Re: [tip:smp/hotplug] perf: Cure hotplug lock ordering issues

From: Peter Zijlstra
Date: Mon Apr 24 2017 - 05:04:58 EST


On Sun, Apr 23, 2017 at 10:16:34AM -0700, tip-bot for Thomas Gleixner wrote:
> Commit-ID: 14aff62ede39a7b069beb7b95c1d02edb8ee912d
> Gitweb: http://git.kernel.org/tip/14aff62ede39a7b069beb7b95c1d02edb8ee912d
> Author: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> AuthorDate: Sun, 23 Apr 2017 12:13:09 +0200
> Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> CommitDate: Sun, 23 Apr 2017 19:11:27 +0200
>
> perf: Cure hotplug lock ordering issues
>
> The get_online_cpus() rework unearthed lock ordering issues.
>
> Reorder hotpluglock and perf_sched_mutex() to avoid circular locking
> dependencies and convert static_branch_disable() to the cpuslocked version
> to avoid hotplug lock recursion.
>
> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> ---
> kernel/events/core.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 8aa3063..b5b4f52f 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -4016,10 +4016,12 @@ static void unaccount_event(struct perf_event *event)
>
> static void perf_sched_delayed(struct work_struct *work)
> {
> + get_online_cpus();
> mutex_lock(&perf_sched_mutex);
> if (atomic_dec_and_test(&perf_sched_count))
> - static_branch_disable(&perf_sched_events);
> + static_branch_disable_cpuslocked(&perf_sched_events);
> mutex_unlock(&perf_sched_mutex);
> + put_online_cpus();
> }

So I think we can simply remove the perf_sched_mutex here. Its only
purpose is to serialize the 0->1 state, such that nobody passes before
we've done the additional sync_sched() call.

Once we're >=1, it really doesn't matter anymore. Not sure why I put it
in here. Maybe extensive paranoia..