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, 174 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-pl030.c b/drivers/rtc/rtc-pl030.c
new file mode 100644
index 000000000..5caaa714f
--- /dev/null
+++ b/drivers/rtc/rtc-pl030.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/drivers/rtc/rtc-pl030.c
+ *
+ *  Copyright (C) 2000-2001 Deep Blue Solutions Ltd.
+ */
+#include <linux/module.h>
+#include <linux/rtc.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/amba/bus.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+
+#define RTC_DR		(0)
+#define RTC_MR		(4)
+#define RTC_STAT	(8)
+#define RTC_EOI		(8)
+#define RTC_LR		(12)
+#define RTC_CR		(16)
+#define RTC_CR_MIE	(1 << 0)
+
+struct pl030_rtc {
+	void __iomem		*base;
+};
+
+static irqreturn_t pl030_interrupt(int irq, void *dev_id)
+{
+	struct pl030_rtc *rtc = dev_id;
+	writel(0, rtc->base + RTC_EOI);
+	return IRQ_HANDLED;
+}
+
+static int pl030_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct pl030_rtc *rtc = dev_get_drvdata(dev);
+
+	rtc_time64_to_tm(readl(rtc->base + RTC_MR), &alrm->time);
+	return 0;
+}
+
+static int pl030_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct pl030_rtc *rtc = dev_get_drvdata(dev);
+
+	writel(rtc_tm_to_time64(&alrm->time), rtc->base + RTC_MR);
+
+	return 0;
+}
+
+static int pl030_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct pl030_rtc *rtc = dev_get_drvdata(dev);
+
+	rtc_time64_to_tm(readl(rtc->base + RTC_DR), tm);
+
+	return 0;
+}
+
+/*
+ * Set the RTC time.  Unfortunately, we can't accurately set
+ * the point at which the counter updates.
+ *
+ * Also, since RTC_LR is transferred to RTC_CR on next rising
+ * edge of the 1Hz clock, we must write the time one second
+ * in advance.
+ */
+static int pl030_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct pl030_rtc *rtc = dev_get_drvdata(dev);
+
+	writel(rtc_tm_to_time64(tm) + 1, rtc->base + RTC_LR);
+
+	return 0;
+}
+
+static const struct rtc_class_ops pl030_ops = {
+	.read_time	= pl030_read_time,
+	.set_time	= pl030_set_time,
+	.read_alarm	= pl030_read_alarm,
+	.set_alarm	= pl030_set_alarm,
+};
+
+static int pl030_probe(struct amba_device *dev, const struct amba_id *id)
+{
+	struct pl030_rtc *rtc;
+	int ret;
+	struct rtc_device *rtc_dev;
+
+	ret = amba_request_regions(dev, NULL);
+	if (ret)
+		goto err_req;
+
+	rtc = devm_kzalloc(&dev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc) {
+		ret = -ENOMEM;
+		goto err_rtc;
+	}
+
+	rtc_dev = devm_rtc_allocate_device(&dev->dev);
+	if (IS_ERR(rtc_dev)) {
+		ret = PTR_ERR(rtc_dev);
+		goto err_rtc;
+	}
+
+	rtc_dev->ops = &pl030_ops;
+	rtc_dev->range_max = U32_MAX;
+	rtc->base = ioremap(dev->res.start, resource_size(&dev->res));
+	if (!rtc->base) {
+		ret = -ENOMEM;
+		goto err_rtc;
+	}
+
+	__raw_writel(0, rtc->base + RTC_CR);
+	__raw_writel(0, rtc->base + RTC_EOI);
+
+	amba_set_drvdata(dev, rtc);
+
+	ret = request_irq(dev->irq[0], pl030_interrupt, 0,
+			  "rtc-pl030", rtc);
+	if (ret)
+		goto err_irq;
+
+	ret = devm_rtc_register_device(rtc_dev);
+	if (ret)
+		goto err_reg;
+
+	return 0;
+
+ err_reg:
+	free_irq(dev->irq[0], rtc);
+ err_irq:
+	iounmap(rtc->base);
+ err_rtc:
+	amba_release_regions(dev);
+ err_req:
+	return ret;
+}
+
+static void pl030_remove(struct amba_device *dev)
+{
+	struct pl030_rtc *rtc = amba_get_drvdata(dev);
+
+	writel(0, rtc->base + RTC_CR);
+
+	free_irq(dev->irq[0], rtc);
+	iounmap(rtc->base);
+	amba_release_regions(dev);
+}
+
+static const struct amba_id pl030_ids[] = {
+	{
+		.id	= 0x00041030,
+		.mask	= 0x000fffff,
+	},
+	{ 0, 0 },
+};
+
+MODULE_DEVICE_TABLE(amba, pl030_ids);
+
+static struct amba_driver pl030_driver = {
+	.drv		= {
+		.name	= "rtc-pl030",
+	},
+	.probe		= pl030_probe,
+	.remove		= pl030_remove,
+	.id_table	= pl030_ids,
+};
+
+module_amba_driver(pl030_driver);
+
+MODULE_AUTHOR("Russell King <rmk@arm.linux.org.uk>");
+MODULE_DESCRIPTION("ARM AMBA PL030 RTC Driver");
+MODULE_LICENSE("GPL");