On Tue, Jan 03, 2017 at 10:40:59AM +0100, Peter Zijlstra wrote: > On Wed, Dec 28, 2016 at 02:31:04PM +0100, Jiri Olsa wrote: > > When in counting mode we setup the counter with the > > longest possible period and read the value with read > > syscall. > > > > We also still setup the PMI to be triggered when such > > counter overflow to reconfigure it. > > > > We also get PEBS interrupt if such counter has precise_ip > > set (which makes no sense, but it's possible). > > I think we should reject non sampling pebs events, as you say they make > no sense what so ever.
ook, attached jirka --- As Peter suggested [1] rejecting non sampling PEBS events, because they dont make any sense and could cause issues in NMI handler [2]. [1] http://lkml.kernel.org/r/20170103094059.GC3093@worktop [2] http://lkml.kernel.org/r/[email protected] Signed-off-by: Jiri Olsa <[email protected]> --- arch/x86/events/core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 64582cfa6976..48b851f0ef89 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; + + /* There's no sense in having PEBS for non sampling events. */ + if (!is_sampling_event(event)) + return -EINVAL; } /* * check that PEBS LBR correction does not conflict with -- 2.9.3
