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, 82 insertions, 0 deletions

diff --git a/drivers/dio/dio-sysfs.c b/drivers/dio/dio-sysfs.c
new file mode 100644
index 000000000..ee1a3b59b
--- /dev/null
+++ b/drivers/dio/dio-sysfs.c
@@ -0,0 +1,82 @@
+/*
+ *  File Attributes for DIO Devices
+ *
+ *  Copyright (C) 2004 Jochen Friedrich
+ *
+ *  Loosely based on drivers/pci/pci-sysfs.c and drivers/zorro/zorro-sysfs.c
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License.  See the file COPYING in the main directory of this archive
+ *  for more details.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/dio.h>
+#include <linux/stat.h>
+
+/* show configuration fields */
+
+static ssize_t dio_show_id(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct dio_dev *d;
+
+	d = to_dio_dev(dev);
+	return sprintf(buf, "0x%02x\n", (d->id & 0xff));
+}
+static DEVICE_ATTR(id, S_IRUGO, dio_show_id, NULL);
+
+static ssize_t dio_show_ipl(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct dio_dev *d;
+
+	d = to_dio_dev(dev);
+	return sprintf(buf, "0x%02x\n", d->ipl);
+}
+static DEVICE_ATTR(ipl, S_IRUGO, dio_show_ipl, NULL);
+
+static ssize_t dio_show_secid(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct dio_dev *d;
+
+	d = to_dio_dev(dev);
+	return sprintf(buf, "0x%02x\n", ((d->id >> 8)& 0xff));
+}
+static DEVICE_ATTR(secid, S_IRUGO, dio_show_secid, NULL);
+
+static ssize_t dio_show_name(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct dio_dev *d;
+
+	d = to_dio_dev(dev);
+	return sprintf(buf, "%s\n", d->name);
+}
+static DEVICE_ATTR(name, S_IRUGO, dio_show_name, NULL);
+
+static ssize_t dio_show_resource(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct dio_dev *d = to_dio_dev(dev);
+
+	return sprintf(buf, "0x%08lx 0x%08lx 0x%08lx\n",
+		       (unsigned long)dio_resource_start(d),
+		       (unsigned long)dio_resource_end(d),
+		       dio_resource_flags(d));
+}
+static DEVICE_ATTR(resource, S_IRUGO, dio_show_resource, NULL);
+
+int dio_create_sysfs_dev_files(struct dio_dev *d)
+{
+	struct device *dev = &d->dev;
+	int error;
+
+	/* current configuration's attributes */
+	if ((error = device_create_file(dev, &dev_attr_id)) ||
+	    (error = device_create_file(dev, &dev_attr_ipl)) ||
+	    (error = device_create_file(dev, &dev_attr_secid)) ||
+	    (error = device_create_file(dev, &dev_attr_name)) ||
+	    (error = device_create_file(dev, &dev_attr_resource)))
+		return error;
+
+	return 0;
+}
+