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 9760AC25B46 for ; Mon, 23 Oct 2023 17:54:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230232AbjJWRyx (ORCPT ); Mon, 23 Oct 2023 13:54:53 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58264 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229613AbjJWRyw (ORCPT ); Mon, 23 Oct 2023 13:54:52 -0400 Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id F0C7BB4 for ; Mon, 23 Oct 2023 10:54:49 -0700 (PDT) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 8C882C433C8; Mon, 23 Oct 2023 17:54:49 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1698083689; bh=a7V+zADw60heqYS/j7vXZFg0binVGkYQy94rpuJfCZ8=; h=Date:To:From:Subject:From; b=S3kNbjr94iVSgzTHUTqus45nAI/BYXipDOsVBdwTZ+y1tKmya4sBStVLkEivEQv5F SXR/l/BLrJhRNChrqEmmb6NGvWdOsI3YGJwtKcem7GfOnhLv9aBcAQoAvt0Uel9ype Aa4CovPGfqpbLsEce97goVsVJRg+P053e78Ze74I= Date: Mon, 23 Oct 2023 10:54:48 -0700 To: mm-commits@vger.kernel.org, ebiederm@xmission.com, oleg@redhat.com, akpm@linux-foundation.org From: Andrew Morton Subject: + do_io_accounting-use-sig-stats_lock.patch added to mm-nonmm-unstable branch Message-Id: <20231023175449.8C882C433C8@smtp.kernel.org> Precedence: bulk Reply-To: linux-kernel@vger.kernel.org List-ID: X-Mailing-List: mm-commits@vger.kernel.org The patch titled Subject: do_io_accounting: use sig->stats_lock has been added to the -mm mm-nonmm-unstable branch. Its filename is do_io_accounting-use-sig-stats_lock.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/do_io_accounting-use-sig-stats_lock.patch This patch will later appear in the mm-nonmm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Oleg Nesterov Subject: do_io_accounting: use sig->stats_lock Date: Mon, 23 Oct 2023 17:34:05 +0200 Rather than lock_task_sighand(), sig->stats_lock was specifically designed for this type of use. This way the "if (whole)" branch runs lockless in the likely case. Link: https://lkml.kernel.org/r/20231023153405.GA4639@redhat.com Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton --- fs/proc/base.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) --- a/fs/proc/base.c~do_io_accounting-use-sig-stats_lock +++ a/fs/proc/base.c @@ -2973,7 +2973,6 @@ static const struct file_operations proc static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole) { struct task_io_accounting acct; - unsigned long flags; int result; result = down_read_killable(&task->signal->exec_update_lock); @@ -2985,15 +2984,24 @@ static int do_io_accounting(struct task_ goto out_unlock; } - if (whole && lock_task_sighand(task, &flags)) { + if (whole) { struct signal_struct *sig = task->signal; struct task_struct *t; + unsigned int seq = 1; + unsigned long flags; - acct = sig->ioac; - __for_each_thread(sig, t) - task_io_accounting_add(&acct, &t->ioac); + rcu_read_lock(); + do { + seq++; /* 2 on the 1st/lockless path, otherwise odd */ + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); - unlock_task_sighand(task, &flags); + acct = sig->ioac; + __for_each_thread(sig, t) + task_io_accounting_add(&acct, &t->ioac); + + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + rcu_read_unlock(); } else { acct = task->ioac; } _ Patches currently in -mm which might be from oleg@redhat.com are do_io_accounting-use-__for_each_thread.patch do_io_accounting-use-sig-stats_lock.patch