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, 165 insertions, 0 deletions

diff --git a/drivers/input/input-compat.c b/drivers/input/input-compat.c
new file mode 100644
index 000000000..8860a0730
--- /dev/null
+++ b/drivers/input/input-compat.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 32bit compatibility wrappers for the input subsystem.
+ *
+ * Very heavily based on evdev.c - Copyright (c) 1999-2002 Vojtech Pavlik
+ */
+
+#include <linux/export.h>
+#include <linux/sprintf.h>
+#include <linux/uaccess.h>
+#include "input-compat.h"
+
+#ifdef CONFIG_COMPAT
+
+int input_event_from_user(const char __user *buffer,
+			  struct input_event *event)
+{
+	if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+		struct input_event_compat compat_event;
+
+		if (copy_from_user(&compat_event, buffer,
+				   sizeof(struct input_event_compat)))
+			return -EFAULT;
+
+		event->input_event_sec = compat_event.sec;
+		event->input_event_usec = compat_event.usec;
+		event->type = compat_event.type;
+		event->code = compat_event.code;
+		event->value = compat_event.value;
+
+	} else {
+		if (copy_from_user(event, buffer, sizeof(struct input_event)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int input_event_to_user(char __user *buffer,
+			const struct input_event *event)
+{
+	if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+		struct input_event_compat compat_event;
+
+		compat_event.sec = event->input_event_sec;
+		compat_event.usec = event->input_event_usec;
+		compat_event.type = event->type;
+		compat_event.code = event->code;
+		compat_event.value = event->value;
+
+		if (copy_to_user(buffer, &compat_event,
+				 sizeof(struct input_event_compat)))
+			return -EFAULT;
+
+	} else {
+		if (copy_to_user(buffer, event, sizeof(struct input_event)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int input_ff_effect_from_user(const char __user *buffer, size_t size,
+			      struct ff_effect *effect)
+{
+	if (in_compat_syscall()) {
+		struct ff_effect_compat *compat_effect;
+
+		if (size != sizeof(struct ff_effect_compat))
+			return -EINVAL;
+
+		/*
+		 * It so happens that the pointer which needs to be changed
+		 * is the last field in the structure, so we can retrieve the
+		 * whole thing and replace just the pointer.
+		 */
+		compat_effect = (struct ff_effect_compat *)effect;
+
+		memset(effect, 0, sizeof(*effect));
+
+		if (copy_from_user(compat_effect, buffer,
+				   sizeof(struct ff_effect_compat)))
+			return -EFAULT;
+
+		if (compat_effect->type == FF_PERIODIC &&
+		    compat_effect->u.periodic.waveform == FF_CUSTOM)
+			effect->u.periodic.custom_data =
+				compat_ptr(compat_effect->u.periodic.custom_data);
+	} else {
+		if (size != sizeof(struct ff_effect))
+			return -EINVAL;
+
+		if (copy_from_user(effect, buffer, sizeof(struct ff_effect)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int input_bits_to_string(char *buf, int buf_size, unsigned long bits,
+			 bool skip_empty)
+{
+	int len = 0;
+
+	if (in_compat_syscall()) {
+		u32 dword = bits >> 32;
+		if (dword || !skip_empty)
+			len += snprintf(buf, buf_size, "%x ", dword);
+
+		dword = bits & 0xffffffffUL;
+		if (dword || !skip_empty || len)
+			len += snprintf(buf + len, max(buf_size - len, 0),
+					"%x", dword);
+	} else {
+		if (bits || !skip_empty)
+			len += snprintf(buf, buf_size, "%lx", bits);
+	}
+
+	return len;
+}
+
+#else
+
+int input_event_from_user(const char __user *buffer,
+			 struct input_event *event)
+{
+	if (copy_from_user(event, buffer, sizeof(struct input_event)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int input_event_to_user(char __user *buffer,
+			const struct input_event *event)
+{
+	if (copy_to_user(buffer, event, sizeof(struct input_event)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int input_ff_effect_from_user(const char __user *buffer, size_t size,
+			      struct ff_effect *effect)
+{
+	if (size != sizeof(struct ff_effect))
+		return -EINVAL;
+
+	if (copy_from_user(effect, buffer, sizeof(struct ff_effect)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int input_bits_to_string(char *buf, int buf_size, unsigned long bits,
+			 bool skip_empty)
+{
+	return bits || !skip_empty ?
+		snprintf(buf, buf_size, "%lx", bits) : 0;
+}
+
+#endif /* CONFIG_COMPAT */
+
+EXPORT_SYMBOL_GPL(input_event_from_user);
+EXPORT_SYMBOL_GPL(input_event_to_user);
+EXPORT_SYMBOL_GPL(input_ff_effect_from_user);