linux-stable/tools/bpf/bpftool/perf.c

248 lines
5.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
tools/bpftool: add perf subcommand The new command "bpftool perf [show | list]" will traverse all processes under /proc, and if any fd is associated with a perf event, it will print out related perf event information. Documentation is also added. Below is an example to show the results using bcc commands. Running the following 4 bcc commands: kprobe: trace.py '__x64_sys_nanosleep' kretprobe: trace.py 'r::__x64_sys_nanosleep' tracepoint: trace.py 't:syscalls:sys_enter_nanosleep' uprobe: trace.py 'p:/home/yhs/a.out:main' The bpftool command line and result: $ bpftool perf pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 $ bpftool -j perf [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] $ bpftool prog 5: kprobe name probe___x64_sys tag e495a0c82f2c7a8d gpl loaded_at 2018-05-15T04:46:37-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 4 7: kprobe name probe___x64_sys tag f2fdee479a503abf gpl loaded_at 2018-05-15T04:48:32-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 7 8: tracepoint name tracepoint__sys tag 5390badef2395fcf gpl loaded_at 2018-05-15T04:48:48-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 8 9: kprobe name probe_main_1 tag 0a87bdc2e2953b6d gpl loaded_at 2018-05-15T04:49:52-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 9 $ ps ax | grep "python ./trace.py" 21711 pts/0 T 0:03 python ./trace.py __x64_sys_write 21765 pts/0 S+ 0:00 python ./trace.py r::__x64_sys_nanosleep 21767 pts/2 S+ 0:00 python ./trace.py t:syscalls:sys_enter_nanosleep 21800 pts/3 S+ 0:00 python ./trace.py p:/home/yhs/a.out:main 22374 pts/1 S+ 0:00 grep --color=auto python ./trace.py Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 18:21:58 +00:00
// Copyright (C) 2018 Facebook
// Author: Yonghong Song <yhs@fb.com>
#define _GNU_SOURCE
#include <ctype.h>
#include <errno.h>
#include <fcntl.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>
#include <ftw.h>
#include <bpf.h>
#include "main.h"
/* 0: undecided, 1: supported, 2: not supported */
static int perf_query_supported;
static bool has_perf_query_support(void)
{
__u64 probe_offset, probe_addr;
__u32 len, prog_id, fd_type;
char buf[256];
int fd;
if (perf_query_supported)
goto out;
fd = open("/", O_RDONLY);
tools/bpftool: add perf subcommand The new command "bpftool perf [show | list]" will traverse all processes under /proc, and if any fd is associated with a perf event, it will print out related perf event information. Documentation is also added. Below is an example to show the results using bcc commands. Running the following 4 bcc commands: kprobe: trace.py '__x64_sys_nanosleep' kretprobe: trace.py 'r::__x64_sys_nanosleep' tracepoint: trace.py 't:syscalls:sys_enter_nanosleep' uprobe: trace.py 'p:/home/yhs/a.out:main' The bpftool command line and result: $ bpftool perf pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 $ bpftool -j perf [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] $ bpftool prog 5: kprobe name probe___x64_sys tag e495a0c82f2c7a8d gpl loaded_at 2018-05-15T04:46:37-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 4 7: kprobe name probe___x64_sys tag f2fdee479a503abf gpl loaded_at 2018-05-15T04:48:32-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 7 8: tracepoint name tracepoint__sys tag 5390badef2395fcf gpl loaded_at 2018-05-15T04:48:48-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 8 9: kprobe name probe_main_1 tag 0a87bdc2e2953b6d gpl loaded_at 2018-05-15T04:49:52-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 9 $ ps ax | grep "python ./trace.py" 21711 pts/0 T 0:03 python ./trace.py __x64_sys_write 21765 pts/0 S+ 0:00 python ./trace.py r::__x64_sys_nanosleep 21767 pts/2 S+ 0:00 python ./trace.py t:syscalls:sys_enter_nanosleep 21800 pts/3 S+ 0:00 python ./trace.py p:/home/yhs/a.out:main 22374 pts/1 S+ 0:00 grep --color=auto python ./trace.py Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 18:21:58 +00:00
if (fd < 0) {
p_err("perf_query_support: cannot open directory \"/\" (%s)",
strerror(errno));
tools/bpftool: add perf subcommand The new command "bpftool perf [show | list]" will traverse all processes under /proc, and if any fd is associated with a perf event, it will print out related perf event information. Documentation is also added. Below is an example to show the results using bcc commands. Running the following 4 bcc commands: kprobe: trace.py '__x64_sys_nanosleep' kretprobe: trace.py 'r::__x64_sys_nanosleep' tracepoint: trace.py 't:syscalls:sys_enter_nanosleep' uprobe: trace.py 'p:/home/yhs/a.out:main' The bpftool command line and result: $ bpftool perf pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 $ bpftool -j perf [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] $ bpftool prog 5: kprobe name probe___x64_sys tag e495a0c82f2c7a8d gpl loaded_at 2018-05-15T04:46:37-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 4 7: kprobe name probe___x64_sys tag f2fdee479a503abf gpl loaded_at 2018-05-15T04:48:32-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 7 8: tracepoint name tracepoint__sys tag 5390badef2395fcf gpl loaded_at 2018-05-15T04:48:48-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 8 9: kprobe name probe_main_1 tag 0a87bdc2e2953b6d gpl loaded_at 2018-05-15T04:49:52-0700 uid 0 xlated 200B not jited memlock 4096B map_ids 9 $ ps ax | grep "python ./trace.py" 21711 pts/0 T 0:03 python ./trace.py __x64_sys_write 21765 pts/0 S+ 0:00 python ./trace.py r::__x64_sys_nanosleep 21767 pts/2 S+ 0:00 python ./trace.py t:syscalls:sys_enter_nanosleep 21800 pts/3 S+ 0:00 python ./trace.py p:/home/yhs/a.out:main 22374 pts/1 S+ 0:00 grep --color=auto python ./trace.py Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 18:21:58 +00:00
goto out;
}
/* the following query will fail as no bpf attachment,
* the expected errno is ENOTSUPP
*/
errno = 0;
len = sizeof(buf);
bpf_task_fd_query(getpid(), fd, 0, buf, &len, &prog_id,
&fd_type, &probe_offset, &probe_addr);
if (errno == 524 /* ENOTSUPP */) {
perf_query_supported = 1;
goto close_fd;
}
perf_query_supported = 2;
p_err("perf_query_support: %s", strerror(errno));
fprintf(stderr,
"HINT: non root or kernel doesn't support TASK_FD_QUERY\n");
close_fd:
close(fd);
out:
return perf_query_supported == 1;
}
static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type,
char *buf, __u64 probe_offset, __u64 probe_addr)
{
jsonw_start_object(json_wtr);
jsonw_int_field(json_wtr, "pid", pid);
jsonw_int_field(json_wtr, "fd", fd);
jsonw_uint_field(json_wtr, "prog_id", prog_id);
switch (fd_type) {
case BPF_FD_TYPE_RAW_TRACEPOINT:
jsonw_string_field(json_wtr, "fd_type", "raw_tracepoint");
jsonw_string_field(json_wtr, "tracepoint", buf);
break;
case BPF_FD_TYPE_TRACEPOINT:
jsonw_string_field(json_wtr, "fd_type", "tracepoint");
jsonw_string_field(json_wtr, "tracepoint", buf);
break;
case BPF_FD_TYPE_KPROBE:
jsonw_string_field(json_wtr, "fd_type", "kprobe");
if (buf[0] != '\0') {
jsonw_string_field(json_wtr, "func", buf);
jsonw_lluint_field(json_wtr, "offset", probe_offset);
} else {
jsonw_lluint_field(json_wtr, "addr", probe_addr);
}
break;
case BPF_FD_TYPE_KRETPROBE:
jsonw_string_field(json_wtr, "fd_type", "kretprobe");
if (buf[0] != '\0') {
jsonw_string_field(json_wtr, "func", buf);
jsonw_lluint_field(json_wtr, "offset", probe_offset);
} else {
jsonw_lluint_field(json_wtr, "addr", probe_addr);
}
break;
case BPF_FD_TYPE_UPROBE:
jsonw_string_field(json_wtr, "fd_type", "uprobe");
jsonw_string_field(json_wtr, "filename", buf);
jsonw_lluint_field(json_wtr, "offset", probe_offset);
break;
case BPF_FD_TYPE_URETPROBE:
jsonw_string_field(json_wtr, "fd_type", "uretprobe");
jsonw_string_field(json_wtr, "filename", buf);
jsonw_lluint_field(json_wtr, "offset", probe_offset);
break;
}
jsonw_end_object(json_wtr);
}
static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type,
char *buf, __u64 probe_offset, __u64 probe_addr)
{
printf("pid %d fd %d: prog_id %u ", pid, fd, prog_id);
switch (fd_type) {
case BPF_FD_TYPE_RAW_TRACEPOINT:
printf("raw_tracepoint %s\n", buf);
break;
case BPF_FD_TYPE_TRACEPOINT:
printf("tracepoint %s\n", buf);
break;
case BPF_FD_TYPE_KPROBE:
if (buf[0] != '\0')
printf("kprobe func %s offset %llu\n", buf,
probe_offset);
else
printf("kprobe addr %llu\n", probe_addr);
break;
case BPF_FD_TYPE_KRETPROBE:
if (buf[0] != '\0')
printf("kretprobe func %s offset %llu\n", buf,
probe_offset);
else
printf("kretprobe addr %llu\n", probe_addr);
break;
case BPF_FD_TYPE_UPROBE:
printf("uprobe filename %s offset %llu\n", buf, probe_offset);
break;
case BPF_FD_TYPE_URETPROBE:
printf("uretprobe filename %s offset %llu\n", buf,
probe_offset);
break;
}
}
static int show_proc(const char *fpath, const struct stat *sb,
int tflag, struct FTW *ftwbuf)
{
__u64 probe_offset, probe_addr;
__u32 len, prog_id, fd_type;
int err, pid = 0, fd = 0;
const char *pch;
char buf[4096];
/* prefix always /proc */
pch = fpath + 5;
if (*pch == '\0')
return 0;
/* pid should be all numbers */
pch++;
while (isdigit(*pch)) {
pid = pid * 10 + *pch - '0';
pch++;
}
if (*pch == '\0')
return 0;
if (*pch != '/')
return FTW_SKIP_SUBTREE;
/* check /proc/<pid>/fd directory */
pch++;
if (strncmp(pch, "fd", 2))
return FTW_SKIP_SUBTREE;
pch += 2;
if (*pch == '\0')
return 0;
if (*pch != '/')
return FTW_SKIP_SUBTREE;
/* check /proc/<pid>/fd/<fd_num> */
pch++;
while (isdigit(*pch)) {
fd = fd * 10 + *pch - '0';
pch++;
}
if (*pch != '\0')
return FTW_SKIP_SUBTREE;
/* query (pid, fd) for potential perf events */
len = sizeof(buf);
err = bpf_task_fd_query(pid, fd, 0, buf, &len, &prog_id, &fd_type,
&probe_offset, &probe_addr);
if (err < 0)
return 0;
if (json_output)
print_perf_json(pid, fd, prog_id, fd_type, buf, probe_offset,
probe_addr);
else
print_perf_plain(pid, fd, prog_id, fd_type, buf, probe_offset,
probe_addr);
return 0;
}
static int do_show(int argc, char **argv)
{
int flags = FTW_ACTIONRETVAL | FTW_PHYS;
int err = 0, nopenfd = 16;
if (!has_perf_query_support())
return -1;
if (json_output)
jsonw_start_array(json_wtr);
if (nftw("/proc", show_proc, nopenfd, flags) == -1) {
p_err("%s", strerror(errno));
err = -1;
}
if (json_output)
jsonw_end_array(json_wtr);
return err;
}
static int do_help(int argc, char **argv)
{
fprintf(stderr,
"Usage: %s %s { show | list | help }\n"
"",
bin_name, argv[-2]);
return 0;
}
static const struct cmd cmds[] = {
{ "show", do_show },
{ "list", do_show },
{ "help", do_help },
{ 0 }
};
int do_perf(int argc, char **argv)
{
return cmd_select(cmds, argc, argv, do_help);
}