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, 226 insertions, 0 deletions

diff --git a/drivers/input/input-leds.c b/drivers/input/input-leds.c
new file mode 100644
index 000000000..b08d1d08d
--- /dev/null
+++ b/drivers/input/input-leds.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2015 Samuel Thibault <samuel.thibault@ens-lyon.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/input.h>
+
+#if IS_ENABLED(CONFIG_VT)
+#define VT_TRIGGER(_name)	.trigger = _name
+#else
+#define VT_TRIGGER(_name)	.trigger = NULL
+#endif
+
+#if IS_ENABLED(CONFIG_SND_CTL_LED)
+#define AUDIO_TRIGGER(_name)	.trigger = _name
+#else
+#define AUDIO_TRIGGER(_name)	.trigger = NULL
+#endif
+
+static const struct {
+	const char *name;
+	const char *trigger;
+} input_led_info[LED_CNT] = {
+	[LED_NUML]	= { "numlock", VT_TRIGGER("kbd-numlock") },
+	[LED_CAPSL]	= { "capslock", VT_TRIGGER("kbd-capslock") },
+	[LED_SCROLLL]	= { "scrolllock", VT_TRIGGER("kbd-scrolllock") },
+	[LED_COMPOSE]	= { "compose" },
+	[LED_KANA]	= { "kana", VT_TRIGGER("kbd-kanalock") },
+	[LED_SLEEP]	= { "sleep" } ,
+	[LED_SUSPEND]	= { "suspend" },
+	[LED_MUTE]	= { "mute", AUDIO_TRIGGER("audio-mute") },
+	[LED_MISC]	= { "misc" },
+	[LED_MAIL]	= { "mail" },
+	[LED_CHARGING]	= { "charging" },
+};
+
+struct input_led {
+	struct led_classdev cdev;
+	struct input_handle *handle;
+	unsigned int code; /* One of LED_* constants */
+};
+
+struct input_leds {
+	struct input_handle handle;
+	unsigned int num_leds;
+	struct input_led leds[] __counted_by(num_leds);
+};
+
+static enum led_brightness input_leds_brightness_get(struct led_classdev *cdev)
+{
+	struct input_led *led = container_of(cdev, struct input_led, cdev);
+	struct input_dev *input = led->handle->dev;
+
+	return test_bit(led->code, input->led) ? cdev->max_brightness : 0;
+}
+
+static void input_leds_brightness_set(struct led_classdev *cdev,
+				      enum led_brightness brightness)
+{
+	struct input_led *led = container_of(cdev, struct input_led, cdev);
+
+	input_inject_event(led->handle, EV_LED, led->code, !!brightness);
+}
+
+static void input_leds_event(struct input_handle *handle, unsigned int type,
+			     unsigned int code, int value)
+{
+}
+
+static int input_leds_get_count(struct input_dev *dev)
+{
+	unsigned int led_code;
+	int count = 0;
+
+	for_each_set_bit(led_code, dev->ledbit, LED_CNT)
+		if (input_led_info[led_code].name)
+			count++;
+
+	return count;
+}
+
+static int input_leds_connect(struct input_handler *handler,
+			      struct input_dev *dev,
+			      const struct input_device_id *id)
+{
+	struct input_leds *leds;
+	struct input_led *led;
+	unsigned int num_leds;
+	unsigned int led_code;
+	int led_no;
+	int error;
+
+	num_leds = input_leds_get_count(dev);
+	if (!num_leds)
+		return -ENXIO;
+
+	leds = kzalloc_flex(*leds, leds, num_leds);
+	if (!leds)
+		return -ENOMEM;
+
+	leds->num_leds = num_leds;
+
+	leds->handle.dev = dev;
+	leds->handle.handler = handler;
+	leds->handle.name = "leds";
+	leds->handle.private = leds;
+
+	error = input_register_handle(&leds->handle);
+	if (error)
+		goto err_free_mem;
+
+	error = input_open_device(&leds->handle);
+	if (error)
+		goto err_unregister_handle;
+
+	led_no = 0;
+	for_each_set_bit(led_code, dev->ledbit, LED_CNT) {
+		if (!input_led_info[led_code].name)
+			continue;
+
+		led = &leds->leds[led_no];
+		led->handle = &leds->handle;
+		led->code = led_code;
+
+		led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s",
+					   dev_name(&dev->dev),
+					   input_led_info[led_code].name);
+		if (!led->cdev.name) {
+			error = -ENOMEM;
+			goto err_unregister_leds;
+		}
+
+		led->cdev.max_brightness = 1;
+		led->cdev.brightness_get = input_leds_brightness_get;
+		led->cdev.brightness_set = input_leds_brightness_set;
+		led->cdev.default_trigger = input_led_info[led_code].trigger;
+
+		error = led_classdev_register(&dev->dev, &led->cdev);
+		if (error) {
+			dev_err(&dev->dev, "failed to register LED %s: %d\n",
+				led->cdev.name, error);
+			kfree(led->cdev.name);
+			goto err_unregister_leds;
+		}
+
+		led_no++;
+	}
+
+	return 0;
+
+err_unregister_leds:
+	while (--led_no >= 0) {
+		struct input_led *led = &leds->leds[led_no];
+
+		led_classdev_unregister(&led->cdev);
+		kfree(led->cdev.name);
+	}
+
+	input_close_device(&leds->handle);
+
+err_unregister_handle:
+	input_unregister_handle(&leds->handle);
+
+err_free_mem:
+	kfree(leds);
+	return error;
+}
+
+static void input_leds_disconnect(struct input_handle *handle)
+{
+	struct input_leds *leds = handle->private;
+	int i;
+
+	for (i = 0; i < leds->num_leds; i++) {
+		struct input_led *led = &leds->leds[i];
+
+		led_classdev_unregister(&led->cdev);
+		kfree(led->cdev.name);
+	}
+
+	input_close_device(handle);
+	input_unregister_handle(handle);
+
+	kfree(leds);
+}
+
+static const struct input_device_id input_leds_ids[] = {
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
+		.evbit = { BIT_MASK(EV_LED) },
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(input, input_leds_ids);
+
+static struct input_handler input_leds_handler = {
+	.event =	input_leds_event,
+	.connect =	input_leds_connect,
+	.disconnect =	input_leds_disconnect,
+	.name =		"leds",
+	.id_table =	input_leds_ids,
+};
+
+static int __init input_leds_init(void)
+{
+	return input_register_handler(&input_leds_handler);
+}
+module_init(input_leds_init);
+
+static void __exit input_leds_exit(void)
+{
+	input_unregister_handler(&input_leds_handler);
+}
+module_exit(input_leds_exit);
+
+MODULE_AUTHOR("Samuel Thibault <samuel.thibault@ens-lyon.org>");
+MODULE_AUTHOR("Dmitry Torokhov <dmitry.torokhov@gmail.com>");
+MODULE_DESCRIPTION("Input -> LEDs Bridge");
+MODULE_LICENSE("GPL v2");