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, 58 insertions, 0 deletions

diff --git a/include/crypto/internal/engine.h b/include/crypto/internal/engine.h
new file mode 100644
index 000000000..6a1d27880
--- /dev/null
+++ b/include/crypto/internal/engine.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Crypto engine API
+ *
+ * Copyright (c) 2016 Baolin Wang <baolin.wang@linaro.org>
+ * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+#ifndef _CRYPTO_INTERNAL_ENGINE_H
+#define _CRYPTO_INTERNAL_ENGINE_H
+
+#include <crypto/algapi.h>
+#include <crypto/engine.h>
+#include <linux/kthread.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+
+#define ENGINE_NAME_LEN	30
+
+struct device;
+
+/*
+ * struct crypto_engine - crypto hardware engine
+ * @name: the engine name
+ * @busy: request pump is busy
+ * @running: the engine is on working
+ * @retry_support: indication that the hardware allows re-execution
+ * of a failed backlog request
+ * crypto-engine, in head position to keep order
+ * @rt: whether this queue is set to run as a realtime task
+ * @list: link with the global crypto engine list
+ * @queue_lock: spinlock to synchronise access to request queue
+ * @queue: the crypto queue of the engine
+ * @kworker: kthread worker struct for request pump
+ * @pump_requests: work struct for scheduling work to the request pump
+ * @priv_data: the engine private data
+ * @cur_req: the current request which is on processing
+ */
+struct crypto_engine {
+	char			name[ENGINE_NAME_LEN];
+	bool			busy;
+	bool			running;
+
+	bool			retry_support;
+	bool			rt;
+
+	struct list_head	list;
+	spinlock_t		queue_lock;
+	struct crypto_queue	queue __guarded_by(&queue_lock);
+	struct device		*dev;
+
+	struct kthread_worker           *kworker;
+	struct kthread_work             pump_requests;
+
+	void				*priv_data;
+	struct crypto_async_request	*cur_req;
+};
+
+#endif