_alloc_state(ce);
if (err)
return err;
}
err = i915_active_acquire(&ce->active);
if (err)
return err;
if (mutex_lock_interruptible(&ce->pin_mutex)) {
err = -EINTR;
goto out_release;
}
if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) {
err = intel_context_active_acquire(ce);
if (unlikely(err))
goto out_unlock;
err = ce->ops->pin(ce);
if (unlikely(err))
goto err_active;
CE_TRACE(ce, "pin ring:{start:%08x, head:%04x, tail:%04x}\n",
i915_ggtt_offset(ce->ring->vma),
ce->ring->head, ce->ring->tail);
smp_mb__before_atomic(); /* flush pin before it is visible */
atomic_inc(&ce->pin_count);
}
GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */
GEM_BUG_ON(i915_active_is_idle(&ce->active));
goto out_unlock;
err_active:
intel_context_active_release(ce);
out_unlock:
mutex_unlock(&ce->pin_mutex);
out_release:
i915_active_release(&ce->active);
return err;
}
void intel_context_unpin(struct intel_context *ce)
{
if (!atomic_dec_and_test(&ce->pin_count))
return;
CE_TRACE(ce, "unpin\n");
ce->ops->unpin(ce);
/*
* Once released, we may asynchronously drop the active reference.
* As that may be the only reference keeping the context alive,
* take an extra now so that it is not freed before we finish
* dereferencing it.
*/
intel_context_get(ce);
intel_context_active_release(ce);
intel_context_put(ce);
}
static int __context_pin_state(struct i915_vma *vma)
{
unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
int err;
err = i915_ggtt_pin(vma, 0, bias | PIN_HIGH);
if (err)
return err;
err = i915_active_acquire(&vma->active);
if (err)
goto err_unpin;
/*
* And mark it as a globally pinned object to let the shrinker know
* it cannot reclaim the object until we release it.
*/
i915_vma_make_unshrinkable(vma);
vma->obj->mm.dirty = true;
return 0;
err_unpin:
i915_vma_unpin(vma);
return err;
}
static void __context_unpin_state(struct i915_vma *vma)
{
i915_vma_make_shrinkable(vma);
i915_active_release(&vma->active);
__i915_vma_unpin(vma);
}
static int __ring_active(struct intel_ring *ring)
{
int err;
err = i915_active_acquire(&ring->vma->active);
if (err)
return err;
err = intel_ring_pin(ring);
if (err)
goto err_active;
return 0;
err_active:
i915_active_release(&ring->vma->active);
return err;
}
static void __ring_retire(struct intel_ring *ring)
{
intel_ring_unpin(ring);
i915_active_release(&ring->vma->active);
}
__i915_active_call
static void __intel_context_retire(struct i915_active *active)
{
struct intel_context *ce = container_of(active, typeof(*ce), active);
CE_TRACE(ce, "retire runtime: { total:%lluns, avg:%lluns }\n",
intel_context_get_total_runtime_ns(ce),
intel_context_get_avg_runtime_ns(ce));
set_bit(CONTEXT_VALID_BIT, &ce->flags);
if (ce->state)
__context_unpin_state(ce->state);
intel_timeline_unpin(ce->timeline);
__ring_retire(ce->ring);
intel_context_put(ce);
}
static int __intel_context_active(struct i915_active *active)
{
struct intel_context *ce = container_of(active, typeof(*ce), active);
int err;
CE_TRACE(ce, "active\n");
intel_context_get(ce);
err = __ring_active(ce->ring);
if (err)
goto err_put;
err = intel_timeline_pin(ce->timeline);
if (err)
goto err_ring;
if (!ce->state)
return 0;
err = __context_pin_state(ce->state);
if (err)
goto err_timeline;
return 0;
err_timeline:
intel_timeline_unpin(ce->timeline);
err_ring:
__ring_retire(ce->ring);
err_put:
intel_context_put(ce);
return err;
}
void
intel_context_init(struct intel_context *ce,
struct intel_engine_cs *engine)
{
GEM_BUG_ON(!engine->cops);
GEM_BUG_ON(!engine->gt->vm);
kref_init(&ce->ref);
ce->engine = engine;
ce->ops = engine->cops;
ce->sseu = engine->sseu;
ce->ring = __intel_context_ring_size(SZ_4K);
ewma_runtime_init(&ce->runtime.avg);
ce->vm = i915_vm_get(engine->gt->vm);
INIT_LIST_HEAD(&ce->signal_link);
INIT_LIST_HEAD(&ce->signals);
mutex_init(&ce->pin_mutex);
i915_active_init(&ce->active,
__intel_context_active, __intel_context_retire);
}
void intel_context_fini(struct intel_context *ce)
{
if (ce->timeline)
intel_timeline_put(ce->timeline);
i915_vm_put(ce->vm);
mutex_destroy(&ce->pin_mutex);
i915_active_fini(&ce->active);
}
static void i915_global_context_shrink(void)
{
kmem_cache_shrink(global.slab_ce);
}
static void i915_global_context_exit(void)
{
kmem_cache_destroy(global.slab_ce);
}
static struct i915_global_context global = { {
|