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, 68 insertions, 0 deletions

diff --git a/include/trace/events/devfreq.h b/include/trace/events/devfreq.h
new file mode 100644
index 000000000..6cbc4d59f
--- /dev/null
+++ b/include/trace/events/devfreq.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM devfreq
+
+#if !defined(_TRACE_DEVFREQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_DEVFREQ_H
+
+#include <linux/devfreq.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(devfreq_frequency,
+	TP_PROTO(struct devfreq *devfreq, unsigned long freq,
+		 unsigned long prev_freq),
+
+	TP_ARGS(devfreq, freq, prev_freq),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(&devfreq->dev))
+		__field(unsigned long, freq)
+		__field(unsigned long, prev_freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__entry->freq = freq;
+		__entry->prev_freq = prev_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+	),
+
+	TP_printk("dev_name=%-30s freq=%-12lu prev_freq=%-12lu load=%-2lu",
+		__get_str(dev_name), __entry->freq, __entry->prev_freq,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+
+TRACE_EVENT(devfreq_monitor,
+	TP_PROTO(struct devfreq *devfreq),
+
+	TP_ARGS(devfreq),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+		__field(unsigned int, polling_ms)
+		__string(dev_name, dev_name(&devfreq->dev))
+	),
+
+	TP_fast_assign(
+		__entry->freq = devfreq->previous_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+		__entry->polling_ms = devfreq->profile->polling_ms;
+		__assign_str(dev_name);
+	),
+
+	TP_printk("dev_name=%-30s freq=%-12lu polling_ms=%-3u load=%-2lu",
+		__get_str(dev_name), __entry->freq, __entry->polling_ms,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+#endif /* _TRACE_DEVFREQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>