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, 124 insertions, 0 deletions

diff --git a/include/trace/events/timestamp.h b/include/trace/events/timestamp.h
new file mode 100644
index 000000000..d6503612d
--- /dev/null
+++ b/include/trace/events/timestamp.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM timestamp
+
+#if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TIMESTAMP_H
+
+#include <linux/tracepoint.h>
+#include <linux/fs.h>
+
+#define CTIME_QUERIED_FLAGS \
+	{ I_CTIME_QUERIED, "Q" }
+
+DECLARE_EVENT_CLASS(ctime,
+	TP_PROTO(struct inode *inode,
+		 struct timespec64 *ctime),
+
+	TP_ARGS(inode, ctime),
+
+	TP_STRUCT__entry(
+		__field(u64,		ino)
+		__field(time64_t,	ctime_s)
+		__field(dev_t,		dev)
+		__field(u32,		ctime_ns)
+		__field(u32,		gen)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->gen		= inode->i_generation;
+		__entry->ctime_s	= ctime->tv_sec;
+		__entry->ctime_ns	= ctime->tv_nsec;
+	),
+
+	TP_printk("ino=%d:%d:%llu:%u ctime=%lld.%u",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen,
+		__entry->ctime_s, __entry->ctime_ns
+	)
+);
+
+DEFINE_EVENT(ctime, inode_set_ctime_to_ts,
+		TP_PROTO(struct inode *inode,
+			 struct timespec64 *ctime),
+		TP_ARGS(inode, ctime));
+
+DEFINE_EVENT(ctime, ctime_xchg_skip,
+		TP_PROTO(struct inode *inode,
+			 struct timespec64 *ctime),
+		TP_ARGS(inode, ctime));
+
+TRACE_EVENT(ctime_ns_xchg,
+	TP_PROTO(struct inode *inode,
+		 u32 old,
+		 u32 new,
+		 u32 cur),
+
+	TP_ARGS(inode, old, new, cur),
+
+	TP_STRUCT__entry(
+		__field(u64,		ino)
+		__field(dev_t,		dev)
+		__field(u32,		gen)
+		__field(u32,		old)
+		__field(u32,		new)
+		__field(u32,		cur)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->gen		= inode->i_generation;
+		__entry->old		= old;
+		__entry->new		= new;
+		__entry->cur		= cur;
+	),
+
+	TP_printk("ino=%d:%d:%llu:%u old=%u:%s new=%u cur=%u:%s",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen,
+		__entry->old & ~I_CTIME_QUERIED,
+		__print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS),
+		__entry->new,
+		__entry->cur & ~I_CTIME_QUERIED,
+		__print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS)
+	)
+);
+
+TRACE_EVENT(fill_mg_cmtime,
+	TP_PROTO(struct inode *inode,
+		 struct timespec64 *ctime,
+		 struct timespec64 *mtime),
+
+	TP_ARGS(inode, ctime, mtime),
+
+	TP_STRUCT__entry(
+		__field(u64,		ino)
+		__field(time64_t,	ctime_s)
+		__field(time64_t,	mtime_s)
+		__field(dev_t,		dev)
+		__field(u32,		ctime_ns)
+		__field(u32,		mtime_ns)
+		__field(u32,		gen)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->gen		= inode->i_generation;
+		__entry->ctime_s	= ctime->tv_sec;
+		__entry->mtime_s	= mtime->tv_sec;
+		__entry->ctime_ns	= ctime->tv_nsec;
+		__entry->mtime_ns	= mtime->tv_nsec;
+	),
+
+	TP_printk("ino=%d:%d:%llu:%u ctime=%lld.%u mtime=%lld.%u",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen,
+		__entry->ctime_s, __entry->ctime_ns,
+		__entry->mtime_s, __entry->mtime_ns
+	)
+);
+#endif /* _TRACE_TIMESTAMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>