1/*
2 * Copyright 2014 Advanced Micro Devices, Inc.
3 * Copyright 2008 Red Hat Inc.
4 * Copyright 2009 Jerome Glisse.
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a
7 * copy of this software and associated documentation files (the "Software"),
8 * to deal in the Software without restriction, including without limitation
9 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
10 * and/or sell copies of the Software, and to permit persons to whom the
11 * Software is furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in
14 * all copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
19 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
20 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
21 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
22 * OTHER DEALINGS IN THE SOFTWARE.
23 *
24 */
25
26#include "amdgpu.h"
27#include "amdgpu_gfx.h"
28#include "amdgpu_rlc.h"
29#include "amdgpu_ras.h"
30
31/* delay 0.1 second to enable gfx off feature */
32#define GFX_OFF_DELAY_ENABLE         msecs_to_jiffies(100)
33
34/*
35 * GPU GFX IP block helpers function.
36 */
37
38int amdgpu_gfx_mec_queue_to_bit(struct amdgpu_device *adev, int mec,
39				int pipe, int queue)
40{
41	int bit = 0;
42
43	bit += mec * adev->gfx.mec.num_pipe_per_mec
44		* adev->gfx.mec.num_queue_per_pipe;
45	bit += pipe * adev->gfx.mec.num_queue_per_pipe;
46	bit += queue;
47
48	return bit;
49}
50
51void amdgpu_queue_mask_bit_to_mec_queue(struct amdgpu_device *adev, int bit,
52				 int *mec, int *pipe, int *queue)
53{
54	*queue = bit % adev->gfx.mec.num_queue_per_pipe;
55	*pipe = (bit / adev->gfx.mec.num_queue_per_pipe)
56		% adev->gfx.mec.num_pipe_per_mec;
57	*mec = (bit / adev->gfx.mec.num_queue_per_pipe)
58	       / adev->gfx.mec.num_pipe_per_mec;
59
60}
61
62bool amdgpu_gfx_is_mec_queue_enabled(struct amdgpu_device *adev,
63				     int mec, int pipe, int queue)
64{
65	return test_bit(amdgpu_gfx_mec_queue_to_bit(adev, mec, pipe, queue),
66			adev->gfx.mec.queue_bitmap);
67}
68
69int amdgpu_gfx_me_queue_to_bit(struct amdgpu_device *adev,
70			       int me, int pipe, int queue)
71{
72	int bit = 0;
73
74	bit += me * adev->gfx.me.num_pipe_per_me
75		* adev->gfx.me.num_queue_per_pipe;
76	bit += pipe * adev->gfx.me.num_queue_per_pipe;
77	bit += queue;
78
79	return bit;
80}
81
82void amdgpu_gfx_bit_to_me_queue(struct amdgpu_device *adev, int bit,
83				int *me, int *pipe, int *queue)
84{
85	*queue = bit % adev->gfx.me.num_queue_per_pipe;
86	*pipe = (bit / adev->gfx.me.num_queue_per_pipe)
87		% adev->gfx.me.num_pipe_per_me;
88	*me = (bit / adev->gfx.me.num_queue_per_pipe)
89		/ adev->gfx.me.num_pipe_per_me;
90}
91
92bool amdgpu_gfx_is_me_queue_enabled(struct amdgpu_device *adev,
93				    int me, int pipe, int queue)
94{
95	return test_bit(amdgpu_gfx_me_queue_to_bit(adev, me, pipe, queue),
96			adev->gfx.me.queue_bitmap);
97}
98
99/**
100 * amdgpu_gfx_scratch_get - Allocate a scratch register
101 *
102 * @adev: amdgpu_device pointer
103 * @reg: scratch register mmio offset
104 *
105 * Allocate a CP scratch register for use by the driver (all asics).
106 * Returns 0 on success or -EINVAL on failure.
107 */
108int amdgpu_gfx_scratch_get(struct amdgpu_device *adev, uint32_t *reg)
109{
110	int i;
111
112	i = ffs(adev->gfx.scratch.free_mask);
113	if (i != 0 && i <= adev->gfx.scratch.num_reg) {
114		i--;
115		adev->gfx.scratch.free_mask &= ~(1u << i);
116		*reg = adev->gfx.scratch.reg_base + i;
117		return 0;
118	}
119	return -EINVAL;
120}
121
122/**
123 * amdgpu_gfx_scratch_free - Free a scratch register
124 *
125 * @adev: amdgpu_device pointer
126 * @reg: scratch register mmio offset
127 *
128 * Free a CP scratch register allocated for use by the driver (all asics)
129 */
130void amdgpu_gfx_scratch_free(struct amdgpu_device *adev, uint32_t reg)
131{
132	adev->gfx.scratch.free_mask |= 1u << (reg - adev->gfx.scratch.reg_base);
133}
134
135/**
136 * amdgpu_gfx_parse_disable_cu - Parse the disable_cu module parameter
137 *
138 * @mask: array in which the per-shader array disable masks will be stored
139 * @max_se: number of SEs
140 * @max_sh: number of SHs
141 *
142 * The bitmask of CUs to be disabled in the shader array determined by se and
143 * sh is stored in mask[se * max_sh + sh].
144 */
145void amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se, unsigned max_sh)
146{
147	unsigned se, sh, cu;
148	const char *p;
149
150	memset(mask, 0, sizeof(*mask) * max_se * max_sh);
151
152	if (!amdgpu_disable_cu || !*amdgpu_disable_cu)
153		return;
154
155	p = amdgpu_disable_cu;
156	for (;;) {
157		char *next;
158		int ret = sscanf(p, "%u.%u.%u", &se, &sh, &cu);
159		if (ret < 3) {
160			DRM_ERROR("amdgpu: could not parse disable_cu\n");
161			return;
162		}
163
164		if (se < max_se && sh < max_sh && cu < 16) {
165			DRM_INFO("amdgpu: disabling CU %u.%u.%u\n", se, sh, cu);
166			mask[se * max_sh + sh] |= 1u << cu;
167		} else {
168			DRM_ERROR("amdgpu: disable_cu %u.%u.%u is out of range\n",
169				  se, sh, cu);
170		}
171
172		next = strchr(p, ',');
173		if (!next)
174			break;
175		p = next + 1;
176	}
177}
178
179static bool amdgpu_gfx_is_multipipe_capable(struct amdgpu_device *adev)
180{
181	if (amdgpu_compute_multipipe != -1) {
182		DRM_INFO("amdgpu: forcing compute pipe policy %d\n",
183			 amdgpu_compute_multipipe);
184		return amdgpu_compute_multipipe == 1;
185	}
186
187	/* FIXME: spreading the queues across pipes causes perf regressions
188	 * on POLARIS11 compute workloads */
189	if (adev->asic_type == CHIP_POLARIS11)
190		return false;
191
192	return adev->gfx.mec.num_mec > 1;
193}
194
195bool amdgpu_gfx_is_high_priority_compute_queue(struct amdgpu_device *adev,
196					       int pipe, int queue)
197{
198	bool multipipe_policy = amdgpu_gfx_is_multipipe_capable(adev);
199	int cond;
200	/* Policy: alternate between normal and high priority */
201	cond = multipipe_policy ? pipe : queue;
202
203	return ((cond % 2) != 0);
204
205}
206
207void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
208{
209	int i, queue, pipe;
210	bool multipipe_policy = amdgpu_gfx_is_multipipe_capable(adev);
211	int max_queues_per_mec = min(adev->gfx.mec.num_pipe_per_mec *
212				     adev->gfx.mec.num_queue_per_pipe,
213				     adev->gfx.num_compute_rings);
214
215	if (multipipe_policy) {
216		/* policy: make queues evenly cross all pipes on MEC1 only */
217		for (i = 0; i < max_queues_per_mec; i++) {
218			pipe = i % adev->gfx.mec.num_pipe_per_mec;
219			queue = (i / adev->gfx.mec.num_pipe_per_mec) %
220				adev->gfx.mec.num_queue_per_pipe;
221
222			set_bit(pipe * adev->gfx.mec.num_queue_per_pipe + queue,
223					adev->gfx.mec.queue_bitmap);
224		}
225	} else {
226		/* policy: amdgpu owns all queues in the given pipe */
227		for (i = 0; i < max_queues_per_mec; ++i)
228			set_bit(i, adev->gfx.mec.queue_bitmap);
229	}
230
231	dev_dbg(adev->dev, "mec queue bitmap weight=%d\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES));
232}
233
234void amdgpu_gfx_graphics_queue_acquire(struct amdgpu_device *adev)
235{
236	int i, queue, me;
237
238	for (i = 0; i < AMDGPU_MAX_GFX_QUEUES; ++i) {
239		queue = i % adev->gfx.me.num_queue_per_pipe;
240		me = (i / adev->gfx.me.num_queue_per_pipe)
241		      / adev->gfx.me.num_pipe_per_me;
242
243		if (me >= adev->gfx.me.num_me)
244			break;
245		/* policy: amdgpu owns the first queue per pipe at this stage
246		 * will extend to mulitple queues per pipe later */
247		if (me == 0 && queue < 1)
248			set_bit(i, adev->gfx.me.queue_bitmap);
249	}
250
251	/* update the number of active graphics rings */
252	adev->gfx.num_gfx_rings =
253		bitmap_weight(adev->gfx.me.queue_bitmap, AMDGPU_MAX_GFX_QUEUES);
254}
255
256static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
257				  struct amdgpu_ring *ring)
258{
259	int queue_bit;
260	int mec, pipe, queue;
261
262	queue_bit = adev->gfx.mec.num_mec
263		    * adev->gfx.mec.num_pipe_per_mec
264		    * adev->gfx.mec.num_queue_per_pipe;
265
266	while (--queue_bit >= 0) {
267		if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap))
268			continue;
269
270		amdgpu_queue_mask_bit_to_mec_queue(adev, queue_bit, &mec, &pipe, &queue);
271
272		/*
273		 * 1. Using pipes 2/3 from MEC 2 seems cause problems.
274		 * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
275		 * only can be issued on queue 0.
276		 */
277		if ((mec == 1 && pipe > 1) || queue != 0)
278			continue;
279
280		ring->me = mec + 1;
281		ring->pipe = pipe;
282		ring->queue = queue;
283
284		return 0;
285	}
286
287	dev_err(adev->dev, "Failed to find a queue for KIQ\n");
288	return -EINVAL;
289}
290
291int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
292			     struct amdgpu_ring *ring,
293			     struct amdgpu_irq_src *irq)
294{
295	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
296	int r = 0;
297
298	spin_lock_init(&kiq->ring_lock);
299
300	ring->adev = NULL;
301	ring->ring_obj = NULL;
302	ring->use_doorbell = true;
303	ring->doorbell_index = adev->doorbell_index.kiq;
304
305	r = amdgpu_gfx_kiq_acquire(adev, ring);
306	if (r)
307		return r;
308
309	ring->eop_gpu_addr = kiq->eop_gpu_addr;
310	ring->no_scheduler = true;
311	sprintf(ring->name, "kiq_%d.%d.%d", ring->me, ring->pipe, ring->queue);
312	r = amdgpu_ring_init(adev, ring, 1024,
313			     irq, AMDGPU_CP_KIQ_IRQ_DRIVER0,
314			     AMDGPU_RING_PRIO_DEFAULT);
315	if (r)
316		dev_warn(adev->dev, "(%d) failed to init kiq ring\n", r);
317
318	return r;
319}
320
321void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring)
322{
323	amdgpu_ring_fini(ring);
324}
325
326void amdgpu_gfx_kiq_fini(struct amdgpu_device *adev)
327{
328	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
329
330	amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
331}
332
333int amdgpu_gfx_kiq_init(struct amdgpu_device *adev,
334			unsigned hpd_size)
335{
336	int r;
337	u32 *hpd;
338	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
339
340	r = amdgpu_bo_create_kernel(adev, hpd_size, PAGE_SIZE,
341				    AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
342				    &kiq->eop_gpu_addr, (void **)&hpd);
343	if (r) {
344		dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
345		return r;
346	}
347
348	memset(hpd, 0, hpd_size);
349
350	r = amdgpu_bo_reserve(kiq->eop_obj, true);
351	if (unlikely(r != 0))
352		dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
353	amdgpu_bo_kunmap(kiq->eop_obj);
354	amdgpu_bo_unreserve(kiq->eop_obj);
355
356	return 0;
357}
358
359/* create MQD for each compute/gfx queue */
360int amdgpu_gfx_mqd_sw_init(struct amdgpu_device *adev,
361			   unsigned mqd_size)
362{
363	struct amdgpu_ring *ring = NULL;
364	int r, i;
365
366	/* create MQD for KIQ */
367	ring = &adev->gfx.kiq.ring;
368	if (!ring->mqd_obj) {
369		/* originaly the KIQ MQD is put in GTT domain, but for SRIOV VRAM domain is a must
370		 * otherwise hypervisor trigger SAVE_VF fail after driver unloaded which mean MQD
371		 * deallocated and gart_unbind, to strict diverage we decide to use VRAM domain for
372		 * KIQ MQD no matter SRIOV or Bare-metal
373		 */
374		r = amdgpu_bo_create_kernel(adev, mqd_size, PAGE_SIZE,
375					    AMDGPU_GEM_DOMAIN_VRAM, &ring->mqd_obj,
376					    &ring->mqd_gpu_addr, &ring->mqd_ptr);
377		if (r) {
378			dev_warn(adev->dev, "failed to create ring mqd ob (%d)", r);
379			return r;
380		}
381
382		/* prepare MQD backup */
383		adev->gfx.mec.mqd_backup[AMDGPU_MAX_COMPUTE_RINGS] = kmalloc(mqd_size, GFP_KERNEL);
384		if (!adev->gfx.mec.mqd_backup[AMDGPU_MAX_COMPUTE_RINGS])
385				dev_warn(adev->dev, "no memory to create MQD backup for ring %s\n", ring->name);
386	}
387
388	if (adev->asic_type >= CHIP_NAVI10 && amdgpu_async_gfx_ring) {
389		/* create MQD for each KGQ */
390		for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
391			ring = &adev->gfx.gfx_ring[i];
392			if (!ring->mqd_obj) {
393				r = amdgpu_bo_create_kernel(adev, mqd_size, PAGE_SIZE,
394							    AMDGPU_GEM_DOMAIN_GTT, &ring->mqd_obj,
395							    &ring->mqd_gpu_addr, &ring->mqd_ptr);
396				if (r) {
397					dev_warn(adev->dev, "failed to create ring mqd bo (%d)", r);
398					return r;
399				}
400
401				/* prepare MQD backup */
402				adev->gfx.me.mqd_backup[i] = kmalloc(mqd_size, GFP_KERNEL);
403				if (!adev->gfx.me.mqd_backup[i])
404					dev_warn(adev->dev, "no memory to create MQD backup for ring %s\n", ring->name);
405			}
406		}
407	}
408
409	/* create MQD for each KCQ */
410	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
411		ring = &adev->gfx.compute_ring[i];
412		if (!ring->mqd_obj) {
413			r = amdgpu_bo_create_kernel(adev, mqd_size, PAGE_SIZE,
414						    AMDGPU_GEM_DOMAIN_GTT, &ring->mqd_obj,
415						    &ring->mqd_gpu_addr, &ring->mqd_ptr);
416			if (r) {
417				dev_warn(adev->dev, "failed to create ring mqd bo (%d)", r);
418				return r;
419			}
420
421			/* prepare MQD backup */
422			adev->gfx.mec.mqd_backup[i] = kmalloc(mqd_size, GFP_KERNEL);
423			if (!adev->gfx.mec.mqd_backup[i])
424				dev_warn(adev->dev, "no memory to create MQD backup for ring %s\n", ring->name);
425		}
426	}
427
428	return 0;
429}
430
431void amdgpu_gfx_mqd_sw_fini(struct amdgpu_device *adev)
432{
433	struct amdgpu_ring *ring = NULL;
434	int i;
435
436	if (adev->asic_type >= CHIP_NAVI10 && amdgpu_async_gfx_ring) {
437		for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
438			ring = &adev->gfx.gfx_ring[i];
439			kfree(adev->gfx.me.mqd_backup[i]);
440			amdgpu_bo_free_kernel(&ring->mqd_obj,
441					      &ring->mqd_gpu_addr,
442					      &ring->mqd_ptr);
443		}
444	}
445
446	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
447		ring = &adev->gfx.compute_ring[i];
448		kfree(adev->gfx.mec.mqd_backup[i]);
449		amdgpu_bo_free_kernel(&ring->mqd_obj,
450				      &ring->mqd_gpu_addr,
451				      &ring->mqd_ptr);
452	}
453
454	ring = &adev->gfx.kiq.ring;
455	kfree(adev->gfx.mec.mqd_backup[AMDGPU_MAX_COMPUTE_RINGS]);
456	amdgpu_bo_free_kernel(&ring->mqd_obj,
457			      &ring->mqd_gpu_addr,
458			      &ring->mqd_ptr);
459}
460
461int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev)
462{
463	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
464	struct amdgpu_ring *kiq_ring = &kiq->ring;
465	int i;
466
467	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
468		return -EINVAL;
469
470	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size *
471					adev->gfx.num_compute_rings))
472		return -ENOMEM;
473
474	for (i = 0; i < adev->gfx.num_compute_rings; i++)
475		kiq->pmf->kiq_unmap_queues(kiq_ring, &adev->gfx.compute_ring[i],
476					   RESET_QUEUES, 0, 0);
477
478	return amdgpu_ring_test_helper(kiq_ring);
479}
480
481int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
482					int queue_bit)
483{
484	int mec, pipe, queue;
485	int set_resource_bit = 0;
486
487	amdgpu_queue_mask_bit_to_mec_queue(adev, queue_bit, &mec, &pipe, &queue);
488
489	set_resource_bit = mec * 4 * 8 + pipe * 8 + queue;
490
491	return set_resource_bit;
492}
493
494int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev)
495{
496	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
497	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
498	uint64_t queue_mask = 0;
499	int r, i;
500
501	if (!kiq->pmf || !kiq->pmf->kiq_map_queues || !kiq->pmf->kiq_set_resources)
502		return -EINVAL;
503
504	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
505		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
506			continue;
507
508		/* This situation may be hit in the future if a new HW
509		 * generation exposes more than 64 queues. If so, the
510		 * definition of queue_mask needs updating */
511		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
512			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
513			break;
514		}
515
516		queue_mask |= (1ull << amdgpu_queue_mask_bit_to_set_resource_bit(adev, i));
517	}
518
519	DRM_INFO("kiq ring mec %d pipe %d q %d\n", kiq_ring->me, kiq_ring->pipe,
520							kiq_ring->queue);
521
522	r = amdgpu_ring_alloc(kiq_ring, kiq->pmf->map_queues_size *
523					adev->gfx.num_compute_rings +
524					kiq->pmf->set_resources_size);
525	if (r) {
526		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
527		return r;
528	}
529
530	kiq->pmf->kiq_set_resources(kiq_ring, queue_mask);
531	for (i = 0; i < adev->gfx.num_compute_rings; i++)
532		kiq->pmf->kiq_map_queues(kiq_ring, &adev->gfx.compute_ring[i]);
533
534	r = amdgpu_ring_test_helper(kiq_ring);
535	if (r)
536		DRM_ERROR("KCQ enable failed\n");
537
538	return r;
539}
540
541/* amdgpu_gfx_off_ctrl - Handle gfx off feature enable/disable
542 *
543 * @adev: amdgpu_device pointer
544 * @bool enable true: enable gfx off feature, false: disable gfx off feature
545 *
546 * 1. gfx off feature will be enabled by gfx ip after gfx cg gp enabled.
547 * 2. other client can send request to disable gfx off feature, the request should be honored.
548 * 3. other client can cancel their request of disable gfx off feature
549 * 4. other client should not send request to enable gfx off feature before disable gfx off feature.
550 */
551
552void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
553{
554	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
555		return;
556
557	mutex_lock(&adev->gfx.gfx_off_mutex);
558
559	if (enable) {
560		/* If the count is already 0, it means there's an imbalance bug somewhere.
561		 * Note that the bug may be in a different caller than the one which triggers the
562		 * WARN_ON_ONCE.
563		 */
564		if (WARN_ON_ONCE(adev->gfx.gfx_off_req_count == 0))
565			goto unlock;
566
567		adev->gfx.gfx_off_req_count--;
568
569		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
570			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
571	} else {
572		if (adev->gfx.gfx_off_req_count == 0) {
573			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
574
575			if (adev->gfx.gfx_off_state &&
576			    !amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
577				adev->gfx.gfx_off_state = false;
578
579				if (adev->gfx.funcs->init_spm_golden) {
580					dev_dbg(adev->dev,
581						"GFXOFF is disabled, re-init SPM golden settings\n");
582					amdgpu_gfx_init_spm_golden(adev);
583				}
584			}
585		}
586
587		adev->gfx.gfx_off_req_count++;
588	}
589
590unlock:
591	mutex_unlock(&adev->gfx.gfx_off_mutex);
592}
593
594int amdgpu_get_gfx_off_status(struct amdgpu_device *adev, uint32_t *value)
595{
596
597	int r = 0;
598
599	mutex_lock(&adev->gfx.gfx_off_mutex);
600
601	r = smu_get_status_gfxoff(adev, value);
602
603	mutex_unlock(&adev->gfx.gfx_off_mutex);
604
605	return r;
606}
607
608int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
609{
610	int r;
611	struct ras_fs_if fs_info = {
612		.sysfs_name = "gfx_err_count",
613	};
614	struct ras_ih_if ih_info = {
615		.cb = amdgpu_gfx_process_ras_data_cb,
616	};
617
618	if (!adev->gfx.ras_if) {
619		adev->gfx.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
620		if (!adev->gfx.ras_if)
621			return -ENOMEM;
622		adev->gfx.ras_if->block = AMDGPU_RAS_BLOCK__GFX;
623		adev->gfx.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
624		adev->gfx.ras_if->sub_block_index = 0;
625		strcpy(adev->gfx.ras_if->name, "gfx");
626	}
627	fs_info.head = ih_info.head = *adev->gfx.ras_if;
628
629	r = amdgpu_ras_late_init(adev, adev->gfx.ras_if,
630				 &fs_info, &ih_info);
631	if (r)
632		goto free;
633
634	if (amdgpu_ras_is_supported(adev, adev->gfx.ras_if->block)) {
635		r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
636		if (r)
637			goto late_fini;
638	} else {
639		/* free gfx ras_if if ras is not supported */
640		r = 0;
641		goto free;
642	}
643
644	return 0;
645late_fini:
646	amdgpu_ras_late_fini(adev, adev->gfx.ras_if, &ih_info);
647free:
648	kfree(adev->gfx.ras_if);
649	adev->gfx.ras_if = NULL;
650	return r;
651}
652
653void amdgpu_gfx_ras_fini(struct amdgpu_device *adev)
654{
655	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX) &&
656			adev->gfx.ras_if) {
657		struct ras_common_if *ras_if = adev->gfx.ras_if;
658		struct ras_ih_if ih_info = {
659			.head = *ras_if,
660			.cb = amdgpu_gfx_process_ras_data_cb,
661		};
662
663		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
664		kfree(ras_if);
665	}
666}
667
668int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
669		void *err_data,
670		struct amdgpu_iv_entry *entry)
671{
672	/* TODO ue will trigger an interrupt.
673	 *
674	 * When “Full RAS” is enabled, the per-IP interrupt sources should
675	 * be disabled and the driver should only look for the aggregated
676	 * interrupt via sync flood
677	 */
678	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) {
679		kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
680		if (adev->gfx.funcs->query_ras_error_count)
681			adev->gfx.funcs->query_ras_error_count(adev, err_data);
682		amdgpu_ras_reset_gpu(adev);
683	}
684	return AMDGPU_RAS_SUCCESS;
685}
686
687int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev,
688				  struct amdgpu_irq_src *source,
689				  struct amdgpu_iv_entry *entry)
690{
691	struct ras_common_if *ras_if = adev->gfx.ras_if;
692	struct ras_dispatch_if ih_data = {
693		.entry = entry,
694	};
695
696	if (!ras_if)
697		return 0;
698
699	ih_data.head = *ras_if;
700
701	DRM_ERROR("CP ECC ERROR IRQ\n");
702	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
703	return 0;
704}
705
706uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
707{
708	signed long r, cnt = 0;
709	unsigned long flags;
710	uint32_t seq, reg_val_offs = 0, value = 0;
711	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
712	struct amdgpu_ring *ring = &kiq->ring;
713
714	if (adev->in_pci_err_recovery)
715		return 0;
716
717	BUG_ON(!ring->funcs->emit_rreg);
718
719	spin_lock_irqsave(&kiq->ring_lock, flags);
720	if (amdgpu_device_wb_get(adev, &reg_val_offs)) {
721		pr_err("critical bug! too many kiq readers\n");
722		goto failed_unlock;
723	}
724	amdgpu_ring_alloc(ring, 32);
725	amdgpu_ring_emit_rreg(ring, reg, reg_val_offs);
726	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
727	if (r)
728		goto failed_undo;
729
730	amdgpu_ring_commit(ring);
731	spin_unlock_irqrestore(&kiq->ring_lock, flags);
732
733	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
734
735	/* don't wait anymore for gpu reset case because this way may
736	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
737	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
738	 * never return if we keep waiting in virt_kiq_rreg, which cause
739	 * gpu_recover() hang there.
740	 *
741	 * also don't wait anymore for IRQ context
742	 * */
743	if (r < 1 && (amdgpu_in_reset(adev) || in_interrupt()))
744		goto failed_kiq_read;
745
746	might_sleep();
747	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
748		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
749		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
750	}
751
752	if (cnt > MAX_KIQ_REG_TRY)
753		goto failed_kiq_read;
754
755	mb();
756	value = adev->wb.wb[reg_val_offs];
757	amdgpu_device_wb_free(adev, reg_val_offs);
758	return value;
759
760failed_undo:
761	amdgpu_ring_undo(ring);
762failed_unlock:
763	spin_unlock_irqrestore(&kiq->ring_lock, flags);
764failed_kiq_read:
765	if (reg_val_offs)
766		amdgpu_device_wb_free(adev, reg_val_offs);
767	dev_err(adev->dev, "failed to read reg:%x\n", reg);
768	return ~0;
769}
770
771void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
772{
773	signed long r, cnt = 0;
774	unsigned long flags;
775	uint32_t seq;
776	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
777	struct amdgpu_ring *ring = &kiq->ring;
778
779	BUG_ON(!ring->funcs->emit_wreg);
780
781	if (adev->in_pci_err_recovery)
782		return;
783
784	spin_lock_irqsave(&kiq->ring_lock, flags);
785	amdgpu_ring_alloc(ring, 32);
786	amdgpu_ring_emit_wreg(ring, reg, v);
787	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
788	if (r)
789		goto failed_undo;
790
791	amdgpu_ring_commit(ring);
792	spin_unlock_irqrestore(&kiq->ring_lock, flags);
793
794	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
795
796	/* don't wait anymore for gpu reset case because this way may
797	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
798	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
799	 * never return if we keep waiting in virt_kiq_rreg, which cause
800	 * gpu_recover() hang there.
801	 *
802	 * also don't wait anymore for IRQ context
803	 * */
804	if (r < 1 && (amdgpu_in_reset(adev) || in_interrupt()))
805		goto failed_kiq_write;
806
807	might_sleep();
808	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
809
810		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
811		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
812	}
813
814	if (cnt > MAX_KIQ_REG_TRY)
815		goto failed_kiq_write;
816
817	return;
818
819failed_undo:
820	amdgpu_ring_undo(ring);
821	spin_unlock_irqrestore(&kiq->ring_lock, flags);
822failed_kiq_write:
823	dev_err(adev->dev, "failed to write reg:%x\n", reg);
824}
825