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, 64 insertions, 0 deletions

diff --git a/include/net/icmp.h b/include/net/icmp.h
new file mode 100644
index 000000000..935ee13d9
--- /dev/null
+++ b/include/net/icmp.h
@@ -0,0 +1,64 @@
+/* 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 ICMP module.
+ *
+ * Version:	@(#)icmp.h	1.0.4	05/13/93
+ *
+ * Authors:	Ross Biro
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ */
+#ifndef _ICMP_H
+#define	_ICMP_H
+
+#include <linux/icmp.h>
+
+#include <net/inet_sock.h>
+#include <net/snmp.h>
+#include <net/ip.h>
+
+struct icmp_err {
+  int		errno;
+  unsigned int	fatal:1;
+};
+
+extern const struct icmp_err icmp_err_convert[];
+#define ICMP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.icmp_statistics, field)
+#define __ICMP_INC_STATS(net, field)	__SNMP_INC_STATS((net)->mib.icmp_statistics, field)
+#define ICMPMSGOUT_INC_STATS(net, field)	SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256)
+#define ICMPMSGIN_INC_STATS(net, field)		SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field)
+
+struct dst_entry;
+struct net_proto_family;
+struct sk_buff;
+struct net;
+
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+		 const struct inet_skb_parm *parm);
+static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+{
+	__icmp_send(skb_in, type, code, info, IPCB(skb_in));
+}
+
+#if IS_ENABLED(CONFIG_NF_NAT)
+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info);
+#else
+static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+{
+	struct inet_skb_parm parm;
+
+	memset(&parm, 0, sizeof(parm));
+	__icmp_send(skb_in, type, code, info, &parm);
+}
+#endif
+
+int icmp_rcv(struct sk_buff *skb);
+int icmp_err(struct sk_buff *skb, u32 info);
+int icmp_init(void);
+void icmp_out_count(struct net *net, unsigned char type);
+bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr);
+
+#endif	/* _ICMP_H */