linux-kernel - Re: [PATCH] mm: don't invoke __alloc_pages_direct

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]

Message-ID: <20120706155920.GA7721@barrios>
Date:	Sat, 7 Jul 2012 00:59:20 +0900
From:	Minchan Kim <minchan@...nel.org>
To:	Joonsoo Kim <js1304@...il.com>
Cc:	akpm@...ux-foundation.org, Pekka Enberg <penberg@...nel.org>,
	Christoph Lameter <cl@...ux-foundation.org>,
	linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH] mm: don't invoke __alloc_pages_direct_compact when order
 0

Hi Joonsoo,

On Sat, Jul 07, 2012 at 12:28:41AM +0900, Joonsoo Kim wrote:
> __alloc_pages_direct_compact has many arguments so invoking it is very costly.

It's already slow path so it's pointless for such optimization.

> And in almost invoking case, order is 0, so return immediately.

You can't make sure it.

> 
> Let's not invoke it when order 0

Let's not ruin git blame.

> 
> Signed-off-by: Joonsoo Kim <js1304@...il.com>
> 
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 6092f33..f4039aa 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -2056,7 +2056,10 @@ out:
>  }
>  
>  #ifdef CONFIG_COMPACTION
> -/* Try memory compaction for high-order allocations before reclaim */
> +/*
> + * Try memory compaction for high-order allocations before reclaim
> + * Must be called with order > 0
> + */
>  static struct page *
>  __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
>  	struct zonelist *zonelist, enum zone_type high_zoneidx,
> @@ -2067,8 +2070,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
>  {
>  	struct page *page;
>  
> -	if (!order)
> -		return NULL;
> +	BUG_ON(!order);
>  
>  	if (compaction_deferred(preferred_zone, order)) {
>  		*deferred_compaction = true;
> @@ -2363,15 +2365,17 @@ rebalance:
>  	 * Try direct compaction. The first pass is asynchronous. Subsequent
>  	 * attempts after direct reclaim are synchronous
>  	 */
> -	page = __alloc_pages_direct_compact(gfp_mask, order,
> -					zonelist, high_zoneidx,
> -					nodemask,
> -					alloc_flags, preferred_zone,
> -					migratetype, sync_migration,
> -					&deferred_compaction,
> -					&did_some_progress);
> -	if (page)
> -		goto got_pg;
> +	if (unlikely(order)) {
> +		page = __alloc_pages_direct_compact(gfp_mask, order,
> +						zonelist, high_zoneidx,
> +						nodemask,
> +						alloc_flags, preferred_zone,
> +						migratetype, sync_migration,
> +						&deferred_compaction,
> +						&did_some_progress);
> +		if (page)
> +			goto got_pg;
> +	}
>  	sync_migration = true;
>  
>  	/*
> @@ -2446,15 +2450,17 @@ rebalance:
>  		 * direct reclaim and reclaim/compaction depends on compaction
>  		 * being called after reclaim so call directly if necessary
>  		 */
> -		page = __alloc_pages_direct_compact(gfp_mask, order,
> -					zonelist, high_zoneidx,
> -					nodemask,
> -					alloc_flags, preferred_zone,
> -					migratetype, sync_migration,
> -					&deferred_compaction,
> -					&did_some_progress);
> -		if (page)
> -			goto got_pg;
> +		if (unlikely(order)) {
> +			page = __alloc_pages_direct_compact(gfp_mask, order,
> +						zonelist, high_zoneidx,
> +						nodemask,
> +						alloc_flags, preferred_zone,
> +						migratetype, sync_migration,
> +						&deferred_compaction,
> +						&did_some_progress);
> +			if (page)
> +				goto got_pg;
> +		}
>  	}
>  
>  nopage:
> -- 
> 1.7.9.5
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@...ck.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@...ck.org"> email@...ck.org </a>
--
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/