On Tue, Feb 01, 2022 at 02:25:38PM -0500, Mathieu Desnoyers wrote:
> +static inline void tg_vcpu_get(struct task_struct *t)
> +{
> + struct cpumask *cpumask = &t->signal->vcpu_mask;
> + unsigned int vcpu;
> +
> + if (t->flags & PF_KTHREAD)
> + return;
> + /* Atomically reserve lowest available vcpu number. */
> + do {
> + vcpu = cpumask_first_zero(cpumask);
> + WARN_ON_ONCE(vcpu >= nr_cpu_ids);
> + } while (cpumask_test_and_set_cpu(vcpu, cpumask));
> + t->tg_vcpu = vcpu;
> +}
> +
> +static inline void tg_vcpu_put(struct task_struct *t)
> +{
> + if (t->flags & PF_KTHREAD)
> + return;
> + cpumask_clear_cpu(t->tg_vcpu, &t->signal->vcpu_mask);
> + t->tg_vcpu = 0;
> +}
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 2e4ae00e52d1..2690e80977b1 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -4795,6 +4795,8 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
> sched_info_switch(rq, prev, next);
> perf_event_task_sched_out(prev, next);
> rseq_preempt(prev);
> + tg_vcpu_put(prev);
> + tg_vcpu_get(next);
URGGHHH!!! that's *2* atomics extra on the context switch path. Worse,
that's on a line that's trivially contended with a few threads.
