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, 98 insertions, 0 deletions

diff --git a/lib/once.c b/lib/once.c
new file mode 100644
index 000000000..d801bfa94
--- /dev/null
+++ b/lib/once.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/once.h>
+#include <linux/random.h>
+#include <linux/module.h>
+
+struct once_work {
+	struct work_struct work;
+	struct static_key_true *key;
+	struct module *module;
+};
+
+static void once_deferred(struct work_struct *w)
+{
+	struct once_work *work;
+
+	work = container_of(w, struct once_work, work);
+	BUG_ON(!static_key_enabled(work->key));
+	static_branch_disable(work->key);
+	module_put(work->module);
+	kfree(work);
+}
+
+static void once_disable_jump(struct static_key_true *key, struct module *mod)
+{
+	struct once_work *w;
+
+	w = kmalloc_obj(*w, GFP_ATOMIC);
+	if (!w)
+		return;
+
+	INIT_WORK(&w->work, once_deferred);
+	w->key = key;
+	w->module = mod;
+	__module_get(mod);
+	schedule_work(&w->work);
+}
+
+static DEFINE_SPINLOCK(once_lock);
+
+bool __do_once_start(bool *done, unsigned long *flags)
+	__acquires(once_lock)
+{
+	spin_lock_irqsave(&once_lock, *flags);
+	if (*done) {
+		spin_unlock_irqrestore(&once_lock, *flags);
+		/* Keep sparse happy by restoring an even lock count on
+		 * this lock. In case we return here, we don't call into
+		 * __do_once_done but return early in the DO_ONCE() macro.
+		 */
+		__acquire(once_lock);
+		return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(__do_once_start);
+
+void __do_once_done(bool *done, struct static_key_true *once_key,
+		    unsigned long *flags, struct module *mod)
+	__releases(once_lock)
+{
+	*done = true;
+	spin_unlock_irqrestore(&once_lock, *flags);
+	once_disable_jump(once_key, mod);
+}
+EXPORT_SYMBOL(__do_once_done);
+
+static DEFINE_MUTEX(once_mutex);
+
+bool __do_once_sleepable_start(bool *done)
+	__acquires(once_mutex)
+{
+	mutex_lock(&once_mutex);
+	if (*done) {
+		mutex_unlock(&once_mutex);
+		/* Keep sparse happy by restoring an even lock count on
+		 * this mutex. In case we return here, we don't call into
+		 * __do_once_done but return early in the DO_ONCE_SLEEPABLE() macro.
+		 */
+		__acquire(once_mutex);
+		return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(__do_once_sleepable_start);
+
+void __do_once_sleepable_done(bool *done, struct static_key_true *once_key,
+			 struct module *mod)
+	__releases(once_mutex)
+{
+	*done = true;
+	mutex_unlock(&once_mutex);
+	static_branch_disable(once_key);
+}
+EXPORT_SYMBOL(__do_once_sleepable_done);