summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/display/intel_frontbuffer.c
blob: d898b370d7a4faa5f9968fee3dd744de69bc7f18 (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
/*
 * Copyright © 2014 Intel Corporation
 *
 * 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 (including the next
 * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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:
 *	Daniel Vetter <daniel.vetter@ffwll.ch>
 */

/**
 * DOC: frontbuffer tracking
 *
 * Many features require us to track changes to the currently active
 * frontbuffer, especially rendering targeted at the frontbuffer.
 *
 * To be able to do so we track frontbuffers using a bitmask for all possible
 * frontbuffer slots through intel_frontbuffer_track(). The functions in this
 * file are then called when the contents of the frontbuffer are invalidated,
 * when frontbuffer rendering has stopped again to flush out all the changes
 * and when the frontbuffer is exchanged with a flip. Subsystems interested in
 * frontbuffer changes (e.g. PSR, FBC, DRRS) should directly put their callbacks
 * into the relevant places and filter for the frontbuffer slots that they are
 * interested int.
 *
 * On a high level there are two types of powersaving features. The first one
 * work like a special cache (FBC and PSR) and are interested when they should
 * stop caching and when to restart caching. This is done by placing callbacks
 * into the invalidate and the flush functions: At invalidate the caching must
 * be stopped and at flush time it can be restarted. And maybe they need to know
 * when the frontbuffer changes (e.g. when the hw doesn't initiate an invalidate
 * and flush on its own) which can be achieved with placing callbacks into the
 * flip functions.
 *
 * The other type of display power saving feature only cares about busyness
 * (e.g. DRRS). In that case all three (invalidate, flush and flip) indicate
 * busyness. There is no direct way to detect idleness. Instead an idle timer
 * work delayed work should be started from the flush and flip functions and
 * cancelled as soon as busyness is detected.
 */

#include "display/intel_dp.h"

#include "i915_drv.h"
#include "intel_display_types.h"
#include "intel_fbc.h"
#include "intel_frontbuffer.h"
#include "intel_psr.h"

/**
 * frontbuffer_flush - flush frontbuffer
 * @i915: i915 device
 * @frontbuffer_bits: frontbuffer plane tracking bits
 * @origin: which operation caused the flush
 *
 * This function gets called every time rendering on the given planes has
 * completed and frontbuffer caching can be started again. Flushes will get
 * delayed if they're blocked by some outstanding asynchronous rendering.
 *
 * Can be called without any locks held.
 */
static void frontbuffer_flush(struct drm_i915_private *i915,
			      unsigned int frontbuffer_bits,
			      enum fb_op_origin origin)
{
	/* Delay flushing when rings are still busy.*/
	spin_lock(&i915->fb_tracking.lock);
	frontbuffer_bits &= ~i915->fb_tracking.busy_bits;
	spin_unlock(&i915->fb_tracking.lock);

	if (!frontbuffer_bits)
		return;

	might_sleep();
	intel_edp_drrs_flush(i915, frontbuffer_bits);
	intel_psr_flush(i915, frontbuffer_bits, origin);
	intel_fbc_flush(i915, frontbuffer_bits, origin);
}

/**
 * intel_frontbuffer_flip_prepare - prepare asynchronous frontbuffer flip
 * @i915: i915 device
 * @frontbuffer_bits: frontbuffer plane tracking bits
 *
 * This function gets called after scheduling a flip on @obj. The actual
 * frontbuffer flushing will be delayed until completion is signalled with
 * intel_frontbuffer_flip_complete. If an invalidate happens in between this
 * flush will be cancelled.
 *
 * Can be called without any locks held.
 */
void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915,
				    unsigned frontbuffer_bits)
{
	spin_lock(&i915->fb_tracking.lock);
	i915->fb_tracking.flip_bits |= frontbuffer_bits;
	/* Remove stale busy bits due to the old buffer. */
	i915->fb_tracking.busy_bits &= ~frontbuffer_bits;
	spin_unlock(&i915->fb_tracking.lock);
}

/**
 * intel_frontbuffer_flip_complete - complete asynchronous frontbuffer flip
 * @i915: i915 device
 * @frontbuffer_bits: frontbuffer plane tracking bits
 *
 * This function gets called after the flip has been latched and will complete
 * on the next vblank. It will execute the flush if it hasn't been cancelled yet.
 *
 * Can be called without any locks held.
 */
void intel_frontbuffer_flip_complete(struct drm_i915_private *i915,
				     unsigned frontbuffer_bits)
{
	spin_lock(&i915->fb_tracking.lock);
	/* Mask any cancelled flips. */
	frontbuffer_bits &= i915->fb_tracking.flip_bits;
	i915->fb_tracking.flip_bits &= ~frontbuffer_bits;
	spin_unlock(&i915->fb_tracking.lock);

	if (frontbuffer_bits)
		frontbuffer_flush(i915, frontbuffer_bits, ORIGIN_FLIP);
}

/**
 * intel_frontbuffer_flip - synchronous frontbuffer flip
 * @i915: i915 device
 * @frontbuffer_bits: frontbuffer plane tracking bits
 *
 * This function gets called after scheduling a flip on @obj. This is for
 * synchronous plane updates which will happen on the next vblank and which will
 * not get delayed by pending gpu rendering.
 *
 * Can be called without any locks held.
 */
void intel_frontbuffer_flip(struct drm_i915_private *i915,
			    unsigned frontbuffer_bits)
{
	spin_lock(&i915->fb_tracking.lock);
	/* Remove stale busy bits due to the old buffer. */
	i915->fb_tracking.busy_bits &= ~frontbuffer_bits;
	spin_unlock(&i915->fb_tracking.lock);

	frontbuffer_flush(i915, frontbuffer_bits, ORIGIN_FLIP);
}

void __intel_fb_invalidate(struct intel_frontbuffer *front,
			   enum fb_op_origin origin,
			   unsigned int frontbuffer_bits)
{
	struct drm_i915_private *i915 = to_i915(front->obj->base.dev);

	if (origin == ORIGIN_CS) {
		spin_lock(&i915->fb_tracking.lock);
		i915->fb_tracking.busy_bits |= frontbuffer_bits;
		i915->fb_tracking.flip_bits &= ~frontbuffer_bits;
		spin_unlock(&i915->fb_tracking.lock);
	}

	might_sleep();
	intel_psr_invalidate(i915, frontbuffer_bits, origin);
	intel_edp_drrs_invalidate(i915, frontbuffer_bits);
	intel_fbc_invalidate(i915, frontbuffer_bits, origin);
}

void __intel_fb_flush(struct intel_frontbuffer *front,
		      enum fb_op_origin origin,
		      unsigned int frontbuffer_bits)
{
	struct drm_i915_private *i915 = to_i915(front->obj->base.dev);

	if (origin == ORIGIN_CS) {
		spin_lock(&i915->fb_tracking.lock);
		/* Filter out new bits since rendering started. */
		frontbuffer_bits &= i915->fb_tracking.busy_bits;
		i915->fb_tracking.busy_bits &= ~frontbuffer_bits;
		spin_unlock(&i915->fb_tracking.lock);
	}

	if (frontbuffer_bits)
		frontbuffer_flush(i915, frontbuffer_bits, origin);
}

static int frontbuffer_active(struct i915_active *ref)
{
	struct intel_frontbuffer *front =
		container_of(ref, typeof(*front), write);

	kref_get(&front->ref);
	return 0;
}

__i915_active_call
static void frontbuffer_retire(struct i915_active *ref)
{
	struct intel_frontbuffer *front =
		container_of(ref, typeof(*front), write);

	intel_frontbuffer_flush(front, ORIGIN_CS);
	intel_frontbuffer_put(front);
}

static void frontbuffer_release(struct kref *ref)
	__releases(&to_i915(front->obj->base.dev)->fb_tracking.lock)
{
	struct intel_frontbuffer *front =
		container_of(ref, typeof(*front), ref);
	struct drm_i915_gem_object *obj = front->obj;
	struct i915_vma *vma;

	spin_lock(&obj->vma.lock);
	for_each_ggtt_vma(vma, obj)
		vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
	spin_unlock(&obj->vma.lock);

	RCU_INIT_POINTER(obj->frontbuffer, NULL);
	spin_unlock(&to_i915(obj->base.dev)->fb_tracking.lock);

	i915_active_fini(&front->write);

	i915_gem_object_put(obj);
	kfree_rcu(front, rcu);
}

struct intel_frontbuffer *
intel_frontbuffer_get(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *i915 = to_i915(obj->base.dev);
	struct intel_frontbuffer *front;

	front = __intel_frontbuffer_get(obj);
	if (front)
		return front;

	front = kmalloc(sizeof(*front), GFP_KERNEL);
	if (!front)
		return NULL;

	front->obj = obj;
	kref_init(&front->ref);
	atomic_set(&front->bits, 0);
	i915_active_init(&front->write,
			 frontbuffer_active,
			 i915_active_may_sleep(frontbuffer_retire));

	spin_lock(&i915->fb_tracking.lock);
	if (rcu_access_pointer(obj->frontbuffer)) {
		kfree(front);
		front = rcu_dereference_protected(obj->frontbuffer, true);
		kref_get(&front->ref);
	} else {
		i915_gem_object_get(obj);
		rcu_assign_pointer(obj->frontbuffer, front);
	}
	spin_unlock(&i915->fb_tracking.lock);

	return front;
}

void intel_frontbuffer_put(struct intel_frontbuffer *front)
{
	kref_put_lock(&front->ref,
		      frontbuffer_release,
		      &to_i915(front->obj->base.dev)->fb_tracking.lock);
}

/**
 * intel_frontbuffer_track - update frontbuffer tracking
 * @old: current buffer for the frontbuffer slots
 * @new: new buffer for the frontbuffer slots
 * @frontbuffer_bits: bitmask of frontbuffer slots
 *
 * This updates the frontbuffer tracking bits @frontbuffer_bits by clearing them
 * from @old and setting them in @new. Both @old and @new can be NULL.
 */
void intel_frontbuffer_track(struct intel_frontbuffer *old,
			     struct intel_frontbuffer *new,
			     unsigned int frontbuffer_bits)
{
	/*
	 * Control of individual bits within the mask are guarded by
	 * the owning plane->mutex, i.e. we can never see concurrent
	 * manipulation of individual bits. But since the bitfield as a whole
	 * is updated using RMW, we need to use atomics in order to update
	 * the bits.
	 */
	BUILD_BUG_ON(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES >
		     BITS_PER_TYPE(atomic_t));

	if (old) {
		drm_WARN_ON(old->obj->base.dev,
			    !(atomic_read(&old->bits) & frontbuffer_bits));
		atomic_andnot(frontbuffer_bits, &old->bits);
	}

	if (new) {
		drm_WARN_ON(new->obj->base.dev,
			    atomic_read(&new->bits) & frontbuffer_bits);
		atomic_or(frontbuffer_bits, &new->bits);
	}
}