[tip: sched/core] sched/fair: Add cgroup_mode switch

["tip-bot2 for Peter Zijlstra" <tip-bot2@linutronix.de>]

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     4161cb2d867b2210b447afc4a941ab4b96e1bd13
Gitweb:        https://git.kernel.org/tip/4161cb2d867b2210b447afc4a941ab4b96e1bd13
Author:        Peter Zijlstra <peterz@infradead.org>
AuthorDate:    Thu, 12 Mar 2026 14:48:44 +01:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 30 Jun 2026 10:56:51 +02:00

sched/fair: Add cgroup_mode switch

The effective task weight (W_t') for a task in cgroup g on CPU n is given by:

                                 W_t
	W_t' = W_g * F_g_n * ----------
                             \Sum W_t_n

Where W_g is the group's weight (cpu.weight), F_g_n is the fraction of the
group weight for CPU n and W_t/W is the relative weight of this task against
all other tasks in the same group on the same CPU.

Furthermore, this makes:

                \Sum W_t_n
	F_g_n = ----------
	         \Sum W_t

The fraction of weight inside the group of CPU n against the whole group.

The problem is with F_g_n, the primary goal of this fraction is to make sure
that the relative weight of tasks, when distributed over CPUs is maintained.
For example, consider 4 (equal weight) tasks and 2 CPUs with a 1:3
distribution, then if F_g_n would simply be 1 (no weight re-distribution) the
effective relative weights (W_t') of the tasks in our group would be:

	CPU0	CPU1
        W_g     W_g/3
	        W_g/3
		W_g/3

IOW, the lucky task on CPU0 would get an equal amount of weight as all 3 tasks
on CPU1 combined. However, with the weight redistribution, this becomes:

	CPU0	CPU1
        W_g/4   W_g/4
	        W_g/4
		W_g/4

All tasks are equal weight (as intended). However, as is already evident from
this example, the more CPUs you add, the smaller F_g_n becomes, which creates a
disparity against tasks not in our group.

Specifically:

	avg(F_g_n) ~ 1/N

This leads to a weight mismatch in the hierarchy. IOW tasks cannot compete
fairly across hierarchy levels.

*Notably*, what is meant by avg(F_g_n) being proportional to 1/N is that when
there are at least N runnable tasks, the average of this fraction tends to 1/N.

For a hierarchy of depth d, this gets even worse, since that gets terms on the
order of:

	avg(F_g_n)^d ~ 1/(N^d)

Given fixed point arithmetic, this also leads to numerical trouble.

However, the meaning of "cpu.weight" is simple and intiutive: the total weight
of the cgroup. But as explored above, there is deception in this simplicity.

Prepare to add a few alternative methods for distributing weight.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260605124051.338602724%40infradead.org
---
 kernel/sched/debug.c | 74 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 40584b2..507e486 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -633,6 +633,76 @@ static void debugfs_fair_server_init(void)
 	}
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static 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, *llc;
@@ -686,6 +756,10 @@ 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();