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, 70 insertions, 0 deletions

diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
new file mode 100644
index 000000000..691397994
--- /dev/null
+++ b/net/ipv4/protocol.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		INET protocol dispatch tables.
+ *
+ * Authors:	Ross Biro
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * Fixes:
+ *		Alan Cox	: Ahah! udp icmp errors don't work because
+ *				  udp_err is never called!
+ *		Alan Cox	: Added new fields for init and ready for
+ *				  proper fragmentation (_NO_ 4K limits!)
+ *		Richard Colella	: Hang on hash collision
+ *		Vince Laviano	: Modified inet_del_protocol() to correctly
+ *				  maintain copy bit.
+ */
+#include <linux/cache.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <net/protocol.h>
+
+struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet_protos);
+const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet_offloads);
+
+int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
+{
+	return !cmpxchg((const struct net_protocol **)&inet_protos[protocol],
+			NULL, prot) ? 0 : -1;
+}
+EXPORT_SYMBOL(inet_add_protocol);
+
+int inet_add_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	return !cmpxchg((const struct net_offload **)&inet_offloads[protocol],
+			NULL, prot) ? 0 : -1;
+}
+EXPORT_SYMBOL(inet_add_offload);
+
+int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
+{
+	int ret;
+
+	ret = (cmpxchg((const struct net_protocol **)&inet_protos[protocol],
+		       prot, NULL) == prot) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(inet_del_protocol);
+
+int inet_del_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	int ret;
+
+	ret = (cmpxchg((const struct net_offload **)&inet_offloads[protocol],
+		       prot, NULL) == prot) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(inet_del_offload);