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>

1 files changed, 103 insertions, 0 deletions

diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
new file mode 100644
index 000000000..88c10823f
--- /dev/null
+++ b/fs/sysfs/mount.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/sysfs/symlink.c - operations for initializing and mounting sysfs
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * Please see Documentation/filesystems/sysfs.rst for more information.
+ */
+
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/user_namespace.h>
+#include <linux/fs_context.h>
+#include <net/net_namespace.h>
+
+#include "sysfs.h"
+
+static struct kernfs_root *sysfs_root;
+struct kernfs_node *sysfs_root_kn;
+
+static void sysfs_fs_context_free(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	if (kfc->ns_tag)
+		kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag);
+	kernfs_free_fs_context(fc);
+	kfree(kfc);
+}
+
+static const struct fs_context_operations sysfs_fs_context_ops = {
+	.free		= sysfs_fs_context_free,
+	.get_tree	= kernfs_get_tree,
+};
+
+static int sysfs_init_fs_context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc;
+	struct ns_common *ns;
+
+	if (!(fc->sb_flags & SB_KERNMOUNT)) {
+		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
+			return -EPERM;
+	}
+
+	kfc = kzalloc_obj(struct kernfs_fs_context);
+	if (!kfc)
+		return -ENOMEM;
+
+	kfc->ns_tag = ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	kfc->root = sysfs_root;
+	kfc->magic = SYSFS_MAGIC;
+	fc->fs_private = kfc;
+	fc->ops = &sysfs_fs_context_ops;
+	if (ns) {
+		struct net *netns = to_net_ns(ns);
+
+		put_user_ns(fc->user_ns);
+		fc->user_ns = get_user_ns(netns->user_ns);
+	}
+	fc->global = true;
+	return 0;
+}
+
+static void sysfs_kill_sb(struct super_block *sb)
+{
+	struct ns_common *ns = (struct ns_common *)kernfs_super_ns(sb);
+
+	kernfs_kill_sb(sb);
+	kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
+}
+
+static struct file_system_type sysfs_fs_type = {
+	.name			= "sysfs",
+	.init_fs_context	= sysfs_init_fs_context,
+	.kill_sb		= sysfs_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED,
+};
+
+int __init sysfs_init(void)
+{
+	int err;
+
+	sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
+					NULL);
+	if (IS_ERR(sysfs_root))
+		return PTR_ERR(sysfs_root);
+
+	sysfs_root_kn = kernfs_root_to_node(sysfs_root);
+
+	err = register_filesystem(&sysfs_fs_type);
+	if (err) {
+		kernfs_destroy_root(sysfs_root);
+		return err;
+	}
+
+	return 0;
+}