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, 102 insertions, 0 deletions

diff --git a/sound/soc/sof/sof-acpi-dev.c b/sound/soc/sof/sof-acpi-dev.c
new file mode 100644
index 000000000..68bf1b570
--- /dev/null
+++ b/sound/soc/sof/sof-acpi-dev.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+//
+// This file is provided under a dual BSD/GPLv2 license.  When using or
+// redistributing this file, you may do so under either license.
+//
+// Copyright(c) 2018 Intel Corporation
+//
+// Author: Liam Girdwood <liam.r.girdwood@linux.intel.com>
+//
+
+#include <linux/acpi.h>
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include <sound/sof.h>
+#include "../intel/common/soc-intel-quirks.h"
+#include "ops.h"
+#include "sof-acpi-dev.h"
+
+/* platform specific devices */
+#include "intel/shim.h"
+
+static char *fw_path;
+module_param(fw_path, charp, 0444);
+MODULE_PARM_DESC(fw_path, "deprecated - moved to snd-sof module.");
+
+static char *tplg_path;
+module_param(tplg_path, charp, 0444);
+MODULE_PARM_DESC(tplg_path, "deprecated - moved to snd-sof module.");
+
+static int sof_acpi_debug;
+module_param_named(sof_acpi_debug, sof_acpi_debug, int, 0444);
+MODULE_PARM_DESC(sof_acpi_debug, "SOF ACPI debug options (0x0 all off)");
+
+#define SOF_ACPI_DISABLE_PM_RUNTIME BIT(0)
+
+EXPORT_NS_DEV_PM_OPS(sof_acpi_pm, SND_SOC_SOF_ACPI_DEV) = {
+	SYSTEM_SLEEP_PM_OPS(snd_sof_suspend, snd_sof_resume)
+	RUNTIME_PM_OPS(snd_sof_runtime_suspend, snd_sof_runtime_resume,
+		       snd_sof_runtime_idle)
+};
+
+static void sof_acpi_probe_complete(struct device *dev)
+{
+	dev_dbg(dev, "Completing SOF ACPI probe");
+
+	if (sof_acpi_debug & SOF_ACPI_DISABLE_PM_RUNTIME)
+		return;
+
+	/* allow runtime_pm */
+	pm_runtime_set_autosuspend_delay(dev, SND_SOF_SUSPEND_DELAY_MS);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_enable(dev);
+}
+
+int sof_acpi_probe(struct platform_device *pdev, const struct sof_dev_desc *desc)
+{
+	struct device *dev = &pdev->dev;
+	struct snd_sof_pdata *sof_pdata;
+
+	dev_dbg(dev, "ACPI DSP detected");
+
+	sof_pdata = devm_kzalloc(dev, sizeof(*sof_pdata), GFP_KERNEL);
+	if (!sof_pdata)
+		return -ENOMEM;
+
+	if (!desc->ops) {
+		dev_err(dev, "error: no matching ACPI descriptor ops\n");
+		return -ENODEV;
+	}
+
+	sof_pdata->desc = desc;
+	sof_pdata->dev = &pdev->dev;
+
+	sof_pdata->ipc_file_profile_base.ipc_type = desc->ipc_default;
+	sof_pdata->ipc_file_profile_base.fw_path = fw_path;
+	sof_pdata->ipc_file_profile_base.tplg_path = tplg_path;
+
+	/* set callback to be called on successful device probe to enable runtime_pm */
+	sof_pdata->sof_probe_complete = sof_acpi_probe_complete;
+
+	/* call sof helper for DSP hardware probe */
+	return snd_sof_device_probe(dev, sof_pdata);
+}
+EXPORT_SYMBOL_NS(sof_acpi_probe, "SND_SOC_SOF_ACPI_DEV");
+
+void sof_acpi_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	if (!(sof_acpi_debug & SOF_ACPI_DISABLE_PM_RUNTIME))
+		pm_runtime_disable(dev);
+
+	/* call sof helper for DSP hardware remove */
+	snd_sof_device_remove(dev);
+}
+EXPORT_SYMBOL_NS(sof_acpi_remove, "SND_SOC_SOF_ACPI_DEV");
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SOF support for ACPI platforms");