On Mon, Aug 12, 2019 at 09:02:49PM -0400, Joel Fernandes wrote: > On Mon, Aug 12, 2019 at 04:01:38PM -0700, Paul E. McKenney wrote: [ . . . ] > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c > > index 8c494a692728..ad906d6a74fb 100644 > > --- a/kernel/rcu/tree.c > > +++ b/kernel/rcu/tree.c > > @@ -651,6 +651,12 @@ 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); > > + } > > > Instead of checking dynticks_nmi_nesting == 2 in rcu_nmi_exit_common(), can > we do the tick_dep_set_cpu(rdp->cpu, TICK_DEP_MASK_RCU) from > rcu_nmi_enter_common() ? We could add this code there, under the "if > (rcu_dynticks_curr_cpu_in_eqs())". This would need to go in an "else" clause, correct? But there would still want to be a check for interrupt from base level (which would admittedly be an equality comparison with zero) and we would also still need to check for rdp->rcu_urgent_qs && !rdp->rcu_forced_tick. Still, an equal-zero comparison is probably going to be a bit cheaper than an equals-two comparison, and this is on the interrupt-entry fastpath, so this change is likely worth making. Good call!!! Thanx, Paul > I will test this patch tomorrow and let you know how it goes. > > thanks, > > - Joel > > > > > > WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */ > > rdp->dynticks_nmi_nesting - 2); > > return; > > @@ -886,6 +892,16 @@ void rcu_irq_enter_irqson(void) > > local_irq_restore(flags); > > } > > > > +/* > > + * If the scheduler-clock interrupt was enabled on a nohz_full CPU > > + * in order to get to a quiescent state, disable it. > > + */ > > +void rcu_disable_tick_upon_qs(struct rcu_data *rdp) > > +{ > > + if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) > > + tick_dep_clear_cpu(rdp->cpu, TICK_DEP_MASK_RCU); > > +} > > + > > /** > > * rcu_is_watching - see if RCU thinks that the current CPU is not idle > > * > > @@ -1980,6 +1996,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) > > if (!offloaded) > > needwake = rcu_accelerate_cbs(rnp, rdp); > > > > + rcu_disable_tick_upon_qs(rdp); > > rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); > > /* ^^^ Released rnp->lock */ > > if (needwake) > > @@ -2269,6 +2286,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) > > int cpu; > > unsigned long flags; > > unsigned long mask; > > + struct rcu_data *rdp; > > struct rcu_node *rnp; > > > > rcu_for_each_leaf_node(rnp) { > > @@ -2293,8 +2311,10 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) > > for_each_leaf_node_possible_cpu(rnp, cpu) { > > unsigned long bit = leaf_node_cpu_bit(rnp, cpu); > > if ((rnp->qsmask & bit) != 0) { > > - if (f(per_cpu_ptr(&rcu_data, cpu))) > > - mask |= bit; > > + rdp = per_cpu_ptr(&rcu_data, cpu); > > + if (f(rdp)) > > + rcu_disable_tick_upon_qs(rdp); > > + mask |= bit; > > } > > } > > if (mask != 0) { > > @@ -2322,7 +2342,7 @@ void rcu_force_quiescent_state(void) > > rnp = __this_cpu_read(rcu_data.mynode); > > for (; rnp != NULL; rnp = rnp->parent) { > > ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) || > > - !raw_spin_trylock(&rnp->fqslock); > > + !raw_spin_trylock(&rnp->fqslock); > > if (rnp_old != NULL) > > raw_spin_unlock(&rnp_old->fqslock); > > if (ret) > > @@ -2855,7 +2875,7 @@ static void rcu_barrier_callback(struct rcu_head *rhp) > > { > > if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) { > > rcu_barrier_trace(TPS("LastCB"), -1, > > - rcu_state.barrier_sequence); > > + rcu_state.barrier_sequence); > > complete(&rcu_state.barrier_completion); > > } else { > > rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence); > > @@ -2879,7 +2899,7 @@ static void rcu_barrier_func(void *unused) > > } else { > > debug_rcu_head_unqueue(&rdp->barrier_head); > > rcu_barrier_trace(TPS("IRQNQ"), -1, > > - rcu_state.barrier_sequence); > > + rcu_state.barrier_sequence); > > } > > rcu_nocb_unlock(rdp); > > } > > @@ -2906,7 +2926,7 @@ void rcu_barrier(void) > > /* Did someone else do our work for us? */ > > if (rcu_seq_done(&rcu_state.barrier_sequence, s)) { > > rcu_barrier_trace(TPS("EarlyExit"), -1, > > - rcu_state.barrier_sequence); > > + rcu_state.barrier_sequence); > > smp_mb(); /* caller's subsequent code after above check. */ > > mutex_unlock(&rcu_state.barrier_mutex); > > return; > > @@ -2938,11 +2958,11 @@ void rcu_barrier(void) > > continue; > > if (rcu_segcblist_n_cbs(&rdp->cblist)) { > > rcu_barrier_trace(TPS("OnlineQ"), cpu, > > - rcu_state.barrier_sequence); > > + rcu_state.barrier_sequence); > > smp_call_function_single(cpu, rcu_barrier_func, NULL, 1); > > } else { > > rcu_barrier_trace(TPS("OnlineNQ"), cpu, > > - rcu_state.barrier_sequence); > > + rcu_state.barrier_sequence); > > } > > } > > put_online_cpus(); > > @@ -3168,6 +3188,7 @@ void rcu_cpu_starting(unsigned int cpu) > > rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq); > > rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags); > > if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ > > + rcu_disable_tick_upon_qs(rdp); > > /* Report QS -after- changing ->qsmaskinitnext! */ > > rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); > > } else { > > diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h > > index c612f306fe89..055c31781d3a 100644 > > --- a/kernel/rcu/tree.h > > +++ b/kernel/rcu/tree.h > > @@ -181,6 +181,7 @@ struct rcu_data { > > atomic_t dynticks; /* Even value for idle, else odd. */ > > bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */ > > bool rcu_urgent_qs; /* GP old need light quiescent state. */ > > + bool rcu_forced_tick; /* Forced tick to provide QS. */ > > #ifdef CONFIG_RCU_FAST_NO_HZ > > bool all_lazy; /* All CPU's CBs lazy at idle start? */ > > unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */