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, 74 insertions, 0 deletions

diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c
new file mode 100644
index 000000000..5c907c2c0
--- /dev/null
+++ b/arch/arm/mach-tegra/hotplug.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 2002 ARM Ltd.
+ *  All Rights Reserved
+ *  Copyright (c) 2010, 2012-2013, NVIDIA Corporation. All rights reserved.
+ */
+
+#include <linux/clk/tegra.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+
+#include <soc/tegra/common.h>
+#include <soc/tegra/fuse.h>
+
+#include <asm/smp_plat.h>
+
+#include "common.h"
+#include "sleep.h"
+
+static void (*tegra_hotplug_shutdown)(void);
+
+int tegra_cpu_kill(unsigned cpu)
+{
+	cpu = cpu_logical_map(cpu);
+
+	/* Clock gate the CPU */
+	tegra_wait_cpu_in_reset(cpu);
+	tegra_disable_cpu_clock(cpu);
+
+	return 1;
+}
+
+/*
+ * platform-specific code to shutdown a CPU
+ *
+ * Called with IRQs disabled
+ */
+void tegra_cpu_die(unsigned int cpu)
+{
+	if (!tegra_hotplug_shutdown) {
+		WARN(1, "hotplug is not yet initialized\n");
+		return;
+	}
+
+	/* Clean L1 data cache */
+	tegra_disable_clean_inv_dcache(TEGRA_FLUSH_CACHE_LOUIS);
+
+	/* Shut down the current CPU. */
+	tegra_hotplug_shutdown();
+
+	/* Should never return here. */
+	BUG();
+}
+
+static int __init tegra_hotplug_init(void)
+{
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return 0;
+
+	if (!soc_is_tegra())
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_TEGRA_2x_SOC) && tegra_get_chip_id() == TEGRA20)
+		tegra_hotplug_shutdown = tegra20_hotplug_shutdown;
+	if (IS_ENABLED(CONFIG_ARCH_TEGRA_3x_SOC) && tegra_get_chip_id() == TEGRA30)
+		tegra_hotplug_shutdown = tegra30_hotplug_shutdown;
+	if (IS_ENABLED(CONFIG_ARCH_TEGRA_114_SOC) && tegra_get_chip_id() == TEGRA114)
+		tegra_hotplug_shutdown = tegra30_hotplug_shutdown;
+	if (IS_ENABLED(CONFIG_ARCH_TEGRA_124_SOC) && tegra_get_chip_id() == TEGRA124)
+		tegra_hotplug_shutdown = tegra30_hotplug_shutdown;
+
+	return 0;
+}
+pure_initcall(tegra_hotplug_init);