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, 77 insertions, 0 deletions

diff --git a/include/net/arp.h b/include/net/arp.h
new file mode 100644
index 000000000..e8747e071
--- /dev/null
+++ b/include/net/arp.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* linux/net/inet/arp.h */
+#ifndef _ARP_H
+#define _ARP_H
+
+#include <linux/if_arp.h>
+#include <linux/hash.h>
+#include <net/neighbour.h>
+
+
+extern struct neigh_table arp_tbl;
+
+static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd)
+{
+	u32 key = *(const u32 *)pkey;
+	u32 val = key ^ hash32_ptr(dev);
+
+	return val * hash_rnd[0];
+}
+
+#ifdef CONFIG_INET
+static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
+{
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		key = INADDR_ANY;
+
+	return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
+}
+#else
+static inline
+struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
+{
+	return NULL;
+}
+#endif
+
+static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key)
+{
+	struct neighbour *n;
+
+	rcu_read_lock();
+	n = __ipv4_neigh_lookup_noref(dev, key);
+	if (n && !refcount_inc_not_zero(&n->refcnt))
+		n = NULL;
+	rcu_read_unlock();
+
+	return n;
+}
+
+static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key)
+{
+	struct neighbour *n;
+
+	rcu_read_lock();
+	n = __ipv4_neigh_lookup_noref(dev, key);
+	neigh_confirm(n);
+	rcu_read_unlock();
+}
+
+void arp_init(void);
+int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg);
+void arp_send(int type, int ptype, __be32 dest_ip,
+	      struct net_device *dev, __be32 src_ip,
+	      const unsigned char *dest_hw,
+	      const unsigned char *src_hw, const unsigned char *th);
+int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir);
+void arp_ifdown(struct net_device *dev);
+int arp_invalidate(struct net_device *dev, __be32 ip, bool force);
+
+struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
+			   struct net_device *dev, __be32 src_ip,
+			   const unsigned char *dest_hw,
+			   const unsigned char *src_hw,
+			   const unsigned char *target_hw);
+void arp_xmit(struct sk_buff *skb);
+
+#endif	/* _ARP_H */