[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20140709083214.GA9918@twins.programming.kicks-ass.net>
Date: Wed, 9 Jul 2014 10:32:14 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: kan.liang@...el.com
Cc: andi@...stfloor.org, linux-kernel@...r.kernel.org,
kvm@...r.kernel.org
Subject: Re: [PATCH V4 1/2] perf ignore LBR and extra_regs.
On Tue, Jul 08, 2014 at 09:49:40AM -0700, kan.liang@...el.com wrote:
> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
> index 2bdfbff..f0e8022 100644
> --- a/arch/x86/kernel/cpu/perf_event.c
> +++ b/arch/x86/kernel/cpu/perf_event.c
> @@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
> continue;
> if (event->attr.config1 & ~er->valid_mask)
> return -EINVAL;
> + /* Check if the extra msrs can be safely accessed*/
> + if (!x86_pmu.extra_msr_access[er->idx])
> + continue;
>
> reg->idx = er->idx;
> reg->config = event->attr.config1;
You should return an error here; doing continue will eventually make
it return 0, which is no-error and things will happily create the event
and malfunction.
Content of type "application/pgp-signature" skipped
Powered by blists - more mailing lists