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, 136 insertions, 0 deletions

diff --git a/drivers/firmware/google/cbmem.c b/drivers/firmware/google/cbmem.c
new file mode 100644
index 000000000..4d20477ed
--- /dev/null
+++ b/drivers/firmware/google/cbmem.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * cbmem.c
+ *
+ * Driver for exporting cbmem entries in sysfs.
+ *
+ * Copyright 2022 Google LLC
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/device-id/coreboot.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+#include "coreboot_table.h"
+
+struct cbmem_entry {
+	char *mem_file_buf;
+	u32 size;
+};
+
+static struct cbmem_entry *to_cbmem_entry(struct kobject *kobj)
+{
+	return dev_get_drvdata(kobj_to_dev(kobj));
+}
+
+static ssize_t mem_read(struct file *filp, struct kobject *kobj,
+			const struct bin_attribute *bin_attr, char *buf, loff_t pos,
+			size_t count)
+{
+	struct cbmem_entry *entry = to_cbmem_entry(kobj);
+
+	return memory_read_from_buffer(buf, count, &pos, entry->mem_file_buf,
+				       entry->size);
+}
+
+static ssize_t mem_write(struct file *filp, struct kobject *kobj,
+			 const struct bin_attribute *bin_attr, char *buf, loff_t pos,
+			 size_t count)
+{
+	struct cbmem_entry *entry = to_cbmem_entry(kobj);
+
+	if (pos < 0 || pos >= entry->size)
+		return -EINVAL;
+	if (count > entry->size - pos)
+		count = entry->size - pos;
+
+	memcpy(entry->mem_file_buf + pos, buf, count);
+	return count;
+}
+static const BIN_ATTR_ADMIN_RW(mem, 0);
+
+static ssize_t address_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct coreboot_device *cbdev = dev_to_coreboot_device(dev);
+
+	return sysfs_emit(buf, "0x%llx\n", cbdev->cbmem_entry.address);
+}
+static DEVICE_ATTR_RO(address);
+
+static ssize_t size_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct coreboot_device *cbdev = dev_to_coreboot_device(dev);
+
+	return sysfs_emit(buf, "0x%x\n", cbdev->cbmem_entry.entry_size);
+}
+static DEVICE_ATTR_RO(size);
+
+static struct attribute *attrs[] = {
+	&dev_attr_address.attr,
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct bin_attribute *const bin_attrs[] = {
+	&bin_attr_mem,
+	NULL,
+};
+
+static const struct attribute_group cbmem_entry_group = {
+	.attrs = attrs,
+	.bin_attrs = bin_attrs,
+};
+
+static const struct attribute_group *dev_groups[] = {
+	&cbmem_entry_group,
+	NULL,
+};
+
+static int cbmem_entry_probe(struct coreboot_device *dev)
+{
+	struct cbmem_entry *entry;
+
+	entry = devm_kzalloc(&dev->dev, sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	dev_set_drvdata(&dev->dev, entry);
+	entry->mem_file_buf = devm_memremap(&dev->dev, dev->cbmem_entry.address,
+					    dev->cbmem_entry.entry_size,
+					    MEMREMAP_WB);
+	if (IS_ERR(entry->mem_file_buf))
+		return PTR_ERR(entry->mem_file_buf);
+
+	entry->size = dev->cbmem_entry.entry_size;
+
+	return 0;
+}
+
+static const struct coreboot_device_id cbmem_ids[] = {
+	{ .tag = LB_TAG_CBMEM_ENTRY },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(coreboot, cbmem_ids);
+
+static struct coreboot_driver cbmem_entry_driver = {
+	.probe = cbmem_entry_probe,
+	.drv = {
+		.name = "cbmem",
+		.dev_groups = dev_groups,
+	},
+	.id_table = cbmem_ids,
+};
+module_coreboot_driver(cbmem_entry_driver);
+
+MODULE_AUTHOR("Jack Rosenthal <jrosenth@chromium.org>");
+MODULE_DESCRIPTION("Driver for exporting CBMEM entries in sysfs");
+MODULE_LICENSE("GPL");