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, 50 insertions, 0 deletions

diff --git a/include/kunit/attributes.h b/include/kunit/attributes.h
new file mode 100644
index 000000000..bc76a0b78
--- /dev/null
+++ b/include/kunit/attributes.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit API to save and access test attributes
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: Rae Moar <rmoar@google.com>
+ */
+
+#ifndef _KUNIT_ATTRIBUTES_H
+#define _KUNIT_ATTRIBUTES_H
+
+/*
+ * struct kunit_attr_filter - representation of attributes filter with the
+ * attribute object and string input
+ */
+struct kunit_attr_filter {
+	struct kunit_attr *attr;
+	char *input;
+};
+
+/*
+ * Returns the name of the filter's attribute.
+ */
+const char *kunit_attr_filter_name(struct kunit_attr_filter filter);
+
+/*
+ * Print all test attributes for a test case or suite.
+ * Output format for test cases: "# <test_name>.<attribute>: <value>"
+ * Output format for test suites: "# <attribute>: <value>"
+ */
+void kunit_print_attr(void *test_or_suite, bool is_test, unsigned int test_level);
+
+/*
+ * Returns the number of fitlers in input.
+ */
+int kunit_get_filter_count(char *input);
+
+/*
+ * Parse attributes filter input and return an objects containing the
+ * attribute object and the string input of the next filter.
+ */
+struct kunit_attr_filter kunit_next_attr_filter(char **filters, int *err);
+
+/*
+ * Returns a copy of the suite containing only tests that pass the filter.
+ */
+struct kunit_suite *kunit_filter_attr_tests(const struct kunit_suite *const suite,
+		struct kunit_attr_filter filter, char *action, int *err);
+
+#endif /* _KUNIT_ATTRIBUTES_H */