linux-kernel - Re: [PATCH] mm: vmscan: handle isolated pages with lru lock released

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Sat, 14 Jan 2012 21:34:25 -0800 (PST)
From:	Hugh Dickins <hughd@...gle.com>
To:	Hillf Danton <dhillf@...il.com>
cc:	linux-mm@...ck.org, Rik van Riel <riel@...hat.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	David Rientjes <rientjes@...gle.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] mm: vmscan: handle isolated pages with lru lock
 released

On Sat, 14 Jan 2012, Hillf Danton wrote:
> 
> When shrinking inactive lru list, isolated pages are queued on locally private
> list, so the lock-hold time could be reduced if pages are counted without lock
> protection. To achive that, firstly updating reclaim stat is delayed until the
> putback stage, which is pointed out by Hugh, after reacquiring the lru lock.
> 
> Secondly operations related to vm and zone stats, are now proteced with
> preemption disabled as they are per-cpu operation.
> 
> Thanks for comments and ideas received.
> 
> 
> Signed-off-by: Hillf Danton <dhillf@...il.com>

Thank you, I like this a lot: it undoes a little of the cleanup I just
did, but for much better reason than I had.  I'm running with it now.

Acked-by: Hugh Dickins <hughd@...gle.com>

> ---
> 
> --- a/mm/vmscan.c	Sat Jan 14 14:02:20 2012
> +++ b/mm/vmscan.c	Sat Jan 14 20:00:46 2012
> @@ -1414,7 +1414,6 @@ update_isolated_counts(struct mem_cgroup
>  		       unsigned long *nr_anon,
>  		       unsigned long *nr_file)
>  {
> -	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
>  	struct zone *zone = mz->zone;
>  	unsigned int count[NR_LRU_LISTS] = { 0, };
>  	unsigned long nr_active = 0;
> @@ -1435,6 +1434,7 @@ update_isolated_counts(struct mem_cgroup
>  		count[lru] += numpages;
>  	}
> 
> +	preempt_disable();
>  	__count_vm_events(PGDEACTIVATE, nr_active);
> 
>  	__mod_zone_page_state(zone, NR_ACTIVE_FILE,
> @@ -1449,8 +1449,9 @@ update_isolated_counts(struct mem_cgroup
>  	*nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
>  	*nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
> 
> -	reclaim_stat->recent_scanned[0] += *nr_anon;
> -	reclaim_stat->recent_scanned[1] += *nr_file;
> +	__mod_zone_page_state(zone, NR_ISOLATED_ANON, *nr_anon);
> +	__mod_zone_page_state(zone, NR_ISOLATED_FILE, *nr_file);
> +	preempt_enable();
>  }
> 
>  /*
> @@ -1512,6 +1513,7 @@ shrink_inactive_list(unsigned long nr_to
>  	unsigned long nr_writeback = 0;
>  	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
>  	struct zone *zone = mz->zone;
> +	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
> 
>  	while (unlikely(too_many_isolated(zone, file, sc))) {
>  		congestion_wait(BLK_RW_ASYNC, HZ/10);
> @@ -1546,19 +1548,13 @@ shrink_inactive_list(unsigned long nr_to
>  			__count_zone_vm_events(PGSCAN_DIRECT, zone,
>  					       nr_scanned);
>  	}
> +	spin_unlock_irq(&zone->lru_lock);
> 
> -	if (nr_taken == 0) {
> -		spin_unlock_irq(&zone->lru_lock);
> +	if (nr_taken == 0)
>  		return 0;
> -	}
> 
>  	update_isolated_counts(mz, &page_list, &nr_anon, &nr_file);
> 
> -	__mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
> -	__mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
> -
> -	spin_unlock_irq(&zone->lru_lock);
> -
>  	nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority,
>  						&nr_dirty, &nr_writeback);
> 
> @@ -1570,6 +1566,9 @@ shrink_inactive_list(unsigned long nr_to
>  	}
> 
>  	spin_lock_irq(&zone->lru_lock);
> +
> +	reclaim_stat->recent_scanned[0] += nr_anon;
> +	reclaim_stat->recent_scanned[1] += nr_file;
> 
>  	if (current_is_kswapd())
>  		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/