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, 85 insertions, 0 deletions

diff --git a/include/net/ping.h b/include/net/ping.h
new file mode 100644
index 000000000..bcbdb5a13
--- /dev/null
+++ b/include/net/ping.h
@@ -0,0 +1,85 @@
+/* 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.
+ *
+ *		Definitions for the "ping" module.
+ */
+#ifndef _PING_H
+#define _PING_H
+
+#include <net/icmp.h>
+#include <net/netns/hash.h>
+
+/* PING_HTABLE_SIZE must be power of 2 */
+#define PING_HTABLE_SIZE 	64
+#define PING_HTABLE_MASK 	(PING_HTABLE_SIZE-1)
+
+#define GID_T_MAX (((gid_t)~0U) - 1)
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+	int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len);
+	void (*ip6_datagram_recv_common_ctl)(struct sock *sk,
+					     struct msghdr *msg,
+					     struct sk_buff *skb);
+	void (*ip6_datagram_recv_specific_ctl)(struct sock *sk,
+					       struct msghdr *msg,
+					       struct sk_buff *skb);
+	int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+	void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+				__be16 port, u32 info, u8 *payload);
+	int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+			     const struct net_device *dev, int strict);
+};
+
+struct ping_iter_state {
+	struct seq_net_private  p;
+	int			bucket;
+	sa_family_t		family;
+};
+
+extern struct proto ping_prot;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
+
+struct pingfakehdr {
+	struct icmphdr icmph;
+	struct msghdr *msg;
+	sa_family_t family;
+	__wsum wcheck;
+};
+
+int  ping_get_port(struct sock *sk, unsigned short ident);
+void ping_unhash(struct sock *sk);
+
+int  ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int  ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int  ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+		  struct sk_buff *);
+
+int  ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		  int flags);
+int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			 void *user_icmph, size_t icmph_len);
+int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
+
+#ifdef CONFIG_PROC_FS
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void ping_seq_stop(struct seq_file *seq, void *v);
+
+int __init ping_proc_init(void);
+void ping_proc_exit(void);
+#endif
+
+void __init ping_init(void);
+int  __init pingv6_init(void);
+void pingv6_exit(void);
+
+#endif /* _PING_H */