Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 8 Apr 2021 12:52:07 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Mel Gorman <mgorman@techsingularity.net>
Cc:     Linux-MM <linux-mm@kvack.org>,
        Linux-RT-Users <linux-rt-users@vger.kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Chuck Lever <chuck.lever@oracle.com>,
        Jesper Dangaard Brouer <brouer@redhat.com>,
        Matthew Wilcox <willy@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@kernel.org>,
        Michal Hocko <mhocko@kernel.org>,
        Oscar Salvador <osalvador@suse.de>
Subject: Re: [PATCH 02/11] mm/page_alloc: Convert per-cpu list protection to
 local_lock
Message-ID: <YG7gV7yAEEjOcQZY@hirez.programming.kicks-ass.net>
References: <20210407202423.16022-1-mgorman@techsingularity.net>
 <20210407202423.16022-3-mgorman@techsingularity.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210407202423.16022-3-mgorman@techsingularity.net>
Precedence: bulk

On Wed, Apr 07, 2021 at 09:24:14PM +0100, Mel Gorman wrote:
> There is a lack of clarity of what exactly local_irq_save/local_irq_restore
> protects in page_alloc.c . It conflates the protection of per-cpu page
> allocation structures with per-cpu vmstat deltas.
> 
> This patch protects the PCP structure using local_lock which for most
> configurations is identical to IRQ enabling/disabling.  The scope of the
> lock is still wider than it should be but this is decreased laster.

> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index a4393ac27336..106da8fbc72a 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h

> @@ -337,6 +338,7 @@ enum zone_watermarks {
>  #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
>  #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
>  
> +/* Fields and list protected by pagesets local_lock in page_alloc.c */
>  struct per_cpu_pages {
>  	int count;		/* number of pages in the list */
>  	int high;		/* high watermark, emptying needed */

> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index a68bacddcae0..e9e60d1a85d4 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -112,6 +112,13 @@ typedef int __bitwise fpi_t;
>  static DEFINE_MUTEX(pcp_batch_high_lock);
>  #define MIN_PERCPU_PAGELIST_FRACTION	(8)
>  
> +struct pagesets {
> +	local_lock_t lock;
> +};
> +static DEFINE_PER_CPU(struct pagesets, pagesets) = {
> +	.lock = INIT_LOCAL_LOCK(lock),
> +};

So why isn't the local_lock_t in struct per_cpu_pages ? That seems to be
the actual object that is protected by it and is already per-cpu.

Is that because you want to avoid the duplication across zones? Is that
worth the effort?