Re: [PATCH tip/core/rcu 08/12] rcu: Force tick on for nohz_full CPUs not reaching quiescent states

[Frederic Weisbecker]

On Wed, Oct 02, 2019 at 06:38:59PM -0700, paulmck@xxxxxxxxxx wrote:
> From: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxx>
> 
> CPUs running for long time periods in the kernel in nohz_full mode
> might leave the scheduling-clock interrupt disabled for then full
> duration of their in-kernel execution.  This can (among other things)
> delay grace periods.  This commit therefore forces the tick back on
> for any nohz_full CPU that is failing to pass through a quiescent state
> upon return from interrupt, which the resched_cpu() will induce.
> 
> Reported-by: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
> [ paulmck: Clear ->rcu_forced_tick as reported by Joel Fernandes testing. ]
> [ paulmck: Apply Joel Fernandes TICK_DEP_MASK_RCU->TICK_DEP_BIT_RCU fix. ]
> Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxx>
> ---
>  kernel/rcu/tree.c | 38 +++++++++++++++++++++++++++++++-------
>  kernel/rcu/tree.h |  1 +
>  2 files changed, 32 insertions(+), 7 deletions(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 74bf5c65..621cc06 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -650,6 +650,12 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
>  	 */
>  	if (rdp->dynticks_nmi_nesting != 1) {
>  		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks);
> +		if (tick_nohz_full_cpu(rdp->cpu) &&
> +		    rdp->dynticks_nmi_nesting == 2 &&
> +		    rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
> +			rdp->rcu_forced_tick = true;
> +			tick_dep_set_cpu(rdp->cpu, TICK_DEP_MASK_RCU);

I understand rdp->cpu is always smp_processor_id() here, right? Because calling
tick_dep_set_cpu() to a remote CPU while in NMI wouldn't be safe. It would warn anyway.