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>

3 files changed, 64 insertions, 0 deletions

diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h
new file mode 100644
index 000000000..388b21208
--- /dev/null
+++ b/tools/include/vdso/bits.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_BITS_H
+#define __VDSO_BITS_H
+
+#include <vdso/const.h>
+
+#define BIT(nr)			(UL(1) << (nr))
+#define BIT_ULL(nr)		(ULL(1) << (nr))
+
+#endif	/* __VDSO_BITS_H */
diff --git a/tools/include/vdso/const.h b/tools/include/vdso/const.h
new file mode 100644
index 000000000..94b385ad4
--- /dev/null
+++ b/tools/include/vdso/const.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_CONST_H
+#define __VDSO_CONST_H
+
+#include <uapi/linux/const.h>
+
+#define UL(x)		(_UL(x))
+#define ULL(x)		(_ULL(x))
+
+#endif /* __VDSO_CONST_H */
diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h
new file mode 100644
index 000000000..9076483c9
--- /dev/null
+++ b/tools/include/vdso/unaligned.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_UNALIGNED_H
+#define __VDSO_UNALIGNED_H
+
+#include <linux/compiler_types.h>
+
+/**
+ * __get_unaligned_t - read an unaligned value from memory.
+ * @type:	the type to load from the pointer.
+ * @ptr:	the pointer to load from.
+ *
+ * Use memcpy to affect an unaligned type sized load avoiding undefined behavior
+ * from approaches like type punning that require -fno-strict-aliasing in order
+ * to be correct. As type may be const, use __unqual_scalar_typeof to map to a
+ * non-const type - you can't memcpy into a const type. The
+ * __get_unaligned_ctrl_type gives __unqual_scalar_typeof its required
+ * expression rather than type, a pointer is used to avoid warnings about mixing
+ * the use of 0 and NULL. The void* cast silences ubsan warnings.
+ */
+#define __get_unaligned_t(type, ptr) ({					\
+	type *__get_unaligned_ctrl_type __always_unused = NULL;		\
+	__unqual_scalar_typeof(*__get_unaligned_ctrl_type) __get_unaligned_val; \
+	__builtin_memcpy(&__get_unaligned_val, (void *)(ptr),		\
+			 sizeof(__get_unaligned_val));			\
+	__get_unaligned_val;						\
+})
+
+/**
+ * __put_unaligned_t - write an unaligned value to memory.
+ * @type:	the type of the value to store.
+ * @val:	the value to store.
+ * @ptr:	the pointer to store to.
+ *
+ * Use memcpy to affect an unaligned type sized store avoiding undefined
+ * behavior from approaches like type punning that require -fno-strict-aliasing
+ * in order to be correct. The void* cast silences ubsan warnings.
+ */
+#define __put_unaligned_t(type, val, ptr) do {				\
+	type __put_unaligned_val = (val);				\
+	__builtin_memcpy((void *)(ptr), &__put_unaligned_val,		\
+			 sizeof(__put_unaligned_val));			\
+} while (0)
+
+#endif /* __VDSO_UNALIGNED_H */