summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/msm/msm_gem.h
blob: 432032ad4aeda984822bea1aec2a74f54a657150 (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
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2013 Red Hat
 * Author: Rob Clark <robdclark@gmail.com>
 */

#ifndef __MSM_GEM_H__
#define __MSM_GEM_H__

#include <linux/kref.h>
#include <linux/dma-resv.h>
#include "drm/gpu_scheduler.h"
#include "msm_drv.h"

/* Make all GEM related WARN_ON()s ratelimited.. when things go wrong they
 * tend to go wrong 1000s of times in a short timespan.
 */
#define GEM_WARN_ON(x)  WARN_RATELIMIT(x, "%s", __stringify(x))

/* Additional internal-use only BO flags: */
#define MSM_BO_STOLEN        0x10000000    /* try to use stolen/splash memory */
#define MSM_BO_MAP_PRIV      0x20000000    /* use IOMMU_PRIV when mapping */

struct msm_gem_address_space {
	const char *name;
	/* NOTE: mm managed at the page level, size is in # of pages
	 * and position mm_node->start is in # of pages:
	 */
	struct drm_mm mm;
	spinlock_t lock; /* Protects drm_mm node allocation/removal */
	struct msm_mmu *mmu;
	struct kref kref;

	/* For address spaces associated with a specific process, this
	 * will be non-NULL:
	 */
	struct pid *pid;

	/* @faults: the number of GPU hangs associated with this address space */
	int faults;

	/** @va_start: lowest possible address to allocate */
	uint64_t va_start;

	/** @va_size: the size of the address space (in bytes) */
	uint64_t va_size;
};

struct msm_gem_address_space *
msm_gem_address_space_get(struct msm_gem_address_space *aspace);

void msm_gem_address_space_put(struct msm_gem_address_space *aspace);

struct msm_gem_address_space *
msm_gem_address_space_create(struct msm_mmu *mmu, const char *name,
		u64 va_start, u64 size);

struct msm_fence_context;

struct msm_gem_vma {
	struct drm_mm_node node;
	uint64_t iova;
	struct msm_gem_address_space *aspace;
	struct list_head list;    /* node in msm_gem_object::vmas */
	bool mapped;
	int inuse;
	uint32_t fence_mask;
	uint32_t fence[MSM_GPU_MAX_RINGS];
	struct msm_fence_context *fctx[MSM_GPU_MAX_RINGS];
};

int msm_gem_init_vma(struct msm_gem_address_space *aspace,
		struct msm_gem_vma *vma, int size,
		u64 range_start, u64 range_end);
bool msm_gem_vma_inuse(struct msm_gem_vma *vma);
void msm_gem_purge_vma(struct msm_gem_address_space *aspace,
		struct msm_gem_vma *vma);
void msm_gem_unpin_vma(struct msm_gem_vma *vma);
void msm_gem_unpin_vma_fenced(struct msm_gem_vma *vma, struct msm_fence_context *fctx);
int msm_gem_map_vma(struct msm_gem_address_space *aspace,
		struct msm_gem_vma *vma, int prot,
		struct sg_table *sgt, int size);
void msm_gem_close_vma(struct msm_gem_address_space *aspace,
		struct msm_gem_vma *vma);

struct msm_gem_object {
	struct drm_gem_object base;

	uint32_t flags;

	/**
	 * Advice: are the backing pages purgeable?
	 */
	uint8_t madv;

	/**
	 * Is object on inactive_dontneed list (ie. counted in priv->shrinkable_count)?
	 */
	bool dontneed : 1;

	/**
	 * Is object evictable (ie. counted in priv->evictable_count)?
	 */
	bool evictable : 1;

	/**
	 * count of active vmap'ing
	 */
	uint8_t vmap_count;

	/**
	 * Node in list of all objects (mainly for debugfs, protected by
	 * priv->obj_lock
	 */
	struct list_head node;

	/**
	 * An object is either:
	 *  inactive - on priv->inactive_dontneed or priv->inactive_willneed
	 *     (depending on purgeability status)
	 *  active   - on one one of the gpu's active_list..  well, at
	 *     least for now we don't have (I don't think) hw sync between
	 *     2d and 3d one devices which have both, meaning we need to
	 *     block on submit if a bo is already on other ring
	 */
	struct list_head mm_list;

	struct page **pages;
	struct sg_table *sgt;
	void *vaddr;

	struct list_head vmas;    /* list of msm_gem_vma */

	/* For physically contiguous buffers.  Used when we don't have
	 * an IOMMU.  Also used for stolen/splashscreen buffer.
	 */
	struct drm_mm_node *vram_node;

	char name[32]; /* Identifier to print for the debugfs files */

	int active_count;
	int pin_count;
};
#define to_msm_bo(x) container_of(x, struct msm_gem_object, base)

uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj);
int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma);
void msm_gem_unpin_locked(struct drm_gem_object *obj);
struct msm_gem_vma *msm_gem_get_vma_locked(struct drm_gem_object *obj,
					   struct msm_gem_address_space *aspace);
int msm_gem_get_iova(struct drm_gem_object *obj,
		struct msm_gem_address_space *aspace, uint64_t *iova);
int msm_gem_set_iova(struct drm_gem_object *obj,
		struct msm_gem_address_space *aspace, uint64_t iova);
int msm_gem_get_and_pin_iova_range(struct drm_gem_object *obj,
		struct msm_gem_address_space *aspace, uint64_t *iova,
		u64 range_start, u64 range_end);
int msm_gem_get_and_pin_iova(struct drm_gem_object *obj,
		struct msm_gem_address_space *aspace, uint64_t *iova);
void msm_gem_unpin_iova(struct drm_gem_object *obj,
		struct msm_gem_address_space *aspace);
struct page **msm_gem_get_pages(struct drm_gem_object *obj);
void msm_gem_put_pages(struct drm_gem_object *obj);
int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
		struct drm_mode_create_dumb *args);
int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
		uint32_t handle, uint64_t *offset);
void *msm_gem_get_vaddr_locked(struct drm_gem_object *obj);
void *msm_gem_get_vaddr(struct drm_gem_object *obj);
void *msm_gem_get_vaddr_active(struct drm_gem_object *obj);
void msm_gem_put_vaddr_locked(struct drm_gem_object *obj);
void msm_gem_put_vaddr(struct drm_gem_object *obj);
int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv);
void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu);
void msm_gem_active_put(struct drm_gem_object *obj);
int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout);
int msm_gem_cpu_fini(struct drm_gem_object *obj);
int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
		uint32_t size, uint32_t flags, uint32_t *handle, char *name);
struct drm_gem_object *msm_gem_new(struct drm_device *dev,
		uint32_t size, uint32_t flags);
void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
		uint32_t flags, struct msm_gem_address_space *aspace,
		struct drm_gem_object **bo, uint64_t *iova);
void msm_gem_kernel_put(struct drm_gem_object *bo,
		struct msm_gem_address_space *aspace);
struct drm_gem_object *msm_gem_import(struct drm_device *dev,
		struct dma_buf *dmabuf, struct sg_table *sgt);
__printf(2, 3)
void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...);

#ifdef CONFIG_DEBUG_FS
struct msm_gem_stats {
	struct {
		unsigned count;
		size_t size;
	} all, active, resident, purgeable, purged;
};

void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m,
		struct msm_gem_stats *stats);
void msm_gem_describe_objects(struct list_head *list, struct seq_file *m);
#endif

static inline void
msm_gem_lock(struct drm_gem_object *obj)
{
	dma_resv_lock(obj->resv, NULL);
}

static inline bool __must_check
msm_gem_trylock(struct drm_gem_object *obj)
{
	return dma_resv_trylock(obj->resv);
}

static inline int
msm_gem_lock_interruptible(struct drm_gem_object *obj)
{
	return dma_resv_lock_interruptible(obj->resv, NULL);
}

static inline void
msm_gem_unlock(struct drm_gem_object *obj)
{
	dma_resv_unlock(obj->resv);
}

static inline bool
msm_gem_is_locked(struct drm_gem_object *obj)
{
	/*
	 * Destroying the object is a special case.. msm_gem_free_object()
	 * calls many things that WARN_ON if the obj lock is not held.  But
	 * acquiring the obj lock in msm_gem_free_object() can cause a
	 * locking order inversion between reservation_ww_class_mutex and
	 * fs_reclaim.
	 *
	 * This deadlock is not actually possible, because no one should
	 * be already holding the lock when msm_gem_free_object() is called.
	 * Unfortunately lockdep is not aware of this detail.  So when the
	 * refcount drops to zero, we pretend it is already locked.
	 */
	return dma_resv_is_locked(obj->resv) || (kref_read(&obj->refcount) == 0);
}

static inline bool is_active(struct msm_gem_object *msm_obj)
{
	GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base));
	return msm_obj->active_count;
}

/* imported/exported objects are not purgeable: */
static inline bool is_unpurgeable(struct msm_gem_object *msm_obj)
{
	return msm_obj->base.import_attach || msm_obj->pin_count;
}

static inline bool is_purgeable(struct msm_gem_object *msm_obj)
{
	return (msm_obj->madv == MSM_MADV_DONTNEED) && msm_obj->sgt &&
			!is_unpurgeable(msm_obj);
}

static inline bool is_vunmapable(struct msm_gem_object *msm_obj)
{
	GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base));
	return (msm_obj->vmap_count == 0) && msm_obj->vaddr;
}

static inline void mark_purgeable(struct msm_gem_object *msm_obj)
{
	struct msm_drm_private *priv = msm_obj->base.dev->dev_private;

	GEM_WARN_ON(!mutex_is_locked(&priv->mm_lock));

	if (is_unpurgeable(msm_obj))
		return;

	if (GEM_WARN_ON(msm_obj->dontneed))
		return;

	priv->shrinkable_count += msm_obj->base.size >> PAGE_SHIFT;
	msm_obj->dontneed = true;
}

static inline void mark_unpurgeable(struct msm_gem_object *msm_obj)
{
	struct msm_drm_private *priv = msm_obj->base.dev->dev_private;

	GEM_WARN_ON(!mutex_is_locked(&priv->mm_lock));

	if (is_unpurgeable(msm_obj))
		return;

	if (GEM_WARN_ON(!msm_obj->dontneed))
		return;

	priv->shrinkable_count -= msm_obj->base.size >> PAGE_SHIFT;
	GEM_WARN_ON(priv->shrinkable_count < 0);
	msm_obj->dontneed = false;
}

static inline bool is_unevictable(struct msm_gem_object *msm_obj)
{
	return is_unpurgeable(msm_obj) || msm_obj->vaddr;
}

static inline void mark_evictable(struct msm_gem_object *msm_obj)
{
	struct msm_drm_private *priv = msm_obj->base.dev->dev_private;

	WARN_ON(!mutex_is_locked(&priv->mm_lock));

	if (is_unevictable(msm_obj))
		return;

	if (WARN_ON(msm_obj->evictable))
		return;

	priv->evictable_count += msm_obj->base.size >> PAGE_SHIFT;
	msm_obj->evictable = true;
}

static inline void mark_unevictable(struct msm_gem_object *msm_obj)
{
	struct msm_drm_private *priv = msm_obj->base.dev->dev_private;

	WARN_ON(!mutex_is_locked(&priv->mm_lock));

	if (is_unevictable(msm_obj))
		return;

	if (WARN_ON(!msm_obj->evictable))
		return;

	priv->evictable_count -= msm_obj->base.size >> PAGE_SHIFT;
	WARN_ON(priv->evictable_count < 0);
	msm_obj->evictable = false;
}

void msm_gem_purge(struct drm_gem_object *obj);
void msm_gem_evict(struct drm_gem_object *obj);
void msm_gem_vunmap(struct drm_gem_object *obj);

/* Created per submit-ioctl, to track bo's and cmdstream bufs, etc,
 * associated with the cmdstream submission for synchronization (and
 * make it easier to unwind when things go wrong, etc).
 */
struct msm_gem_submit {
	struct drm_sched_job base;
	struct kref ref;
	struct drm_device *dev;
	struct msm_gpu *gpu;
	struct msm_gem_address_space *aspace;
	struct list_head node;   /* node in ring submit list */
	struct ww_acquire_ctx ticket;
	uint32_t seqno;		/* Sequence number of the submit on the ring */

	/* Hw fence, which is created when the scheduler executes the job, and
	 * is signaled when the hw finishes (via seqno write from cmdstream)
	 */
	struct dma_fence *hw_fence;

	/* Userspace visible fence, which is signaled by the scheduler after
	 * the hw_fence is signaled.
	 */
	struct dma_fence *user_fence;

	int fence_id;       /* key into queue->fence_idr */
	struct msm_gpu_submitqueue *queue;
	struct pid *pid;    /* submitting process */
	bool fault_dumped;  /* Limit devcoredump dumping to one per submit */
	bool valid;         /* true if no cmdstream patching needed */
	bool in_rb;         /* "sudo" mode, copy cmds into RB */
	struct msm_ringbuffer *ring;
	unsigned int nr_cmds;
	unsigned int nr_bos;
	u32 ident;	   /* A "identifier" for the submit for logging */
	struct {
		uint32_t type;
		uint32_t size;  /* in dwords */
		uint64_t iova;
		uint32_t offset;/* in dwords */
		uint32_t idx;   /* cmdstream buffer idx in bos[] */
		uint32_t nr_relocs;
		struct drm_msm_gem_submit_reloc *relocs;
	} *cmd;  /* array of size nr_cmds */
	struct {
/* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
#define BO_VALID	0x8000	/* is current addr in cmdstream correct/valid? */
#define BO_LOCKED	0x4000	/* obj lock is held */
#define BO_ACTIVE	0x2000	/* active refcnt is held */
#define BO_OBJ_PINNED	0x1000	/* obj (pages) is pinned and on active list */
#define BO_VMA_PINNED	0x0800	/* vma (virtual address) is pinned */
		uint32_t flags;
		union {
			struct msm_gem_object *obj;
			uint32_t handle;
		};
		uint64_t iova;
		struct msm_gem_vma *vma;
	} bos[];
};

static inline struct msm_gem_submit *to_msm_submit(struct drm_sched_job *job)
{
	return container_of(job, struct msm_gem_submit, base);
}

void __msm_gem_submit_destroy(struct kref *kref);

static inline void msm_gem_submit_get(struct msm_gem_submit *submit)
{
	kref_get(&submit->ref);
}

static inline void msm_gem_submit_put(struct msm_gem_submit *submit)
{
	kref_put(&submit->ref, __msm_gem_submit_destroy);
}

void msm_submit_retire(struct msm_gem_submit *submit);

/* helper to determine of a buffer in submit should be dumped, used for both
 * devcoredump and debugfs cmdstream dumping:
 */
static inline bool
should_dump(struct msm_gem_submit *submit, int idx)
{
	extern bool rd_full;
	return rd_full || (submit->bos[idx].flags & MSM_SUBMIT_BO_DUMP);
}

#endif /* __MSM_GEM_H__ */