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, 85 insertions, 0 deletions

diff --git a/drivers/firmware/imx/sm-cpu.c b/drivers/firmware/imx/sm-cpu.c
new file mode 100644
index 000000000..091b014f7
--- /dev/null
+++ b/drivers/firmware/imx/sm-cpu.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2025 NXP
+ */
+
+#include <linux/firmware/imx/sm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/scmi_protocol.h>
+#include <linux/scmi_imx_protocol.h>
+
+static const struct scmi_imx_cpu_proto_ops *imx_cpu_ops;
+static struct scmi_protocol_handle *ph;
+
+int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start, bool boot,
+				  bool resume)
+{
+	if (!ph)
+		return -EPROBE_DEFER;
+
+	return imx_cpu_ops->cpu_reset_vector_set(ph, cpuid, vector, start,
+						 boot, resume);
+}
+EXPORT_SYMBOL(scmi_imx_cpu_reset_vector_set);
+
+int scmi_imx_cpu_start(u32 cpuid, bool start)
+{
+	if (!ph)
+		return -EPROBE_DEFER;
+
+	if (start)
+		return imx_cpu_ops->cpu_start(ph, cpuid, true);
+
+	return imx_cpu_ops->cpu_start(ph, cpuid, false);
+};
+EXPORT_SYMBOL(scmi_imx_cpu_start);
+
+int scmi_imx_cpu_started(u32 cpuid, bool *started)
+{
+	if (!ph)
+		return -EPROBE_DEFER;
+
+	if (!started)
+		return -EINVAL;
+
+	return imx_cpu_ops->cpu_started(ph, cpuid, started);
+};
+EXPORT_SYMBOL(scmi_imx_cpu_started);
+
+static int scmi_imx_cpu_probe(struct scmi_device *sdev)
+{
+	const struct scmi_handle *handle = sdev->handle;
+
+	if (!handle)
+		return -ENODEV;
+
+	if (imx_cpu_ops) {
+		dev_err(&sdev->dev, "sm cpu already initialized\n");
+		return -EEXIST;
+	}
+
+	imx_cpu_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_IMX_CPU, &ph);
+	if (IS_ERR(imx_cpu_ops))
+		return PTR_ERR(imx_cpu_ops);
+
+	return 0;
+}
+
+static const struct scmi_device_id scmi_id_table[] = {
+	{ SCMI_PROTOCOL_IMX_CPU, "imx-cpu" },
+	{ },
+};
+MODULE_DEVICE_TABLE(scmi, scmi_id_table);
+
+static struct scmi_driver scmi_imx_cpu_driver = {
+	.name = "scmi-imx-cpu",
+	.probe = scmi_imx_cpu_probe,
+	.id_table = scmi_id_table,
+};
+module_scmi_driver(scmi_imx_cpu_driver);
+
+MODULE_AUTHOR("Peng Fan <peng.fan@nxp.com>");
+MODULE_DESCRIPTION("IMX SM CPU driver");
+MODULE_LICENSE("GPL");