summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
blob: b1969f2b2038db79af8447fc9826ba8257207cf4 (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
/*
 * Copyright 2014 Advanced Micro Devices, 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:
 *    Christian König <christian.koenig@amd.com>
 */

#include <linux/firmware.h>
#include <linux/module.h>
#include <linux/mmu_notifier.h>
#include <drm/drmP.h>
#include <drm/drm.h>

#include "amdgpu.h"

struct amdgpu_mn {
	/* constant after initialisation */
	struct amdgpu_device	*adev;
	struct mm_struct	*mm;
	struct mmu_notifier	mn;

	/* only used on destruction */
	struct work_struct	work;

	/* protected by adev->mn_lock */
	struct hlist_node	node;

	/* objects protected by lock */
	struct mutex		lock;
	struct rb_root		objects;
};

struct amdgpu_mn_node {
	struct interval_tree_node	it;
	struct list_head		bos;
};

/**
 * amdgpu_mn_destroy - destroy the rmn
 *
 * @work: previously sheduled work item
 *
 * Lazy destroys the notifier from a work item
 */
static void amdgpu_mn_destroy(struct work_struct *work)
{
	struct amdgpu_mn *rmn = container_of(work, struct amdgpu_mn, work);
	struct amdgpu_device *adev = rmn->adev;
	struct amdgpu_mn_node *node, *next_node;
	struct amdgpu_bo *bo, *next_bo;

	mutex_lock(&adev->mn_lock);
	mutex_lock(&rmn->lock);
	hash_del(&rmn->node);
	rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects,
					     it.rb) {

		interval_tree_remove(&node->it, &rmn->objects);
		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
			bo->mn = NULL;
			list_del_init(&bo->mn_list);
		}
		kfree(node);
	}
	mutex_unlock(&rmn->lock);
	mutex_unlock(&adev->mn_lock);
	mmu_notifier_unregister(&rmn->mn, rmn->mm);
	kfree(rmn);
}

/**
 * amdgpu_mn_release - callback to notify about mm destruction
 *
 * @mn: our notifier
 * @mn: the mm this callback is about
 *
 * Shedule a work item to lazy destroy our notifier.
 */
static void amdgpu_mn_release(struct mmu_notifier *mn,
			      struct mm_struct *mm)
{
	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
	INIT_WORK(&rmn->work, amdgpu_mn_destroy);
	schedule_work(&rmn->work);
}

/**
 * amdgpu_mn_invalidate_range_start - callback to notify about mm change
 *
 * @mn: our notifier
 * @mn: the mm this callback is about
 * @start: start of updated range
 * @end: end of updated range
 *
 * We block for all BOs between start and end to be idle and
 * unmap them by move them into system domain again.
 */
static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
					     struct mm_struct *mm,
					     unsigned long start,
					     unsigned long end)
{
	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
	struct interval_tree_node *it;

	/* notification is exclusive, but interval is inclusive */
	end -= 1;

	mutex_lock(&rmn->lock);

	it = interval_tree_iter_first(&rmn->objects, start, end);
	while (it) {
		struct amdgpu_mn_node *node;
		struct amdgpu_bo *bo;
		long r;

		node = container_of(it, struct amdgpu_mn_node, it);
		it = interval_tree_iter_next(it, start, end);

		list_for_each_entry(bo, &node->bos, mn_list) {

			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
				continue;

			r = amdgpu_bo_reserve(bo, true);
			if (r) {
				DRM_ERROR("(%ld) failed to reserve user bo\n", r);
				continue;
			}

			r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
				true, false, MAX_SCHEDULE_TIMEOUT);
			if (r <= 0)
				DRM_ERROR("(%ld) failed to wait for user bo\n", r);

			amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
			r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
			if (r)
				DRM_ERROR("(%ld) failed to validate user bo\n", r);

			amdgpu_bo_unreserve(bo);
		}
	}

	mutex_unlock(&rmn->lock);
}

static const struct mmu_notifier_ops amdgpu_mn_ops = {
	.release = amdgpu_mn_release,
	.invalidate_range_start = amdgpu_mn_invalidate_range_start,
};

/**
 * amdgpu_mn_get - create notifier context
 *
 * @adev: amdgpu device pointer
 *
 * Creates a notifier context for current->mm.
 */
static struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
{
	struct mm_struct *mm = current->mm;
	struct amdgpu_mn *rmn;
	int r;

	down_write(&mm->mmap_sem);
	mutex_lock(&adev->mn_lock);

	hash_for_each_possible(adev->mn_hash, rmn, node, (unsigned long)mm)
		if (rmn->mm == mm)
			goto release_locks;

	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
	if (!rmn) {
		rmn = ERR_PTR(-ENOMEM);
		goto release_locks;
	}

	rmn->adev = adev;
	rmn->mm = mm;
	rmn->mn.ops = &amdgpu_mn_ops;
	mutex_init(&rmn->lock);
	rmn->objects = RB_ROOT;

	r = __mmu_notifier_register(&rmn->mn, mm);
	if (r)
		goto free_rmn;

	hash_add(adev->mn_hash, &rmn->node, (unsigned long)mm);

release_locks:
	mutex_unlock(&adev->mn_lock);
	up_write(&mm->mmap_sem);

	return rmn;

free_rmn:
	mutex_unlock(&adev->mn_lock);
	up_write(&mm->mmap_sem);
	kfree(rmn);

	return ERR_PTR(r);
}

/**
 * amdgpu_mn_register - register a BO for notifier updates
 *
 * @bo: amdgpu buffer object
 * @addr: userptr addr we should monitor
 *
 * Registers an MMU notifier for the given BO at the specified address.
 * Returns 0 on success, -ERRNO if anything goes wrong.
 */
int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
{
	unsigned long end = addr + amdgpu_bo_size(bo) - 1;
	struct amdgpu_device *adev = bo->adev;
	struct amdgpu_mn *rmn;
	struct amdgpu_mn_node *node = NULL;
	struct list_head bos;
	struct interval_tree_node *it;

	rmn = amdgpu_mn_get(adev);
	if (IS_ERR(rmn))
		return PTR_ERR(rmn);

	INIT_LIST_HEAD(&bos);

	mutex_lock(&rmn->lock);

	while ((it = interval_tree_iter_first(&rmn->objects, addr, end))) {
		kfree(node);
		node = container_of(it, struct amdgpu_mn_node, it);
		interval_tree_remove(&node->it, &rmn->objects);
		addr = min(it->start, addr);
		end = max(it->last, end);
		list_splice(&node->bos, &bos);
	}

	if (!node) {
		node = kmalloc(sizeof(struct amdgpu_mn_node), GFP_KERNEL);
		if (!node) {
			mutex_unlock(&rmn->lock);
			return -ENOMEM;
		}
	}

	bo->mn = rmn;

	node->it.start = addr;
	node->it.last = end;
	INIT_LIST_HEAD(&node->bos);
	list_splice(&bos, &node->bos);
	list_add(&bo->mn_list, &node->bos);

	interval_tree_insert(&node->it, &rmn->objects);

	mutex_unlock(&rmn->lock);

	return 0;
}

/**
 * amdgpu_mn_unregister - unregister a BO for notifier updates
 *
 * @bo: amdgpu buffer object
 *
 * Remove any registration of MMU notifier updates from the buffer object.
 */
void amdgpu_mn_unregister(struct amdgpu_bo *bo)
{
	struct amdgpu_device *adev = bo->adev;
	struct amdgpu_mn *rmn;
	struct list_head *head;

	mutex_lock(&adev->mn_lock);
	rmn = bo->mn;
	if (rmn == NULL) {
		mutex_unlock(&adev->mn_lock);
		return;
	}

	mutex_lock(&rmn->lock);
	/* save the next list entry for later */
	head = bo->mn_list.next;

	bo->mn = NULL;
	list_del(&bo->mn_list);

	if (list_empty(head)) {
		struct amdgpu_mn_node *node;
		node = container_of(head, struct amdgpu_mn_node, bos);
		interval_tree_remove(&node->it, &rmn->objects);
		kfree(node);
	}

	mutex_unlock(&rmn->lock);
	mutex_unlock(&adev->mn_lock);
}
OpenPOWER on IntegriCloud