From 2333210b26cf7aaf48d71343029afb860103d9f9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jun 2013 12:34:33 -0700 Subject: [PATCH] nohz_full: Add rcu_dyntick data for scalable detection of all-idle state This commit adds fields to the rcu_dyntick structure that are used to detect idle CPUs. These new fields differ from the existing ones in that the existing ones consider a CPU executing in user mode to be idle, where the new ones consider CPUs executing in user mode to be busy. The handling of these new fields is otherwise quite similar to that for the exiting fields. This commit also adds the initialization required for these fields. So, why is usermode execution treated differently, with RCU considering it a quiescent state equivalent to idle, while in contrast the new full-system idle state detection considers usermode execution to be non-idle? It turns out that although one of RCU's quiescent states is usermode execution, it is not a full-system idle state. This is because the purpose of the full-system idle state is not RCU, but rather determining when accurate timekeeping can safely be disabled. Whenever accurate timekeeping is required in a CONFIG_NO_HZ_FULL kernel, at least one CPU must keep the scheduling-clock tick going. If even one CPU is executing in user mode, accurate timekeeping is requires, particularly for architectures where gettimeofday() and friends do not enter the kernel. Only when all CPUs are really and truly idle can accurate timekeeping be disabled, allowing all CPUs to turn off the scheduling clock interrupt, thus greatly improving energy efficiency. This naturally raises the question "Why is this code in RCU rather than in timekeeping?", and the answer is that RCU has the data and infrastructure to efficiently make this determination. Signed-off-by: Paul E. McKenney Acked-by: Frederic Weisbecker Cc: Steven Rostedt Reviewed-by: Josh Triplett --- kernel/rcutree.c | 5 +++++ kernel/rcutree.h | 9 +++++++++ kernel/rcutree_plugin.h | 19 +++++++++++++++++++ 3 files changed, 33 insertions(+) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 8807019138c6..4f27b85d8c86 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -224,6 +224,10 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(1), +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, + .dynticks_idle = ATOMIC_INIT(1), +#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ @@ -2904,6 +2908,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->blimit = blimit; init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; + rcu_sysidle_init_percpu_data(rdp->dynticks); atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ diff --git a/kernel/rcutree.h b/kernel/rcutree.h index cbdeac6cea9e..52d1be108e75 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -88,6 +88,14 @@ struct rcu_dynticks { /* Process level is worth LLONG_MAX/2. */ int dynticks_nmi_nesting; /* Track NMI nesting level. */ atomic_t dynticks; /* Even value for idle, else odd. */ +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + long long dynticks_idle_nesting; + /* irq/process nesting level from idle. */ + atomic_t dynticks_idle; /* Even value for idle, else odd. */ + /* "Idle" excludes userspace execution. */ + unsigned long dynticks_idle_jiffies; + /* End of last non-NMI non-idle period. */ +#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ #ifdef CONFIG_RCU_FAST_NO_HZ bool all_lazy; /* Are all CPU's CBs lazy? */ unsigned long nonlazy_posted; @@ -545,6 +553,7 @@ static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); static void rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); +static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index dff86f53ee09..e5baccbd8038 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -2373,3 +2373,22 @@ static void rcu_kick_nohz_cpu(int cpu) smp_send_reschedule(cpu); #endif /* #ifdef CONFIG_NO_HZ_FULL */ } + + +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + +/* + * Initialize dynticks sysidle state for CPUs coming online. + */ +static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) +{ + rdtp->dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE; +} + +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ -- 2.20.1