summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
blob: a98fbbb4739f65dad15dc717c1e66722770b5420 (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
/*
 * Copyright 2008 Advanced Micro Devices, Inc.
 * Copyright 2008 Red Hat Inc.
 * Copyright 2009 Jerome Glisse.
 *
 * 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.
 *
 * Authors: Dave Airlie
 *          Alex Deucher
 *          Jerome Glisse
 *          Christian König
 */
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
#include <drm/drmP.h>
#include <drm/amdgpu_drm.h>
#include "amdgpu.h"
#include "atom.h"

/*
 * Rings
 * Most engines on the GPU are fed via ring buffers.  Ring
 * buffers are areas of GPU accessible memory that the host
 * writes commands into and the GPU reads commands out of.
 * There is a rptr (read pointer) that determines where the
 * GPU is currently reading, and a wptr (write pointer)
 * which determines where the host has written.  When the
 * pointers are equal, the ring is idle.  When the host
 * writes commands to the ring buffer, it increments the
 * wptr.  The GPU then starts fetching commands and executes
 * them until the pointers are equal again.
 */
static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
				    struct amdgpu_ring *ring);
static void amdgpu_debugfs_ring_fini(struct amdgpu_ring *ring);

/**
 * amdgpu_ring_alloc - allocate space on the ring buffer
 *
 * @adev: amdgpu_device pointer
 * @ring: amdgpu_ring structure holding ring information
 * @ndw: number of dwords to allocate in the ring buffer
 *
 * Allocate @ndw dwords in the ring buffer (all asics).
 * Returns 0 on success, error on failure.
 */
int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw)
{
	/* Align requested size with padding so unlock_commit can
	 * pad safely */
	ndw = (ndw + ring->funcs->align_mask) & ~ring->funcs->align_mask;

	/* Make sure we aren't trying to allocate more space
	 * than the maximum for one submission
	 */
	if (WARN_ON_ONCE(ndw > ring->max_dw))
		return -ENOMEM;

	ring->count_dw = ndw;
	ring->wptr_old = ring->wptr;

	if (ring->funcs->begin_use)
		ring->funcs->begin_use(ring);

	return 0;
}

/** amdgpu_ring_insert_nop - insert NOP packets
 *
 * @ring: amdgpu_ring structure holding ring information
 * @count: the number of NOP packets to insert
 *
 * This is the generic insert_nop function for rings except SDMA
 */
void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
	int i;

	for (i = 0; i < count; i++)
		amdgpu_ring_write(ring, ring->funcs->nop);
}

/** amdgpu_ring_generic_pad_ib - pad IB with NOP packets
 *
 * @ring: amdgpu_ring structure holding ring information
 * @ib: IB to add NOP packets to
 *
 * This is the generic pad_ib function for rings except SDMA
 */
void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
{
	while (ib->length_dw & ring->funcs->align_mask)
		ib->ptr[ib->length_dw++] = ring->funcs->nop;
}

/**
 * amdgpu_ring_commit - tell the GPU to execute the new
 * commands on the ring buffer
 *
 * @adev: amdgpu_device pointer
 * @ring: amdgpu_ring structure holding ring information
 *
 * Update the wptr (write pointer) to tell the GPU to
 * execute new commands on the ring buffer (all asics).
 */
void amdgpu_ring_commit(struct amdgpu_ring *ring)
{
	uint32_t count;

	/* We pad to match fetch size */
	count = ring->funcs->align_mask + 1 -
		(ring->wptr & ring->funcs->align_mask);
	count %= ring->funcs->align_mask + 1;
	ring->funcs->insert_nop(ring, count);

	mb();
	amdgpu_ring_set_wptr(ring);

	if (ring->funcs->end_use)
		ring->funcs->end_use(ring);

	if (ring->funcs->type != AMDGPU_RING_TYPE_KIQ)
		amdgpu_ring_lru_touch(ring->adev, ring);
}

/**
 * amdgpu_ring_undo - reset the wptr
 *
 * @ring: amdgpu_ring structure holding ring information
 *
 * Reset the driver's copy of the wptr (all asics).
 */
void amdgpu_ring_undo(struct amdgpu_ring *ring)
{
	ring->wptr = ring->wptr_old;

	if (ring->funcs->end_use)
		ring->funcs->end_use(ring);
}

/**
 * amdgpu_ring_priority_put - restore a ring's priority
 *
 * @ring: amdgpu_ring structure holding the information
 * @priority: target priority
 *
 * Release a request for executing at @priority
 */
void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
			      enum amd_sched_priority priority)
{
	int i;

	if (!ring->funcs->set_priority)
		return;

	if (atomic_dec_return(&ring->num_jobs[priority]) > 0)
		return;

	/* no need to restore if the job is already at the lowest priority */
	if (priority == AMD_SCHED_PRIORITY_NORMAL)
		return;

	mutex_lock(&ring->priority_mutex);
	/* something higher prio is executing, no need to decay */
	if (ring->priority > priority)
		goto out_unlock;

	/* decay priority to the next level with a job available */
	for (i = priority; i >= AMD_SCHED_PRIORITY_MIN; i--) {
		if (i == AMD_SCHED_PRIORITY_NORMAL
				|| atomic_read(&ring->num_jobs[i])) {
			ring->priority = i;
			ring->funcs->set_priority(ring, i);
			break;
		}
	}

out_unlock:
	mutex_unlock(&ring->priority_mutex);
}

/**
 * amdgpu_ring_priority_get - change the ring's priority
 *
 * @ring: amdgpu_ring structure holding the information
 * @priority: target priority
 *
 * Request a ring's priority to be raised to @priority (refcounted).
 */
void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
			      enum amd_sched_priority priority)
{
	if (!ring->funcs->set_priority)
		return;

	atomic_inc(&ring->num_jobs[priority]);

	mutex_lock(&ring->priority_mutex);
	if (priority <= ring->priority)
		goto out_unlock;

	ring->priority = priority;
	ring->funcs->set_priority(ring, priority);

out_unlock:
	mutex_unlock(&ring->priority_mutex);
}

/**
 * amdgpu_ring_init - init driver ring struct.
 *
 * @adev: amdgpu_device pointer
 * @ring: amdgpu_ring structure holding ring information
 * @max_ndw: maximum number of dw for ring alloc
 * @nop: nop packet for this ring
 *
 * Initialize the driver information for the selected ring (all asics).
 * Returns 0 on success, error on failure.
 */
int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
		     unsigned max_dw, struct amdgpu_irq_src *irq_src,
		     unsigned irq_type)
{
	int r, i;
	int sched_hw_submission = amdgpu_sched_hw_submission;

	/* Set the hw submission limit higher for KIQ because
	 * it's used for a number of gfx/compute tasks by both
	 * KFD and KGD which may have outstanding fences and
	 * it doesn't really use the gpu scheduler anyway;
	 * KIQ tasks get submitted directly to the ring.
	 */
	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
		sched_hw_submission = max(sched_hw_submission, 256);

	if (ring->adev == NULL) {
		if (adev->num_rings >= AMDGPU_MAX_RINGS)
			return -EINVAL;

		ring->adev = adev;
		ring->idx = adev->num_rings++;
		adev->rings[ring->idx] = ring;
		r = amdgpu_fence_driver_init_ring(ring, sched_hw_submission);
		if (r)
			return r;
	}

	r = amdgpu_wb_get(adev, &ring->rptr_offs);
	if (r) {
		dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
		return r;
	}

	r = amdgpu_wb_get(adev, &ring->wptr_offs);
	if (r) {
		dev_err(adev->dev, "(%d) ring wptr_offs wb alloc failed\n", r);
		return r;
	}

	r = amdgpu_wb_get(adev, &ring->fence_offs);
	if (r) {
		dev_err(adev->dev, "(%d) ring fence_offs wb alloc failed\n", r);
		return r;
	}

	r = amdgpu_wb_get(adev, &ring->cond_exe_offs);
	if (r) {
		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
		return r;
	}
	ring->cond_exe_gpu_addr = adev->wb.gpu_addr + (ring->cond_exe_offs * 4);
	ring->cond_exe_cpu_addr = &adev->wb.wb[ring->cond_exe_offs];
	/* always set cond_exec_polling to CONTINUE */
	*ring->cond_exe_cpu_addr = 1;

	r = amdgpu_fence_driver_start_ring(ring, irq_src, irq_type);
	if (r) {
		dev_err(adev->dev, "failed initializing fences (%d).\n", r);
		return r;
	}

	ring->ring_size = roundup_pow_of_two(max_dw * 4 * sched_hw_submission);

	ring->buf_mask = (ring->ring_size / 4) - 1;
	ring->ptr_mask = ring->funcs->support_64bit_ptrs ?
		0xffffffffffffffff : ring->buf_mask;
	/* Allocate ring buffer */
	if (ring->ring_obj == NULL) {
		r = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE,
					    AMDGPU_GEM_DOMAIN_GTT,
					    &ring->ring_obj,
					    &ring->gpu_addr,
					    (void **)&ring->ring);
		if (r) {
			dev_err(adev->dev, "(%d) ring create failed\n", r);
			return r;
		}
		amdgpu_ring_clear_ring(ring);
	}

	ring->max_dw = max_dw;
	ring->priority = AMD_SCHED_PRIORITY_NORMAL;
	mutex_init(&ring->priority_mutex);
	INIT_LIST_HEAD(&ring->lru_list);
	amdgpu_ring_lru_touch(adev, ring);

	for (i = 0; i < AMD_SCHED_PRIORITY_MAX; ++i)
		atomic_set(&ring->num_jobs[i], 0);

	if (amdgpu_debugfs_ring_init(adev, ring)) {
		DRM_ERROR("Failed to register debugfs file for rings !\n");
	}

	return 0;
}

/**
 * amdgpu_ring_fini - tear down the driver ring struct.
 *
 * @adev: amdgpu_device pointer
 * @ring: amdgpu_ring structure holding ring information
 *
 * Tear down the driver information for the selected ring (all asics).
 */
void amdgpu_ring_fini(struct amdgpu_ring *ring)
{
	ring->ready = false;

	/* Not to finish a ring which is not initialized */
	if (!(ring->adev) || !(ring->adev->rings[ring->idx]))
		return;

	amdgpu_wb_free(ring->adev, ring->rptr_offs);
	amdgpu_wb_free(ring->adev, ring->wptr_offs);

	amdgpu_wb_free(ring->adev, ring->cond_exe_offs);
	amdgpu_wb_free(ring->adev, ring->fence_offs);

	amdgpu_bo_free_kernel(&ring->ring_obj,
			      &ring->gpu_addr,
			      (void **)&ring->ring);

	amdgpu_debugfs_ring_fini(ring);

	ring->adev->rings[ring->idx] = NULL;
}

static void amdgpu_ring_lru_touch_locked(struct amdgpu_device *adev,
					 struct amdgpu_ring *ring)
{
	/* list_move_tail handles the case where ring isn't part of the list */
	list_move_tail(&ring->lru_list, &adev->ring_lru_list);
}

static bool amdgpu_ring_is_blacklisted(struct amdgpu_ring *ring,
				       int *blacklist, int num_blacklist)
{
	int i;

	for (i = 0; i < num_blacklist; i++) {
		if (ring->idx == blacklist[i])
			return true;
	}

	return false;
}

/**
 * amdgpu_ring_lru_get - get the least recently used ring for a HW IP block
 *
 * @adev: amdgpu_device pointer
 * @type: amdgpu_ring_type enum
 * @blacklist: blacklisted ring ids array
 * @num_blacklist: number of entries in @blacklist
 * @lru_pipe_order: find a ring from the least recently used pipe
 * @ring: output ring
 *
 * Retrieve the amdgpu_ring structure for the least recently used ring of
 * a specific IP block (all asics).
 * Returns 0 on success, error on failure.
 */
int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
			int *blacklist,	int num_blacklist,
			bool lru_pipe_order, struct amdgpu_ring **ring)
{
	struct amdgpu_ring *entry;

	/* List is sorted in LRU order, find first entry corresponding
	 * to the desired HW IP */
	*ring = NULL;
	spin_lock(&adev->ring_lru_list_lock);
	list_for_each_entry(entry, &adev->ring_lru_list, lru_list) {
		if (entry->funcs->type != type)
			continue;

		if (amdgpu_ring_is_blacklisted(entry, blacklist, num_blacklist))
			continue;

		if (!*ring) {
			*ring = entry;

			/* We are done for ring LRU */
			if (!lru_pipe_order)
				break;
		}

		/* Move all rings on the same pipe to the end of the list */
		if (entry->pipe == (*ring)->pipe)
			amdgpu_ring_lru_touch_locked(adev, entry);
	}

	/* Move the ring we found to the end of the list */
	if (*ring)
		amdgpu_ring_lru_touch_locked(adev, *ring);

	spin_unlock(&adev->ring_lru_list_lock);

	if (!*ring) {
		DRM_ERROR("Ring LRU contains no entries for ring type:%d\n", type);
		return -EINVAL;
	}

	return 0;
}

/**
 * amdgpu_ring_lru_touch - mark a ring as recently being used
 *
 * @adev: amdgpu_device pointer
 * @ring: ring to touch
 *
 * Move @ring to the tail of the lru list
 */
void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring)
{
	spin_lock(&adev->ring_lru_list_lock);
	amdgpu_ring_lru_touch_locked(adev, ring);
	spin_unlock(&adev->ring_lru_list_lock);
}

/*
 * Debugfs info
 */
#if defined(CONFIG_DEBUG_FS)

/* Layout of file is 12 bytes consisting of
 * - rptr
 * - wptr
 * - driver's copy of wptr
 *
 * followed by n-words of ring data
 */
static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
					size_t size, loff_t *pos)
{
	struct amdgpu_ring *ring = file_inode(f)->i_private;
	int r, i;
	uint32_t value, result, early[3];

	if (*pos & 3 || size & 3)
		return -EINVAL;

	result = 0;

	if (*pos < 12) {
		early[0] = amdgpu_ring_get_rptr(ring);
		early[1] = amdgpu_ring_get_wptr(ring) & ring->buf_mask;
		early[2] = ring->wptr & ring->buf_mask;
		for (i = *pos / 4; i < 3 && size; i++) {
			r = put_user(early[i], (uint32_t *)buf);
			if (r)
				return r;
			buf += 4;
			result += 4;
			size -= 4;
			*pos += 4;
		}
	}

	while (size) {
		if (*pos >= (ring->ring_size + 12))
			return result;

		value = ring->ring[(*pos - 12)/4];
		r = put_user(value, (uint32_t*)buf);
		if (r)
			return r;
		buf += 4;
		result += 4;
		size -= 4;
		*pos += 4;
	}

	return result;
}

static const struct file_operations amdgpu_debugfs_ring_fops = {
	.owner = THIS_MODULE,
	.read = amdgpu_debugfs_ring_read,
	.llseek = default_llseek
};

#endif

static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
				    struct amdgpu_ring *ring)
{
#if defined(CONFIG_DEBUG_FS)
	struct drm_minor *minor = adev->ddev->primary;
	struct dentry *ent, *root = minor->debugfs_root;
	char name[32];

	sprintf(name, "amdgpu_ring_%s", ring->name);

	ent = debugfs_create_file(name,
				  S_IFREG | S_IRUGO, root,
				  ring, &amdgpu_debugfs_ring_fops);
	if (!ent)
		return -ENOMEM;

	i_size_write(ent->d_inode, ring->ring_size + 12);
	ring->ent = ent;
#endif
	return 0;
}

static void amdgpu_debugfs_ring_fini(struct amdgpu_ring *ring)
{
#if defined(CONFIG_DEBUG_FS)
	debugfs_remove(ring->ent);
#endif
}