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, 155 insertions, 0 deletions

diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h
new file mode 100644
index 000000000..9fb3e9385
--- /dev/null
+++ b/include/net/netdev_lock.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _NET_NETDEV_LOCK_H
+#define _NET_NETDEV_LOCK_H
+
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+
+static inline bool netdev_trylock(struct net_device *dev)
+{
+	return mutex_trylock(&dev->lock);
+}
+
+static inline void netdev_assert_locked(const struct net_device *dev)
+{
+	lockdep_assert_held(&dev->lock);
+}
+
+static inline void
+netdev_assert_locked_or_invisible(const struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_REGISTERED ||
+	    dev->reg_state == NETREG_UNREGISTERING)
+		netdev_assert_locked(dev);
+}
+
+static inline bool netdev_need_ops_lock(const struct net_device *dev)
+{
+	bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops;
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	ret |= !!dev->netdev_ops->net_shaper_ops;
+#endif
+
+	return ret;
+}
+
+static inline void netdev_lock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+}
+
+static inline void netdev_lock_ops_to_full(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+	else
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_full_to_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+	else
+		netdev_unlock(dev);
+}
+
+static inline void netdev_assert_locked_ops_compat(const struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		lockdep_assert_held(&dev->lock);
+	else
+		ASSERT_RTNL();
+}
+
+static inline void
+netdev_assert_locked_ops_compat_or_invisible(const struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_REGISTERED ||
+	    dev->reg_state == NETREG_UNREGISTERING)
+		netdev_assert_locked_ops_compat(dev);
+}
+
+static inline void netdev_assert_locked_ops(const struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+}
+
+static inline void netdev_lock_ops_compat(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+	else
+		rtnl_lock();
+}
+
+static inline void netdev_unlock_ops_compat(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+	else
+		rtnl_unlock();
+}
+
+/* Matching "ops protected" category from netdevice.h */
+static inline int netdev_is_locked_ops_compat(const struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		return lockdep_is_held(&dev->lock);
+	return lockdep_rtnl_is_held();
+}
+
+static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
+				     const struct lockdep_map *b)
+{
+	if (a == b)
+		return 0;
+
+	/* Allow locking multiple devices only under rtnl_lock,
+	 * the exact order doesn't matter.
+	 * Note that upper devices don't lock their ops, so nesting
+	 * mostly happens in batched device removal for now.
+	 */
+	return lockdep_rtnl_is_held() ? -1 : 1;
+}
+
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
+	static struct lock_class_key dev_instance_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key);		\
+	lockdep_set_class(&(dev)->lock,				\
+			  &dev_instance_lock_key);		\
+	lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL);	\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
+#define netdev_lock_dereference(p, dev)				\
+	rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock))
+
+#define netdev_ops_lock_dereference(p, dev)				\
+	rcu_dereference_protected(p, netdev_is_locked_ops_compat(dev))
+
+int netdev_debug_event(struct notifier_block *nb, unsigned long event,
+		       void *ptr);
+
+#endif