From 5dc855d44c2ad960a86f593c60461f1ae1566b6d Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 16 Mar 2017 12:59:39 -0700 Subject: x86/perf: Fix CR4.PCE propagation to use active_mm instead of mm If one thread mmaps a perf event while another thread in the same mm is in some context where active_mm != mm (which can happen in the scheduler, for example), refresh_pce() would write the wrong value to CR4.PCE. This broke some PAPI tests. Reported-and-tested-by: Vince Weaver Signed-off-by: Andy Lutomirski Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: 7911d3f7af14 ("perf/x86: Only allow rdpmc if a perf_event is mapped") Link: http://lkml.kernel.org/r/0c5b38a76ea50e405f9abe07a13dfaef87c173a1.1489694270.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 1635c0c8df23..e07b36c5588a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2100,8 +2100,8 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->mm) - load_mm_cr4(current->mm); + if (current->active_mm) + load_mm_cr4(current->active_mm); } static void x86_pmu_event_mapped(struct perf_event *event) -- cgit v1.2.3 From 4b07372a32c0c1505a7634ad7e607d83340ef645 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 16 Mar 2017 12:59:40 -0700 Subject: x86/perf: Clarify why x86_pmu_event_mapped() isn't racy Naively, it looks racy, but ->mmap_sem saves it. Add a comment and a lockdep assertion. Signed-off-by: Andy Lutomirski Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/03a1e629063899168dfc4707f3bb6e581e21f5c6.1489694270.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index e07b36c5588a..183a972f9210 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2109,6 +2109,18 @@ static void x86_pmu_event_mapped(struct perf_event *event) if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; + /* + * This function relies on not being called concurrently in two + * tasks in the same mm. Otherwise one task could observe + * perf_rdpmc_allowed > 1 and return all the way back to + * userspace with CR4.PCE clear while another task is still + * doing on_each_cpu_mask() to propagate CR4.PCE. + * + * For now, this can't happen because all callers hold mmap_sem + * for write. If this changes, we'll need a different solution. + */ + lockdep_assert_held_exclusive(¤t->mm->mmap_sem); + if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1) on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); } -- cgit v1.2.3