summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/kvm/dirty_log_perf_test.c
blob: e9d6d1aecf89cb346070184115c982325d307960 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * KVM dirty page logging performance test
 *
 * Based on dirty_log_test.c
 *
 * Copyright (C) 2018, Red Hat, Inc.
 * Copyright (C) 2020, Google, Inc.
 */

#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <pthread.h>
#include <linux/bitmap.h>

#include "kvm_util.h"
#include "test_util.h"
#include "memstress.h"
#include "guest_modes.h"

#ifdef __aarch64__
#include "aarch64/vgic.h"

#define GICD_BASE_GPA			0x8000000ULL
#define GICR_BASE_GPA			0x80A0000ULL

static int gic_fd;

static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
{
	/*
	 * The test can still run even if hardware does not support GICv3, as it
	 * is only an optimization to reduce guest exits.
	 */
	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
}

static void arch_cleanup_vm(struct kvm_vm *vm)
{
	if (gic_fd > 0)
		close(gic_fd);
}

#else /* __aarch64__ */

static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
{
}

static void arch_cleanup_vm(struct kvm_vm *vm)
{
}

#endif

/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
#define TEST_HOST_LOOP_N		2UL

static int nr_vcpus = 1;
static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
static bool run_vcpus_while_disabling_dirty_logging;

/* Host variables */
static u64 dirty_log_manual_caps;
static bool host_quit;
static int iteration;
static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];

static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
{
	struct kvm_vcpu *vcpu = vcpu_args->vcpu;
	int vcpu_idx = vcpu_args->vcpu_idx;
	uint64_t pages_count = 0;
	struct kvm_run *run;
	struct timespec start;
	struct timespec ts_diff;
	struct timespec total = (struct timespec){0};
	struct timespec avg;
	int ret;

	run = vcpu->run;

	while (!READ_ONCE(host_quit)) {
		int current_iteration = READ_ONCE(iteration);

		clock_gettime(CLOCK_MONOTONIC, &start);
		ret = _vcpu_run(vcpu);
		ts_diff = timespec_elapsed(start);

		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
			    "Invalid guest sync status: exit_reason=%s\n",
			    exit_reason_str(run->exit_reason));

		pr_debug("Got sync event from vCPU %d\n", vcpu_idx);
		vcpu_last_completed_iteration[vcpu_idx] = current_iteration;
		pr_debug("vCPU %d updated last completed iteration to %d\n",
			 vcpu_idx, vcpu_last_completed_iteration[vcpu_idx]);

		if (current_iteration) {
			pages_count += vcpu_args->pages;
			total = timespec_add(total, ts_diff);
			pr_debug("vCPU %d iteration %d dirty memory time: %ld.%.9lds\n",
				vcpu_idx, current_iteration, ts_diff.tv_sec,
				ts_diff.tv_nsec);
		} else {
			pr_debug("vCPU %d iteration %d populate memory time: %ld.%.9lds\n",
				vcpu_idx, current_iteration, ts_diff.tv_sec,
				ts_diff.tv_nsec);
		}

		/*
		 * Keep running the guest while dirty logging is being disabled
		 * (iteration is negative) so that vCPUs are accessing memory
		 * for the entire duration of zapping collapsible SPTEs.
		 */
		while (current_iteration == READ_ONCE(iteration) &&
		       READ_ONCE(iteration) >= 0 && !READ_ONCE(host_quit)) {}
	}

	avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_idx]);
	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
		vcpu_idx, pages_count, vcpu_last_completed_iteration[vcpu_idx],
		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
}

struct test_params {
	unsigned long iterations;
	uint64_t phys_offset;
	bool partition_vcpu_memory_access;
	enum vm_mem_backing_src_type backing_src;
	int slots;
	uint32_t write_percent;
	uint32_t random_seed;
	bool random_access;
};

static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable)
{
	int i;

	for (i = 0; i < slots; i++) {
		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
		int flags = enable ? KVM_MEM_LOG_DIRTY_PAGES : 0;

		vm_mem_region_set_flags(vm, slot, flags);
	}
}

static inline void enable_dirty_logging(struct kvm_vm *vm, int slots)
{
	toggle_dirty_logging(vm, slots, true);
}

static inline void disable_dirty_logging(struct kvm_vm *vm, int slots)
{
	toggle_dirty_logging(vm, slots, false);
}

static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots)
{
	int i;

	for (i = 0; i < slots; i++) {
		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;

		kvm_vm_get_dirty_log(vm, slot, bitmaps[i]);
	}
}

static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
			    int slots, uint64_t pages_per_slot)
{
	int i;

	for (i = 0; i < slots; i++) {
		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;

		kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot);
	}
}

static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot)
{
	unsigned long **bitmaps;
	int i;

	bitmaps = malloc(slots * sizeof(bitmaps[0]));
	TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array.");

	for (i = 0; i < slots; i++) {
		bitmaps[i] = bitmap_zalloc(pages_per_slot);
		TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap.");
	}

	return bitmaps;
}

static void free_bitmaps(unsigned long *bitmaps[], int slots)
{
	int i;

	for (i = 0; i < slots; i++)
		free(bitmaps[i]);

	free(bitmaps);
}

static void run_test(enum vm_guest_mode mode, void *arg)
{
	struct test_params *p = arg;
	struct kvm_vm *vm;
	unsigned long **bitmaps;
	uint64_t guest_num_pages;
	uint64_t host_num_pages;
	uint64_t pages_per_slot;
	struct timespec start;
	struct timespec ts_diff;
	struct timespec get_dirty_log_total = (struct timespec){0};
	struct timespec vcpu_dirty_total = (struct timespec){0};
	struct timespec avg;
	struct timespec clear_dirty_log_total = (struct timespec){0};
	int i;

	vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
				 p->slots, p->backing_src,
				 p->partition_vcpu_memory_access);

	pr_info("Random seed: %u\n", p->random_seed);
	memstress_set_random_seed(vm, p->random_seed);
	memstress_set_write_percent(vm, p->write_percent);

	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm->page_shift;
	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
	pages_per_slot = host_num_pages / p->slots;

	bitmaps = alloc_bitmaps(p->slots, pages_per_slot);

	if (dirty_log_manual_caps)
		vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2,
			      dirty_log_manual_caps);

	arch_setup_vm(vm, nr_vcpus);

	/* Start the iterations */
	iteration = 0;
	host_quit = false;

	clock_gettime(CLOCK_MONOTONIC, &start);
	for (i = 0; i < nr_vcpus; i++)
		vcpu_last_completed_iteration[i] = -1;

	/*
	 * Use 100% writes during the population phase to ensure all
	 * memory is actually populated and not just mapped to the zero
	 * page. The prevents expensive copy-on-write faults from
	 * occurring during the dirty memory iterations below, which
	 * would pollute the performance results.
	 */
	memstress_set_write_percent(vm, 100);
	memstress_set_random_access(vm, false);
	memstress_start_vcpu_threads(nr_vcpus, vcpu_worker);

	/* Allow the vCPUs to populate memory */
	pr_debug("Starting iteration %d - Populating\n", iteration);
	for (i = 0; i < nr_vcpus; i++) {
		while (READ_ONCE(vcpu_last_completed_iteration[i]) !=
		       iteration)
			;
	}

	ts_diff = timespec_elapsed(start);
	pr_info("Populate memory time: %ld.%.9lds\n",
		ts_diff.tv_sec, ts_diff.tv_nsec);

	/* Enable dirty logging */
	clock_gettime(CLOCK_MONOTONIC, &start);
	enable_dirty_logging(vm, p->slots);
	ts_diff = timespec_elapsed(start);
	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
		ts_diff.tv_sec, ts_diff.tv_nsec);

	memstress_set_write_percent(vm, p->write_percent);
	memstress_set_random_access(vm, p->random_access);

	while (iteration < p->iterations) {
		/*
		 * Incrementing the iteration number will start the vCPUs
		 * dirtying memory again.
		 */
		clock_gettime(CLOCK_MONOTONIC, &start);
		iteration++;

		pr_debug("Starting iteration %d\n", iteration);
		for (i = 0; i < nr_vcpus; i++) {
			while (READ_ONCE(vcpu_last_completed_iteration[i])
			       != iteration)
				;
		}

		ts_diff = timespec_elapsed(start);
		vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff);
		pr_info("Iteration %d dirty memory time: %ld.%.9lds\n",
			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);

		clock_gettime(CLOCK_MONOTONIC, &start);
		get_dirty_log(vm, bitmaps, p->slots);
		ts_diff = timespec_elapsed(start);
		get_dirty_log_total = timespec_add(get_dirty_log_total,
						   ts_diff);
		pr_info("Iteration %d get dirty log time: %ld.%.9lds\n",
			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);

		if (dirty_log_manual_caps) {
			clock_gettime(CLOCK_MONOTONIC, &start);
			clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot);
			ts_diff = timespec_elapsed(start);
			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
							     ts_diff);
			pr_info("Iteration %d clear dirty log time: %ld.%.9lds\n",
				iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
		}
	}

	/*
	 * Run vCPUs while dirty logging is being disabled to stress disabling
	 * in terms of both performance and correctness.  Opt-in via command
	 * line as this significantly increases time to disable dirty logging.
	 */
	if (run_vcpus_while_disabling_dirty_logging)
		WRITE_ONCE(iteration, -1);

	/* Disable dirty logging */
	clock_gettime(CLOCK_MONOTONIC, &start);
	disable_dirty_logging(vm, p->slots);
	ts_diff = timespec_elapsed(start);
	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
		ts_diff.tv_sec, ts_diff.tv_nsec);

	/*
	 * Tell the vCPU threads to quit.  No need to manually check that vCPUs
	 * have stopped running after disabling dirty logging, the join will
	 * wait for them to exit.
	 */
	host_quit = true;
	memstress_join_vcpu_threads(nr_vcpus);

	avg = timespec_div(get_dirty_log_total, p->iterations);
	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
		p->iterations, get_dirty_log_total.tv_sec,
		get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);

	if (dirty_log_manual_caps) {
		avg = timespec_div(clear_dirty_log_total, p->iterations);
		pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
			p->iterations, clear_dirty_log_total.tv_sec,
			clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
	}

	free_bitmaps(bitmaps, p->slots);
	arch_cleanup_vm(vm);
	memstress_destroy_vm(vm);
}

static void help(char *name)
{
	puts("");
	printf("usage: %s [-h] [-a] [-i iterations] [-p offset] [-g] "
	       "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-r random seed ] [-s mem type]"
	       "[-x memslots] [-w percentage] [-c physical cpus to run test on]\n", name);
	puts("");
	printf(" -a: access memory randomly rather than in order.\n");
	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
	       TEST_HOST_LOOP_N);
	printf(" -g: Do not enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2. This\n"
	       "     makes KVM_GET_DIRTY_LOG clear the dirty log (i.e.\n"
	       "     KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is not enabled)\n"
	       "     and writes will be tracked as soon as dirty logging is\n"
	       "     enabled on the memslot (i.e. KVM_DIRTY_LOG_INITIALLY_SET\n"
	       "     is not enabled).\n");
	printf(" -p: specify guest physical test memory offset\n"
	       "     Warning: a low offset can conflict with the loaded test code.\n");
	guest_modes_help();
	printf(" -n: Run the vCPUs in nested mode (L2)\n");
	printf(" -e: Run vCPUs while dirty logging is being disabled.  This\n"
	       "     can significantly increase runtime, especially if there\n"
	       "     isn't a dedicated pCPU for the main thread.\n");
	printf(" -b: specify the size of the memory region which should be\n"
	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
	       "     (default: 1G)\n");
	printf(" -v: specify the number of vCPUs to run.\n");
	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
	       "     them into a separate region of memory for each vCPU.\n");
	printf(" -r: specify the starting random seed.\n");
	backing_src_help("-s");
	printf(" -x: Split the memory region into this number of memslots.\n"
	       "     (default: 1)\n");
	printf(" -w: specify the percentage of pages which should be written to\n"
	       "     as an integer from 0-100 inclusive. This is probabilistic,\n"
	       "     so -w X means each page has an X%% chance of writing\n"
	       "     and a (100-X)%% chance of reading.\n"
	       "     (default: 100 i.e. all pages are written to.)\n");
	printf(" -c: Pin tasks to physical CPUs.  Takes a list of comma separated\n"
	       "     values (target pCPU), one for each vCPU, plus an optional\n"
	       "     entry for the main application task (specified via entry\n"
	       "     <nr_vcpus + 1>).  If used, entries must be provided for all\n"
	       "     vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
	       "     E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
	       "     vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
	       "         ./dirty_log_perf_test -v 3 -c 22,23,24,50\n\n"
	       "     To leave the application task unpinned, drop the final entry:\n\n"
	       "         ./dirty_log_perf_test -v 3 -c 22,23,24\n\n"
	       "     (default: no pinning)\n");
	puts("");
	exit(0);
}

int main(int argc, char *argv[])
{
	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
	const char *pcpu_list = NULL;
	struct test_params p = {
		.iterations = TEST_HOST_LOOP_N,
		.partition_vcpu_memory_access = true,
		.backing_src = DEFAULT_VM_MEM_SRC,
		.slots = 1,
		.random_seed = 1,
		.write_percent = 100,
	};
	int opt;

	dirty_log_manual_caps =
		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
				  KVM_DIRTY_LOG_INITIALLY_SET);

	guest_modes_append_default();

	while ((opt = getopt(argc, argv, "ab:c:eghi:m:nop:r:s:v:x:w:")) != -1) {
		switch (opt) {
		case 'a':
			p.random_access = true;
			break;
		case 'b':
			guest_percpu_mem_size = parse_size(optarg);
			break;
		case 'c':
			pcpu_list = optarg;
			break;
		case 'e':
			/* 'e' is for evil. */
			run_vcpus_while_disabling_dirty_logging = true;
			break;
		case 'g':
			dirty_log_manual_caps = 0;
			break;
		case 'h':
			help(argv[0]);
			break;
		case 'i':
			p.iterations = atoi_positive("Number of iterations", optarg);
			break;
		case 'm':
			guest_modes_cmdline(optarg);
			break;
		case 'n':
			memstress_args.nested = true;
			break;
		case 'o':
			p.partition_vcpu_memory_access = false;
			break;
		case 'p':
			p.phys_offset = strtoull(optarg, NULL, 0);
			break;
		case 'r':
			p.random_seed = atoi_positive("Random seed", optarg);
			break;
		case 's':
			p.backing_src = parse_backing_src_type(optarg);
			break;
		case 'v':
			nr_vcpus = atoi_positive("Number of vCPUs", optarg);
			TEST_ASSERT(nr_vcpus <= max_vcpus,
				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
			break;
		case 'w':
			p.write_percent = atoi_non_negative("Write percentage", optarg);
			TEST_ASSERT(p.write_percent <= 100,
				    "Write percentage must be between 0 and 100");
			break;
		case 'x':
			p.slots = atoi_positive("Number of slots", optarg);
			break;
		default:
			help(argv[0]);
			break;
		}
	}

	if (pcpu_list) {
		kvm_parse_vcpu_pinning(pcpu_list, memstress_args.vcpu_to_pcpu,
				       nr_vcpus);
		memstress_args.pin_vcpus = true;
	}

	TEST_ASSERT(p.iterations >= 2, "The test should have at least two iterations");

	pr_info("Test iterations: %"PRIu64"\n",	p.iterations);

	for_each_guest_mode(run_test, &p);

	return 0;
}