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, 74 insertions, 0 deletions

diff --git a/net/wireless/ap.c b/net/wireless/ap.c
new file mode 100644
index 000000000..9a9a87080
--- /dev/null
+++ b/net/wireless/ap.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Parts of this file are
+ * Copyright (C) 2022-2023 Intel Corporation
+ */
+#include <linux/ieee80211.h>
+#include <linux/export.h>
+#include <net/cfg80211.h>
+#include "nl80211.h"
+#include "core.h"
+#include "rdev-ops.h"
+
+
+static int ___cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
+			       struct net_device *dev, unsigned int link_id,
+			       bool notify)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	lockdep_assert_wiphy(wdev->wiphy);
+
+	if (!rdev->ops->stop_ap)
+		return -EOPNOTSUPP;
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP &&
+	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
+		return -EOPNOTSUPP;
+
+	if (!wdev->links[link_id].ap.beacon_interval)
+		return -ENOENT;
+
+	err = rdev_stop_ap(rdev, dev, link_id);
+	if (!err) {
+		wdev->conn_owner_nlportid = 0;
+		wdev->links[link_id].ap.beacon_interval = 0;
+		memset(&wdev->links[link_id].ap.chandef, 0,
+		       sizeof(wdev->links[link_id].ap.chandef));
+		wdev->u.ap.ssid_len = 0;
+		rdev_set_qos_map(rdev, dev, NULL);
+		if (notify)
+			nl80211_send_ap_stopped(wdev, link_id);
+
+		/* Should we apply the grace period during beaconing interface
+		 * shutdown also?
+		 */
+		cfg80211_sched_dfs_chan_update(rdev);
+	}
+
+	schedule_work(&cfg80211_disconnect_work);
+
+	return err;
+}
+
+int cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
+		     struct net_device *dev, int link_id,
+		     bool notify)
+{
+	unsigned int link;
+	int ret = 0;
+
+	if (link_id >= 0)
+		return ___cfg80211_stop_ap(rdev, dev, link_id, notify);
+
+	for_each_valid_link(dev->ieee80211_ptr, link) {
+		int ret1 = ___cfg80211_stop_ap(rdev, dev, link, notify);
+
+		if (ret1)
+			ret = ret1;
+		/* try the next one also if one errored */
+	}
+
+	return ret;
+}