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, 92 insertions, 0 deletions

diff --git a/drivers/rtc/proc.c b/drivers/rtc/proc.c
new file mode 100644
index 000000000..cbcdbb19d
--- /dev/null
+++ b/drivers/rtc/proc.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC subsystem, proc interface
+ *
+ * Copyright (C) 2005-06 Tower Technologies
+ * Author: Alessandro Zummo <a.zummo@towertech.it>
+ *
+ * based on arch/arm/common/rtctime.c
+ */
+
+#include <linux/module.h>
+#include <linux/rtc.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+#include "rtc-core.h"
+
+#define NAME_SIZE	10
+
+#if defined(CONFIG_RTC_HCTOSYS_DEVICE)
+static bool is_rtc_hctosys(struct rtc_device *rtc)
+{
+	int size;
+	char name[NAME_SIZE];
+
+	size = snprintf(name, NAME_SIZE, "rtc%d", rtc->id);
+	if (size >= NAME_SIZE)
+		return false;
+
+	return !strncmp(name, CONFIG_RTC_HCTOSYS_DEVICE, NAME_SIZE);
+}
+#else
+static bool is_rtc_hctosys(struct rtc_device *rtc)
+{
+	return (rtc->id == 0);
+}
+#endif
+
+static int rtc_proc_show(struct seq_file *seq, void *offset)
+{
+	int err;
+	struct rtc_device *rtc = seq->private;
+	const struct rtc_class_ops *ops = rtc->ops;
+	struct rtc_wkalrm alrm;
+	struct rtc_time tm;
+
+	err = rtc_read_time(rtc, &tm);
+	if (err == 0) {
+		seq_printf(seq,
+			   "rtc_time\t: %ptRt\n"
+			   "rtc_date\t: %ptRd\n",
+			   &tm, &tm);
+	}
+
+	err = rtc_read_alarm(rtc, &alrm);
+	if (err == 0) {
+		seq_printf(seq, "alrm_time\t: %ptRt\n", &alrm.time);
+		seq_printf(seq, "alrm_date\t: %ptRd\n", &alrm.time);
+		seq_printf(seq, "alarm_IRQ\t: %s\n",
+			   alrm.enabled ? "yes" : "no");
+		seq_printf(seq, "alrm_pending\t: %s\n",
+			   alrm.pending ? "yes" : "no");
+		seq_printf(seq, "update IRQ enabled\t: %s\n",
+			   (rtc->uie_rtctimer.enabled) ? "yes" : "no");
+		seq_printf(seq, "periodic IRQ enabled\t: %s\n",
+			   (rtc->pie_enabled) ? "yes" : "no");
+		seq_printf(seq, "periodic IRQ frequency\t: %d\n",
+			   rtc->irq_freq);
+		seq_printf(seq, "max user IRQ frequency\t: %d\n",
+			   rtc->max_user_freq);
+	}
+
+	seq_printf(seq, "24hr\t\t: yes\n");
+
+	if (ops->proc)
+		ops->proc(rtc->dev.parent, seq);
+
+	return 0;
+}
+
+void rtc_proc_add_device(struct rtc_device *rtc)
+{
+	if (is_rtc_hctosys(rtc))
+		proc_create_single_data("driver/rtc", 0, NULL, rtc_proc_show,
+					rtc);
+}
+
+void rtc_proc_del_device(struct rtc_device *rtc)
+{
+	if (is_rtc_hctosys(rtc))
+		remove_proc_entry("driver/rtc", NULL);
+}