From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3929AC76188 for ; Wed, 5 Apr 2023 13:21:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S238167AbjDENVA (ORCPT ); Wed, 5 Apr 2023 09:21:00 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35044 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237944AbjDENU6 (ORCPT ); Wed, 5 Apr 2023 09:20:58 -0400 Received: from dfw.source.kernel.org (dfw.source.kernel.org [139.178.84.217]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 30B951FFD; Wed, 5 Apr 2023 06:20:57 -0700 (PDT) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id BEDAE63761; Wed, 5 Apr 2023 13:20:56 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id E66BDC4339B; Wed, 5 Apr 2023 13:20:55 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1680700856; bh=QIhxJxgeabElsKbsT4Kwv+/L8XzSVixHmAIIkwb8yxs=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=XtnsDQmkv7UQzCCCuyXer91QTOIhbSTDFLrx9ooPRpxwbbQhM7JipVUkO9NwLwM7p +AZ/a8LK7zPC5dPZ2WA1kHPC/OqJOuC28VeYmEenGeyMUAcFKdQ+8cdxGy9naL5bUn C75sfNFcEleIG7pv6b08Ja5/v4TcVY9mFuC1nHVEVb6mORPA2u/gD2mtB2icD3DSL2 u6RbnHVIdjEy+YdV3ZTLr3DgDVMm8bBf9U/PsKuvg8EJ5hrLtPa6bftzBWQMsW0VTY x5apGxE56qwrWZug4wb3u7mzh4Elk2ymvnIq8GRqM61FEtuXg5GSKpr0/4UrJNX0qF yvzcLTruJUDfw== Received: by quaco.ghostprotocols.net (Postfix, from userid 1000) id 3D31A4052D; Wed, 5 Apr 2023 10:20:53 -0300 (-03) Date: Wed, 5 Apr 2023 10:20:53 -0300 From: Arnaldo Carvalho de Melo To: Adrian Hunter Cc: Ian Rogers , Peter Zijlstra , Ingo Molnar , Mark Rutland , Alexander Shishkin , Jiri Olsa , Namhyung Kim , Thomas Gleixner , Darren Hart , Davidlohr Bueso , James Clark , John Garry , Riccardo Mancini , Yury Norov , Andy Shevchenko , Andrew Morton , Leo Yan , Andi Kleen , Thomas Richter , Kan Liang , Madhavan Srinivasan , Shunsuke Nakamura , Song Liu , Masami Hiramatsu , Steven Rostedt , Miaoqian Lin , Stephen Brennan , Kajol Jain , Alexey Bayduraev , German Gomez , linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, Eric Dumazet , Dmitry Vyukov , Hao Luo , Stephane Eranian Subject: Re: [PATCH v5 00/17] Reference count checker and related fixes Message-ID: References: <20230320212248.1175731-1-irogers@google.com> <7443d427-783b-44b6-85e6-5e667bb83a94@intel.com> <527b8bcb-d462-5fff-5310-703b55902a61@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <527b8bcb-d462-5fff-5310-703b55902a61@intel.com> X-Url: http://acmel.wordpress.com Precedence: bulk List-ID: X-Mailing-List: linux-perf-users@vger.kernel.org Em Wed, Apr 05, 2023 at 11:47:26AM +0300, Adrian Hunter escreveu: > On 4/04/23 21:54, Arnaldo Carvalho de Melo wrote: > > Em Tue, Apr 04, 2023 at 03:41:38PM -0300, Arnaldo Carvalho de Melo escreveu: > >> Em Tue, Apr 04, 2023 at 08:25:41PM +0300, Adrian Hunter escreveu: > >>> On 4/04/23 18:58, Ian Rogers wrote: > >>>> Ping. It would be nice to have this landed or at least the first 10 > >>>> patches that refactor the map API and are the bulk of the > >>>> lines-of-code changed. Having those landed would make it easier to > >>>> rebase in the future, but I also think the whole series is ready to > >>>> go. > >>> > >>> I was wondering if the handling of dynamic data like struct map makes > >>> any sense at present. Perhaps someone can reassure me. > >>> > >>> A struct map can be updated when an MMAP event is processed. So it > >> > >> Yes, it can, and the update is made via a new PERF_RECORD_MMAP, right? > >> > >> So: > >> > >> perf_event__process_mmap() > >> machine__process_mmap2_event() > >> map__new() + thread__insert_map(thread, map) > >> maps__fixup_overlappings() > >> maps__insert(thread->maps, map); > >> > >> Ok, from this point on new samples on ] map->start .. map->end ] will > >> grab a refcount to this new map in its hist_entry, right? > >> > >> When we want to sort by dso we will look at hist_entry->map->dso, etc. > > > > And in 'perf top' we go decaying hist entries, when we delete the > > hist_entry, drop the reference count to things it holds, that will then > > be finally deleted when no more hist_entries point to it. > > > >>> seems like anything racing with event processing is already broken, and > >>> reference counting / locking cannot help - unless there is also > >>> copy-on-write (which there isn't at present)? > So I checked, and struct map *is* copy-on-write in > maps__fixup_overlappings(), so that should not be a problem. > >>> For struct maps, referencing it while simultaneously processing > >>> events seems to make even less sense? > >> Can you elaborate some more? > Only that the maps are not necessarily stable e.g. the map that you > need has been replaced in the meantime. Well, it may be sliced in several or shrunk by new ones overlapping it, but it if completely disappears, say a new map starts before the one disappearing and ends after it, then it remains with reference counts if there are hist_entries (or other data structure) pointing to them, right? > But upon investigation, the only user at the moment is > maps__find_ams(). If we kept the removed maps (we used to), > it might be possible to make maps__find_ams() work correctly > in any case. Humm, I think I see what you mean, maps__find_ams() is called when we are annotating a symbol, not when we're processing a sample, so it may be the case that at the time of annotation the executable that is being found (its parsing the target IP of a 'call' assembly instruction) was replaced, is that the case? - Arnaldo