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
|
/*
* Generic helpers for smp ipi calls
*
* (C) Jens Axboe <jens.axboe@oracle.com> 2008
*
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/smp.h>
static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
static LIST_HEAD(call_function_queue);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
enum {
CSD_FLAG_WAIT = 0x01,
CSD_FLAG_ALLOC = 0x02,
};
struct call_function_data {
struct call_single_data csd;
spinlock_t lock;
unsigned int refs;
cpumask_t cpumask;
struct rcu_head rcu_head;
};
struct call_single_queue {
struct list_head list;
spinlock_t lock;
};
static int __cpuinit init_call_single_data(void)
{
int i;
for_each_possible_cpu(i) {
struct call_single_queue *q = &per_cpu(call_single_queue, i);
spin_lock_init(&q->lock);
INIT_LIST_HEAD(&q->list);
}
return 0;
}
early_initcall(init_call_single_data);
static void csd_flag_wait(struct call_single_data *data)
{
/* Wait for response */
do {
/*
* We need to see the flags store in the IPI handler
*/
smp_mb();
if (!(data->flags & CSD_FLAG_WAIT))
break;
cpu_relax();
} while (1);
}
/*
* Insert a previously allocated call_single_data element for execution
* on the given CPU. data must already have ->func, ->info, and ->flags set.
*/
static void generic_exec_single(int cpu, struct call_single_data *data)
{
struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
int wait = data->flags & CSD_FLAG_WAIT, ipi;
unsigned long flags;
spin_lock_irqsave(&dst->lock, flags);
ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
spin_unlock_irqrestore(&dst->lock, flags);
if (ipi)
arch_send_call_function_single_ipi(cpu);
if (wait)
csd_flag_wait(data);
}
static void rcu_free_call_data(struct rcu_head *head)
{
struct call_function_data *data;
data = container_of(head, struct call_function_data, rcu_head);
kfree(data);
}
/*
* Invoked by arch to handle an IPI for call function. Must be called with
* interrupts disabled.
*/
void generic_smp_call_function_interrupt(void)
{
struct call_function_data *data;
int cpu = get_cpu();
/*
* It's ok to use list_for_each_rcu() here even though we may delete
* 'pos', since list_del_rcu() doesn't clear ->next
*/
rcu_read_lock();
list_for_each_entry_rcu(data, &call_function_queue, csd.list) {
int refs;
if (!cpu_isset(cpu, data->cpumask))
continue;
data->csd.func(data->csd.info);
spin_lock(&data->lock);
cpu_clear(cpu, data->cpumask);
WARN_ON(data->refs == 0);
data->refs--;
refs = data->refs;
spin_unlock(&data->lock);
if (refs)
continue;
spin_lock(&call_function_lock);
list_del_rcu(&data->csd.list);
spin_unlock(&call_function_lock);
if (data->csd.flags & CSD_FLAG_WAIT) {
/*
* serialize stores to data with the flag clear
* and wakeup
*/
smp_wmb();
data->csd.flags &= ~CSD_FLAG_WAIT;
}
if (data->csd.flags & CSD_FLAG_ALLOC)
call_rcu(&data->rcu_head, rcu_free_call_data);
}
rcu_read_unlock();
put_cpu();
}
/*
* Invoked by arch to handle an IPI for call function single. Must be called
* from the arch with interrupts disabled.
*/
void generic_smp_call_function_single_interrupt(void)
{
struct call_single_queue *q = &__get_cpu_var(call_single_queue);
LIST_HEAD(list);
/*
* Need to see other stores to list head for checking whether
* list is empty without holding q->lock
*/
smp_mb();
while (!list_empty(&q->list)) {
unsigned int data_flags;
spin_lock(&q->lock);
list_replace_init(&q->list, &list);
spin_unlock(&q->lock);
while (!list_empty(&list)) {
struct call_single_data *data;
data = list_entry(list.next, struct call_single_data,
list);
list_del(&data->list);
/*
* 'data' can be invalid after this call if
* flags == 0 (when called through
* generic_exec_single(), so save them away before
* making the call.
*/
data_flags = data->flags;
data->func(data->info);
if (data_flags & CSD_FLAG_WAIT) {
smp_wmb();
data->flags &= ~CSD_FLAG_WAIT;
} else if (data_flags & CSD_FLAG_ALLOC)
kfree(data);
}
/*
* See comment on outer loop
*/
smp_mb();
}
}
/*
* smp_call_function_single - Run a function on a specific CPU
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait until function has completed on other CPUs.
*
* Returns 0 on success, else a negative status code. Note that @wait
* will be implicitly turned on in case of allocation failures, since
* we fall back to on-stack allocation.
*/
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
int wait)
{
struct call_single_data d;
unsigned long flags;
/* prevent preemption and reschedule on another processor */
int me = get_cpu();
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
if (cpu == me) {
local_irq_save(flags);
func(info);
local_irq_restore(flags);
} else {
struct call_single_data *data = NULL;
if (!wait) {
data = kmalloc(sizeof(*data), GFP_ATOMIC);
if (data)
data->flags = CSD_FLAG_ALLOC;
}
if (!data) {
data = &d;
data->flags = CSD_FLAG_WAIT;
}
data->func = func;
data->info = info;
generic_exec_single(cpu, data);
}
put_cpu();
return 0;
}
EXPORT_SYMBOL(smp_call_function_single);
/**
* __smp_call_function_single(): Run a function on another CPU
* @cpu: The CPU to run on.
* @data: Pre-allocated and setup data structure
*
* Like smp_call_function_single(), but allow caller to pass in a pre-allocated
* data structure. Useful for embedding @data inside other structures, for
* instance.
*
*/
void __smp_call_function_single(int cpu, struct call_single_data *data)
{
/* Can deadlock when called with interrupts disabled */
WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
generic_exec_single(cpu, data);
}
/* Dummy function */
static void quiesce_dummy(void *unused)
{
}
/*
* Ensure stack based data used in call function mask is safe to free.
*
* This is needed by smp_call_function_mask when using on-stack data, because
* a single call function queue is shared by all CPUs, and any CPU may pick up
* the data item on the queue at any time before it is deleted. So we need to
* ensure that all CPUs have transitioned through a quiescent state after
* this call.
*
* This is a very slow function, implemented by sending synchronous IPIs to
* all possible CPUs. For this reason, we have to alloc data rather than use
* stack based data even in the case of synchronous calls. The stack based
* data is then just used for deadlock/oom fallback which will be very rare.
*
* If a faster scheme can be made, we could go back to preferring stack based
* data -- the data allocation/free is non-zero cost.
*/
static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
{
struct call_single_data data;
int cpu;
data.func = quiesce_dummy;
data.info = NULL;
for_each_cpu_mask(cpu, mask) {
data.flags = CSD_FLAG_WAIT;
generic_exec_single(cpu, &data);
}
}
/**
* smp_call_function_mask(): Run a function on a set of other CPUs.
* @mask: The set of cpus to run on.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait (atomically) until function has completed on other CPUs.
*
* Returns 0 on success, else a negative status code.
*
* If @wait is true, then returns once @func has returned. Note that @wait
* will be implicitly turned on in case of allocation failures, since
* we fall back to on-stack allocation.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler. Preemption
* must be disabled when calling this function.
*/
int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
int wait)
{
struct call_function_data d;
struct call_function_data *data = NULL;
cpumask_t allbutself;
unsigned long flags;
int cpu, num_cpus;
int slowpath = 0;
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
cpu = smp_processor_id();
allbutself = cpu_online_map;
cpu_clear(cpu, allbutself);
cpus_and(mask, mask, allbutself);
num_cpus = cpus_weight(mask);
/*
* If zero CPUs, return. If just a single CPU, turn this request
* into a targetted single call instead since it's faster.
*/
if (!num_cpus)
return 0;
else if (num_cpus == 1) {
cpu = first_cpu(mask);
|