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, 84 insertions, 0 deletions

diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
new file mode 100644
index 000000000..e95c79b80
--- /dev/null
+++ b/tools/perf/util/namespaces.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#ifndef __PERF_NAMESPACES_H
+#define __PERF_NAMESPACES_H
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <linux/stddef.h>
+#include <linux/perf_event.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+#include <internal/rc_check.h>
+
+#ifndef HAVE_SETNS_SUPPORT
+int setns(int fd, int nstype);
+#endif
+
+struct perf_record_namespaces;
+
+struct namespaces {
+	struct list_head list;
+	u64 end_time;
+	struct perf_ns_link_info link_info[];
+};
+
+struct namespaces *namespaces__new(struct perf_record_namespaces *event);
+void namespaces__free(struct namespaces *namespaces);
+
+DECLARE_RC_STRUCT(nsinfo) {
+	pid_t			pid;
+	pid_t			tgid;
+	pid_t			nstgid;
+	bool			need_setns;
+	bool			in_pidns;
+	char			*mntns_path;
+	refcount_t		refcnt;
+};
+
+struct nscookie {
+	int			oldns;
+	int			newns;
+	char			*oldcwd;
+};
+
+int nsinfo__init(struct nsinfo *nsi);
+struct nsinfo *nsinfo__new(pid_t pid);
+struct nsinfo *nsinfo__copy(const struct nsinfo *nsi);
+
+struct nsinfo *nsinfo__get(struct nsinfo *nsi);
+void nsinfo__put(struct nsinfo *nsi);
+
+bool nsinfo__need_setns(const struct nsinfo *nsi);
+void nsinfo__clear_need_setns(struct nsinfo *nsi);
+pid_t nsinfo__tgid(const struct nsinfo  *nsi);
+pid_t nsinfo__nstgid(const struct nsinfo  *nsi);
+pid_t nsinfo__pid(const struct nsinfo  *nsi);
+bool nsinfo__in_pidns(const struct nsinfo  *nsi);
+void nsinfo__set_in_pidns(struct nsinfo *nsi);
+
+void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc);
+void nsinfo__mountns_exit(struct nscookie *nc);
+
+char *nsinfo__realpath(const char *path, struct nsinfo *nsi);
+int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi);
+
+bool nsinfo__is_in_root_namespace(void);
+
+static inline void __nsinfo__zput(struct nsinfo **nsip)
+{
+	if (nsip) {
+		nsinfo__put(*nsip);
+		*nsip = NULL;
+	}
+}
+
+#define nsinfo__zput(nsi) __nsinfo__zput(&nsi)
+
+const char *perf_ns__name(unsigned int id);
+
+#endif  /* __PERF_NAMESPACES_H */