From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751654AbdBHRFQ (ORCPT ); Wed, 8 Feb 2017 12:05:16 -0500 Received: from Galois.linutronix.de ([146.0.238.70]:54321 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753651AbdBHREm (ORCPT ); Wed, 8 Feb 2017 12:04:42 -0500 Date: Wed, 8 Feb 2017 16:27:47 +0100 (CET) From: Thomas Gleixner To: Mel Gorman cc: Andrew Morton , Peter Zijlstra , Michal Hocko , Vlastimil Babka , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Ingo Molnar Subject: Re: [PATCH] mm, page_alloc: only use per-cpu allocator for irq-safe requests -fix v2 In-Reply-To: <20170208152200.ydlvia2c7lm7ln3t@techsingularity.net> Message-ID: References: <20170208152200.ydlvia2c7lm7ln3t@techsingularity.net> User-Agent: Alpine 2.20 (DEB 67 2015-01-07) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 8 Feb 2017, Mel Gorman wrote: > preempt_enable_no_resched() was used based on review feedback that had > no strong objection at the time. The thinking was that it avoided adding > a preemption point where one didn't exist before so the feedback was > applied. This reasoning was wrong. > > There was an indirect preemption point as explained by Thomas Gleixner where > an interrupt could set_need_resched() followed by preempt_enable being > a preemption point that matters. This use of preempt_enable_no_resched > is bad from both a mainline and RT perspective and a violation of the > preemption mechanism. Peter Zijlstra noted that "the only acceptable use > of preempt_enable_no_resched() is if the next statement is a schedule() > variant". > > The usage was outright broken and I should have stuck to preempt_enable() > as it was originally developed. It's known from previous tests > that there was no detectable difference to the performance by using > preempt_enable_no_resched(). > > This is a fix to the mmotm patch > mm-page_alloc-only-use-per-cpu-allocator-for-irq-safe-requests.patch > > Signed-off-by: Mel Gorman Reviewed-by: Thomas Gleixner > --- > mm/page_alloc.c | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index eaecb4b145e6..2a36dad03dac 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -2520,7 +2520,7 @@ void free_hot_cold_page(struct page *page, bool cold) > } > > out: > - preempt_enable_no_resched(); > + preempt_enable(); > } > > /* > @@ -2686,7 +2686,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, > __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); > zone_statistics(preferred_zone, zone); > } > - preempt_enable_no_resched(); > + preempt_enable(); > return page; > } > > > -- > Mel Gorman > SUSE Labs >