Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Jiri Olsa <olsajiri@gmail.com>
Date:   Fri, 17 Jun 2022 12:21:43 +0200
To:     "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc:     Steven Rostedt <rostedt@goodmis.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>, Yonghong Song <yhs@fb.com>,
        bpf <bpf@vger.kernel.org>, Kernel Team <kernel-team@fb.com>,
        linux-kernel@vger.kernel.org, stable@vger.kernel.org
Subject: Re: [PATCH] tracing/kprobes: Check whether get_kretprobe() returns
 NULL in kretprobe_dispatcher()
Message-ID: <YqxVt4KoSIMHUH+/@krava>
References: <165366693881.797669.16926184644089588731.stgit@devnote2>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <165366693881.797669.16926184644089588731.stgit@devnote2>
Precedence: bulk

On Sat, May 28, 2022 at 12:55:39AM +0900, Masami Hiramatsu (Google) wrote:
> From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> 
> There is a small chance that get_kretprobe(ri) returns NULL in
> kretprobe_dispatcher() when another CPU unregisters the kretprobe
> right after __kretprobe_trampoline_handler().
> 
> To avoid this issue, kretprobe_dispatcher() checks the get_kretprobe()
> return value again. And if it is NULL, it returns soon because that
> kretprobe is under unregistering process.
> 
> This issue has been introduced when the kretprobe is decoupled
> from the struct kretprobe_instance by commit d741bf41d7c7
> ("kprobes: Remove kretprobe hash"). Before that commit, the
> struct kretprob_instance::rp directly points the kretprobe
> and it is never be NULL.
> 
> Reported-by: Yonghong Song <yhs@fb.com>
> Fixes: d741bf41d7c7 ("kprobes: Remove kretprobe hash")
> Cc: stable@vger.kernel.org
> Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>

Acked-by: Jiri Olsa <jolsa@kernel.org>

jirka

> ---
>  kernel/trace/trace_kprobe.c |   11 ++++++++++-
>  1 file changed, 10 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
> index 93507330462c..a245ea673715 100644
> --- a/kernel/trace/trace_kprobe.c
> +++ b/kernel/trace/trace_kprobe.c
> @@ -1718,8 +1718,17 @@ static int
>  kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
>  {
>  	struct kretprobe *rp = get_kretprobe(ri);
> -	struct trace_kprobe *tk = container_of(rp, struct trace_kprobe, rp);
> +	struct trace_kprobe *tk;
> +
> +	/*
> +	 * There is a small chance that get_kretprobe(ri) returns NULL when
> +	 * the kretprobe is unregister on another CPU between kretprobe's
> +	 * trampoline_handler and this function.
> +	 */
> +	if (unlikely(!rp))
> +		return 0;
>  
> +	tk = container_of(rp, struct trace_kprobe, rp);
>  	raw_cpu_inc(*tk->nhit);
>  
>  	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
>