diff options
author | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2013-06-21 15:34:33 -0400 |
---|---|---|
committer | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2013-08-18 21:58:31 -0400 |
commit | 2333210b26cf7aaf48d71343029afb860103d9f9 (patch) | |
tree | d3395575543b67a7ca6a91158d65c3ee760500bf /kernel/rcutree.c | |
parent | b44379af1cf40050794832c38ea6a64e07eb5087 (diff) |
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 <paulmck@linux.vnet.ibm.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Diffstat (limited to 'kernel/rcutree.c')
-rw-r--r-- | kernel/rcutree.c | 5 |
1 files changed, 5 insertions, 0 deletions
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); | |||
224 | DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { | 224 | DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { |
225 | .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, | 225 | .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, |
226 | .dynticks = ATOMIC_INIT(1), | 226 | .dynticks = ATOMIC_INIT(1), |
227 | #ifdef CONFIG_NO_HZ_FULL_SYSIDLE | ||
228 | .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, | ||
229 | .dynticks_idle = ATOMIC_INIT(1), | ||
230 | #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ | ||
227 | }; | 231 | }; |
228 | 232 | ||
229 | static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ | 233 | 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) | |||
2904 | rdp->blimit = blimit; | 2908 | rdp->blimit = blimit; |
2905 | init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ | 2909 | init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ |
2906 | rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; | 2910 | rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; |
2911 | rcu_sysidle_init_percpu_data(rdp->dynticks); | ||
2907 | atomic_set(&rdp->dynticks->dynticks, | 2912 | atomic_set(&rdp->dynticks->dynticks, |
2908 | (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); | 2913 | (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); |
2909 | raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ | 2914 | raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ |