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, 180 insertions, 0 deletions

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
new file mode 100644
index 000000000..79b42f2bf
--- /dev/null
+++ b/fs/proc/stat.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpumask.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/sched/stat.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/time_namespace.h>
+#include <linux/irqnr.h>
+#include <linux/sched/cputime.h>
+#include <linux/tick.h>
+
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+
+static void show_irq_gap(struct seq_file *p, unsigned int gap)
+{
+	static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0";
+
+	while (gap > 0) {
+		unsigned int inc;
+
+		inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2);
+		seq_write(p, zeros, 2 * inc);
+		gap -= inc;
+	}
+}
+
+static void show_all_irqs(struct seq_file *p)
+{
+	unsigned int i, next = 0;
+
+	for_each_active_irq(i) {
+		show_irq_gap(p, i - next);
+		seq_put_decimal_ull(p, " ", kstat_irqs_usr(i));
+		next = i + 1;
+	}
+	show_irq_gap(p, irq_get_nr_irqs() - next);
+}
+
+static int show_stat(struct seq_file *p, void *v)
+{
+	int i, j;
+	u64 user, nice, system, idle, iowait, irq, softirq, steal;
+	u64 guest, guest_nice;
+	u64 sum = 0;
+	u64 sum_softirq = 0;
+	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
+	struct timespec64 boottime;
+
+	user = nice = system = idle = iowait =
+		irq = softirq = steal = 0;
+	guest = guest_nice = 0;
+	getboottime64(&boottime);
+	/* shift boot timestamp according to the timens offset */
+	timens_sub_boottime(&boottime);
+
+	for_each_possible_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user		+= cpustat[CPUTIME_USER];
+		nice		+= cpustat[CPUTIME_NICE];
+		system		+= cpustat[CPUTIME_SYSTEM];
+		idle		+= cpustat[CPUTIME_IDLE];
+		iowait		+= cpustat[CPUTIME_IOWAIT];
+		irq		+= cpustat[CPUTIME_IRQ];
+		softirq		+= cpustat[CPUTIME_SOFTIRQ];
+		steal		+= cpustat[CPUTIME_STEAL];
+		guest		+= cpustat[CPUTIME_GUEST];
+		guest_nice	+= cpustat[CPUTIME_GUEST_NICE];
+		sum		+= kstat_cpu_irqs_sum(i);
+		sum		+= arch_irq_stat_cpu(i);
+
+		for (j = 0; j < NR_SOFTIRQS; j++) {
+			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
+
+			per_softirq_sums[j] += softirq_stat;
+			sum_softirq += softirq_stat;
+		}
+	}
+
+	seq_put_decimal_ull(p, "cpu  ", nsec_to_clock_t(user));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+	seq_putc(p, '\n');
+
+	for_each_online_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
+		user		= cpustat[CPUTIME_USER];
+		nice		= cpustat[CPUTIME_NICE];
+		system		= cpustat[CPUTIME_SYSTEM];
+		idle		= cpustat[CPUTIME_IDLE];
+		iowait		= cpustat[CPUTIME_IOWAIT];
+		irq		= cpustat[CPUTIME_IRQ];
+		softirq		= cpustat[CPUTIME_SOFTIRQ];
+		steal		= cpustat[CPUTIME_STEAL];
+		guest		= cpustat[CPUTIME_GUEST];
+		guest_nice	= cpustat[CPUTIME_GUEST_NICE];
+		seq_printf(p, "cpu%d", i);
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+		seq_putc(p, '\n');
+	}
+	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
+
+	show_all_irqs(p);
+
+	seq_printf(p,
+		"\nctxt %llu\n"
+		"btime %llu\n"
+		"processes %lu\n"
+		"procs_running %u\n"
+		"procs_blocked %u\n",
+		nr_context_switches(),
+		(unsigned long long)boottime.tv_sec,
+		total_forks,
+		nr_running(),
+		nr_iowait());
+
+	seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
+
+	for (i = 0; i < NR_SOFTIRQS; i++)
+		seq_put_decimal_ull(p, " ", per_softirq_sums[i]);
+	seq_putc(p, '\n');
+
+	return 0;
+}
+
+static int stat_open(struct inode *inode, struct file *file)
+{
+	unsigned int size = 1024 + 128 * num_online_cpus();
+
+	/* minimum size to display an interrupt count : 2 bytes */
+	size += 2 * irq_get_nr_irqs();
+	return single_open_size(file, show_stat, NULL, size);
+}
+
+static const struct proc_ops stat_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_open	= stat_open,
+	.proc_read_iter	= seq_read_iter,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+};
+
+static int __init proc_stat_init(void)
+{
+	proc_create("stat", 0, NULL, &stat_proc_ops);
+	return 0;
+}
+fs_initcall(proc_stat_init);