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, 122 insertions, 0 deletions

diff --git a/drivers/input/apm-power.c b/drivers/input/apm-power.c
new file mode 100644
index 000000000..028fcaf4c
--- /dev/null
+++ b/drivers/input/apm-power.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Input Power Event -> APM Bridge
+ *
+ *  Copyright (c) 2007 Richard Purdie
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/input.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/delay.h>
+#include <linux/pm.h>
+#include <linux/apm-emulation.h>
+
+static void system_power_event(unsigned int keycode)
+{
+	switch (keycode) {
+	case KEY_SUSPEND:
+		apm_queue_event(APM_USER_SUSPEND);
+		pr_info("Requesting system suspend...\n");
+		break;
+	default:
+		break;
+	}
+}
+
+static void apmpower_event(struct input_handle *handle, unsigned int type,
+			   unsigned int code, int value)
+{
+	/* only react on key down events */
+	if (value != 1)
+		return;
+
+	switch (type) {
+	case EV_PWR:
+		system_power_event(code);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static int apmpower_connect(struct input_handler *handler,
+					  struct input_dev *dev,
+					  const struct input_device_id *id)
+{
+	struct input_handle *handle;
+	int error;
+
+	handle = kzalloc_obj(struct input_handle);
+	if (!handle)
+		return -ENOMEM;
+
+	handle->dev = dev;
+	handle->handler = handler;
+	handle->name = "apm-power";
+
+	error = input_register_handle(handle);
+	if (error) {
+		pr_err("Failed to register input power handler, error %d\n",
+		       error);
+		kfree(handle);
+		return error;
+	}
+
+	error = input_open_device(handle);
+	if (error) {
+		pr_err("Failed to open input power device, error %d\n", error);
+		input_unregister_handle(handle);
+		kfree(handle);
+		return error;
+	}
+
+	return 0;
+}
+
+static void apmpower_disconnect(struct input_handle *handle)
+{
+	input_close_device(handle);
+	input_unregister_handle(handle);
+	kfree(handle);
+}
+
+static const struct input_device_id apmpower_ids[] = {
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
+		.evbit = { BIT_MASK(EV_PWR) },
+	},
+	{ },
+};
+
+MODULE_DEVICE_TABLE(input, apmpower_ids);
+
+static struct input_handler apmpower_handler = {
+	.event =	apmpower_event,
+	.connect =	apmpower_connect,
+	.disconnect =	apmpower_disconnect,
+	.name =		"apm-power",
+	.id_table =	apmpower_ids,
+};
+
+static int __init apmpower_init(void)
+{
+	return input_register_handler(&apmpower_handler);
+}
+
+static void __exit apmpower_exit(void)
+{
+	input_unregister_handler(&apmpower_handler);
+}
+
+module_init(apmpower_init);
+module_exit(apmpower_exit);
+
+MODULE_AUTHOR("Richard Purdie <rpurdie@rpsys.net>");
+MODULE_DESCRIPTION("Input Power Event -> APM Bridge");
+MODULE_LICENSE("GPL");