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, 56 insertions, 0 deletions

diff --git a/include/net/psample.h b/include/net/psample.h
new file mode 100644
index 000000000..5071b5fc2
--- /dev/null
+++ b/include/net/psample.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_PSAMPLE_H
+#define __NET_PSAMPLE_H
+
+#include <uapi/linux/psample.h>
+#include <linux/list.h>
+
+struct psample_group {
+	struct list_head list;
+	struct net *net;
+	u32 group_num;
+	u32 refcount;
+	u32 seq;
+	struct rcu_head rcu;
+};
+
+struct psample_metadata {
+	u32 trunc_size;
+	int in_ifindex;
+	int out_ifindex;
+	u16 out_tc;
+	u64 out_tc_occ;	/* bytes */
+	u64 latency;	/* nanoseconds */
+	u8 out_tc_valid:1,
+	   out_tc_occ_valid:1,
+	   latency_valid:1,
+	   rate_as_probability:1,
+	   unused:4;
+	const u8 *user_cookie;
+	u32 user_cookie_len;
+};
+
+struct psample_group *psample_group_get(struct net *net, u32 group_num);
+void psample_group_take(struct psample_group *group);
+void psample_group_put(struct psample_group *group);
+
+struct sk_buff;
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+
+void psample_sample_packet(struct psample_group *group,
+			   const struct sk_buff *skb, u32 sample_rate,
+			   const struct psample_metadata *md);
+
+#else
+
+static inline void psample_sample_packet(struct psample_group *group,
+					 const struct sk_buff *skb,
+					 u32 sample_rate,
+					 const struct psample_metadata *md)
+{
+}
+
+#endif
+
+#endif /* __NET_PSAMPLE_H */