summaryrefslogtreecommitdiffstats
path: root/kernel/rcu/refscale.c
blob: dbd670376c42e42704e195b39974571e126e114c (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
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
// SPDX-License-Identifier: GPL-2.0+
//
// Scalability test comparing RCU vs other mechanisms
// for acquiring references on objects.
//
// Copyright (C) Google, 2020.
//
// Author: Joel Fernandes <joel@joelfernandes.org>

#define pr_fmt(fmt) fmt

#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/completion.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kthread.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/rcupdate_trace.h>
#include <linux/reboot.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/stat.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/torture.h>
#include <linux/types.h>

#include "rcu.h"

#define SCALE_FLAG "-ref-scale: "

#define SCALEOUT(s, x...) \
	pr_alert("%s" SCALE_FLAG s, scale_type, ## x)

#define VERBOSE_SCALEOUT(s, x...) \
	do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0)

#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \
	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0)

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>");

static char *scale_type = "rcu";
module_param(scale_type, charp, 0444);
MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock.");

torture_param(int, verbose, 0, "Enable verbose debugging printk()s");

// Wait until there are multiple CPUs before starting test.
torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
	      "Holdoff time before test start (s)");
// Number of loops per experiment, all readers execute operations concurrently.
torture_param(long, loops, 10000, "Number of loops per experiment.");
// Number of readers, with -1 defaulting to about 75% of the CPUs.
torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs.");
// Number of runs.
torture_param(int, nruns, 30, "Number of experiments to run.");
// Reader delay in nanoseconds, 0 for no delay.
torture_param(int, readdelay, 0, "Read-side delay in nanoseconds.");

#ifdef MODULE
# define REFSCALE_SHUTDOWN 0
#else
# define REFSCALE_SHUTDOWN 1
#endif

torture_param(bool, shutdown, REFSCALE_SHUTDOWN,
	      "Shutdown at end of scalability tests.");

struct reader_task {
	struct task_struct *task;
	int start_reader;
	wait_queue_head_t wq;
	u64 last_duration_ns;
};

static struct task_struct *shutdown_task;
static wait_queue_head_t shutdown_wq;

static struct task_struct *main_task;
static wait_queue_head_t main_wq;
static int shutdown_start;

static struct reader_task *reader_tasks;

// Number of readers that are part of the current experiment.
static atomic_t nreaders_exp;

// Use to wait for all threads to start.
static atomic_t n_init;
static atomic_t n_started;
static atomic_t n_warmedup;
static atomic_t n_cooleddown;

// Track which experiment is currently running.
static int exp_idx;

// Operations vector for selecting different types of tests.
struct ref_scale_ops {
	void (*init)(void);
	void (*cleanup)(void);
	void (*readsection)(const int nloops);
	void (*delaysection)(const int nloops, const int udl, const int ndl);
	const char *name;
};

static struct ref_scale_ops *cur_ops;

static void un_delay(const int udl, const int ndl)
{
	if (udl)
		udelay(udl);
	if (ndl)
		ndelay(ndl);
}

static void ref_rcu_read_section(const int nloops)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		rcu_read_lock();
		rcu_read_unlock();
	}
}

static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		rcu_read_lock();
		un_delay(udl, ndl);
		rcu_read_unlock();
	}
}

static void rcu_sync_scale_init(void)
{
}

static struct ref_scale_ops rcu_ops = {
	.init		= rcu_sync_scale_init,
	.readsection	= ref_rcu_read_section,
	.delaysection	= ref_rcu_delay_section,
	.name		= "rcu"
};

// Definitions for SRCU ref scale testing.
DEFINE_STATIC_SRCU(srcu_refctl_scale);
static struct srcu_struct *srcu_ctlp = &srcu_refctl_scale;

static void srcu_ref_scale_read_section(const int nloops)
{
	int i;
	int idx;

	for (i = nloops; i >= 0; i--) {
		idx = srcu_read_lock(srcu_ctlp);
		srcu_read_unlock(srcu_ctlp, idx);
	}
}

static void srcu_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;
	int idx;

	for (i = nloops; i >= 0; i--) {
		idx = srcu_read_lock(srcu_ctlp);
		un_delay(udl, ndl);
		srcu_read_unlock(srcu_ctlp, idx);
	}
}

static struct ref_scale_ops srcu_ops = {
	.init		= rcu_sync_scale_init,
	.readsection	= srcu_ref_scale_read_section,
	.delaysection	= srcu_ref_scale_delay_section,
	.name		= "srcu"
};

// Definitions for RCU Tasks ref scale testing: Empty read markers.
// These definitions also work for RCU Rude readers.
static void rcu_tasks_ref_scale_read_section(const int nloops)
{
	int i;

	for (i = nloops; i >= 0; i--)
		continue;
}

static void rcu_tasks_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;

	for (i = nloops; i >= 0; i--)
		un_delay(udl, ndl);
}

static struct ref_scale_ops rcu_tasks_ops = {
	.init		= rcu_sync_scale_init,
	.readsection	= rcu_tasks_ref_scale_read_section,
	.delaysection	= rcu_tasks_ref_scale_delay_section,
	.name		= "rcu-tasks"
};

// Definitions for RCU Tasks Trace ref scale testing.
static void rcu_trace_ref_scale_read_section(const int nloops)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		rcu_read_lock_trace();
		rcu_read_unlock_trace();
	}
}

static void rcu_trace_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		rcu_read_lock_trace();
		un_delay(udl, ndl);
		rcu_read_unlock_trace();
	}
}

static struct ref_scale_ops rcu_trace_ops = {
	.init		= rcu_sync_scale_init,
	.readsection	= rcu_trace_ref_scale_read_section,
	.delaysection	= rcu_trace_ref_scale_delay_section,
	.name		= "rcu-trace"
};

// Definitions for reference count
static atomic_t refcnt;

static void ref_refcnt_section(const int nloops)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		atomic_inc(&refcnt);
		atomic_dec(&refcnt);
	}
}

static void ref_refcnt_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		atomic_inc(&refcnt);
		un_delay(udl, ndl);
		atomic_dec(&refcnt);
	}
}

static struct ref_scale_ops refcnt_ops = {
	.init		= rcu_sync_scale_init,
	.readsection	= ref_refcnt_section,
	.delaysection	= ref_refcnt_delay_section,
	.name		= "refcnt"
};

// Definitions for rwlock
static rwlock_t test_rwlock;

static void ref_rwlock_init(void)
{
	rwlock_init(&test_rwlock);
}

static void ref_rwlock_section(const int nloops)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		read_lock(&test_rwlock);
		read_unlock(&test_rwlock);
	}
}

static void ref_rwlock_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		read_lock(&test_rwlock);
		un_delay(udl, ndl);
		read_unlock(&test_rwlock);
	}
}

static struct ref_scale_ops rwlock_ops = {
	.init		= ref_rwlock_init,
	.readsection	= ref_rwlock_section,
	.delaysection	= ref_rwlock_delay_section,
	.name		= "rwlock"
};

// Definitions for rwsem
static struct rw_semaphore test_rwsem;

static void ref_rwsem_init(void)
{
	init_rwsem(&test_rwsem);
}

static void ref_rwsem_section(const int nloops)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		down_read(&test_rwsem);
		up_read(&test_rwsem);
	}
}

static void ref_rwsem_delay_section(const int nloops, const int udl, const int ndl)
{
	int i;

	for (i = nloops; i >= 0; i--) {
		down_read(&test_rwsem);
		un_delay(udl, ndl);
		up_read(&test_rwsem);
	}
}

static struct ref_scale_ops rwsem_ops = {
	.init		= ref_rwsem_init,
	.readsection	= ref_rwsem_section,
	.delaysection	= ref_rwsem_delay_section,
	.name		= "rwsem"
};

static void rcu_scale_one_reader(void)
{
	if (readdelay <= 0)
		cur_ops->readsection(loops);
	else
		cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000);
}

// Reader kthread.  Repeatedly does empty RCU read-side
// critical section, minimizing update-side interference.
static int
ref_scale_reader(void *arg)
{
	unsigned long flags;
	long me = (long)arg;
	struct reader_task *rt = &(reader_tasks[me]);
	u64 start;
	s64 duration;

	VERBOSE_SCALEOUT("ref_scale_reader %ld: task started", me);
	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
	set_user_nice(current, MAX_NICE);
	atomic_inc(&n_init);
	if (holdoff)
		schedule_timeout_interruptible(holdoff * HZ);
repeat:
	VERBOSE_SCALEOUT("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());

	// Wait for signal that this reader can start.
	wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
			   torture_must_stop());

	if (torture_must_stop())
		goto end;

	// Make sure that the CPU is affinitized appropriately during testing.
	WARN_ON_ONCE(smp_processor_id() != me);

	WRITE_ONCE(rt->start_reader, 0);
	if (!atomic_dec_return(&n_started))
		while (atomic_read_acquire(&n_started))
			cpu_relax();

	VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d started", me, exp_idx);


	// To reduce noise, do an initial cache-warming invocation, check
	// in, and then keep warming until everyone has checked in.
	rcu_scale_one_reader();
	if (!atomic_dec_return(&n_warmedup))
		while (atomic_read_acquire(&n_warmedup))
			rcu_scale_one_reader();
	// Also keep interrupts disabled.  This also has the effect
	// of preventing entries into slow path for rcu_read_unlock().
	local_irq_save(flags);
	start = ktime_get_mono_fast_ns();

	rcu_scale_one_reader();

	duration = ktime_get_mono_fast_ns() - start;
	local_irq_restore(flags);

	rt->last_duration_ns = WARN_ON_ONCE(duration < 0) ? 0 : duration;
	// To reduce runtime-skew noise, do maintain-load invocations until
	// everyone is done.
	if (!atomic_dec_return(&n_cooleddown))
		while (atomic_read_acquire(&n_cooleddown))
			rcu_scale_one_reader();

	if (atomic_dec_and_test(&nreaders_exp))
		wake_up(&main_wq);

	VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d ended, (readers remaining=%d)",
			me, exp_idx, atomic_read(&nreaders_exp));

	if (!torture_must_stop())
		goto repeat;
end:
	torture_kthread_stopping("ref_scale_reader");
	return 0;
}

static void reset_readers(void)
{
	int i;
	struct reader_task *rt;

	for (i = 0; i < nreaders; i++) {
		rt = &(reader_tasks[i]);

		rt->last_duration_ns = 0;
	}
}

// Print the results of each reader and return the sum of all their durations.
static u64 process_durations(int n)
{
	int i;
	struct reader_task *rt;
	char buf1[64];
	char *buf;
	u64 sum = 0;

	buf = kmalloc(128 + nreaders * 32, GFP_KERNEL);
	if (!buf)
		return 0;
	buf[0] = 0;
	sprintf(buf, "Experiment #%d (Format: <THREAD-NUM>:<Total loop time in ns>)",
		exp_idx);

	for (i = 0; i < n && !torture_must_stop(); i++) {
		rt = &(reader_tasks[i]);
		sprintf(buf1, "%d: %llu\t", i, rt->last_duration_ns);

		if (i % 5 == 0)
			strcat(buf, "\n");
		strcat(buf, buf1);

		sum += rt->last_duration_ns;
	}
	strcat(buf, "\n");

	SCALEOUT("%s\n", buf);

	kfree(buf);
	return sum;
}

// The main_func is the main orchestrator, it performs a bunch of
// experiments.  For every experiment, it orders all the readers
// involved to start and waits for them to finish the experiment. It
// then reads their timestamps and starts the next experiment. Each
// experiment progresses from 1 concurrent reader to N of them at which
// point all the timestamps are printed.
static int main_func(void *arg)
{
	bool errexit = false;
	int exp, r;
	char buf1[64];
	char *buf;
	u64 *result_avg;

	set_cpus_allowed_ptr(current, cpumask_of(nreaders % nr_cpu_ids));
	set_user_nice(current, MAX_NICE);

	VERBOSE_SCALEOUT("main_func task started");
	result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL);
	buf = kzalloc(64 + nruns * 32, GFP_KERNEL);
	if (!result_avg || !buf) {
		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
		errexit = true;
	}
	if (holdoff)
		schedule_timeout_interruptible(holdoff * HZ);

	// Wait for all threads to start.
	atomic_inc(&n_init);
	while (atomic_read(&n_init) < nreaders + 1)
		schedule_timeout_uninterruptible(1);

	// Start exp readers up per experiment
	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
		if (errexit)
			break;
		if (torture_must_stop())
			goto end;

		reset_readers();
		atomic_set(&nreaders_exp, nreaders);
		atomic_set(&n_started, nreaders);
		atomic_set(&n_warmedup, nreaders);
		atomic_set(&n_cooleddown, nreaders);

		exp_idx = exp;

		for (r = 0; r < nreaders; r++) {
			smp_store_release(&reader_tasks[r].start_reader, 1);
			wake_up(&reader_tasks[r].wq);
		}

		VERBOSE_SCALEOUT("main_func: experiment started, waiting for %d readers",
				nreaders);

		wait_event(main_wq,
			   !atomic_read(&nreaders_exp) || torture_must_stop());

		VERBOSE_SCALEOUT("main_func: experiment ended");

		if (torture_must_stop())
			goto end;

		result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops);
	}

	// Print the average of all experiments
	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");

	if (!errexit) {
		buf[0] = 0;
		strcat(buf, "\n");
		strcat(buf, "Runs\tTime(ns)\n");
	}

	for (exp = 0; exp < nruns; exp++) {
		u64 avg;
		u32 rem;

		if (errexit)
			break;
		avg = div_u64_rem(result_avg[exp], 1000, &rem);
		sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem);
		strcat(buf, buf1);
	}

	if (!errexit)
		SCALEOUT("%s", buf);

	// This will shutdown everything including us.
	if (shutdown) {
		shutdown_start = 1;
		wake_up(&shutdown_wq);
	}

	// Wait for torture to stop us
	while (!torture_must_stop())
		schedule_timeout_uninterruptible(1);

end:
	torture_kthread_stopping("main_func");
	kfree(result_avg);
	kfree(buf);
	return 0;
}

static void
ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag)
{
	pr_alert("%s" SCALE_FLAG
		 "--- %s:  verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
		 verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay);
}

static void
ref_scale_cleanup(void)
{
	int i;

	if (torture_cleanup_begin())
		return;

	if (!cur_ops) {
		torture_cleanup_end();
		return;
	}

	if (reader_tasks) {
		for (i = 0; i < nreaders; i++)
			torture_stop_kthread("ref_scale_reader",
					     reader_tasks[i].task);
	}
	kfree(reader_tasks);

	torture_stop_kthread("main_task", main_task);
	kfree(main_task);

	// Do scale-type-specific cleanup operations.
	if (cur_ops->cleanup != NULL)
		cur_ops->cleanup();

	torture_cleanup_end();
}

// Shutdown kthread.  Just waits to be awakened, then shuts down system.
static int
ref_scale_shutdown(void *arg)
{
	wait_event_idle(shutdown_wq, shutdown_start);

	smp_mb(); // Wake before output.
	ref_scale_cleanup();
	kernel_power_off();

	return -EINVAL;
}

static int __init
ref_scale_init(void)
{
	long i;
	int firsterr = 0;
	static struct ref_scale_ops *scale_ops[] = {
		&rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops,
		&refcnt_ops, &rwlock_ops, &rwsem_ops,
	};

	if (!torture_init_begin(scale_type, verbose))
		return -EBUSY;

	for (i = 0; i < ARRAY_SIZE(scale_ops); i++) {
		cur_ops = scale_ops[i];
		if (strcmp(scale_type, cur_ops->name) == 0)
			break;
	}
	if (i == ARRAY_SIZE(scale_ops)) {
		pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type);
		pr_alert("rcu-scale types:");
		for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
			pr_cont(" %s", scale_ops[i]->name);
		pr_cont("\n");
		WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST));
		firsterr = -EINVAL;
		cur_ops = NULL;
		goto unwind;
	}
	if (cur_ops->init)
		cur_ops->init();

	ref_scale_print_module_parms(cur_ops, "Start of test");

	// Shutdown task
	if (shutdown) {
		init_waitqueue_head(&shutdown_wq);
		firsterr = torture_create_kthread(ref_scale_shutdown, NULL,
						  shutdown_task);
		if (firsterr)
			goto unwind;
		schedule_timeout_uninterruptible(1);
	}

	// Reader tasks (default to ~75% of online CPUs).
	if (nreaders < 0)
		nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2);
	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
			       GFP_KERNEL);
	if (!reader_tasks) {
		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
		firsterr = -ENOMEM;
		goto unwind;
	}

	VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders);

	for (i = 0; i < nreaders; i++) {
		init_waitqueue_head(&reader_tasks[i].wq);
		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
						  reader_tasks[i].task);
		if (firsterr)
			goto unwind;
	}

	// Main Task
	init_waitqueue_head(&main_wq);
	firsterr = torture_create_kthread(main_func, NULL, main_task);
	if (firsterr)
		goto unwind;

	torture_init_end();
	return 0;

unwind:
	torture_init_end();
	ref_scale_cleanup();
	return firsterr;
}

module_init(ref_scale_init);
module_exit(ref_scale_cleanup);