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, 57 insertions, 0 deletions

diff --git a/include/kunit/skbuff.h b/include/kunit/skbuff.h
new file mode 100644
index 000000000..077846943
--- /dev/null
+++ b/include/kunit/skbuff.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit resource management helpers for SKBs (skbuff).
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+
+#ifndef _KUNIT_SKBUFF_H
+#define _KUNIT_SKBUFF_H
+
+#include <kunit/resource.h>
+#include <linux/skbuff.h>
+
+static void kunit_action_kfree_skb(void *p)
+{
+	kfree_skb((struct sk_buff *)p);
+}
+
+/**
+ * kunit_zalloc_skb() - Allocate and initialize a resource managed skb.
+ * @test: The test case to which the skb belongs
+ * @len: size to allocate
+ * @gfp: allocation flags
+ *
+ * Allocate a new struct sk_buff with gfp flags, zero fill the given length
+ * and add it as a resource to the kunit test for automatic cleanup.
+ *
+ * Returns: newly allocated SKB, or %NULL on error
+ */
+static inline struct sk_buff *kunit_zalloc_skb(struct kunit *test, int len,
+					       gfp_t gfp)
+{
+	struct sk_buff *res = alloc_skb(len, gfp);
+
+	if (!res || skb_pad(res, len))
+		return NULL;
+
+	if (kunit_add_action_or_reset(test, kunit_action_kfree_skb, res))
+		return NULL;
+
+	return res;
+}
+
+/**
+ * kunit_kfree_skb() - Like kfree_skb except for allocations managed by KUnit.
+ * @test: The test case to which the resource belongs.
+ * @skb: The SKB to free.
+ */
+static inline void kunit_kfree_skb(struct kunit *test, struct sk_buff *skb)
+{
+	if (!skb)
+		return;
+
+	kunit_release_action(test, kunit_action_kfree_skb, (void *)skb);
+}
+
+#endif /* _KUNIT_SKBUFF_H */