numa: add a sysctl for numa_balancing

Add a working sysctl to enable/disable automatic numa memory balancing
at runtime.

This allows us to track down performance problems with this feature and
is generally a good idea.

This was possible earlier through debugfs, but only with special
debugging options set.  Also fix the boot message.

[akpm@linux-foundation.org: s/sched_numa_balancing/sysctl_numa_balancing/]
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NMel Gorman <mgorman@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

include/linux/sched/sysctl.h

@@ -99,4 +99,8 @@ extern int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
+extern int sysctl_numa_balancing(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */

kernel/sched/core.c

@@ -1770,7 +1770,29 @@ void set_numabalancing_state(bool enabled)
 	numabalancing_enabled = enabled;
 }
 #endif /* CONFIG_SCHED_DEBUG */
-#endif /* CONFIG_NUMA_BALANCING */
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_numa_balancing(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = numabalancing_enabled;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_numabalancing_state(state);
+	return err;
+}
+#endif
+#endif
 
 /*
  * fork()/clone()-time setup:

kernel/sysctl.c

@@ -389,6 +389,15 @@ static struct ctl_table kern_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing",
+		.data		= NULL, /* filled in by handler */
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_numa_balancing,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{

mm/mempolicy.c

@@ -2668,7 +2668,7 @@ static void __init check_numabalancing_enable(void)
 
 	if (nr_node_ids > 1 && !numabalancing_override) {
 		printk(KERN_INFO "Enabling automatic NUMA balancing. "
-			"Configure with numa_balancing= or sysctl");
+			"Configure with numa_balancing= or the kernel.numa_balancing sysctl");
 		set_numabalancing_state(numabalancing_default);
 	}
 }