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, 113 insertions, 0 deletions

diff --git a/drivers/reset/reset-eic7700-hsp.c b/drivers/reset/reset-eic7700-hsp.c
new file mode 100644
index 000000000..1575ee4a2
--- /dev/null
+++ b/drivers/reset/reset-eic7700-hsp.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2026, Beijing ESWIN Computing Technology Co., Ltd..
+ * All rights reserved.
+ *
+ * ESWIN EIC7700 HSP Reset Driver
+ *
+ * Authors: Xuyang Dong <dongxuyang@eswincomputing.com>
+ */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/reset/eswin,eic7700-hspcrg.h>
+
+/**
+ * struct eic7700_hsp_reset_data - reset controller information structure
+ * @rcdev: reset controller entity
+ * @regmap: regmap handle containing the memory-mapped reset registers
+ */
+struct eic7700_hsp_reset_data {
+	struct reset_controller_dev rcdev;
+	struct regmap *regmap;
+};
+
+struct eic7700_hsp_reg {
+	u32 reg;
+	u32 bit;
+	bool active_low;
+};
+
+static inline struct eic7700_hsp_reset_data *
+to_eic7700_hsp_reset(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct eic7700_hsp_reset_data, rcdev);
+}
+
+static const struct eic7700_hsp_reg eic7700_hsp_reset[] = {
+	[EIC7700_HSP_RST_SATA_P0]	= {0x340, BIT(0), false},
+	[EIC7700_HSP_RST_SATA_PHY]	= {0x340, BIT(1), false},
+	[EIC7700_HSP_RST_USB0]		= {0x800, BIT(24), true},
+	[EIC7700_HSP_RST_USB1]		= {0x900, BIT(24), true},
+	[EIC7700_HSP_RST_USB0_PHY]	= {0x800, BIT(25), false},
+	[EIC7700_HSP_RST_USB1_PHY]	= {0x900, BIT(25), false},
+};
+
+static int eic7700_hsp_reset_assert(struct reset_controller_dev *rcdev,
+				    unsigned long id)
+{
+	struct eic7700_hsp_reset_data *data = to_eic7700_hsp_reset(rcdev);
+
+	return regmap_assign_bits(data->regmap, eic7700_hsp_reset[id].reg,
+				  eic7700_hsp_reset[id].bit,
+				  !eic7700_hsp_reset[id].active_low);
+}
+
+static int eic7700_hsp_reset_deassert(struct reset_controller_dev *rcdev,
+				      unsigned long id)
+{
+	struct eic7700_hsp_reset_data *data = to_eic7700_hsp_reset(rcdev);
+
+	return regmap_assign_bits(data->regmap, eic7700_hsp_reset[id].reg,
+				  eic7700_hsp_reset[id].bit,
+				  eic7700_hsp_reset[id].active_low);
+}
+
+static const struct reset_control_ops eic7700_hsp_reset_ops = {
+	.assert = eic7700_hsp_reset_assert,
+	.deassert = eic7700_hsp_reset_deassert,
+};
+
+static int eic7700_hsp_reset_probe(struct auxiliary_device *adev,
+				   const struct auxiliary_device_id *id)
+{
+	struct eic7700_hsp_reset_data *data;
+	struct device *dev = &adev->dev;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!data->regmap)
+		return dev_err_probe(dev, -ENODEV, "failed to get regmap!\n");
+
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.ops = &eic7700_hsp_reset_ops;
+	data->rcdev.of_node = dev->parent->of_node;
+	data->rcdev.dev = dev;
+	data->rcdev.nr_resets = ARRAY_SIZE(eic7700_hsp_reset);
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static const struct auxiliary_device_id eic7700_hsp_reset_ids[] = {
+	{ .name = "clk_eic7700_hsp.hsp-reset", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(auxiliary, eic7700_hsp_reset_ids);
+
+static struct auxiliary_driver eic7700_hsp_reset_driver = {
+	.probe	= eic7700_hsp_reset_probe,
+	.id_table = eic7700_hsp_reset_ids,
+};
+
+module_auxiliary_driver(eic7700_hsp_reset_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Xuyang Dong <dongxuyang@eswincomputing.com>");
+MODULE_DESCRIPTION("ESWIN EIC7700 HSP Reset Controller Driver");