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, 210 insertions, 0 deletions

diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
new file mode 100644
index 000000000..2bfbf2b2b
--- /dev/null
+++ b/net/rxrpc/security.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* RxRPC security handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/crypto.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <keys/rxrpc-type.h>
+#include "ar-internal.h"
+
+static const struct rxrpc_security *rxrpc_security_types[] = {
+	[RXRPC_SECURITY_NONE]	= &rxrpc_no_security,
+#ifdef CONFIG_RXKAD
+	[RXRPC_SECURITY_RXKAD]	= &rxkad,
+#endif
+#ifdef CONFIG_RXGK
+	[RXRPC_SECURITY_YFS_RXGK] = &rxgk_yfs,
+#endif
+};
+
+int __init rxrpc_init_security(void)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) {
+		if (rxrpc_security_types[i]) {
+			ret = rxrpc_security_types[i]->init();
+			if (ret < 0)
+				goto failed;
+		}
+	}
+
+	return 0;
+
+failed:
+	for (i--; i >= 0; i--)
+		if (rxrpc_security_types[i])
+			rxrpc_security_types[i]->exit();
+	return ret;
+}
+
+void rxrpc_exit_security(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++)
+		if (rxrpc_security_types[i])
+			rxrpc_security_types[i]->exit();
+}
+
+/*
+ * look up an rxrpc security module
+ */
+const struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
+{
+	if (security_index >= ARRAY_SIZE(rxrpc_security_types))
+		return NULL;
+	return rxrpc_security_types[security_index];
+}
+
+/*
+ * Initialise the security on a client call.
+ */
+int rxrpc_init_client_call_security(struct rxrpc_call *call)
+{
+	const struct rxrpc_security *sec = &rxrpc_no_security;
+	struct rxrpc_key_token *token;
+	struct key *key = call->key;
+	int ret;
+
+	if (!key)
+		goto found;
+
+	ret = key_validate(key);
+	if (ret < 0)
+		return ret;
+
+	for (token = key->payload.data[0]; token; token = token->next) {
+		sec = rxrpc_security_lookup(token->security_index);
+		if (sec)
+			goto found;
+	}
+	return -EKEYREJECTED;
+
+found:
+	call->security = sec;
+	call->security_ix = sec->security_index;
+	return 0;
+}
+
+/*
+ * initialise the security on a client connection
+ */
+int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
+{
+	struct rxrpc_key_token *token;
+	struct key *key = conn->key;
+	int ret = 0;
+
+	_enter("{%d},{%x}", conn->debug_id, key_serial(key));
+
+	for (token = key->payload.data[0]; token; token = token->next) {
+		if (token->security_index == conn->security->security_index)
+			goto found;
+	}
+	return -EKEYREJECTED;
+
+found:
+	mutex_lock(&conn->security_lock);
+	if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+		ret = conn->security->init_connection_security(conn, token);
+		if (ret == 0) {
+			spin_lock_irq(&conn->state_lock);
+			if (conn->state == RXRPC_CONN_CLIENT_UNSECURED)
+				conn->state = RXRPC_CONN_CLIENT;
+			spin_unlock_irq(&conn->state_lock);
+		}
+	}
+	mutex_unlock(&conn->security_lock);
+	return ret;
+}
+
+/*
+ * Set the ops a server connection.
+ */
+const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx,
+							 struct sk_buff *skb)
+{
+	const struct rxrpc_security *sec;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	_enter("");
+
+	sec = rxrpc_security_lookup(sp->hdr.securityIndex);
+	if (!sec) {
+		rxrpc_direct_conn_abort(skb, rxrpc_abort_unsupported_security,
+					RX_INVALID_OPERATION, -EKEYREJECTED);
+		return NULL;
+	}
+
+	if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE &&
+	    !rx->securities) {
+		rxrpc_direct_conn_abort(skb, rxrpc_abort_no_service_key,
+					sec->no_key_abort, -EKEYREJECTED);
+		return NULL;
+	}
+
+	return sec;
+}
+
+/*
+ * Find the security key for a server connection.
+ */
+struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn,
+					  struct sk_buff *skb,
+					  u32 kvno, u32 enctype)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_sock *rx;
+	struct key *key = ERR_PTR(-EKEYREJECTED);
+	key_ref_t kref = NULL;
+	char kdesc[5 + 1 + 3 + 1 + 12 + 1 + 12 + 1];
+	int ret;
+
+	_enter("");
+
+	if (enctype)
+		sprintf(kdesc, "%u:%u:%u:%u",
+			sp->hdr.serviceId, sp->hdr.securityIndex, kvno, enctype);
+	else if (kvno)
+		sprintf(kdesc, "%u:%u:%u",
+			sp->hdr.serviceId, sp->hdr.securityIndex, kvno);
+	else
+		sprintf(kdesc, "%u:%u",
+			sp->hdr.serviceId, sp->hdr.securityIndex);
+
+	read_lock(&conn->local->services_lock);
+
+	rx = conn->local->service;
+	if (!rx)
+		goto out;
+
+	/* look through the service's keyring */
+	kref = keyring_search(make_key_ref(rx->securities, 1UL),
+			      &key_type_rxrpc_s, kdesc, true);
+	if (IS_ERR(kref)) {
+		key = ERR_CAST(kref);
+		goto out;
+	}
+
+	key = key_ref_to_ptr(kref);
+
+	ret = key_validate(key);
+	if (ret < 0) {
+		key_put(key);
+		key = ERR_PTR(ret);
+		goto out;
+	}
+
+out:
+	read_unlock(&conn->local->services_lock);
+	return key;
+}