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, 79 insertions, 0 deletions

diff --git a/tools/testing/radix-tree/regression4.c b/tools/testing/radix-tree/regression4.c
new file mode 100644
index 000000000..cf4e5aba6
--- /dev/null
+++ b/tools/testing/radix-tree/regression4.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+#include <linux/rcupdate.h>
+#include <stdlib.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <assert.h>
+
+#include "regression.h"
+
+static pthread_barrier_t worker_barrier;
+static int obj0, obj1;
+static RADIX_TREE(mt_tree, GFP_KERNEL);
+
+static void *reader_fn(void *arg)
+{
+	int i;
+	void *entry;
+
+	rcu_register_thread();
+	pthread_barrier_wait(&worker_barrier);
+
+	for (i = 0; i < 1000000; i++) {
+		rcu_read_lock();
+		entry = radix_tree_lookup(&mt_tree, 0);
+		rcu_read_unlock();
+		if (entry != &obj0) {
+			printf("iteration %d bad entry = %p\n", i, entry);
+			abort();
+		}
+	}
+
+	rcu_unregister_thread();
+
+	return NULL;
+}
+
+static void *writer_fn(void *arg)
+{
+	int i;
+
+	rcu_register_thread();
+	pthread_barrier_wait(&worker_barrier);
+
+	for (i = 0; i < 1000000; i++) {
+		radix_tree_insert(&mt_tree, 1, &obj1);
+		radix_tree_delete(&mt_tree, 1);
+	}
+
+	rcu_unregister_thread();
+
+	return NULL;
+}
+
+void regression4_test(void)
+{
+	pthread_t reader, writer;
+
+	printv(1, "regression test 4 starting\n");
+
+	radix_tree_insert(&mt_tree, 0, &obj0);
+	pthread_barrier_init(&worker_barrier, NULL, 2);
+
+	if (pthread_create(&reader, NULL, reader_fn, NULL) ||
+	    pthread_create(&writer, NULL, writer_fn, NULL)) {
+		perror("pthread_create");
+		exit(1);
+	}
+
+	if (pthread_join(reader, NULL) || pthread_join(writer, NULL)) {
+		perror("pthread_join");
+		exit(1);
+	}
+
+	printv(1, "regression test 4 passed\n");
+}