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, 73 insertions, 0 deletions

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
new file mode 100644
index 000000000..3a9001a04
--- /dev/null
+++ b/include/net/dst_ops.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_DST_OPS_H
+#define _NET_DST_OPS_H
+#include <linux/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/cache.h>
+
+struct dst_entry;
+struct kmem_cachep;
+struct net_device;
+struct sk_buff;
+struct sock;
+struct net;
+
+struct dst_ops {
+	unsigned short		family;
+	unsigned int		gc_thresh;
+
+	void			(*gc)(struct dst_ops *ops);
+	struct dst_entry *	(*check)(struct dst_entry *, __u32 cookie);
+	unsigned int		(*default_advmss)(const struct dst_entry *);
+	unsigned int		(*mtu)(const struct dst_entry *);
+	u32 *			(*cow_metrics)(struct dst_entry *, unsigned long);
+	void			(*destroy)(struct dst_entry *);
+	void			(*ifdown)(struct dst_entry *,
+					  struct net_device *dev);
+	void			(*negative_advice)(struct sock *sk, struct dst_entry *);
+	void			(*link_failure)(struct sk_buff *);
+	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
+	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
+					    struct sk_buff *skb);
+	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
+	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
+						struct sk_buff *skb,
+						const void *daddr);
+	void			(*confirm_neigh)(const struct dst_entry *dst,
+						 const void *daddr);
+
+	struct kmem_cache	*kmem_cachep;
+
+	struct percpu_counter	pcpuc_entries ____cacheline_aligned_in_smp;
+};
+
+static inline int dst_entries_get_fast(struct dst_ops *dst)
+{
+	return percpu_counter_read_positive(&dst->pcpuc_entries);
+}
+
+static inline int dst_entries_get_slow(struct dst_ops *dst)
+{
+	return percpu_counter_sum_positive(&dst->pcpuc_entries);
+}
+
+#define DST_PERCPU_COUNTER_BATCH 32
+static inline void dst_entries_add(struct dst_ops *dst, int val)
+{
+	percpu_counter_add_batch(&dst->pcpuc_entries, val,
+				 DST_PERCPU_COUNTER_BATCH);
+}
+
+static inline int dst_entries_init(struct dst_ops *dst)
+{
+	return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
+}
+
+static inline void dst_entries_destroy(struct dst_ops *dst)
+{
+	percpu_counter_destroy(&dst->pcpuc_entries);
+}
+
+#endif