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, 220 insertions, 0 deletions

diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
new file mode 100644
index 000000000..9c5b695db
--- /dev/null
+++ b/net/rfkill/rfkill-gpio.c
@@ -0,0 +1,220 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2011, NVIDIA Corporation.
+ */
+
+#include <linux/dmi.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rfkill.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/acpi.h>
+#include <linux/gpio/consumer.h>
+
+struct rfkill_gpio_data {
+	const char		*name;
+	enum rfkill_type	type;
+	struct gpio_desc	*reset_gpio;
+	struct gpio_desc	*shutdown_gpio;
+
+	struct rfkill		*rfkill_dev;
+	struct clk		*clk;
+
+	bool			clk_enabled;
+};
+
+static int rfkill_gpio_set_power(void *data, bool blocked)
+{
+	struct rfkill_gpio_data *rfkill = data;
+
+	if (!blocked && !IS_ERR(rfkill->clk) && !rfkill->clk_enabled) {
+		int ret = clk_enable(rfkill->clk);
+
+		if (ret)
+			return ret;
+	}
+
+	gpiod_set_value_cansleep(rfkill->shutdown_gpio, !blocked);
+	gpiod_set_value_cansleep(rfkill->reset_gpio, !blocked);
+
+	if (blocked && !IS_ERR(rfkill->clk) && rfkill->clk_enabled)
+		clk_disable(rfkill->clk);
+
+	rfkill->clk_enabled = !blocked;
+
+	return 0;
+}
+
+static const struct rfkill_ops rfkill_gpio_ops = {
+	.set_block = rfkill_gpio_set_power,
+};
+
+static const struct acpi_gpio_params reset_gpios = { 0, 0, false };
+static const struct acpi_gpio_params shutdown_gpios = { 1, 0, false };
+
+static const struct acpi_gpio_mapping acpi_rfkill_default_gpios[] = {
+	{ "reset-gpios", &reset_gpios, 1 },
+	{ "shutdown-gpios", &shutdown_gpios, 1 },
+	{ },
+};
+
+static int rfkill_gpio_acpi_probe(struct device *dev,
+				  struct rfkill_gpio_data *rfkill)
+{
+	const struct acpi_device_id *id;
+
+	id = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!id)
+		return -ENODEV;
+
+	rfkill->type = (unsigned)id->driver_data;
+
+	return devm_acpi_dev_add_driver_gpios(dev, acpi_rfkill_default_gpios);
+}
+
+/* List of DMI matches for devices on which rfkill-gpio should not load,
+ * to avoid firmware bugs.
+ */
+static const struct dmi_system_id rfkill_gpio_deny_table[] = {
+	{
+		/* Lenovo Yoga Tab 3 Pro YT3-X90, bogus "BCM4752" device in DSDT */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
+		},
+	},
+	{ }
+};
+
+static int rfkill_gpio_probe(struct platform_device *pdev)
+{
+	struct rfkill_gpio_data *rfkill;
+	const char *type_name = NULL;
+	const char *name_property;
+	const char *type_property;
+	struct gpio_desc *gpio;
+	int ret;
+
+	if (dmi_check_system(rfkill_gpio_deny_table))
+		return -ENODEV;
+
+	rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL);
+	if (!rfkill)
+		return -ENOMEM;
+
+	if (dev_of_node(&pdev->dev)) {
+		name_property = "label";
+		type_property = "radio-type";
+	} else {
+		name_property = "name";
+		type_property = "type";
+	}
+	device_property_read_string(&pdev->dev, name_property, &rfkill->name);
+	device_property_read_string(&pdev->dev, type_property, &type_name);
+
+	if (!rfkill->name)
+		rfkill->name = dev_name(&pdev->dev);
+
+	rfkill->type = rfkill_find_type(type_name);
+
+	if (ACPI_HANDLE(&pdev->dev)) {
+		ret = rfkill_gpio_acpi_probe(&pdev->dev, rfkill);
+		if (ret)
+			return ret;
+	}
+
+	rfkill->clk = devm_clk_get(&pdev->dev, NULL);
+
+	gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS);
+	if (IS_ERR(gpio))
+		return PTR_ERR(gpio);
+
+	rfkill->reset_gpio = gpio;
+
+	gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS);
+	if (IS_ERR(gpio))
+		return PTR_ERR(gpio);
+
+	rfkill->shutdown_gpio = gpio;
+
+	/* Make sure at-least one GPIO is defined for this instance */
+	if (!rfkill->reset_gpio && !rfkill->shutdown_gpio) {
+		dev_err(&pdev->dev, "invalid platform data\n");
+		return -EINVAL;
+	}
+
+	ret = gpiod_direction_output(rfkill->reset_gpio, true);
+	if (ret)
+		return ret;
+
+	ret = gpiod_direction_output(rfkill->shutdown_gpio, true);
+	if (ret)
+		return ret;
+
+	rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev,
+					  rfkill->type, &rfkill_gpio_ops,
+					  rfkill);
+	if (!rfkill->rfkill_dev)
+		return -ENOMEM;
+
+	if (device_property_present(&pdev->dev, "default-blocked"))
+		rfkill_init_sw_state(rfkill->rfkill_dev, true);
+
+	ret = rfkill_register(rfkill->rfkill_dev);
+	if (ret < 0)
+		goto err_destroy;
+
+	platform_set_drvdata(pdev, rfkill);
+
+	dev_info(&pdev->dev, "%s device registered.\n", rfkill->name);
+
+	return 0;
+
+err_destroy:
+	rfkill_destroy(rfkill->rfkill_dev);
+
+	return ret;
+}
+
+static void rfkill_gpio_remove(struct platform_device *pdev)
+{
+	struct rfkill_gpio_data *rfkill = platform_get_drvdata(pdev);
+
+	rfkill_unregister(rfkill->rfkill_dev);
+	rfkill_destroy(rfkill->rfkill_dev);
+}
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id rfkill_acpi_match[] = {
+	{ "BCM4752", RFKILL_TYPE_GPS },
+	{ "LNV4752", RFKILL_TYPE_GPS },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, rfkill_acpi_match);
+#endif
+
+static const struct of_device_id rfkill_of_match[] __maybe_unused = {
+	{ .compatible = "rfkill-gpio", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rfkill_of_match);
+
+static struct platform_driver rfkill_gpio_driver = {
+	.probe = rfkill_gpio_probe,
+	.remove = rfkill_gpio_remove,
+	.driver = {
+		.name = "rfkill_gpio",
+		.acpi_match_table = ACPI_PTR(rfkill_acpi_match),
+		.of_match_table = of_match_ptr(rfkill_of_match),
+	},
+};
+
+module_platform_driver(rfkill_gpio_driver);
+
+MODULE_DESCRIPTION("gpio rfkill");
+MODULE_AUTHOR("NVIDIA");
+MODULE_LICENSE("GPL");