From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S933442AbdCWJAt (ORCPT <rfc822;w@1wt.eu>);
        Thu, 23 Mar 2017 05:00:49 -0400
Received: from mail-pg0-f66.google.com ([74.125.83.66]:36527 "EHLO
        mail-pg0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S933361AbdCWJAr (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 23 Mar 2017 05:00:47 -0400
Date: Thu, 23 Mar 2017 18:00:42 +0900
From: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
To: Petr Mladek <pmladek@suse.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Peter Zijlstra <peterz@infradead.org>,
        "Rafael J . Wysocki" <rjw@rjwysocki.net>, linux-kernel@vger.kernel.org,
        Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Subject: Re: [RFC][PATCH 2/4] printk: offload printing from
 wake_up_klogd_work_func()
Message-ID: <20170323090042.GA376@jagdpanzerIV.localdomain>
References: <20170306124554.828-1-sergey.senozhatsky@gmail.com>
 <20170306124554.828-3-sergey.senozhatsky@gmail.com>
 <20170317121944.GO3977@pathway.suse.cz>
 <20170318095738.GA398@jagdpanzerIV.localdomain>
 <20170320160928.GT3977@pathway.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20170320160928.GT3977@pathway.suse.cz>
User-Agent: Mutt/1.8.0 (2017-02-23)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On (03/20/17 17:09), Petr Mladek wrote:
[..]
> 
> BTW: wake_up_klogd_work does not need to be per-CPU as well.
> irq_work infrastructure heavily uses per-CPU variables.
> But a global struct irq_work is safe, see irq_work_claim().

so I have a patch that turns wake_up_klogd_work into a global variable,
out of curiosity, but I'm not entire sure about it. the sort of a problem
is that queued irq_works still go into a per-CPU run_lists.  per-CPU
wake_up_klogd_work permits us to queue irq work on several CPUs so we
might have better chances to execute wake_up_klogd_work_func(), while
global wake_up_klogd_work will be only in one run_list. this can defer
wake_up_klogd_work processing until that particular single CPU handles
its interrupt and calls irq_work_run_list(). what do you think?

	-ss