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, 71 insertions, 0 deletions

diff --git a/net/dsa/user.h b/net/dsa/user.h
new file mode 100644
index 000000000..016884bea
--- /dev/null
+++ b/net/dsa/user.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __DSA_USER_H
+#define __DSA_USER_H
+
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/list.h>
+#include <linux/netpoll.h>
+#include <linux/types.h>
+#include <net/dsa.h>
+#include <net/gro_cells.h>
+
+struct net_device;
+struct netlink_ext_ack;
+
+extern struct notifier_block dsa_user_switchdev_notifier;
+extern struct notifier_block dsa_user_switchdev_blocking_notifier;
+
+struct dsa_user_priv {
+	/* Copy of CPU port xmit for faster access in user transmit hot path */
+	struct sk_buff *	(*xmit)(struct sk_buff *skb,
+					struct net_device *dev);
+
+	struct gro_cells	gcells;
+
+	/* DSA port data, such as switch, port index, etc. */
+	struct dsa_port		*dp;
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	struct netpoll		*netpoll;
+#endif
+
+	/* TC context */
+	struct list_head	mall_tc_list;
+};
+
+void dsa_user_mii_bus_init(struct dsa_switch *ds);
+int dsa_user_create(struct dsa_port *dp);
+void dsa_user_destroy(struct net_device *user_dev);
+int dsa_user_suspend(struct net_device *user_dev);
+int dsa_user_resume(struct net_device *user_dev);
+int dsa_user_register_notifier(void);
+void dsa_user_unregister_notifier(void);
+int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr);
+void dsa_user_host_uc_uninstall(struct net_device *dev);
+void dsa_user_sync_ha(struct net_device *dev);
+void dsa_user_unsync_ha(struct net_device *dev);
+void dsa_user_setup_tagger(struct net_device *user);
+int dsa_user_change_mtu(struct net_device *dev, int new_mtu);
+int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit,
+			    struct netlink_ext_ack *extack);
+int dsa_user_manage_vlan_filtering(struct net_device *dev,
+				   bool vlan_filtering);
+
+static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev)
+{
+	struct dsa_user_priv *p = netdev_priv(dev);
+
+	return p->dp;
+}
+
+static inline struct net_device *
+dsa_user_to_conduit(const struct net_device *dev)
+{
+	struct dsa_port *dp = dsa_user_to_port(dev);
+
+	return dsa_port_to_conduit(dp);
+}
+
+#endif