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, 80 insertions, 0 deletions

diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c
new file mode 100644
index 000000000..44b62b3c3
--- /dev/null
+++ b/fs/jfs/jfs_debug.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *   Copyright (C) International Business Machines Corp., 2000-2004
+ *   Portions Copyright (C) Christoph Hellwig, 2001-2002
+ */
+
+#include <linux/fs.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include "jfs_incore.h"
+#include "jfs_filsys.h"
+#include "jfs_debug.h"
+
+#ifdef PROC_FS_JFS /* see jfs_debug.h */
+
+#ifdef CONFIG_JFS_DEBUG
+static int jfs_loglevel_proc_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "%d\n", jfsloglevel);
+	return 0;
+}
+
+static int jfs_loglevel_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, jfs_loglevel_proc_show, NULL);
+}
+
+static ssize_t jfs_loglevel_proc_write(struct file *file,
+		const char __user *buffer, size_t count, loff_t *ppos)
+{
+	char c;
+
+	if (get_user(c, buffer))
+		return -EFAULT;
+
+	/* yes, I know this is an ASCIIism.  --hch */
+	if (c < '0' || c > '9')
+		return -EINVAL;
+	jfsloglevel = c - '0';
+	return count;
+}
+
+static const struct proc_ops jfs_loglevel_proc_ops = {
+	.proc_open	= jfs_loglevel_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= jfs_loglevel_proc_write,
+};
+#endif
+
+void jfs_proc_init(void)
+{
+	struct proc_dir_entry *base;
+
+	base = proc_mkdir("fs/jfs", NULL);
+	if (!base)
+		return;
+
+#ifdef CONFIG_JFS_STATISTICS
+	proc_create_single("lmstats", 0, base, jfs_lmstats_proc_show);
+	proc_create_single("txstats", 0, base, jfs_txstats_proc_show);
+	proc_create_single("xtstat", 0, base, jfs_xtstat_proc_show);
+	proc_create_single("mpstat", 0, base, jfs_mpstat_proc_show);
+#endif
+#ifdef CONFIG_JFS_DEBUG
+	proc_create_single("TxAnchor", 0, base, jfs_txanchor_proc_show);
+	proc_create("loglevel", 0, base, &jfs_loglevel_proc_ops);
+#endif
+}
+
+void jfs_proc_clean(void)
+{
+	remove_proc_subtree("fs/jfs", NULL);
+}
+
+#endif /* PROC_FS_JFS */