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, 153 insertions, 0 deletions

diff --git a/drivers/input/misc/qnap-mcu-input.c b/drivers/input/misc/qnap-mcu-input.c
new file mode 100644
index 000000000..3be899bfc
--- /dev/null
+++ b/drivers/input/misc/qnap-mcu-input.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Driver for input events on QNAP-MCUs
+ *
+ * Copyright (C) 2024 Heiko Stuebner <heiko@sntech.de>
+ */
+
+#include <linux/input.h>
+#include <linux/mfd/qnap-mcu.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <uapi/linux/input-event-codes.h>
+
+/*
+ * The power-key needs to be pressed for a while to create an event,
+ * so there is no use for overly frequent polling.
+ */
+#define POLL_INTERVAL		500
+
+struct qnap_mcu_input_dev {
+	struct input_dev *input;
+	struct qnap_mcu *mcu;
+	struct device *dev;
+
+	struct work_struct beep_work;
+	int beep_type;
+};
+
+static void qnap_mcu_input_poll(struct input_dev *input)
+{
+	struct qnap_mcu_input_dev *idev = input_get_drvdata(input);
+	static const u8 cmd[] = { '@', 'C', 'V' };
+	u8 reply[4];
+	int state, ret;
+
+	/* poll the power button */
+	ret = qnap_mcu_exec(idev->mcu, cmd, sizeof(cmd), reply, sizeof(reply));
+	if (ret)
+		return;
+
+	/* First bytes must mirror the sent command */
+	if (memcmp(cmd, reply, sizeof(cmd))) {
+		dev_err(idev->dev, "malformed data received\n");
+		return;
+	}
+
+	state = reply[3] - 0x30;
+	input_event(input, EV_KEY, KEY_POWER, state);
+	input_sync(input);
+}
+
+static void qnap_mcu_input_beeper_work(struct work_struct *work)
+{
+	struct qnap_mcu_input_dev *idev =
+		container_of(work, struct qnap_mcu_input_dev, beep_work);
+	const u8 cmd[] = { '@', 'C', (idev->beep_type == SND_TONE) ? '3' : '2' };
+
+	qnap_mcu_exec_with_ack(idev->mcu, cmd, sizeof(cmd));
+}
+
+static int qnap_mcu_input_event(struct input_dev *input, unsigned int type,
+				unsigned int code, int value)
+{
+	struct qnap_mcu_input_dev *idev = input_get_drvdata(input);
+
+	if (type != EV_SND || (code != SND_BELL && code != SND_TONE))
+		return -EOPNOTSUPP;
+
+	if (value < 0)
+		return -EINVAL;
+
+	/* beep runtime is determined by the MCU */
+	if (value == 0)
+		return 0;
+
+	/* Schedule work to actually turn the beeper on */
+	idev->beep_type = code;
+	schedule_work(&idev->beep_work);
+
+	return 0;
+}
+
+static void qnap_mcu_input_close(struct input_dev *input)
+{
+	struct qnap_mcu_input_dev *idev = input_get_drvdata(input);
+
+	cancel_work_sync(&idev->beep_work);
+}
+
+static int qnap_mcu_input_probe(struct platform_device *pdev)
+{
+	struct qnap_mcu *mcu = dev_get_drvdata(pdev->dev.parent);
+	struct qnap_mcu_input_dev *idev;
+	struct device *dev = &pdev->dev;
+	struct input_dev *input;
+	int ret;
+
+	idev = devm_kzalloc(dev, sizeof(*idev), GFP_KERNEL);
+	if (!idev)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(dev);
+	if (!input)
+		return -ENOMEM;
+
+	idev->input = input;
+	idev->dev = dev;
+	idev->mcu = mcu;
+
+	input_set_drvdata(input, idev);
+
+	input->name		= "qnap-mcu";
+	input->phys		= "qnap-mcu-input/input0";
+	input->id.bustype	= BUS_HOST;
+	input->id.vendor	= 0x0001;
+	input->id.product	= 0x0001;
+	input->id.version	= 0x0100;
+	input->event		= qnap_mcu_input_event;
+	input->close		= qnap_mcu_input_close;
+
+	input_set_capability(input, EV_KEY, KEY_POWER);
+	input_set_capability(input, EV_SND, SND_BELL);
+	input_set_capability(input, EV_SND, SND_TONE);
+
+	INIT_WORK(&idev->beep_work, qnap_mcu_input_beeper_work);
+
+	ret = input_setup_polling(input, qnap_mcu_input_poll);
+	if (ret)
+		return dev_err_probe(dev, ret, "unable to set up polling\n");
+
+	input_set_poll_interval(input, POLL_INTERVAL);
+
+	ret = input_register_device(input);
+	if (ret)
+		return dev_err_probe(dev, ret, "unable to register input device\n");
+
+	return 0;
+}
+
+static struct platform_driver qnap_mcu_input_driver = {
+	.probe = qnap_mcu_input_probe,
+	.driver = {
+		.name = "qnap-mcu-input",
+	},
+};
+module_platform_driver(qnap_mcu_input_driver);
+
+MODULE_ALIAS("platform:qnap-mcu-input");
+MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
+MODULE_DESCRIPTION("QNAP MCU input driver");
+MODULE_LICENSE("GPL");