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, 71 insertions, 0 deletions

diff --git a/include/soc/tegra/flowctrl.h b/include/soc/tegra/flowctrl.h
new file mode 100644
index 000000000..2a60bd493
--- /dev/null
+++ b/include/soc/tegra/flowctrl.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Functions and macros to control the flowcontroller
+ *
+ * Copyright (c) 2010-2012, NVIDIA Corporation. All rights reserved.
+ */
+
+#ifndef __SOC_TEGRA_FLOWCTRL_H__
+#define __SOC_TEGRA_FLOWCTRL_H__
+
+#define FLOW_CTRL_HALT_CPU0_EVENTS	0x0
+#define FLOW_CTRL_WAITEVENT		(2 << 29)
+#define FLOW_CTRL_WAIT_FOR_INTERRUPT	(4 << 29)
+#define FLOW_CTRL_JTAG_RESUME		(1 << 28)
+#define FLOW_CTRL_SCLK_RESUME		(1 << 27)
+#define FLOW_CTRL_HALT_CPU_IRQ		(1 << 10)
+#define	FLOW_CTRL_HALT_CPU_FIQ		(1 << 8)
+#define FLOW_CTRL_HALT_LIC_IRQ		(1 << 11)
+#define FLOW_CTRL_HALT_LIC_FIQ		(1 << 10)
+#define FLOW_CTRL_HALT_GIC_IRQ		(1 << 9)
+#define FLOW_CTRL_HALT_GIC_FIQ		(1 << 8)
+#define FLOW_CTRL_CPU0_CSR		0x8
+#define	FLOW_CTRL_CSR_INTR_FLAG		(1 << 15)
+#define FLOW_CTRL_CSR_EVENT_FLAG	(1 << 14)
+#define FLOW_CTRL_CSR_ENABLE_EXT_CRAIL	(1 << 13)
+#define FLOW_CTRL_CSR_ENABLE_EXT_NCPU	(1 << 12)
+#define FLOW_CTRL_CSR_ENABLE_EXT_MASK ( \
+		FLOW_CTRL_CSR_ENABLE_EXT_NCPU | \
+		FLOW_CTRL_CSR_ENABLE_EXT_CRAIL)
+#define FLOW_CTRL_CSR_ENABLE		(1 << 0)
+#define FLOW_CTRL_HALT_CPU1_EVENTS	0x14
+#define FLOW_CTRL_CPU1_CSR		0x18
+
+#define TEGRA20_FLOW_CTRL_CSR_WFE_CPU0		(1 << 4)
+#define TEGRA20_FLOW_CTRL_CSR_WFE_BITMAP	(3 << 4)
+#define TEGRA20_FLOW_CTRL_CSR_WFI_BITMAP	0
+
+#define TEGRA30_FLOW_CTRL_CSR_WFI_CPU0		(1 << 8)
+#define TEGRA30_FLOW_CTRL_CSR_WFE_BITMAP	(0xF << 4)
+#define TEGRA30_FLOW_CTRL_CSR_WFI_BITMAP	(0xF << 8)
+
+#ifndef __ASSEMBLER__
+#ifdef CONFIG_SOC_TEGRA_FLOWCTRL
+u32 flowctrl_read_cpu_csr(unsigned int cpuid);
+void flowctrl_write_cpu_csr(unsigned int cpuid, u32 value);
+void flowctrl_write_cpu_halt(unsigned int cpuid, u32 value);
+
+void flowctrl_cpu_suspend_enter(unsigned int cpuid);
+void flowctrl_cpu_suspend_exit(unsigned int cpuid);
+#else
+static inline u32 flowctrl_read_cpu_csr(unsigned int cpuid)
+{
+	return 0;
+}
+
+static inline void flowctrl_write_cpu_csr(unsigned int cpuid, u32 value)
+{
+}
+
+static inline void flowctrl_write_cpu_halt(unsigned int cpuid, u32 value) {}
+
+static inline void flowctrl_cpu_suspend_enter(unsigned int cpuid)
+{
+}
+
+static inline void flowctrl_cpu_suspend_exit(unsigned int cpuid)
+{
+}
+#endif /* CONFIG_SOC_TEGRA_FLOWCTRL */
+#endif /* __ASSEMBLER__ */
+#endif /* __SOC_TEGRA_FLOWCTRL_H__ */