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, 100 insertions, 0 deletions

diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
new file mode 100644
index 000000000..51f8f3881
--- /dev/null
+++ b/include/asm-generic/preempt.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <linux/thread_info.h>
+
+#define PREEMPT_ENABLED	(0)
+
+static __always_inline int preempt_count(void)
+{
+	return READ_ONCE(current_thread_info()->preempt_count);
+}
+
+static __always_inline volatile int *preempt_count_ptr(void)
+{
+	return &current_thread_info()->preempt_count;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+	*preempt_count_ptr() = pc;
+}
+
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+static __always_inline void set_preempt_need_resched(void)
+{
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return false;
+}
+
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+	*preempt_count_ptr() += val;
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+	*preempt_count_ptr() -= val;
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	/*
+	 * Because of load-store architectures cannot do per-cpu atomic
+	 * operations; we cannot use PREEMPT_NEED_RESCHED because it might get
+	 * lost.
+	 */
+	return !--*preempt_count_ptr() && tif_need_resched();
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(int preempt_offset)
+{
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
+}
+
+#ifdef CONFIG_PREEMPTION
+extern asmlinkage void preempt_schedule(void);
+extern asmlinkage void preempt_schedule_notrace(void);
+
+#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+
+void dynamic_preempt_schedule(void);
+void dynamic_preempt_schedule_notrace(void);
+#define __preempt_schedule()		dynamic_preempt_schedule()
+#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
+
+#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
+
+#define __preempt_schedule() preempt_schedule()
+#define __preempt_schedule_notrace() preempt_schedule_notrace()
+
+#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
+#endif /* CONFIG_PREEMPTION */
+
+#endif /* __ASM_PREEMPT_H */