Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1750950AbdGYS1v (ORCPT <rfc822;w@1wt.eu>);
        Tue, 25 Jul 2017 14:27:51 -0400
Received: from mail-qt0-f196.google.com ([209.85.216.196]:34555 "EHLO
        mail-qt0-f196.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751502AbdGYS10 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 25 Jul 2017 14:27:26 -0400
Date: Tue, 25 Jul 2017 14:27:24 -0400
From: Josef Bacik <josef@toxicpanda.com>
To: Dennis Zhou <dennisz@fb.com>
Cc: Tejun Heo <tj@kernel.org>, Christoph Lameter <cl@linux.com>,
        Josef Bacik <josef@toxicpanda.com>, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, kernel-team@fb.com,
        Dennis Zhou <dennisszhou@gmail.com>
Subject: Re: [PATCH v2 10/23] percpu: change the number of pages marked in
 the first_chunk pop bitmap
Message-ID: <20170725182723.GJ18880@destiny>
References: <20170724230220.21774-1-dennisz@fb.com>
 <20170724230220.21774-11-dennisz@fb.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20170724230220.21774-11-dennisz@fb.com>
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
Content-Length: 1219
Lines: 27

On Mon, Jul 24, 2017 at 07:02:07PM -0400, Dennis Zhou wrote:
> From: "Dennis Zhou (Facebook)" <dennisszhou@gmail.com>
> 
> The populated bitmap represents the state of the pages the chunk serves.
> Prior, the bitmap was marked completely used as the first chunk was
> allocated and immutable. This is misleading because the first chunk may
> not be completely filled. Additionally, with moving the base_addr up in
> the previous patch, the population check no longer corresponds to what
> was being checked.
> 
> This patch modifies the population map to be only the number of pages
> the region serves and to make what it was checking correspond correctly
> again. The change is to remove any misunderstanding between the size of
> the populated bitmap and the actual size of it. The work function page
> iterators now use nr_pages for the check rather than pcpu_unit_pages
> because nr_populated is now chunk specific. Without this, the work
> function would try to populate the remainder of these chunks despite it
> not serving any more than nr_pages when nr_pages is set less than
> pcpu_unit_pages.
> 
> Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>

Reviewed-by: Josef Bacik <jbacik@fb.com>

Thanks,

Josef