Skip to contentSkip to conversation

Did you still need asynchronous grace-period detection?

PATCH Paul E. McKenney 2 participants 3 messages May 2, 2014 – May 5, 2014 RCU

lore
Share & tools
lore
#0 lore raw

Hello, Peter,

The following commit seems to have been dropped on the floor. Given that you haven't complained, I feel the need to ask you if you still need it. ;-)

If you do need it, I will push it into 3.16.

Thanx, Paul

------------------------------------------------------------------------

rcu: Provide grace-period piggybacking API

The following pattern is currently not well supported by RCU:

1. Make data element inaccessible to RCU readers.

2. Do work that probably lasts for more than one grace period.

3. Do something to make sure RCU readers in flight before #1 above
have completed.

Here are some things that could currently be done:

a. Do a synchronize_rcu() unconditionally at either #1 or #3 above.
This works, but imposes needless work and latency.

b. Post an RCU callback at #1 above that does a wakeup, then
wait for the wakeup at #3. This works well, but likely results in an extra unneeded grace period. Open-coding this is also a bit more semi-tricky code than would be good.

This commit therefore adds get_state_synchronize_rcu() and cond_synchronize_rcu() APIs. Call get_state_synchronize_rcu() at #1 above and pass its return value to cond_synchronize_rcu() at #3 above. This results in a call to synchronize_rcu() if no grace period has elapsed between #1 and #3, but requires only a load, comparison, and memory barrier if a full grace period did elapse.

include/linux/rcutiny.h +10 -0
index e8cb6e3b52a7..425c659d54e5 100644
@@ -27,6 +27,16 @@
 
 #include <linux/cache.h>
 
+static inline unsigned long get_state_synchronize_rcu(void)
+{
+	return 0;
+}
+
+static inline void cond_synchronize_rcu(unsigned long oldstate)
+{
+	might_sleep();
+}
+
 static inline void rcu_barrier_bh(void)
 {
 	wait_rcu_gp(call_rcu_bh);
include/linux/rcutree.h +2 -0
index e9c63884df0a..a59ca05fd4e3 100644
@@ -76,6 +76,8 @@ static inline void synchronize_rcu_bh_expedited(void)
 void rcu_barrier(void);
 void rcu_barrier_bh(void);
 void rcu_barrier_sched(void);
+unsigned long get_state_synchronize_rcu(void);
+void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
kernel/rcu/tree.c +58 -4

87 lines not on this page · raw message

#1 lore raw
Quoted 8 lines · Paul E. McKenney

Hello, Peter,

The following commit seems to have been dropped on the floor. Given that you haven't complained, I feel the need to ask you if you still need it. ;-)

If you do need it, I will push it into 3.16.

Yes, I do.. thanks for reminding me, I'll need to go find the patch that needs it :-)

#2 lore raw
Quoted 11 lines · Peter Zijlstra
Quoted 7 lines · Paul E. McKenney

Hello, Peter,

The following commit seems to have been dropped on the floor. Given that you haven't complained, I feel the need to ask you if you still need it. ;-)

If you do need it, I will push it into 3.16.

Yes, I do.. thanks for reminding me, I'll need to go find the patch that needs it :-)

No problem!

And it turns out that it is in fact in mainline. I was looking at an obsolete patch, thus looking in the wrong place for it. :-/

Good thing I didn't try to add it again...

Thanx, Paul