diff options
| author | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2014-03-16 21:36:25 -0700 |
|---|---|---|
| committer | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2014-05-14 09:46:11 -0700 |
| commit | ac1bea85781e9004da9b3e8a4b097c18492d857c (patch) | |
| tree | e28ea65bf56d1624371885954a46ab64cab1524b /kernel/sched | |
| parent | 0e980234c97f98be6619b9281d83777f725b94ff (diff) | |
sched,rcu: Make cond_resched() report RCU quiescent states
Given a CPU running a loop containing cond_resched(), with no
other tasks runnable on that CPU, RCU will eventually report RCU
CPU stall warnings due to lack of quiescent states. Fortunately,
every call to cond_resched() is a perfectly good quiescent state.
Unfortunately, invoking rcu_note_context_switch() is a bit heavyweight
for cond_resched(), especially given the need to disable preemption,
and, for RCU-preempt, interrupts as well.
This commit therefore maintains a per-CPU counter that causes
cond_resched(), cond_resched_lock(), and cond_resched_softirq() to call
rcu_note_context_switch(), but only about once per 256 invocations.
This ratio was chosen in keeping with the relative time constants of
RCU grace periods.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 268a45ea238c..9f530c9ed911 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4051,6 +4051,7 @@ static void __cond_resched(void) int __sched _cond_resched(void) { + rcu_cond_resched(); if (should_resched()) { __cond_resched(); return 1; @@ -4069,15 +4070,18 @@ EXPORT_SYMBOL(_cond_resched); */ int __cond_resched_lock(spinlock_t *lock) { + bool need_rcu_resched = rcu_should_resched(); int resched = should_resched(); int ret = 0; lockdep_assert_held(lock); - if (spin_needbreak(lock) || resched) { + if (spin_needbreak(lock) || resched || need_rcu_resched) { spin_unlock(lock); if (resched) __cond_resched(); + else if (unlikely(need_rcu_resched)) + rcu_resched(); else cpu_relax(); ret = 1; @@ -4091,6 +4095,7 @@ int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); + rcu_cond_resched(); /* BH disabled OK, just recording QSes. */ if (should_resched()) { local_bh_enable(); __cond_resched(); |