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, 88 insertions, 0 deletions

diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c
new file mode 100644
index 000000000..dda323e0a
--- /dev/null
+++ b/net/nfc/af_nfc.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2011 Instituto Nokia de Tecnologia
+ *
+ * Authors:
+ *    Aloisio Almeida Jr <aloisio.almeida@openbossa.org>
+ *    Lauro Ramos Venancio <lauro.venancio@openbossa.org>
+ */
+
+#include <linux/nfc.h>
+#include <linux/module.h>
+
+#include "nfc.h"
+
+static DEFINE_RWLOCK(proto_tab_lock);
+static const struct nfc_protocol *proto_tab[NFC_SOCKPROTO_MAX];
+
+static int nfc_sock_create(struct net *net, struct socket *sock, int proto,
+			   int kern)
+{
+	int rc = -EPROTONOSUPPORT;
+
+	if (net != &init_net)
+		return -EAFNOSUPPORT;
+
+	if (proto < 0 || proto >= NFC_SOCKPROTO_MAX)
+		return -EINVAL;
+
+	read_lock(&proto_tab_lock);
+	if (proto_tab[proto] &&	try_module_get(proto_tab[proto]->owner)) {
+		rc = proto_tab[proto]->create(net, sock, proto_tab[proto], kern);
+		module_put(proto_tab[proto]->owner);
+	}
+	read_unlock(&proto_tab_lock);
+
+	return rc;
+}
+
+static const struct net_proto_family nfc_sock_family_ops = {
+	.owner  = THIS_MODULE,
+	.family = PF_NFC,
+	.create = nfc_sock_create,
+};
+
+int nfc_proto_register(const struct nfc_protocol *nfc_proto)
+{
+	int rc;
+
+	if (nfc_proto->id < 0 || nfc_proto->id >= NFC_SOCKPROTO_MAX)
+		return -EINVAL;
+
+	rc = proto_register(nfc_proto->proto, 0);
+	if (rc)
+		return rc;
+
+	write_lock(&proto_tab_lock);
+	if (proto_tab[nfc_proto->id])
+		rc = -EBUSY;
+	else
+		proto_tab[nfc_proto->id] = nfc_proto;
+	write_unlock(&proto_tab_lock);
+
+	if (rc)
+		proto_unregister(nfc_proto->proto);
+
+	return rc;
+}
+EXPORT_SYMBOL(nfc_proto_register);
+
+void nfc_proto_unregister(const struct nfc_protocol *nfc_proto)
+{
+	write_lock(&proto_tab_lock);
+	proto_tab[nfc_proto->id] = NULL;
+	write_unlock(&proto_tab_lock);
+
+	proto_unregister(nfc_proto->proto);
+}
+EXPORT_SYMBOL(nfc_proto_unregister);
+
+int __init af_nfc_init(void)
+{
+	return sock_register(&nfc_sock_family_ops);
+}
+
+void __exit af_nfc_exit(void)
+{
+	sock_unregister(PF_NFC);
+}