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, 218 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-cv1800.c b/drivers/rtc/rtc-cv1800.c
new file mode 100644
index 000000000..678c2c10b
--- /dev/null
+++ b/drivers/rtc/rtc-cv1800.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rtc-cv1800.c: RTC driver for Sophgo cv1800 RTC
+ *
+ * Author: Jingbao Qiu <qiujingbao.dlmu@gmail.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+
+#define SEC_PULSE_GEN          0x1004
+#define ALARM_TIME             0x1008
+#define ALARM_ENABLE           0x100C
+#define SET_SEC_CNTR_VAL       0x1010
+#define SET_SEC_CNTR_TRIG      0x1014
+#define SEC_CNTR_VAL           0x1018
+
+/*
+ * When in VDDBKUP domain, this MACRO register
+ * does not power down
+ */
+#define MACRO_RO_T             0x14A8
+#define MACRO_RG_SET_T         0x1498
+
+#define ALARM_ENABLE_MASK      BIT(0)
+#define SEL_SEC_PULSE          BIT(31)
+
+struct cv1800_rtc_priv {
+	struct rtc_device *rtc_dev;
+	struct regmap *rtc_map;
+	struct clk *clk;
+	int irq;
+};
+
+static bool cv1800_rtc_enabled(struct device *dev)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	u32 reg;
+
+	regmap_read(info->rtc_map, SEC_PULSE_GEN, &reg);
+
+	return (reg & SEL_SEC_PULSE) == 0;
+}
+
+static void cv1800_rtc_enable(struct device *dev)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+
+	/* Sec pulse generated internally */
+	regmap_update_bits(info->rtc_map, SEC_PULSE_GEN, SEL_SEC_PULSE, 0);
+}
+
+static int cv1800_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+
+	regmap_write(info->rtc_map, ALARM_ENABLE, enabled);
+
+	return 0;
+}
+
+static int cv1800_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	unsigned long alarm_time;
+
+	alarm_time = rtc_tm_to_time64(&alrm->time);
+
+	cv1800_rtc_alarm_irq_enable(dev, 0);
+
+	regmap_write(info->rtc_map, ALARM_TIME, alarm_time);
+
+	cv1800_rtc_alarm_irq_enable(dev, alrm->enabled);
+
+	return 0;
+}
+
+static int cv1800_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	u32 enabled;
+	u32 time;
+
+	if (!cv1800_rtc_enabled(dev)) {
+		alarm->enabled = 0;
+		return 0;
+	}
+
+	regmap_read(info->rtc_map, ALARM_ENABLE, &enabled);
+
+	alarm->enabled = enabled & ALARM_ENABLE_MASK;
+
+	regmap_read(info->rtc_map, ALARM_TIME, &time);
+
+	rtc_time64_to_tm(time, &alarm->time);
+
+	return 0;
+}
+
+static int cv1800_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	u32 sec;
+
+	if (!cv1800_rtc_enabled(dev))
+		return -EINVAL;
+
+	regmap_read(info->rtc_map, SEC_CNTR_VAL, &sec);
+
+	rtc_time64_to_tm(sec, tm);
+
+	return 0;
+}
+
+static int cv1800_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	unsigned long sec;
+
+	sec = rtc_tm_to_time64(tm);
+
+	regmap_write(info->rtc_map, SET_SEC_CNTR_VAL, sec);
+	regmap_write(info->rtc_map, SET_SEC_CNTR_TRIG, 1);
+
+	regmap_write(info->rtc_map, MACRO_RG_SET_T, sec);
+
+	cv1800_rtc_enable(dev);
+
+	return 0;
+}
+
+static irqreturn_t cv1800_rtc_irq_handler(int irq, void *dev_id)
+{
+	struct cv1800_rtc_priv *info = dev_id;
+
+	rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF);
+
+	regmap_write(info->rtc_map, ALARM_ENABLE, 0);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops cv1800_rtc_ops = {
+	.read_time = cv1800_rtc_read_time,
+	.set_time = cv1800_rtc_set_time,
+	.read_alarm = cv1800_rtc_read_alarm,
+	.set_alarm = cv1800_rtc_set_alarm,
+	.alarm_irq_enable = cv1800_rtc_alarm_irq_enable,
+};
+
+static int cv1800_rtc_probe(struct platform_device *pdev)
+{
+	struct cv1800_rtc_priv *rtc;
+	int ret;
+
+	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc->rtc_map = device_node_to_regmap(pdev->dev.parent->of_node);
+	if (IS_ERR(rtc->rtc_map))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rtc->rtc_map),
+				     "cannot get parent regmap\n");
+
+	rtc->irq = platform_get_irq(pdev, 0);
+	if (rtc->irq < 0)
+		return rtc->irq;
+
+	rtc->clk = devm_clk_get_enabled(pdev->dev.parent, "rtc");
+	if (IS_ERR(rtc->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rtc->clk),
+				     "rtc clk not found\n");
+
+	platform_set_drvdata(pdev, rtc);
+
+	device_init_wakeup(&pdev->dev, 1);
+
+	rtc->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc->rtc_dev))
+		return PTR_ERR(rtc->rtc_dev);
+
+	rtc->rtc_dev->ops = &cv1800_rtc_ops;
+	rtc->rtc_dev->range_max = U32_MAX;
+
+	ret = devm_request_irq(&pdev->dev, rtc->irq, cv1800_rtc_irq_handler,
+			       IRQF_TRIGGER_HIGH, "rtc alarm", rtc);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "cannot register interrupt handler\n");
+
+	return devm_rtc_register_device(rtc->rtc_dev);
+}
+
+static const struct platform_device_id cv1800_rtc_id[] = {
+	{ .name = "cv1800b-rtc" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(platform, cv1800_rtc_id);
+
+static struct platform_driver cv1800_rtc_driver = {
+	.driver = {
+		.name = "sophgo-cv1800-rtc",
+	},
+	.probe = cv1800_rtc_probe,
+	.id_table = cv1800_rtc_id,
+};
+
+module_platform_driver(cv1800_rtc_driver);
+MODULE_AUTHOR("Jingbao Qiu");
+MODULE_DESCRIPTION("Sophgo cv1800 RTC Driver");
+MODULE_LICENSE("GPL");