summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
blob: cf62f43a03da1d5eb4eb635b64ffa2913c77d9a1 (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
/*
 * 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.
 */

/* amdgpu_amdkfd.h defines the private interface between amdgpu and amdkfd. */

#ifndef AMDGPU_AMDKFD_H_INCLUDED
#define AMDGPU_AMDKFD_H_INCLUDED

#include <linux/types.h>
#include <linux/mm.h>
#include <linux/kthread.h>
#include <linux/workqueue.h>
#include <kgd_kfd_interface.h>
#include <drm/ttm/ttm_execbuf_util.h>
#include "amdgpu_sync.h"
#include "amdgpu_vm.h"

extern uint64_t amdgpu_amdkfd_total_mem_size;

enum TLB_FLUSH_TYPE {
	TLB_FLUSH_LEGACY = 0,
	TLB_FLUSH_LIGHTWEIGHT,
	TLB_FLUSH_HEAVYWEIGHT
};

struct amdgpu_device;

enum kfd_mem_attachment_type {
	KFD_MEM_ATT_SHARED,	/* Share kgd_mem->bo or another attachment's */
	KFD_MEM_ATT_USERPTR,	/* SG bo to DMA map pages from a userptr bo */
	KFD_MEM_ATT_DMABUF,	/* DMAbuf to DMA map TTM BOs */
};

struct kfd_mem_attachment {
	struct list_head list;
	enum kfd_mem_attachment_type type;
	bool is_mapped;
	struct amdgpu_bo_va *bo_va;
	struct amdgpu_device *adev;
	uint64_t va;
	uint64_t pte_flags;
};

struct kgd_mem {
	struct mutex lock;
	struct amdgpu_bo *bo;
	struct dma_buf *dmabuf;
	struct list_head attachments;
	/* protected by amdkfd_process_info.lock */
	struct ttm_validate_buffer validate_list;
	struct ttm_validate_buffer resv_list;
	uint32_t domain;
	unsigned int mapped_to_gpu_memory;
	uint64_t va;

	uint32_t alloc_flags;

	atomic_t invalid;
	struct amdkfd_process_info *process_info;

	struct amdgpu_sync sync;

	bool aql_queue;
	bool is_imported;
};

/* KFD Memory Eviction */
struct amdgpu_amdkfd_fence {
	struct dma_fence base;
	struct mm_struct *mm;
	spinlock_t lock;
	char timeline_name[TASK_COMM_LEN];
	struct svm_range_bo *svm_bo;
};

struct amdgpu_kfd_dev {
	struct kfd_dev *dev;
	uint64_t vram_used;
	bool init_complete;
};

enum kgd_engine_type {
	KGD_ENGINE_PFP = 1,
	KGD_ENGINE_ME,
	KGD_ENGINE_CE,
	KGD_ENGINE_MEC1,
	KGD_ENGINE_MEC2,
	KGD_ENGINE_RLC,
	KGD_ENGINE_SDMA1,
	KGD_ENGINE_SDMA2,
	KGD_ENGINE_MAX
};


struct amdkfd_process_info {
	/* List head of all VMs that belong to a KFD process */
	struct list_head vm_list_head;
	/* List head for all KFD BOs that belong to a KFD process. */
	struct list_head kfd_bo_list;
	/* List of userptr BOs that are valid or invalid */
	struct list_head userptr_valid_list;
	struct list_head userptr_inval_list;
	/* Lock to protect kfd_bo_list */
	struct mutex lock;

	/* Number of VMs */
	unsigned int n_vms;
	/* Eviction Fence */
	struct amdgpu_amdkfd_fence *eviction_fence;

	/* MMU-notifier related fields */
	atomic_t evicted_bos;
	struct delayed_work restore_userptr_work;
	struct pid *pid;
};

int amdgpu_amdkfd_init(void);
void amdgpu_amdkfd_fini(void);

void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
			const void *ih_ring_entry);
void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev);
int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
				uint32_t vmid, uint64_t gpu_addr,
				uint32_t *ib_cmd, uint32_t ib_len);
void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd);
int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid);
int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid,
				      enum TLB_FLUSH_TYPE flush_type);

bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);

int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);

int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);

void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);

int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
					int queue_bit);

struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
				struct mm_struct *mm,
				struct svm_range_bo *svm_bo);
#if IS_ENABLED(CONFIG_HSA_AMD)
bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo);
int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
#else
static inline
bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm)
{
	return false;
}

static inline
struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
{
	return NULL;
}

static inline
int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)
{
	return 0;
}

static inline
int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm)
{
	return 0;
}
#endif
/* Shared API */
int amdgpu_amdkfd_alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
				void **mem_obj, uint64_t *gpu_addr,
				void **cpu_ptr, bool mqd_gfx9);
void amdgpu_amdkfd_free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
int amdgpu_amdkfd_alloc_gws(struct kgd_dev *kgd, size_t size, void **mem_obj);
void amdgpu_amdkfd_free_gws(struct kgd_dev *kgd, void *mem_obj);
int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem);
int amdgpu_amdkfd_remove_gws_from_process(void *info, void *mem);
uint32_t amdgpu_amdkfd_get_fw_version(struct kgd_dev *kgd,
				      enum kgd_engine_type type);
void amdgpu_amdkfd_get_local_mem_info(struct kgd_dev *kgd,
				      struct kfd_local_mem_info *mem_info);
uint64_t amdgpu_amdkfd_get_gpu_clock_counter(struct kgd_dev *kgd);

uint32_t amdgpu_amdkfd_get_max_engine_clock_in_mhz(struct kgd_dev *kgd);
void amdgpu_amdkfd_get_cu_info(struct kgd_dev *kgd, struct kfd_cu_info *cu_info);
int amdgpu_amdkfd_get_dmabuf_info(struct kgd_dev *kgd, int dma_buf_fd,
				  struct kgd_dev **dmabuf_kgd,
				  uint64_t *bo_size, void *metadata_buffer,
				  size_t buffer_size, uint32_t *metadata_size,
				  uint32_t *flags);
uint64_t amdgpu_amdkfd_get_vram_usage(struct kgd_dev *kgd);
uint64_t amdgpu_amdkfd_get_hive_id(struct kgd_dev *kgd);
uint64_t amdgpu_amdkfd_get_unique_id(struct kgd_dev *kgd);
uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd);
uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);
uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);

/* Read user wptr from a specified user address space with page fault
 * disabled. The memory must be pinned and mapped to the hardware when
 * this is called in hqd_load functions, so it should never fault in
 * the first place. This resolves a circular lock dependency involving
 * four locks, including the DQM lock and mmap_lock.
 */
#define read_user_wptr(mmptr, wptr, dst)				\
	({								\
		bool valid = false;					\
		if ((mmptr) && (wptr)) {				\
			pagefault_disable();				\
			if ((mmptr) == current->mm) {			\
				valid = !get_user((dst), (wptr));	\
			} else if (current->flags & PF_KTHREAD) {	\
				kthread_use_mm(mmptr);			\
				valid = !get_user((dst), (wptr));	\
				kthread_unuse_mm(mmptr);		\
			}						\
			pagefault_enable();				\
		}							\
		valid;							\
	})

/* GPUVM API */
#define drm_priv_to_vm(drm_priv)					\
	(&((struct amdgpu_fpriv *)					\
		((struct drm_file *)(drm_priv))->driver_priv)->vm)

int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
					struct file *filp, u32 pasid,
					void **process_info,
					struct dma_fence **ef);
void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *drm_priv);
uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv);
int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
		struct kgd_dev *kgd, uint64_t va, uint64_t size,
		void *drm_priv, struct kgd_mem **mem,
		uint64_t *offset, uint32_t flags);
int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
		uint64_t *size);
int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_sync_memory(
		struct kgd_dev *kgd, struct kgd_mem *mem, bool intr);
int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
		struct kgd_mem *mem, void **kptr, uint64_t *size);
int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
					    struct dma_fence **ef);
int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
					      struct kfd_vm_fault_info *info);
int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
				      struct dma_buf *dmabuf,
				      uint64_t va, void *drm_priv,
				      struct kgd_mem **mem, uint64_t *size,
				      uint64_t *mmap_offset);
int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
				struct tile_config *config);
#if IS_ENABLED(CONFIG_HSA_AMD)
void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
				struct amdgpu_vm *vm);
void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
void amdgpu_amdkfd_reserve_system_mem(uint64_t size);
#else
static inline
void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
{
}

static inline
void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
					struct amdgpu_vm *vm)
{
}

static inline
void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
{
}
#endif
/* KGD2KFD callbacks */
int kgd2kfd_quiesce_mm(struct mm_struct *mm);
int kgd2kfd_resume_mm(struct mm_struct *mm);
int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
						struct dma_fence *fence);
#if IS_ENABLED(CONFIG_HSA_AMD)
int kgd2kfd_init(void);
void kgd2kfd_exit(void);
struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
			      unsigned int asic_type, bool vf);
bool kgd2kfd_device_init(struct kfd_dev *kfd,
			 struct drm_device *ddev,
			 const struct kgd2kfd_shared_resources *gpu_resources);
void kgd2kfd_device_exit(struct kfd_dev *kfd);
void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
int kgd2kfd_pre_reset(struct kfd_dev *kfd);
int kgd2kfd_post_reset(struct kfd_dev *kfd);
void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask);
#else
static inline int kgd2kfd_init(void)
{
	return -ENOENT;
}

static inline void kgd2kfd_exit(void)
{
}

static inline
struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
					unsigned int asic_type, bool vf)
{
	return NULL;
}

static inline
bool kgd2kfd_device_init(struct kfd_dev *kfd, struct drm_device *ddev,
				const struct kgd2kfd_shared_resources *gpu_resources)
{
	return false;
}

static inline void kgd2kfd_device_exit(struct kfd_dev *kfd)
{
}

static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
{
}

static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
{
	return 0;
}

static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd)
{
	return 0;
}

static inline int kgd2kfd_post_reset(struct kfd_dev *kfd)
{
	return 0;
}

static inline
void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
{
}

static inline
void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
{
}

static inline
void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
{
}
#endif
#endif /* AMDGPU_AMDKFD_H_INCLUDED */