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, 44 insertions, 0 deletions

diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
new file mode 100644
index 000000000..8fb06d853
--- /dev/null
+++ b/drivers/md/md-cluster.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+
+#ifndef _MD_CLUSTER_H
+#define _MD_CLUSTER_H
+
+#include "md.h"
+
+struct mddev;
+struct md_rdev;
+
+struct md_cluster_operations {
+	struct md_submodule_head head;
+
+	int (*join)(struct mddev *mddev, int nodes);
+	int (*leave)(struct mddev *mddev);
+	int (*slot_number)(struct mddev *mddev);
+	int (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi);
+	int (*resync_start_notify)(struct mddev *mddev);
+	int (*resync_status_get)(struct mddev *mddev);
+	void (*resync_info_get)(struct mddev *mddev, sector_t *lo, sector_t *hi);
+	int (*metadata_update_start)(struct mddev *mddev);
+	int (*metadata_update_finish)(struct mddev *mddev);
+	void (*metadata_update_cancel)(struct mddev *mddev);
+	int (*resync_start)(struct mddev *mddev);
+	int (*resync_finish)(struct mddev *mddev);
+	int (*area_resyncing)(struct mddev *mddev, int direction, sector_t lo, sector_t hi);
+	int (*add_new_disk)(struct mddev *mddev, struct md_rdev *rdev);
+	void (*add_new_disk_cancel)(struct mddev *mddev);
+	int (*new_disk_ack)(struct mddev *mddev, bool ack);
+	int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
+	void (*load_bitmaps)(struct mddev *mddev, int total_slots);
+	int (*gather_bitmaps)(struct md_rdev *rdev);
+	int (*resize_bitmaps)(struct mddev *mddev, sector_t newsize, sector_t oldsize);
+	int (*lock_all_bitmaps)(struct mddev *mddev);
+	void (*unlock_all_bitmaps)(struct mddev *mddev);
+	void (*update_size)(struct mddev *mddev, sector_t old_dev_sectors);
+};
+
+extern int md_setup_cluster(struct mddev *mddev, int nodes);
+extern void md_cluster_stop(struct mddev *mddev);
+extern void md_reload_sb(struct mddev *mddev, int raid_disk);
+
+#endif /* _MD_CLUSTER_H */