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, 65 insertions, 0 deletions

diff --git a/net/wireless/ocb.c b/net/wireless/ocb.c
new file mode 100644
index 000000000..7d2d67f13
--- /dev/null
+++ b/net/wireless/ocb.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OCB mode implementation
+ *
+ * Copyright: (c) 2014 Czech Technical University in Prague
+ *            (c) 2014 Volkswagen Group Research
+ * Copyright (C) 2022-2023 Intel Corporation
+ * Author:    Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
+ * Funded by: Volkswagen Group Research
+ */
+
+#include <linux/ieee80211.h>
+#include <net/cfg80211.h>
+#include "nl80211.h"
+#include "core.h"
+#include "rdev-ops.h"
+
+int cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev,
+		      struct ocb_setup *setup)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	lockdep_assert_wiphy(wdev->wiphy);
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB)
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->join_ocb)
+		return -EOPNOTSUPP;
+
+	if (WARN_ON(!setup->chandef.chan))
+		return -EINVAL;
+
+	err = rdev_join_ocb(rdev, dev, setup);
+	if (!err)
+		wdev->u.ocb.chandef = setup->chandef;
+
+	return err;
+}
+
+int cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	lockdep_assert_wiphy(wdev->wiphy);
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB)
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->leave_ocb)
+		return -EOPNOTSUPP;
+
+	if (!wdev->u.ocb.chandef.chan)
+		return -ENOTCONN;
+
+	err = rdev_leave_ocb(rdev, dev);
+	if (!err)
+		memset(&wdev->u.ocb.chandef, 0, sizeof(wdev->u.ocb.chandef));
+
+	return err;
+}