From mboxrd@z Thu Jan 1 00:00:00 1970 From: Steven Rostedt Subject: Re: [PATCH -tip v3 00/23] kprobes: introduce NOKPROBE_SYMBOL() and general cleaning of kprobe blacklist Date: Wed, 20 Nov 2013 12:56:49 -0500 Message-ID: <20131120125649.40ca99c3@gandalf.local.home> References: <20131120042148.15296.88360.stgit@kbuild-fedora.novalocal> <20131120153801.GA9743@gmail.com> <20131120173600.GK8993@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: Received: from cdptpa-outbound-snat.email.rr.com ([107.14.166.225]:58884 "EHLO cdptpa-oedge-vip.email.rr.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754649Ab3KTR4x (ORCPT ); Wed, 20 Nov 2013 12:56:53 -0500 In-Reply-To: <20131120173600.GK8993@redhat.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: "Frank Ch. Eigler" Cc: Ingo Molnar , Masami Hiramatsu , linux-arch@vger.kernel.org, Ananth N Mavinakayanahalli , Sandeepa Prabhu , x86@kernel.org, lkml , virtualization@lists.linux-foundation.org, systemtap@sourceware.org, "David S. Miller" On Wed, 20 Nov 2013 12:36:00 -0500 "Frank Ch. Eigler" wrote: > Hi - > > > > Does this new blacklist cover enough that the kernel now survives a > > > broadly wildcarded perf-probe, e.g. over e.g. all of its kallsyms? > > > > That's generally the purpose of the annotations - if it doesn't then > > that's a bug. > > AFAIK, no kernel since kprobes was introduced has ever stood up to > that test. perf probe lacks the wildcarding powers of systemtap, so > one needs to resort to something like: > > # cat /proc/kallsyms | grep ' [tT] ' | while read addr type symbol; do > perf probe $symbol > done I'm curious to why one would do that. IIUC, perf now has function tracing support. -- Steve > > then wait for a few hours for that to finish. Then, or while the loop > is still running, run > > # perf record -e 'probe:*' -aR sleep 1 > > to take a kernel down. > > > - FChE