From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <SRS0=j30r=B4=vger.kernel.org=bpf-owner@kernel.org>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on
	aws-us-west-2-korg-lkml-1.web.codeaurora.org
X-Spam-Level: 
X-Spam-Status: No, score=-3.8 required=3.0 tests=BAYES_00,
	HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS
	autolearn=no autolearn_force=no version=3.4.0
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id D7D9DC433E1
	for <bpf@archiver.kernel.org>; Tue, 18 Aug 2020 02:23:07 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id B15E4206DA
	for <bpf@archiver.kernel.org>; Tue, 18 Aug 2020 02:23:07 +0000 (UTC)
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1726328AbgHRCXE (ORCPT <rfc822;bpf@archiver.kernel.org>);
        Mon, 17 Aug 2020 22:23:04 -0400
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50798 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1726303AbgHRCXE (ORCPT <rfc822;bpf@vger.kernel.org>);
        Mon, 17 Aug 2020 22:23:04 -0400
Received: from ZenIV.linux.org.uk (zeniv.linux.org.uk [IPv6:2002:c35c:fd02::1])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A83A0C061389;
        Mon, 17 Aug 2020 19:23:03 -0700 (PDT)
Received: from viro by ZenIV.linux.org.uk with local (Exim 4.92.3 #3 (Red Hat Linux))
        id 1k7rGz-0004QP-Sn; Tue, 18 Aug 2020 02:22:49 +0000
Date:   Tue, 18 Aug 2020 03:22:49 +0100
From:   Al Viro <viro@zeniv.linux.org.uk>
To:     "Eric W. Biederman" <ebiederm@xmission.com>
Cc:     linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        criu@openvz.org, bpf@vger.kernel.org,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Christian Brauner <christian.brauner@ubuntu.com>,
        Oleg Nesterov <oleg@redhat.com>,
        Cyrill Gorcunov <gorcunov@gmail.com>,
        Jann Horn <jann@thejh.net>, Kees Cook <keescook@chromium.org>,
        Daniel =?iso-8859-1?Q?P=2E_Berrang=E9?= <berrange@redhat.com>,
        Jeff Layton <jlayton@redhat.com>,
        Miklos Szeredi <miklos@szeredi.hu>,
        Matthew Wilcox <willy@debian.org>,
        "J. Bruce Fields" <bfields@fieldses.org>,
        Matthew Wilcox <matthew@wil.cx>,
        Trond Myklebust <trond.myklebust@fys.uio.no>,
        Chris Wright <chrisw@redhat.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Martin KaFai Lau <kafai@fb.com>,
        Song Liu <songliubraving@fb.com>, Yonghong Song <yhs@fb.com>,
        Andrii Nakryiko <andriin@fb.com>,
        John Fastabend <john.fastabend@gmail.com>,
        KP Singh <kpsingh@chromium.org>
Subject: Re: [PATCH 10/17] proc/fd: In proc_readfd_common use fnext_task
Message-ID: <20200818022249.GC1236603@ZenIV.linux.org.uk>
References: <87ft8l6ic3.fsf@x220.int.ebiederm.org>
 <20200817220425.9389-10-ebiederm@xmission.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200817220425.9389-10-ebiederm@xmission.com>
Sender: bpf-owner@vger.kernel.org
Precedence: bulk
List-ID: <bpf.vger.kernel.org>
X-Mailing-List: bpf@vger.kernel.org

On Mon, Aug 17, 2020 at 05:04:18PM -0500, Eric W. Biederman wrote:
> When discussing[1] exec and posix file locks it was realized that none
> of the callers of get_files_struct fundamentally needed to call
> get_files_struct, and that by switching them to helper functions
> instead it will both simplify their code and remove unnecessary
> increments of files_struct.count.  Those unnecessary increments can
> result in exec unnecessarily unsharing files_struct which breaking
> posix locks, and it can result in fget_light having to fallback to
> fget reducing system performance.
> 
> Using fnext_task simplifies proc_readfd_common, by moving the checking
> for the maximum file descritor into the generic code, and by
> remvoing the need for capturing and releasing a reference on
> files_struct.

Yecchhh...  So you keep locking/unlocking the damn thing for each
descriptor?