On Fri, May 03, 2013 at 10:52:36AM +0300, Julian Anastasov wrote: > > Hello, > > On Thu, 2 May 2013, Paul E. McKenney wrote: > > > mainline, and missed the one that you added. Revisiting that, a > > question: > > > > > +#ifdef CONFIG_PREEMPT_RCU > > > +#define PREEMPT_RCU_OFFSET 1 > > > > Does this really want to be "1" instead of PREEMPT_OFFSET? > > In this case when CONFIG_PREEMPT_RCU is enabled > we (RCU) do not touch the preempt counters. Instead, the units > are accounted in current->rcu_read_lock_nesting: > > #define rcu_preempt_depth() (current->rcu_read_lock_nesting) > > __rcu_read_lock: > current->rcu_read_lock_nesting++; > > and the path is __might_sleep -> preempt_count_equals -> > rcu_preempt_depth > > For now both places do not use PREEMPT_OFFSET: > > - #define inc_preempt_count() add_preempt_count(1) > - __rcu_read_lock: current->rcu_read_lock_nesting++; > > so, ... it does not matter much for me. In short, > the trick is in preempt_count_equals() where preempt_offset > is a combination of preempt count and RCU preempt depth: > > #ifdef CONFIG_PREEMPT_RCU > #define PREEMPT_RCU_OFFSET (0 /* preempt */ + 1 /* RCU */) > #else > #define PREEMPT_RCU_OFFSET (PREEMPT_CHECK_OFFSET + 0 /* RCU */) > #endif > > Let me know for your preference about this definition... OK, after getting some sleep, I might have located the root cause of my confusion yesterday. The key point is that I don't understand why we cannot get the effect we are looking for with the following in sched.h (or wherever): static inline int cond_resched_rcu(void) { #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) rcu_read_unlock(); cond_resched(); rcu_read_lock(); #endif } This adds absolutely no overhead in non-debug builds of CONFIG_PREEMPT_RCU, does the checking in debug builds, and allows voluntary preemption in !CONFIG_PREEMPT_RCU builds. CONFIG_PROVE_RCU builds will check for an (illegal) outer rcu_read_lock() in CONFIG_PREEMPT_RCU builds, and you will get "scheduling while atomic" in response to an outer rcu_read_lock() in !CONFIG_PREEMPT_RCU builds. It also seems to me a lot simpler. Does this work, or am I still missing something? Thanx, Paul -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html