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 S1751457AbdB0RBM (ORCPT <rfc822;w@1wt.eu>);
        Mon, 27 Feb 2017 12:01:12 -0500
Received: from mail-it0-f41.google.com ([209.85.214.41]:37530 "EHLO
        mail-it0-f41.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1750971AbdB0RBL (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 27 Feb 2017 12:01:11 -0500
MIME-Version: 1.0
In-Reply-To: <20170227152516.GJ26504@dhcp22.suse.cz>
References: <201702260805.zhem8KFI%fengguang.wu@intel.com> <20170226043829.14270-1-tahsin@google.com>
 <20170227095258.GG14029@dhcp22.suse.cz> <CAAeU0aMaGa63Nj=JvZKKy82FftAT9dF56=gZsufDvrkqDSGUrw@mail.gmail.com>
 <20170227152516.GJ26504@dhcp22.suse.cz>
From: Tahsin Erdogan <tahsin@google.com>
Date: Mon, 27 Feb 2017 09:01:09 -0800
Message-ID: <CAAeU0aOCGrwmYGPWgA_7Y=2O2RXG_Ux14h4FrogpKPAKvVNaXg@mail.gmail.com>
Subject: Re: [PATCH v2 3/3] percpu: improve allocation success rate for
 non-GFP_KERNEL callers
To: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>, Christoph Lameter <cl@linux.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Chris Wilson <chris@chris-wilson.co.uk>,
        Andrey Ryabinin <aryabinin@virtuozzo.com>,
        Roman Pen <r.peniaev@gmail.com>,
        Joonas Lahtinen <joonas.lahtinen@linux.intel.com>,
        zijun_hu <zijun_hu@htc.com>, Joonsoo Kim <iamjoonsoo.kim@lge.com>,
        David Rientjes <rientjes@google.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Feb 27, 2017 at 7:25 AM, Michal Hocko <mhocko@kernel.org> wrote:
>         /*
>          * No space left.  Create a new chunk.  We don't want multiple
>          * tasks to create chunks simultaneously.  Serialize and create iff
>          * there's still no empty chunk after grabbing the mutex.
>          */
>         if (is_atomic)
>                 goto fail;
>
> right before pcpu_populate_chunk so is this actually a problem?

Yes, this prevents adding more pcpu chunks and so cause "atomic" allocations
to fail more easily.

>> By the way, I now noticed the might_sleep() in alloc_vmap_area() which makes
>> it unsafe to call vmalloc* in GFP_ATOMIC contexts. It was added recently:
>
> Do we call alloc_vmap_area from true atomic contexts (aka from under
> spinlocks etc)? I thought this was a nogo and GFP_NOWAIT resp.
> GFP_ATOMIC was more about optimistic request resp. access to memory
> reserves rather than true atomicity requirements.

In the call path that I am trying to fix, the caller uses GFP_NOWAIT mask.
The caller is holding a spinlock (request_queue->queue_lock) so we can't afford
to sleep.