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, 63 insertions, 0 deletions

diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c
new file mode 100644
index 000000000..4012c4372
--- /dev/null
+++ b/net/tls/tls_proc.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/snmp.h>
+#include <net/tls.h>
+
+#include "tls.h"
+
+#ifdef CONFIG_PROC_FS
+static const struct snmp_mib tls_mib_list[] = {
+	SNMP_MIB_ITEM("TlsCurrTxSw", LINUX_MIB_TLSCURRTXSW),
+	SNMP_MIB_ITEM("TlsCurrRxSw", LINUX_MIB_TLSCURRRXSW),
+	SNMP_MIB_ITEM("TlsCurrTxDevice", LINUX_MIB_TLSCURRTXDEVICE),
+	SNMP_MIB_ITEM("TlsCurrRxDevice", LINUX_MIB_TLSCURRRXDEVICE),
+	SNMP_MIB_ITEM("TlsTxSw", LINUX_MIB_TLSTXSW),
+	SNMP_MIB_ITEM("TlsRxSw", LINUX_MIB_TLSRXSW),
+	SNMP_MIB_ITEM("TlsTxDevice", LINUX_MIB_TLSTXDEVICE),
+	SNMP_MIB_ITEM("TlsRxDevice", LINUX_MIB_TLSRXDEVICE),
+	SNMP_MIB_ITEM("TlsDecryptError", LINUX_MIB_TLSDECRYPTERROR),
+	SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC),
+	SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIB_TLSDECRYPTRETRY),
+	SNMP_MIB_ITEM("TlsRxNoPadViolation", LINUX_MIB_TLSRXNOPADVIOL),
+	SNMP_MIB_ITEM("TlsRxRekeyOk", LINUX_MIB_TLSRXREKEYOK),
+	SNMP_MIB_ITEM("TlsRxRekeyError", LINUX_MIB_TLSRXREKEYERROR),
+	SNMP_MIB_ITEM("TlsTxRekeyOk", LINUX_MIB_TLSTXREKEYOK),
+	SNMP_MIB_ITEM("TlsTxRekeyError", LINUX_MIB_TLSTXREKEYERROR),
+	SNMP_MIB_ITEM("TlsRxRekeyReceived", LINUX_MIB_TLSRXREKEYRECEIVED),
+};
+
+static int tls_statistics_seq_show(struct seq_file *seq, void *v)
+{
+	unsigned long buf[ARRAY_SIZE(tls_mib_list)];
+	const int cnt = ARRAY_SIZE(tls_mib_list);
+	struct net *net = seq->private;
+	int i;
+
+	memset(buf, 0, sizeof(buf));
+	snmp_get_cpu_field_batch_cnt(buf, tls_mib_list, cnt,
+				     net->mib.tls_statistics);
+	for (i = 0; i < cnt; i++)
+		seq_printf(seq, "%-32s\t%lu\n", tls_mib_list[i].name, buf[i]);
+
+	return 0;
+}
+#endif
+
+int __net_init tls_proc_init(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+	if (!proc_create_net_single("tls_stat", 0444, net->proc_net,
+				    tls_statistics_seq_show, NULL))
+		return -ENOMEM;
+#endif /* CONFIG_PROC_FS */
+
+	return 0;
+}
+
+void __net_exit tls_proc_fini(struct net *net)
+{
+	remove_proc_entry("tls_stat", net->proc_net);
+}