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, 92 insertions, 0 deletions

diff --git a/crypto/sm4_generic.c b/crypto/sm4_generic.c
new file mode 100644
index 000000000..d57444e84
--- /dev/null
+++ b/crypto/sm4_generic.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * SM4 Cipher Algorithm.
+ *
+ * Copyright (C) 2018 ARM Limited or its affiliates.
+ * All rights reserved.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/sm4.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/byteorder.h>
+#include <linux/unaligned.h>
+
+/**
+ * sm4_setkey - Set the SM4 key.
+ * @tfm:	The %crypto_tfm that is used in the context.
+ * @in_key:	The input key.
+ * @key_len:	The size of the key.
+ *
+ * This function uses sm4_expandkey() to expand the key.
+ * &sm4_ctx _must_ be the private data embedded in @tfm which is
+ * retrieved with crypto_tfm_ctx().
+ *
+ * Return: 0 on success; -EINVAL on failure (only happens for bad key lengths)
+ */
+static int sm4_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	return sm4_expandkey(ctx, in_key, key_len);
+}
+
+/* encrypt a block of text */
+
+static void sm4_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	sm4_crypt_block(ctx->rkey_enc, out, in);
+}
+
+/* decrypt a block of text */
+
+static void sm4_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	sm4_crypt_block(ctx->rkey_dec, out, in);
+}
+
+static struct crypto_alg sm4_alg = {
+	.cra_name		=	"sm4",
+	.cra_driver_name	=	"sm4-generic",
+	.cra_priority		=	100,
+	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		=	SM4_BLOCK_SIZE,
+	.cra_ctxsize		=	sizeof(struct sm4_ctx),
+	.cra_module		=	THIS_MODULE,
+	.cra_u			=	{
+		.cipher = {
+			.cia_min_keysize	=	SM4_KEY_SIZE,
+			.cia_max_keysize	=	SM4_KEY_SIZE,
+			.cia_setkey		=	sm4_setkey,
+			.cia_encrypt		=	sm4_encrypt,
+			.cia_decrypt		=	sm4_decrypt
+		}
+	}
+};
+
+static int __init sm4_init(void)
+{
+	return crypto_register_alg(&sm4_alg);
+}
+
+static void __exit sm4_fini(void)
+{
+	crypto_unregister_alg(&sm4_alg);
+}
+
+module_init(sm4_init);
+module_exit(sm4_fini);
+
+MODULE_DESCRIPTION("SM4 Cipher Algorithm");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-generic");