summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
blob: 91baf95212a6beefbf8a23bba57c227961d007e1 (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
397
398
399
400
401
402
403
404
405
406
407
/*
 * 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/idr.h>
#include <linux/kfifo.h>
#include <linux/rbtree.h>
#include <drm/gpu_scheduler.h>
#include <drm/drm_file.h>
#include <drm/ttm/ttm_bo_driver.h>

#include "amdgpu_sync.h"
#include "amdgpu_ring.h"
#include "amdgpu_ids.h"

struct amdgpu_bo_va;
struct amdgpu_job;
struct amdgpu_bo_list_entry;

/*
 * GPUVM handling
 */

/* 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)

#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)

/* PTE is handled as PDE for VEGA10 (Translate Further) */
#define AMDGPU_PTE_TF		(1ULL << 56)

/* PDE Block Fragment Size for VEGA10 */
#define AMDGPU_PDE_BFS(a)	((uint64_t)a << 59)


/* For GFX9 */
#define AMDGPU_PTE_MTYPE(a)    ((uint64_t)a << 57)
#define AMDGPU_PTE_MTYPE_MASK	AMDGPU_PTE_MTYPE(3ULL)

#define AMDGPU_MTYPE_NC 0
#define AMDGPU_MTYPE_CC 2

#define AMDGPU_PTE_DEFAULT_ATC  (AMDGPU_PTE_SYSTEM      \
                                | AMDGPU_PTE_SNOOPED    \
                                | AMDGPU_PTE_EXECUTABLE \
                                | AMDGPU_PTE_READABLE   \
                                | AMDGPU_PTE_WRITEABLE  \
                                | AMDGPU_PTE_MTYPE(AMDGPU_MTYPE_CC))

/* 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			(1ULL << 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)

/* VMPT level enumerate, and the hiberachy is:
 * PDB2->PDB1->PDB0->PTB
 */
enum amdgpu_vm_level {
	AMDGPU_VM_PDB2,
	AMDGPU_VM_PDB1,
	AMDGPU_VM_PDB0,
	AMDGPU_VM_PTB
};

/* 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 amdgpu_vm_bo_base	*next;

	/* protected by spinlock */
	struct list_head		vm_status;

	/* protected by the BO being reserved */
	bool				moved;
};

struct amdgpu_vm_pt {
	struct amdgpu_vm_bo_base	base;

	/* array of page tables, one for each directory entry */
	struct amdgpu_vm_pt		*entries;
};

/* provided by hw blocks that can write ptes, e.g., sdma */
struct amdgpu_vm_pte_funcs {
	/* number of dw to reserve per operation */
	unsigned	copy_pte_num_dw;

	/* copy pte entries from GART */
	void (*copy_pte)(struct amdgpu_ib *ib,
			 uint64_t pe, uint64_t src,
			 unsigned count);

	/* write pte one entry at a time with addr mapping */
	void (*write_pte)(struct amdgpu_ib *ib, uint64_t pe,
			  uint64_t value, unsigned count,
			  uint32_t incr);
	/* for linear pte/pde updates without addr mapping */
	void (*set_pte_pde)(struct amdgpu_ib *ib,
			    uint64_t pe,
			    uint64_t addr, unsigned count,
			    uint32_t incr, uint64_t flags);
};

struct amdgpu_task_info {
	char	process_name[TASK_COMM_LEN];
	char	task_name[TASK_COMM_LEN];
	pid_t	pid;
	pid_t	tgid;
};

/**
 * struct amdgpu_vm_update_params
 *
 * Encapsulate some VM table update parameters to reduce
 * the number of function parameters
 *
 */
struct amdgpu_vm_update_params {

	/**
	 * @adev: amdgpu device we do this update for
	 */
	struct amdgpu_device *adev;

	/**
	 * @vm: optional amdgpu_vm we do this update for
	 */
	struct amdgpu_vm *vm;

	/**
	 * @pages_addr:
	 *
	 * DMA addresses to use for mapping
	 */
	dma_addr_t *pages_addr;

	/**
	 * @job: job to used for hw submission
	 */
	struct amdgpu_job *job;

	/**
	 * @num_dw_left: number of dw left for the IB
	 */
	unsigned int num_dw_left;
};

struct amdgpu_vm_update_funcs {
	int (*map_table)(struct amdgpu_bo *bo);
	int (*prepare)(struct amdgpu_vm_update_params *p, void * owner,
		       struct dma_fence *exclusive);
	int (*update)(struct amdgpu_vm_update_params *p,
		      struct amdgpu_bo *bo, uint64_t pe, uint64_t addr,
		      unsigned count, uint32_t incr, uint64_t flags);
	int (*commit)(struct amdgpu_vm_update_params *p,
		      struct dma_fence **fence);
};

struct amdgpu_vm {
	/* tree of virtual addresses mapped */
	struct rb_root_cached	va;

	/* BOs who needs a validation */
	struct list_head	evicted;

	/* PT BOs which relocated and their parent need an update */
	struct list_head	relocated;

	/* per VM BOs moved, but not yet updated in the PT */
	struct list_head	moved;

	/* All BOs of this VM not currently in the state machine */
	struct list_head	idle;

	/* regular invalidated BOs, but not yet updated in the PT */
	struct list_head	invalidated;
	spinlock_t		invalidated_lock;

	/* 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_update;

	/* Scheduler entity for page table updates */
	struct drm_sched_entity	entity;

	unsigned int		pasid;
	/* dedicated to vm */
	struct amdgpu_vmid	*reserved_vmid[AMDGPU_MAX_VMHUBS];

	/* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */
	bool					use_cpu_for_update;

	/* Functions to use for VM table updates */
	const struct amdgpu_vm_update_funcs	*update_funcs;

	/* Flag to indicate ATS support from PTE for GFX9 */
	bool			pte_support_ats;

	/* Up to 128 pending retry page faults */
	DECLARE_KFIFO(faults, u64, 128);

	/* Points to the KFD process VM info */
	struct amdkfd_process_info *process_info;

	/* List node in amdkfd_process_info.vm_list_head */
	struct list_head	vm_list_node;

	/* Valid while the PD is reserved or fenced */
	uint64_t		pd_phys_addr;

	/* Some basic info about the task */
	struct amdgpu_task_info task_info;

	/* Store positions of group of BOs */
	struct ttm_lru_bulk_move lru_bulk_move;
	/* mark whether can do the bulk move */
	bool			bulk_moveable;
};

struct amdgpu_vm_manager {
	/* Handling of VMIDs */
	struct amdgpu_vmid_mgr			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;
	uint32_t				block_size;
	uint32_t				fragment_size;
	enum amdgpu_vm_level			root_level;
	/* vram base address for page table entry  */
	u64					vram_base_offset;
	/* vm pte handling */
	const struct amdgpu_vm_pte_funcs	*vm_pte_funcs;
	struct drm_sched_rq			*vm_pte_rqs[AMDGPU_MAX_RINGS];
	unsigned				vm_pte_num_rqs;
	struct amdgpu_ring			*page_fault;

	/* 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;

	/* PASID to VM mapping, will be used in interrupt context to
	 * look up VM of a page fault
	 */
	struct idr				pasid_idr;
	spinlock_t				pasid_lock;

	/* counter of mapped memory through xgmi */
	uint32_t				xgmi_map_counter;
	struct mutex				lock_pstate;
};

#define amdgpu_vm_copy_pte(adev, ib, pe, src, count) ((adev)->vm_manager.vm_pte_funcs->copy_pte((ib), (pe), (src), (count)))
#define amdgpu_vm_write_pte(adev, ib, pe, value, count, incr) ((adev)->vm_manager.vm_pte_funcs->write_pte((ib), (pe), (value), (count), (incr)))
#define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags)))

extern const struct amdgpu_vm_update_funcs amdgpu_vm_cpu_funcs;
extern const struct amdgpu_vm_update_funcs amdgpu_vm_sdma_funcs;

void amdgpu_vm_manager_init(struct amdgpu_device *adev);
void amdgpu_vm_manager_fini(struct amdgpu_device *adev);

long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
		   int vm_context, unsigned int pasid);
int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid);
void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
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);
bool amdgpu_vm_ready(struct amdgpu_vm *vm);
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_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync);
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_handle_moved(struct amdgpu_device *adev,
			   struct amdgpu_vm *vm);
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, bool evicted);
uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr);
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);
struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
							 uint64_t addr);
void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket);
void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
		      struct amdgpu_bo_va *bo_va);
void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size,
			   uint32_t fragment_size_default, unsigned max_level,
			   unsigned max_bits);
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);

void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
			     struct amdgpu_task_info *task_info);

void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);

void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
				struct amdgpu_vm *vm);
void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo);

#endif