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
|
/*
* Copyright (c) 2012-2013,2015,2018 ARM Limited
* All rights reserved
*
* The license below extends only to copyright in the software and shall
* not be construed as granting a license to any other intellectual
* property including but not limited to intellectual property relating
* to a hardware implementation of the functionality of the software
* licensed hereunder. You may use the software subject to the license
* terms below provided that you ensure that this notice is replicated
* unmodified and in its entirety in all distributions of the software,
* modified or unmodified, in source code or in binary form.
*
* Copyright (c) 2002-2005 The Regents of The University of Michigan
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met: redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer;
* redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution;
* neither the name of the copyright holders nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* Authors: Steve Reinhardt
*/
#ifndef __CPU_SIMPLE_TIMING_HH__
#define __CPU_SIMPLE_TIMING_HH__
#include "cpu/simple/base.hh"
#include "cpu/simple/exec_context.hh"
#include "cpu/translation.hh"
#include "params/TimingSimpleCPU.hh"
class TimingSimpleCPU : public BaseSimpleCPU
{
public:
TimingSimpleCPU(TimingSimpleCPUParams * params);
virtual ~TimingSimpleCPU();
void init() override;
private:
/*
* If an access needs to be broken into fragments, currently at most two,
* the the following two classes are used as the sender state of the
* packets so the CPU can keep track of everything. In the main packet
* sender state, there's an array with a spot for each fragment. If a
* fragment has already been accepted by the CPU, aka isn't waiting for
* a retry, it's pointer is NULL. After each fragment has successfully
* been processed, the "outstanding" counter is decremented. Once the
* count is zero, the entire larger access is complete.
*/
class SplitMainSenderState : public Packet::SenderState
{
public:
int outstanding;
PacketPtr fragments[2];
int
getPendingFragment()
{
if (fragments[0]) {
return 0;
} else if (fragments[1]) {
return 1;
} else {
return -1;
}
}
};
class SplitFragmentSenderState : public Packet::SenderState
{
public:
SplitFragmentSenderState(PacketPtr _bigPkt, int _index) :
bigPkt(_bigPkt), index(_index)
{}
PacketPtr bigPkt;
int index;
void
clearFromParent()
{
SplitMainSenderState * main_send_state =
dynamic_cast<SplitMainSenderState *>(bigPkt->senderState);
main_send_state->fragments[index] = NULL;
}
};
class FetchTranslation : public BaseTLB::Translation
{
protected:
TimingSimpleCPU *cpu;
public:
FetchTranslation(TimingSimpleCPU *_cpu)
: cpu(_cpu)
{}
void
markDelayed()
{
assert(cpu->_status == BaseSimpleCPU::Running);
cpu->_status = ITBWaitResponse;
}
void
finish(const Fault &fault, const RequestPtr &req, ThreadContext *tc,
BaseTLB::Mode mode)
{
cpu->sendFetch(fault, req, tc);
}
};
FetchTranslation fetchTranslation;
void threadSnoop(PacketPtr pkt, ThreadID sender);
void sendData(const RequestPtr &req,
uint8_t *data, uint64_t *res, bool read);
void sendSplitData(const RequestPtr &req1, const RequestPtr &req2,
const RequestPtr &req,
uint8_t *data, bool read);
void translationFault(const Fault &fault);
PacketPtr buildPacket(const RequestPtr &req, bool read);
void buildSplitPacket(PacketPtr &pkt1, PacketPtr &pkt2,
const RequestPtr &req1, const RequestPtr &req2,
const RequestPtr &req,
uint8_t *data, bool read);
bool handleReadPacket(PacketPtr pkt);
// This function always implicitly uses dcache_pkt.
bool handleWritePacket();
/**
* A TimingCPUPort overrides the default behaviour of the
* recvTiming and recvRetry and implements events for the
* scheduling of handling of incoming packets in the following
* cycle.
*/
class TimingCPUPort : public MasterPort
{
public:
TimingCPUPort(const std::string& _name, TimingSimpleCPU* _cpu)
: MasterPort(_name, _cpu), cpu(_cpu),
retryRespEvent([this]{ sendRetryResp(); }, name())
{ }
protected:
TimingSimpleCPU* cpu;
struct TickEvent : public Event
{
PacketPtr pkt;
TimingSimpleCPU *cpu;
TickEvent(TimingSimpleCPU *_cpu) : pkt(NULL), cpu(_cpu) {}
const char *description() const { return "Timing CPU tick"; }
void schedule(PacketPtr _pkt, Tick t);
};
EventFunctionWrapper retryRespEvent;
};
class IcachePort : public TimingCPUPort
{
public:
IcachePort(TimingSimpleCPU *_cpu)
: TimingCPUPort(_cpu->name() + ".icache_port", _cpu),
tickEvent(_cpu)
{ }
protected:
virtual bool recvTimingResp(PacketPtr pkt);
virtual void recvReqRetry();
struct ITickEvent : public TickEvent
{
ITickEvent(TimingSimpleCPU *_cpu)
: TickEvent(_cpu) {}
void process();
const char *description() const { return "Timing CPU icache tick"; }
};
ITickEvent tickEvent;
};
class DcachePort : public TimingCPUPort
{
public:
DcachePort(TimingSimpleCPU *_cpu)
: TimingCPUPort(_cpu->name() + ".dcache_port", _cpu),
tickEvent(_cpu)
{
cacheBlockMask = ~(cpu->cacheLineSize() - 1);
}
Addr cacheBlockMask;
protected:
/** Snoop a coherence request, we need to check if this causes
* a wakeup event on a cpu that is monitoring an address
*/
virtual void recvTimingSnoopReq(PacketPtr pkt);
virtual void recvFunctionalSnoop(PacketPtr pkt);
virtual bool recvTimingResp(PacketPtr pkt);
virtual void recvReqRetry();
virtual bool isSnooping() const {
return true;
}
struct DTickEvent : public TickEvent
{
DTickEvent(TimingSimpleCPU *_cpu)
: TickEvent(_cpu) {}
void process();
const char *description() const { return "Timing CPU dcache tick"; }
};
DTickEvent tickEvent;
};
void updateCycleCounts();
IcachePort icachePort;
DcachePort dcachePort;
PacketPtr ifetch_pkt;
PacketPtr dcache_pkt;
Cycles previousCycle;
protected:
/** Return a reference to the data port. */
Port &getDataPort() override { return dcachePort; }
/** Return a reference to the instruction port. */
Port &getInstPort() override { return icachePort; }
public:
DrainState drain() override;
void drainResume() override;
void switchOut() override;
void takeOverFrom(BaseCPU *oldCPU) override;
void verifyMemoryMode() const override;
void activateContext(ThreadID thread_num) override;
void suspendContext(ThreadID thread_num) override;
Fault initiateMemRead(Addr addr, unsigned size,
Request::Flags flags,
const std::vector<bool>& byte_enable =std::vector<bool>())
override;
Fault writeMem(uint8_t *data, unsigned size,
Addr addr, Request::Flags flags, uint64_t *res,
const std::vector<bool>& byte_enable = std::vector<bool>())
override;
Fault initiateMemAMO(Addr addr, unsigned size, Request::Flags flags,
AtomicOpFunctorPtr amo_op) override;
void fetch();
void sendFetch(const Fault &fault,
const RequestPtr &req, ThreadContext *tc);
void completeIfetch(PacketPtr );
void completeDataAccess(PacketPtr pkt);
void advanceInst(const Fault &fault);
/** This function is used by the page table walker to determine if it could
* translate the a pending request or if the underlying request has been
* squashed. This always returns false for the simple timing CPU as it never
* executes any instructions speculatively.
* @ return Is the current instruction squashed?
*/
bool isSquashed() const { return false; }
/**
* Print state of address in memory system via PrintReq (for
* debugging).
*/
void printAddr(Addr a);
/**
* Finish a DTB translation.
* @param state The DTB translation state.
*/
void finishTranslation(WholeTranslationState *state);
private:
EventFunctionWrapper fetchEvent;
struct IprEvent : Event {
Packet *pkt;
TimingSimpleCPU *cpu;
IprEvent(Packet *_pkt, TimingSimpleCPU *_cpu, Tick t);
virtual void process();
virtual const char *description() const;
};
/**
* Check if a system is in a drained state.
*
* We need to drain if:
* <ul>
* <li>We are in the middle of a microcode sequence as some CPUs
* (e.g., HW accelerated CPUs) can't be started in the middle
* of a gem5 microcode sequence.
*
* <li>Stay at PC is true.
*
* <li>A fetch event is scheduled. Normally this would never be the
* case with microPC() == 0, but right after a context is
* activated it can happen.
* </ul>
*/
bool isCpuDrained() const {
SimpleExecContext& t_info = *threadInfo[curThread];
SimpleThread* thread = t_info.thread;
return thread->microPC() == 0 && !t_info.stayAtPC &&
!fetchEvent.scheduled();
}
/**
* Try to complete a drain request.
*
* @returns true if the CPU is drained, false otherwise.
*/
bool tryCompleteDrain();
};
#endif // __CPU_SIMPLE_TIMING_HH__
|