mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-29 05:44:11 +00:00
fa853c4b83
Introduce 'perf stat -b' option, which counts events for BPF programs, like:
[root@localhost ~]# ~/perf stat -e ref-cycles,cycles -b 254 -I 1000
1.487903822 115,200 ref-cycles
1.487903822 86,012 cycles
2.489147029 80,560 ref-cycles
2.489147029 73,784 cycles
3.490341825 60,720 ref-cycles
3.490341825 37,797 cycles
4.491540887 37,120 ref-cycles
4.491540887 31,963 cycles
The example above counts 'cycles' and 'ref-cycles' of BPF program of id
254. This is similar to bpftool-prog-profile command, but more
flexible.
'perf stat -b' creates per-cpu perf_event and loads fentry/fexit BPF
programs (monitor-progs) to the target BPF program (target-prog). The
monitor-progs read perf_event before and after the target-prog, and
aggregate the difference in a BPF map. Then the user space reads data
from these maps.
A new 'struct bpf_counter' is introduced to provide a common interface
that uses BPF programs/maps to count perf events.
Committer notes:
Removed all but bpf_counter.h includes from evsel.h, not needed at all.
Also BPF map lookups for PERCPU_ARRAYs need to have as its value receive
buffer passed to the kernel libbpf_num_possible_cpus() entries, not
evsel__nr_cpus(evsel), as the former uses
/sys/devices/system/cpu/possible while the later uses
/sys/devices/system/cpu/online, which may be less than the 'possible'
number making the bpf map lookup overwrite memory and cause hard to
debug memory corruption.
We need to continue using evsel__nr_cpus(evsel) when accessing the
perf_counts array tho, not to overwrite another are of memory :-)
Signed-off-by: Song Liu <songliubraving@fb.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/lkml/20210120163031.GU12699@kernel.org/
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Link: http://lore.kernel.org/lkml/20201229214214.3413833-4-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
97 lines
2.4 KiB
C
97 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _PERF_TARGET_H
|
|
#define _PERF_TARGET_H
|
|
|
|
#include <stdbool.h>
|
|
#include <sys/types.h>
|
|
|
|
struct target {
|
|
const char *pid;
|
|
const char *tid;
|
|
const char *cpu_list;
|
|
const char *uid_str;
|
|
const char *bpf_str;
|
|
uid_t uid;
|
|
bool system_wide;
|
|
bool uses_mmap;
|
|
bool default_per_cpu;
|
|
bool per_thread;
|
|
};
|
|
|
|
enum target_errno {
|
|
TARGET_ERRNO__SUCCESS = 0,
|
|
|
|
/*
|
|
* Choose an arbitrary negative big number not to clash with standard
|
|
* errno since SUS requires the errno has distinct positive values.
|
|
* See 'Issue 6' in the link below.
|
|
*
|
|
* http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
|
|
*/
|
|
__TARGET_ERRNO__START = -10000,
|
|
|
|
/* for target__validate() */
|
|
TARGET_ERRNO__PID_OVERRIDE_CPU = __TARGET_ERRNO__START,
|
|
TARGET_ERRNO__PID_OVERRIDE_UID,
|
|
TARGET_ERRNO__UID_OVERRIDE_CPU,
|
|
TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
|
|
TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
|
|
TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
|
|
TARGET_ERRNO__BPF_OVERRIDE_CPU,
|
|
TARGET_ERRNO__BPF_OVERRIDE_PID,
|
|
TARGET_ERRNO__BPF_OVERRIDE_UID,
|
|
TARGET_ERRNO__BPF_OVERRIDE_THREAD,
|
|
|
|
/* for target__parse_uid() */
|
|
TARGET_ERRNO__INVALID_UID,
|
|
TARGET_ERRNO__USER_NOT_FOUND,
|
|
|
|
__TARGET_ERRNO__END,
|
|
};
|
|
|
|
enum target_errno target__validate(struct target *target);
|
|
enum target_errno target__parse_uid(struct target *target);
|
|
|
|
int target__strerror(struct target *target, int errnum, char *buf, size_t buflen);
|
|
|
|
static inline bool target__has_task(struct target *target)
|
|
{
|
|
return target->tid || target->pid || target->uid_str;
|
|
}
|
|
|
|
static inline bool target__has_cpu(struct target *target)
|
|
{
|
|
return target->system_wide || target->cpu_list;
|
|
}
|
|
|
|
static inline bool target__has_bpf(struct target *target)
|
|
{
|
|
return target->bpf_str;
|
|
}
|
|
|
|
static inline bool target__none(struct target *target)
|
|
{
|
|
return !target__has_task(target) && !target__has_cpu(target);
|
|
}
|
|
|
|
static inline bool target__has_per_thread(struct target *target)
|
|
{
|
|
return target->system_wide && target->per_thread;
|
|
}
|
|
|
|
static inline bool target__uses_dummy_map(struct target *target)
|
|
{
|
|
bool use_dummy = false;
|
|
|
|
if (target->default_per_cpu)
|
|
use_dummy = target->per_thread ? true : false;
|
|
else if (target__has_task(target) ||
|
|
(!target__has_cpu(target) && !target->uses_mmap))
|
|
use_dummy = true;
|
|
else if (target__has_per_thread(target))
|
|
use_dummy = true;
|
|
|
|
return use_dummy;
|
|
}
|
|
|
|
#endif /* _PERF_TARGET_H */
|