mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-08-05 16:54:27 +00:00
de07b18289
The strncmp benchmark uses the bpf_strncmp helper and a hand-written
loop to compare two strings. The values of the strings are filled from
userspace. One of the strings is non-const (in .bss) while the other is
const (in .rodata) since that is the requirement of bpf_strncmp.
The problem is that in the hand-written loop, Clang optimizes the reads
from the const string to always return 0 which breaks the benchmark.
Use barrier_var to prevent the optimization.
The effect can be seen on the strncmp-no-helper variant.
Before this change:
# ./bench strncmp-no-helper
Setting up benchmark 'strncmp-no-helper'...
Benchmark 'strncmp-no-helper' started.
Iter 0 (112.309us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Iter 1 (-23.238us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Iter 2 ( 58.994us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Iter 3 (-30.466us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Iter 4 ( 29.996us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Iter 5 ( 16.949us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Iter 6 (-60.035us): hits 0.000M/s ( 0.000M/prod), drops 0.000M/s, total operations 0.000M/s
Summary: hits 0.000 ± 0.000M/s ( 0.000M/prod), drops 0.000 ± 0.000M/s, total operations 0.000 ± 0.000M/s
After this change:
# ./bench strncmp-no-helper
Setting up benchmark 'strncmp-no-helper'...
Benchmark 'strncmp-no-helper' started.
Iter 0 ( 77.711us): hits 5.534M/s ( 5.534M/prod), drops 0.000M/s, total operations 5.534M/s
Iter 1 ( 11.215us): hits 6.006M/s ( 6.006M/prod), drops 0.000M/s, total operations 6.006M/s
Iter 2 (-14.253us): hits 5.931M/s ( 5.931M/prod), drops 0.000M/s, total operations 5.931M/s
Iter 3 ( 59.087us): hits 6.005M/s ( 6.005M/prod), drops 0.000M/s, total operations 6.005M/s
Iter 4 (-21.379us): hits 6.010M/s ( 6.010M/prod), drops 0.000M/s, total operations 6.010M/s
Iter 5 (-20.310us): hits 5.861M/s ( 5.861M/prod), drops 0.000M/s, total operations 5.861M/s
Iter 6 ( 53.937us): hits 6.004M/s ( 6.004M/prod), drops 0.000M/s, total operations 6.004M/s
Summary: hits 5.969 ± 0.061M/s ( 5.969M/prod), drops 0.000 ± 0.000M/s, total operations 5.969 ± 0.061M/s
Fixes: 9c42652f8b ("selftests/bpf: Add benchmark for bpf_strncmp() helper")
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Viktor Malik <vmalik@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20250313122852.1365202-1-vmalik@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
53 lines
1.1 KiB
C
53 lines
1.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
|
|
#include <linux/types.h>
|
|
#include <linux/bpf.h>
|
|
#include <bpf/bpf_helpers.h>
|
|
#include <bpf/bpf_tracing.h>
|
|
|
|
#define STRNCMP_STR_SZ 4096
|
|
|
|
/* Will be updated by benchmark before program loading */
|
|
const volatile unsigned int cmp_str_len = 1;
|
|
const char target[STRNCMP_STR_SZ];
|
|
|
|
long hits = 0;
|
|
char str[STRNCMP_STR_SZ];
|
|
|
|
char _license[] SEC("license") = "GPL";
|
|
|
|
static __always_inline int local_strncmp(const char *s1, unsigned int sz,
|
|
const char *s2)
|
|
{
|
|
int ret = 0;
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < sz; i++) {
|
|
/* E.g. 0xff > 0x31 */
|
|
ret = (unsigned char)s1[i] - (unsigned char)s2[i];
|
|
if (ret || !s1[i])
|
|
break;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
SEC("tp/syscalls/sys_enter_getpgid")
|
|
int strncmp_no_helper(void *ctx)
|
|
{
|
|
const char *target_str = target;
|
|
|
|
barrier_var(target_str);
|
|
if (local_strncmp(str, cmp_str_len + 1, target_str) < 0)
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|
|
SEC("tp/syscalls/sys_enter_getpgid")
|
|
int strncmp_helper(void *ctx)
|
|
{
|
|
if (bpf_strncmp(str, cmp_str_len + 1, target) < 0)
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|