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, 123 insertions, 0 deletions

diff --git a/net/dsa/switch.h b/net/dsa/switch.h
new file mode 100644
index 000000000..be0a2749c
--- /dev/null
+++ b/net/dsa/switch.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __DSA_SWITCH_H
+#define __DSA_SWITCH_H
+
+#include <net/dsa.h>
+
+struct netlink_ext_ack;
+
+enum {
+	DSA_NOTIFIER_AGEING_TIME,
+	DSA_NOTIFIER_BRIDGE_JOIN,
+	DSA_NOTIFIER_BRIDGE_LEAVE,
+	DSA_NOTIFIER_FDB_ADD,
+	DSA_NOTIFIER_FDB_DEL,
+	DSA_NOTIFIER_HOST_FDB_ADD,
+	DSA_NOTIFIER_HOST_FDB_DEL,
+	DSA_NOTIFIER_LAG_FDB_ADD,
+	DSA_NOTIFIER_LAG_FDB_DEL,
+	DSA_NOTIFIER_LAG_CHANGE,
+	DSA_NOTIFIER_LAG_JOIN,
+	DSA_NOTIFIER_LAG_LEAVE,
+	DSA_NOTIFIER_MDB_ADD,
+	DSA_NOTIFIER_MDB_DEL,
+	DSA_NOTIFIER_HOST_MDB_ADD,
+	DSA_NOTIFIER_HOST_MDB_DEL,
+	DSA_NOTIFIER_VLAN_ADD,
+	DSA_NOTIFIER_VLAN_DEL,
+	DSA_NOTIFIER_HOST_VLAN_ADD,
+	DSA_NOTIFIER_HOST_VLAN_DEL,
+	DSA_NOTIFIER_MTU,
+	DSA_NOTIFIER_TAG_PROTO,
+	DSA_NOTIFIER_TAG_PROTO_CONNECT,
+	DSA_NOTIFIER_TAG_PROTO_DISCONNECT,
+	DSA_NOTIFIER_TAG_8021Q_VLAN_ADD,
+	DSA_NOTIFIER_TAG_8021Q_VLAN_DEL,
+	DSA_NOTIFIER_CONDUIT_STATE_CHANGE,
+};
+
+/* DSA_NOTIFIER_AGEING_TIME */
+struct dsa_notifier_ageing_time_info {
+	unsigned int ageing_time;
+};
+
+/* DSA_NOTIFIER_BRIDGE_* */
+struct dsa_notifier_bridge_info {
+	const struct dsa_port *dp;
+	struct dsa_bridge bridge;
+	bool tx_fwd_offload;
+	struct netlink_ext_ack *extack;
+};
+
+/* DSA_NOTIFIER_FDB_* */
+struct dsa_notifier_fdb_info {
+	const struct dsa_port *dp;
+	const unsigned char *addr;
+	u16 vid;
+	struct dsa_db db;
+};
+
+/* DSA_NOTIFIER_LAG_FDB_* */
+struct dsa_notifier_lag_fdb_info {
+	struct dsa_lag *lag;
+	const unsigned char *addr;
+	u16 vid;
+	struct dsa_db db;
+};
+
+/* DSA_NOTIFIER_MDB_* */
+struct dsa_notifier_mdb_info {
+	const struct dsa_port *dp;
+	const struct switchdev_obj_port_mdb *mdb;
+	struct dsa_db db;
+};
+
+/* DSA_NOTIFIER_LAG_* */
+struct dsa_notifier_lag_info {
+	const struct dsa_port *dp;
+	struct dsa_lag lag;
+	struct netdev_lag_upper_info *info;
+	struct netlink_ext_ack *extack;
+};
+
+/* DSA_NOTIFIER_VLAN_* */
+struct dsa_notifier_vlan_info {
+	const struct dsa_port *dp;
+	const struct switchdev_obj_port_vlan *vlan;
+	struct netlink_ext_ack *extack;
+};
+
+/* DSA_NOTIFIER_MTU */
+struct dsa_notifier_mtu_info {
+	const struct dsa_port *dp;
+	int mtu;
+};
+
+/* DSA_NOTIFIER_TAG_PROTO_* */
+struct dsa_notifier_tag_proto_info {
+	const struct dsa_device_ops *tag_ops;
+};
+
+/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */
+struct dsa_notifier_tag_8021q_vlan_info {
+	const struct dsa_port *dp;
+	u16 vid;
+};
+
+/* DSA_NOTIFIER_CONDUIT_STATE_CHANGE */
+struct dsa_notifier_conduit_state_info {
+	const struct net_device *conduit;
+	bool operational;
+};
+
+struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
+			       const struct switchdev_obj_port_vlan *vlan);
+
+int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v);
+int dsa_broadcast(unsigned long e, void *v);
+
+int dsa_switch_register_notifier(struct dsa_switch *ds);
+void dsa_switch_unregister_notifier(struct dsa_switch *ds);
+
+#endif