summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_active.h
blob: 7eb44132183aacd7f1b51d5a7a3e54a12bcb6eb6 (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
/*
 * SPDX-License-Identifier: MIT
 *
 * Copyright © 2019 Intel Corporation
 */

#ifndef _I915_ACTIVE_H_
#define _I915_ACTIVE_H_

#include <linux/lockdep.h>

#include "i915_active_types.h"
#include "i915_request.h"

struct i915_request;
struct intel_engine_cs;
struct intel_timeline;

/*
 * We treat requests as fences. This is not be to confused with our
 * "fence registers" but pipeline synchronisation objects ala GL_ARB_sync.
 * We use the fences to synchronize access from the CPU with activity on the
 * GPU, for example, we should not rewrite an object's PTE whilst the GPU
 * is reading them. We also track fences at a higher level to provide
 * implicit synchronisation around GEM objects, e.g. set-domain will wait
 * for outstanding GPU rendering before marking the object ready for CPU
 * access, or a pageflip will wait until the GPU is complete before showing
 * the frame on the scanout.
 *
 * In order to use a fence, the object must track the fence it needs to
 * serialise with. For example, GEM objects want to track both read and
 * write access so that we can perform concurrent read operations between
 * the CPU and GPU engines, as well as waiting for all rendering to
 * complete, or waiting for the last GPU user of a "fence register". The
 * object then embeds a #i915_active_fence to track the most recent (in
 * retirement order) request relevant for the desired mode of access.
 * The #i915_active_fence is updated with i915_active_fence_set() to
 * track the most recent fence request, typically this is done as part of
 * i915_vma_move_to_active().
 *
 * When the #i915_active_fence completes (is retired), it will
 * signal its completion to the owner through a callback as well as mark
 * itself as idle (i915_active_fence.request == NULL). The owner
 * can then perform any action, such as delayed freeing of an active
 * resource including itself.
 */

void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb);

/**
 * __i915_active_fence_init - prepares the activity tracker for use
 * @active - the active tracker
 * @fence - initial fence to track, can be NULL
 * @func - a callback when then the tracker is retired (becomes idle),
 *         can be NULL
 *
 * i915_active_fence_init() prepares the embedded @active struct for use as
 * an activity tracker, that is for tracking the last known active fence
 * associated with it. When the last fence becomes idle, when it is retired
 * after completion, the optional callback @func is invoked.
 */
static inline void
__i915_active_fence_init(struct i915_active_fence *active,
			 void *fence,
			 dma_fence_func_t fn)
{
	RCU_INIT_POINTER(active->fence, fence);
	active->cb.func = fn ?: i915_active_noop;
}

#define INIT_ACTIVE_FENCE(A) \
	__i915_active_fence_init((A), NULL, NULL)

struct dma_fence *
__i915_active_fence_set(struct i915_active_fence *active,
			struct dma_fence *fence);

/**
 * i915_active_fence_set - updates the tracker to watch the current fence
 * @active - the active tracker
 * @rq - the request to watch
 *
 * i915_active_fence_set() watches the given @rq for completion. While
 * that @rq is busy, the @active reports busy. When that @rq is signaled
 * (or else retired) the @active tracker is updated to report idle.
 */
int __must_check
i915_active_fence_set(struct i915_active_fence *active,
		      struct i915_request *rq);
/**
 * i915_active_fence_get - return a reference to the active fence
 * @active - the active tracker
 *
 * i915_active_fence_get() returns a reference to the active fence,
 * or NULL if the active tracker is idle. The reference is obtained under RCU,
 * so no locking is required by the caller.
 *
 * The reference should be freed with dma_fence_put().
 */
static inline struct dma_fence *
i915_active_fence_get(struct i915_active_fence *active)
{
	struct dma_fence *fence;

	rcu_read_lock();
	fence = dma_fence_get_rcu_safe(&active->fence);
	rcu_read_unlock();

	return fence;
}

/**
 * i915_active_fence_isset - report whether the active tracker is assigned
 * @active - the active tracker
 *
 * i915_active_fence_isset() returns true if the active tracker is currently
 * assigned to a fence. Due to the lazy retiring, that fence may be idle
 * and this may report stale information.
 */
static inline bool
i915_active_fence_isset(const struct i915_active_fence *active)
{
	return rcu_access_pointer(active->fence);
}

/*
 * GPU activity tracking
 *
 * Each set of commands submitted to the GPU compromises a single request that
 * signals a fence upon completion. struct i915_request combines the
 * command submission, scheduling and fence signaling roles. If we want to see
 * if a particular task is complete, we need to grab the fence (struct
 * i915_request) for that task and check or wait for it to be signaled. More
 * often though we want to track the status of a bunch of tasks, for example
 * to wait for the GPU to finish accessing some memory across a variety of
 * different command pipelines from different clients. We could choose to
 * track every single request associated with the task, but knowing that
 * each request belongs to an ordered timeline (later requests within a
 * timeline must wait for earlier requests), we need only track the
 * latest request in each timeline to determine the overall status of the
 * task.
 *
 * struct i915_active provides this tracking across timelines. It builds a
 * composite shared-fence, and is updated as new work is submitted to the task,
 * forming a snapshot of the current status. It should be embedded into the
 * different resources that need to track their associated GPU activity to
 * provide a callback when that GPU activity has ceased, or otherwise to
 * provide a serialisation point either for request submission or for CPU
 * synchronisation.
 */

void __i915_active_init(struct i915_active *ref,
			int (*active)(struct i915_active *ref),
			void (*retire)(struct i915_active *ref),
			unsigned long flags,
			struct lock_class_key *mkey,
			struct lock_class_key *wkey);

/* Specialise each class of i915_active to avoid impossible lockdep cycles. */
#define i915_active_init(ref, active, retire, flags) do {			\
	static struct lock_class_key __mkey;					\
	static struct lock_class_key __wkey;					\
										\
	__i915_active_init(ref, active, retire, flags, &__mkey, &__wkey);	\
} while (0)

int i915_active_add_request(struct i915_active *ref, struct i915_request *rq);

struct dma_fence *
i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f);

int __i915_active_wait(struct i915_active *ref, int state);
static inline int i915_active_wait(struct i915_active *ref)
{
	return __i915_active_wait(ref, TASK_INTERRUPTIBLE);
}

int i915_sw_fence_await_active(struct i915_sw_fence *fence,
			       struct i915_active *ref,
			       unsigned int flags);
int i915_request_await_active(struct i915_request *rq,
			      struct i915_active *ref,
			      unsigned int flags);
#define I915_ACTIVE_AWAIT_EXCL BIT(0)
#define I915_ACTIVE_AWAIT_ACTIVE BIT(1)
#define I915_ACTIVE_AWAIT_BARRIER BIT(2)

int i915_active_acquire(struct i915_active *ref);
int i915_active_acquire_for_context(struct i915_active *ref, u64 idx);
bool i915_active_acquire_if_busy(struct i915_active *ref);

void i915_active_release(struct i915_active *ref);

static inline void __i915_active_acquire(struct i915_active *ref)
{
	GEM_BUG_ON(!atomic_read(&ref->count));
	atomic_inc(&ref->count);
}

static inline bool
i915_active_is_idle(const struct i915_active *ref)
{
	return !atomic_read(&ref->count);
}

void i915_active_fini(struct i915_active *ref);

int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
					    struct intel_engine_cs *engine);
void i915_active_acquire_barrier(struct i915_active *ref);
void i915_request_add_active_barriers(struct i915_request *rq);

void i915_active_print(struct i915_active *ref, struct drm_printer *m);
void i915_active_unlock_wait(struct i915_active *ref);

struct i915_active *i915_active_create(void);
struct i915_active *i915_active_get(struct i915_active *ref);
void i915_active_put(struct i915_active *ref);

static inline int __i915_request_await_exclusive(struct i915_request *rq,
						 struct i915_active *active)
{
	struct dma_fence *fence;
	int err = 0;

	fence = i915_active_fence_get(&active->excl);
	if (fence) {
		err = i915_request_await_dma_fence(rq, fence);
		dma_fence_put(fence);
	}

	return err;
}

void i915_active_module_exit(void);
int i915_active_module_init(void);

#endif /* _I915_ACTIVE_H_ */