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? [..] > 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? 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 */ > +}