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, 92 insertions, 0 deletions

diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
new file mode 100644
index 000000000..6b737e195
--- /dev/null
+++ b/tools/perf/util/debug.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* For debugging general purposes */
+#ifndef __PERF_DEBUG_H
+#define __PERF_DEBUG_H
+
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <linux/compiler.h>
+
+extern int verbose;
+extern int debug_kmaps;
+extern int debug_peo_args;
+extern bool quiet, dump_trace;
+extern int debug_ordered_events;
+extern int debug_data_convert;
+extern int debug_type_profile;
+
+#ifndef pr_fmt
+#define pr_fmt(fmt) fmt
+#endif
+
+#define pr_err(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning_once(fmt, ...) ({		\
+	static int __warned;			\
+	if (unlikely(!__warned)) {		\
+		pr_warning(fmt, ##__VA_ARGS__); \
+		__warned = 1;			\
+	}					\
+})
+#define pr_info(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug(fmt, ...) \
+	eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debugN(n, fmt, ...) \
+	eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+
+/* Special macro to print perf_event_open arguments/return value. */
+#define pr_debug2_peo(fmt, ...) {				\
+	if (debug_peo_args)						\
+		pr_debugN(0, pr_fmt(fmt), ##__VA_ARGS__);	\
+	else							\
+		pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__);	\
+}
+
+#define pr_time_N(n, var, t, fmt, ...) \
+	eprintf_time(n, var, t, fmt, ##__VA_ARGS__)
+
+#define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
+
+union perf_event;
+
+int dump_printf(const char *fmt, ...) __printf(1, 2);
+void trace_event(union perf_event *event);
+
+int ui__error(const char *format, ...) __printf(1, 2);
+int ui__warning(const char *format, ...) __printf(1, 2);
+#define ui__warning_once(format, ...) ({		\
+	static int __warned;				\
+	if (unlikely(!__warned)) {			\
+		ui__warning(format, ##__VA_ARGS__);	\
+		__warned = 1;				\
+	}						\
+})
+
+void pr_stat(const char *fmt, ...);
+
+int eprintf(int level, int var, const char *fmt, ...) __printf(3, 4);
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5);
+int veprintf(int level, int var, const char *fmt, va_list args);
+
+int perf_debug_option(const char *str);
+FILE *debug_file(void);
+void debug_set_file(FILE *file);
+void debug_set_display_time(bool set);
+void perf_debug_setup(void);
+int perf_quiet_option(void);
+
+void __dump_stack(FILE *file, void **stackdump, size_t stackdump_size);
+void dump_stack(void);
+void sighandler_dump_stack(int sig);
+
+#endif	/* __PERF_DEBUG_H */