[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1ddfd892-cf15-f7ca-4649-c3bb11682ce0@suse.cz>
Date: Wed, 18 Oct 2017 14:54:02 +0200
From: Vlastimil Babka <vbabka@...e.cz>
To: David Rientjes <rientjes@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>
Cc: Christoph Lameter <cl@...ux.com>,
Joonsoo Kim <iamjoonsoo.kim@....com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Mel Gorman <mgorman@...hsingularity.net>
Subject: Re: [patch] mm, slab: only set __GFP_RECLAIMABLE once
+CC Mel who added that code (long time ago though :) in case he
remembers some catch.
On 10/18/2017 12:30 AM, David Rientjes wrote:
> SLAB_RECLAIM_ACCOUNT is a permanent attribute of a slab cache. Set
> __GFP_RECLAIMABLE as part of its ->allocflags rather than check the cachep
> flag on every page allocation.
>
> Signed-off-by: David Rientjes <rientjes@...gle.com>
Seems correct to me, and SLUB does that this way too, since the beginning.
Acked-by: Vlastimil Babka <vbabka@...e.cz>
> ---
> mm/slab.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/mm/slab.c b/mm/slab.c
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -1409,8 +1409,6 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
> int nr_pages;
>
> flags |= cachep->allocflags;
> - if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
> - flags |= __GFP_RECLAIMABLE;
>
> page = __alloc_pages_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
> if (!page) {
> @@ -2143,6 +2141,8 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
> cachep->allocflags = __GFP_COMP;
> if (flags & SLAB_CACHE_DMA)
> cachep->allocflags |= GFP_DMA;
> + if (flags & SLAB_RECLAIM_ACCOUNT)
> + cachep->allocflags |= __GFP_RECLAIMABLE;
> cachep->size = size;
> cachep->reciprocal_buffer_size = reciprocal_value(size);
>
>
> --
> 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>
>
Powered by blists - more mailing lists