summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/msm/msm_gem_submit.c
blob: 7bd83e0afa971e13de295e7595ac1abd0902c2a9 (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
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
/*
 * Copyright (C) 2013 Red Hat
 * Author: Rob Clark <robdclark@gmail.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/sync_file.h>

#include "msm_drv.h"
#include "msm_gpu.h"
#include "msm_gem.h"

/*
 * Cmdstream submission:
 */

/* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
#define BO_VALID    0x8000   /* is current addr in cmdstream correct/valid? */
#define BO_LOCKED   0x4000
#define BO_PINNED   0x2000

static struct msm_gem_submit *submit_create(struct drm_device *dev,
		struct msm_gpu *gpu, struct msm_gpu_submitqueue *queue,
		uint32_t nr_bos, uint32_t nr_cmds)
{
	struct msm_gem_submit *submit;
	uint64_t sz = sizeof(*submit) + ((u64)nr_bos * sizeof(submit->bos[0])) +
		((u64)nr_cmds * sizeof(submit->cmd[0]));

	if (sz > SIZE_MAX)
		return NULL;

	submit = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
	if (!submit)
		return NULL;

	submit->dev = dev;
	submit->gpu = gpu;
	submit->fence = NULL;
	submit->pid = get_pid(task_pid(current));
	submit->cmd = (void *)&submit->bos[nr_bos];
	submit->queue = queue;
	submit->ring = gpu->rb[queue->prio];

	/* initially, until copy_from_user() and bo lookup succeeds: */
	submit->nr_bos = 0;
	submit->nr_cmds = 0;

	INIT_LIST_HEAD(&submit->node);
	INIT_LIST_HEAD(&submit->bo_list);
	ww_acquire_init(&submit->ticket, &reservation_ww_class);

	return submit;
}

void msm_gem_submit_free(struct msm_gem_submit *submit)
{
	dma_fence_put(submit->fence);
	list_del(&submit->node);
	put_pid(submit->pid);
	msm_submitqueue_put(submit->queue);

	kfree(submit);
}

static inline unsigned long __must_check
copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
{
	if (access_ok(VERIFY_READ, from, n))
		return __copy_from_user_inatomic(to, from, n);
	return -EFAULT;
}

static int submit_lookup_objects(struct msm_gem_submit *submit,
		struct drm_msm_gem_submit *args, struct drm_file *file)
{
	unsigned i;
	int ret = 0;

	spin_lock(&file->table_lock);
	pagefault_disable();

	for (i = 0; i < args->nr_bos; i++) {
		struct drm_msm_gem_submit_bo submit_bo;
		struct drm_gem_object *obj;
		struct msm_gem_object *msm_obj;
		void __user *userptr =
			u64_to_user_ptr(args->bos + (i * sizeof(submit_bo)));

		/* make sure we don't have garbage flags, in case we hit
		 * error path before flags is initialized:
		 */
		submit->bos[i].flags = 0;

		if (copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo))) {
			pagefault_enable();
			spin_unlock(&file->table_lock);
			if (copy_from_user(&submit_bo, userptr, sizeof(submit_bo))) {
				ret = -EFAULT;
				goto out;
			}
			spin_lock(&file->table_lock);
			pagefault_disable();
		}

		if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) ||
			!(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) {
			DRM_ERROR("invalid flags: %x\n", submit_bo.flags);
			ret = -EINVAL;
			goto out_unlock;
		}

		submit->bos[i].flags = submit_bo.flags;
		/* in validate_objects() we figure out if this is true: */
		submit->bos[i].iova  = submit_bo.presumed;

		/* normally use drm_gem_object_lookup(), but for bulk lookup
		 * all under single table_lock just hit object_idr directly:
		 */
		obj = idr_find(&file->object_idr, submit_bo.handle);
		if (!obj) {
			DRM_ERROR("invalid handle %u at index %u\n", submit_bo.handle, i);
			ret = -EINVAL;
			goto out_unlock;
		}

		msm_obj = to_msm_bo(obj);

		if (!list_empty(&msm_obj->submit_entry)) {
			DRM_ERROR("handle %u at index %u already on submit list\n",
					submit_bo.handle, i);
			ret = -EINVAL;
			goto out_unlock;
		}

		drm_gem_object_reference(obj);

		submit->bos[i].obj = msm_obj;

		list_add_tail(&msm_obj->submit_entry, &submit->bo_list);
	}

out_unlock:
	pagefault_enable();
	spin_unlock(&file->table_lock);

out:
	submit->nr_bos = i;

	return ret;
}

static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
		int i, bool backoff)
{
	struct msm_gem_object *msm_obj = submit->bos[i].obj;

	if (submit->bos[i].flags & BO_PINNED)
		msm_gem_put_iova(&msm_obj->base, submit->gpu->aspace);

	if (submit->bos[i].flags & BO_LOCKED)
		ww_mutex_unlock(&msm_obj->resv->lock);

	if (backoff && !(submit->bos[i].flags & BO_VALID))
		submit->bos[i].iova = 0;

	submit->bos[i].flags &= ~(BO_LOCKED | BO_PINNED);
}

/* This is where we make sure all the bo's are reserved and pin'd: */
static int submit_lock_objects(struct msm_gem_submit *submit)
{
	int contended, slow_locked = -1, i, ret = 0;

retry:
	for (i = 0; i < submit->nr_bos; i++) {
		struct msm_gem_object *msm_obj = submit->bos[i].obj;

		if (slow_locked == i)
			slow_locked = -1;

		contended = i;

		if (!(submit->bos[i].flags & BO_LOCKED)) {
			ret = ww_mutex_lock_interruptible(&msm_obj->resv->lock,
					&submit->ticket);
			if (ret)
				goto fail;
			submit->bos[i].flags |= BO_LOCKED;
		}
	}

	ww_acquire_done(&submit->ticket);

	return 0;

fail:
	for (; i >= 0; i--)
		submit_unlock_unpin_bo(submit, i, true);

	if (slow_locked > 0)
		submit_unlock_unpin_bo(submit, slow_locked, true);

	if (ret == -EDEADLK) {
		struct msm_gem_object *msm_obj = submit->bos[contended].obj;
		/* we lost out in a seqno race, lock and retry.. */
		ret = ww_mutex_lock_slow_interruptible(&msm_obj->resv->lock,
				&submit->ticket);
		if (!ret) {
			submit->bos[contended].flags |= BO_LOCKED;
			slow_locked = contended;
			goto retry;
		}
	}

	return ret;
}

static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
{
	int i, ret = 0;

	for (i = 0; i < submit->nr_bos; i++) {
		struct msm_gem_object *msm_obj = submit->bos[i].obj;
		bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE;

		if (!write) {
			/* NOTE: _reserve_shared() must happen before
			 * _add_shared_fence(), which makes this a slightly
			 * strange place to call it.  OTOH this is a
			 * convenient can-fail point to hook it in.
			 */
			ret = reservation_object_reserve_shared(msm_obj->resv);
			if (ret)
				return ret;
		}

		if (no_implicit)
			continue;

		ret = msm_gem_sync_object(&msm_obj->base, submit->ring->fctx,
			write);
		if (ret)
			break;
	}

	return ret;
}

static int submit_pin_objects(struct msm_gem_submit *submit)
{
	int i, ret = 0;

	submit->valid = true;

	for (i = 0; i < submit->nr_bos; i++) {
		struct msm_gem_object *msm_obj = submit->bos[i].obj;
		uint64_t iova;

		/* if locking succeeded, pin bo: */
		ret = msm_gem_get_iova(&msm_obj->base,
				submit->gpu->aspace, &iova);

		if (ret)
			break;

		submit->bos[i].flags |= BO_PINNED;

		if (iova == submit->bos[i].iova) {
			submit->bos[i].flags |= BO_VALID;
		} else {
			submit->bos[i].iova = iova;
			/* iova changed, so address in cmdstream is not valid: */
			submit->bos[i].flags &= ~BO_VALID;
			submit->valid = false;
		}
	}

	return ret;
}

static int submit_bo(struct msm_gem_submit *submit, uint32_t idx,
		struct msm_gem_object **obj, uint64_t *iova, bool *valid)
{
	if (idx >= submit->nr_bos) {
		DRM_ERROR("invalid buffer index: %u (out of %u)\n",
				idx, submit->nr_bos);
		return -EINVAL;
	}

	if (obj)
		*obj = submit->bos[idx].obj;
	if (iova)
		*iova = submit->bos[idx].iova;
	if (valid)
		*valid = !!(submit->bos[idx].flags & BO_VALID);

	return 0;
}

/* process the reloc's and patch up the cmdstream as needed: */
static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *obj,
		uint32_t offset, uint32_t nr_relocs, uint64_t relocs)
{
	uint32_t i, last_offset = 0;
	uint32_t *ptr;
	int ret = 0;

	if (offset % 4) {
		DRM_ERROR("non-aligned cmdstream buffer: %u\n", offset);
		return -EINVAL;
	}

	/* For now, just map the entire thing.  Eventually we probably
	 * to do it page-by-page, w/ kmap() if not vmap()d..
	 */
	ptr = msm_gem_get_vaddr(&obj->base);

	if (IS_ERR(ptr)) {
		ret = PTR_ERR(ptr);
		DBG("failed to map: %d", ret);
		return ret;
	}

	for (i = 0; i < nr_relocs; i++) {
		struct drm_msm_gem_submit_reloc submit_reloc;
		void __user *userptr =
			u64_to_user_ptr(relocs + (i * sizeof(submit_reloc)));
		uint32_t off;
		uint64_t iova;
		bool valid;

		if (copy_from_user(&submit_reloc, userptr, sizeof(submit_reloc))) {
			ret = -EFAULT;
			goto out;
		}

		if (submit_reloc.submit_offset % 4) {
			DRM_ERROR("non-aligned reloc offset: %u\n",
					submit_reloc.submit_offset);
			ret = -EINVAL;
			goto out;
		}

		/* offset in dwords: */
		off = submit_reloc.submit_offset / 4;

		if ((off >= (obj->base.size / 4)) ||
				(off < last_offset)) {
			DRM_ERROR("invalid offset %u at reloc %u\n", off, i);
			ret = -EINVAL;
			goto out;
		}

		ret = submit_bo(submit, submit_reloc.reloc_idx, NULL, &iova, &valid);
		if (ret)
			goto out;

		if (valid)
			continue;

		iova += submit_reloc.reloc_offset;

		if (submit_reloc.shift < 0)
			iova >>= -submit_reloc.shift;
		else
			iova <<= submit_reloc.shift;

		ptr[off] = iova | submit_reloc.or;

		last_offset = off;
	}

out:
	msm_gem_put_vaddr(&obj->base);

	return ret;
}

static void submit_cleanup(struct msm_gem_submit *submit)
{
	unsigned i;

	for (i = 0; i < submit->nr_bos; i++) {
		struct msm_gem_object *msm_obj = submit->bos[i].obj;
		submit_unlock_unpin_bo(submit, i, false);
		list_del_init(&msm_obj->submit_entry);
		drm_gem_object_unreference(&msm_obj->base);
	}

	ww_acquire_fini(&submit->ticket);
}

int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
		struct drm_file *file)
{
	struct msm_drm_private *priv = dev->dev_private;
	struct drm_msm_gem_submit *args = data;
	struct msm_file_private *ctx = file->driver_priv;
	struct msm_gem_submit *submit;
	struct msm_gpu *gpu = priv->gpu;
	struct dma_fence *in_fence = NULL;
	struct sync_file *sync_file = NULL;
	struct msm_gpu_submitqueue *queue;
	struct msm_ringbuffer *ring;
	int out_fence_fd = -1;
	unsigned i;
	int ret;

	if (!gpu)
		return -ENXIO;

	/* for now, we just have 3d pipe.. eventually this would need to
	 * be more clever to dispatch to appropriate gpu module:
	 */
	if (MSM_PIPE_ID(args->flags) != MSM_PIPE_3D0)
		return -EINVAL;

	if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_FLAGS)
		return -EINVAL;

	if (args->flags & MSM_SUBMIT_SUDO) {
		if (!IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) ||
		    !capable(CAP_SYS_RAWIO))
			return -EINVAL;
	}

	queue = msm_submitqueue_get(ctx, args->queueid);
	if (!queue)
		return -ENOENT;

	ring = gpu->rb[queue->prio];

	if (args->flags & MSM_SUBMIT_FENCE_FD_IN) {
		in_fence = sync_file_get_fence(args->fence_fd);

		if (!in_fence)
			return -EINVAL;

		/*
		 * Wait if the fence is from a foreign context, or if the fence
		 * array contains any fence from a foreign context.
		 */
		if (!dma_fence_match_context(in_fence, ring->fctx->context)) {
			ret = dma_fence_wait(in_fence, true);
			if (ret)
				return ret;
		}
	}

	ret = mutex_lock_interruptible(&dev->struct_mutex);
	if (ret)
		return ret;

	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
		if (out_fence_fd < 0) {
			ret = out_fence_fd;
			goto out_unlock;
		}
	}

	submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds);
	if (!submit) {
		ret = -ENOMEM;
		goto out_unlock;
	}

	if (args->flags & MSM_SUBMIT_SUDO)
		submit->in_rb = true;

	ret = submit_lookup_objects(submit, args, file);
	if (ret)
		goto out;

	ret = submit_lock_objects(submit);
	if (ret)
		goto out;

	ret = submit_fence_sync(submit, !!(args->flags & MSM_SUBMIT_NO_IMPLICIT));
	if (ret)
		goto out;

	ret = submit_pin_objects(submit);
	if (ret)
		goto out;

	for (i = 0; i < args->nr_cmds; i++) {
		struct drm_msm_gem_submit_cmd submit_cmd;
		void __user *userptr =
			u64_to_user_ptr(args->cmds + (i * sizeof(submit_cmd)));
		struct msm_gem_object *msm_obj;
		uint64_t iova;

		ret = copy_from_user(&submit_cmd, userptr, sizeof(submit_cmd));
		if (ret) {
			ret = -EFAULT;
			goto out;
		}

		/* validate input from userspace: */
		switch (submit_cmd.type) {
		case MSM_SUBMIT_CMD_BUF:
		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
			break;
		default:
			DRM_ERROR("invalid type: %08x\n", submit_cmd.type);
			ret = -EINVAL;
			goto out;
		}

		ret = submit_bo(submit, submit_cmd.submit_idx,
				&msm_obj, &iova, NULL);
		if (ret)
			goto out;

		if (submit_cmd.size % 4) {
			DRM_ERROR("non-aligned cmdstream buffer size: %u\n",
					submit_cmd.size);
			ret = -EINVAL;
			goto out;
		}

		if (!submit_cmd.size ||
			((submit_cmd.size + submit_cmd.submit_offset) >
				msm_obj->base.size)) {
			DRM_ERROR("invalid cmdstream size: %u\n", submit_cmd.size);
			ret = -EINVAL;
			goto out;
		}

		submit->cmd[i].type = submit_cmd.type;
		submit->cmd[i].size = submit_cmd.size / 4;
		submit->cmd[i].iova = iova + submit_cmd.submit_offset;
		submit->cmd[i].idx  = submit_cmd.submit_idx;

		if (submit->valid)
			continue;

		ret = submit_reloc(submit, msm_obj, submit_cmd.submit_offset,
				submit_cmd.nr_relocs, submit_cmd.relocs);
		if (ret)
			goto out;
	}

	submit->nr_cmds = i;

	submit->fence = msm_fence_alloc(ring->fctx);
	if (IS_ERR(submit->fence)) {
		ret = PTR_ERR(submit->fence);
		submit->fence = NULL;
		goto out;
	}

	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
		sync_file = sync_file_create(submit->fence);
		if (!sync_file) {
			ret = -ENOMEM;
			goto out;
		}
	}

	msm_gpu_submit(gpu, submit, ctx);

	args->fence = submit->fence->seqno;

	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
		fd_install(out_fence_fd, sync_file->file);
		args->fence_fd = out_fence_fd;
	}

out:
	if (in_fence)
		dma_fence_put(in_fence);
	submit_cleanup(submit);
	if (ret)
		msm_gem_submit_free(submit);
out_unlock:
	if (ret && (out_fence_fd >= 0))
		put_unused_fd(out_fence_fd);
	mutex_unlock(&dev->struct_mutex);
	return ret;
}