| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 25 Mar 2019 08:08:00 -0700
From: "Paul E. McKenney" <paulmck@...ux.ibm.com>
To: Joel Fernandes <joel@...lfernandes.org>
Cc: Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
linux-kernel@...r.kernel.org,
Josh Triplett <josh@...htriplett.org>,
Steven Rostedt <rostedt@...dmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Lai Jiangshan <jiangshanlai@...il.com>, tglx@...utronix.de,
Mike Galbraith <efault@....de>
Subject: Re: [PATCH v3] rcu: Allow to eliminate softirq processing from
rcutree
On Mon, Mar 25, 2019 at 09:41:29AM -0400, Joel Fernandes wrote:
> On Sun, Mar 24, 2019 at 04:42:11PM -0700, Paul E. McKenney wrote:
> > On Sat, Mar 23, 2019 at 09:10:02AM -0700, Paul E. McKenney wrote:
> > > On Fri, Mar 22, 2019 at 05:25:19PM -0700, Paul E. McKenney wrote:
> > > > On Fri, Mar 22, 2019 at 07:48:19PM -0400, Joel Fernandes wrote:
> > > > > On Wed, Mar 20, 2019 at 10:13:33PM +0100, Sebastian Andrzej Siewior wrote:
> > > > > > Running RCU out of softirq is a problem for some workloads that would
> > > > > > like to manage RCU core processing independently of other softirq
> > > > > > work, for example, setting kthread priority. This commit therefore
> > > > > > introduces the `rcunosoftirq' option which moves the RCU core work
> > > > > > from softirq to a per-CPU/per-flavor SCHED_OTHER kthread named rcuc.
> > > > > > The SCHED_OTHER approach avoids the scalability problems that appeared
> > > > > > with the earlier attempt to move RCU core processing to from softirq
> > > > > > to kthreads. That said, kernels built with RCU_BOOST=y will run the
> > > > > > rcuc kthreads at the RCU-boosting priority.
> > > > > [snip]
> > > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > > > > index 0f31b79eb6761..05a1e42fdaf10 100644
> > > > > > --- a/kernel/rcu/tree.c
> > > > > > +++ b/kernel/rcu/tree.c
> > > > > > @@ -51,6 +51,12 @@
> > > > > > #include <linux/tick.h>
> > > > > > #include <linux/sysrq.h>
> > > > > > #include <linux/kprobes.h>
> > > > > > +#include <linux/gfp.h>
> > > > > > +#include <linux/oom.h>
> > > > > > +#include <linux/smpboot.h>
> > > > > > +#include <linux/jiffies.h>
> > > > > > +#include <linux/sched/isolation.h>
> > > > > > +#include "../time/tick-internal.h"
> > > > > >
> > > > > > #include "tree.h"
> > > > > > #include "rcu.h"
> > > > > > @@ -92,6 +98,9 @@ struct rcu_state rcu_state = {
> > > > > > /* Dump rcu_node combining tree at boot to verify correct setup. */
> > > > > > static bool dump_tree;
> > > > > > module_param(dump_tree, bool, 0444);
> > > > > > +/* Move RCU_SOFTIRQ to rcuc kthreads. */
> > > > > > +static bool use_softirq = 1;
> > > > > > +module_param(use_softirq, bool, 0444);
> > > > > > /* Control rcu_node-tree auto-balancing at boot time. */
> > > > > > static bool rcu_fanout_exact;
> > > > > > module_param(rcu_fanout_exact, bool, 0444);
> > > > > > @@ -2253,7 +2262,7 @@ void rcu_force_quiescent_state(void)
> > > > > > EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
> > > > > >
> > > > > > /* Perform RCU core processing work for the current CPU. */
> > > > > > -static __latent_entropy void rcu_core(struct softirq_action *unused)
> > > > > > +static __latent_entropy void rcu_core(void)
> > > > > > {
> > > > > > unsigned long flags;
> > > > > > struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
> > > > > > @@ -2295,6 +2304,34 @@ static __latent_entropy void rcu_core(struct softirq_action *unused)
> > > > > > trace_rcu_utilization(TPS("End RCU core"));
> > > > > > }
> > > > > >
> > > > > > +static void rcu_core_si(struct softirq_action *h)
> > > > > > +{
> > > > > > + rcu_core();
> > > > > > +}
> > > > > > +
> > > > > > +static void rcu_wake_cond(struct task_struct *t, int status)
> > > > > > +{
> > > > > > + /*
> > > > > > + * If the thread is yielding, only wake it when this
> > > > > > + * is invoked from idle
> > > > > > + */
> > > > > > + if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
> > > > > > + wake_up_process(t);
> > > > > > +}
> > > > > > +
> > > > > > +static void invoke_rcu_core_kthread(void)
> > > > > > +{
> > > > > > + struct task_struct *t;
> > > > > > + unsigned long flags;
> > > > > > +
> > > > > > + local_irq_save(flags);
> > > > > > + __this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
> > > > > > + t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task);
> > > > > > + if (t != NULL && t != current)
> > > > > > + rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
> > > > > > + local_irq_restore(flags);
> > > > > > +}
> > > > > > +
> > > > > > /*
> > > > > > * Schedule RCU callback invocation. If the running implementation of RCU
> > > > > > * does not support RCU priority boosting, just do a direct call, otherwise
> > > > > > @@ -2306,19 +2343,95 @@ static void invoke_rcu_callbacks(struct rcu_data *rdp)
> > > > > > {
> > > > > > if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
> > > > > > return;
> > > > > > - if (likely(!rcu_state.boost)) {
> > > > > > - rcu_do_batch(rdp);
> > > > > > - return;
> > > > > > - }
> > > > > > - invoke_rcu_callbacks_kthread();
> > > > > > + if (rcu_state.boost || !use_softirq)
> > > > > > + invoke_rcu_core_kthread();
> > > > > > + rcu_do_batch(rdp);
> > > > >
> > > > > Shouldn't there be an else before the rcu_do_batch? If we are waking up the
> > > > > rcuc thread, then that will do the rcu_do_batch when it runs right?
> > > > >
> > > > > Something like:
> > > > > if (rcu_state.boost || !use_softirq)
> > > > > invoke_rcu_core_kthread();
> > > > > else
> > > > > rcu_do_batch(rdp);
> > > > >
> > > > > Previous code similarly had a return; also.
> > > >
> > > > I believe that you are correct, so I will give it a shot. Good eyes!
> > >
> > > Yet rcutorture disagrees. Actually, if we are using rcuc kthreads, this
> > > is only ever invoked from within tha thread, so the only check we need is
> > > for the scheduler being operational. I am therefore trying this one out.
> > >
> > > Thoughts?
> >
> > And rcutorture likes this one, though at this point this function should
> > be pulled into its sole callsite. ;-)
>
> Great, I'm glad the testing is going well.
Which reminds me... I have been assuming that Frederic Weisbecker's
split-softirq patches were stalled for the time being.
http://lkml.kernel.org/r/20190228171242.32144-1-frederic@kernel.org
If those were to show up soonish, perhaps that would allow per-softirq
control of priority.
My thought is not to wait, but I figured I should mention it.
> By the way I enlightened that jitter.sh script about CPU offline issues as
> well (sent patch last week). Let me know if you agree with it.
I just sent a reply. Still trying to remember why I excluded CPU 0. ;-)
Perhaps because of issues with single-CPU rcutorture runs?
Thanx, Paul
Powered by blists - more mailing lists