On Fri, May 12, 2017 at 11:40:32AM +0100, Chris Wilson wrote:
> In commit 1fd7e4169954 ("perf/core: Remove perf_cpu_context::unique_pmu"),
> the search for another user of the pmu_cpu_context was removed, and so
> we unconditionally free it during perf_pmu_unregister. This leads to
> random corruption later and a BUG at mm/percpu.c:689.
> 
> Fixes: 1fd7e4169954 ("perf/core: Remove perf_cpu_context::unique_pmu")
> Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
> Cc: David Carrillo-Cisneros <davi...@google.com>
> Cc: Peter Zijlstra (Intel) <pet...@infradead.org>
> Cc: Ingo Molnar <mi...@redhat.com>
> Cc: <sta...@vger.kernel.org> # v4.11+
> ---
>  kernel/events/core.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index aaefaa27e1a6..e62b6207925c 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -9005,7 +9005,8 @@ void perf_pmu_unregister(struct pmu *pmu)
>               device_del(pmu->dev);
>               put_device(pmu->dev);
>       }
> -     free_pmu_context(pmu);
> +     if (!find_pmu_context(pmu->task_ctx_nr))

Bleh, that find should be under some guard, such as the mutex we held
ealier.

> +             free_pmu_context(pmu);
>  }
>  EXPORT_SYMBOL_GPL(perf_pmu_unregister);
>  
> -- 
> 2.11.0
> 

-- 
Chris Wilson, Intel Open Source Technology Centre

Reply via email to