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, 49 insertions, 0 deletions

diff --git a/include/net/handshake.h b/include/net/handshake.h
new file mode 100644
index 000000000..8ebd4f9ed
--- /dev/null
+++ b/include/net/handshake.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic netlink HANDSHAKE service.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#ifndef _NET_HANDSHAKE_H
+#define _NET_HANDSHAKE_H
+
+enum {
+	TLS_NO_KEYRING = 0,
+	TLS_NO_PEERID = 0,
+	TLS_NO_CERT = 0,
+	TLS_NO_PRIVKEY = 0,
+};
+
+typedef void	(*tls_done_func_t)(void *data, int status,
+				   key_serial_t peerid);
+
+struct tls_handshake_args {
+	struct socket		*ta_sock;
+	tls_done_func_t		ta_done;
+	void			*ta_data;
+	const char		*ta_peername;
+	unsigned int		ta_timeout_ms;
+	key_serial_t		ta_keyring;
+	key_serial_t		ta_my_cert;
+	key_serial_t		ta_my_privkey;
+	unsigned int		ta_num_peerids;
+	key_serial_t		ta_my_peerids[5];
+};
+
+int tls_client_hello_anon(const struct tls_handshake_args *args, gfp_t flags);
+int tls_client_hello_x509(const struct tls_handshake_args *args, gfp_t flags);
+int tls_client_hello_psk(const struct tls_handshake_args *args, gfp_t flags);
+int tls_server_hello_x509(const struct tls_handshake_args *args, gfp_t flags);
+int tls_server_hello_psk(const struct tls_handshake_args *args, gfp_t flags);
+
+bool tls_handshake_cancel(struct sock *sk);
+void tls_handshake_close(struct socket *sock);
+
+u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *msg);
+void tls_alert_recv(const struct sock *sk, const struct msghdr *msg,
+		    u8 *level, u8 *description);
+
+#endif /* _NET_HANDSHAKE_H */