Re: Using perf_event_open() to sample multiple events of a process

[Peter Zijlstra]

On Thu, Nov 04, 2021 at 10:57:50PM -0700, Nadav Amit wrote:
> Hello Ken, Peter,
> 
> I would appreciate some help regarding the use of perf_event_open()
> to have multiple samples getting into the same mmap’d memory when they
> are both attached to the same process.
> 
> I am doing so (using both PERF_FLAG_FD_NO_GROUP and PERF_FLAG_FD_OUTPUT),
> but it results in -EINVAL. Debugging the code shows that
> perf_event_set_output() fails due to the following check:
> 
>         /*
>          * If its not a per-cpu rb, it must be the same task.
>          */
>         if (output_event->cpu == -1 && output_event->ctx != event->ctx)
>                 goto out;
> 
> However, it appears that at this point, event->ctx is not initialized
> (it is null) so the test fails and the whole perf_event_open() syscall
> fails.
> 
> Am I missing something? If not, I am unsure, unfortunately, what the
> proper way to fix it is…
> 
> I include a small test that fails on my system. The second
> perf_event_open fails due to the check in perf_event_set_output():
> 

Works when you use the SET_OUTPUT ioctl()...

I think something went sideways in the syscall path and things went out
of order :/ I'll try and have a look.


---
#define _GNU_SOURCE 1

#include <asm/unistd.h>
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
#include <sys/mman.h>
#include <sys/ioctl.h>
#include <unistd.h>
#include <stdlib.h>
#include <stdio.h>

long perf_event_open(struct perf_event_attr* event_attr, pid_t pid, int cpu,
		int group_fd, unsigned long flags)
{
	return syscall(__NR_perf_event_open, event_attr, pid, cpu, group_fd, flags);
}

int main(void)
{
	pid_t pid = getpid();
	int group_fd, fd, err;
	void *p;
	struct perf_event_attr pe = {
		.type = 4,
		.size = sizeof(struct perf_event_attr),
		.config = 0x11d0,
		.sample_type = 0x8,
		.sample_period = 1000,
		.precise_ip = 2,
	};

	group_fd = perf_event_open(&pe, pid, -1, -1, PERF_FLAG_FD_CLOEXEC |
			PERF_FLAG_FD_NO_GROUP |
			PERF_FLAG_FD_OUTPUT);

	if (group_fd < 0) {
		perror("first perf_event_open");
		exit(-1);
	}

	p = mmap(NULL, 3 * 4096, PROT_READ|PROT_WRITE, MAP_SHARED, group_fd, 0);

	if (p == MAP_FAILED) {
		perror("MAP_FAILED");
		exit(-1);
	}

	pe.config = 0x12d0;

	fd = perf_event_open(&pe, pid, -1, -1, PERF_FLAG_FD_CLOEXEC |
			PERF_FLAG_FD_NO_GROUP |
			PERF_FLAG_FD_OUTPUT);

	if (fd < 0) {
		perror("second perf_event_open");
		exit(-1);
	}

	err = ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, group_fd);
	if (err < 0) {
		perror("ioctl");
		exit(-1);
	}

	printf("success\n");
}