Re: [patch 00/12] Slab defragmentation V3

[Christoph Lameter <clameter@sgi.com>]

On Fri, 8 Jun 2007, Michal Piotrowski wrote:

> 0xc1081630 is in list_locations (mm/slub.c:3388).
> 3383                    struct page *page;
> 3384
> 3385                    if (!atomic_read(&n->nr_slabs))
> 3386                            continue;
> 3387
> 3388                    spin_lock_irqsave(&n->list_lock, flags);
> 3389                    list_for_each_entry(page, &n->partial, lru)
> 3390                            process_slab(&t, s, page, alloc);
> 3391                    list_for_each_entry(page, &n->full, lru)
> 3392                            process_slab(&t, s, page, alloc);


Yes process slab needs some temporary data to generate the lists of 
functions calling etc and that is a GFP_TEMPORARY alloc.

Does this fix it?

---
 mm/slub.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Index: slub/mm/slub.c
===================================================================
--- slub.orig/mm/slub.c	2007-06-08 12:35:56.000000000 -0700
+++ slub/mm/slub.c	2007-06-08 12:37:32.000000000 -0700
@@ -2930,7 +2930,7 @@ static int alloc_loc_track(struct loc_tr
 
 	order = get_order(sizeof(struct location) * max);
 
-	l = (void *)__get_free_pages(GFP_TEMPORARY, order);
+	l = (void *)__get_free_pages(GFP_ATOMIC, order);
 
 	if (!l)
 		return 0;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/