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, 110 insertions, 0 deletions

diff --git a/net/handshake/alert.c b/net/handshake/alert.c
new file mode 100644
index 000000000..329d91984
--- /dev/null
+++ b/net/handshake/alert.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Handle the TLS Alert protocol
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/inet.h>
+
+#include <net/sock.h>
+#include <net/handshake.h>
+#include <net/tls.h>
+#include <net/tls_prot.h>
+
+#include "handshake.h"
+
+#include <trace/events/handshake.h>
+
+/**
+ * tls_alert_send - send a TLS Alert on a kTLS socket
+ * @sock: open kTLS socket to send on
+ * @level: TLS Alert level
+ * @description: TLS Alert description
+ *
+ * Returns zero on success or a negative errno.
+ */
+int tls_alert_send(struct socket *sock, u8 level, u8 description)
+{
+	u8 record_type = TLS_RECORD_TYPE_ALERT;
+	u8 buf[CMSG_SPACE(sizeof(record_type))];
+	struct msghdr msg = { 0 };
+	struct cmsghdr *cmsg;
+	struct kvec iov;
+	u8 alert[2];
+	int ret;
+
+	trace_tls_alert_send(sock->sk, level, description);
+
+	alert[0] = level;
+	alert[1] = description;
+	iov.iov_base = alert;
+	iov.iov_len = sizeof(alert);
+
+	memset(buf, 0, sizeof(buf));
+	msg.msg_control = buf;
+	msg.msg_controllen = sizeof(buf);
+	msg.msg_flags = MSG_DONTWAIT;
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_TLS;
+	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(record_type));
+	memcpy(CMSG_DATA(cmsg), &record_type, sizeof(record_type));
+
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, iov.iov_len);
+	ret = sock_sendmsg(sock, &msg);
+	return ret < 0 ? ret : 0;
+}
+
+/**
+ * tls_get_record_type - Look for TLS RECORD_TYPE information
+ * @sk: socket (for IP address information)
+ * @cmsg: incoming message to be parsed
+ *
+ * Returns zero or a TLS_RECORD_TYPE value.
+ */
+u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *cmsg)
+{
+	u8 record_type;
+
+	if (cmsg->cmsg_level != SOL_TLS)
+		return 0;
+	if (cmsg->cmsg_type != TLS_GET_RECORD_TYPE)
+		return 0;
+
+	record_type = *((u8 *)CMSG_DATA(cmsg));
+	trace_tls_contenttype(sk, record_type);
+	return record_type;
+}
+EXPORT_SYMBOL(tls_get_record_type);
+
+/**
+ * tls_alert_recv - Parse TLS Alert messages
+ * @sk: socket (for IP address information)
+ * @msg: incoming message to be parsed
+ * @level: OUT - TLS AlertLevel value
+ * @description: OUT - TLS AlertDescription value
+ *
+ */
+void tls_alert_recv(const struct sock *sk, const struct msghdr *msg,
+		    u8 *level, u8 *description)
+{
+	const struct kvec *iov;
+	u8 *data;
+
+	iov = msg->msg_iter.kvec;
+	data = iov->iov_base;
+	*level = data[0];
+	*description = data[1];
+
+	trace_tls_alert_recv(sk, *level, *description);
+}
+EXPORT_SYMBOL(tls_alert_recv);