sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 95 insertions, 0 deletions

diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c
new file mode 100644
index 000000000..463a74a27
--- /dev/null
+++ b/net/phonet/sysctl.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * File: sysctl.c
+ *
+ * Phonet /proc/sys/net/phonet interface implementation
+ *
+ * Copyright (C) 2008 Nokia Corporation.
+ *
+ * Author: Rémi Denis-Courmont
+ */
+
+#include <linux/seqlock.h>
+#include <linux/sysctl.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+
+#include <net/sock.h>
+#include <linux/phonet.h>
+#include <net/phonet/phonet.h>
+
+#define DYNAMIC_PORT_MIN	0x40
+#define DYNAMIC_PORT_MAX	0x7f
+
+static DEFINE_SEQLOCK(local_port_range_lock);
+static int local_port_range_min[2] = {0, 0};
+static int local_port_range_max[2] = {1023, 1023};
+static int local_port_range[2] = {DYNAMIC_PORT_MIN, DYNAMIC_PORT_MAX};
+static struct ctl_table_header *phonet_table_hrd;
+
+static void set_local_port_range(int range[2])
+{
+	write_seqlock(&local_port_range_lock);
+	local_port_range[0] = range[0];
+	local_port_range[1] = range[1];
+	write_sequnlock(&local_port_range_lock);
+}
+
+void phonet_get_local_port_range(int *min, int *max)
+{
+	unsigned int seq;
+
+	do {
+		seq = read_seqbegin(&local_port_range_lock);
+		if (min)
+			*min = local_port_range[0];
+		if (max)
+			*max = local_port_range[1];
+	} while (read_seqretry(&local_port_range_lock, seq));
+}
+
+static int proc_local_port_range(const struct ctl_table *table, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+	int range[2] = {local_port_range[0], local_port_range[1]};
+	struct ctl_table tmp = {
+		.data = &range,
+		.maxlen = sizeof(range),
+		.mode = table->mode,
+		.extra1 = &local_port_range_min,
+		.extra2 = &local_port_range_max,
+	};
+
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+
+	if (write && ret == 0) {
+		if (range[1] < range[0])
+			ret = -EINVAL;
+		else
+			set_local_port_range(range);
+	}
+
+	return ret;
+}
+
+static struct ctl_table phonet_table[] = {
+	{
+		.procname	= "local_port_range",
+		.data		= &local_port_range,
+		.maxlen		= sizeof(local_port_range),
+		.mode		= 0644,
+		.proc_handler	= proc_local_port_range,
+	},
+};
+
+int __init phonet_sysctl_init(void)
+{
+	phonet_table_hrd = register_net_sysctl(&init_net, "net/phonet", phonet_table);
+	return phonet_table_hrd == NULL ? -ENOMEM : 0;
+}
+
+void phonet_sysctl_exit(void)
+{
+	unregister_net_sysctl_table(phonet_table_hrd);
+}