[PATCH v4 1/8] drivers: base: Add hardware prefetch control core driver

[Kohei Tarumizu <tarumizu.kohei@fujitsu.com>]

Adds a register/unregister function to provide sysfs interface to
control CPU's hardware prefetch behavior. It creates the
"prefetch_control" sysfs directory and some attributes.

Attributes are hardware dependent, so it must be implemented for each
hardware. If CPU has a hardware prefetch behavior, call this function
to create sysfs.

Following patches add support for A64FX and x86.

Signed-off-by: Kohei Tarumizu <tarumizu.kohei@fujitsu.com>
---
 drivers/base/pfctl.c  | 180 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/pfctl.h |  14 ++++
 2 files changed, 194 insertions(+)
 create mode 100644 drivers/base/pfctl.c
 create mode 100644 include/linux/pfctl.h

diff --git a/drivers/base/pfctl.c b/drivers/base/pfctl.c
new file mode 100644
index 000000000000..08ee8faaf277
--- /dev/null
+++ b/drivers/base/pfctl.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hardware prefetch control support via sysfs.
+ *
+ * Copyright 2022 FUJITSU LIMITED
+ *
+ * See Documentation/ABI/testing/sysfs-devices-system-cpu for more information.
+ */
+
+#include <linux/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/pfctl.h>
+#include <linux/slab.h>
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+const struct pfctl_group *pgroups;
+enum cpuhp_state hp_online;
+
+static struct device_attribute **
+get_pfctl_attribute(unsigned int level, enum cache_type type)
+{
+	int i;
+
+	for (i = 0; pgroups[i].attrs; i++)
+		if ((level == pgroups[i].level) && (type == pgroups[i].type))
+			return pgroups[i].attrs;
+
+	return NULL;
+}
+
+static int remove_pfctl_attr(struct device *index_dev, void *data)
+{
+	struct cacheinfo *leaf = dev_get_drvdata(index_dev);
+	struct device_attribute **attrs;
+	struct device *pfctl_dev;
+	int i;
+
+	attrs = get_pfctl_attribute(leaf->level, leaf->type);
+	if (!attrs)
+		return 0;
+
+	pfctl_dev = device_find_child_by_name(index_dev, "prefetch_control");
+	if (!pfctl_dev)
+		return 0;
+
+	for (i = 0; attrs[i]; i++)
+		device_remove_file(pfctl_dev, attrs[i]);
+
+	device_unregister(pfctl_dev);
+	put_device(pfctl_dev);
+
+	pfctl_dev = NULL;
+
+	return 0;
+}
+
+static int create_pfctl_attr(struct device *index_dev, void *data)
+{
+	struct cacheinfo *leaf = dev_get_drvdata(index_dev);
+	struct device_attribute **attrs;
+	struct device *pfctl_dev;
+	int i, err;
+
+	attrs = get_pfctl_attribute(leaf->level, leaf->type);
+	if (!attrs)
+		return 0;
+
+	pfctl_dev = cpu_device_create(index_dev, NULL, NULL,
+				      "prefetch_control");
+	if (IS_ERR(pfctl_dev))
+		return PTR_ERR(pfctl_dev);
+
+	for (i = 0; attrs[i]; i++) {
+		err = device_create_file(pfctl_dev, attrs[i]);
+		if (err) {
+			while (--i >= 0)
+				device_remove_file(pfctl_dev, attrs[i]);
+
+			device_unregister(pfctl_dev);
+			pfctl_dev = NULL;
+
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int pfctl_online(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct device *cache_dev;
+	int ret;
+
+	cache_dev = device_find_child_by_name(cpu_dev, "cache");
+	if (!cache_dev)
+		return -ENODEV;
+
+	ret = device_for_each_child(cache_dev, NULL, create_pfctl_attr);
+	if (ret < 0)
+		device_for_each_child(cache_dev, NULL, remove_pfctl_attr);
+
+	put_device(cache_dev);
+
+	return ret;
+}
+
+static int pfctl_prepare_down(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct device *cache_dev;
+
+	cache_dev = device_find_child_by_name(cpu_dev, "cache");
+	if (!cache_dev)
+		return 0;
+
+	device_for_each_child(cache_dev, NULL, remove_pfctl_attr);
+
+	put_device(cache_dev);
+
+	return 0;
+}
+
+/**
+ * pfctl_register_attrs - register a Hardware Prefetch Control attributes
+ * @pfctl_groups: pfctl_groups contains device attribute group to control the
+ *                hardware prefetch register.
+ *
+ * Note: Call this function after the cache device is initialized because it
+ * requires access to the cache device. (e.g. Call at the late_initcall)
+ *
+ * Context: Any context.
+ * Return: 0 on success, negative error code on failure.
+ */
+int pfctl_register_attrs(const struct pfctl_group *pfctl_groups)
+{
+	int ret;
+
+	if (pgroups)
+		return -EEXIST;
+
+	pgroups = pfctl_groups;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "base/pfctl:online",
+				pfctl_online, pfctl_prepare_down);
+	if (ret < 0) {
+		pr_err("failed to register hotplug callbacks\n");
+		pgroups = NULL;
+		return ret;
+	}
+
+	hp_online = ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pfctl_register_attrs);
+
+/**
+ * pfctl_unregister_attrs - unregister the Hardware Prefetch Control driver
+ * @pfctl_groups: Used to verify that this function is called by the same driver
+ *                that called pfctl_register_attrs.
+ *
+ * Context: Any context.
+ * Return: nothing.
+ */
+void pfctl_unregister_attrs(const struct pfctl_group *pfctl_groups)
+{
+	if (!pgroups || (pfctl_groups != pgroups))
+		return;
+
+	cpuhp_remove_state(hp_online);
+
+	pgroups = NULL;
+}
+EXPORT_SYMBOL_GPL(pfctl_unregister_attrs);
diff --git a/include/linux/pfctl.h b/include/linux/pfctl.h
new file mode 100644
index 000000000000..ecdab78be09f
--- /dev/null
+++ b/include/linux/pfctl.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PFCTL_H
+#define _LINUX_PFCTL_H
+
+struct pfctl_group {
+	unsigned int		level;
+	enum cache_type		type;
+	struct device_attribute	**attrs;
+};
+
+int pfctl_register_attrs(const struct pfctl_group *pfctl_groups);
+void pfctl_unregister_attrs(const struct pfctl_group *pfctl_groups);
+
+#endif
-- 
2.27.0