mm: sched: numa: Control enabling and disabling of NUMA balancing

This patch adds Kconfig options and kernel parameters to allow the
enabling and disabling of automatic NUMA balancing. The existance
of such a switch was and is very important when debugging problems
related to transparent hugepages and we should have the same for
automatic NUMA placement.

Signed-off-by: Mel Gorman <mgorman@suse.de>

3 files changed, 40 insertions, 17 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9d255bc0e278..7a45015274ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -192,23 +192,10 @@ static void sched_feat_disable(int i) { };
 static void sched_feat_enable(int i) { };
 #endif /* HAVE_JUMP_LABEL */
 
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-                size_t cnt, loff_t *ppos)
+static int sched_feat_set(char *cmp)
 {
-        char buf[64];
-        char *cmp;
-        int neg = 0;
         int i;
-
-        if (cnt > 63)
-                cnt = 63;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-        cmp = strstrip(buf);
+        int neg = 0;
 
         if (strncmp(cmp, "NO_", 3) == 0) {
                 neg = 1;
@@ -228,6 +215,27 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
                 }
         }
 
+        return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+                size_t cnt, loff_t *ppos)
+{
+        char buf[64];
+        char *cmp;
+        int i;
+
+        if (cnt > 63)
+                cnt = 63;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+        cmp = strstrip(buf);
+
+        i = sched_feat_set(cmp);
         if (i == __SCHED_FEAT_NR)
                 return -EINVAL;
 
@@ -1549,6 +1557,16 @@ static void __sched_fork(struct task_struct *p)
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+void set_numabalancing_state(bool enabled)
+{
+        if (enabled)
+                sched_feat_set("NUMA");
+        else
+                sched_feat_set("NO_NUMA");
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /*
  * fork()/clone()-time setup:
  */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4b577863933f..7a02a2082e95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -811,6 +811,9 @@ void task_numa_fault(int node, int pages, bool migrated)
 {
         struct task_struct *p = current;
 
+        if (!sched_feat_numa(NUMA))
+                return;
+
         /* FIXME: Allocate task-specific structure for placement policy here */
 
         /*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 5fb7aefbec80..d2373a3e3252 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -63,8 +63,10 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 
 /*
- * Apply the automatic NUMA scheduling policy
+ * Apply the automatic NUMA scheduling policy. Enabled automatically
+ * at runtime if running on a NUMA machine. Can be controlled via
+ * numa_balancing=
  */
 #ifdef CONFIG_NUMA_BALANCING
-SCHED_FEAT(NUMA,        true)
+SCHED_FEAT(NUMA,        false)
 #endif