Messages in this thread | | | Date | Tue, 25 Oct 2016 10:39:46 -0700 | From | "Paul E. McKenney" <> | Subject | Re: Untested patch to recheck idle state for expedited grace periods |
| |
On Tue, Oct 11, 2016 at 09:15:40AM -0700, Paul E. McKenney wrote: > On Tue, Oct 11, 2016 at 06:28:49AM -0700, Paul E. McKenney wrote: > > Hello, Rik, > > > > And it turns out that I did not in fact do the recheck at IPI time. > > The (untested) patch below is an alleged fix. Thoughts? > > And it passes modest rcutorture testing, for whatever that might be > worth.
How does it do at your end? If I don't hear otherwise, I will assume that it doesn't help and will mothball it.
Thanx, Paul
> > ------------------------------------------------------------------------ > > > > commit e53e0b3e7b3c783962f9461bcb9aa8bc3e3a8688 > > Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > Date: Tue Oct 11 06:09:59 2016 -0700 > > > > rcu: Make expedited grace periods recheck dyntick idle state > > > > Expedited grace periods check dyntick-idle state, and avoid sending > > IPIs to idle CPUs, including those running guest OSes, and, on NOHZ_FULL > > kernels, nohz_full CPUs. However, the kernel has been observed checking > > a CPU while it was non-idle, but sending the IPI after it has gone > > idle. This commit therefore rechecks idle state immediately before > > sending the IPI, refraining from IPIing CPUs that have since gone idle. > > > > Reported-by: Rik van Riel <riel@redhat.com> > > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > > > diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h > > index e99a5234d9ed..fe98dd24adf8 100644 > > --- a/kernel/rcu/tree.h > > +++ b/kernel/rcu/tree.h > > @@ -404,6 +404,7 @@ struct rcu_data { > > atomic_long_t exp_workdone1; /* # done by others #1. */ > > atomic_long_t exp_workdone2; /* # done by others #2. */ > > atomic_long_t exp_workdone3; /* # done by others #3. */ > > + int exp_dynticks_snap; /* Double-check need for IPI. */ > > > > /* 7) Callback offloading. */ > > #ifdef CONFIG_RCU_NOCB_CPU > > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h > > index 24343eb87b58..d3053e99fdb6 100644 > > --- a/kernel/rcu/tree_exp.h > > +++ b/kernel/rcu/tree_exp.h > > @@ -358,8 +358,10 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, > > struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); > > struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); > > > > + rdp->exp_dynticks_snap = > > + atomic_add_return(0, &rdtp->dynticks); > > if (raw_smp_processor_id() == cpu || > > - !(atomic_add_return(0, &rdtp->dynticks) & 0x1) || > > + !(rdp->exp_dynticks_snap & 0x1) || > > !(rnp->qsmaskinitnext & rdp->grpmask)) > > mask_ofl_test |= rdp->grpmask; > > } > > @@ -377,9 +379,17 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, > > /* IPI the remaining CPUs for expedited quiescent state. */ > > for_each_leaf_node_possible_cpu(rnp, cpu) { > > unsigned long mask = leaf_node_cpu_bit(rnp, cpu); > > + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); > > + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); > > + > > if (!(mask_ofl_ipi & mask)) > > continue; > > retry_ipi: > > + if (atomic_add_return(0, &rdtp->dynticks) != > > + rdp->exp_dynticks_snap) { > > + mask_ofl_test |= mask; > > + continue; > > + } > > ret = smp_call_function_single(cpu, func, rsp, 0); > > if (!ret) { > > mask_ofl_ipi &= ~mask;
| |