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, 98 insertions, 0 deletions

diff --git a/drivers/input/misc/88pm886-onkey.c b/drivers/input/misc/88pm886-onkey.c
new file mode 100644
index 000000000..284ff5190
--- /dev/null
+++ b/drivers/input/misc/88pm886-onkey.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <linux/mfd/88pm886.h>
+
+struct pm886_onkey {
+	struct input_dev *idev;
+	struct pm886_chip *chip;
+};
+
+static irqreturn_t pm886_onkey_irq_handler(int irq, void *data)
+{
+	struct pm886_onkey *onkey = data;
+	struct regmap *regmap = onkey->chip->regmap;
+	struct input_dev *idev = onkey->idev;
+	struct device *parent = idev->dev.parent;
+	unsigned int val;
+	int err;
+
+	err = regmap_read(regmap, PM886_REG_STATUS1, &val);
+	if (err) {
+		dev_err(parent, "Failed to read status: %d\n", err);
+		return IRQ_NONE;
+	}
+	val &= PM886_ONKEY_STS1;
+
+	input_report_key(idev, KEY_POWER, val);
+	input_sync(idev);
+
+	return IRQ_HANDLED;
+}
+
+static int pm886_onkey_probe(struct platform_device *pdev)
+{
+	struct pm886_chip *chip = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct pm886_onkey *onkey;
+	struct input_dev *idev;
+	int irq, err;
+
+	onkey = devm_kzalloc(dev, sizeof(*onkey), GFP_KERNEL);
+	if (!onkey)
+		return -ENOMEM;
+
+	onkey->chip = chip;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return dev_err_probe(dev, irq, "Failed to get IRQ\n");
+
+	idev = devm_input_allocate_device(dev);
+	if (!idev) {
+		dev_err(dev, "Failed to allocate input device\n");
+		return -ENOMEM;
+	}
+	onkey->idev = idev;
+
+	idev->name = "88pm886-onkey";
+	idev->phys = "88pm886-onkey/input0";
+	idev->id.bustype = BUS_I2C;
+
+	input_set_capability(idev, EV_KEY, KEY_POWER);
+
+	err = devm_request_threaded_irq(dev, irq, NULL, pm886_onkey_irq_handler,
+					IRQF_ONESHOT | IRQF_NO_SUSPEND, "onkey",
+					onkey);
+	if (err)
+		return dev_err_probe(dev, err, "Failed to request IRQ\n");
+
+	err = input_register_device(idev);
+	if (err)
+		return dev_err_probe(dev, err, "Failed to register input device\n");
+
+	return 0;
+}
+
+static const struct platform_device_id pm886_onkey_id_table[] = {
+	{ "88pm886-onkey", },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, pm886_onkey_id_table);
+
+static struct platform_driver pm886_onkey_driver = {
+	.driver = {
+		.name = "88pm886-onkey",
+	},
+	.probe = pm886_onkey_probe,
+	.id_table = pm886_onkey_id_table,
+};
+module_platform_driver(pm886_onkey_driver);
+
+MODULE_DESCRIPTION("Marvell 88PM886 onkey driver");
+MODULE_AUTHOR("Karel Balej <balejk@matfyz.cz>");
+MODULE_LICENSE("GPL");