[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250922063616.GN3245006@noisy.programming.kicks-ass.net>
Date: Mon, 22 Sep 2025 08:36:16 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Alexei Starovoitov <alexei.starovoitov@...il.com>
Cc: Menglong Dong <menglong8.dong@...il.com>, Jiri Olsa <jolsa@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>, X86 ML <x86@...nel.org>,
"H. Peter Anvin" <hpa@...or.com>, Kees Cook <kees@...nel.org>,
Sami Tolvanen <samitolvanen@...gle.com>,
Mike Rapoport <rppt@...nel.org>, Andy Lutomirski <luto@...nel.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Alexei Starovoitov <ast@...nel.org>,
Andrii Nakryiko <andrii@...nel.org>,
LKML <linux-kernel@...r.kernel.org>, bpf <bpf@...r.kernel.org>
Subject: Re: [PATCH] x86/ibt: make is_endbr() notrace
On Thu, Sep 18, 2025 at 10:53:51AM -0700, Alexei Starovoitov wrote:
> > notrace don't help with kprobes in general, only with __fentry__ sites.
>
> Are you sure ? Last time I checked "notrace" prevents kprobing
> anywhere in that function.
#define notrace __attribute__((__no_instrument_function__))
AFAICT that only inhibits the compiler from generating __fentry__ calls.
There is NOKPROBE_SYMBOL() to explicitly exclude kprobes from a symbol.
And we have noinstr, which along with a gazillion code-gen attributes
puts things in a .noinstr.text section and that section is also excluded
from kprobe placement.
Powered by blists - more mailing lists