summaryrefslogtreecommitdiff
path: root/kernel/cgroup/rstat.c
blob: 07e2284bb4997123dd3c6699d98f6d42ae0e6166 (plain)
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
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
// SPDX-License-Identifier: GPL-2.0-only
#include "cgroup-internal.h"

#include <linux/sched/cputime.h>

#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/btf_ids.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.
 */
__bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
{
	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
	unsigned long flags;

	/*
	 * Speculative already-on-list test. This may race leading to
	 * temporary inaccuracies, which is fine.
	 *
	 * 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 (data_race(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 */
	while (true) {
		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
		struct cgroup *parent = cgroup_parent(cgrp);
		struct cgroup_rstat_cpu *prstatc;

		/*
		 * Both additions and removals are bottom-up.  If a cgroup
		 * is already in the tree, all ancestors are.
		 */
		if (rstatc->updated_next)
			break;

		/* Root has no parent to link it to, but mark it busy */
		if (!parent) {
			rstatc->updated_next = cgrp;
			break;
		}

		prstatc = cgroup_rstat_cpu(parent, cpu);
		rstatc->updated_next = prstatc->updated_children;
		prstatc->updated_children = cgrp;

		cgrp = parent;
	}

	raw_spin_unlock_irqrestore(cpu_lock, flags);
}

/**
 * cgroup_rstat_push_children - push children cgroups into the given list
 * @head: current head of the list (= subtree root)
 * @child: first child of the root
 * @cpu: target cpu
 * Return: A new singly linked list of cgroups to be flush
 *
 * Iteratively traverse down the cgroup_rstat_cpu updated tree level by
 * level and push all the parents first before their next level children
 * into a singly linked list built from the tail backward like "pushing"
 * cgroups into a stack. The root is pushed by the caller.
 */
static struct cgroup *cgroup_rstat_push_children(struct cgroup *head,
						 struct cgroup *child, int cpu)
{
	struct cgroup *chead = child;	/* Head of child cgroup level */
	struct cgroup *ghead = NULL;	/* Head of grandchild cgroup level */
	struct cgroup *parent, *grandchild;
	struct cgroup_rstat_cpu *crstatc;

	child->rstat_flush_next = NULL;

next_level:
	while (chead) {
		child = chead;
		chead = child->rstat_flush_next;
		parent = cgroup_parent(child);

		/* updated_next is parent cgroup terminated */
		while (child != parent) {
			child->rstat_flush_next = head;
			head = child;
			crstatc = cgroup_rstat_cpu(child, cpu);
			grandchild = crstatc->updated_children;
			if (grandchild != child) {
				/* Push the grand child to the next level */
				crstatc->updated_children = child;
				grandchild->rstat_flush_next = ghead;
				ghead = grandchild;
			}
			child = crstatc->updated_next;
			crstatc->updated_next = NULL;
		}
	}

	if (ghead) {
		chead = ghead;
		ghead = NULL;
		goto next_level;
	}
	return head;
}

/**
 * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed
 * @root: root of the cgroup subtree to traverse
 * @cpu: target cpu
 * Return: A singly linked list of cgroups to be flushed
 *
 * Walks the updated rstat_cpu tree on @cpu from @root.  During traversal,
 * each returned cgroup is unlinked from the updated tree.
 *
 * The only ordering guarantee is that, for a parent and a child pair
 * covered by a given traversal, the child is before its parent in
 * the list.
 *
 * Note that updated_children is self terminated and points to a list of
 * child cgroups if not empty. Whereas updated_next is like a sibling link
 * within the children list and terminated by the parent cgroup. An exception
 * here is the cgroup root whose updated_next can be self terminated.
 */
static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
{
	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu);
	struct cgroup *head = NULL, *parent, *child;
	unsigned long flags;

	/*
	 * The _irqsave() is needed because cgroup_rstat_lock is
	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
	 * this lock with the _irq() suffix only disables interrupts on
	 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
	 * interrupts on both configurations. The _irqsave() ensures
	 * that interrupts are always disabled and later restored.
	 */
	raw_spin_lock_irqsave(cpu_lock, flags);

	/* Return NULL if this subtree is not on-list */
	if (!rstatc->updated_next)
		goto unlock_ret;

	/*
	 * Unlink @root from its parent. As the updated_children list is
	 * singly linked, we have to walk it to find the removal point.
	 */
	parent = cgroup_parent(root);
	if (parent) {
		struct cgroup_rstat_cpu *prstatc;
		struct cgroup **nextp;

		prstatc = cgroup_rstat_cpu(parent, cpu);
		nextp = &prstatc->updated_children;
		while (*nextp != root) {
			struct cgroup_rstat_cpu *nrstatc;

			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
			WARN_ON_ONCE(*nextp == parent);
			nextp = &nrstatc->updated_next;
		}
		*nextp = rstatc->updated_next;
	}

	rstatc->updated_next = NULL;

	/* Push @root to the list first before pushing the children */
	head = root;
	root->rstat_flush_next = NULL;
	child = rstatc->updated_children;
	rstatc->updated_children = root;
	if (child != root)
		head = cgroup_rstat_push_children(head, child, cpu);
unlock_ret:
	raw_spin_unlock_irqrestore(cpu_lock, flags);
	return head;
}

/*
 * A hook for bpf stat collectors to attach to and flush their stats.
 * Together with providing bpf kfuncs for cgroup_rstat_updated() and
 * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that
 * collect cgroup stats can integrate with rstat for efficient flushing.
 *
 * A static noinline declaration here could cause the compiler to optimize away
 * the function. A global noinline declaration will keep the definition, but may
 * optimize away the callsite. Therefore, __weak is needed to ensure that the
 * call is still emitted, by telling the compiler that we don't know what the
 * function might eventually be.
 */

__bpf_hook_start();

__weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
				     struct cgroup *parent, int cpu)
{
}

__bpf_hook_end();

/* see cgroup_rstat_flush() */
static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
{
	int cpu;

	lockdep_assert_held(&cgroup_rstat_lock);

	for_each_possible_cpu(cpu) {
		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);

		for (; pos; pos = pos->rstat_flush_next) {
			struct cgroup_subsys_state *css;

			cgroup_base_stat_flush(pos, cpu);
			bpf_rstat_flush(pos, cgroup_parent(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();
		}

		/* play nice and yield if necessary */
		if (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.
 */
__bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
{
	might_sleep();

	spin_lock_irq(&cgroup_rstat_lock);
	cgroup_rstat_flush_locked(cgrp);
	spin_unlock_irq(&cgroup_rstat_lock);
}

/**
 * cgroup_rstat_flush_hold - 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);
}

/**
 * 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));
}

/*
 * Functions for cgroup basic resource statistics implemented on top of
 * rstat.
 */
static void cgroup_base_stat_add(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;
#ifdef CONFIG_SCHED_CORE
	dst_bstat->forceidle_sum += src_bstat->forceidle_sum;
#endif
}

static void cgroup_base_stat_sub(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;
#ifdef CONFIG_SCHED_CORE
	dst_bstat->forceidle_sum -= src_bstat->forceidle_sum;
#endif
}

static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
{
	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
	struct cgroup *parent = cgroup_parent(cgrp);
	struct cgroup_rstat_cpu *prstatc;
	struct cgroup_base_stat delta;
	unsigned seq;

	/* Root-level stats are sourced from system-wide CPU stats */
	if (!parent)
		return;

	/* fetch the current per-cpu values */
	do {
		seq = __u64_stats_fetch_begin(&rstatc->bsync);
		delta = rstatc->bstat;
	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));

	/* propagate per-cpu delta to cgroup and per-cpu global statistics */
	cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
	cgroup_base_stat_add(&cgrp->bstat, &delta);
	cgroup_base_stat_add(&rstatc->last_bstat, &delta);
	cgroup_base_stat_add(&rstatc->subtree_bstat, &delta);

	/* propagate cgroup and per-cpu global delta to parent (unless that's root) */
	if (cgroup_parent(parent)) {
		delta = cgrp->bstat;
		cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
		cgroup_base_stat_add(&parent->bstat, &delta);
		cgroup_base_stat_add(&cgrp->last_bstat, &delta);

		delta = rstatc->subtree_bstat;
		prstatc = cgroup_rstat_cpu(parent, cpu);
		cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat);
		cgroup_base_stat_add(&prstatc->subtree_bstat, &delta);
		cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta);
	}
}

static struct cgroup_rstat_cpu *
cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags)
{
	struct cgroup_rstat_cpu *rstatc;

	rstatc = get_cpu_ptr(cgrp->rstat_cpu);
	*flags = u64_stats_update_begin_irqsave(&rstatc->bsync);
	return rstatc;
}

static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
						 struct cgroup_rstat_cpu *rstatc,
						 unsigned long flags)
{
	u64_stats_update_end_irqrestore(&rstatc->bsync, flags);
	cgroup_rstat_updated(cgrp, smp_processor_id());
	put_cpu_ptr(rstatc);
}

void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
{
	struct cgroup_rstat_cpu *rstatc;
	unsigned long flags;

	rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
	rstatc->bstat.cputime.sum_exec_runtime += delta_exec;
	cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
}

void __cgroup_account_cputime_field(struct cgroup *cgrp,
				    enum cpu_usage_stat index, u64 delta_exec)
{
	struct cgroup_rstat_cpu *rstatc;
	unsigned long flags;

	rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);

	switch (index) {
	case CPUTIME_USER:
	case CPUTIME_NICE:
		rstatc->bstat.cputime.utime += delta_exec;
		break;
	case CPUTIME_SYSTEM:
	case CPUTIME_IRQ:
	case CPUTIME_SOFTIRQ:
		rstatc->bstat.cputime.stime += delta_exec;
		break;
#ifdef CONFIG_SCHED_CORE
	case CPUTIME_FORCEIDLE:
		rstatc->bstat.forceidle_sum += delta_exec;
		break;
#endif
	default:
		break;
	}

	cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
}

/*
 * compute the cputime for the root cgroup by getting the per cpu data
 * at a global level, then categorizing the fields in a manner consistent
 * with how it is done by __cgroup_account_cputime_field for each bit of
 * cpu time attributed to a cgroup.
 */
static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
{
	struct task_cputime *cputime = &bstat->cputime;
	int i;

	memset(bstat, 0, sizeof(*bstat));
	for_each_possible_cpu(i) {
		struct kernel_cpustat kcpustat;
		u64 *cpustat = kcpustat.cpustat;
		u64 user = 0;
		u64 sys = 0;

		kcpustat_cpu_fetch(&kcpustat, i);

		user += cpustat[CPUTIME_USER];
		user += cpustat[CPUTIME_NICE];
		cputime->utime += user;

		sys += cpustat[CPUTIME_SYSTEM];
		sys += cpustat[CPUTIME_IRQ];
		sys += cpustat[CPUTIME_SOFTIRQ];
		cputime->stime += sys;

		cputime->sum_exec_runtime += user;
		cputime->sum_exec_runtime += sys;
		cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];

#ifdef CONFIG_SCHED_CORE
		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
#endif
	}
}

void cgroup_base_stat_cputime_show(struct seq_file *seq)
{
	struct cgroup *cgrp = seq_css(seq)->cgroup;
	u64 usage, utime, stime;
	struct cgroup_base_stat bstat;
#ifdef CONFIG_SCHED_CORE
	u64 forceidle_time;
#endif

	if (cgroup_parent(cgrp)) {
		cgroup_rstat_flush_hold(cgrp);
		usage = cgrp->bstat.cputime.sum_exec_runtime;
		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
			       &utime, &stime);
#ifdef CONFIG_SCHED_CORE
		forceidle_time = cgrp->bstat.forceidle_sum;
#endif
		cgroup_rstat_flush_release();
	} else {
		root_cgroup_cputime(&bstat);
		usage = bstat.cputime.sum_exec_runtime;
		utime = bstat.cputime.utime;
		stime = bstat.cputime.stime;
#ifdef CONFIG_SCHED_CORE
		forceidle_time = bstat.forceidle_sum;
#endif
	}

	do_div(usage, NSEC_PER_USEC);
	do_div(utime, NSEC_PER_USEC);
	do_div(stime, NSEC_PER_USEC);
#ifdef CONFIG_SCHED_CORE
	do_div(forceidle_time, NSEC_PER_USEC);
#endif

	seq_printf(seq, "usage_usec %llu\n"
		   "user_usec %llu\n"
		   "system_usec %llu\n",
		   usage, utime, stime);

#ifdef CONFIG_SCHED_CORE
	seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
#endif
}

/* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */
BTF_KFUNCS_START(bpf_rstat_kfunc_ids)
BTF_ID_FLAGS(func, cgroup_rstat_updated)
BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE)
BTF_KFUNCS_END(bpf_rstat_kfunc_ids)

static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = {
	.owner          = THIS_MODULE,
	.set            = &bpf_rstat_kfunc_ids,
};

static int __init bpf_rstat_kfunc_init(void)
{
	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
					 &bpf_rstat_kfunc_set);
}
late_initcall(bpf_rstat_kfunc_init);