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, 86 insertions, 0 deletions

diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h
new file mode 100644
index 000000000..718fb42bd
--- /dev/null
+++ b/drivers/net/wireguard/peer.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _WG_PEER_H
+#define _WG_PEER_H
+
+#include "device.h"
+#include "noise.h"
+#include "cookie.h"
+
+#include <linux/types.h>
+#include <linux/netfilter.h>
+#include <linux/spinlock.h>
+#include <linux/kref.h>
+#include <net/dst_cache.h>
+
+struct wg_device;
+
+struct endpoint {
+	union {
+		struct sockaddr_inet addr;     /* Large enough for both address families */
+		struct sockaddr_in addr4;
+		struct sockaddr_in6 addr6;
+	};
+	union {
+		struct {
+			struct in_addr src4;
+			/* Essentially the same as addr6->scope_id */
+			int src_if4;
+		};
+		struct in6_addr src6;
+	};
+};
+
+struct wg_peer {
+	struct wg_device *device;
+	struct prev_queue tx_queue, rx_queue;
+	struct sk_buff_head staged_packet_queue;
+	int serial_work_cpu;
+	bool is_dead;
+	struct noise_keypairs keypairs;
+	struct endpoint endpoint;
+	struct dst_cache endpoint_cache;
+	rwlock_t endpoint_lock;
+	struct noise_handshake handshake;
+	atomic64_t last_sent_handshake;
+	struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work;
+	struct cookie latest_cookie;
+	struct hlist_node pubkey_hash;
+	u64 rx_bytes, tx_bytes;
+	struct timer_list timer_retransmit_handshake, timer_send_keepalive;
+	struct timer_list timer_new_handshake, timer_zero_key_material;
+	struct timer_list timer_persistent_keepalive;
+	unsigned int timer_handshake_attempts;
+	u16 persistent_keepalive_interval;
+	bool timer_need_another_keepalive;
+	bool sent_lastminute_handshake;
+	struct timespec64 walltime_last_handshake;
+	struct kref refcount;
+	struct rcu_head rcu;
+	struct list_head peer_list;
+	struct list_head allowedips_list;
+	struct napi_struct napi;
+	u64 internal_id;
+};
+
+struct wg_peer *wg_peer_create(struct wg_device *wg,
+			       const u8 public_key[NOISE_PUBLIC_KEY_LEN],
+			       const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]);
+
+struct wg_peer *__must_check wg_peer_get_maybe_zero(struct wg_peer *peer);
+static inline struct wg_peer *wg_peer_get(struct wg_peer *peer)
+{
+	kref_get(&peer->refcount);
+	return peer;
+}
+void wg_peer_put(struct wg_peer *peer);
+void wg_peer_remove(struct wg_peer *peer);
+void wg_peer_remove_all(struct wg_device *wg);
+
+int wg_peer_init(void);
+void wg_peer_uninit(void);
+
+#endif /* _WG_PEER_H */