[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241107105211.3275831b@gandalf.local.home>
Date: Thu, 7 Nov 2024 10:52:11 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: Marco Elver <elver@...gle.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>, Kees Cook
<keescook@...omium.org>, Masami Hiramatsu <mhiramat@...nel.org>, Andrew
Morton <akpm@...ux-foundation.org>, Oleg Nesterov <oleg@...hat.com>,
linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org, Dmitry
Vyukov <dvyukov@...gle.com>, kasan-dev@...glegroups.com
Subject: Re: [PATCH v2 1/2] tracing: Add task_prctl_unknown tracepoint
On Thu, 7 Nov 2024 16:46:47 +0100
Marco Elver <elver@...gle.com> wrote:
> > My concern is that we start adding tons of special-case
> > tracepoints to the implementation of system calls which
> > are redundant with the sys_enter/exit tracepoints.
> >
> > Why favor this approach rather than hooking on sys_enter/exit ?
>
> It's __extremely__ expensive when deployed at scale. See note in
> commit description above.
Agreed. The sys_enter/exit trace events make all syscalls go the slow path,
which can be quite expensive.
-- Steve
Powered by blists - more mailing lists