From mboxrd@z Thu Jan 1 00:00:00 1970 From: Masami Hiramatsu Subject: Re: [PATCH v4 2/9] perf/core: open access for CAP_SYS_PERFMON privileged process Date: Sun, 12 Jan 2020 10:44:46 +0900 Message-ID: <20200112104446.f667df82b061dfb9c7a6bdce@kernel.org> References: <20200108160713.GI2844@hirez.programming.kicks-ass.net> <20200110140234.GO2844@hirez.programming.kicks-ass.net> <20200111005213.6dfd98fb36ace098004bde0e@kernel.org> <20200110164531.GA2598@kernel.org> <20200111084735.0ff01c758bfbfd0ae2e1f24e@kernel.org> <2B79131A-3F76-47F5-AAB4-08BCA820473F@fb.com> <5e191833.1c69fb81.8bc25.a88c@mx.google.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <5e191833.1c69fb81.8bc25.a88c@mx.google.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" To: arnaldo.melo@gmail.com Cc: Mark Rutland , Song Liu , Peter Zijlstra , Benjamin Herrenschmidt , Will Deacon , Alexei Starovoitov , Stephane Eranian , james.bottomley@hansenpartnership.com, Paul Mackerras , Jiri Olsa , Andi Kleen , Michael Ellerman , Igor Lubashev , James Morris , Alexander Shishkin , Ingo Molnar , "oprofile-list@lists.sf.net" , Serge Hallyn , Robert Richter , Kees Cook , Jann Horn , "selinux@vger.kernel.org" , intel-gfx@lists.freedesktop List-Id: linux-perf-users.vger.kernel.org On Fri, 10 Jan 2020 21:35:12 -0300 arnaldo.melo@gmail.com wrote: > ,Jann Horn ,Thomas Gleixner ,Tvrtko Ursulin ,Lionel Landwerlin ,linux-kernel ,"linux-security-module@vger.kernel.org" ,"selinux@vger.kernel.org" ,"intel-gfx@lists.freedesktop.org" ,"bpf@vger.kernel.org" ,"linux-parisc@vger.kernel.org" ,"linuxppc-dev@lists.ozlabs.org" ,"linux-perf-users@vger.kernel.org" ,"linux-arm-kernel@lists.infradead.org" ,"oprofile-list@lists.sf.net" > From: Arnaldo Carvalho de Melo > Message-ID: > > On January 10, 2020 9:23:27 PM GMT-03:00, Song Liu wrote: > > > > > >> On Jan 10, 2020, at 3:47 PM, Masami Hiramatsu > >wrote: > >> > >> On Fri, 10 Jan 2020 13:45:31 -0300 > >> Arnaldo Carvalho de Melo wrote: > >> > >>> Em Sat, Jan 11, 2020 at 12:52:13AM +0900, Masami Hiramatsu escreveu: > >>>> On Fri, 10 Jan 2020 15:02:34 +0100 Peter Zijlstra > > wrote: > >>>>> Again, this only allows attaching to previously created kprobes, > >it does > >>>>> not allow creating kprobes, right? > >>> > >>>>> That is; I don't think CAP_SYS_PERFMON should be allowed to create > >>>>> kprobes. > >>> > >>>>> As might be clear; I don't actually know what the user-ABI is for > >>>>> creating kprobes. > >>> > >>>> There are 2 ABIs nowadays, ftrace and ebpf. perf-probe uses ftrace > >interface to > >>>> define new kprobe events, and those events are treated as > >completely same as > >>>> tracepoint events. On the other hand, ebpf tries to define new > >probe event > >>>> via perf_event interface. Above one is that interface. IOW, it > >creates new kprobe. > >>> > >>> Masami, any plans to make 'perf probe' use the perf_event_open() > >>> interface for creating kprobes/uprobes? > >> > >> Would you mean perf probe to switch to perf_event_open()? > >> No, perf probe is for setting up the ftrace probe events. I think we > >can add an > >> option to use perf_event_open(). But current kprobe creation from > >perf_event_open() > >> is separated from ftrace by design. > > > >I guess we can extend event parser to understand kprobe directly. > >Instead of > > > > perf probe kernel_func > > perf stat/record -e probe:kernel_func ... > > > >We can just do > > > > perf stat/record -e kprobe:kernel_func ... > > > You took the words from my mouth, exactly, that is a perfect use case, an alternative to the 'perf probe' one of making a disabled event that then gets activated via record/stat/trace, in many cases it's better, removes the explicit probe setup case. Ah, I got it. If the perf event parser just kicks perf's kprobe creation interface, it will be easy. In that case, there should be following differences. - perf * -e "kprobe":kernel_func will put a local (hidden) kprobe events. So ftrace user can not access it. - perf * -e "kprobe":kernel_func may not support inline/function-body nor trace local variables etc. Hm, if we support inline function via -e "kprobe" interface, we have to expand perf_event_open() to support multi-probe event. Thanks, > > Regards, > > - Arnaldo > > > > >Thanks, > >Song > -- Masami Hiramatsu