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/drivers/mtd/mtdblock_ro.c b/drivers/mtd/mtdblock_ro.c
new file mode 100644
index 000000000..e564521d6
--- /dev/null
+++ b/drivers/mtd/mtdblock_ro.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Simple read-only (writable only for RAM) mtdblock driver
+ *
+ * Copyright © 2001-2010 David Woodhouse <dwmw2@infradead.org>
+ */
+
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/blktrans.h>
+#include <linux/module.h>
+#include <linux/major.h>
+
+static int mtdblock_readsect(struct mtd_blktrans_dev *dev,
+			      unsigned long block, char *buf)
+{
+	size_t retlen;
+	int err;
+
+	err = mtd_read(dev->mtd, (block * 512), 512, &retlen, buf);
+	if (err && !mtd_is_bitflip(err))
+		return 1;
+	return 0;
+}
+
+static int mtdblock_writesect(struct mtd_blktrans_dev *dev,
+			      unsigned long block, char *buf)
+{
+	size_t retlen;
+
+	if (mtd_write(dev->mtd, (block * 512), 512, &retlen, buf))
+		return 1;
+	return 0;
+}
+
+static void mtdblock_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
+{
+	struct mtd_blktrans_dev *dev = kzalloc_obj(*dev);
+
+	if (!dev)
+		return;
+
+	dev->mtd = mtd;
+	dev->devnum = mtd->index;
+
+	dev->size = mtd->size >> 9;
+	dev->tr = tr;
+	dev->readonly = 1;
+
+	if (mtd_type_is_nand(mtd))
+		pr_warn_ratelimited("%s: MTD device '%s' is NAND, please consider using UBI block devices instead.\n",
+			tr->name, mtd->name);
+
+	if (add_mtd_blktrans_dev(dev))
+		kfree(dev);
+}
+
+static void mtdblock_remove_dev(struct mtd_blktrans_dev *dev)
+{
+	del_mtd_blktrans_dev(dev);
+}
+
+static struct mtd_blktrans_ops mtdblock_tr = {
+	.name		= "mtdblock",
+	.major		= MTD_BLOCK_MAJOR,
+	.part_bits	= 0,
+	.blksize 	= 512,
+	.readsect	= mtdblock_readsect,
+	.writesect	= mtdblock_writesect,
+	.add_mtd	= mtdblock_add_mtd,
+	.remove_dev	= mtdblock_remove_dev,
+	.owner		= THIS_MODULE,
+};
+
+module_mtd_blktrans(mtdblock_tr);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
+MODULE_DESCRIPTION("Simple read-only block device emulation access to MTD devices");