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, 115 insertions, 0 deletions

diff --git a/mm/mmzone.c b/mm/mmzone.c
new file mode 100644
index 000000000..9cc9ef588
--- /dev/null
+++ b/mm/mmzone.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/mm/mmzone.c
+ *
+ * management codes for pgdats, zones and page flags
+ */
+
+
+#include <linux/stddef.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+
+struct pglist_data *first_online_pgdat(void)
+{
+	return NODE_DATA(first_online_node);
+}
+
+struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
+{
+	int nid = next_online_node(pgdat->node_id);
+
+	if (nid == MAX_NUMNODES)
+		return NULL;
+	return NODE_DATA(nid);
+}
+
+/*
+ * next_zone - helper magic for for_each_zone()
+ */
+struct zone *next_zone(struct zone *zone)
+{
+	pg_data_t *pgdat = zone->zone_pgdat;
+
+	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
+		zone++;
+	else {
+		pgdat = next_online_pgdat(pgdat);
+		if (pgdat)
+			zone = pgdat->node_zones;
+		else
+			zone = NULL;
+	}
+	return zone;
+}
+
+static inline int zref_in_nodemask(struct zoneref *zref,
+				   const nodemask_t *nodes)
+{
+#ifdef CONFIG_NUMA
+	return node_isset(zonelist_node_idx(zref), *nodes);
+#else
+	return 1;
+#endif /* CONFIG_NUMA */
+}
+
+/* Returns the next zone at or below highest_zoneidx in a zonelist */
+struct zoneref *__next_zones_zonelist(struct zoneref *z,
+					enum zone_type highest_zoneidx,
+					const nodemask_t *nodes)
+{
+	/*
+	 * Find the next suitable zone to use for the allocation.
+	 * Only filter based on nodemask if it's set
+	 */
+	if (unlikely(nodes == NULL))
+		while (zonelist_zone_idx(z) > highest_zoneidx)
+			z++;
+	else
+		while (zonelist_zone_idx(z) > highest_zoneidx ||
+				(zonelist_zone(z) && !zref_in_nodemask(z, nodes)))
+			z++;
+
+	return z;
+}
+
+void lruvec_init(struct lruvec *lruvec)
+{
+	enum lru_list lru;
+
+	memset(lruvec, 0, sizeof(struct lruvec));
+	spin_lock_init(&lruvec->lru_lock);
+	spin_lock_init(&lruvec->cost_lock);
+	zswap_lruvec_state_init(lruvec);
+
+	for_each_lru(lru)
+		INIT_LIST_HEAD(&lruvec->lists[lru]);
+	/*
+	 * The "Unevictable LRU" is imaginary: though its size is maintained,
+	 * it is never scanned, and unevictable pages are not threaded on it
+	 * (so that their lru fields can be reused to hold mlock_count).
+	 * Poison its list head, so that any operations on it would crash.
+	 */
+	list_del(&lruvec->lists[LRU_UNEVICTABLE]);
+
+	lru_gen_init_lruvec(lruvec);
+}
+
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
+int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
+{
+	unsigned long old_flags, flags;
+	int last_cpupid;
+
+	old_flags = READ_ONCE(folio->flags.f);
+	do {
+		flags = old_flags;
+		last_cpupid = (flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
+
+		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
+		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
+	} while (unlikely(!try_cmpxchg(&folio->flags.f, &old_flags, flags)));
+
+	return last_cpupid;
+}
+#endif