From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752352AbcGRLX5 (ORCPT ); Mon, 18 Jul 2016 07:23:57 -0400 Received: from mga11.intel.com ([192.55.52.93]:17436 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752331AbcGRLXx (ORCPT ); Mon, 18 Jul 2016 07:23:53 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.28,383,1464678000"; d="scan'208";a="1023866268" From: Alexander Shishkin To: Mathieu Poirier Cc: peterz@infradead.org, mingo@redhat.com, linux-kernel@vger.kernel.org Subject: Re: [PATCH RFC 2/3] perf/core: update filter only on executable mmap In-Reply-To: <1468621541-31024-3-git-send-email-mathieu.poirier@linaro.org> References: <1468621541-31024-1-git-send-email-mathieu.poirier@linaro.org> <1468621541-31024-3-git-send-email-mathieu.poirier@linaro.org> User-Agent: Notmuch/0.21 (http://notmuchmail.org) Emacs/24.5.1 (x86_64-pc-linux-gnu) Date: Mon, 18 Jul 2016 14:23:50 +0300 Message-ID: <874m7np4u1.fsf@ashishki-desk.ger.corp.intel.com> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Mathieu Poirier writes: > Function perf_event_mmap() is called by the MM subsystem each time > part of a binary is loaded in memory. There can be several mapping > for a binary, many times unrelated to the code section. > > Each time a section of a binary is mapped address filters are > updated, event when the map doesn't pertain to the code section. > The end result is that filters are configured based on the last map > event that was received rather than the last mapping of the code > segment. Good catch! I'd like to fix it in 4.7-stable as well; I think it's too late for 4.7 already. > Signed-off-by: Mathieu Poirier > --- > 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 df21611585d7..b9aa8f0ff070 100644 > --- a/kernel/events/core.c > +++ b/kernel/events/core.c > @@ -6604,7 +6604,8 @@ void perf_event_mmap(struct vm_area_struct *vma) > /* .flags (attr_mmap2 only) */ > }; > > - perf_addr_filters_adjust(vma); > + if ((vma->vm_flags & VM_EXEC) && (vma->vm_pgoff == 0)) > + perf_addr_filters_adjust(vma); You shouldn't need the vm_pgoff check; the range comparison logic in __perf_addr_filters_adjust() should already take it into account. Also, I'd put the check to perf_addr_filters_adjust() instead, with a comment that we don't do data-based filters yet or something along those lines. Thanks, -- Alex