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, 117 insertions, 0 deletions

diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
new file mode 100644
index 000000000..f138a4335
--- /dev/null
+++ b/drivers/acpi/container.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * container.c  - ACPI Generic Container Driver
+ *
+ * Copyright (C) 2004 Anil S Keshavamurthy (anil.s.keshavamurthy@intel.com)
+ * Copyright (C) 2004 Keiichiro Tokunaga (tokunaga.keiich@jp.fujitsu.com)
+ * Copyright (C) 2004 Motoyuki Ito (motoyuki@soft.fujitsu.com)
+ * Copyright (C) 2004 FUJITSU LIMITED
+ * Copyright (C) 2004, 2013 Intel Corp.
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ */
+#include <linux/acpi.h>
+#include <linux/container.h>
+
+#include "internal.h"
+
+static const struct acpi_device_id container_device_ids[] = {
+	{"ACPI0004", 0},
+	{"PNP0A05", 0},
+	{"PNP0A06", 0},
+	{"", 0},
+};
+
+#ifdef CONFIG_ACPI_CONTAINER
+
+static int check_offline(struct acpi_device *adev, void *not_used)
+{
+	if (acpi_scan_is_offline(adev, false))
+		return 0;
+
+	return -EBUSY;
+}
+
+static int acpi_container_offline(struct container_dev *cdev)
+{
+	/* Check all of the dependent devices' physical companions. */
+	return acpi_dev_for_each_child(ACPI_COMPANION(&cdev->dev), check_offline, NULL);
+}
+
+static void acpi_container_release(struct device *dev)
+{
+	kfree(to_container_dev(dev));
+}
+
+static int container_device_attach(struct acpi_device *adev,
+				   const struct acpi_device_id *not_used)
+{
+	struct container_dev *cdev;
+	struct device *dev;
+	int ret;
+
+	if (adev->flags.is_dock_station)
+		return 0;
+
+	cdev = kzalloc_obj(*cdev);
+	if (!cdev)
+		return -ENOMEM;
+
+	cdev->offline = acpi_container_offline;
+	dev = &cdev->dev;
+	dev->bus = &container_subsys;
+	dev_set_name(dev, "%s", dev_name(&adev->dev));
+	ACPI_COMPANION_SET(dev, adev);
+	dev->release = acpi_container_release;
+	ret = device_register(dev);
+	if (ret) {
+		put_device(dev);
+		return ret;
+	}
+	adev->driver_data = dev;
+	return 1;
+}
+
+static void container_device_detach(struct acpi_device *adev)
+{
+	struct device *dev = acpi_driver_data(adev);
+
+	adev->driver_data = NULL;
+	if (dev)
+		device_unregister(dev);
+}
+
+static void container_device_online(struct acpi_device *adev)
+{
+	struct device *dev = acpi_driver_data(adev);
+
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+static struct acpi_scan_handler container_handler = {
+	.ids = container_device_ids,
+	.attach = container_device_attach,
+	.detach = container_device_detach,
+	.hotplug = {
+		.enabled = true,
+		.demand_offline = true,
+		.notify_online = container_device_online,
+	},
+};
+
+void __init acpi_container_init(void)
+{
+	acpi_scan_add_handler(&container_handler);
+}
+
+#else
+
+static struct acpi_scan_handler container_handler = {
+	.ids = container_device_ids,
+};
+
+void __init acpi_container_init(void)
+{
+	acpi_scan_add_handler_with_hotplug(&container_handler, "container");
+}
+
+#endif /* CONFIG_ACPI_CONTAINER */