Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1577332

Re: [PATCH] mm, page_alloc: only use per-cpu allocator for irq-safe requests -fix v2

From "Hillf Danton" <hillf.zj@alibaba-inc.com>
Newsgroups linux.kernel
Subject Re: [PATCH] mm, page_alloc: only use per-cpu allocator for irq-safe requests -fix v2
Date 2017-02-09 07:40 +0100
Message-ID <t8QyC-2vb-9@gated-at.bofh.it> (permalink)
References <t8DUK-33r-25@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On February 08, 2017 11:22 PM 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 <mgorman@techsingularity.net>
> ---
Thanks for fixing it.

Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>

>  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;
>  }
> 

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread


Thread

[PATCH] mm, page_alloc: only use per-cpu allocator for irq-safe  requests -fix v2 Mel Gorman <mgorman@techsingularity.net> - 2017-02-08 21:30 +0100
  Re: [PATCH] mm, page_alloc: only use per-cpu allocator for irq-safe requests -fix v2 "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2017-02-09 07:40 +0100

csiph-web