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
|
/*
* Copyright 2016 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.
*
* Authors: Christian König
*/
#ifndef __AMDGPU_VM_H__
#define __AMDGPU_VM_H__
#include <linux/rbtree.h>
#include "gpu_scheduler.h"
#include "amdgpu_sync.h"
#include "amdgpu_ring.h"
struct amdgpu_bo_va;
struct amdgpu_job;
struct amdgpu_bo_list_entry;
/*
* GPUVM handling
*/
/* maximum number of VMIDs */
#define AMDGPU_NUM_VM 16
/* Maximum number of PTEs the hardware can write with one command */
#define AMDGPU_VM_MAX_UPDATE_SIZE 0x3FFFF
/* number of entries in page table */
#define AMDGPU_VM_PTE_COUNT(adev) (1 << (adev)->vm_manager.block_size)
/* PTBs (Page Table Blocks) need to be aligned to 32K */
#define AMDGPU_VM_PTB_ALIGN_SIZE 32768
#define AMDGPU_PTE_VALID (1ULL << 0)
#define AMDGPU_PTE_SYSTEM (1ULL << 1)
#define AMDGPU_PTE_SNOOPED (1ULL << 2)
/* VI only */
#define AMDGPU_PTE_EXECUTABLE (1ULL << 4)
#define AMDGPU_PTE_READABLE (1ULL << 5)
#define AMDGPU_PTE_WRITEABLE (1ULL << 6)
#define AMDGPU_PTE_FRAG(x) ((x & 0x1fULL) << 7)
/* TILED for VEGA10, reserved for older ASICs */
#define AMDGPU_PTE_PRT (1ULL << 51)
/* PDE is handled as PTE for VEGA10 */
#define AMDGPU_PDE_PTE (1ULL << 54)
/* VEGA10 only */
#define AMDGPU_PTE_MTYPE(a) ((uint64_t)a << 57)
#define AMDGPU_PTE_MTYPE_MASK AMDGPU_PTE_MTYPE(3ULL)
/* How to programm VM fault handling */
#define AMDGPU_VM_FAULT_STOP_NEVER 0
#define AMDGPU_VM_FAULT_STOP_FIRST 1
#define AMDGPU_VM_FAULT_STOP_ALWAYS 2
/* max number of VMHUB */
#define AMDGPU_MAX_VMHUBS 2
#define AMDGPU_GFXHUB 0
#define AMDGPU_MMHUB 1
/* hardcode that limit for now */
#define AMDGPU_VA_RESERVED_SIZE (8 << 20)
/* max vmids dedicated for process */
#define AMDGPU_VM_MAX_RESERVED_VMID 1
#define AMDGPU_VM_CONTEXT_GFX 0
#define AMDGPU_VM_CONTEXT_COMPUTE 1
/* See vm_update_mode */
#define AMDGPU_VM_USE_CPU_FOR_GFX (1 << 0)
#define AMDGPU_VM_USE_CPU_FOR_COMPUTE (1 << 1)
/* base structure for tracking BO usage in a VM */
struct amdgpu_vm_bo_base {
/* constant after initialization */
struct amdgpu_vm *vm;
struct amdgpu_bo *bo;
/* protected by bo being reserved */
struct list_head bo_list;
/* protected by spinlock */
struct list_head vm_status;
};
struct amdgpu_vm_pt {
struct amdgpu_bo *bo;
uint64_t addr;
/* array of page tables, one for each directory entry */
struct amdgpu_vm_pt *entries;
unsigned last_entry_used;
};
struct amdgpu_vm {
/* tree of virtual addresses mapped */
struct rb_root va;
/* protecting invalidated */
spinlock_t status_lock;
/* BOs moved, but not yet updated in the PT */
struct list_head moved;
/* BOs cleared in the PT because of a move */
struct list_head cleared;
/* BO mappings freed, but not yet updated in the PT */
struct list_head freed;
/* contains the page directory */
struct amdgpu_vm_pt root;
struct dma_fence *last_dir_update;
uint64_t last_eviction_counter;
/* protecting freed */
spinlock_t freed_lock;
/* Scheduler entity for page table updates */
struct amd_sched_entity entity;
/* client id */
u64 client_id;
/* dedicated to vm */
struct amdgpu_vm_id *reserved_vmid[AMDGPU_MAX_VMHUBS];
/* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */
bool use_cpu_for_update;
/* Flag to indicate ATS support from PTE for GFX9 */
bool pte_support_ats;
};
struct amdgpu_vm_id {
struct list_head list;
struct amdgpu_sync active;
struct dma_fence *last_flush;
atomic64_t owner;
uint64_t pd_gpu_addr;
/* last flushed PD/PT update */
struct dma_fence *flushed_updates;
uint32_t current_gpu_reset_count;
uint32_t gds_base;
uint32_t gds_size;
uint32_t gws_base;
uint32_t gws_size;
uint32_t oa_base;
uint32_t oa_size;
};
struct amdgpu_vm_id_manager {
struct mutex lock;
unsigned num_ids;
struct list_head ids_lru;
struct amdgpu_vm_id ids[AMDGPU_NUM_VM];
atomic_t reserved_vmid_num;
};
struct amdgpu_vm_manager {
/* Handling of VMIDs */
struct amdgpu_vm_id_manager id_mgr[AMDGPU_MAX_VMHUBS];
/* Handling of VM fences */
u64 fence_context;
unsigned seqno[AMDGPU_MAX_RINGS];
uint64_t max_pfn;
uint32_t num_level;
uint64_t vm_size;
uint32_t block_size;
uint32_t fragment_size;
/* vram base address for page table entry */
u64 vram_base_offset;
/* vm pte handling */
const struct amdgpu_vm_pte_funcs *vm_pte_funcs;
struct amdgpu_ring *vm_pte_rings[AMDGPU_MAX_RINGS];
unsigned vm_pte_num_rings;
atomic_t vm_pte_next_ring;
/* client id counter */
atomic64_t client_counter;
/* partial resident texture handling */
spinlock_t prt_lock;
atomic_t num_prt_users;
/* controls how VM page tables are updated for Graphics and Compute.
* BIT0[= 0] Graphics updated by SDMA [= 1] by CPU
* BIT1[= 0] Compute updated by SDMA [= 1] by CPU
*/
int vm_update_mode;
};
void amdgpu_vm_manager_init(struct amdgpu_device *adev);
void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
int vm_context);
void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
struct list_head *validated,
struct amdgpu_bo_list_entry *entry);
int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
int (*callback)(void *p, struct amdgpu_bo *bo),
void *param);
int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
struct amdgpu_vm *vm,
uint64_t saddr, uint64_t size);
int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
struct amdgpu_sync *sync, struct dma_fence *fence,
struct amdgpu_job *job);
int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync);
void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
unsigned vmid);
void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev);
int amdgpu_vm_update_directories(struct amdgpu_device *adev,
struct amdgpu_vm *vm);
int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
struct amdgpu_vm *vm,
struct dma_fence **fence);
int amdgpu_vm_clear_moved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
struct amdgpu_sync *sync);
int amdgpu_vm_bo_update(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va,
bool clear);
void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
struct amdgpu_bo *bo);
struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
struct amdgpu_bo *bo);
struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
struct amdgpu_vm *vm,
struct amdgpu_bo *bo);
int amdgpu_vm_bo_map(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va,
uint64_t addr, uint64_t offset,
uint64_t size, uint64_t flags);
int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va,
uint64_t addr, uint64_t offset,
uint64_t size, uint64_t flags);
int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va,
uint64_t addr);
int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
struct amdgpu_vm *vm,
uint64_t saddr, uint64_t size);
void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va);
void amdgpu_vm_set_fragment_size(struct amdgpu_device *adev,
uint32_t fragment_size_default);
void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size,
uint32_t fragment_size_default);
int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
struct amdgpu_job *job);
void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
#endif
|
