[PATCH v2 04/10] sched/fair: Add cgroup_mode switch

[Peter Zijlstra <peterz@infradead.org>]

Since calc_group_shares() has issues with 'many' CPUs, specifically the
computed shares value gets to be roughly 1/nr_cpus, prepare to add a few
alternative methods.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/debug.c |   74 +++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |    1 
 2 files changed, 75 insertions(+)

--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -588,6 +588,76 @@ static void debugfs_fair_server_init(voi
 	}
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+int cgroup_mode = 0;
+
+static const char *cgroup_mode_str[] = {
+	"smp",
+};
+
+static int sched_cgroup_mode(const char *str)
+{
+	for (int i = 0; i < ARRAY_SIZE(cgroup_mode_str); i++) {
+		if (!strcmp(str, cgroup_mode_str[i]))
+			return i;
+	}
+	return -EINVAL;
+}
+
+static ssize_t sched_cgroup_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *ppos)
+{
+	char buf[16];
+	int mode;
+
+	if (cnt > 15)
+		cnt = 15;
+
+	if (copy_from_user(buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	mode = sched_cgroup_mode(strstrip(buf));
+	if (mode < 0)
+		return mode;
+
+	WRITE_ONCE(cgroup_mode, mode);
+
+	*ppos += cnt;
+	return cnt;
+}
+
+static int sched_cgroup_show(struct seq_file *m, void *v)
+{
+	int mode = READ_ONCE(cgroup_mode);
+
+	for (int i = 0; i < ARRAY_SIZE(cgroup_mode_str); i++) {
+		if (mode == i)
+			seq_puts(m, "(");
+		seq_puts(m, cgroup_mode_str[i]);
+		if (mode == i)
+			seq_puts(m, ")");
+
+		seq_puts(m, " ");
+	}
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static int sched_cgroup_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_cgroup_show, NULL);
+}
+
+static const struct file_operations sched_cgroup_fops = {
+	.open		= sched_cgroup_open,
+	.write		= sched_cgroup_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+#endif
+
 static __init int sched_init_debug(void)
 {
 	struct dentry __maybe_unused *numa;
@@ -625,6 +695,10 @@ static __init int sched_init_debug(void)
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	debugfs_create_file("cgroup_mode", 0644, debugfs_sched, NULL, &sched_cgroup_fops);
+#endif
+
 	debugfs_fair_server_init();
 #ifdef CONFIG_SCHED_CLASS_EXT
 	debugfs_ext_server_init();
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -565,6 +565,7 @@ static inline struct task_group *css_tg(
 extern int tg_nop(struct task_group *tg, void *data);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+extern int cgroup_mode;
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
 extern void online_fair_sched_group(struct task_group *tg);