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, 63 insertions, 0 deletions

diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h
new file mode 100644
index 000000000..931958cb6
--- /dev/null
+++ b/drivers/net/wireguard/allowedips.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _WG_ALLOWEDIPS_H
+#define _WG_ALLOWEDIPS_H
+
+#include <linux/mutex.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+struct wg_peer;
+
+struct allowedips_node {
+	struct wg_peer __rcu *peer;
+	struct allowedips_node __rcu *bit[2];
+	u8 cidr, bit_at_a, bit_at_b, bitlen;
+	u8 bits[16] __aligned(__alignof(u64));
+
+	/* Keep rarely used members at bottom to be beyond cache line. */
+	unsigned long parent_bit_packed;
+	union {
+		struct list_head peer_list;
+		struct rcu_head rcu;
+	};
+};
+
+struct allowedips {
+	struct allowedips_node __rcu *root4;
+	struct allowedips_node __rcu *root6;
+	u64 seq;
+} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */
+
+void wg_allowedips_init(struct allowedips *table);
+void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
+int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+int wg_allowedips_remove_v4(struct allowedips *table, const struct in_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+int wg_allowedips_remove_v6(struct allowedips *table, const struct in6_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+void wg_allowedips_remove_by_peer(struct allowedips *table,
+				  struct wg_peer *peer, struct mutex *lock);
+/* The ip input pointer should be __aligned(__alignof(u64))) */
+int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr);
+
+/* These return a strong reference to a peer: */
+struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
+					 struct sk_buff *skb);
+struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
+					 struct sk_buff *skb);
+
+#ifdef DEBUG
+bool wg_allowedips_selftest(void);
+#endif
+
+int wg_allowedips_slab_init(void);
+void wg_allowedips_slab_uninit(void);
+
+#endif /* _WG_ALLOWEDIPS_H */