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, 86 insertions, 0 deletions

diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
new file mode 100644
index 000000000..a2af90ee9
--- /dev/null
+++ b/net/openvswitch/dp_notify.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ */
+
+#include <linux/netdevice.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static void dp_detach_port_notify(struct vport *vport)
+{
+	struct sk_buff *notify;
+	struct datapath *dp;
+
+	dp = vport->dp;
+	notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp),
+					  0, 0, OVS_VPORT_CMD_DEL);
+	ovs_dp_detach_port(vport);
+	if (IS_ERR(notify)) {
+		genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
+			     0, PTR_ERR(notify));
+		return;
+	}
+
+	genlmsg_multicast_netns(&dp_vport_genl_family,
+				ovs_dp_get_net(dp), notify, 0,
+				0, GFP_KERNEL);
+}
+
+void ovs_dp_notify_wq(struct work_struct *work)
+{
+	struct ovs_net *ovs_net = container_of(work, struct ovs_net, dp_notify_work);
+	struct datapath *dp;
+
+	ovs_lock();
+	list_for_each_entry(dp, &ovs_net->dps, list_node) {
+		int i;
+
+		for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+			struct vport *vport;
+			struct hlist_node *n;
+
+			hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
+				if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
+					continue;
+
+				if (!(netif_is_ovs_port(vport->dev)))
+					dp_detach_port_notify(vport);
+			}
+		}
+	}
+	ovs_unlock();
+}
+
+static int dp_device_event(struct notifier_block *unused, unsigned long event,
+			   void *ptr)
+{
+	struct ovs_net *ovs_net;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct vport *vport = NULL;
+
+	if (!ovs_is_internal_dev(dev))
+		vport = ovs_netdev_get_vport(dev);
+
+	if (!vport)
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_UNREGISTER) {
+		/* upper_dev_unlink and decrement promisc immediately */
+		ovs_netdev_detach_dev(vport);
+
+		/* schedule vport destroy, dev_put and genl notification */
+		ovs_net = net_generic(dev_net(dev), ovs_net_id);
+		queue_work(system_percpu_wq, &ovs_net->dp_notify_work);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ovs_dp_device_notifier = {
+	.notifier_call = dp_device_event
+};