1/*
2 * Copyright 2014 Advanced Micro Devices, Inc.
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
17 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
18 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
19 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
20 * OTHER DEALINGS IN THE SOFTWARE.
21 */
22
23#include <linux/bsearch.h>
24#include <linux/pci.h>
25#include <linux/slab.h>
26#include "kfd_priv.h"
27#include "kfd_device_queue_manager.h"
28#include "kfd_pm4_headers_vi.h"
29#include "cwsr_trap_handler.h"
30#include "kfd_iommu.h"
31#include "amdgpu_amdkfd.h"
32#include "kfd_smi_events.h"
33
34#define MQD_SIZE_ALIGNED 768
35
36/*
37 * kfd_locked is used to lock the kfd driver during suspend or reset
38 * once locked, kfd driver will stop any further GPU execution.
39 * create process (open) will return -EAGAIN.
40 */
41static atomic_t kfd_locked = ATOMIC_INIT(0);
42
43#ifdef CONFIG_DRM_AMDGPU_CIK
44extern const struct kfd2kgd_calls gfx_v7_kfd2kgd;
45#endif
46extern const struct kfd2kgd_calls gfx_v8_kfd2kgd;
47extern const struct kfd2kgd_calls gfx_v9_kfd2kgd;
48extern const struct kfd2kgd_calls arcturus_kfd2kgd;
49extern const struct kfd2kgd_calls gfx_v10_kfd2kgd;
50extern const struct kfd2kgd_calls gfx_v10_3_kfd2kgd;
51
52static const struct kfd2kgd_calls *kfd2kgd_funcs[] = {
53#ifdef KFD_SUPPORT_IOMMU_V2
54#ifdef CONFIG_DRM_AMDGPU_CIK
55	[CHIP_KAVERI] = &gfx_v7_kfd2kgd,
56#endif
57	[CHIP_CARRIZO] = &gfx_v8_kfd2kgd,
58	[CHIP_RAVEN] = &gfx_v9_kfd2kgd,
59#endif
60#ifdef CONFIG_DRM_AMDGPU_CIK
61	[CHIP_HAWAII] = &gfx_v7_kfd2kgd,
62#endif
63	[CHIP_TONGA] = &gfx_v8_kfd2kgd,
64	[CHIP_FIJI] = &gfx_v8_kfd2kgd,
65	[CHIP_POLARIS10] = &gfx_v8_kfd2kgd,
66	[CHIP_POLARIS11] = &gfx_v8_kfd2kgd,
67	[CHIP_POLARIS12] = &gfx_v8_kfd2kgd,
68	[CHIP_VEGAM] = &gfx_v8_kfd2kgd,
69	[CHIP_VEGA10] = &gfx_v9_kfd2kgd,
70	[CHIP_VEGA12] = &gfx_v9_kfd2kgd,
71	[CHIP_VEGA20] = &gfx_v9_kfd2kgd,
72	[CHIP_RENOIR] = &gfx_v9_kfd2kgd,
73	[CHIP_ARCTURUS] = &arcturus_kfd2kgd,
74	[CHIP_NAVI10] = &gfx_v10_kfd2kgd,
75	[CHIP_NAVI12] = &gfx_v10_kfd2kgd,
76	[CHIP_NAVI14] = &gfx_v10_kfd2kgd,
77	[CHIP_SIENNA_CICHLID] = &gfx_v10_3_kfd2kgd,
78	[CHIP_NAVY_FLOUNDER] = &gfx_v10_3_kfd2kgd,
79};
80
81#ifdef KFD_SUPPORT_IOMMU_V2
82static const struct kfd_device_info kaveri_device_info = {
83	.asic_family = CHIP_KAVERI,
84	.asic_name = "kaveri",
85	.max_pasid_bits = 16,
86	/* max num of queues for KV.TODO should be a dynamic value */
87	.max_no_of_hqd	= 24,
88	.doorbell_size  = 4,
89	.ih_ring_entry_size = 4 * sizeof(uint32_t),
90	.event_interrupt_class = &event_interrupt_class_cik,
91	.num_of_watch_points = 4,
92	.mqd_size_aligned = MQD_SIZE_ALIGNED,
93	.supports_cwsr = false,
94	.needs_iommu_device = true,
95	.needs_pci_atomics = false,
96	.num_sdma_engines = 2,
97	.num_xgmi_sdma_engines = 0,
98	.num_sdma_queues_per_engine = 2,
99};
100
101static const struct kfd_device_info carrizo_device_info = {
102	.asic_family = CHIP_CARRIZO,
103	.asic_name = "carrizo",
104	.max_pasid_bits = 16,
105	/* max num of queues for CZ.TODO should be a dynamic value */
106	.max_no_of_hqd	= 24,
107	.doorbell_size  = 4,
108	.ih_ring_entry_size = 4 * sizeof(uint32_t),
109	.event_interrupt_class = &event_interrupt_class_cik,
110	.num_of_watch_points = 4,
111	.mqd_size_aligned = MQD_SIZE_ALIGNED,
112	.supports_cwsr = true,
113	.needs_iommu_device = true,
114	.needs_pci_atomics = false,
115	.num_sdma_engines = 2,
116	.num_xgmi_sdma_engines = 0,
117	.num_sdma_queues_per_engine = 2,
118};
119#endif
120
121static const struct kfd_device_info raven_device_info = {
122	.asic_family = CHIP_RAVEN,
123	.asic_name = "raven",
124	.max_pasid_bits = 16,
125	.max_no_of_hqd  = 24,
126	.doorbell_size  = 8,
127	.ih_ring_entry_size = 8 * sizeof(uint32_t),
128	.event_interrupt_class = &event_interrupt_class_v9,
129	.num_of_watch_points = 4,
130	.mqd_size_aligned = MQD_SIZE_ALIGNED,
131	.supports_cwsr = true,
132	.needs_iommu_device = true,
133	.needs_pci_atomics = true,
134	.num_sdma_engines = 1,
135	.num_xgmi_sdma_engines = 0,
136	.num_sdma_queues_per_engine = 2,
137};
138
139static const struct kfd_device_info hawaii_device_info = {
140	.asic_family = CHIP_HAWAII,
141	.asic_name = "hawaii",
142	.max_pasid_bits = 16,
143	/* max num of queues for KV.TODO should be a dynamic value */
144	.max_no_of_hqd	= 24,
145	.doorbell_size  = 4,
146	.ih_ring_entry_size = 4 * sizeof(uint32_t),
147	.event_interrupt_class = &event_interrupt_class_cik,
148	.num_of_watch_points = 4,
149	.mqd_size_aligned = MQD_SIZE_ALIGNED,
150	.supports_cwsr = false,
151	.needs_iommu_device = false,
152	.needs_pci_atomics = false,
153	.num_sdma_engines = 2,
154	.num_xgmi_sdma_engines = 0,
155	.num_sdma_queues_per_engine = 2,
156};
157
158static const struct kfd_device_info tonga_device_info = {
159	.asic_family = CHIP_TONGA,
160	.asic_name = "tonga",
161	.max_pasid_bits = 16,
162	.max_no_of_hqd  = 24,
163	.doorbell_size  = 4,
164	.ih_ring_entry_size = 4 * sizeof(uint32_t),
165	.event_interrupt_class = &event_interrupt_class_cik,
166	.num_of_watch_points = 4,
167	.mqd_size_aligned = MQD_SIZE_ALIGNED,
168	.supports_cwsr = false,
169	.needs_iommu_device = false,
170	.needs_pci_atomics = true,
171	.num_sdma_engines = 2,
172	.num_xgmi_sdma_engines = 0,
173	.num_sdma_queues_per_engine = 2,
174};
175
176static const struct kfd_device_info fiji_device_info = {
177	.asic_family = CHIP_FIJI,
178	.asic_name = "fiji",
179	.max_pasid_bits = 16,
180	.max_no_of_hqd  = 24,
181	.doorbell_size  = 4,
182	.ih_ring_entry_size = 4 * sizeof(uint32_t),
183	.event_interrupt_class = &event_interrupt_class_cik,
184	.num_of_watch_points = 4,
185	.mqd_size_aligned = MQD_SIZE_ALIGNED,
186	.supports_cwsr = true,
187	.needs_iommu_device = false,
188	.needs_pci_atomics = true,
189	.num_sdma_engines = 2,
190	.num_xgmi_sdma_engines = 0,
191	.num_sdma_queues_per_engine = 2,
192};
193
194static const struct kfd_device_info fiji_vf_device_info = {
195	.asic_family = CHIP_FIJI,
196	.asic_name = "fiji",
197	.max_pasid_bits = 16,
198	.max_no_of_hqd  = 24,
199	.doorbell_size  = 4,
200	.ih_ring_entry_size = 4 * sizeof(uint32_t),
201	.event_interrupt_class = &event_interrupt_class_cik,
202	.num_of_watch_points = 4,
203	.mqd_size_aligned = MQD_SIZE_ALIGNED,
204	.supports_cwsr = true,
205	.needs_iommu_device = false,
206	.needs_pci_atomics = false,
207	.num_sdma_engines = 2,
208	.num_xgmi_sdma_engines = 0,
209	.num_sdma_queues_per_engine = 2,
210};
211
212
213static const struct kfd_device_info polaris10_device_info = {
214	.asic_family = CHIP_POLARIS10,
215	.asic_name = "polaris10",
216	.max_pasid_bits = 16,
217	.max_no_of_hqd  = 24,
218	.doorbell_size  = 4,
219	.ih_ring_entry_size = 4 * sizeof(uint32_t),
220	.event_interrupt_class = &event_interrupt_class_cik,
221	.num_of_watch_points = 4,
222	.mqd_size_aligned = MQD_SIZE_ALIGNED,
223	.supports_cwsr = true,
224	.needs_iommu_device = false,
225	.needs_pci_atomics = true,
226	.num_sdma_engines = 2,
227	.num_xgmi_sdma_engines = 0,
228	.num_sdma_queues_per_engine = 2,
229};
230
231static const struct kfd_device_info polaris10_vf_device_info = {
232	.asic_family = CHIP_POLARIS10,
233	.asic_name = "polaris10",
234	.max_pasid_bits = 16,
235	.max_no_of_hqd  = 24,
236	.doorbell_size  = 4,
237	.ih_ring_entry_size = 4 * sizeof(uint32_t),
238	.event_interrupt_class = &event_interrupt_class_cik,
239	.num_of_watch_points = 4,
240	.mqd_size_aligned = MQD_SIZE_ALIGNED,
241	.supports_cwsr = true,
242	.needs_iommu_device = false,
243	.needs_pci_atomics = false,
244	.num_sdma_engines = 2,
245	.num_xgmi_sdma_engines = 0,
246	.num_sdma_queues_per_engine = 2,
247};
248
249static const struct kfd_device_info polaris11_device_info = {
250	.asic_family = CHIP_POLARIS11,
251	.asic_name = "polaris11",
252	.max_pasid_bits = 16,
253	.max_no_of_hqd  = 24,
254	.doorbell_size  = 4,
255	.ih_ring_entry_size = 4 * sizeof(uint32_t),
256	.event_interrupt_class = &event_interrupt_class_cik,
257	.num_of_watch_points = 4,
258	.mqd_size_aligned = MQD_SIZE_ALIGNED,
259	.supports_cwsr = true,
260	.needs_iommu_device = false,
261	.needs_pci_atomics = true,
262	.num_sdma_engines = 2,
263	.num_xgmi_sdma_engines = 0,
264	.num_sdma_queues_per_engine = 2,
265};
266
267static const struct kfd_device_info polaris12_device_info = {
268	.asic_family = CHIP_POLARIS12,
269	.asic_name = "polaris12",
270	.max_pasid_bits = 16,
271	.max_no_of_hqd  = 24,
272	.doorbell_size  = 4,
273	.ih_ring_entry_size = 4 * sizeof(uint32_t),
274	.event_interrupt_class = &event_interrupt_class_cik,
275	.num_of_watch_points = 4,
276	.mqd_size_aligned = MQD_SIZE_ALIGNED,
277	.supports_cwsr = true,
278	.needs_iommu_device = false,
279	.needs_pci_atomics = true,
280	.num_sdma_engines = 2,
281	.num_xgmi_sdma_engines = 0,
282	.num_sdma_queues_per_engine = 2,
283};
284
285static const struct kfd_device_info vegam_device_info = {
286	.asic_family = CHIP_VEGAM,
287	.asic_name = "vegam",
288	.max_pasid_bits = 16,
289	.max_no_of_hqd  = 24,
290	.doorbell_size  = 4,
291	.ih_ring_entry_size = 4 * sizeof(uint32_t),
292	.event_interrupt_class = &event_interrupt_class_cik,
293	.num_of_watch_points = 4,
294	.mqd_size_aligned = MQD_SIZE_ALIGNED,
295	.supports_cwsr = true,
296	.needs_iommu_device = false,
297	.needs_pci_atomics = true,
298	.num_sdma_engines = 2,
299	.num_xgmi_sdma_engines = 0,
300	.num_sdma_queues_per_engine = 2,
301};
302
303static const struct kfd_device_info vega10_device_info = {
304	.asic_family = CHIP_VEGA10,
305	.asic_name = "vega10",
306	.max_pasid_bits = 16,
307	.max_no_of_hqd  = 24,
308	.doorbell_size  = 8,
309	.ih_ring_entry_size = 8 * sizeof(uint32_t),
310	.event_interrupt_class = &event_interrupt_class_v9,
311	.num_of_watch_points = 4,
312	.mqd_size_aligned = MQD_SIZE_ALIGNED,
313	.supports_cwsr = true,
314	.needs_iommu_device = false,
315	.needs_pci_atomics = false,
316	.num_sdma_engines = 2,
317	.num_xgmi_sdma_engines = 0,
318	.num_sdma_queues_per_engine = 2,
319};
320
321static const struct kfd_device_info vega10_vf_device_info = {
322	.asic_family = CHIP_VEGA10,
323	.asic_name = "vega10",
324	.max_pasid_bits = 16,
325	.max_no_of_hqd  = 24,
326	.doorbell_size  = 8,
327	.ih_ring_entry_size = 8 * sizeof(uint32_t),
328	.event_interrupt_class = &event_interrupt_class_v9,
329	.num_of_watch_points = 4,
330	.mqd_size_aligned = MQD_SIZE_ALIGNED,
331	.supports_cwsr = true,
332	.needs_iommu_device = false,
333	.needs_pci_atomics = false,
334	.num_sdma_engines = 2,
335	.num_xgmi_sdma_engines = 0,
336	.num_sdma_queues_per_engine = 2,
337};
338
339static const struct kfd_device_info vega12_device_info = {
340	.asic_family = CHIP_VEGA12,
341	.asic_name = "vega12",
342	.max_pasid_bits = 16,
343	.max_no_of_hqd  = 24,
344	.doorbell_size  = 8,
345	.ih_ring_entry_size = 8 * sizeof(uint32_t),
346	.event_interrupt_class = &event_interrupt_class_v9,
347	.num_of_watch_points = 4,
348	.mqd_size_aligned = MQD_SIZE_ALIGNED,
349	.supports_cwsr = true,
350	.needs_iommu_device = false,
351	.needs_pci_atomics = false,
352	.num_sdma_engines = 2,
353	.num_xgmi_sdma_engines = 0,
354	.num_sdma_queues_per_engine = 2,
355};
356
357static const struct kfd_device_info vega20_device_info = {
358	.asic_family = CHIP_VEGA20,
359	.asic_name = "vega20",
360	.max_pasid_bits = 16,
361	.max_no_of_hqd	= 24,
362	.doorbell_size	= 8,
363	.ih_ring_entry_size = 8 * sizeof(uint32_t),
364	.event_interrupt_class = &event_interrupt_class_v9,
365	.num_of_watch_points = 4,
366	.mqd_size_aligned = MQD_SIZE_ALIGNED,
367	.supports_cwsr = true,
368	.needs_iommu_device = false,
369	.needs_pci_atomics = false,
370	.num_sdma_engines = 2,
371	.num_xgmi_sdma_engines = 0,
372	.num_sdma_queues_per_engine = 8,
373};
374
375static const struct kfd_device_info arcturus_device_info = {
376	.asic_family = CHIP_ARCTURUS,
377	.asic_name = "arcturus",
378	.max_pasid_bits = 16,
379	.max_no_of_hqd	= 24,
380	.doorbell_size	= 8,
381	.ih_ring_entry_size = 8 * sizeof(uint32_t),
382	.event_interrupt_class = &event_interrupt_class_v9,
383	.num_of_watch_points = 4,
384	.mqd_size_aligned = MQD_SIZE_ALIGNED,
385	.supports_cwsr = true,
386	.needs_iommu_device = false,
387	.needs_pci_atomics = false,
388	.num_sdma_engines = 2,
389	.num_xgmi_sdma_engines = 6,
390	.num_sdma_queues_per_engine = 8,
391};
392
393static const struct kfd_device_info renoir_device_info = {
394	.asic_family = CHIP_RENOIR,
395	.asic_name = "renoir",
396	.max_pasid_bits = 16,
397	.max_no_of_hqd  = 24,
398	.doorbell_size  = 8,
399	.ih_ring_entry_size = 8 * sizeof(uint32_t),
400	.event_interrupt_class = &event_interrupt_class_v9,
401	.num_of_watch_points = 4,
402	.mqd_size_aligned = MQD_SIZE_ALIGNED,
403	.supports_cwsr = true,
404	.needs_iommu_device = false,
405	.needs_pci_atomics = false,
406	.num_sdma_engines = 1,
407	.num_xgmi_sdma_engines = 0,
408	.num_sdma_queues_per_engine = 2,
409};
410
411static const struct kfd_device_info navi10_device_info = {
412	.asic_family = CHIP_NAVI10,
413	.asic_name = "navi10",
414	.max_pasid_bits = 16,
415	.max_no_of_hqd  = 24,
416	.doorbell_size  = 8,
417	.ih_ring_entry_size = 8 * sizeof(uint32_t),
418	.event_interrupt_class = &event_interrupt_class_v9,
419	.num_of_watch_points = 4,
420	.mqd_size_aligned = MQD_SIZE_ALIGNED,
421	.needs_iommu_device = false,
422	.supports_cwsr = true,
423	.needs_pci_atomics = false,
424	.num_sdma_engines = 2,
425	.num_xgmi_sdma_engines = 0,
426	.num_sdma_queues_per_engine = 8,
427};
428
429static const struct kfd_device_info navi12_device_info = {
430	.asic_family = CHIP_NAVI12,
431	.asic_name = "navi12",
432	.max_pasid_bits = 16,
433	.max_no_of_hqd  = 24,
434	.doorbell_size  = 8,
435	.ih_ring_entry_size = 8 * sizeof(uint32_t),
436	.event_interrupt_class = &event_interrupt_class_v9,
437	.num_of_watch_points = 4,
438	.mqd_size_aligned = MQD_SIZE_ALIGNED,
439	.needs_iommu_device = false,
440	.supports_cwsr = true,
441	.needs_pci_atomics = false,
442	.num_sdma_engines = 2,
443	.num_xgmi_sdma_engines = 0,
444	.num_sdma_queues_per_engine = 8,
445};
446
447static const struct kfd_device_info navi14_device_info = {
448	.asic_family = CHIP_NAVI14,
449	.asic_name = "navi14",
450	.max_pasid_bits = 16,
451	.max_no_of_hqd  = 24,
452	.doorbell_size  = 8,
453	.ih_ring_entry_size = 8 * sizeof(uint32_t),
454	.event_interrupt_class = &event_interrupt_class_v9,
455	.num_of_watch_points = 4,
456	.mqd_size_aligned = MQD_SIZE_ALIGNED,
457	.needs_iommu_device = false,
458	.supports_cwsr = true,
459	.needs_pci_atomics = false,
460	.num_sdma_engines = 2,
461	.num_xgmi_sdma_engines = 0,
462	.num_sdma_queues_per_engine = 8,
463};
464
465static const struct kfd_device_info sienna_cichlid_device_info = {
466	.asic_family = CHIP_SIENNA_CICHLID,
467	.asic_name = "sienna_cichlid",
468	.max_pasid_bits = 16,
469	.max_no_of_hqd  = 24,
470	.doorbell_size  = 8,
471	.ih_ring_entry_size = 8 * sizeof(uint32_t),
472	.event_interrupt_class = &event_interrupt_class_v9,
473	.num_of_watch_points = 4,
474	.mqd_size_aligned = MQD_SIZE_ALIGNED,
475	.needs_iommu_device = false,
476	.supports_cwsr = true,
477	.needs_pci_atomics = false,
478	.num_sdma_engines = 4,
479	.num_xgmi_sdma_engines = 0,
480	.num_sdma_queues_per_engine = 8,
481};
482
483static const struct kfd_device_info navy_flounder_device_info = {
484	.asic_family = CHIP_NAVY_FLOUNDER,
485	.asic_name = "navy_flounder",
486	.max_pasid_bits = 16,
487	.max_no_of_hqd  = 24,
488	.doorbell_size  = 8,
489	.ih_ring_entry_size = 8 * sizeof(uint32_t),
490	.event_interrupt_class = &event_interrupt_class_v9,
491	.num_of_watch_points = 4,
492	.mqd_size_aligned = MQD_SIZE_ALIGNED,
493	.needs_iommu_device = false,
494	.supports_cwsr = true,
495	.needs_pci_atomics = false,
496	.num_sdma_engines = 2,
497	.num_xgmi_sdma_engines = 0,
498	.num_sdma_queues_per_engine = 8,
499};
500
501/* For each entry, [0] is regular and [1] is virtualisation device. */
502static const struct kfd_device_info *kfd_supported_devices[][2] = {
503#ifdef KFD_SUPPORT_IOMMU_V2
504	[CHIP_KAVERI] = {&kaveri_device_info, NULL},
505	[CHIP_CARRIZO] = {&carrizo_device_info, NULL},
506#endif
507	[CHIP_RAVEN] = {&raven_device_info, NULL},
508	[CHIP_HAWAII] = {&hawaii_device_info, NULL},
509	[CHIP_TONGA] = {&tonga_device_info, NULL},
510	[CHIP_FIJI] = {&fiji_device_info, &fiji_vf_device_info},
511	[CHIP_POLARIS10] = {&polaris10_device_info, &polaris10_vf_device_info},
512	[CHIP_POLARIS11] = {&polaris11_device_info, NULL},
513	[CHIP_POLARIS12] = {&polaris12_device_info, NULL},
514	[CHIP_VEGAM] = {&vegam_device_info, NULL},
515	[CHIP_VEGA10] = {&vega10_device_info, &vega10_vf_device_info},
516	[CHIP_VEGA12] = {&vega12_device_info, NULL},
517	[CHIP_VEGA20] = {&vega20_device_info, NULL},
518	[CHIP_RENOIR] = {&renoir_device_info, NULL},
519	[CHIP_ARCTURUS] = {&arcturus_device_info, &arcturus_device_info},
520	[CHIP_NAVI10] = {&navi10_device_info, NULL},
521	[CHIP_NAVI12] = {&navi12_device_info, &navi12_device_info},
522	[CHIP_NAVI14] = {&navi14_device_info, NULL},
523	[CHIP_SIENNA_CICHLID] = {&sienna_cichlid_device_info, &sienna_cichlid_device_info},
524	[CHIP_NAVY_FLOUNDER] = {&navy_flounder_device_info, &navy_flounder_device_info},
525};
526
527static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
528				unsigned int chunk_size);
529static void kfd_gtt_sa_fini(struct kfd_dev *kfd);
530
531static int kfd_resume(struct kfd_dev *kfd);
532
533struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
534	struct pci_dev *pdev, unsigned int asic_type, bool vf)
535{
536	struct kfd_dev *kfd;
537	const struct kfd_device_info *device_info;
538	const struct kfd2kgd_calls *f2g;
539
540	if (asic_type >= sizeof(kfd_supported_devices) / (sizeof(void *) * 2)
541		|| asic_type >= sizeof(kfd2kgd_funcs) / sizeof(void *)) {
542		dev_err(kfd_device, "asic_type %d out of range\n", asic_type);
543		return NULL; /* asic_type out of range */
544	}
545
546	device_info = kfd_supported_devices[asic_type][vf];
547	f2g = kfd2kgd_funcs[asic_type];
548
549	if (!device_info || !f2g) {
550		dev_err(kfd_device, "%s %s not supported in kfd\n",
551			amdgpu_asic_name[asic_type], vf ? "VF" : "");
552		return NULL;
553	}
554
555	kfd = kzalloc(sizeof(*kfd), GFP_KERNEL);
556	if (!kfd)
557		return NULL;
558
559	/* Allow BIF to recode atomics to PCIe 3.0 AtomicOps.
560	 * 32 and 64-bit requests are possible and must be
561	 * supported.
562	 */
563	kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kgd);
564	if (device_info->needs_pci_atomics &&
565	    !kfd->pci_atomic_requested) {
566		dev_info(kfd_device,
567			 "skipped device %x:%x, PCI rejects atomics\n",
568			 pdev->vendor, pdev->device);
569		kfree(kfd);
570		return NULL;
571	}
572
573	kfd->kgd = kgd;
574	kfd->device_info = device_info;
575	kfd->pdev = pdev;
576	kfd->init_complete = false;
577	kfd->kfd2kgd = f2g;
578	atomic_set(&kfd->compute_profile, 0);
579
580	mutex_init(&kfd->doorbell_mutex);
581	memset(&kfd->doorbell_available_index, 0,
582		sizeof(kfd->doorbell_available_index));
583
584	atomic_set(&kfd->sram_ecc_flag, 0);
585
586	ida_init(&kfd->doorbell_ida);
587
588	return kfd;
589}
590
591static void kfd_cwsr_init(struct kfd_dev *kfd)
592{
593	if (cwsr_enable && kfd->device_info->supports_cwsr) {
594		if (kfd->device_info->asic_family < CHIP_VEGA10) {
595			BUILD_BUG_ON(sizeof(cwsr_trap_gfx8_hex) > PAGE_SIZE);
596			kfd->cwsr_isa = cwsr_trap_gfx8_hex;
597			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx8_hex);
598		} else if (kfd->device_info->asic_family == CHIP_ARCTURUS) {
599			BUILD_BUG_ON(sizeof(cwsr_trap_arcturus_hex) > PAGE_SIZE);
600			kfd->cwsr_isa = cwsr_trap_arcturus_hex;
601			kfd->cwsr_isa_size = sizeof(cwsr_trap_arcturus_hex);
602		} else if (kfd->device_info->asic_family < CHIP_NAVI10) {
603			BUILD_BUG_ON(sizeof(cwsr_trap_gfx9_hex) > PAGE_SIZE);
604			kfd->cwsr_isa = cwsr_trap_gfx9_hex;
605			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx9_hex);
606		} else if (kfd->device_info->asic_family < CHIP_SIENNA_CICHLID) {
607			BUILD_BUG_ON(sizeof(cwsr_trap_nv1x_hex) > PAGE_SIZE);
608			kfd->cwsr_isa = cwsr_trap_nv1x_hex;
609			kfd->cwsr_isa_size = sizeof(cwsr_trap_nv1x_hex);
610		} else {
611			BUILD_BUG_ON(sizeof(cwsr_trap_gfx10_hex) > PAGE_SIZE);
612			kfd->cwsr_isa = cwsr_trap_gfx10_hex;
613			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx10_hex);
614		}
615
616		kfd->cwsr_enabled = true;
617	}
618}
619
620static int kfd_gws_init(struct kfd_dev *kfd)
621{
622	int ret = 0;
623
624	if (kfd->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS)
625		return 0;
626
627	if (hws_gws_support
628		|| (kfd->device_info->asic_family == CHIP_VEGA10
629			&& kfd->mec2_fw_version >= 0x81b3)
630		|| (kfd->device_info->asic_family >= CHIP_VEGA12
631			&& kfd->device_info->asic_family <= CHIP_RAVEN
632			&& kfd->mec2_fw_version >= 0x1b3)
633		|| (kfd->device_info->asic_family == CHIP_ARCTURUS
634			&& kfd->mec2_fw_version >= 0x30))
635		ret = amdgpu_amdkfd_alloc_gws(kfd->kgd,
636				amdgpu_amdkfd_get_num_gws(kfd->kgd), &kfd->gws);
637
638	return ret;
639}
640
641static void kfd_smi_init(struct kfd_dev *dev) {
642	INIT_LIST_HEAD(&dev->smi_clients);
643	spin_lock_init(&dev->smi_lock);
644}
645
646bool kgd2kfd_device_init(struct kfd_dev *kfd,
647			 struct drm_device *ddev,
648			 const struct kgd2kfd_shared_resources *gpu_resources)
649{
650	unsigned int size;
651
652	kfd->ddev = ddev;
653	kfd->mec_fw_version = amdgpu_amdkfd_get_fw_version(kfd->kgd,
654			KGD_ENGINE_MEC1);
655	kfd->mec2_fw_version = amdgpu_amdkfd_get_fw_version(kfd->kgd,
656			KGD_ENGINE_MEC2);
657	kfd->sdma_fw_version = amdgpu_amdkfd_get_fw_version(kfd->kgd,
658			KGD_ENGINE_SDMA1);
659	kfd->shared_resources = *gpu_resources;
660
661	kfd->vm_info.first_vmid_kfd = ffs(gpu_resources->compute_vmid_bitmap)-1;
662	kfd->vm_info.last_vmid_kfd = fls(gpu_resources->compute_vmid_bitmap)-1;
663	kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd
664			- kfd->vm_info.first_vmid_kfd + 1;
665
666	/* Verify module parameters regarding mapped process number*/
667	if (hws_max_conc_proc >= 0)
668		kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd);
669	else
670		kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd;
671
672	/* calculate max size of mqds needed for queues */
673	size = max_num_of_queues_per_device *
674			kfd->device_info->mqd_size_aligned;
675
676	/*
677	 * calculate max size of runlist packet.
678	 * There can be only 2 packets at once
679	 */
680	size += (KFD_MAX_NUM_OF_PROCESSES * sizeof(struct pm4_mes_map_process) +
681		max_num_of_queues_per_device * sizeof(struct pm4_mes_map_queues)
682		+ sizeof(struct pm4_mes_runlist)) * 2;
683
684	/* Add size of HIQ & DIQ */
685	size += KFD_KERNEL_QUEUE_SIZE * 2;
686
687	/* add another 512KB for all other allocations on gart (HPD, fences) */
688	size += 512 * 1024;
689
690	if (amdgpu_amdkfd_alloc_gtt_mem(
691			kfd->kgd, size, &kfd->gtt_mem,
692			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr,
693			false)) {
694		dev_err(kfd_device, "Could not allocate %d bytes\n", size);
695		goto alloc_gtt_mem_failure;
696	}
697
698	dev_info(kfd_device, "Allocated %d bytes on gart\n", size);
699
700	/* Initialize GTT sa with 512 byte chunk size */
701	if (kfd_gtt_sa_init(kfd, size, 512) != 0) {
702		dev_err(kfd_device, "Error initializing gtt sub-allocator\n");
703		goto kfd_gtt_sa_init_error;
704	}
705
706	if (kfd_doorbell_init(kfd)) {
707		dev_err(kfd_device,
708			"Error initializing doorbell aperture\n");
709		goto kfd_doorbell_error;
710	}
711
712	kfd->hive_id = amdgpu_amdkfd_get_hive_id(kfd->kgd);
713
714	kfd->unique_id = amdgpu_amdkfd_get_unique_id(kfd->kgd);
715
716	kfd->noretry = amdgpu_amdkfd_get_noretry(kfd->kgd);
717
718	if (kfd_interrupt_init(kfd)) {
719		dev_err(kfd_device, "Error initializing interrupts\n");
720		goto kfd_interrupt_error;
721	}
722
723	kfd->dqm = device_queue_manager_init(kfd);
724	if (!kfd->dqm) {
725		dev_err(kfd_device, "Error initializing queue manager\n");
726		goto device_queue_manager_error;
727	}
728
729	/* If supported on this device, allocate global GWS that is shared
730	 * by all KFD processes
731	 */
732	if (kfd_gws_init(kfd)) {
733		dev_err(kfd_device, "Could not allocate %d gws\n",
734			amdgpu_amdkfd_get_num_gws(kfd->kgd));
735		goto gws_error;
736	}
737
738	/* If CRAT is broken, won't set iommu enabled */
739	kfd_double_confirm_iommu_support(kfd);
740
741	if (kfd_iommu_device_init(kfd)) {
742		kfd->use_iommu_v2 = false;
743		dev_err(kfd_device, "Error initializing iommuv2\n");
744		goto device_iommu_error;
745	}
746
747	kfd_cwsr_init(kfd);
748
749	if(kgd2kfd_resume_iommu(kfd))
750		goto device_iommu_error;
751
752	if (kfd_resume(kfd))
753		goto kfd_resume_error;
754
755	kfd->dbgmgr = NULL;
756
757	if (kfd_topology_add_device(kfd)) {
758		dev_err(kfd_device, "Error adding device to topology\n");
759		goto kfd_topology_add_device_error;
760	}
761
762	kfd_smi_init(kfd);
763
764	kfd->init_complete = true;
765	dev_info(kfd_device, "added device %x:%x\n", kfd->pdev->vendor,
766		 kfd->pdev->device);
767
768	pr_debug("Starting kfd with the following scheduling policy %d\n",
769		kfd->dqm->sched_policy);
770
771	goto out;
772
773kfd_topology_add_device_error:
774kfd_resume_error:
775device_iommu_error:
776gws_error:
777	device_queue_manager_uninit(kfd->dqm);
778device_queue_manager_error:
779	kfd_interrupt_exit(kfd);
780kfd_interrupt_error:
781	kfd_doorbell_fini(kfd);
782kfd_doorbell_error:
783	kfd_gtt_sa_fini(kfd);
784kfd_gtt_sa_init_error:
785	amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
786alloc_gtt_mem_failure:
787	if (kfd->gws)
788		amdgpu_amdkfd_free_gws(kfd->kgd, kfd->gws);
789	dev_err(kfd_device,
790		"device %x:%x NOT added due to errors\n",
791		kfd->pdev->vendor, kfd->pdev->device);
792out:
793	return kfd->init_complete;
794}
795
796void kgd2kfd_device_exit(struct kfd_dev *kfd)
797{
798	if (kfd->init_complete) {
799		kgd2kfd_suspend(kfd, false);
800		device_queue_manager_uninit(kfd->dqm);
801		kfd_interrupt_exit(kfd);
802		kfd_topology_remove_device(kfd);
803		kfd_doorbell_fini(kfd);
804		ida_destroy(&kfd->doorbell_ida);
805		kfd_gtt_sa_fini(kfd);
806		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
807		if (kfd->gws)
808			amdgpu_amdkfd_free_gws(kfd->kgd, kfd->gws);
809	}
810
811	kfree(kfd);
812}
813
814int kgd2kfd_pre_reset(struct kfd_dev *kfd)
815{
816	if (!kfd->init_complete)
817		return 0;
818
819	kfd_smi_event_update_gpu_reset(kfd, false);
820
821	kfd->dqm->ops.pre_reset(kfd->dqm);
822
823	kgd2kfd_suspend(kfd, false);
824
825	kfd_signal_reset_event(kfd);
826	return 0;
827}
828
829/*
830 * Fix me. KFD won't be able to resume existing process for now.
831 * We will keep all existing process in a evicted state and
832 * wait the process to be terminated.
833 */
834
835int kgd2kfd_post_reset(struct kfd_dev *kfd)
836{
837	int ret;
838
839	if (!kfd->init_complete)
840		return 0;
841
842	ret = kfd_resume(kfd);
843	if (ret)
844		return ret;
845	atomic_dec(&kfd_locked);
846
847	atomic_set(&kfd->sram_ecc_flag, 0);
848
849	kfd_smi_event_update_gpu_reset(kfd, true);
850
851	return 0;
852}
853
854bool kfd_is_locked(void)
855{
856	return  (atomic_read(&kfd_locked) > 0);
857}
858
859void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
860{
861	if (!kfd->init_complete)
862		return;
863
864	/* for runtime suspend, skip locking kfd */
865	if (!run_pm) {
866		/* For first KFD device suspend all the KFD processes */
867		if (atomic_inc_return(&kfd_locked) == 1)
868			kfd_suspend_all_processes();
869	}
870
871	kfd->dqm->ops.stop(kfd->dqm);
872	kfd_iommu_suspend(kfd);
873}
874
875int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
876{
877	int ret, count;
878
879	if (!kfd->init_complete)
880		return 0;
881
882	ret = kfd_resume(kfd);
883	if (ret)
884		return ret;
885
886	/* for runtime resume, skip unlocking kfd */
887	if (!run_pm) {
888		count = atomic_dec_return(&kfd_locked);
889		WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
890		if (count == 0)
891			ret = kfd_resume_all_processes();
892	}
893
894	return ret;
895}
896
897int kgd2kfd_resume_iommu(struct kfd_dev *kfd)
898{
899	int err = 0;
900
901	err = kfd_iommu_resume(kfd);
902	if (err)
903		dev_err(kfd_device,
904			"Failed to resume IOMMU for device %x:%x\n",
905			kfd->pdev->vendor, kfd->pdev->device);
906	return err;
907}
908
909static int kfd_resume(struct kfd_dev *kfd)
910{
911	int err = 0;
912
913	err = kfd->dqm->ops.start(kfd->dqm);
914	if (err) {
915		dev_err(kfd_device,
916			"Error starting queue manager for device %x:%x\n",
917			kfd->pdev->vendor, kfd->pdev->device);
918		goto dqm_start_error;
919	}
920
921	return err;
922
923dqm_start_error:
924	kfd_iommu_suspend(kfd);
925	return err;
926}
927
928static inline void kfd_queue_work(struct workqueue_struct *wq,
929				  struct work_struct *work)
930{
931	int cpu, new_cpu;
932
933	cpu = new_cpu = smp_processor_id();
934	do {
935		new_cpu = cpumask_next(new_cpu, cpu_online_mask) % nr_cpu_ids;
936		if (cpu_to_node(new_cpu) == numa_node_id())
937			break;
938	} while (cpu != new_cpu);
939
940	queue_work_on(new_cpu, wq, work);
941}
942
943/* This is called directly from KGD at ISR. */
944void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
945{
946	uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE];
947	bool is_patched = false;
948	unsigned long flags;
949
950	if (!kfd->init_complete)
951		return;
952
953	if (kfd->device_info->ih_ring_entry_size > sizeof(patched_ihre)) {
954		dev_err_once(kfd_device, "Ring entry too small\n");
955		return;
956	}
957
958	spin_lock_irqsave(&kfd->interrupt_lock, flags);
959
960	if (kfd->interrupts_active
961	    && interrupt_is_wanted(kfd, ih_ring_entry,
962				   patched_ihre, &is_patched)
963	    && enqueue_ih_ring_entry(kfd,
964				     is_patched ? patched_ihre : ih_ring_entry))
965		kfd_queue_work(kfd->ih_wq, &kfd->interrupt_work);
966
967	spin_unlock_irqrestore(&kfd->interrupt_lock, flags);
968}
969
970int kgd2kfd_quiesce_mm(struct mm_struct *mm)
971{
972	struct kfd_process *p;
973	int r;
974
975	/* Because we are called from arbitrary context (workqueue) as opposed
976	 * to process context, kfd_process could attempt to exit while we are
977	 * running so the lookup function increments the process ref count.
978	 */
979	p = kfd_lookup_process_by_mm(mm);
980	if (!p)
981		return -ESRCH;
982
983	WARN(debug_evictions, "Evicting pid %d", p->lead_thread->pid);
984	r = kfd_process_evict_queues(p);
985
986	kfd_unref_process(p);
987	return r;
988}
989
990int kgd2kfd_resume_mm(struct mm_struct *mm)
991{
992	struct kfd_process *p;
993	int r;
994
995	/* Because we are called from arbitrary context (workqueue) as opposed
996	 * to process context, kfd_process could attempt to exit while we are
997	 * running so the lookup function increments the process ref count.
998	 */
999	p = kfd_lookup_process_by_mm(mm);
1000	if (!p)
1001		return -ESRCH;
1002
1003	r = kfd_process_restore_queues(p);
1004
1005	kfd_unref_process(p);
1006	return r;
1007}
1008
1009/** kgd2kfd_schedule_evict_and_restore_process - Schedules work queue that will
1010 *   prepare for safe eviction of KFD BOs that belong to the specified
1011 *   process.
1012 *
1013 * @mm: mm_struct that identifies the specified KFD process
1014 * @fence: eviction fence attached to KFD process BOs
1015 *
1016 */
1017int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
1018					       struct dma_fence *fence)
1019{
1020	struct kfd_process *p;
1021	unsigned long active_time;
1022	unsigned long delay_jiffies = msecs_to_jiffies(PROCESS_ACTIVE_TIME_MS);
1023
1024	if (!fence)
1025		return -EINVAL;
1026
1027	if (dma_fence_is_signaled(fence))
1028		return 0;
1029
1030	p = kfd_lookup_process_by_mm(mm);
1031	if (!p)
1032		return -ENODEV;
1033
1034	if (fence->seqno == p->last_eviction_seqno)
1035		goto out;
1036
1037	p->last_eviction_seqno = fence->seqno;
1038
1039	/* Avoid KFD process starvation. Wait for at least
1040	 * PROCESS_ACTIVE_TIME_MS before evicting the process again
1041	 */
1042	active_time = get_jiffies_64() - p->last_restore_timestamp;
1043	if (delay_jiffies > active_time)
1044		delay_jiffies -= active_time;
1045	else
1046		delay_jiffies = 0;
1047
1048	/* During process initialization eviction_work.dwork is initialized
1049	 * to kfd_evict_bo_worker
1050	 */
1051	WARN(debug_evictions, "Scheduling eviction of pid %d in %ld jiffies",
1052	     p->lead_thread->pid, delay_jiffies);
1053	schedule_delayed_work(&p->eviction_work, delay_jiffies);
1054out:
1055	kfd_unref_process(p);
1056	return 0;
1057}
1058
1059static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
1060				unsigned int chunk_size)
1061{
1062	unsigned int num_of_longs;
1063
1064	if (WARN_ON(buf_size < chunk_size))
1065		return -EINVAL;
1066	if (WARN_ON(buf_size == 0))
1067		return -EINVAL;
1068	if (WARN_ON(chunk_size == 0))
1069		return -EINVAL;
1070
1071	kfd->gtt_sa_chunk_size = chunk_size;
1072	kfd->gtt_sa_num_of_chunks = buf_size / chunk_size;
1073
1074	num_of_longs = (kfd->gtt_sa_num_of_chunks + BITS_PER_LONG - 1) /
1075		BITS_PER_LONG;
1076
1077	kfd->gtt_sa_bitmap = kcalloc(num_of_longs, sizeof(long), GFP_KERNEL);
1078
1079	if (!kfd->gtt_sa_bitmap)
1080		return -ENOMEM;
1081
1082	pr_debug("gtt_sa_num_of_chunks = %d, gtt_sa_bitmap = %p\n",
1083			kfd->gtt_sa_num_of_chunks, kfd->gtt_sa_bitmap);
1084
1085	mutex_init(&kfd->gtt_sa_lock);
1086
1087	return 0;
1088
1089}
1090
1091static void kfd_gtt_sa_fini(struct kfd_dev *kfd)
1092{
1093	mutex_destroy(&kfd->gtt_sa_lock);
1094	kfree(kfd->gtt_sa_bitmap);
1095}
1096
1097static inline uint64_t kfd_gtt_sa_calc_gpu_addr(uint64_t start_addr,
1098						unsigned int bit_num,
1099						unsigned int chunk_size)
1100{
1101	return start_addr + bit_num * chunk_size;
1102}
1103
1104static inline uint32_t *kfd_gtt_sa_calc_cpu_addr(void *start_addr,
1105						unsigned int bit_num,
1106						unsigned int chunk_size)
1107{
1108	return (uint32_t *) ((uint64_t) start_addr + bit_num * chunk_size);
1109}
1110
1111int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
1112			struct kfd_mem_obj **mem_obj)
1113{
1114	unsigned int found, start_search, cur_size;
1115
1116	if (size == 0)
1117		return -EINVAL;
1118
1119	if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size)
1120		return -ENOMEM;
1121
1122	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
1123	if (!(*mem_obj))
1124		return -ENOMEM;
1125
1126	pr_debug("Allocated mem_obj = %p for size = %d\n", *mem_obj, size);
1127
1128	start_search = 0;
1129
1130	mutex_lock(&kfd->gtt_sa_lock);
1131
1132kfd_gtt_restart_search:
1133	/* Find the first chunk that is free */
1134	found = find_next_zero_bit(kfd->gtt_sa_bitmap,
1135					kfd->gtt_sa_num_of_chunks,
1136					start_search);
1137
1138	pr_debug("Found = %d\n", found);
1139
1140	/* If there wasn't any free chunk, bail out */
1141	if (found == kfd->gtt_sa_num_of_chunks)
1142		goto kfd_gtt_no_free_chunk;
1143
1144	/* Update fields of mem_obj */
1145	(*mem_obj)->range_start = found;
1146	(*mem_obj)->range_end = found;
1147	(*mem_obj)->gpu_addr = kfd_gtt_sa_calc_gpu_addr(
1148					kfd->gtt_start_gpu_addr,
1149					found,
1150					kfd->gtt_sa_chunk_size);
1151	(*mem_obj)->cpu_ptr = kfd_gtt_sa_calc_cpu_addr(
1152					kfd->gtt_start_cpu_ptr,
1153					found,
1154					kfd->gtt_sa_chunk_size);
1155
1156	pr_debug("gpu_addr = %p, cpu_addr = %p\n",
1157			(uint64_t *) (*mem_obj)->gpu_addr, (*mem_obj)->cpu_ptr);
1158
1159	/* If we need only one chunk, mark it as allocated and get out */
1160	if (size <= kfd->gtt_sa_chunk_size) {
1161		pr_debug("Single bit\n");
1162		set_bit(found, kfd->gtt_sa_bitmap);
1163		goto kfd_gtt_out;
1164	}
1165
1166	/* Otherwise, try to see if we have enough contiguous chunks */
1167	cur_size = size - kfd->gtt_sa_chunk_size;
1168	do {
1169		(*mem_obj)->range_end =
1170			find_next_zero_bit(kfd->gtt_sa_bitmap,
1171					kfd->gtt_sa_num_of_chunks, ++found);
1172		/*
1173		 * If next free chunk is not contiguous than we need to
1174		 * restart our search from the last free chunk we found (which
1175		 * wasn't contiguous to the previous ones
1176		 */
1177		if ((*mem_obj)->range_end != found) {
1178			start_search = found;
1179			goto kfd_gtt_restart_search;
1180		}
1181
1182		/*
1183		 * If we reached end of buffer, bail out with error
1184		 */
1185		if (found == kfd->gtt_sa_num_of_chunks)
1186			goto kfd_gtt_no_free_chunk;
1187
1188		/* Check if we don't need another chunk */
1189		if (cur_size <= kfd->gtt_sa_chunk_size)
1190			cur_size = 0;
1191		else
1192			cur_size -= kfd->gtt_sa_chunk_size;
1193
1194	} while (cur_size > 0);
1195
1196	pr_debug("range_start = %d, range_end = %d\n",
1197		(*mem_obj)->range_start, (*mem_obj)->range_end);
1198
1199	/* Mark the chunks as allocated */
1200	for (found = (*mem_obj)->range_start;
1201		found <= (*mem_obj)->range_end;
1202		found++)
1203		set_bit(found, kfd->gtt_sa_bitmap);
1204
1205kfd_gtt_out:
1206	mutex_unlock(&kfd->gtt_sa_lock);
1207	return 0;
1208
1209kfd_gtt_no_free_chunk:
1210	pr_debug("Allocation failed with mem_obj = %p\n", *mem_obj);
1211	mutex_unlock(&kfd->gtt_sa_lock);
1212	kfree(*mem_obj);
1213	return -ENOMEM;
1214}
1215
1216int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj)
1217{
1218	unsigned int bit;
1219
1220	/* Act like kfree when trying to free a NULL object */
1221	if (!mem_obj)
1222		return 0;
1223
1224	pr_debug("Free mem_obj = %p, range_start = %d, range_end = %d\n",
1225			mem_obj, mem_obj->range_start, mem_obj->range_end);
1226
1227	mutex_lock(&kfd->gtt_sa_lock);
1228
1229	/* Mark the chunks as free */
1230	for (bit = mem_obj->range_start;
1231		bit <= mem_obj->range_end;
1232		bit++)
1233		clear_bit(bit, kfd->gtt_sa_bitmap);
1234
1235	mutex_unlock(&kfd->gtt_sa_lock);
1236
1237	kfree(mem_obj);
1238	return 0;
1239}
1240
1241void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
1242{
1243	if (kfd)
1244		atomic_inc(&kfd->sram_ecc_flag);
1245}
1246
1247void kfd_inc_compute_active(struct kfd_dev *kfd)
1248{
1249	if (atomic_inc_return(&kfd->compute_profile) == 1)
1250		amdgpu_amdkfd_set_compute_idle(kfd->kgd, false);
1251}
1252
1253void kfd_dec_compute_active(struct kfd_dev *kfd)
1254{
1255	int count = atomic_dec_return(&kfd->compute_profile);
1256
1257	if (count == 0)
1258		amdgpu_amdkfd_set_compute_idle(kfd->kgd, true);
1259	WARN_ONCE(count < 0, "Compute profile ref. count error");
1260}
1261
1262void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
1263{
1264	if (kfd)
1265		kfd_smi_event_update_thermal_throttling(kfd, throttle_bitmask);
1266}
1267
1268#if defined(CONFIG_DEBUG_FS)
1269
1270/* This function will send a package to HIQ to hang the HWS
1271 * which will trigger a GPU reset and bring the HWS back to normal state
1272 */
1273int kfd_debugfs_hang_hws(struct kfd_dev *dev)
1274{
1275	int r = 0;
1276
1277	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
1278		pr_err("HWS is not enabled");
1279		return -EINVAL;
1280	}
1281
1282	r = pm_debugfs_hang_hws(&dev->dqm->packets);
1283	if (!r)
1284		r = dqm_debugfs_execute_queues(dev->dqm);
1285
1286	return r;
1287}
1288
1289#endif
1290