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, 94 insertions, 0 deletions

diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
new file mode 100644
index 000000000..0b39046bd
--- /dev/null
+++ b/net/rxrpc/insecure.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Null security operations.
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static int none_init_connection_security(struct rxrpc_connection *conn,
+					 struct rxrpc_key_token *token)
+{
+	return 0;
+}
+
+/*
+ * Allocate an appropriately sized buffer for the amount of data remaining.
+ */
+static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp)
+{
+	return rxrpc_alloc_data_txbuf(call, umin(remain, RXRPC_JUMBO_DATALEN), 1, gfp);
+}
+
+static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
+{
+	txb->pkt_len = txb->len;
+	if (txb->len == RXRPC_JUMBO_DATALEN)
+		txb->jumboable = true;
+	return 0;
+}
+
+static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
+{
+	return 0;
+}
+
+static void none_free_call_crypto(struct rxrpc_call *call)
+{
+}
+
+static bool none_validate_challenge(struct rxrpc_connection *conn,
+				    struct sk_buff *skb)
+{
+	rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+			 rxrpc_eproto_rxnull_challenge);
+	return true;
+}
+
+static int none_sendmsg_respond_to_challenge(struct sk_buff *challenge,
+					     struct msghdr *msg)
+{
+	return -EINVAL;
+}
+
+static int none_verify_response(struct rxrpc_connection *conn,
+				struct sk_buff *response_skb,
+				void *response, unsigned int len)
+{
+	return rxrpc_abort_conn(conn, response_skb, RX_PROTOCOL_ERROR, -EPROTO,
+				rxrpc_eproto_rxnull_response);
+}
+
+static void none_clear(struct rxrpc_connection *conn)
+{
+}
+
+static int none_init(void)
+{
+	return 0;
+}
+
+static void none_exit(void)
+{
+}
+
+/*
+ * RxRPC Kerberos-based security
+ */
+const struct rxrpc_security rxrpc_no_security = {
+	.name				= "none",
+	.security_index			= RXRPC_SECURITY_NONE,
+	.init				= none_init,
+	.exit				= none_exit,
+	.init_connection_security	= none_init_connection_security,
+	.free_call_crypto		= none_free_call_crypto,
+	.alloc_txbuf			= none_alloc_txbuf,
+	.secure_packet			= none_secure_packet,
+	.verify_packet			= none_verify_packet,
+	.validate_challenge		= none_validate_challenge,
+	.sendmsg_respond_to_challenge	= none_sendmsg_respond_to_challenge,
+	.verify_response		= none_verify_response,
+	.clear				= none_clear,
+};