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, 149 insertions, 0 deletions

diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
new file mode 100644
index 000000000..935f47ca9
--- /dev/null
+++ b/net/batman-adv/hard-interface.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ */
+
+#ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_
+#define _NET_BATMAN_ADV_HARD_INTERFACE_H_
+
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/init.h>
+#include <linux/kref.h>
+#include <linux/netdevice.h>
+#include <linux/rcupdate.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+/**
+ * enum batadv_hard_if_state - State of a hard interface
+ */
+enum batadv_hard_if_state {
+	/**
+	 * @BATADV_IF_TO_BE_REMOVED: interface will be removed from mesh
+	 * interface
+	 */
+	BATADV_IF_TO_BE_REMOVED,
+
+	/** @BATADV_IF_INACTIVE: interface is deactivated */
+	BATADV_IF_INACTIVE,
+
+	/** @BATADV_IF_ACTIVE: interface is used */
+	BATADV_IF_ACTIVE,
+
+	/** @BATADV_IF_TO_BE_ACTIVATED: interface is getting activated */
+	BATADV_IF_TO_BE_ACTIVATED,
+};
+
+/**
+ * enum batadv_hard_if_bcast - broadcast avoidance options
+ */
+enum batadv_hard_if_bcast {
+	/** @BATADV_HARDIF_BCAST_OK: Do broadcast on according hard interface */
+	BATADV_HARDIF_BCAST_OK = 0,
+
+	/**
+	 * @BATADV_HARDIF_BCAST_NORECIPIENT: Broadcast not needed, there is no
+	 *  recipient
+	 */
+	BATADV_HARDIF_BCAST_NORECIPIENT,
+
+	/**
+	 * @BATADV_HARDIF_BCAST_DUPFWD: There is just the neighbor we got it
+	 *  from
+	 */
+	BATADV_HARDIF_BCAST_DUPFWD,
+
+	/** @BATADV_HARDIF_BCAST_DUPORIG: There is just the originator */
+	BATADV_HARDIF_BCAST_DUPORIG,
+};
+
+extern struct notifier_block batadv_hard_if_notifier;
+
+struct net_device *__batadv_get_real_netdev(struct net_device *net_device);
+struct net_device *batadv_get_real_netdev(struct net_device *net_device);
+u32 batadv_netdev_get_wifi_flags(struct net_device *net_dev);
+u32 batadv_hardif_get_wifi_flags(struct batadv_hard_iface *hard_iface);
+bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface);
+struct batadv_hard_iface*
+batadv_hardif_get_by_netdev(struct net_device *net_dev);
+int batadv_hardif_enable_interface(struct net_device *net_dev,
+				   struct net_device *mesh_iface);
+void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface);
+int batadv_hardif_min_mtu(struct net_device *mesh_iface);
+void batadv_update_min_mtu(struct net_device *mesh_iface);
+void batadv_hardif_release(struct kref *ref);
+int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing,
+			       u8 *orig_addr, u8 *orig_neigh);
+int __init batadv_wifi_net_devices_init(void);
+void batadv_wifi_net_devices_deinit(void);
+
+/**
+ * batadv_hardif_put() - decrement the hard interface refcounter and possibly
+ *  release it
+ * @hard_iface: the hard interface to free
+ */
+static inline void batadv_hardif_put(struct batadv_hard_iface *hard_iface)
+{
+	if (!hard_iface)
+		return;
+
+	kref_put(&hard_iface->refcount, batadv_hardif_release);
+}
+
+/**
+ * batadv_primary_if_get_selected() - Get reference to primary interface
+ * @bat_priv: the bat priv with all the mesh interface information
+ *
+ * Return: primary interface (with increased refcnt), otherwise NULL
+ */
+static inline struct batadv_hard_iface *
+batadv_primary_if_get_selected(struct batadv_priv *bat_priv)
+{
+	struct batadv_hard_iface *hard_iface;
+
+	rcu_read_lock();
+	hard_iface = rcu_dereference(bat_priv->primary_if);
+	if (!hard_iface)
+		goto out;
+
+	if (!kref_get_unless_zero(&hard_iface->refcount))
+		hard_iface = NULL;
+
+out:
+	rcu_read_unlock();
+	return hard_iface;
+}
+
+/**
+ * batadv_is_cfg80211() - check if the given hardif is a cfg80211
+ *  wifi interface
+ * @wifi_flags: extracted batadv_hard_iface_wifi_flags of a net_device
+ *
+ * Return: true if the net device is a cfg80211 wireless device, false
+ *  otherwise.
+ */
+static inline bool batadv_is_cfg80211(u32 wifi_flags)
+{
+	u32 allowed_flags = 0;
+
+	allowed_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT;
+	allowed_flags |= BATADV_HARDIF_WIFI_CFG80211_INDIRECT;
+
+	return !!(wifi_flags & allowed_flags);
+}
+
+/**
+ * batadv_is_wifi() - check if flags belong to wifi interface
+ * @wifi_flags: extracted batadv_hard_iface_wifi_flags of a net_device
+ *
+ * Return: true if the net device is a 802.11 wireless device, false otherwise.
+ */
+static inline bool batadv_is_wifi(u32 wifi_flags)
+{
+	return wifi_flags != 0;
+}
+
+#endif /* _NET_BATMAN_ADV_HARD_INTERFACE_H_ */