padata: Dont scale the parallel objects with the cpus

Scaling the maximum number of objects in the parallel
codepath can lead to out of memory problems on bigsmp
machines.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/kernel/padata.c b/kernel/padata.c
index 0282478bc584a800dc08f8dbbc7d3e35ab675972..5085046d83fb5a5762838c91209d885e0ec950a9 100644 (file)
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -28,7 +28,7 @@
 #include <linux/rcupdate.h>
 
 #define MAX_SEQ_NR INT_MAX - NR_CPUS
-#define MAX_OBJ_NUM 10000 * NR_CPUS
+#define MAX_OBJ_NUM 1000
 
 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 {