On Wed, Aug 21, 2019 at 06:19:04PM -0500, Scott Wood wrote:
> A plain local_bh_disable() is documented as creating an RCU critical
> section, and (at least) rcutorture expects this to be the case. However,
> in_softirq() doesn't block a grace period on PREEMPT_RT, since RCU checks
> preempt_count() directly. Even if RCU were changed to check
> in_softirq(), that wouldn't allow blocked BH disablers to be boosted.
>
> Fix this by calling rcu_read_lock() from local_bh_disable(), and update
> rcu_read_lock_bh_held() accordingly.
Cool! Some questions and comments below.
Thanx, Paul
> Signed-off-by: Scott Wood <sw...@redhat.com>
> ---
> Another question is whether non-raw spinlocks are intended to create an
> RCU read-side critical section due to implicit preempt disable.
Hmmm... Did non-raw spinlocks act like rcu_read_lock_sched()
and rcu_read_unlock_sched() pairs in -rt prior to the RCU flavor
consolidation? If not, I don't see why they should do so after that
consolidation in -rt.
> If they
> are, then we'd need to add rcu_read_lock() there as well since RT doesn't
> disable preemption (and rcutorture should explicitly test with a
> spinlock). If not, the documentation should make that clear.
True enough!
> include/linux/rcupdate.h | 4 ++++
> kernel/rcu/update.c | 4 ++++
> kernel/softirq.c | 12 +++++++++---
> 3 files changed, 17 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> index 388ace315f32..d6e357378732 100644
> --- a/include/linux/rcupdate.h
> +++ b/include/linux/rcupdate.h
> @@ -615,10 +615,12 @@ static inline void rcu_read_unlock(void)
> static inline void rcu_read_lock_bh(void)
> {
> local_bh_disable();
> +#ifndef CONFIG_PREEMPT_RT_FULL
> __acquire(RCU_BH);
> rcu_lock_acquire(&rcu_bh_lock_map);
> RCU_LOCKDEP_WARN(!rcu_is_watching(),
> "rcu_read_lock_bh() used illegally while idle");
> +#endif
Any chance of this using "if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))"?
We should be OK providing a do-nothing __maybe_unused rcu_bh_lock_map
for lockdep-enabled -rt kernels, right?
> }
>
> /*
> @@ -628,10 +630,12 @@ static inline void rcu_read_lock_bh(void)
> */
> static inline void rcu_read_unlock_bh(void)
> {
> +#ifndef CONFIG_PREEMPT_RT_FULL
> RCU_LOCKDEP_WARN(!rcu_is_watching(),
> "rcu_read_unlock_bh() used illegally while idle");
> rcu_lock_release(&rcu_bh_lock_map);
> __release(RCU_BH);
> +#endif
Ditto.
> local_bh_enable();
> }
>
> diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
> index 016c66a98292..a9cdf3d562bc 100644
> --- a/kernel/rcu/update.c
> +++ b/kernel/rcu/update.c
> @@ -296,7 +296,11 @@ int rcu_read_lock_bh_held(void)
> return 0;
> if (!rcu_lockdep_current_cpu_online())
> return 0;
> +#ifdef CONFIG_PREEMPT_RT_FULL
> + return lock_is_held(&rcu_lock_map) || irqs_disabled();
> +#else
> return in_softirq() || irqs_disabled();
> +#endif
And globally.
> }
> EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
>
> diff --git a/kernel/softirq.c b/kernel/softirq.c
> index d16d080a74f7..6080c9328df1 100644
> --- a/kernel/softirq.c
> +++ b/kernel/softirq.c
> @@ -115,8 +115,10 @@ void __local_bh_disable_ip(unsigned long ip, unsigned
> int cnt)
> long soft_cnt;
>
> WARN_ON_ONCE(in_irq());
> - if (!in_atomic())
> + if (!in_atomic()) {
> local_lock(bh_lock);
> + rcu_read_lock();
> + }
> soft_cnt = this_cpu_inc_return(softirq_counter);
> WARN_ON_ONCE(soft_cnt == 0);
> current->softirq_count += SOFTIRQ_DISABLE_OFFSET;
> @@ -151,8 +153,10 @@ void _local_bh_enable(void)
> #endif
>
> current->softirq_count -= SOFTIRQ_DISABLE_OFFSET;
> - if (!in_atomic())
> + if (!in_atomic()) {
> + rcu_read_unlock();
> local_unlock(bh_lock);
> + }
> }
>
> void _local_bh_enable_rt(void)
> @@ -185,8 +189,10 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int
> cnt)
> WARN_ON_ONCE(count < 0);
> local_irq_enable();
>
> - if (!in_atomic())
> + if (!in_atomic()) {
> + rcu_read_unlock();
> local_unlock(bh_lock);
> + }
The return from in_atomic() is guaranteed to be the same at
local_bh_enable() time as was at the call to the corresponding
local_bh_disable()?
I could have sworn that I ran afoul of this last year. Might these
added rcu_read_lock() and rcu_read_unlock() calls need to check for
CONFIG_PREEMPT_RT_FULL?
> current->softirq_count -= SOFTIRQ_DISABLE_OFFSET;
> preempt_check_resched();
> --
> 1.8.3.1
>
