From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 2663 invoked by alias); 8 Oct 2005 11:31:36 -0000 Mailing-List: contact systemtap-help@sources.redhat.com; run by ezmlm Precedence: bulk List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sources.redhat.com Received: (qmail 2651 invoked by uid 22791); 8 Oct 2005 11:31:34 -0000 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: function probe point Date: Sat, 08 Oct 2005 11:31:00 -0000 Message-ID: <9FBCE015AF479F46B3B410499F3AE05B089743@pdsmsx405> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: function probe point Thread-Index: AcXL+9R5I8jVIVLqShikaVY31oqmCw== From: "Mao, Bibo" To: X-OriginalArrivalTime: 08 Oct 2005 11:31:31.0661 (UTC) FILETIME=[D4C187D0:01C5CBFB] X-Scanned-By: MIMEDefang 2.52 on 10.7.209.17 X-SW-Source: 2005-q4/txt/msg00024.txt.bz2 Hi, I view systemtap source code, and by the notation and test, I find that kretprobe function probe point is based on the entry pc of this function, but for kprobe function probe point it is based on the prologue-end of this function.=20 I ever objdumped vmlinux, and found that in IA32, EM64T platform kprobe function probe point is based on prologue-end place, a pointer after the function's frame has been set up. But in IA64 platform, the function kprobe point always is entry point plus 1. I do not know why. Any suggestion is welcome. Regards Bibo,mao