summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
blob: 5f8ada1d872bcc022ed88920b33c7f14eea0486b (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
/*
 * Copyright 2014 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 */

#include "amdgpu_amdkfd.h"
#include "amd_shared.h"
#include <drm/drmP.h>
#include "amdgpu.h"
#include "amdgpu_gfx.h"
#include <linux/module.h>

const struct kfd2kgd_calls *kfd2kgd;
const struct kgd2kfd_calls *kgd2kfd;
bool (*kgd2kfd_init_p)(unsigned, const struct kgd2kfd_calls**);

int amdgpu_amdkfd_init(void)
{
	int ret;

#if defined(CONFIG_HSA_AMD_MODULE)
	int (*kgd2kfd_init_p)(unsigned, const struct kgd2kfd_calls**);

	kgd2kfd_init_p = symbol_request(kgd2kfd_init);

	if (kgd2kfd_init_p == NULL)
		return -ENOENT;

	ret = kgd2kfd_init_p(KFD_INTERFACE_VERSION, &kgd2kfd);
	if (ret) {
		symbol_put(kgd2kfd_init);
		kgd2kfd = NULL;
	}

#elif defined(CONFIG_HSA_AMD)
	ret = kgd2kfd_init(KFD_INTERFACE_VERSION, &kgd2kfd);
	if (ret)
		kgd2kfd = NULL;

#else
	ret = -ENOENT;
#endif

	return ret;
}

bool amdgpu_amdkfd_load_interface(struct amdgpu_device *adev)
{
	switch (adev->asic_type) {
#ifdef CONFIG_DRM_AMDGPU_CIK
	case CHIP_KAVERI:
		kfd2kgd = amdgpu_amdkfd_gfx_7_get_functions();
		break;
#endif
	case CHIP_CARRIZO:
		kfd2kgd = amdgpu_amdkfd_gfx_8_0_get_functions();
		break;
	default:
		return false;
	}

	return true;
}

void amdgpu_amdkfd_fini(void)
{
	if (kgd2kfd) {
		kgd2kfd->exit();
		symbol_put(kgd2kfd_init);
	}
}

void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
{
	if (kgd2kfd)
		adev->kfd = kgd2kfd->probe((struct kgd_dev *)adev,
					adev->pdev, kfd2kgd);
}

void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
{
	int i;
	int last_valid_bit;
	if (adev->kfd) {
		struct kgd2kfd_shared_resources gpu_resources = {
			.compute_vmid_bitmap = 0xFF00,
			.num_mec = adev->gfx.mec.num_mec,
			.num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
			.num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe
		};

		/* this is going to have a few of the MSBs set that we need to
		 * clear */
		bitmap_complement(gpu_resources.queue_bitmap,
				  adev->gfx.mec.queue_bitmap,
				  KGD_MAX_QUEUES);

		/* remove the KIQ bit as well */
		if (adev->gfx.kiq.ring.ready)
			clear_bit(amdgpu_gfx_queue_to_bit(adev,
							  adev->gfx.kiq.ring.me - 1,
							  adev->gfx.kiq.ring.pipe,
							  adev->gfx.kiq.ring.queue),
				  gpu_resources.queue_bitmap);

		/* According to linux/bitmap.h we shouldn't use bitmap_clear if
		 * nbits is not compile time constant */
		last_valid_bit = adev->gfx.mec.num_mec
				* adev->gfx.mec.num_pipe_per_mec
				* adev->gfx.mec.num_queue_per_pipe;
		for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i)
			clear_bit(i, gpu_resources.queue_bitmap);

		amdgpu_doorbell_get_kfd_info(adev,
				&gpu_resources.doorbell_physical_address,
				&gpu_resources.doorbell_aperture_size,
				&gpu_resources.doorbell_start_offset);

		kgd2kfd->device_init(adev->kfd, &gpu_resources);
	}
}

void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev)
{
	if (adev->kfd) {
		kgd2kfd->device_exit(adev->kfd);
		adev->kfd = NULL;
	}
}

void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
		const void *ih_ring_entry)
{
	if (adev->kfd)
		kgd2kfd->interrupt(adev->kfd, ih_ring_entry);
}

void amdgpu_amdkfd_suspend(struct amdgpu_device *adev)
{
	if (adev->kfd)
		kgd2kfd->suspend(adev->kfd);
}

int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
{
	int r = 0;

	if (adev->kfd)
		r = kgd2kfd->resume(adev->kfd);

	return r;
}

int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
			void **mem_obj, uint64_t *gpu_addr,
			void **cpu_ptr)
{
	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
	struct kgd_mem **mem = (struct kgd_mem **) mem_obj;
	int r;

	BUG_ON(kgd == NULL);
	BUG_ON(gpu_addr == NULL);
	BUG_ON(cpu_ptr == NULL);

	*mem = kmalloc(sizeof(struct kgd_mem), GFP_KERNEL);
	if ((*mem) == NULL)
		return -ENOMEM;

	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
			     AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, NULL, &(*mem)->bo);
	if (r) {
		dev_err(adev->dev,
			"failed to allocate BO for amdkfd (%d)\n", r);
		return r;
	}

	/* map the buffer */
	r = amdgpu_bo_reserve((*mem)->bo, true);
	if (r) {
		dev_err(adev->dev, "(%d) failed to reserve bo for amdkfd\n", r);
		goto allocate_mem_reserve_bo_failed;
	}

	r = amdgpu_bo_pin((*mem)->bo, AMDGPU_GEM_DOMAIN_GTT,
				&(*mem)->gpu_addr);
	if (r) {
		dev_err(adev->dev, "(%d) failed to pin bo for amdkfd\n", r);
		goto allocate_mem_pin_bo_failed;
	}
	*gpu_addr = (*mem)->gpu_addr;

	r = amdgpu_bo_kmap((*mem)->bo, &(*mem)->cpu_ptr);
	if (r) {
		dev_err(adev->dev,
			"(%d) failed to map bo to kernel for amdkfd\n", r);
		goto allocate_mem_kmap_bo_failed;
	}
	*cpu_ptr = (*mem)->cpu_ptr;

	amdgpu_bo_unreserve((*mem)->bo);

	return 0;

allocate_mem_kmap_bo_failed:
	amdgpu_bo_unpin((*mem)->bo);
allocate_mem_pin_bo_failed:
	amdgpu_bo_unreserve((*mem)->bo);
allocate_mem_reserve_bo_failed:
	amdgpu_bo_unref(&(*mem)->bo);

	return r;
}

void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj)
{
	struct kgd_mem *mem = (struct kgd_mem *) mem_obj;

	BUG_ON(mem == NULL);

	amdgpu_bo_reserve(mem->bo, true);
	amdgpu_bo_kunmap(mem->bo);
	amdgpu_bo_unpin(mem->bo);
	amdgpu_bo_unreserve(mem->bo);
	amdgpu_bo_unref(&(mem->bo));
	kfree(mem);
}

uint64_t get_vmem_size(struct kgd_dev *kgd)
{
	struct amdgpu_device *adev =
		(struct amdgpu_device *)kgd;

	BUG_ON(kgd == NULL);

	return adev->mc.real_vram_size;
}

uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
{
	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;

	if (adev->gfx.funcs->get_gpu_clock_counter)
		return adev->gfx.funcs->get_gpu_clock_counter(adev);
	return 0;
}

uint32_t get_max_engine_clock_in_mhz(struct kgd_dev *kgd)
{
	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;

	/* The sclk is in quantas of 10kHz */
	return adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk / 100;
}