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, 50 insertions, 0 deletions

diff --git a/include/net/esp.h b/include/net/esp.h
new file mode 100644
index 000000000..322950727
--- /dev/null
+++ b/include/net/esp.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_ESP_H
+#define _NET_ESP_H
+
+#include <linux/skbuff.h>
+
+struct ip_esp_hdr;
+struct xfrm_state;
+
+static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb)
+{
+	return (struct ip_esp_hdr *)skb_transport_header(skb);
+}
+
+static inline void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
+{
+	/* Fill padding... */
+	if (tfclen) {
+		memset(tail, 0, tfclen);
+		tail += tfclen;
+	}
+	do {
+		int i;
+		for (i = 0; i < plen - 2; i++)
+			tail[i] = i + 1;
+	} while (0);
+	tail[plen - 2] = plen - 2;
+	tail[plen - 1] = proto;
+}
+
+struct esp_info {
+	struct	ip_esp_hdr *esph;
+	__be64	seqno;
+	int	tfclen;
+	int	tailen;
+	int	plen;
+	int	clen;
+	int 	len;
+	int 	nfrags;
+	__u8	proto;
+	bool	inplace;
+};
+
+int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp_input_done2(struct sk_buff *skb, int err);
+int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp6_input_done2(struct sk_buff *skb, int err);
+#endif