summaryrefslogtreecommitdiff
path: root/samples/bpf/xdp_monitor_user.c
blob: 894bc64c2cac651851c0603e8f51af45a3692a45 (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
/* SPDX-License-Identifier: GPL-2.0
 * Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
 */
static const char *__doc__=
 "XDP monitor tool, based on tracepoints\n"
;

static const char *__doc_err_only__=
 " NOTICE: Only tracking XDP redirect errors\n"
 "         Enable TX success stats via '--stats'\n"
 "         (which comes with a per packet processing overhead)\n"
;

#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdbool.h>
#include <stdint.h>
#include <string.h>
#include <ctype.h>
#include <unistd.h>
#include <locale.h>

#include <sys/resource.h>
#include <getopt.h>
#include <net/if.h>
#include <time.h>

#include "libbpf.h"
#include "bpf_load.h"
#include "bpf_util.h"

static int verbose = 1;
static bool debug = false;

static const struct option long_options[] = {
	{"help",	no_argument,		NULL, 'h' },
	{"debug",	no_argument,		NULL, 'D' },
	{"stats",	no_argument,		NULL, 'S' },
	{"sec", 	required_argument,	NULL, 's' },
	{0, 0, NULL,  0 }
};

/* C standard specifies two constants, EXIT_SUCCESS(0) and EXIT_FAILURE(1) */
#define EXIT_FAIL_MEM	5

static void usage(char *argv[])
{
	int i;
	printf("\nDOCUMENTATION:\n%s\n", __doc__);
	printf("\n");
	printf(" Usage: %s (options-see-below)\n",
	       argv[0]);
	printf(" Listing options:\n");
	for (i = 0; long_options[i].name != 0; i++) {
		printf(" --%-15s", long_options[i].name);
		if (long_options[i].flag != NULL)
			printf(" flag (internal value:%d)",
			       *long_options[i].flag);
		else
			printf("(internal short-option: -%c)",
			       long_options[i].val);
		printf("\n");
	}
	printf("\n");
}

#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
static __u64 gettime(void)
{
	struct timespec t;
	int res;

	res = clock_gettime(CLOCK_MONOTONIC, &t);
	if (res < 0) {
		fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
		exit(EXIT_FAILURE);
	}
	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
}

enum {
	REDIR_SUCCESS = 0,
	REDIR_ERROR = 1,
};
#define REDIR_RES_MAX 2
static const char *redir_names[REDIR_RES_MAX] = {
	[REDIR_SUCCESS]	= "Success",
	[REDIR_ERROR]	= "Error",
};
static const char *err2str(int err)
{
	if (err < REDIR_RES_MAX)
		return redir_names[err];
	return NULL;
}
/* enum xdp_action */
#define XDP_UNKNOWN	XDP_REDIRECT + 1
#define XDP_ACTION_MAX (XDP_UNKNOWN + 1)
static const char *xdp_action_names[XDP_ACTION_MAX] = {
	[XDP_ABORTED]	= "XDP_ABORTED",
	[XDP_DROP]	= "XDP_DROP",
	[XDP_PASS]	= "XDP_PASS",
	[XDP_TX]	= "XDP_TX",
	[XDP_REDIRECT]	= "XDP_REDIRECT",
	[XDP_UNKNOWN]	= "XDP_UNKNOWN",
};
static const char *action2str(int action)
{
	if (action < XDP_ACTION_MAX)
		return xdp_action_names[action];
	return NULL;
}

/* Common stats data record shared with _kern.c */
struct datarec {
	__u64 processed;
	__u64 dropped;
	__u64 info;
};
#define MAX_CPUS 64

/* Userspace structs for collection of stats from maps */
struct record {
	__u64 timestamp;
	struct datarec total;
	struct datarec *cpu;
};
struct u64rec {
	__u64 processed;
};
struct record_u64 {
	/* record for _kern side __u64 values */
	__u64 timestamp;
	struct u64rec total;
	struct u64rec *cpu;
};

struct stats_record {
	struct record_u64 xdp_redirect[REDIR_RES_MAX];
	struct record_u64 xdp_exception[XDP_ACTION_MAX];
	struct record xdp_cpumap_kthread;
	struct record xdp_cpumap_enqueue[MAX_CPUS];
};

static bool map_collect_record(int fd, __u32 key, struct record *rec)
{
	/* For percpu maps, userspace gets a value per possible CPU */
	unsigned int nr_cpus = bpf_num_possible_cpus();
	struct datarec values[nr_cpus];
	__u64 sum_processed = 0;
	__u64 sum_dropped = 0;
	__u64 sum_info = 0;
	int i;

	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
		fprintf(stderr,
			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
		return false;
	}
	/* Get time as close as possible to reading map contents */
	rec->timestamp = gettime();

	/* Record and sum values from each CPU */
	for (i = 0; i < nr_cpus; i++) {
		rec->cpu[i].processed = values[i].processed;
		sum_processed        += values[i].processed;
		rec->cpu[i].dropped = values[i].dropped;
		sum_dropped        += values[i].dropped;
		rec->cpu[i].info = values[i].info;
		sum_info        += values[i].info;
	}
	rec->total.processed = sum_processed;
	rec->total.dropped   = sum_dropped;
	rec->total.info      = sum_info;
	return true;
}

static bool map_collect_record_u64(int fd, __u32 key, struct record_u64 *rec)
{
	/* For percpu maps, userspace gets a value per possible CPU */
	unsigned int nr_cpus = bpf_num_possible_cpus();
	struct u64rec values[nr_cpus];
	__u64 sum_total = 0;
	int i;

	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
		fprintf(stderr,
			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
		return false;
	}
	/* Get time as close as possible to reading map contents */
	rec->timestamp = gettime();

	/* Record and sum values from each CPU */
	for (i = 0; i < nr_cpus; i++) {
		rec->cpu[i].processed = values[i].processed;
		sum_total            += values[i].processed;
	}
	rec->total.processed = sum_total;
	return true;
}

static double calc_period(struct record *r, struct record *p)
{
	double period_ = 0;
	__u64 period = 0;

	period = r->timestamp - p->timestamp;
	if (period > 0)
		period_ = ((double) period / NANOSEC_PER_SEC);

	return period_;
}

static double calc_period_u64(struct record_u64 *r, struct record_u64 *p)
{
	double period_ = 0;
	__u64 period = 0;

	period = r->timestamp - p->timestamp;
	if (period > 0)
		period_ = ((double) period / NANOSEC_PER_SEC);

	return period_;
}

static double calc_pps(struct datarec *r, struct datarec *p, double period)
{
	__u64 packets = 0;
	double pps = 0;

	if (period > 0) {
		packets = r->processed - p->processed;
		pps = packets / period;
	}
	return pps;
}

static double calc_pps_u64(struct u64rec *r, struct u64rec *p, double period)
{
	__u64 packets = 0;
	double pps = 0;

	if (period > 0) {
		packets = r->processed - p->processed;
		pps = packets / period;
	}
	return pps;
}

static double calc_drop(struct datarec *r, struct datarec *p, double period)
{
	__u64 packets = 0;
	double pps = 0;

	if (period > 0) {
		packets = r->dropped - p->dropped;
		pps = packets / period;
	}
	return pps;
}

static double calc_info(struct datarec *r, struct datarec *p, double period)
{
	__u64 packets = 0;
	double pps = 0;

	if (period > 0) {
		packets = r->info - p->info;
		pps = packets / period;
	}
	return pps;
}

static void stats_print(struct stats_record *stats_rec,
			struct stats_record *stats_prev,
			bool err_only)
{
	unsigned int nr_cpus = bpf_num_possible_cpus();
	int rec_i = 0, i, to_cpu;
	double t = 0, pps = 0;

	/* Header */
	printf("%-15s %-7s %-12s %-12s %-9s\n",
	       "XDP-event", "CPU:to", "pps", "drop-pps", "extra-info");

	/* tracepoint: xdp:xdp_redirect_* */
	if (err_only)
		rec_i = REDIR_ERROR;

	for (; rec_i < REDIR_RES_MAX; rec_i++) {
		struct record_u64 *rec, *prev;
		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %s\n";
		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %s\n";

		rec  =  &stats_rec->xdp_redirect[rec_i];
		prev = &stats_prev->xdp_redirect[rec_i];
		t = calc_period_u64(rec, prev);

		for (i = 0; i < nr_cpus; i++) {
			struct u64rec *r = &rec->cpu[i];
			struct u64rec *p = &prev->cpu[i];

			pps = calc_pps_u64(r, p, t);
			if (pps > 0)
				printf(fmt1, "XDP_REDIRECT", i,
				       rec_i ? 0.0: pps, rec_i ? pps : 0.0,
				       err2str(rec_i));
		}
		pps = calc_pps_u64(&rec->total, &prev->total, t);
		printf(fmt2, "XDP_REDIRECT", "total",
		       rec_i ? 0.0: pps, rec_i ? pps : 0.0, err2str(rec_i));
	}

	/* tracepoint: xdp:xdp_exception */
	for (rec_i = 0; rec_i < XDP_ACTION_MAX; rec_i++) {
		struct record_u64 *rec, *prev;
		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %s\n";
		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %s\n";

		rec  =  &stats_rec->xdp_exception[rec_i];
		prev = &stats_prev->xdp_exception[rec_i];
		t = calc_period_u64(rec, prev);

		for (i = 0; i < nr_cpus; i++) {
			struct u64rec *r = &rec->cpu[i];
			struct u64rec *p = &prev->cpu[i];

			pps = calc_pps_u64(r, p, t);
			if (pps > 0)
				printf(fmt1, "Exception", i,
				       0.0, pps, action2str(rec_i));
		}
		pps = calc_pps_u64(&rec->total, &prev->total, t);
		if (pps > 0)
			printf(fmt2, "Exception", "total",
			       0.0, pps, action2str(rec_i));
	}

	/* cpumap enqueue stats */
	for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) {
		char *fmt1 = "%-15s %3d:%-3d %'-12.0f %'-12.0f %'-10.2f %s\n";
		char *fmt2 = "%-15s %3s:%-3d %'-12.0f %'-12.0f %'-10.2f %s\n";
		struct record *rec, *prev;
		char *info_str = "";
		double drop, info;

		rec  =  &stats_rec->xdp_cpumap_enqueue[to_cpu];
		prev = &stats_prev->xdp_cpumap_enqueue[to_cpu];
		t = calc_period(rec, prev);
		for (i = 0; i < nr_cpus; i++) {
			struct datarec *r = &rec->cpu[i];
			struct datarec *p = &prev->cpu[i];

			pps  = calc_pps(r, p, t);
			drop = calc_drop(r, p, t);
			info = calc_info(r, p, t);
			if (info > 0) {
				info_str = "bulk-average";
				info = pps / info; /* calc average bulk size */
			}
			if (pps > 0)
				printf(fmt1, "cpumap-enqueue",
				       i, to_cpu, pps, drop, info, info_str);
		}
		pps = calc_pps(&rec->total, &prev->total, t);
		if (pps > 0) {
			drop = calc_drop(&rec->total, &prev->total, t);
			info = calc_info(&rec->total, &prev->total, t);
			if (info > 0) {
				info_str = "bulk-average";
				info = pps / info; /* calc average bulk size */
			}
			printf(fmt2, "cpumap-enqueue",
			       "sum", to_cpu, pps, drop, info, info_str);
		}
	}

	/* cpumap kthread stats */
	{
		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.0f %s\n";
		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.0f %s\n";
		struct record *rec, *prev;
		double drop, info;
		char *i_str = "";

		rec  =  &stats_rec->xdp_cpumap_kthread;
		prev = &stats_prev->xdp_cpumap_kthread;
		t = calc_period(rec, prev);
		for (i = 0; i < nr_cpus; i++) {
			struct datarec *r = &rec->cpu[i];
			struct datarec *p = &prev->cpu[i];

			pps  = calc_pps(r, p, t);
			drop = calc_drop(r, p, t);
			info = calc_info(r, p, t);
			if (info > 0)
				i_str = "sched";
			if (pps > 0)
				printf(fmt1, "cpumap-kthread",
				       i, pps, drop, info, i_str);
		}
		pps = calc_pps(&rec->total, &prev->total, t);
		drop = calc_drop(&rec->total, &prev->total, t);
		info = calc_info(&rec->total, &prev->total, t);
		if (info > 0)
			i_str = "sched-sum";
		printf(fmt2, "cpumap-kthread", "total", pps, drop, info, i_str);
	}

	printf("\n");
}

static bool stats_collect(struct stats_record *rec)
{
	int fd;
	int i;

	/* TODO: Detect if someone unloaded the perf event_fd's, as
	 * this can happen by someone running perf-record -e
	 */

	fd = map_data[0].fd; /* map0: redirect_err_cnt */
	for (i = 0; i < REDIR_RES_MAX; i++)
		map_collect_record_u64(fd, i, &rec->xdp_redirect[i]);

	fd = map_data[1].fd; /* map1: exception_cnt */
	for (i = 0; i < XDP_ACTION_MAX; i++) {
		map_collect_record_u64(fd, i, &rec->xdp_exception[i]);
	}

	fd = map_data[2].fd; /* map2: cpumap_enqueue_cnt */
	for (i = 0; i < MAX_CPUS; i++)
		map_collect_record(fd, i, &rec->xdp_cpumap_enqueue[i]);

	fd = map_data[3].fd; /* map3: cpumap_kthread_cnt */
	map_collect_record(fd, 0, &rec->xdp_cpumap_kthread);

	return true;
}

static void *alloc_rec_per_cpu(int record_size)
{
	unsigned int nr_cpus = bpf_num_possible_cpus();
	void *array;
	size_t size;

	size = record_size * nr_cpus;
	array = malloc(size);
	memset(array, 0, size);
	if (!array) {
		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
		exit(EXIT_FAIL_MEM);
	}
	return array;
}

static struct stats_record *alloc_stats_record(void)
{
	struct stats_record *rec;
	int rec_sz;
	int i;

	/* Alloc main stats_record structure */
	rec = malloc(sizeof(*rec));
	memset(rec, 0, sizeof(*rec));
	if (!rec) {
		fprintf(stderr, "Mem alloc error\n");
		exit(EXIT_FAIL_MEM);
	}

	/* Alloc stats stored per CPU for each record */
	rec_sz = sizeof(struct u64rec);
	for (i = 0; i < REDIR_RES_MAX; i++)
		rec->xdp_redirect[i].cpu = alloc_rec_per_cpu(rec_sz);

	for (i = 0; i < XDP_ACTION_MAX; i++)
		rec->xdp_exception[i].cpu = alloc_rec_per_cpu(rec_sz);

	rec_sz = sizeof(struct datarec);
	rec->xdp_cpumap_kthread.cpu = alloc_rec_per_cpu(rec_sz);

	for (i = 0; i < MAX_CPUS; i++)
		rec->xdp_cpumap_enqueue[i].cpu = alloc_rec_per_cpu(rec_sz);

	return rec;
}

static void free_stats_record(struct stats_record *r)
{
	int i;

	for (i = 0; i < REDIR_RES_MAX; i++)
		free(r->xdp_redirect[i].cpu);

	for (i = 0; i < XDP_ACTION_MAX; i++)
		free(r->xdp_exception[i].cpu);

	free(r->xdp_cpumap_kthread.cpu);

	for (i = 0; i < MAX_CPUS; i++)
		free(r->xdp_cpumap_enqueue[i].cpu);

	free(r);
}

/* Pointer swap trick */
static inline void swap(struct stats_record **a, struct stats_record **b)
{
	struct stats_record *tmp;

	tmp = *a;
	*a = *b;
	*b = tmp;
}

static void stats_poll(int interval, bool err_only)
{
	struct stats_record *rec, *prev;

	rec  = alloc_stats_record();
	prev = alloc_stats_record();
	stats_collect(rec);

	if (err_only)
		printf("\n%s\n", __doc_err_only__);

	/* Trick to pretty printf with thousands separators use %' */
	setlocale(LC_NUMERIC, "en_US");

	/* Header */
	if (verbose)
		printf("\n%s", __doc__);

	/* TODO Need more advanced stats on error types */
	if (verbose) {
		printf(" - Stats map0: %s\n", map_data[0].name);
		printf(" - Stats map1: %s\n", map_data[1].name);
		printf("\n");
	}
	fflush(stdout);

	while (1) {
		swap(&prev, &rec);
		stats_collect(rec);
		stats_print(rec, prev, err_only);
		fflush(stdout);
		sleep(interval);
	}

	free_stats_record(rec);
	free_stats_record(prev);
}

static void print_bpf_prog_info(void)
{
	int i;

	/* Prog info */
	printf("Loaded BPF prog have %d bpf program(s)\n", prog_cnt);
	for (i = 0; i < prog_cnt; i++) {
		printf(" - prog_fd[%d] = fd(%d)\n", i, prog_fd[i]);
	}

	/* Maps info */
	printf("Loaded BPF prog have %d map(s)\n", map_data_count);
	for (i = 0; i < map_data_count; i++) {
		char *name = map_data[i].name;
		int fd     = map_data[i].fd;

		printf(" - map_data[%d] = fd(%d) name:%s\n", i, fd, name);
	}

	/* Event info */
	printf("Searching for (max:%d) event file descriptor(s)\n", prog_cnt);
	for (i = 0; i < prog_cnt; i++) {
		if (event_fd[i] != -1)
			printf(" - event_fd[%d] = fd(%d)\n", i, event_fd[i]);
	}
}

int main(int argc, char **argv)
{
	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
	int longindex = 0, opt;
	int ret = EXIT_SUCCESS;
	char bpf_obj_file[256];

	/* Default settings: */
	bool errors_only = true;
	int interval = 2;

	snprintf(bpf_obj_file, sizeof(bpf_obj_file), "%s_kern.o", argv[0]);

	/* Parse commands line args */
	while ((opt = getopt_long(argc, argv, "h",
				  long_options, &longindex)) != -1) {
		switch (opt) {
		case 'D':
			debug = true;
			break;
		case 'S':
			errors_only = false;
			break;
		case 's':
			interval = atoi(optarg);
			break;
		case 'h':
		default:
			usage(argv);
			return EXIT_FAILURE;
		}
	}

	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
		perror("setrlimit(RLIMIT_MEMLOCK)");
		return EXIT_FAILURE;
	}

	if (load_bpf_file(bpf_obj_file)) {
		printf("ERROR - bpf_log_buf: %s", bpf_log_buf);
		return EXIT_FAILURE;
	}
	if (!prog_fd[0]) {
		printf("ERROR - load_bpf_file: %s\n", strerror(errno));
		return EXIT_FAILURE;
	}

	if (debug) {
		print_bpf_prog_info();
	}

	/* Unload/stop tracepoint event by closing fd's */
	if (errors_only) {
		/* The prog_fd[i] and event_fd[i] depend on the
		 * order the functions was defined in _kern.c
		 */
		close(event_fd[2]); /* tracepoint/xdp/xdp_redirect */
		close(prog_fd[2]);  /* func: trace_xdp_redirect */
		close(event_fd[3]); /* tracepoint/xdp/xdp_redirect_map */
		close(prog_fd[3]);  /* func: trace_xdp_redirect_map */
	}

	stats_poll(interval, errors_only);

	return ret;
}