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, 36 insertions, 0 deletions

diff --git a/include/uapi/fwctl/mlx5.h b/include/uapi/fwctl/mlx5.h
new file mode 100644
index 000000000..625819180
--- /dev/null
+++ b/include/uapi/fwctl/mlx5.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ *
+ * These are definitions for the command interface for mlx5 HW. mlx5 FW has a
+ * User Context mechanism which allows the FW to understand a security scope.
+ * FWCTL binds each FD to a FW user context and then places the User Context ID
+ * (UID) in each command header. The created User Context has a capability set
+ * that is appropriate for FWCTL's security model.
+ *
+ * Command formation should use a copy of the structs in mlx5_ifc.h following
+ * the Programmers Reference Manual. A open release is available here:
+ *
+ *  https://network.nvidia.com/files/doc-2020/ethernet-adapters-programming-manual.pdf
+ *
+ * The device_type for this file is FWCTL_DEVICE_TYPE_MLX5.
+ */
+#ifndef _UAPI_FWCTL_MLX5_H
+#define _UAPI_FWCTL_MLX5_H
+
+#include <linux/types.h>
+
+/**
+ * struct fwctl_info_mlx5 - ioctl(FWCTL_INFO) out_device_data
+ * @uid: The FW UID this FD is bound to. Each command header will force
+ *	this value.
+ * @uctx_caps: The FW capabilities that are enabled for the uid.
+ *
+ * Return basic information about the FW interface available.
+ */
+struct fwctl_info_mlx5 {
+	__u32 uid;
+	__u32 uctx_caps;
+};
+
+#endif