kernel_optimize_test/tools/testing/selftests/bpf/trace_helpers.c
Daniel Borkmann 3dca21156b bpf, libbpf: simplify and cleanup perf ring buffer walk
Simplify bpf_perf_event_read_simple() a bit and fix up some minor
things along the way: the return code in the header is not of type
int but enum bpf_perf_event_ret instead. Once callback indicated
to break the loop walking event data, it also needs to be consumed
in data_tail since it has been processed already.

Moreover, bpf_perf_event_print_t callback should avoid void * as
we actually get a pointer to struct perf_event_header and thus
applications can make use of container_of() to have type checks.
The walk also doesn't have to use modulo op since the ring size is
required to be power of two.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-20 23:13:32 -07:00

212 lines
4.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#include <errno.h>
#include <poll.h>
#include <unistd.h>
#include <linux/perf_event.h>
#include <sys/mman.h>
#include "trace_helpers.h"
#define MAX_SYMS 300000
static struct ksym syms[MAX_SYMS];
static int sym_cnt;
static int ksym_cmp(const void *p1, const void *p2)
{
return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
}
int load_kallsyms(void)
{
FILE *f = fopen("/proc/kallsyms", "r");
char func[256], buf[256];
char symbol;
void *addr;
int i = 0;
if (!f)
return -ENOENT;
while (!feof(f)) {
if (!fgets(buf, sizeof(buf), f))
break;
if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
break;
if (!addr)
continue;
syms[i].addr = (long) addr;
syms[i].name = strdup(func);
i++;
}
fclose(f);
sym_cnt = i;
qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
return 0;
}
struct ksym *ksym_search(long key)
{
int start = 0, end = sym_cnt;
int result;
while (start < end) {
size_t mid = start + (end - start) / 2;
result = key - syms[mid].addr;
if (result < 0)
end = mid;
else if (result > 0)
start = mid + 1;
else
return &syms[mid];
}
if (start >= 1 && syms[start - 1].addr < key &&
key < syms[start].addr)
/* valid ksym */
return &syms[start - 1];
/* out of range. return _stext */
return &syms[0];
}
long ksym_get_addr(const char *name)
{
int i;
for (i = 0; i < sym_cnt; i++) {
if (strcmp(syms[i].name, name) == 0)
return syms[i].addr;
}
return 0;
}
static int page_size;
static int page_cnt = 8;
static struct perf_event_mmap_page *header;
int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header)
{
void *base;
int mmap_size;
page_size = getpagesize();
mmap_size = page_size * (page_cnt + 1);
base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
if (base == MAP_FAILED) {
printf("mmap err\n");
return -1;
}
*header = base;
return 0;
}
int perf_event_mmap(int fd)
{
return perf_event_mmap_header(fd, &header);
}
static int perf_event_poll(int fd)
{
struct pollfd pfd = { .fd = fd, .events = POLLIN };
return poll(&pfd, 1, 1000);
}
struct perf_event_sample {
struct perf_event_header header;
__u32 size;
char data[];
};
static enum bpf_perf_event_ret
bpf_perf_event_print(struct perf_event_header *hdr, void *private_data)
{
struct perf_event_sample *e = (struct perf_event_sample *)hdr;
perf_event_print_fn fn = private_data;
int ret;
if (e->header.type == PERF_RECORD_SAMPLE) {
ret = fn(e->data, e->size);
if (ret != LIBBPF_PERF_EVENT_CONT)
return ret;
} else if (e->header.type == PERF_RECORD_LOST) {
struct {
struct perf_event_header header;
__u64 id;
__u64 lost;
} *lost = (void *) e;
printf("lost %lld events\n", lost->lost);
} else {
printf("unknown event type=%d size=%d\n",
e->header.type, e->header.size);
}
return LIBBPF_PERF_EVENT_CONT;
}
int perf_event_poller(int fd, perf_event_print_fn output_fn)
{
enum bpf_perf_event_ret ret;
void *buf = NULL;
size_t len = 0;
for (;;) {
perf_event_poll(fd);
ret = bpf_perf_event_read_simple(header, page_cnt * page_size,
page_size, &buf, &len,
bpf_perf_event_print,
output_fn);
if (ret != LIBBPF_PERF_EVENT_CONT)
break;
}
free(buf);
return ret;
}
int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
int num_fds, perf_event_print_fn output_fn)
{
enum bpf_perf_event_ret ret;
struct pollfd *pfds;
void *buf = NULL;
size_t len = 0;
int i;
pfds = calloc(num_fds, sizeof(*pfds));
if (!pfds)
return LIBBPF_PERF_EVENT_ERROR;
for (i = 0; i < num_fds; i++) {
pfds[i].fd = fds[i];
pfds[i].events = POLLIN;
}
for (;;) {
poll(pfds, num_fds, 1000);
for (i = 0; i < num_fds; i++) {
if (!pfds[i].revents)
continue;
ret = bpf_perf_event_read_simple(headers[i],
page_cnt * page_size,
page_size, &buf, &len,
bpf_perf_event_print,
output_fn);
if (ret != LIBBPF_PERF_EVENT_CONT)
break;
}
}
free(buf);
free(pfds);
return ret;
}