tools/sched_ext: scx_qmap: Restart on hotplug instead of cpu_online/offline

The cid mapping is built from the online cpu set at scheduler enable
and stays valid for that set; routine hotplug invalidates it. The
default cid behavior is to restart the scheduler so the mapping gets
rebuilt against the new online set, and that requires not implementing
cpu_online / cpu_offline (which suppress the kernel's ACT_RESTART).

Drop the two ops along with their print_cpus() helper - the cluster
view was only useful as a hotplug demo and is meaningless over the
dense cid space the scheduler will move to. Wire main() to handle the
ACT_RESTART exit by reopening the skel and reattaching, matching the
pattern in scx_simple / scx_central / scx_flatcg etc. Reset optind so
getopt re-parses argv into the fresh skel rodata each iteration.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Reviewed-by: Changwoo Min <changwoo@igalia.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index ba4879031dac88cd1380e9d92c67544c52eaf47e..78a1dd118c7ecd2ba9200aea885108379fd3ec88 100644 (file)
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -843,63 +843,6 @@ void BPF_STRUCT_OPS(qmap_cgroup_set_bandwidth, struct cgroup *cgrp,
                           cgrp->kn->id, period_us, quota_us, burst_us);
 }
 
-/*
- * Print out the online and possible CPU map using bpf_printk() as a
- * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
- */
-static void print_cpus(void)
-{
-       const struct cpumask *possible, *online;
-       s32 cpu;
-       char buf[128] = "", *p;
-       int idx;
-
-       possible = scx_bpf_get_possible_cpumask();
-       online = scx_bpf_get_online_cpumask();
-
-       idx = 0;
-       bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) {
-               if (!(p = MEMBER_VPTR(buf, [idx++])))
-                       break;
-               if (bpf_cpumask_test_cpu(cpu, online))
-                       *p++ = 'O';
-               else if (bpf_cpumask_test_cpu(cpu, possible))
-                       *p++ = 'X';
-               else
-                       *p++ = ' ';
-
-               if ((cpu & 7) == 7) {
-                       if (!(p = MEMBER_VPTR(buf, [idx++])))
-                               break;
-                       *p++ = '|';
-               }
-       }
-       buf[sizeof(buf) - 1] = '\0';
-
-       scx_bpf_put_cpumask(online);
-       scx_bpf_put_cpumask(possible);
-
-       bpf_printk("CPUS: |%s", buf);
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu)
-{
-       if (print_msgs) {
-               bpf_printk("CPU %d coming online", cpu);
-               /* @cpu is already online at this point */
-               print_cpus();
-       }
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu)
-{
-       if (print_msgs) {
-               bpf_printk("CPU %d going offline", cpu);
-               /* @cpu is still online at this point */
-               print_cpus();
-       }
-}
-
 struct monitor_timer {
        struct bpf_timer timer;
 };
@@ -1078,9 +1021,6 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
                slab[i].next_free = (i + 1 < max_tasks) ? &slab[i + 1] : NULL;
        qa.task_free_head = &slab[0];
 
-       if (print_msgs && !sub_cgroup_id)
-               print_cpus();
-
        ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
        if (ret) {
                scx_bpf_error("failed to create DSQ %d (%d)", SHARED_DSQ, ret);
@@ -1174,8 +1114,6 @@ SCX_OPS_DEFINE(qmap_ops,
               .cgroup_set_bandwidth    = (void *)qmap_cgroup_set_bandwidth,
               .sub_attach              = (void *)qmap_sub_attach,
               .sub_detach              = (void *)qmap_sub_detach,
-              .cpu_online              = (void *)qmap_cpu_online,
-              .cpu_offline             = (void *)qmap_cpu_offline,
               .init                    = (void *)qmap_init,
               .exit                    = (void *)qmap_exit,
               .timeout_ms              = 5000U,

diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 725c4880058dead6e9ad8db2f7d500eadd3180fb..99408b1bb1ec1a636d68e8eaf1d3fa1b0732e087 100644 (file)
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -67,12 +67,14 @@ int main(int argc, char **argv)
        struct bpf_link *link;
        struct qmap_arena *qa;
        __u32 test_error_cnt = 0;
+       __u64 ecode;
        int opt;
 
        libbpf_set_print(libbpf_print_fn);
        signal(SIGINT, sigint_handler);
        signal(SIGTERM, sigint_handler);
-
+restart:
+       optind = 1;
        skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
        skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
@@ -184,11 +186,10 @@ int main(int argc, char **argv)
        }
 
        bpf_link__destroy(link);
-       UEI_REPORT(skel, uei);
+       ecode = UEI_REPORT(skel, uei);
        scx_qmap__destroy(skel);
-       /*
-        * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart
-        * on CPU hotplug events.
-        */
+
+       if (UEI_ECODE_RESTART(ecode))
+               goto restart;
        return 0;
 }