From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Masami Hiramatsu <mhiramat@kernel.org>
Cc: linux-perf-users@vger.kernel.org
Subject: Re: perf probe: Trying to read a 'ctx' named local variable
Date: Thu, 20 Jul 2023 11:40:42 -0300 [thread overview]
Message-ID: <ZLlHagQuZGAhOk50@kernel.org> (raw)
In-Reply-To: <20230718085451.f6e099de7d34f2ae3dc4b7fe@kernel.org>
Em Tue, Jul 18, 2023 at 08:54:51AM +0900, Masami Hiramatsu escreveu:
> On Mon, 17 Jul 2023 15:06:10 -0300
> Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
>
> > Hi Masami,
> >
> > Trying to use perf to debug perf I stumbled on this:
> >
> > [root@quaco ~]# perf probe -x ~/bin/perf -L sigtrap_handler
> > <sigtrap_handler@/home/acme/git/perf-tools/tools/perf/tests/sigtrap.c:0>
> > 0 sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused)
> > {
> > if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED))
> > 3 ctx.first_siginfo = *info;
> > 4 __atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED);
> > }
> >
> > static void *test_thread(void *arg)
> >
> > [root@quaco ~]# perf probe -x ~/bin/perf sigtrap_handler:4 "ctx.signal_count"
> > Failed to write event: Invalid argument
> > Please upgrade your kernel to at least 3.14 to have access to feature @ctx
> > Error: Failed to add events.
> > [root@quaco ~]#
>
> Ah, this is a wrong usage (I'm also trapped the same thing). Correctly, it should
> pass it as a single parameter.
>
> perf probe -x ~/bin/perf "sigtrap_handler:4 ctx.signal_count"
[root@five ~]# perf probe -x ~/bin/perf "sigtrap_handler:4 ctx.signal_count"
Failed to write event: Invalid argument
Please upgrade your kernel to at least 3.14 to have access to feature @ctx
Error: Failed to add events.
[root@five ~]#
Didn't work?
- Arnaldo
> This is for adding several events at the same time. But now it becomes just a trap.
> Can I change the syntax from
>
> perf probe [OPTIONS] <PROBE-DEFINITION> [PROBE-DEFINITION...]
>
> To,
>
> perf probe [OPTIONS] <PROBE-POINT> [ARGS...]
>
> ?
>
> We can keep --add having optional parameter as below.
>
> perf probe [OPTIONS] --add <PROBE-DEFINITION>
>
> Thank you,
>
> >
> > [root@quaco ~]# uname -a
> > Linux quaco 6.3.8-100.fc37.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Jun 15 01:51:54 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux
> > [root@quaco ~]# rpm -qa | grep kernel-debuginfo
> > kernel-debuginfo-common-x86_64-6.3.8-100.fc37.x86_64
> > kernel-debuginfo-6.3.8-100.fc37.x86_64
> > [root@quaco ~]#
> >
> > --
> >
> > - Arnaldo
>
>
> --
> Masami Hiramatsu (Google) <mhiramat@kernel.org>
--
- Arnaldo
next prev parent reply other threads:[~2023-07-20 14:40 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-17 18:06 perf probe: Trying to read a 'ctx' named local variable Arnaldo Carvalho de Melo
2023-07-17 23:54 ` Masami Hiramatsu
2023-07-20 14:40 ` Arnaldo Carvalho de Melo [this message]
2023-07-21 0:38 ` Masami Hiramatsu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ZLlHagQuZGAhOk50@kernel.org \
--to=acme@kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mhiramat@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).