Re: [PATCH v2 2/2] selftests/bpf: bpf_cookie: make perf_event subtest trigger reliably

[Jiri Olsa <olsajiri@gmail.com>]

On Sat, Feb 28, 2026 at 03:45:55PM +0800, Sun Jian wrote:
> The perf_event subtest relies on SW_CPU_CLOCK sampling to trigger the BPF
> program, but the current CPU burn loop can be too short on slower systems
> and may fail to generate any overflow sample. This leaves pe_res unchanged
> and makes the test flaky.
> 
> Make burn_cpu() take a loop count and use a longer burn only for the
> perf_event subtest. Also scope perf_event_open() to the current task to
> avoid wasting samples on unrelated activity.
> 
> Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
> 
> ---
> Changes in v2:
> 
> Move the perf_event_open() argument change here from patch 1/2.
> 
> v1: <https://lore.kernel.org/lkml/20260227164037.84110-1-sun.jian.kdev@gmail.com/>
> ---
>  .../selftests/bpf/prog_tests/bpf_cookie.c     | 19 +++++++++++--------
>  1 file changed, 11 insertions(+), 8 deletions(-)
> 
> diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
> index b7643a5bf7ad..35adc3f6d443 100644
> --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
> +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
> @@ -6,6 +6,7 @@
>  #include <sys/syscall.h>
>  #include <sys/mman.h>
>  #include <unistd.h>
> +#include <linux/compiler.h>
>  #include <test_progs.h>
>  #include <network_helpers.h>
>  #include <bpf/btf.h>
> @@ -431,11 +432,12 @@ static void tp_subtest(struct test_bpf_cookie *skel)
>  	bpf_link__destroy(link3);
>  }
>  
> -static void burn_cpu(void)
> +static void burn_cpu(long loops)

nit, there's another burn_cpu in prog_tests/perf_link.c,
we could add it to trace_helpers.c or test_progs.c 

>  {
> -	volatile int j = 0;
> +	long j = 0;
>  	cpu_set_t cpu_set;
> -	int i, err;
> +	long i;
> +	int err;
>  
>  	/* generate some branches on cpu 0 */
>  	CPU_ZERO(&cpu_set);
> @@ -443,9 +445,10 @@ static void burn_cpu(void)
>  	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
>  	ASSERT_OK(err, "set_thread_affinity");
>  
> -	/* spin the loop for a while (random high number) */
> -	for (i = 0; i < 1000000; ++i)
> +	for (i = 0; i < loops; ++i) {
>  		++j;
> +		barrier();

what's the rationale for barrier call in here,
together with the volatile change above?

thanks,
jirka


> +	}
>  }
>  
>  static void pe_subtest(struct test_bpf_cookie *skel)
> @@ -461,7 +464,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
>  	attr.type = PERF_TYPE_SOFTWARE;
>  	attr.config = PERF_COUNT_SW_CPU_CLOCK;
>  	attr.sample_period = 100000;
> -	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
> +	pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC);
>  	if (!ASSERT_GE(pfd, 0, "perf_fd"))
>  		goto cleanup;
>  
> @@ -470,7 +473,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
>  	if (!ASSERT_OK_PTR(link, "link1"))
>  		goto cleanup;
>  
> -	burn_cpu(); /* trigger BPF prog */
> +	burn_cpu(100000000L); /* trigger BPF prog */
>  
>  	ASSERT_EQ(skel->bss->pe_res, 0x100000, "pe_res1");
>  
> @@ -489,7 +492,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
>  	if (!ASSERT_OK_PTR(link, "link2"))
>  		goto cleanup;
>  
> -	burn_cpu(); /* trigger BPF prog */
> +	burn_cpu(100000000L); /* trigger BPF prog */
>  
>  	ASSERT_EQ(skel->bss->pe_res, 0x200000, "pe_res2");
>  
> -- 
> 2.43.0
> 
>