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, 77 insertions, 0 deletions

diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
new file mode 100644
index 000000000..b567b9ffe
--- /dev/null
+++ b/include/trace/events/napi.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM napi
+
+#if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NAPI_H
+
+#include <linux/netdevice.h>
+#include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
+
+	TP_PROTO(struct napi_struct *napi, int work, int budget),
+
+	TP_ARGS(napi, work, budget),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+		__field(	int,			work)
+		__field(	int,			budget)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name);
+		__entry->work = work;
+		__entry->budget = budget;
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s work %d budget %d",
+		  __entry->napi, __get_str(dev_name),
+		  __entry->work, __entry->budget)
+);
+
+TRACE_EVENT(dql_stall_detected,
+
+	TP_PROTO(unsigned short thrs, unsigned int len,
+		 unsigned long last_reap, unsigned long hist_head,
+		 unsigned long now, unsigned long *hist),
+
+	TP_ARGS(thrs, len, last_reap, hist_head, now, hist),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		thrs)
+		__field(	unsigned int,		len)
+		__field(	unsigned long,		last_reap)
+		__field(	unsigned long,		hist_head)
+		__field(	unsigned long,		now)
+		__array(	unsigned long,		hist, 4)
+	),
+
+	TP_fast_assign(
+		__entry->thrs = thrs;
+		__entry->len = len;
+		__entry->last_reap = last_reap;
+		__entry->hist_head = hist_head * BITS_PER_LONG;
+		__entry->now = now;
+		memcpy(__entry->hist, hist, sizeof(entry->hist));
+	),
+
+	TP_printk("thrs %u  len %u  last_reap %lu  hist_head %lu  now %lu  hist %016lx %016lx %016lx %016lx",
+		  __entry->thrs, __entry->len,
+		  __entry->last_reap, __entry->hist_head, __entry->now,
+		  __entry->hist[0], __entry->hist[1],
+		  __entry->hist[2], __entry->hist[3])
+);
+
+#undef NO_DEV
+
+#endif /* _TRACE_NAPI_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>