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, 58 insertions, 0 deletions

diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h
new file mode 100644
index 000000000..957d9ef92
--- /dev/null
+++ b/include/net/mctpdevice.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Management Component Transport Protocol (MCTP) - device
+ * definitions.
+ *
+ * Copyright (c) 2021 Code Construct
+ * Copyright (c) 2021 Google
+ */
+
+#ifndef __NET_MCTPDEVICE_H
+#define __NET_MCTPDEVICE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/refcount.h>
+
+struct mctp_sk_key;
+
+struct mctp_dev {
+	struct net_device	*dev;
+
+	refcount_t		refs;
+
+	unsigned int		net;
+	enum mctp_phys_binding	binding;
+
+	const struct mctp_netdev_ops *ops;
+
+	/* Only modified under RTNL. Reads have addrs_lock held */
+	u8			*addrs;
+	size_t			num_addrs;
+	spinlock_t		addrs_lock;
+
+	struct rcu_head		rcu;
+};
+
+struct mctp_netdev_ops {
+	void			(*release_flow)(struct mctp_dev *dev,
+						struct mctp_sk_key *key);
+};
+
+#define MCTP_INITIAL_DEFAULT_NET	1
+
+struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev);
+struct mctp_dev *__mctp_dev_get(const struct net_device *dev);
+
+int mctp_register_netdev(struct net_device *dev,
+			 const struct mctp_netdev_ops *ops,
+			 enum mctp_phys_binding binding);
+void mctp_unregister_netdev(struct net_device *dev);
+
+void mctp_dev_hold(struct mctp_dev *mdev);
+void mctp_dev_put(struct mctp_dev *mdev);
+
+void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key);
+void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key);
+
+#endif /* __NET_MCTPDEVICE_H */