On 19/08/25 16:02, Juri Lelli wrote: > On 19/08/25 12:34, Gabriele Monaco wrote:
... > > > As per the whole _tp() thing, you can attach to the actual > > > sched_switch tracepoint with a module and read whatever you want. > > > > Yeah I believe Juri referred to model constraints on the already > > existing events rather than new tracepoints here. > > Separately from this series, maybe we should put such a module/bpf thing > somewhere shared, so it's easier to use it when needed. Maybe we could --- diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 383cfc684e8e..994b6973d77d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -117,6 +117,10 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_throttle_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_replenish_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_server_start_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_server_stop_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); --- so that the new tps can be used from modules like sched_tp Phil mentioned? Thanks, Juri
