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, 82 insertions, 0 deletions

diff --git a/crypto/arc4.c b/crypto/arc4.c
new file mode 100644
index 000000000..160801811
--- /dev/null
+++ b/crypto/arc4.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Cryptographic API
+ *
+ * ARC4 Cipher Algorithm
+ *
+ * Jon Oberheide <jon@oberheide.org>
+ */
+
+#include <crypto/arc4.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+
+#define ARC4_ALIGN __alignof__(struct arc4_ctx)
+
+static int crypto_arc4_setkey(struct crypto_lskcipher *tfm, const u8 *in_key,
+			      unsigned int key_len)
+{
+	struct arc4_ctx *ctx = crypto_lskcipher_ctx(tfm);
+
+	return arc4_setkey(ctx, in_key, key_len);
+}
+
+static int crypto_arc4_crypt(struct crypto_lskcipher *tfm, const u8 *src,
+			     u8 *dst, unsigned nbytes, u8 *siv, u32 flags)
+{
+	struct arc4_ctx *ctx = crypto_lskcipher_ctx(tfm);
+
+	if (!(flags & CRYPTO_LSKCIPHER_FLAG_CONT))
+		memcpy(siv, ctx, sizeof(*ctx));
+
+	ctx = (struct arc4_ctx *)siv;
+
+	arc4_crypt(ctx, dst, src, nbytes);
+	return 0;
+}
+
+static int crypto_arc4_init(struct crypto_lskcipher *tfm)
+{
+	pr_warn_ratelimited("\"%s\" (%ld) uses obsolete ecb(arc4) skcipher\n",
+			    current->comm, (unsigned long)current->pid);
+
+	return 0;
+}
+
+static struct lskcipher_alg arc4_alg = {
+	.co.base.cra_name		=	"arc4",
+	.co.base.cra_driver_name	=	"arc4-generic",
+	.co.base.cra_priority		=	100,
+	.co.base.cra_blocksize		=	ARC4_BLOCK_SIZE,
+	.co.base.cra_ctxsize		=	sizeof(struct arc4_ctx),
+	.co.base.cra_alignmask		=	ARC4_ALIGN - 1,
+	.co.base.cra_module		=	THIS_MODULE,
+	.co.min_keysize			=	ARC4_MIN_KEY_SIZE,
+	.co.max_keysize			=	ARC4_MAX_KEY_SIZE,
+	.co.statesize			=	sizeof(struct arc4_ctx),
+	.setkey				=	crypto_arc4_setkey,
+	.encrypt			=	crypto_arc4_crypt,
+	.decrypt			=	crypto_arc4_crypt,
+	.init				=	crypto_arc4_init,
+};
+
+static int __init arc4_init(void)
+{
+	return crypto_register_lskcipher(&arc4_alg);
+}
+
+static void __exit arc4_exit(void)
+{
+	crypto_unregister_lskcipher(&arc4_alg);
+}
+
+module_init(arc4_init);
+module_exit(arc4_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ARC4 Cipher Algorithm");
+MODULE_AUTHOR("Jon Oberheide <jon@oberheide.org>");
+MODULE_ALIAS_CRYPTO("ecb(arc4)");