Re: [PATCH RFC v2 tip/core/rcu 01/22] sched/core: Add function to sample state of locked-down task

From: Paul E. McKenney
Date: Tue Mar 24 2020 - 11:48:25 EST


On Mon, Mar 23, 2020 at 08:06:39PM -0400, Joel Fernandes wrote:
> On Thu, Mar 19, 2020 at 07:49:43PM -0700, Paul E. McKenney wrote:
> [...]
> > Thanx, Paul
> >
> > ------------------------------------------------------------------------
> >
> > commit e26a234c1205bf02b62b62cd7f15f8086fc0b13b
> > Author: Paul E. McKenney <paulmck@xxxxxxxxxx>
> > Date: Thu Mar 19 15:33:12 2020 -0700
> >
> > rcu-tasks: Avoid IPIing userspace/idle tasks if kernel is so built
> >
> > Systems running CPU-bound real-time task do not want IPIs sent to CPUs
> > executing nohz_full userspace tasks. Battery-powered systems don't
> > want IPIs sent to idle CPUs in low-power mode. Unfortunately, RCU tasks
> > trace can and will send such IPIs in some cases.
> >
> > Both of these situations occur only when the target CPU is in RCU
> > dyntick-idle mode, in other words, when RCU is not watching the
> > target CPU. This suggests that CPUs in dyntick-idle mode should use
> > memory barriers in outermost invocations of rcu_read_lock_trace()
> > and rcu_read_unlock_trace(), which would allow the RCU tasks trace
> > grace period to directly read out the target CPU's read-side state.
> > One challenge is that RCU tasks trace is not targeting a specific
> > CPU, but rather a task. And that task could switch from one CPU to
> > another at any time.
> >
> > This commit therefore uses try_invoke_on_locked_down_task()
> > and checks for task_curr() in trc_inspect_reader_notrunning().
> > When this condition holds, the target task is running and cannot move.
> > If CONFIG_TASKS_TRACE_RCU_READ_MB=y, the new rcu_dynticks_zero_in_eqs()
> > function can be used to check if the specified integer (in this case,
> > t->trc_reader_nesting) is zero while the target CPU remains in that same
> > dyntick-idle sojourn. If so, the target task is in a quiescent state.
> > If not, trc_read_check_handler() must indicate failure so that the
> > grace-period kthread can take appropriate action or retry after an
> > appropriate delay, as the case may be.
> >
> > With this change, given CONFIG_TASKS_TRACE_RCU_READ_MB=y, if a given
> > CPU remains idle or a given task continues executing in nohz_full mode,
> > the RCU tasks trace grace-period kthread will detect this without the
> > need to send an IPI.
> >
> > Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> > Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
> >
> > diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
> > index e1089fd..296f926 100644
> > --- a/kernel/rcu/rcu.h
> > +++ b/kernel/rcu/rcu.h
> > @@ -501,6 +501,7 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
> > #endif
> >
> > #ifdef CONFIG_TINY_RCU
> > +static inline bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { return false; }
> > static inline unsigned long rcu_get_gp_seq(void) { return 0; }
> > static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
> > static inline unsigned long
> > @@ -510,6 +511,7 @@ static inline void show_rcu_gp_kthreads(void) { }
> > static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
> > static inline void rcu_fwd_progress_check(unsigned long j) { }
> > #else /* #ifdef CONFIG_TINY_RCU */
> > +bool rcu_dynticks_zero_in_eqs(int cpu, int *vp);
> > unsigned long rcu_get_gp_seq(void);
> > unsigned long rcu_exp_batches_completed(void);
> > unsigned long srcu_batches_completed(struct srcu_struct *sp);
> > diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
> > index d31ed74..36f03d3 100644
> > --- a/kernel/rcu/tasks.h
> > +++ b/kernel/rcu/tasks.h
> > @@ -802,22 +802,38 @@ static void trc_read_check_handler(void *t_in)
> > /* Callback function for scheduler to check non-running) task. */
> > static bool trc_inspect_reader_notrunning(struct task_struct *t, void *arg)
>
> This function name is a bit confusing. The task could be running when this
> function is called. Below you are detecting that the task is running, by
> calling task_curr().
>
> Maybe just trc_inspect_reader() is better?

Sold! ;-)

> [..]
>
> > diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
> > index 44edd0a..43991a4 100644
> > --- a/kernel/rcu/tree.h
> > +++ b/kernel/rcu/tree.h
> > @@ -455,6 +455,8 @@ static void rcu_bind_gp_kthread(void);
> > static bool rcu_nohz_full_cpu(void);
> > static void rcu_dynticks_task_enter(void);
> > static void rcu_dynticks_task_exit(void);
> > +static void rcu_dynticks_task_trace_enter(void);
> > +static void rcu_dynticks_task_trace_exit(void);
> >
> > /* Forward declarations for tree_stall.h */
> > static void record_gp_stall_check_time(void);
> > diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> > index 9355536..f4a344e 100644
> > --- a/kernel/rcu/tree_plugin.h
> > +++ b/kernel/rcu/tree_plugin.h
> > @@ -2553,3 +2553,21 @@ static void rcu_dynticks_task_exit(void)
> > WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
> > #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
> > }
> > +
> > +/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
> > +static void rcu_dynticks_task_trace_enter(void)
> > +{
> > +#ifdef CONFIG_TASKS_RCU_TRACE
> > + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
> > + current->trc_reader_special.b.need_mb = true;
>
> If this is every called from middle of a reader section (that is we
> transition from IPI-mode to using heavier reader-sections), then is a memory
> barrier needed here just to protect the reader section that already started?

That memory barrier is provided by the memory ordering in the callers
of rcu_dynticks_task_trace_enter() and rcu_dynticks_task_trace_exit(),
namely, those callers' atomic_add_return() invocations. These barriers
pair with the pair of smp_rmb() calls in rcu_dynticks_zero_in_eqs(),
which is in turn invoked from the function formerly known as
trc_inspect_reader_notrunning(), AKA trc_inspect_reader().

This same pair of smp_rmb() calls also pair with the conditional smp_mb()
calls in rcu_read_lock_trace() and rcu_read_unlock_trace().

In your scenario, the calls in rcu_read_lock_trace() and
rcu_read_unlock_trace() wouldn't happen, but in that case the ordering
from atomic_add_return() would suffice.

Does that work? Or is there an ordering bug in there somewhere?

Thanx, Paul

> thanks,
>
> - Joel
>
>
> > +#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
> > +}
> > +
> > +/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
> > +static void rcu_dynticks_task_trace_exit(void)
> > +{
> > +#ifdef CONFIG_TASKS_RCU_TRACE
> > + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
> > + current->trc_reader_special.b.need_mb = false;
> > +#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
> > +}