From mboxrd@z Thu Jan 1 00:00:00 1970 From: Namhyung Kim Subject: Re: Fw: Re: Re: Howto make perf probe work Date: Thu, 04 Apr 2013 15:05:54 +0900 Message-ID: <876202esot.fsf@sejong.aot.lge.com> References: <201304010130139026692@gmail.com> <201304012320294652937@gmail.com> <201304012324395211298@gmail.com> <201304021710591525728@gmail.com> <201304040128323646722@gmail.com> Mime-Version: 1.0 Content-Type: text/plain Return-path: Received: from LGEMRELSE7Q.lge.com ([156.147.1.151]:57383 "EHLO LGEMRELSE7Q.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756556Ab3DDGF4 (ORCPT ); Thu, 4 Apr 2013 02:05:56 -0400 In-Reply-To: <201304040128323646722@gmail.com> (osdepend@gmail.com's message of "Thu, 4 Apr 2013 01:28:34 +0800") Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: OSDepend Cc: linux-perf-users , nelakurthi koteswararao Hi, On Thu, 4 Apr 2013 01:28:34 +0800, OSDepend wrote: >> On Tue, 2 Apr 2013 17:11:01 +0800, OSDepend wrote: >> >> For some reason, do_page_fault() is marked as __kprobe on some arch >> >> which means it cannot be probed. >> > >> > My kernel is runing on X86_64 arch, is there any chance for me to get the do_page_fault() entry/exit work? >> nope, AFAIK. > Is there any guide for us to decide which tracepoint (or other kernel symbol) canbe used, and which cannot? > For some of the kallsyms cannot be used directly. Such as do_raw_spin_lock. > perf probe -a test=do_raw_spin_lock > Fatal: Kernel symbol 'do_raw_spin_lock' not found - probe not added. Hmm.. it seems not, currently. Maybe we can change perf to output the symbol was not able to be probed after checking symbol address and it's between __kprobes_text_{start,end}. I'll take a look at it later. Thanks, Namhyung