[patch 18/87] mm: SLUB fix reclaim_state

From: Greg KH
Date: Tue Jun 09 2009 - 06:19:56 EST

2.6.29-stable review patch. If anyone has any objections, please let us know.


From: Nick Piggin <npiggin@xxxxxxx>

commit 1eb5ac6466d4be7b15b38ce3ab709600f1bc891f upstream.

SLUB does not correctly account reclaim_state.reclaimed_slab, so it will
break memory reclaim. Account it like SLAB does.

Cc: linux-mm@xxxxxxxxx
Cc: Matt Mackall <mpm@xxxxxxxxxxx>
Acked-by: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Nick Piggin <npiggin@xxxxxxx>
Signed-off-by: Pekka Enberg <penberg@xxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>

mm/slub.c | 3 +++
1 file changed, 3 insertions(+)

--- a/mm/slub.c
+++ b/mm/slub.c
@@ -9,6 +9,7 @@

#include <linux/mm.h>
+#include <linux/swap.h> /* struct reclaim_state */
#include <linux/module.h>
#include <linux/bit_spinlock.h>
#include <linux/interrupt.h>
@@ -1175,6 +1176,8 @@ static void __free_slab(struct kmem_cach

+ if (current->reclaim_state)
+ current->reclaim_state->reclaimed_slab += pages;
__free_pages(page, order);

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/