summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
blob: 8bf84efafb049cd693e156a8dbf2dff396c70164 (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
/*
 * Copyright 2011 Red Hat Inc.
 * 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 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
 * THE COPYRIGHT HOLDERS, AUTHORS 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.
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 */
/*
 * Authors:
 *    Jerome Glisse <glisse@freedesktop.org>
 */
/* Algorithm:
 *
 * We store the last allocated bo in "hole", we always try to allocate
 * after the last allocated bo. Principle is that in a linear GPU ring
 * progression was is after last is the oldest bo we allocated and thus
 * the first one that should no longer be in use by the GPU.
 *
 * If it's not the case we skip over the bo after last to the closest
 * done bo if such one exist. If none exist and we are not asked to
 * block we report failure to allocate.
 *
 * If we are asked to block we wait on all the oldest fence of all
 * rings. We just wait for any of those fence to complete.
 */
#include <drm/drmP.h>
#include "amdgpu.h"

static void amdgpu_sa_bo_remove_locked(struct amdgpu_sa_bo *sa_bo);
static void amdgpu_sa_bo_try_free(struct amdgpu_sa_manager *sa_manager);

int amdgpu_sa_bo_manager_init(struct amdgpu_device *adev,
			      struct amdgpu_sa_manager *sa_manager,
			      unsigned size, u32 align, u32 domain)
{
	int i, r;

	init_waitqueue_head(&sa_manager->wq);
	sa_manager->bo = NULL;
	sa_manager->size = size;
	sa_manager->domain = domain;
	sa_manager->align = align;
	sa_manager->hole = &sa_manager->olist;
	INIT_LIST_HEAD(&sa_manager->olist);
	for (i = 0; i < AMDGPU_SA_NUM_FENCE_LISTS; ++i)
		INIT_LIST_HEAD(&sa_manager->flist[i]);

	r = amdgpu_bo_create(adev, size, align, true, domain,
			     0, NULL, NULL, &sa_manager->bo);
	if (r) {
		dev_err(adev->dev, "(%d) failed to allocate bo for manager\n", r);
		return r;
	}

	return r;
}

void amdgpu_sa_bo_manager_fini(struct amdgpu_device *adev,
			       struct amdgpu_sa_manager *sa_manager)
{
	struct amdgpu_sa_bo *sa_bo, *tmp;

	if (!list_empty(&sa_manager->olist)) {
		sa_manager->hole = &sa_manager->olist,
		amdgpu_sa_bo_try_free(sa_manager);
		if (!list_empty(&sa_manager->olist)) {
			dev_err(adev->dev, "sa_manager is not empty, clearing anyway\n");
		}
	}
	list_for_each_entry_safe(sa_bo, tmp, &sa_manager->olist, olist) {
		amdgpu_sa_bo_remove_locked(sa_bo);
	}
	amdgpu_bo_unref(&sa_manager->bo);
	sa_manager->size = 0;
}

int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev,
			       struct amdgpu_sa_manager *sa_manager)
{
	int r;

	if (sa_manager->bo == NULL) {
		dev_err(adev->dev, "no bo for sa manager\n");
		return -EINVAL;
	}

	/* map the buffer */
	r = amdgpu_bo_reserve(sa_manager->bo, false);
	if (r) {
		dev_err(adev->dev, "(%d) failed to reserve manager bo\n", r);
		return r;
	}
	r = amdgpu_bo_pin(sa_manager->bo, sa_manager->domain, &sa_manager->gpu_addr);
	if (r) {
		amdgpu_bo_unreserve(sa_manager->bo);
		dev_err(adev->dev, "(%d) failed to pin manager bo\n", r);
		return r;
	}
	r = amdgpu_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
	amdgpu_bo_unreserve(sa_manager->bo);
	return r;
}

int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev,
				 struct amdgpu_sa_manager *sa_manager)
{
	int r;

	if (sa_manager->bo == NULL) {
		dev_err(adev->dev, "no bo for sa manager\n");
		return -EINVAL;
	}

	r = amdgpu_bo_reserve(sa_manager->bo, false);
	if (!r) {
		amdgpu_bo_kunmap(sa_manager->bo);
		amdgpu_bo_unpin(sa_manager->bo);
		amdgpu_bo_unreserve(sa_manager->bo);
	}
	return r;
}

static void amdgpu_sa_bo_remove_locked(struct amdgpu_sa_bo *sa_bo)
{
	struct amdgpu_sa_manager *sa_manager = sa_bo->manager;
	if (sa_manager->hole == &sa_bo->olist) {
		sa_manager->hole = sa_bo->olist.prev;
	}
	list_del_init(&sa_bo->olist);
	list_del_init(&sa_bo->flist);
	fence_put(sa_bo->fence);
	kfree(sa_bo);
}

static void amdgpu_sa_bo_try_free(struct amdgpu_sa_manager *sa_manager)
{
	struct amdgpu_sa_bo *sa_bo, *tmp;

	if (sa_manager->hole->next == &sa_manager->olist)
		return;

	sa_bo = list_entry(sa_manager->hole->next, struct amdgpu_sa_bo, olist);
	list_for_each_entry_safe_from(sa_bo, tmp, &sa_manager->olist, olist) {
		if (sa_bo->fence == NULL ||
		    !fence_is_signaled(sa_bo->fence)) {
			return;
		}
		amdgpu_sa_bo_remove_locked(sa_bo);
	}
}

static inline unsigned amdgpu_sa_bo_hole_soffset(struct amdgpu_sa_manager *sa_manager)
{
	struct list_head *hole = sa_manager->hole;

	if (hole != &sa_manager->olist) {
		return list_entry(hole, struct amdgpu_sa_bo, olist)->eoffset;
	}
	return 0;
}

static inline unsigned amdgpu_sa_bo_hole_eoffset(struct amdgpu_sa_manager *sa_manager)
{
	struct list_head *hole = sa_manager->hole;

	if (hole->next != &sa_manager->olist) {
		return list_entry(hole->next, struct amdgpu_sa_bo, olist)->soffset;
	}
	return sa_manager->size;
}

static bool amdgpu_sa_bo_try_alloc(struct amdgpu_sa_manager *sa_manager,
				   struct amdgpu_sa_bo *sa_bo,
				   unsigned size, unsigned align)
{
	unsigned soffset, eoffset, wasted;

	soffset = amdgpu_sa_bo_hole_soffset(sa_manager);
	eoffset = amdgpu_sa_bo_hole_eoffset(sa_manager);
	wasted = (align - (soffset % align)) % align;

	if ((eoffset - soffset) >= (size + wasted)) {
		soffset += wasted;

		sa_bo->manager = sa_manager;
		sa_bo->soffset = soffset;
		sa_bo->eoffset = soffset + size;
		list_add(&sa_bo->olist, sa_manager->hole);
		INIT_LIST_HEAD(&sa_bo->flist);
		sa_manager->hole = &sa_bo->olist;
		return true;
	}
	return false;
}

/**
 * amdgpu_sa_event - Check if we can stop waiting
 *
 * @sa_manager: pointer to the sa_manager
 * @size: number of bytes we want to allocate
 * @align: alignment we need to match
 *
 * Check if either there is a fence we can wait for or
 * enough free memory to satisfy the allocation directly
 */
static bool amdgpu_sa_event(struct amdgpu_sa_manager *sa_manager,
			    unsigned size, unsigned align)
{
	unsigned soffset, eoffset, wasted;
	int i;

	for (i = 0; i < AMDGPU_SA_NUM_FENCE_LISTS; ++i)
		if (!list_empty(&sa_manager->flist[i]))
			return true;

	soffset = amdgpu_sa_bo_hole_soffset(sa_manager);
	eoffset = amdgpu_sa_bo_hole_eoffset(sa_manager);
	wasted = (align - (soffset % align)) % align;

	if ((eoffset - soffset) >= (size + wasted)) {
		return true;
	}

	return false;
}

static bool amdgpu_sa_bo_next_hole(struct amdgpu_sa_manager *sa_manager,
				   struct fence **fences,
				   unsigned *tries)
{
	struct amdgpu_sa_bo *best_bo = NULL;
	unsigned i, soffset, best, tmp;

	/* if hole points to the end of the buffer */
	if (sa_manager->hole->next == &sa_manager->olist) {
		/* try again with its beginning */
		sa_manager->hole = &sa_manager->olist;
		return true;
	}

	soffset = amdgpu_sa_bo_hole_soffset(sa_manager);
	/* to handle wrap around we add sa_manager->size */
	best = sa_manager->size * 2;
	/* go over all fence list and try to find the closest sa_bo
	 * of the current last
	 */
	for (i = 0; i < AMDGPU_SA_NUM_FENCE_LISTS; ++i) {
		struct amdgpu_sa_bo *sa_bo;

		if (list_empty(&sa_manager->flist[i]))
			continue;

		sa_bo = list_first_entry(&sa_manager->flist[i],
					 struct amdgpu_sa_bo, flist);

		if (!fence_is_signaled(sa_bo->fence)) {
			fences[i] = sa_bo->fence;
			continue;
		}

		/* limit the number of tries each ring gets */
		if (tries[i] > 2) {
			continue;
		}

		tmp = sa_bo->soffset;
		if (tmp < soffset) {
			/* wrap around, pretend it's after */
			tmp += sa_manager->size;
		}
		tmp -= soffset;
		if (tmp < best) {
			/* this sa bo is the closest one */
			best = tmp;
			best_bo = sa_bo;
		}
	}

	if (best_bo) {
		uint32_t idx = best_bo->fence->context;

		idx %= AMDGPU_SA_NUM_FENCE_LISTS;
		++tries[idx];
		sa_manager->hole = best_bo->olist.prev;

		/* we knew that this one is signaled,
		   so it's save to remote it */
		amdgpu_sa_bo_remove_locked(best_bo);
		return true;
	}
	return false;
}

int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
		     struct amdgpu_sa_bo **sa_bo,
		     unsigned size, unsigned align)
{
	struct fence *fences[AMDGPU_SA_NUM_FENCE_LISTS];
	unsigned tries[AMDGPU_SA_NUM_FENCE_LISTS];
	unsigned count;
	int i, r;
	signed long t;

	if (WARN_ON_ONCE(align > sa_manager->align))
		return -EINVAL;

	if (WARN_ON_ONCE(size > sa_manager->size))
		return -EINVAL;

	*sa_bo = kmalloc(sizeof(struct amdgpu_sa_bo), GFP_KERNEL);
	if ((*sa_bo) == NULL) {
		return -ENOMEM;
	}
	(*sa_bo)->manager = sa_manager;
	(*sa_bo)->fence = NULL;
	INIT_LIST_HEAD(&(*sa_bo)->olist);
	INIT_LIST_HEAD(&(*sa_bo)->flist);

	spin_lock(&sa_manager->wq.lock);
	do {
		for (i = 0; i < AMDGPU_SA_NUM_FENCE_LISTS; ++i) {
			fences[i] = NULL;
			tries[i] = 0;
		}

		do {
			amdgpu_sa_bo_try_free(sa_manager);

			if (amdgpu_sa_bo_try_alloc(sa_manager, *sa_bo,
						   size, align)) {
				spin_unlock(&sa_manager->wq.lock);
				return 0;
			}

			/* see if we can skip over some allocations */
		} while (amdgpu_sa_bo_next_hole(sa_manager, fences, tries));

		for (i = 0, count = 0; i < AMDGPU_SA_NUM_FENCE_LISTS; ++i)
			if (fences[i])
				fences[count++] = fence_get(fences[i]);

		if (count) {
			spin_unlock(&sa_manager->wq.lock);
			t = fence_wait_any_timeout(fences, count, false,
						   MAX_SCHEDULE_TIMEOUT);
			for (i = 0; i < count; ++i)
				fence_put(fences[i]);

			r = (t > 0) ? 0 : t;
			spin_lock(&sa_manager->wq.lock);
		} else {
			/* if we have nothing to wait for block */
			r = wait_event_interruptible_locked(
				sa_manager->wq,
				amdgpu_sa_event(sa_manager, size, align)
			);
		}

	} while (!r);

	spin_unlock(&sa_manager->wq.lock);
	kfree(*sa_bo);
	*sa_bo = NULL;
	return r;
}

void amdgpu_sa_bo_free(struct amdgpu_device *adev, struct amdgpu_sa_bo **sa_bo,
		       struct fence *fence)
{
	struct amdgpu_sa_manager *sa_manager;

	if (sa_bo == NULL || *sa_bo == NULL) {
		return;
	}

	sa_manager = (*sa_bo)->manager;
	spin_lock(&sa_manager->wq.lock);
	if (fence && !fence_is_signaled(fence)) {
		uint32_t idx;

		(*sa_bo)->fence = fence_get(fence);
		idx = fence->context % AMDGPU_SA_NUM_FENCE_LISTS;
		list_add_tail(&(*sa_bo)->flist, &sa_manager->flist[idx]);
	} else {
		amdgpu_sa_bo_remove_locked(*sa_bo);
	}
	wake_up_all_locked(&sa_manager->wq);
	spin_unlock(&sa_manager->wq.lock);
	*sa_bo = NULL;
}

#if defined(CONFIG_DEBUG_FS)

void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
				  struct seq_file *m)
{
	struct amdgpu_sa_bo *i;

	spin_lock(&sa_manager->wq.lock);
	list_for_each_entry(i, &sa_manager->olist, olist) {
		uint64_t soffset = i->soffset + sa_manager->gpu_addr;
		uint64_t eoffset = i->eoffset + sa_manager->gpu_addr;
		if (&i->olist == sa_manager->hole) {
			seq_printf(m, ">");
		} else {
			seq_printf(m, " ");
		}
		seq_printf(m, "[0x%010llx 0x%010llx] size %8lld",
			   soffset, eoffset, eoffset - soffset);

		if (i->fence)
			seq_printf(m, " protected by 0x%08x on context %d",
				   i->fence->seqno, i->fence->context);

		seq_printf(m, "\n");
	}
	spin_unlock(&sa_manager->wq.lock);
}
#endif