In the presence of memoryless nodes, the workqueue code incorrectly uses
cpu_to_node() to determine what node to prefer memory allocations come
from. cpu_to_mem() should be used instead, which will use the nearest
NUMA node with memory.
Signed-off-by: Nishanth Aravamudan <nacc@xxxxxxxxxxxxxxxxxx>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 35974ac..0bba022 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3547,7 +3547,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
for_each_node(node) {
if (cpumask_subset(pool->attrs->cpumask,
wq_numa_possible_cpumask[node])) {
- pool->node = node;
+ /*
+ * We could use local_memory_node(node) here,
+ * but it is expensive and the following caches
+ * the same value.
+ */
+ pool->node = cpu_to_mem(cpumask_first(pool->attrs->cpumask));
break;
}
}
@@ -4921,7 +4926,7 @@ static int __init init_workqueues(void)
pool->cpu = cpu;
cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
pool->attrs->nice = std_nice[i++];
- pool->node = cpu_to_node(cpu);
+ pool->node = cpu_to_mem(cpu);
/* alloc pool ID */
mutex_lock(&wq_pool_mutex);
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>