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, 150 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c
new file mode 100644
index 000000000..7d38258cb
--- /dev/null
+++ b/drivers/rtc/rtc-meson-vrtc.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2015 Amlogic, Inc. All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/time64.h>
+
+struct meson_vrtc_data {
+	void __iomem *io_alarm;
+	unsigned long alarm_time;
+	bool enabled;
+};
+
+static int meson_vrtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct timespec64 time;
+
+	dev_dbg(dev, "%s\n", __func__);
+	ktime_get_real_ts64(&time);
+	rtc_time64_to_tm(time.tv_sec, tm);
+
+	return 0;
+}
+
+static void meson_vrtc_set_wakeup_time(struct meson_vrtc_data *vrtc,
+				       unsigned long time)
+{
+	writel_relaxed(time, vrtc->io_alarm);
+}
+
+static int meson_vrtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct meson_vrtc_data *vrtc = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s: alarm->enabled=%d\n", __func__, alarm->enabled);
+	if (alarm->enabled)
+		vrtc->alarm_time = rtc_tm_to_time64(&alarm->time);
+	else
+		vrtc->alarm_time = 0;
+
+	return 0;
+}
+
+static int meson_vrtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct meson_vrtc_data *vrtc = dev_get_drvdata(dev);
+
+	vrtc->enabled = enabled;
+	return 0;
+}
+
+static const struct rtc_class_ops meson_vrtc_ops = {
+	.read_time = meson_vrtc_read_time,
+	.set_alarm = meson_vrtc_set_alarm,
+	.alarm_irq_enable = meson_vrtc_alarm_irq_enable,
+};
+
+static int meson_vrtc_probe(struct platform_device *pdev)
+{
+	struct meson_vrtc_data *vrtc;
+	struct rtc_device *rtc;
+
+	vrtc = devm_kzalloc(&pdev->dev, sizeof(*vrtc), GFP_KERNEL);
+	if (!vrtc)
+		return -ENOMEM;
+
+	vrtc->io_alarm = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(vrtc->io_alarm))
+		return PTR_ERR(vrtc->io_alarm);
+
+	device_init_wakeup(&pdev->dev, true);
+
+	platform_set_drvdata(pdev, vrtc);
+
+	rtc = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	rtc->ops = &meson_vrtc_ops;
+	return devm_rtc_register_device(rtc);
+}
+
+static int __maybe_unused meson_vrtc_suspend(struct device *dev)
+{
+	struct meson_vrtc_data *vrtc = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+	if (vrtc->alarm_time) {
+		unsigned long local_time;
+		long alarm_secs;
+		struct timespec64 time;
+
+		ktime_get_real_ts64(&time);
+		local_time = time.tv_sec;
+
+		dev_dbg(dev, "alarm_time = %lus, local_time=%lus\n",
+			vrtc->alarm_time, local_time);
+		alarm_secs = vrtc->alarm_time - local_time;
+		if (alarm_secs > 0) {
+			meson_vrtc_set_wakeup_time(vrtc, alarm_secs);
+			dev_dbg(dev, "system will wakeup in %lds.\n",
+				alarm_secs);
+		} else {
+			dev_err(dev, "alarm time already passed: %lds.\n",
+				alarm_secs);
+		}
+	}
+
+	return 0;
+}
+
+static int __maybe_unused meson_vrtc_resume(struct device *dev)
+{
+	struct meson_vrtc_data *vrtc = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	vrtc->alarm_time = 0;
+	meson_vrtc_set_wakeup_time(vrtc, 0);
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(meson_vrtc_pm_ops,
+			 meson_vrtc_suspend, meson_vrtc_resume);
+
+static const struct of_device_id meson_vrtc_dt_match[] = {
+	{ .compatible = "amlogic,meson-vrtc"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, meson_vrtc_dt_match);
+
+static struct platform_driver meson_vrtc_driver = {
+	.probe = meson_vrtc_probe,
+	.driver = {
+		.name = "meson-vrtc",
+		.of_match_table = meson_vrtc_dt_match,
+		.pm = &meson_vrtc_pm_ops,
+	},
+};
+
+module_platform_driver(meson_vrtc_driver);
+
+MODULE_DESCRIPTION("Amlogic Virtual Wakeup RTC Timer driver");
+MODULE_LICENSE("GPL");