Deleted Added
sdiff udiff text old ( 11859:76c36516e0ae ) new ( 11937:e6621fafa62d )
full compact
1/*
2 * Copyright (c) 2012, 2015, 2017 ARM Limited
3 * All rights reserved
4 *
5 * The license below extends only to copyright in the software and shall
6 * not be construed as granting a license to any other intellectual
7 * property including but not limited to intellectual property relating
8 * to a hardware implementation of the functionality of the software
9 * licensed hereunder. You may use the software subject to the license
10 * terms below provided that you ensure that this notice is replicated
11 * unmodified and in its entirety in all distributions of the software,
12 * modified or unmodified, in source code or in binary form.
13 *
14 * Redistribution and use in source and binary forms, with or without
15 * modification, are permitted provided that the following conditions are
16 * met: redistributions of source code must retain the above copyright
17 * notice, this list of conditions and the following disclaimer;
18 * redistributions in binary form must reproduce the above copyright
19 * notice, this list of conditions and the following disclaimer in the
20 * documentation and/or other materials provided with the distribution;
21 * neither the name of the copyright holders nor the names of its
22 * contributors may be used to endorse or promote products derived from
23 * this software without specific prior written permission.
24 *
25 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
26 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
27 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
28 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
29 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
30 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
31 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
32 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
33 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
34 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
35 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
36 *
37 * Authors: Andreas Sandberg
38 */
39
40#ifndef __SIM_DRAIN_HH__
41#define __SIM_DRAIN_HH__
42
43#include <atomic>
44#include <mutex>
45#include <vector>
46
47class Drainable;
48
49#ifndef SWIG // SWIG doesn't support strongly typed enums
50/**
51 * Object drain/handover states
52 *
53 * An object starts out in the Running state. When the simulator
54 * prepares to take a snapshot or prepares a CPU for handover, it
55 * calls the drain() method to transfer the object into the Draining
56 * or Drained state. If any object enters the Draining state
57 * (Drainable::drain() returning >0), simulation continues until it
58 * all objects have entered the Drained state.
59 *
60 * Before resuming simulation, the simulator calls resume() to
61 * transfer the object to the Running state. This in turn results in a
62 * call to drainResume() for all Drainable objects in the
63 * simulator. New Drainable objects may be created while resuming. In
64 * such cases, the new objects will be created in the Resuming state
65 * and later resumed.
66 *
67 * \note Even though the state of an object (visible to the rest of
68 * the world through Drainable::getState()) could be used to determine
69 * if all objects have entered the Drained state, the protocol is
70 * actually a bit more elaborate. See Drainable::drain() for details.
71 */
72enum class DrainState {
73 Running, /** Running normally */
74 Draining, /** Draining buffers pending serialization/handover */
75 Drained, /** Buffers drained, ready for serialization/handover */
76 Resuming, /** Transient state while the simulator is resuming */
77};
78#endif
79
80/**
81 * This class coordinates draining of a System.
82 *
83 * When draining the simulator, we need to make sure that all
84 * Drainable objects within the system have ended up in the drained
85 * state before declaring the operation to be successful. This class
86 * keeps track of how many objects are still in the process of
87 * draining. Once it determines that all objects have drained their
88 * state, it exits the simulation loop.
89 *
90 * @note A System might not be completely drained even though the
91 * DrainManager has caused the simulation loop to exit. Draining needs
92 * to be restarted until all Drainable objects declare that they don't
93 * need further simulation to be completely drained. See Drainable for
94 * more information.
95 */
96class DrainManager
97{
98 private:
99 DrainManager();
100#ifndef SWIG
101 DrainManager(DrainManager &) = delete;
102#endif
103 ~DrainManager();
104
105 public:
106 /** Get the singleton DrainManager instance */
107 static DrainManager &instance() { return _instance; }
108
109 /**
110 * Try to drain the system.
111 *
112 * Try to drain the system and return true if all objects are in a
113 * the Drained state at which point the whole simulator is in a
114 * consistent state and ready for checkpointing or CPU
115 * handover. The simulation script must continue simulating until
116 * the simulation loop returns "Finished drain", at which point
117 * this method should be called again. This cycle should continue
118 * until this method returns true.
119 *
120 * @return true if all objects were drained successfully, false if
121 * more simulation is needed.
122 */
123 bool tryDrain();
124
125 /**
126 * Resume normal simulation in a Drained system.
127 */
128 void resume();
129
130 /**
131 * Run state fixups before a checkpoint restore operation
132 *
133 * The drain state of an object isn't stored in a checkpoint since
134 * the whole system is always going to be in the Drained state
135 * when the checkpoint is created. When the checkpoint is restored
136 * at a later stage, recreated objects will be in the Running
137 * state since the state isn't stored in checkpoints. This method
138 * performs state fixups on all Drainable objects and the
139 * DrainManager itself.
140 */
141 void preCheckpointRestore();
142
143 /** Check if the system is drained */
144 bool isDrained() const { return _state == DrainState::Drained; }
145
146 /** Get the simulators global drain state */
147 DrainState state() const { return _state; }
148
149 /**
150 * Notify the DrainManager that a Drainable object has finished
151 * draining.
152 */
153 void signalDrainDone();
154
155 public:
156 void registerDrainable(Drainable *obj);
157 void unregisterDrainable(Drainable *obj);
158
159 private:
160 /**
161 * Helper function to check if all Drainable objects are in a
162 * specific state.
163 */
164 bool allInState(DrainState state) const;
165
166 /**
167 * Thread-safe helper function to get the number of Drainable
168 * objects in a system.
169 */
170 size_t drainableCount() const;
171
172 /** Lock protecting the set of drainable objects */
173 mutable std::mutex globalLock;
174
175 /** Set of all drainable objects */
176 std::vector<Drainable *> _allDrainable;
177
178 /**
179 * Number of objects still draining. This is flagged atomic since
180 * it can be manipulated by SimObjects living in different
181 * threads.
182 */
183 std::atomic_uint _count;
184
185 /** Global simulator drain state */
186 DrainState _state;
187
188 /** Singleton instance of the drain manager */
189 static DrainManager _instance;
190};
191
192/**
193 * Interface for objects that might require draining before
194 * checkpointing.
195 *
196 * An object's internal state needs to be drained when creating a
197 * checkpoint, switching between CPU models, or switching between
198 * timing models. Once the internal state has been drained from
199 * <i>all</i> objects in the simulator, the objects are serialized to
200 * disc or the configuration change takes place. The process works as
201 * follows (see simulate.py for details):
202 *
203 * <ol>
204 * <li>DrainManager::tryDrain() calls Drainable::drain() for every
205 * object in the system. Draining has completed if all of them
206 * return true. Otherwise, the drain manager keeps track of the
207 * objects that requested draining and waits for them to signal
208 * that they are done draining using the signalDrainDone() method.
209 *
210 * <li>Continue simulation. When an object has finished draining its
211 * internal state, it calls DrainManager::signalDrainDone() on the
212 * manager. The drain manager keeps track of the objects that
213 * haven't drained yet, simulation stops when the set of
214 * non-drained objects becomes empty.
215 *
216 * <li>Check if any object still needs draining
217 * (DrainManager::tryDrain()), if so repeat the process above.
218 *
219 * <li>Serialize objects, switch CPU model, or change timing model.
220 *
221 * <li>Call DrainManager::resume(), which in turn calls
222 * Drainable::drainResume() for all objects, and then continue the
223 * simulation.
224 * </ol>
225 *
226 */
227class Drainable
228{
229 friend class DrainManager;
230
231 protected:
232 Drainable();
233 virtual ~Drainable();
234
235 /**
236 * Notify an object that it needs to drain its state.
237 *
238 * If the object does not need further simulation to drain
239 * internal buffers, it returns DrainState::Drained and
240 * automatically switches to the Drained state. If the object
241 * needs more simulation, it returns DrainState::Draining and
242 * automatically enters the Draining state. Other return values
243 * are invalid.
244 *
245 * @note An object that has entered the Drained state can be
246 * disturbed by other objects in the system and consequently stop
247 * being drained. These perturbations are not visible in the drain
248 * state. The simulator therefore repeats the draining process
249 * until all objects return DrainState::Drained on the first call
250 * to drain().
251 *
252 * @return DrainState::Drained if the object is drained at this
253 * point in time, DrainState::Draining if it needs further
254 * simulation.
255 */
256 virtual DrainState drain() = 0;
257
258 /**
259 * Resume execution after a successful drain.
260 */
261 virtual void drainResume() {};
262
263 /**
264 * Signal that an object is drained
265 *
266 * This method is designed to be called whenever an object enters
267 * into a state where it is ready to be drained. The method is
268 * safe to call multiple times and there is no need to check that
269 * draining has been requested before calling this method.
270 */
271 void signalDrainDone() const {
272 switch (_drainState) {
273 case DrainState::Running:
274 case DrainState::Drained:
275 case DrainState::Resuming:
276 return;
277 case DrainState::Draining:
278 _drainState = DrainState::Drained;
279 _drainManager.signalDrainDone();
280 return;
281 }
282 }
283
284 public:
285 /** Return the current drain state of an object. */
286 DrainState drainState() const { return _drainState; }
287
288 /**
289 * Notify a child process of a fork.
290 *
291 * When calling fork in gem5, we need to ensure that resources
292 * shared between the parent and the child are consistent. This
293 * method is intended to be overloaded to handle that. For
294 * example, an object could use this method to re-open input files
295 * to get a separate file description with a private file offset.
296 *
297 * This method is only called in the child of the fork. The call
298 * takes place in a drained system.
299 */
300 virtual void notifyFork() {};
301
302 private:
303 /** DrainManager interface to request a drain operation */
304 DrainState dmDrain();
305 /** DrainManager interface to request a resume operation */
306 void dmDrainResume();
307
308 /** Convenience reference to the drain manager */
309 DrainManager &_drainManager;
310
311 /**
312 * Current drain state of the object. Needs to be mutable since
313 * objects need to be able to signal that they have transitioned
314 * into a Drained state even if the calling method is const.
315 */
316 mutable DrainState _drainState;
317};
318
319#endif