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, 132 insertions, 0 deletions

diff --git a/drivers/reset/reset-qcom-aoss.c b/drivers/reset/reset-qcom-aoss.c
new file mode 100644
index 000000000..93c84d70e
--- /dev/null
+++ b/drivers/reset/reset-qcom-aoss.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <dt-bindings/reset/qcom,sdm845-aoss.h>
+
+struct qcom_aoss_reset_map {
+	unsigned int reg;
+};
+
+struct qcom_aoss_desc {
+	const struct qcom_aoss_reset_map *resets;
+	size_t num_resets;
+};
+
+struct qcom_aoss_reset_data {
+	struct reset_controller_dev rcdev;
+	void __iomem *base;
+	const struct qcom_aoss_desc *desc;
+};
+
+static const struct qcom_aoss_reset_map sdm845_aoss_resets[] = {
+	[AOSS_CC_MSS_RESTART] = {0x10000},
+	[AOSS_CC_CAMSS_RESTART] = {0x11000},
+	[AOSS_CC_VENUS_RESTART] = {0x12000},
+	[AOSS_CC_GPU_RESTART] = {0x13000},
+	[AOSS_CC_DISPSS_RESTART] = {0x14000},
+	[AOSS_CC_WCSS_RESTART] = {0x20000},
+	[AOSS_CC_LPASS_RESTART] = {0x30000},
+};
+
+static const struct qcom_aoss_desc sdm845_aoss_desc = {
+	.resets = sdm845_aoss_resets,
+	.num_resets = ARRAY_SIZE(sdm845_aoss_resets),
+};
+
+static inline struct qcom_aoss_reset_data *to_qcom_aoss_reset_data(
+				struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct qcom_aoss_reset_data, rcdev);
+}
+
+static int qcom_aoss_control_assert(struct reset_controller_dev *rcdev,
+				    unsigned long idx)
+{
+	struct qcom_aoss_reset_data *data = to_qcom_aoss_reset_data(rcdev);
+	const struct qcom_aoss_reset_map *map = &data->desc->resets[idx];
+
+	writel(1, data->base + map->reg);
+	/* Wait 6 32kHz sleep cycles for reset */
+	usleep_range(200, 300);
+	return 0;
+}
+
+static int qcom_aoss_control_deassert(struct reset_controller_dev *rcdev,
+				      unsigned long idx)
+{
+	struct qcom_aoss_reset_data *data = to_qcom_aoss_reset_data(rcdev);
+	const struct qcom_aoss_reset_map *map = &data->desc->resets[idx];
+
+	writel(0, data->base + map->reg);
+	/* Wait 6 32kHz sleep cycles for reset */
+	usleep_range(200, 300);
+	return 0;
+}
+
+static int qcom_aoss_control_reset(struct reset_controller_dev *rcdev,
+					unsigned long idx)
+{
+	qcom_aoss_control_assert(rcdev, idx);
+
+	return qcom_aoss_control_deassert(rcdev, idx);
+}
+
+static const struct reset_control_ops qcom_aoss_reset_ops = {
+	.reset = qcom_aoss_control_reset,
+	.assert = qcom_aoss_control_assert,
+	.deassert = qcom_aoss_control_deassert,
+};
+
+static int qcom_aoss_reset_probe(struct platform_device *pdev)
+{
+	struct qcom_aoss_reset_data *data;
+	struct device *dev = &pdev->dev;
+	const struct qcom_aoss_desc *desc;
+
+	desc = of_device_get_match_data(dev);
+	if (!desc)
+		return -EINVAL;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->desc = desc;
+	data->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.ops = &qcom_aoss_reset_ops;
+	data->rcdev.nr_resets = desc->num_resets;
+	data->rcdev.of_node = dev->of_node;
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static const struct of_device_id qcom_aoss_reset_of_match[] = {
+	{ .compatible = "qcom,sdm845-aoss-cc", .data = &sdm845_aoss_desc },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qcom_aoss_reset_of_match);
+
+static struct platform_driver qcom_aoss_reset_driver = {
+	.probe = qcom_aoss_reset_probe,
+	.driver  = {
+		.name = "qcom_aoss_reset",
+		.of_match_table = qcom_aoss_reset_of_match,
+	},
+};
+
+module_platform_driver(qcom_aoss_reset_driver);
+
+MODULE_DESCRIPTION("Qualcomm AOSS Reset Driver");
+MODULE_LICENSE("GPL v2");