sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

3 files changed, 452 insertions, 0 deletions

diff --git a/samples/kobject/Makefile b/samples/kobject/Makefile
new file mode 100644
index 000000000..bb5d21997
--- /dev/null
+++ b/samples/kobject/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SAMPLE_KOBJECT) += kobject-example.o kset-example.o
diff --git a/samples/kobject/kobject-example.c b/samples/kobject/kobject-example.c
new file mode 100644
index 000000000..36d87ca0b
--- /dev/null
+++ b/samples/kobject/kobject-example.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Sample kobject implementation
+ *
+ * Copyright (C) 2004-2007 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2007 Novell Inc.
+ */
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+/*
+ * This module shows how to create a simple subdirectory in sysfs called
+ * /sys/kernel/kobject_example  In that directory, 3 files are created:
+ * "foo", "baz", and "bar".  If an integer is written to these files, it can be
+ * later read out of it.
+ */
+
+static int foo;
+static int baz;
+static int bar;
+
+/*
+ * The "foo" file where a static variable is read from and written to.
+ */
+static ssize_t foo_show(struct kobject *kobj, struct kobj_attribute *attr,
+			char *buf)
+{
+	return sysfs_emit(buf, "%d\n", foo);
+}
+
+static ssize_t foo_store(struct kobject *kobj, struct kobj_attribute *attr,
+			 const char *buf, size_t count)
+{
+	int ret;
+
+	ret = kstrtoint(buf, 10, &foo);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+/* Sysfs attributes cannot be world-writable. */
+static struct kobj_attribute foo_attribute =
+	__ATTR(foo, 0664, foo_show, foo_store);
+
+/*
+ * More complex function where we determine which variable is being accessed by
+ * looking at the attribute for the "baz" and "bar" files.
+ */
+static ssize_t b_show(struct kobject *kobj, struct kobj_attribute *attr,
+		      char *buf)
+{
+	int var;
+
+	if (strcmp(attr->attr.name, "baz") == 0)
+		var = baz;
+	else
+		var = bar;
+	return sysfs_emit(buf, "%d\n", var);
+}
+
+static ssize_t b_store(struct kobject *kobj, struct kobj_attribute *attr,
+		       const char *buf, size_t count)
+{
+	int var, ret;
+
+	ret = kstrtoint(buf, 10, &var);
+	if (ret < 0)
+		return ret;
+
+	if (strcmp(attr->attr.name, "baz") == 0)
+		baz = var;
+	else
+		bar = var;
+	return count;
+}
+
+static struct kobj_attribute baz_attribute =
+	__ATTR(baz, 0664, b_show, b_store);
+static struct kobj_attribute bar_attribute =
+	__ATTR(bar, 0664, b_show, b_store);
+
+
+/*
+ * Create a group of attributes so that we can create and destroy them all
+ * at once.
+ */
+static struct attribute *attrs[] = {
+	&foo_attribute.attr,
+	&baz_attribute.attr,
+	&bar_attribute.attr,
+	NULL,	/* need to NULL terminate the list of attributes */
+};
+
+/*
+ * An unnamed attribute group will put all of the attributes directly in
+ * the kobject directory.  If we specify a name, a subdirectory will be
+ * created for the attributes with the directory being the name of the
+ * attribute group.
+ */
+static const struct attribute_group attr_group = {
+	.attrs = attrs,
+};
+
+static struct kobject *example_kobj;
+
+static int __init example_init(void)
+{
+	int retval;
+
+	/*
+	 * Create a simple kobject with the name of "kobject_example",
+	 * located under /sys/kernel/
+	 *
+	 * As this is a simple directory, no uevent will be sent to
+	 * userspace.  That is why this function should not be used for
+	 * any type of dynamic kobjects, where the name and number are
+	 * not known ahead of time.
+	 */
+	example_kobj = kobject_create_and_add("kobject_example", kernel_kobj);
+	if (!example_kobj)
+		return -ENOMEM;
+
+	/* Create the files associated with this kobject */
+	retval = sysfs_create_group(example_kobj, &attr_group);
+	if (retval)
+		kobject_put(example_kobj);
+
+	return retval;
+}
+
+static void __exit example_exit(void)
+{
+	kobject_put(example_kobj);
+}
+
+module_init(example_init);
+module_exit(example_exit);
+MODULE_DESCRIPTION("Sample kobject implementation");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Greg Kroah-Hartman <greg@kroah.com>");
diff --git a/samples/kobject/kset-example.c b/samples/kobject/kset-example.c
new file mode 100644
index 000000000..d0103904e
--- /dev/null
+++ b/samples/kobject/kset-example.c
@@ -0,0 +1,305 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Sample kset and ktype implementation
+ *
+ * Copyright (C) 2004-2007 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2007 Novell Inc.
+ */
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+/*
+ * This module shows how to create a kset in sysfs called
+ * /sys/kernel/kset_example
+ * Then three kobjects are created and assigned to this kset, "foo", "baz",
+ * and "bar".  In those kobjects, attributes of the same name are also
+ * created and if an integer is written to these files, it can be later
+ * read out of it.
+ */
+
+
+/*
+ * This is our "object" that we will create a few of and register them with
+ * sysfs.
+ */
+struct foo_obj {
+	struct kobject kobj;
+	int foo;
+	int baz;
+	int bar;
+};
+#define to_foo_obj(x) container_of(x, struct foo_obj, kobj)
+
+/* a custom attribute that works just for a struct foo_obj. */
+struct foo_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct foo_obj *foo, const struct foo_attribute *attr, char *buf);
+	ssize_t (*store)(struct foo_obj *foo, const struct foo_attribute *attr,
+			 const char *buf, size_t count);
+};
+#define to_foo_attr(x) container_of_const(x, struct foo_attribute, attr)
+
+/*
+ * The default show function that must be passed to sysfs.  This will be
+ * called by sysfs for whenever a show function is called by the user on a
+ * sysfs file associated with the kobjects we have registered.  We need to
+ * transpose back from a "default" kobject to our custom struct foo_obj and
+ * then call the show function for that specific object.
+ */
+static ssize_t foo_attr_show(struct kobject *kobj,
+			     struct attribute *attr,
+			     char *buf)
+{
+	const struct foo_attribute *attribute;
+	struct foo_obj *foo;
+
+	attribute = to_foo_attr(attr);
+	foo = to_foo_obj(kobj);
+
+	if (!attribute->show)
+		return -EIO;
+
+	return attribute->show(foo, attribute, buf);
+}
+
+/*
+ * Just like the default show function above, but this one is for when the
+ * sysfs "store" is requested (when a value is written to a file.)
+ */
+static ssize_t foo_attr_store(struct kobject *kobj,
+			      struct attribute *attr,
+			      const char *buf, size_t len)
+{
+	const struct foo_attribute *attribute;
+	struct foo_obj *foo;
+
+	attribute = to_foo_attr(attr);
+	foo = to_foo_obj(kobj);
+
+	if (!attribute->store)
+		return -EIO;
+
+	return attribute->store(foo, attribute, buf, len);
+}
+
+/* Our custom sysfs_ops that we will associate with our ktype later on */
+static const struct sysfs_ops foo_sysfs_ops = {
+	.show = foo_attr_show,
+	.store = foo_attr_store,
+};
+
+/*
+ * The release function for our object.  This is REQUIRED by the kernel to
+ * have.  We free the memory held in our object here.
+ *
+ * NEVER try to get away with just a "blank" release function to try to be
+ * smarter than the kernel.  Turns out, no one ever is...
+ */
+static void foo_release(struct kobject *kobj)
+{
+	struct foo_obj *foo;
+
+	foo = to_foo_obj(kobj);
+	kfree(foo);
+}
+
+/*
+ * The "foo" file where the .foo variable is read from and written to.
+ */
+static ssize_t foo_show(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+			char *buf)
+{
+	return sysfs_emit(buf, "%d\n", foo_obj->foo);
+}
+
+static ssize_t foo_store(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+			 const char *buf, size_t count)
+{
+	int ret;
+
+	ret = kstrtoint(buf, 10, &foo_obj->foo);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+/* Sysfs attributes cannot be world-writable. */
+static const struct foo_attribute foo_attribute =
+	__ATTR(foo, 0664, foo_show, foo_store);
+
+/*
+ * More complex function where we determine which variable is being accessed by
+ * looking at the attribute for the "baz" and "bar" files.
+ */
+static ssize_t b_show(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+		      char *buf)
+{
+	int var;
+
+	if (strcmp(attr->attr.name, "baz") == 0)
+		var = foo_obj->baz;
+	else
+		var = foo_obj->bar;
+	return sysfs_emit(buf, "%d\n", var);
+}
+
+static ssize_t b_store(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+		       const char *buf, size_t count)
+{
+	int var, ret;
+
+	ret = kstrtoint(buf, 10, &var);
+	if (ret < 0)
+		return ret;
+
+	if (strcmp(attr->attr.name, "baz") == 0)
+		foo_obj->baz = var;
+	else
+		foo_obj->bar = var;
+	return count;
+}
+
+static const struct foo_attribute baz_attribute =
+	__ATTR(baz, 0664, b_show, b_store);
+static const struct foo_attribute bar_attribute =
+	__ATTR(bar, 0664, b_show, b_store);
+
+/*
+ * Create a group of attributes so that we can create and destroy them all
+ * at once.
+ */
+static const struct attribute *const foo_default_attrs[] = {
+	&foo_attribute.attr,
+	&baz_attribute.attr,
+	&bar_attribute.attr,
+	NULL,	/* need to NULL terminate the list of attributes */
+};
+
+static umode_t foo_default_attrs_is_visible(struct kobject *kobj,
+					    const struct attribute *attr,
+					    int n)
+{
+	/* Hide attributes with the same name as the kobject. */
+	if (strcmp(kobject_name(kobj), attr->name) == 0)
+		return 0;
+	return attr->mode;
+}
+
+static const struct attribute_group foo_default_group = {
+	.attrs_const		= foo_default_attrs,
+	.is_visible_const	= foo_default_attrs_is_visible,
+};
+__ATTRIBUTE_GROUPS(foo_default);
+
+/*
+ * Our own ktype for our kobjects.  Here we specify our sysfs ops, the
+ * release function, and the set of default attributes we want created
+ * whenever a kobject of this type is registered with the kernel.
+ */
+static const struct kobj_type foo_ktype = {
+	.sysfs_ops = &foo_sysfs_ops,
+	.release = foo_release,
+	.default_groups = foo_default_groups,
+};
+
+static struct kset *example_kset;
+static struct foo_obj *foo_obj;
+static struct foo_obj *bar_obj;
+static struct foo_obj *baz_obj;
+
+static struct foo_obj *create_foo_obj(const char *name)
+{
+	struct foo_obj *foo;
+	int retval;
+
+	/* allocate the memory for the whole object */
+	foo = kzalloc(sizeof(*foo), GFP_KERNEL);
+	if (!foo)
+		return NULL;
+
+	/*
+	 * As we have a kset for this kobject, we need to set it before calling
+	 * the kobject core.
+	 */
+	foo->kobj.kset = example_kset;
+
+	/*
+	 * Initialize and add the kobject to the kernel.  All the default files
+	 * will be created here.  As we have already specified a kset for this
+	 * kobject, we don't have to set a parent for the kobject, the kobject
+	 * will be placed beneath that kset automatically.
+	 */
+	retval = kobject_init_and_add(&foo->kobj, &foo_ktype, NULL, "%s", name);
+	if (retval) {
+		kobject_put(&foo->kobj);
+		return NULL;
+	}
+
+	/*
+	 * We are always responsible for sending the uevent that the kobject
+	 * was added to the system.
+	 */
+	kobject_uevent(&foo->kobj, KOBJ_ADD);
+
+	return foo;
+}
+
+static void destroy_foo_obj(struct foo_obj *foo)
+{
+	kobject_put(&foo->kobj);
+}
+
+static int __init example_init(void)
+{
+	/*
+	 * Create a kset with the name of "kset_example",
+	 * located under /sys/kernel/
+	 */
+	example_kset = kset_create_and_add("kset_example", NULL, kernel_kobj);
+	if (!example_kset)
+		return -ENOMEM;
+
+	/*
+	 * Create three objects and register them with our kset
+	 */
+	foo_obj = create_foo_obj("foo");
+	if (!foo_obj)
+		goto foo_error;
+
+	bar_obj = create_foo_obj("bar");
+	if (!bar_obj)
+		goto bar_error;
+
+	baz_obj = create_foo_obj("baz");
+	if (!baz_obj)
+		goto baz_error;
+
+	return 0;
+
+baz_error:
+	destroy_foo_obj(bar_obj);
+bar_error:
+	destroy_foo_obj(foo_obj);
+foo_error:
+	kset_unregister(example_kset);
+	return -EINVAL;
+}
+
+static void __exit example_exit(void)
+{
+	destroy_foo_obj(baz_obj);
+	destroy_foo_obj(bar_obj);
+	destroy_foo_obj(foo_obj);
+	kset_unregister(example_kset);
+}
+
+module_init(example_init);
+module_exit(example_exit);
+MODULE_DESCRIPTION("Sample kset and ktype implementation");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Greg Kroah-Hartman <greg@kroah.com>");