summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
blob: b5e28fa3f4144fccfe7db3a7e21181aaf0394e31 (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
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
/*
 * Copyright 2019 Advanced Micro Devices, Inc.
 *
 * 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, sublicense,
 * 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 above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * 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 NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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.
 *
 * based on nouveau_prime.c
 *
 * Authors: Alex Deucher
 */

/**
 * DOC: PRIME Buffer Sharing
 *
 * The following callback implementations are used for :ref:`sharing GEM buffer
 * objects between different devices via PRIME <prime_buffer_sharing>`.
 */

#include "amdgpu.h"
#include "amdgpu_display.h"
#include "amdgpu_gem.h"
#include "amdgpu_dma_buf.h"
#include "amdgpu_xgmi.h"
#include <drm/amdgpu_drm.h>
#include <drm/ttm/ttm_tt.h>
#include <linux/dma-buf.h>
#include <linux/dma-fence-array.h>
#include <linux/pci-p2pdma.h>
#include <linux/pm_runtime.h>

/**
 * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
 *
 * @dmabuf: DMA-buf where we attach to
 * @attach: attachment to add
 *
 * Add the attachment as user to the exported DMA-buf.
 */
static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
				 struct dma_buf_attachment *attach)
{
	struct drm_gem_object *obj = dmabuf->priv;
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	int r;

	if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
		attach->peer2peer = false;

	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
	if (r < 0)
		goto out;

	return 0;

out:
	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
	return r;
}

/**
 * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation
 *
 * @dmabuf: DMA-buf where we remove the attachment from
 * @attach: the attachment to remove
 *
 * Called when an attachment is removed from the DMA-buf.
 */
static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
				  struct dma_buf_attachment *attach)
{
	struct drm_gem_object *obj = dmabuf->priv;
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);

	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
}

/**
 * amdgpu_dma_buf_pin - &dma_buf_ops.pin implementation
 *
 * @attach: attachment to pin down
 *
 * Pin the BO which is backing the DMA-buf so that it can't move any more.
 */
static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
{
	struct drm_gem_object *obj = attach->dmabuf->priv;
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);

	/* pin buffer into GTT */
	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
}

/**
 * amdgpu_dma_buf_unpin - &dma_buf_ops.unpin implementation
 *
 * @attach: attachment to unpin
 *
 * Unpin a previously pinned BO to make it movable again.
 */
static void amdgpu_dma_buf_unpin(struct dma_buf_attachment *attach)
{
	struct drm_gem_object *obj = attach->dmabuf->priv;
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);

	amdgpu_bo_unpin(bo);
}

/**
 * amdgpu_dma_buf_map - &dma_buf_ops.map_dma_buf implementation
 * @attach: DMA-buf attachment
 * @dir: DMA direction
 *
 * Makes sure that the shared DMA buffer can be accessed by the target device.
 * For now, simply pins it to the GTT domain, where it should be accessible by
 * all DMA devices.
 *
 * Returns:
 * sg_table filled with the DMA addresses to use or ERR_PRT with negative error
 * code.
 */
static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
					   enum dma_data_direction dir)
{
	struct dma_buf *dma_buf = attach->dmabuf;
	struct drm_gem_object *obj = dma_buf->priv;
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct sg_table *sgt;
	long r;

	if (!bo->tbo.pin_count) {
		/* move buffer into GTT or VRAM */
		struct ttm_operation_ctx ctx = { false, false };
		unsigned int domains = AMDGPU_GEM_DOMAIN_GTT;

		if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
		    attach->peer2peer) {
			bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
			domains |= AMDGPU_GEM_DOMAIN_VRAM;
		}
		amdgpu_bo_placement_from_domain(bo, domains);
		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
		if (r)
			return ERR_PTR(r);

	} else if (!(amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type) &
		     AMDGPU_GEM_DOMAIN_GTT)) {
		return ERR_PTR(-EBUSY);
	}

	switch (bo->tbo.resource->mem_type) {
	case TTM_PL_TT:
		sgt = drm_prime_pages_to_sg(obj->dev,
					    bo->tbo.ttm->pages,
					    bo->tbo.ttm->num_pages);
		if (IS_ERR(sgt))
			return sgt;

		if (dma_map_sgtable(attach->dev, sgt, dir,
				    DMA_ATTR_SKIP_CPU_SYNC))
			goto error_free;
		break;

	case TTM_PL_VRAM:
		r = amdgpu_vram_mgr_alloc_sgt(adev, bo->tbo.resource, 0,
					      bo->tbo.base.size, attach->dev,
					      dir, &sgt);
		if (r)
			return ERR_PTR(r);
		break;
	default:
		return ERR_PTR(-EINVAL);
	}

	return sgt;

error_free:
	sg_free_table(sgt);
	kfree(sgt);
	return ERR_PTR(-EBUSY);
}

/**
 * amdgpu_dma_buf_unmap - &dma_buf_ops.unmap_dma_buf implementation
 * @attach: DMA-buf attachment
 * @sgt: sg_table to unmap
 * @dir: DMA direction
 *
 * This is called when a shared DMA buffer no longer needs to be accessible by
 * another device. For now, simply unpins the buffer from GTT.
 */
static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
				 struct sg_table *sgt,
				 enum dma_data_direction dir)
{
	if (sgt->sgl->page_link) {
		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
		sg_free_table(sgt);
		kfree(sgt);
	} else {
		amdgpu_vram_mgr_free_sgt(attach->dev, dir, sgt);
	}
}

/**
 * amdgpu_dma_buf_begin_cpu_access - &dma_buf_ops.begin_cpu_access implementation
 * @dma_buf: Shared DMA buffer
 * @direction: Direction of DMA transfer
 *
 * This is called before CPU access to the shared DMA buffer's memory. If it's
 * a read access, the buffer is moved to the GTT domain if possible, for optimal
 * CPU read performance.
 *
 * Returns:
 * 0 on success or a negative error code on failure.
 */
static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
					   enum dma_data_direction direction)
{
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dma_buf->priv);
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct ttm_operation_ctx ctx = { true, false };
	u32 domain = amdgpu_display_supported_domains(adev, bo->flags);
	int ret;
	bool reads = (direction == DMA_BIDIRECTIONAL ||
		      direction == DMA_FROM_DEVICE);

	if (!reads || !(domain & AMDGPU_GEM_DOMAIN_GTT))
		return 0;

	/* move to gtt */
	ret = amdgpu_bo_reserve(bo, false);
	if (unlikely(ret != 0))
		return ret;

	if (!bo->tbo.pin_count &&
	    (bo->allowed_domains & AMDGPU_GEM_DOMAIN_GTT)) {
		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
	}

	amdgpu_bo_unreserve(bo);
	return ret;
}

const struct dma_buf_ops amdgpu_dmabuf_ops = {
	.attach = amdgpu_dma_buf_attach,
	.detach = amdgpu_dma_buf_detach,
	.pin = amdgpu_dma_buf_pin,
	.unpin = amdgpu_dma_buf_unpin,
	.map_dma_buf = amdgpu_dma_buf_map,
	.unmap_dma_buf = amdgpu_dma_buf_unmap,
	.release = drm_gem_dmabuf_release,
	.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,
	.mmap = drm_gem_dmabuf_mmap,
	.vmap = drm_gem_dmabuf_vmap,
	.vunmap = drm_gem_dmabuf_vunmap,
};

/**
 * amdgpu_gem_prime_export - &drm_driver.gem_prime_export implementation
 * @gobj: GEM BO
 * @flags: Flags such as DRM_CLOEXEC and DRM_RDWR.
 *
 * The main work is done by the &drm_gem_prime_export helper.
 *
 * Returns:
 * Shared DMA buffer representing the GEM BO from the given device.
 */
struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
					int flags)
{
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);
	struct dma_buf *buf;

	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) ||
	    bo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID)
		return ERR_PTR(-EPERM);

	buf = drm_gem_prime_export(gobj, flags);
	if (!IS_ERR(buf))
		buf->ops = &amdgpu_dmabuf_ops;

	return buf;
}

/**
 * amdgpu_dma_buf_create_obj - create BO for DMA-buf import
 *
 * @dev: DRM device
 * @dma_buf: DMA-buf
 *
 * Creates an empty SG BO for DMA-buf import.
 *
 * Returns:
 * A new GEM BO of the given DRM device, representing the memory
 * described by the given DMA-buf attachment and scatter/gather table.
 */
static struct drm_gem_object *
amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
{
	struct dma_resv *resv = dma_buf->resv;
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct drm_gem_object *gobj;
	struct amdgpu_bo *bo;
	uint64_t flags = 0;
	int ret;

	dma_resv_lock(resv, NULL);

	if (dma_buf->ops == &amdgpu_dmabuf_ops) {
		struct amdgpu_bo *other = gem_to_amdgpu_bo(dma_buf->priv);

		flags |= other->flags & (AMDGPU_GEM_CREATE_CPU_GTT_USWC |
					 AMDGPU_GEM_CREATE_COHERENT |
					 AMDGPU_GEM_CREATE_EXT_COHERENT |
					 AMDGPU_GEM_CREATE_UNCACHED);
	}

	ret = amdgpu_gem_object_create(adev, dma_buf->size, PAGE_SIZE,
				       AMDGPU_GEM_DOMAIN_CPU, flags,
				       ttm_bo_type_sg, resv, &gobj, 0);
	if (ret)
		goto error;

	bo = gem_to_amdgpu_bo(gobj);
	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;

	dma_resv_unlock(resv);
	return gobj;

error:
	dma_resv_unlock(resv);
	return ERR_PTR(ret);
}

/**
 * amdgpu_dma_buf_move_notify - &attach.move_notify implementation
 *
 * @attach: the DMA-buf attachment
 *
 * Invalidate the DMA-buf attachment, making sure that the we re-create the
 * mapping before the next use.
 */
static void
amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach)
{
	struct drm_gem_object *obj = attach->importer_priv;
	struct ww_acquire_ctx *ticket = dma_resv_locking_ctx(obj->resv);
	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct ttm_operation_ctx ctx = { false, false };
	struct ttm_placement placement = {};
	struct amdgpu_vm_bo_base *bo_base;
	int r;

	if (!bo->tbo.resource || bo->tbo.resource->mem_type == TTM_PL_SYSTEM)
		return;

	r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
	if (r) {
		DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r);
		return;
	}

	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
		struct amdgpu_vm *vm = bo_base->vm;
		struct dma_resv *resv = vm->root.bo->tbo.base.resv;

		if (ticket) {
			/* When we get an error here it means that somebody
			 * else is holding the VM lock and updating page tables
			 * So we can just continue here.
			 */
			r = dma_resv_lock(resv, ticket);
			if (r)
				continue;

		} else {
			/* TODO: This is more problematic and we actually need
			 * to allow page tables updates without holding the
			 * lock.
			 */
			if (!dma_resv_trylock(resv))
				continue;
		}

		/* Reserve fences for two SDMA page table updates */
		r = dma_resv_reserve_fences(resv, 2);
		if (!r)
			r = amdgpu_vm_clear_freed(adev, vm, NULL);
		if (!r)
			r = amdgpu_vm_handle_moved(adev, vm);

		if (r && r != -EBUSY)
			DRM_ERROR("Failed to invalidate VM page tables (%d))\n",
				  r);

		dma_resv_unlock(resv);
	}
}

static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = {
	.allow_peer2peer = true,
	.move_notify = amdgpu_dma_buf_move_notify
};

/**
 * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation
 * @dev: DRM device
 * @dma_buf: Shared DMA buffer
 *
 * Import a dma_buf into a the driver and potentially create a new GEM object.
 *
 * Returns:
 * GEM BO representing the shared DMA buffer for the given device.
 */
struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
					       struct dma_buf *dma_buf)
{
	struct dma_buf_attachment *attach;
	struct drm_gem_object *obj;

	if (dma_buf->ops == &amdgpu_dmabuf_ops) {
		obj = dma_buf->priv;
		if (obj->dev == dev) {
			/*
			 * Importing dmabuf exported from out own gem increases
			 * refcount on gem itself instead of f_count of dmabuf.
			 */
			drm_gem_object_get(obj);
			return obj;
		}
	}

	obj = amdgpu_dma_buf_create_obj(dev, dma_buf);
	if (IS_ERR(obj))
		return obj;

	attach = dma_buf_dynamic_attach(dma_buf, dev->dev,
					&amdgpu_dma_buf_attach_ops, obj);
	if (IS_ERR(attach)) {
		drm_gem_object_put(obj);
		return ERR_CAST(attach);
	}

	get_dma_buf(dma_buf);
	obj->import_attach = attach;
	return obj;
}

/**
 * amdgpu_dmabuf_is_xgmi_accessible - Check if xgmi available for P2P transfer
 *
 * @adev: amdgpu_device pointer of the importer
 * @bo: amdgpu buffer object
 *
 * Returns:
 * True if dmabuf accessible over xgmi, false otherwise.
 */
bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
				      struct amdgpu_bo *bo)
{
	struct drm_gem_object *obj = &bo->tbo.base;
	struct drm_gem_object *gobj;

	if (obj->import_attach) {
		struct dma_buf *dma_buf = obj->import_attach->dmabuf;

		if (dma_buf->ops != &amdgpu_dmabuf_ops)
			/* No XGMI with non AMD GPUs */
			return false;

		gobj = dma_buf->priv;
		bo = gem_to_amdgpu_bo(gobj);
	}

	if (amdgpu_xgmi_same_hive(adev, amdgpu_ttm_adev(bo->tbo.bdev)) &&
			(bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM))
		return true;

	return false;
}