sched: Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

When allocating space for load_balance_mask, in sched_init, when
CPUMASK_OFFSTACK is set, we've managed to spill over
KMALLOC_MAX_SIZE on our 6144 core machine.  The patch below
breaks up the allocations so that they don't overflow the max
alloc size.  It also allocates the masks on the the node from
which they'll most commonly be accessed, to minimize remote
accesses on NUMA machines.

Suggested-by: George Beshers <[email protected]>
Signed-off-by: Alex Thorlton <[email protected]>
Cc: George Beshers <[email protected]>
Cc: Russ Anderson <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Linus Torvalds <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

1 files changed, 5 insertions, 8 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b78add6..c0accc00566e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7113,9 +7113,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	alloc_size += num_possible_cpus() * cpumask_size();
-#endif
 	if (alloc_size) {
 		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
@@ -7135,13 +7132,13 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
+	}
 #ifdef CONFIG_CPUMASK_OFFSTACK
-		for_each_possible_cpu(i) {
-			per_cpu(load_balance_mask, i) = (void *)ptr;
-			ptr += cpumask_size();
-		}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
+	for_each_possible_cpu(i) {
+		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
+			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth,
 			global_rt_period(), global_rt_runtime());