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
|
#include "cgroup-internal.h"
#include <linux/sched/cputime.h>
static DEFINE_SPINLOCK(cgroup_rstat_lock);
static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
{
return per_cpu_ptr(cgrp->rstat_cpu, cpu);
}
/**
* cgroup_rstat_updated - keep track of updated rstat_cpu
* @cgrp: target cgroup
* @cpu: cpu on which rstat_cpu was updated
*
* @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching
* rstat_cpu->updated_children list. See the comment on top of
* cgroup_rstat_cpu definition for details.
*/
void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
{
raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
struct cgroup *parent;
unsigned long flags;
/* nothing to do for root */
if (!cgroup_parent(cgrp))
return;
/*
* Paired with the one in cgroup_rstat_cpu_pop_upated(). Either we
* see NULL updated_next or they see our updated stat.
*/
smp_mb();
/*
* Because @parent's updated_children is terminated with @parent
* instead of NULL, we can tell whether @cgrp is on the list by
* testing the next pointer for NULL.
*/
if (cgroup_rstat_cpu(cgrp, cpu)->updated_next)
return;
raw_spin_lock_irqsave(cpu_lock, flags);
/* put @cgrp and all ancestors on the corresponding updated lists */
for (parent = cgroup_parent(cgrp); parent;
cgrp = parent, parent = cgroup_parent(cgrp)) {
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
/*
* Both additions and removals are bottom-up. If a cgroup
* is already in the tree, all ancestors are.
*/
if (rstatc->updated_next)
break;
rstatc->updated_next = prstatc->updated_children;
prstatc->updated_children = cgrp;
}
raw_spin_unlock_irqrestore(cpu_lock, flags);
}
EXPORT_SYMBOL_GPL(cgroup_rstat_updated);
/**
* cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
* @pos: current position
* @root: root of the tree to traversal
* @cpu: target cpu
*
* Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts
* the traversal and %NULL return indicates the end. During traversal,
* each returned cgroup is unlinked from the tree. Must be called with the
* matching cgroup_rstat_cpu_lock held.
*
* The only ordering guarantee is that, for a parent and a child pair
* covered by a given traversal, if a child is visited, its parent is
* guaranteed to be visited afterwards.
*/
static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
struct cgroup *root, int cpu)
{
struct cgroup_rstat_cpu *rstatc;
if (pos == root)
return NULL;
/*
* We're gonna walk down to the first leaf and visit/remove it. We
* can pick whatever unvisited node as the starting point.
*/
if (!pos)
pos = root;
else
pos = cgroup_parent(pos);
/* walk down to the first leaf */
while (true) {
rstatc = cgroup_rstat_cpu(pos, cpu);
if (rstatc->updated_children == pos)
break;
pos = rstatc->updated_children;
}
/*
* Unlink @pos from the tree. As the updated_children list is
* singly linked, we have to walk it to find the removal point.
* However, due to the way we traverse, @pos will be the first
* child in most cases. The only exception is @root.
*/
if (rstatc->updated_next) {
struct cgroup *parent = cgroup_parent(pos);
struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
struct cgroup_rstat_cpu *nrstatc;
struct cgroup **nextp;
nextp = &prstatc->updated_children;
while (true) {
nrstatc = cgroup_rstat_cpu(*nextp, cpu);
if (*nextp == pos)
break;
WARN_ON_ONCE(*nextp == parent);
nextp = &nrstatc->updated_next;
}
*nextp = rstatc->updated_next;
rstatc->updated_next = NULL;
/*
* Paired with the one in cgroup_rstat_cpu_updated().
* Either they see NULL updated_next or we see their
* updated stat.
*/
smp_mb();
return pos;
}
/* only happens for @root */
return NULL;
}
/* see cgroup_rstat_flush() */
static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
{
int cpu;
lockdep_assert_held(&cgroup_rstat_lock);
for_each_possible_cpu(cpu) {
raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
cpu);
struct cgroup *pos = NULL;
raw_spin_lock(cpu_lock);
while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
struct cgroup_subsys_state *css;
cgroup_base_stat_flush(pos, cpu);
rcu_read_lock();
list_for_each_entry_rcu(css, &pos->rstat_css_list,
rstat_css_node)
css->ss->css_rstat_flush(css, cpu);
rcu_read_unlock();
}
raw_spin_unlock(cpu_lock);
/* if @may_sleep, play nice and yield if necessary */
if (may_sleep && (need_resched() ||
spin_needbreak(&cgroup_rstat_lock))) {
spin_unlock_irq(&cgroup_rstat_lock);
if (!cond_resched())
cpu_relax();
spin_lock_irq(&cgroup_rstat_lock);
}
}
}
/**
* cgroup_rstat_flush - flush stats in @cgrp's subtree
* @cgrp: target cgroup
*
* Collect all per-cpu stats in @cgrp's subtree into the global counters
* and propagate them upwards. After this function returns, all cgroups in
* the subtree have up-to-date ->stat.
*
* This also gets all cgroups in the subtree including @cgrp off the
* ->updated_children lists.
*
* This function may block.
*/
void cgroup_rstat_flush(struct cgroup *cgrp)
{
might_sleep();
spin_lock_irq(&cgroup_rstat_lock);
cgroup_rstat_flush_locked(cgrp, true);
spin_unlock_irq(&cgroup_rstat_lock);
}
/**
* cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush()
* @cgrp: target cgroup
*
* This function can be called from any context.
*/
void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp)
{
unsigned long flags;
spin_lock_irqsave(&cgroup_rstat_lock, flags);
cgroup_rstat_flush_locked(cgrp, false);
spin_unlock_irqrestore(&cgroup_rstat_lock, flags);
}
/**
* cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold
* @cgrp: target cgroup
*
* Flush stats in @cgrp's subtree and prevent further flushes. Must be
* paired with cgroup_rstat_flush_release().
*
* This function may block.
*/
void cgroup_rstat_flush_hold(struct cgroup *cgrp)
__acquires(&cgroup_rstat_lock)
{
might_sleep();
spin_lock_irq(&cgroup_rstat_lock);
cgroup_rstat_flush_locked(cgrp, true);
}
/**
* cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
*/
void cgroup_rstat_flush_release(void)
__releases(&cgroup_rstat_lock)
{
spin_unlock_irq(&cgroup_rstat_lock);
}
int cgroup_rstat_init(struct cgroup *cgrp)
{
int cpu;
/* the root cgrp has rstat_cpu preallocated */
if (!cgrp->rstat_cpu) {
cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu);
if (!cgrp->rstat_cpu)
return -ENOMEM;
}
/* ->updated_children list is self terminated */
for_each_possible_cpu(cpu) {
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
rstatc->updated_children = cgrp;
u64_stats_init(&rstatc->bsync);
}
return 0;
}
void cgroup_rstat_exit(struct cgroup *cgrp)
{
int cpu;
cgroup_rstat_flush(cgrp);
/* sanity check */
for_each_possible_cpu(cpu) {
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
if (WARN_ON_ONCE(rstatc->updated_children != cgrp) ||
WARN_ON_ONCE(rstatc->updated_next))
return;
}
free_percpu(cgrp->rstat_cpu);
cgrp->rstat_cpu = NULL;
}
void __init cgroup_rstat_boot(void)
{
int cpu;
for_each_possible_cpu(cpu)
raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp));
}
/*
* Functions for cgroup basic resource statistics implemented on top of
* rstat.
*/
static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat,
struct cgroup_base_stat *src_bstat)
{
dst_bstat->cputime.utime += src_bstat->cputime.utime;
dst_bstat->cputime.stime += src_bstat->cputime.stime;
dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
}
static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
{
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
struct task_cputime *last_cputime = &rstatc->last_bstat.cputime;
struct task_cputime cputime;
struct cgroup_base_stat delta;
unsigned seq;
/* fetch the current per-cpu values */
do {
seq = __u64_stats_fetch_begin(&rstatc->bsync);
cputime = rstatc->bstat.cputime;
} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
/* calculate the delta to propgate */
delta.cputime.utime = cputime.utime -
|