From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:47106) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1g9SI0-0006AK-Qx for qemu-devel@nongnu.org; Mon, 08 Oct 2018 05:57:27 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1g9S2v-0006jw-0d for qemu-devel@nongnu.org; Mon, 08 Oct 2018 05:41:52 -0400 Received: from mail-wr1-x444.google.com ([2a00:1450:4864:20::444]:39096) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1g9S2u-0006jH-PX for qemu-devel@nongnu.org; Mon, 08 Oct 2018 05:41:48 -0400 Received: by mail-wr1-x444.google.com with SMTP id 61-v6so19291026wrb.6 for ; Mon, 08 Oct 2018 02:41:47 -0700 (PDT) References: <20181005154910.3099-1-alex.bennee@linaro.org> <20181005154910.3099-5-alex.bennee@linaro.org> <20181007014216.GC23787@flamenco> From: Alex =?utf-8?Q?Benn=C3=A9e?= In-reply-to: <20181007014216.GC23787@flamenco> Date: Mon, 08 Oct 2018 10:41:45 +0100 Message-ID: <877eisojvq.fsf@linaro.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [RFC PATCH 04/21] trace: enable the exec_tb trace events List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Emilio G. Cota" Cc: qemu-devel@nongnu.org, Pavel.Dovgaluk@ispras.ru, vilanova@ac.upc.edu, Paolo Bonzini , Peter Crosthwaite , Richard Henderson Emilio G. Cota writes: > On Fri, Oct 05, 2018 at 16:48:53 +0100, Alex Benn=C3=A9e wrote: >> Our performance isn't so critical that we can't spare a simple flag >> check when we exec a TB considering everything else we check in the >> outer loop. > > [I know this is just done to illustrate how function names > in plugins can bind to tracing calls, but someone might > get confused by expecting more from "exec_tb" than it > actually does.] > > This flag check costs nothing because "exec_tb" is > almost never called. The way it works right now, we > need -d nochain for "exec_tb" to actually generate > an event every time a TB executes. I'll reword the commit a bit. > IMO an eventual plugin API should let plugins decide whether > to subscribe to the execution of a particular TB, when > said TB is being translated, instead of providing > an all-or-nothing switch. Well we will want pre/post instruction translation hooks which would be the obvious place to add this. Using -d nochain is a useful enough hack for now. > > Thanks, > > E. -- Alex Benn=C3=A9e