Re: [PATCH RFC] tracepoint: Introduce tracepoint callbacks executing with preempt on

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: rostedt <rostedt@goodmis.org>
Cc: Joel Fernandes <joelaf@google.com>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Tom Zanussi <tom.zanussi@linux.intel.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Boqun Feng <boqun.feng@gmail.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	fweisbec <fweisbec@gmail.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	kbuild test robot <fengguang.wu@intel.com>,
	baohong liu <baohong.liu@intel.com>,
	vedang patel <vedang.patel@intel.com>,
	kernel-team <kernel-team@android.com>
Subject: Re: [PATCH RFC] tracepoint: Introduce tracepoint callbacks executing with preempt on
Date: Fri, 27 Apr 2018 11:42:15 -0400 (EDT)	[thread overview]
Message-ID: <362165882.5842.1524843735295.JavaMail.zimbra@efficios.com> (raw)
In-Reply-To: <20180427104747.2d965925@gandalf.local.home>

----- On Apr 27, 2018, at 10:47 AM, rostedt rostedt@goodmis.org wrote:

> On Fri, 27 Apr 2018 10:26:29 -0400 (EDT)
> Mathieu Desnoyers <mathieu.desnoyers@efficios.com> wrote:
> 
>> The general approach and the implementation look fine, except for
>> one small detail: I would be tempted to explicitly disable preemption
>> around the call to the tracepoint callback for the rcuidle variant,
>> unless we plan to audit every tracer right away to remove any assumption
>> that preemption is disabled in the callback implementation.
> 
> I'm thinking that we do that audit. There shouldn't be many instances
> of it. I like the idea that a tracepoint callback gets called with
> preemption enabled.

I see that ftrace explicitly disables preemption in its ring buffer
code. FWIW, this is redundant when called from sched-rcu tracepoints
and from kprobes which adds unnecessary performance overhead.

LTTng expects preemption to be disabled when invoked. I can adapt on my
side as needed, but would prefer not to have redundant preemption disabling
for probes hooking on sched-rcu tracepoints (which is the common case).

Do perf callbacks expect preemption to be disabled ?

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com