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, 140 insertions, 0 deletions

diff --git a/crypto/kpp.c b/crypto/kpp.c
new file mode 100644
index 000000000..522c352a0
--- /dev/null
+++ b/crypto/kpp.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ */
+
+#include <crypto/internal/kpp.h>
+#include <linux/cryptouser.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/string.h>
+#include <net/netlink.h>
+
+#include "internal.h"
+
+static int __maybe_unused crypto_kpp_report(
+	struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_kpp rkpp = {
+		.type = "kpp",
+	};
+
+	return nla_put(skb, CRYPTOCFGA_REPORT_KPP, sizeof(rkpp), &rkpp);
+}
+
+static void __maybe_unused crypto_kpp_show(struct seq_file *m,
+					   struct crypto_alg *alg)
+{
+	seq_puts(m, "type         : kpp\n");
+}
+
+static void crypto_kpp_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_kpp *kpp = __crypto_kpp_tfm(tfm);
+	struct kpp_alg *alg = crypto_kpp_alg(kpp);
+
+	alg->exit(kpp);
+}
+
+static int crypto_kpp_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_kpp *kpp = __crypto_kpp_tfm(tfm);
+	struct kpp_alg *alg = crypto_kpp_alg(kpp);
+
+	if (alg->exit)
+		kpp->base.exit = crypto_kpp_exit_tfm;
+
+	if (alg->init)
+		return alg->init(kpp);
+
+	return 0;
+}
+
+static void crypto_kpp_free_instance(struct crypto_instance *inst)
+{
+	struct kpp_instance *kpp = kpp_instance(inst);
+
+	kpp->free(kpp);
+}
+
+static const struct crypto_type crypto_kpp_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_kpp_init_tfm,
+	.free = crypto_kpp_free_instance,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_kpp_show,
+#endif
+#if IS_ENABLED(CONFIG_CRYPTO_USER)
+	.report = crypto_kpp_report,
+#endif
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_KPP,
+	.tfmsize = offsetof(struct crypto_kpp, base),
+	.algsize = offsetof(struct kpp_alg, base),
+};
+
+struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_kpp_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_kpp);
+
+int crypto_grab_kpp(struct crypto_kpp_spawn *spawn,
+		    struct crypto_instance *inst,
+		    const char *name, u32 type, u32 mask)
+{
+	spawn->base.frontend = &crypto_kpp_type;
+	return crypto_grab_spawn(&spawn->base, inst, name, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_grab_kpp);
+
+int crypto_has_kpp(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_type_has_alg(alg_name, &crypto_kpp_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_has_kpp);
+
+static void kpp_prepare_alg(struct kpp_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	base->cra_type = &crypto_kpp_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_KPP;
+}
+
+int crypto_register_kpp(struct kpp_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	kpp_prepare_alg(alg);
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_kpp);
+
+void crypto_unregister_kpp(struct kpp_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_kpp);
+
+int kpp_register_instance(struct crypto_template *tmpl,
+			  struct kpp_instance *inst)
+{
+	if (WARN_ON(!inst->free))
+		return -EINVAL;
+
+	kpp_prepare_alg(&inst->alg);
+
+	return crypto_register_instance(tmpl, kpp_crypto_instance(inst));
+}
+EXPORT_SYMBOL_GPL(kpp_register_instance);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Key-agreement Protocol Primitives");