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, 62 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/resource.h b/include/uapi/asm-generic/resource.h
new file mode 100644
index 000000000..f12db7a0d
--- /dev/null
+++ b/include/uapi/asm-generic/resource.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_GENERIC_RESOURCE_H
+#define _UAPI_ASM_GENERIC_RESOURCE_H
+
+/*
+ * Resource limit IDs
+ *
+ * ( Compatibility detail: there are architectures that have
+ *   a different rlimit ID order in the 5-9 range and want
+ *   to keep that order for binary compatibility. The reasons
+ *   are historic and all new rlimits are identical across all
+ *   arches. If an arch has such special order for some rlimits
+ *   then it defines them prior including asm-generic/resource.h. )
+ */
+
+#define RLIMIT_CPU		0	/* CPU time in sec */
+#define RLIMIT_FSIZE		1	/* Maximum filesize */
+#define RLIMIT_DATA		2	/* max data size */
+#define RLIMIT_STACK		3	/* max stack size */
+#define RLIMIT_CORE		4	/* max core file size */
+
+#ifndef RLIMIT_RSS
+# define RLIMIT_RSS		5	/* max resident set size */
+#endif
+
+#ifndef RLIMIT_NPROC
+# define RLIMIT_NPROC		6	/* max number of processes */
+#endif
+
+#ifndef RLIMIT_NOFILE
+# define RLIMIT_NOFILE		7	/* max number of open files */
+#endif
+
+#ifndef RLIMIT_MEMLOCK
+# define RLIMIT_MEMLOCK		8	/* max locked-in-memory address space */
+#endif
+
+#ifndef RLIMIT_AS
+# define RLIMIT_AS		9	/* address space limit */
+#endif
+
+#define RLIMIT_LOCKS		10	/* maximum file locks held */
+#define RLIMIT_SIGPENDING	11	/* max number of pending signals */
+#define RLIMIT_MSGQUEUE		12	/* maximum bytes in POSIX mqueues */
+#define RLIMIT_NICE		13	/* max nice prio allowed to raise to
+					   0-39 for nice level 19 .. -20 */
+#define RLIMIT_RTPRIO		14	/* maximum realtime priority */
+#define RLIMIT_RTTIME		15	/* timeout for RT tasks in us */
+#define RLIM_NLIMITS		16
+
+/*
+ * SuS says limits have to be unsigned.
+ * Which makes a ton more sense anyway.
+ *
+ * Some architectures override this (for compatibility reasons):
+ */
+#ifndef RLIM_INFINITY
+# define RLIM_INFINITY		(~0UL)
+#endif
+
+
+#endif /* _UAPI_ASM_GENERIC_RESOURCE_H */