On Mon, May 06, 2024 at 05:29:32AM +0000, Mingwei Zhang wrote:
> @@ -5791,6 +5801,100 @@ void perf_put_mediated_pmu(void)
> }
> EXPORT_SYMBOL_GPL(perf_put_mediated_pmu);
>
> +static void perf_sched_out_exclude_guest(struct perf_event_context *ctx)
> +{
> + struct perf_event_pmu_context *pmu_ctx;
> +
> + update_context_time(ctx);
> + list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
> + struct perf_event *event, *tmp;
> + struct pmu *pmu = pmu_ctx->pmu;
> +
> + if (!(pmu->capabilities & PERF_PMU_CAP_PASSTHROUGH_VPMU))
> + continue;
> +
> + perf_pmu_disable(pmu);
> +
> + /*
> + * All active events must be exclude_guest events.
> + * See perf_get_mediated_pmu().
> + * Unconditionally remove all active events.
> + */
> + list_for_each_entry_safe(event, tmp, &pmu_ctx->pinned_active, active_list)
> + group_sched_out(event, pmu_ctx->ctx);
> +
> + list_for_each_entry_safe(event, tmp, &pmu_ctx->flexible_active, active_list)
> + group_sched_out(event, pmu_ctx->ctx);
> +
> + pmu_ctx->rotate_necessary = 0;
> +
> + perf_pmu_enable(pmu);
> + }
> +}
> +
> +/* When entering a guest, schedule out all exclude_guest events. */
> +void perf_guest_enter(void)
> +{
> + struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
> +
> + lockdep_assert_irqs_disabled();
> +
> + perf_ctx_lock(cpuctx, cpuctx->task_ctx);
> +
> + if (WARN_ON_ONCE(__this_cpu_read(perf_in_guest))) {
> + perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
> + return;
> + }
> +
> + perf_sched_out_exclude_guest(&cpuctx->ctx);
> + if (cpuctx->task_ctx)
> + perf_sched_out_exclude_guest(cpuctx->task_ctx);
> +
> + __this_cpu_write(perf_in_guest, true);
> +
> + perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
> +}
> +
> +static void perf_sched_in_exclude_guest(struct perf_event_context *ctx)
> +{
> + struct perf_event_pmu_context *pmu_ctx;
> +
> + update_context_time(ctx);
> + list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
> + struct pmu *pmu = pmu_ctx->pmu;
> +
> + if (!(pmu->capabilities & PERF_PMU_CAP_PASSTHROUGH_VPMU))
> + continue;
> +
> + perf_pmu_disable(pmu);
> + pmu_groups_sched_in(ctx, &ctx->pinned_groups, pmu);
> + pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu);
> + perf_pmu_enable(pmu);
> + }
> +}
> +
> +void perf_guest_exit(void)
> +{
> + struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
> +
> + lockdep_assert_irqs_disabled();
> +
> + perf_ctx_lock(cpuctx, cpuctx->task_ctx);
> +
> + if (WARN_ON_ONCE(!__this_cpu_read(perf_in_guest))) {
> + perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
> + return;
> + }
> +
> + __this_cpu_write(perf_in_guest, false);
> +
> + perf_sched_in_exclude_guest(&cpuctx->ctx);
> + if (cpuctx->task_ctx)
> + perf_sched_in_exclude_guest(cpuctx->task_ctx);
> +
> + perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
> +}
Bah, this is a ton of copy-paste from the normal scheduling code with
random changes. Why ?
Why can't this use ctx_sched_{in,out}() ? Surely the whole
CAP_PASSTHROUGHT thing is but a flag away.
