linux-kernel - Re: [PATCH] perf record: Fix perf_can_aux_sample

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20191122134257.GA9996@kernel.org>
Date:   Fri, 22 Nov 2019 10:42:57 -0300
From:   Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
To:     Adrian Hunter <adrian.hunter@...el.com>
Cc:     Jiri Olsa <jolsa@...hat.com>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] perf record: Fix perf_can_aux_sample_size()

Em Fri, Nov 22, 2019 at 11:48:56AM +0200, Adrian Hunter escreveu:
> perf_can_aux_sample_size() always returned true because it did not pass
> the attribute size to sys_perf_event_open, nor correctly check the
> return value and errno.
> 
> Before:
> 
>   # perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
>   Error:
>   The sys_perf_event_open() syscall returned with 7 (Argument list too long) for event (branch-misses:u).
>   /bin/dmesg | grep -i perf may provide additional information.
> 
> After:
> 
>   # perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
>   AUX area sampling is not supported by kernel

Since this hasn't been sent to Ingo, I combined it with the patch that
introduced the problem, this one:

c31d79e7a052 perf record: Add a function to test for kernel support for AUX area sampling

Thanks for the quick fix,

- Arnaldo

 
> Signed-off-by: Adrian Hunter <adrian.hunter@...el.com>
> ---
>  tools/perf/util/record.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
> index e2321edcdd8f..7def66168503 100644
> --- a/tools/perf/util/record.c
> +++ b/tools/perf/util/record.c
> @@ -143,6 +143,7 @@ bool perf_can_record_cpu_wide(void)
>  bool perf_can_aux_sample(void)
>  {
>  	struct perf_event_attr attr = {
> +		.size = sizeof(struct perf_event_attr),
>  		.exclude_kernel = 1,
>  		/*
>  		 * Non-zero value causes the kernel to calculate the effective
> @@ -158,7 +159,7 @@ bool perf_can_aux_sample(void)
>  	 * then we assume that it is supported. We are relying on the kernel to
>  	 * validate the attribute size before anything else that could be wrong.
>  	 */
> -	if (fd == -E2BIG)
> +	if (fd < 0 && errno == E2BIG)
>  		return false;
>  	if (fd >= 0)
>  		close(fd);
> -- 
> 2.17.1

-- 

- Arnaldo