☰

Archlinux，“kernel.perf_event_paranoid”不被尊重

tag-icon • tag-icon arch-linux linux-kernel performance perf-event
Archlinux，“kernel.perf_event_paranoid”不被尊重

当读取 CPUS 上的性能计数器 (PMC) 时，必须kernel.perf_event_paranoid（<=1请参阅内核文档）

下面的程序读取 PMC 并且应该提前退出1，如果它无法打开计数器，kernel.perf_event_paranoid即>1（在 后检查syscall）

我测试过

  • ArchLinuxLinux host1 5.17.9-arch1-1 #1 SMP PREEMPT Wed, 18 May 2022 17:30:11 +0000 x86_64 GNU/Linux
  • 乌班图Linux host2 5.15.0-30-generic #31-Ubuntu SMP Thu May 5 10:00:34 UTC 2022 x86_64 x86_64 x86_64 GNU/Linux

现在，默认情况下，参数为2(Arch)、4(Ubuntu)。我运行该程序，它应该无法打开性能计数器。在 Arch 上，它仍然可以做到，在 Ubuntu 上失败（正如预期的那样）。

经过修补和指针从卡米尔在 SU SE 上，我发现有Ubuntu一个补丁需要设置才能4真正生效。

  • ArchLinux 上有类似的东西吗？
  • 这种行为也可以在其他发行版上重现吗？

该脚本可以帮助重现

#!/bin/bash

cat >pmc.c <<'EOF'
#include <linux/perf_event.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <unistd.h>

static struct perf_event_attr attr;
static int fdperf = -1;
static struct perf_event_mmap_page *buf = 0;

long long cpucycles_amd64rdpmc(void) {
  long long result;
  unsigned int seq;
  long long index;
  long long offset;

  if (fdperf == -1) {
    attr.type = PERF_TYPE_HARDWARE;
    attr.config = PERF_COUNT_HW_CPU_CYCLES;
    attr.exclude_kernel = 1;
    fdperf = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
    if (fdperf == -1){
        fprintf(stderr, "\033[31m--> could not open perf counter. Check paranoid setting\033[0m\n");
        exit(1);
    }
    buf = mmap(NULL, sysconf(_SC_PAGESIZE), PROT_READ, MAP_SHARED, fdperf, 0);
  }

  do {
    seq = buf->lock;
    asm volatile("" ::: "memory");
    index = buf->index;
    offset = buf->offset;
    asm volatile("rdpmc;shlq $32,%%rdx;orq %%rdx,%%rax"
                 : "=a"(result)
                 : "c"(index - 1)
                 : "%rdx");
    asm volatile("" ::: "memory");
  } while (buf->lock != seq);

  result += offset;
  result &= 0xffffffffffff;
  return result;
}

int main() {

  long long c = cpucycles_amd64rdpmc();
  printf("counter: %llx\n", c);
  return 0;
}
EOF

param_name=kernel.perf_event_paranoid
read_pmc() {
  echo -n "--> reading, "
  sysctl "${param_name}"
}

set_pmc() {
  n=$1
  echo -e "--> setting to ${n}"
  sudo sysctl -w "${param_name}=${n}"

  read_pmc
  echo "should be ${n}"
}

run() {
  echo "--> running"
  ./pmc
}

#compile
gcc pmc.c -o pmc

read_pmc
run
echo -e "\n--> if ${param_name} as >1, that should have printed the error message\n\n"

set_pmc 1

run
echo -e "\n--> that should have worked and printed the counter.\n"

#re-set to 2
set_pmc 2
run
echo -e "\033[31m--> that should NOT have worked but it printed the counter\033[0m.\n"

rm pmc.c pmc

（rdpmc 代码基于 cpucycles/amd64rdpmc.c超级警察）

有关的：

相关内容