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, 58 insertions, 0 deletions

diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h
new file mode 100644
index 000000000..957d9ef92
--- /dev/null
+++ b/include/net/mctpdevice.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Management Component Transport Protocol (MCTP) - device
+ * definitions.
+ *
+ * Copyright (c) 2021 Code Construct
+ * Copyright (c) 2021 Google
+ */
+
+#ifndef __NET_MCTPDEVICE_H
+#define __NET_MCTPDEVICE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/refcount.h>
+
+struct mctp_sk_key;
+
+struct mctp_dev {
+	struct net_device	*dev;
+
+	refcount_t		refs;
+
+	unsigned int		net;
+	enum mctp_phys_binding	binding;
+
+	const struct mctp_netdev_ops *ops;
+
+	/* Only modified under RTNL. Reads have addrs_lock held */
+	u8			*addrs;
+	size_t			num_addrs;
+	spinlock_t		addrs_lock;
+
+	struct rcu_head		rcu;
+};
+
+struct mctp_netdev_ops {
+	void			(*release_flow)(struct mctp_dev *dev,
+						struct mctp_sk_key *key);
+};
+
+#define MCTP_INITIAL_DEFAULT_NET	1
+
+struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev);
+struct mctp_dev *__mctp_dev_get(const struct net_device *dev);
+
+int mctp_register_netdev(struct net_device *dev,
+			 const struct mctp_netdev_ops *ops,
+			 enum mctp_phys_binding binding);
+void mctp_unregister_netdev(struct net_device *dev);
+
+void mctp_dev_hold(struct mctp_dev *mdev);
+void mctp_dev_put(struct mctp_dev *mdev);
+
+void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key);
+void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key);
+
+#endif /* __NET_MCTPDEVICE_H */