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, 83 insertions, 0 deletions

diff --git a/drivers/hwmon/surface_fan.c b/drivers/hwmon/surface_fan.c
new file mode 100644
index 000000000..aafb4ac92
--- /dev/null
+++ b/drivers/hwmon/surface_fan.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Surface Fan driver for Surface System Aggregator Module. It provides access
+ * to the fan's rpm through the hwmon system.
+ *
+ * Copyright (C) 2023 Ivor Wanders <ivor@iwanders.net>
+ */
+
+#include <linux/hwmon.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/surface_aggregator/device.h>
+#include <linux/types.h>
+
+// SSAM
+SSAM_DEFINE_SYNC_REQUEST_CL_R(__ssam_fan_rpm_get, __le16, {
+	.target_category = SSAM_SSH_TC_FAN,
+	.command_id      = 0x01,
+});
+
+static int surface_fan_hwmon_read(struct device *dev,
+				  enum hwmon_sensor_types type, u32 attr,
+				  int channel, long *val)
+{
+	struct ssam_device *sdev = dev_get_drvdata(dev);
+	int ret;
+	__le16 value;
+
+	ret = __ssam_fan_rpm_get(sdev, &value);
+	if (ret)
+		return ret;
+
+	*val = le16_to_cpu(value);
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *const surface_fan_info[] = {
+	HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT),
+	NULL
+};
+
+static const struct hwmon_ops surface_fan_hwmon_ops = {
+	.visible = 0444,
+	.read = surface_fan_hwmon_read,
+};
+
+static const struct hwmon_chip_info surface_fan_chip_info = {
+	.ops = &surface_fan_hwmon_ops,
+	.info = surface_fan_info,
+};
+
+static int surface_fan_probe(struct ssam_device *sdev)
+{
+	struct device *hdev;
+
+	hdev = devm_hwmon_device_register_with_info(&sdev->dev,
+						    "surface_fan", sdev,
+						    &surface_fan_chip_info,
+						    NULL);
+
+	return PTR_ERR_OR_ZERO(hdev);
+}
+
+static const struct ssam_device_id ssam_fan_match[] = {
+	{ SSAM_SDEV(FAN, SAM, 0x01, 0x01) },
+	{},
+};
+MODULE_DEVICE_TABLE(ssam, ssam_fan_match);
+
+static struct ssam_device_driver surface_fan = {
+	.probe = surface_fan_probe,
+	.match_table = ssam_fan_match,
+	.driver = {
+		.name = "surface_fan",
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+	},
+};
+module_ssam_device_driver(surface_fan);
+
+MODULE_AUTHOR("Ivor Wanders <ivor@iwanders.net>");
+MODULE_DESCRIPTION("Fan Driver for Surface System Aggregator Module");
+MODULE_LICENSE("GPL");