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 <[email protected]>

Documentation/kernel-parameters.txt

@@ -1996,6 +1996,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
 
+	numa_balancing=	[KNL,X86] Enable or disable automatic NUMA balancing.
+			Allowed values are enable and disable
+
 	numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
 			one of ['zone', 'node', 'default'] can be specified
 			This can be set from sysctl after boot.

include/linux/sched.h

@@ -1563,10 +1563,14 @@ struct task_struct {
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int node, int pages, bool migrated);
+extern void set_numabalancing_state(bool enabled);
 #else
 static inline void task_numa_fault(int node, int pages, bool migrated)
 {
 }
+static inline void set_numabalancing_state(bool enabled)
+{
+}
 #endif
 
 /*

init/Kconfig

@@ -720,6 +720,14 @@ config ARCH_USES_NUMA_PROT_NONE
 	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
 	depends on NUMA_BALANCING
 
+config NUMA_BALANCING_DEFAULT_ENABLED
+	bool "Automatically enable NUMA aware memory/task placement"
+	default y
+	depends on NUMA_BALANCING
+	help
+	  If set, autonumic NUMA balancing will be enabled if running on a NUMA
+	  machine.
+
 config NUMA_BALANCING
 	bool "Memory placement aware NUMA scheduler"
 	default y

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:
  */

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 */
 
 	/*

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

mm/mempolicy.c

@@ -2521,6 +2521,50 @@ void mpol_free_shared_policy(struct shared_policy *p)
 	mutex_unlock(&p->mutex);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static bool __initdata numabalancing_override;
+
+static void __init check_numabalancing_enable(void)
+{
+	bool numabalancing_default = false;
+
+	if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
+		numabalancing_default = true;
+
+	if (nr_node_ids > 1 && !numabalancing_override) {
+		printk(KERN_INFO "Enabling automatic NUMA balancing. "
+			"Configure with numa_balancing= or sysctl");
+		set_numabalancing_state(numabalancing_default);
+	}
+}
+
+static int __init setup_numabalancing(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+	numabalancing_override = true;
+
+	if (!strcmp(str, "enable")) {
+		set_numabalancing_state(true);
+		ret = 1;
+	} else if (!strcmp(str, "disable")) {
+		set_numabalancing_state(false);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		printk(KERN_WARNING "Unable to parse numa_balancing=\n");
+
+	return ret;
+}
+__setup("numa_balancing=", setup_numabalancing);
+#else
+static inline void __init check_numabalancing_enable(void)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /* assumes fs == KERNEL_DS */
 void __init numa_policy_init(void)
 {
@@ -2571,6 +2615,8 @@ void __init numa_policy_init(void)
 
 	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
 		printk("numa_policy_init: interleaving failed\n");
+
+	check_numabalancing_enable();
 }
 
 /* Reset policy of current process to default */