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, 93 insertions, 0 deletions

diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c
new file mode 100644
index 000000000..3f369c6f8
--- /dev/null
+++ b/fs/cachefiles/main.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Network filesystem caching backend to use cache files on a premounted
+ * filesystem
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/sysctl.h>
+#include <linux/miscdevice.h>
+#include <linux/netfs.h>
+#include <trace/events/netfs.h>
+#define CREATE_TRACE_POINTS
+#include "internal.h"
+
+unsigned cachefiles_debug;
+module_param_named(debug, cachefiles_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(cachefiles_debug, "CacheFiles debugging mask");
+
+MODULE_DESCRIPTION("Mounted-filesystem based cache");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+struct kmem_cache *cachefiles_object_jar;
+
+static struct miscdevice cachefiles_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "cachefiles",
+	.fops	= &cachefiles_daemon_fops,
+};
+
+/*
+ * initialise the fs caching module
+ */
+static int __init cachefiles_init(void)
+{
+	int ret;
+
+	ret = cachefiles_register_error_injection();
+	if (ret < 0)
+		goto error_einj;
+	ret = misc_register(&cachefiles_dev);
+	if (ret < 0)
+		goto error_dev;
+
+	/* create an object jar */
+	ret = -ENOMEM;
+	cachefiles_object_jar =
+		kmem_cache_create("cachefiles_object_jar",
+				  sizeof(struct cachefiles_object),
+				  0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!cachefiles_object_jar) {
+		pr_notice("Failed to allocate an object jar\n");
+		goto error_object_jar;
+	}
+
+	pr_info("Loaded\n");
+	return 0;
+
+error_object_jar:
+	misc_deregister(&cachefiles_dev);
+error_dev:
+	cachefiles_unregister_error_injection();
+error_einj:
+	pr_err("failed to register: %d\n", ret);
+	return ret;
+}
+
+fs_initcall(cachefiles_init);
+
+/*
+ * clean up on module removal
+ */
+static void __exit cachefiles_exit(void)
+{
+	pr_info("Unloading\n");
+
+	kmem_cache_destroy(cachefiles_object_jar);
+	misc_deregister(&cachefiles_dev);
+	cachefiles_unregister_error_injection();
+}
+
+module_exit(cachefiles_exit);