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
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
|
/*
* arch/arm/common/mcpm_entry.c -- entry point for multi-cluster PM
*
* Created by: Nicolas Pitre, March 2012
* Copyright: (C) 2012-2013 Linaro Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/irqflags.h>
#include <linux/cpu_pm.h>
#include <asm/mcpm.h>
#include <asm/cacheflush.h>
#include <asm/idmap.h>
#include <asm/cputype.h>
#include <asm/suspend.h>
/*
* The public API for this code is documented in arch/arm/include/asm/mcpm.h.
* For a comprehensive description of the main algorithm used here, please
* see Documentation/arm/cluster-pm-race-avoidance.txt.
*/
struct sync_struct mcpm_sync;
/*
* __mcpm_cpu_going_down: Indicates that the cpu is being torn down.
* This must be called at the point of committing to teardown of a CPU.
* The CPU cache (SCTRL.C bit) is expected to still be active.
*/
static void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster)
{
mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN;
sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
}
/*
* __mcpm_cpu_down: Indicates that cpu teardown is complete and that the
* cluster can be torn down without disrupting this CPU.
* To avoid deadlocks, this must be called before a CPU is powered down.
* The CPU cache (SCTRL.C bit) is expected to be off.
* However L2 cache might or might not be active.
*/
static void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster)
{
dmb();
mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN;
sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
sev();
}
/*
* __mcpm_outbound_leave_critical: Leave the cluster teardown critical section.
* @state: the final state of the cluster:
* CLUSTER_UP: no destructive teardown was done and the cluster has been
* restored to the previous state (CPU cache still active); or
* CLUSTER_DOWN: the cluster has been torn-down, ready for power-off
* (CPU cache disabled, L2 cache either enabled or disabled).
*/
static void __mcpm_outbound_leave_critical(unsigned int cluster, int state)
{
dmb();
mcpm_sync.clusters[cluster].cluster = state;
sync_cache_w(&mcpm_sync.clusters[cluster].cluster);
sev();
}
/*
* __mcpm_outbound_enter_critical: Enter the cluster teardown critical section.
* This function should be called by the last man, after local CPU teardown
* is complete. CPU cache expected to be active.
*
* Returns:
* false: the critical section was not entered because an inbound CPU was
* observed, or the cluster is already being set up;
* true: the critical section was entered: it is now safe to tear down the
* cluster.
*/
static bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster)
{
unsigned int i;
struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster];
/* Warn inbound CPUs that the cluster is being torn down: */
c->cluster = CLUSTER_GOING_DOWN;
sync_cache_w(&c->cluster);
/* Back out if the inbound cluster is already in the critical region: */
sync_cache_r(&c->inbound);
if (c->inbound == INBOUND_COMING_UP)
goto abort;
/*
* Wait for all CPUs to get out of the GOING_DOWN state, so that local
* teardown is complete on each CPU before tearing down the cluster.
*
* If any CPU has been woken up again from the DOWN state, then we
* shouldn't be taking the cluster down at all: abort in that case.
*/
sync_cache_r(&c->cpus);
for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) {
int cpustate;
if (i == cpu)
continue;
while (1) {
cpustate = c->cpus[i].cpu;
if (cpustate != CPU_GOING_DOWN)
break;
wfe();
sync_cache_r(&c->cpus[i].cpu);
}
switch (cpustate) {
case CPU_DOWN:
continue;
default:
goto abort;
}
}
return true;
abort:
__mcpm_outbound_leave_critical(cluster, CLUSTER_UP);
return false;
}
static int __mcpm_cluster_state(unsigned int cluster)
{
sync_cache_r(&mcpm_sync.clusters[cluster].cluster);
return mcpm_sync.clusters[cluster].cluster;
}
extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
{
unsigned long val = ptr ? __pa_symbol(ptr) : 0;
mcpm_entry_vectors[cluster][cpu] = val;
sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
}
extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2];
void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
unsigned long poke_phys_addr, unsigned long poke_val)
{
unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
poke[0] = poke_phys_addr;
poke[1] = poke_val;
__sync_cache_range_w(poke, 2 * sizeof(*poke));
}
static const struct mcpm_platform_ops *platform_ops;
int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)
{
if (platform_ops)
return -EBUSY;
platform_ops = ops;
return 0;
}
bool mcpm_is_available(void)
{
return (platform_ops) ? true : false;
}
/*
* We can't use regular spinlocks. In the switcher case, it is possible
* for an outbound CPU to call power_down() after its inbound counterpart
* is already live using the same logical CPU number which trips lockdep
* debugging.
*/
static arch_spinlock_t mcpm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
static int mcpm_cpu_use_count[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
static inline bool mcpm_cluster_unused(unsigned int cluster)
{
int i, cnt;
for (i = 0, cnt = 0; i < MAX_CPUS_PER_CLUSTER; i++)
cnt |= mcpm_cpu_use_count[cluster][i];
return !cnt;
}
int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster)
{
bool cpu_is_down, cluster_is_down;
int ret = 0;
pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
if (!platform_ops)
return -EUNATCH; /* try not to shadow power_up errors */
might_sleep();
/*
* Since this is called with IRQs enabled, and no arch_spin_lock_irq
* variant exists, we need to disable IRQs manually here.
*/
local_irq_disable();
arch_spin_lock(&mcpm_lock);
cpu_is_down = !mcpm_cpu_use_count[cluster][cpu];
cluster_is_down = mcpm_cluster_unused(cluster);
mcpm_cpu_use_count[cluster][cpu]++;
/*
* The only possible values are:
* 0 = CPU down
* 1 = CPU (still) up
* 2 = CPU requested to be up before it had a chance
* to actually make itself down.
* Any other value is a bug.
*/
BUG_ON(mcpm_cpu_use_count[cluster][cpu] != 1 &&
mcpm_cpu_use_count[cluster][cpu] != 2);
if (cluster_is_down)
ret = platform_ops->cluster_powerup(cluster);
if (cpu_is_down && !ret)
ret = platform_ops->cpu_powerup(cpu, cluster);
arch_spin_unlock(&mcpm_lock);
local_irq_enable();
return ret;
}
typedef typeof(cpu_reset) phys_reset_t;
void mcpm_cpu_power_down(void)
{
unsigned int mpidr, cpu, cluster;
bool cpu_going_down, last_man;
phys_reset_t phys_reset;
mpidr = read_cpuid_mpidr();
cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
if (WARN_ON_ONCE(!platform_ops))
return;
BUG_ON(!irqs_disabled());
setup_mm_for_reboot();
__mcpm_cpu_going_down(cpu, cluster);
arch_spin_lock(&mcpm_lock);
BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
mcpm_cpu_use_count[cluster][cpu]--;
BUG_ON(mcpm_cpu_use_count[cluster][cpu] != 0 &&
mcpm_cpu_use_count[cluster][cpu] != 1);
cpu_going_down = !mcpm_cpu_use_count[cluster][cpu];
last_man = mcpm_cluster_unused(cluster);
if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
platform_ops->cpu_powerdown_prepare(cpu, cluster);
platform_ops->cluster_powerdown_prepare(cluster);
arch_spin_unlock(&mcpm_lock);
platform_ops->cluster_cache_disable();
__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
} else {
if (cpu_going_down)
platform_ops->cpu_powerdown_prepare(cpu, cluster);
arch_spin_unlock(&mcpm_lock);
/*
* If cpu_going_down is false here, that means a power_up
* request raced ahead of us. Even if we do not want to
* shut this CPU down, the caller still expects execution
* to return through the system resume entry path, like
* when the WFI is aborted due to a new IRQ or the like..
* So let's continue with cache cleaning in all cases.
*/
platform_ops->cpu_cache_disable();
}
__mcpm_cpu_down(cpu, cluster);
/* Now we are prepared for power-down, do it: */
if (cpu_going_down)
wfi();
/*
* It is possible for a power_up request to happen concurrently
* with a power_down request for the same CPU. In this case the
* CPU might not be able to actually enter a powered down state
* with the WFI instruction if the power_up request has removed
* the required reset condition. We must perform a re-entry in
* the kernel
|