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, 81 insertions, 0 deletions

diff --git a/drivers/input/input-compat.h b/drivers/input/input-compat.h
new file mode 100644
index 000000000..99c87ceb9
--- /dev/null
+++ b/drivers/input/input-compat.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _INPUT_COMPAT_H
+#define _INPUT_COMPAT_H
+
+/*
+ * 32bit compatibility wrappers for the input subsystem.
+ *
+ * Very heavily based on evdev.c - Copyright (c) 1999-2002 Vojtech Pavlik
+ */
+
+#include <linux/compiler.h>
+#include <linux/compat.h>
+#include <linux/input.h>
+
+#ifdef CONFIG_COMPAT
+
+struct input_event_compat {
+	compat_ulong_t sec;
+	compat_ulong_t usec;
+	__u16 type;
+	__u16 code;
+	__s32 value;
+};
+
+struct ff_periodic_effect_compat {
+	__u16 waveform;
+	__u16 period;
+	__s16 magnitude;
+	__s16 offset;
+	__u16 phase;
+
+	struct ff_envelope envelope;
+
+	__u32 custom_len;
+	compat_uptr_t custom_data;
+};
+
+struct ff_effect_compat {
+	__u16 type;
+	__s16 id;
+	__u16 direction;
+	struct ff_trigger trigger;
+	struct ff_replay replay;
+
+	union {
+		struct ff_constant_effect constant;
+		struct ff_ramp_effect ramp;
+		struct ff_periodic_effect_compat periodic;
+		struct ff_condition_effect condition[2]; /* One for each axis */
+		struct ff_rumble_effect rumble;
+	} u;
+};
+
+static inline size_t input_event_size(void)
+{
+	return (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) ?
+		sizeof(struct input_event_compat) : sizeof(struct input_event);
+}
+
+#else
+
+static inline size_t input_event_size(void)
+{
+	return sizeof(struct input_event);
+}
+
+#endif /* CONFIG_COMPAT */
+
+int input_event_from_user(const char __user *buffer,
+			 struct input_event *event);
+
+int input_event_to_user(char __user *buffer,
+			const struct input_event *event);
+
+int input_ff_effect_from_user(const char __user *buffer, size_t size,
+			      struct ff_effect *effect);
+
+int input_bits_to_string(char *buf, int buf_size, unsigned long bits,
+                         bool skip_empty);
+
+#endif /* _INPUT_COMPAT_H */