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, 85 insertions, 0 deletions

diff --git a/include/net/ping.h b/include/net/ping.h
new file mode 100644
index 000000000..bcbdb5a13
--- /dev/null
+++ b/include/net/ping.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions for the "ping" module.
+ */
+#ifndef _PING_H
+#define _PING_H
+
+#include <net/icmp.h>
+#include <net/netns/hash.h>
+
+/* PING_HTABLE_SIZE must be power of 2 */
+#define PING_HTABLE_SIZE 	64
+#define PING_HTABLE_MASK 	(PING_HTABLE_SIZE-1)
+
+#define GID_T_MAX (((gid_t)~0U) - 1)
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+	int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len);
+	void (*ip6_datagram_recv_common_ctl)(struct sock *sk,
+					     struct msghdr *msg,
+					     struct sk_buff *skb);
+	void (*ip6_datagram_recv_specific_ctl)(struct sock *sk,
+					       struct msghdr *msg,
+					       struct sk_buff *skb);
+	int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+	void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+				__be16 port, u32 info, u8 *payload);
+	int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+			     const struct net_device *dev, int strict);
+};
+
+struct ping_iter_state {
+	struct seq_net_private  p;
+	int			bucket;
+	sa_family_t		family;
+};
+
+extern struct proto ping_prot;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
+
+struct pingfakehdr {
+	struct icmphdr icmph;
+	struct msghdr *msg;
+	sa_family_t family;
+	__wsum wcheck;
+};
+
+int  ping_get_port(struct sock *sk, unsigned short ident);
+void ping_unhash(struct sock *sk);
+
+int  ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int  ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int  ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+		  struct sk_buff *);
+
+int  ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		  int flags);
+int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			 void *user_icmph, size_t icmph_len);
+int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
+
+#ifdef CONFIG_PROC_FS
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void ping_seq_stop(struct seq_file *seq, void *v);
+
+int __init ping_proc_init(void);
+void ping_proc_exit(void);
+#endif
+
+void __init ping_init(void);
+int  __init pingv6_init(void);
+void pingv6_exit(void);
+
+#endif /* _PING_H */