[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200212232830.GB170680@google.com>
Date: Wed, 12 Feb 2020 18:28:30 -0500
From: Joel Fernandes <joel@...lfernandes.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, linux-arch@...r.kernel.org,
rostedt@...dmis.org, mingo@...nel.org, gregkh@...uxfoundation.org,
gustavo@...eddedor.com, tglx@...utronix.de, paulmck@...nel.org,
josh@...htriplett.org, mathieu.desnoyers@...icios.com,
jiangshanlai@...il.com,
"Steven Rostedt (VMware)" <rosted@...dmis.org>
Subject: Re: [PATCH v2 6/9] perf,tracing: Prepare the perf-trace interface
for RCU changes
On Wed, Feb 12, 2020 at 10:01:45PM +0100, Peter Zijlstra wrote:
> The tracepoint interface will stop providing regular RCU context; make
> sure we do it ourselves, since perf makes use of regular RCU protected
> data.
>
> Suggested-by: Steven Rostedt (VMware) <rosted@...dmis.org>
> Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
> ---
> kernel/events/core.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -8950,6 +8950,7 @@ void perf_tp_event(u16 event_type, u64 c
> {
> struct perf_sample_data data;
> struct perf_event *event;
> + unsigned long rcu_flags;
The flags are not needed I guess, if you agree on not using in_nmi() in
trace_rcu_enter().
thanks,
- Joel
> struct perf_raw_record raw = {
> .frag = {
> @@ -8961,6 +8962,8 @@ void perf_tp_event(u16 event_type, u64 c
> perf_sample_data_init(&data, 0, 0);
> data.raw = &raw;
>
> + rcu_flags = trace_rcu_enter();
> +
> perf_trace_buf_update(record, event_type);
>
> hlist_for_each_entry_rcu(event, head, hlist_entry) {
> @@ -8996,6 +8999,8 @@ void perf_tp_event(u16 event_type, u64 c
> }
>
> perf_swevent_put_recursion_context(rctx);
> +
> + trace_rcu_exit(rcu_flags);
> }
> EXPORT_SYMBOL_GPL(perf_tp_event);
>
>
>
Powered by blists - more mailing lists