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, 109 insertions, 0 deletions

diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
new file mode 100644
index 000000000..26d235d15
--- /dev/null
+++ b/drivers/net/wireguard/queueing.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include "queueing.h"
+#include <linux/skb_array.h>
+
+struct multicore_worker __percpu *
+wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
+{
+	int cpu;
+	struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker);
+
+	if (!worker)
+		return NULL;
+
+	for_each_possible_cpu(cpu) {
+		per_cpu_ptr(worker, cpu)->ptr = ptr;
+		INIT_WORK(&per_cpu_ptr(worker, cpu)->work, function);
+	}
+	return worker;
+}
+
+int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
+			 unsigned int len)
+{
+	int ret;
+
+	memset(queue, 0, sizeof(*queue));
+	queue->last_cpu = -1;
+	ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
+	if (ret)
+		return ret;
+	queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue);
+	if (!queue->worker) {
+		ptr_ring_cleanup(&queue->ring, NULL);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void wg_packet_queue_free(struct crypt_queue *queue, bool purge)
+{
+	free_percpu(queue->worker);
+	WARN_ON(!purge && !__ptr_ring_empty(&queue->ring));
+	ptr_ring_cleanup(&queue->ring, purge ? __skb_array_destroy_skb : NULL);
+}
+
+#define NEXT(skb) ((skb)->prev)
+#define STUB(queue) ((struct sk_buff *)&queue->empty)
+
+void wg_prev_queue_init(struct prev_queue *queue)
+{
+	NEXT(STUB(queue)) = NULL;
+	queue->head = queue->tail = STUB(queue);
+	queue->peeked = NULL;
+	atomic_set(&queue->count, 0);
+	BUILD_BUG_ON(
+		offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) -
+							offsetof(struct prev_queue, empty) ||
+		offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) -
+							 offsetof(struct prev_queue, empty));
+}
+
+static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
+{
+	WRITE_ONCE(NEXT(skb), NULL);
+	WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb);
+}
+
+bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
+{
+	if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS))
+		return false;
+	__wg_prev_queue_enqueue(queue, skb);
+	return true;
+}
+
+struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue)
+{
+	struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail));
+
+	if (tail == STUB(queue)) {
+		if (!next)
+			return NULL;
+		queue->tail = next;
+		tail = next;
+		next = smp_load_acquire(&NEXT(next));
+	}
+	if (next) {
+		queue->tail = next;
+		atomic_dec(&queue->count);
+		return tail;
+	}
+	if (tail != READ_ONCE(queue->head))
+		return NULL;
+	__wg_prev_queue_enqueue(queue, STUB(queue));
+	next = smp_load_acquire(&NEXT(tail));
+	if (next) {
+		queue->tail = next;
+		atomic_dec(&queue->count);
+		return tail;
+	}
+	return NULL;
+}
+
+#undef NEXT
+#undef STUB