Re: [PATCH tip/core/rcu 0/13] percpu-rwsem patches for 4.4

[Josh Triplett]

On Tue, Oct 06, 2015 at 09:45:14AM -0700, Paul E. McKenney wrote:
> Hello!
> 
> This series contains performance improvements and locktorture testing
> for percpu-rwsem:
> 
> 1.	Add rtmutex torturing to locktorture, courtesy of Davidlohr Bueso.
> 
> 2.	Add exports to allow locktorture to be built as a module.
> 
> 3.	Add torture tests for percpu-rwsem.
> 
> 4.	Consolidate cond_resched_rcu_qs() into stutter_wait().
> 
> 5.	Create rcu_sync infrastructure, courtesy of Oleg Nesterov.
> 
> 6.	Simplify rcu_sync using new rcu_sync_ops structure, courtesy
> 	of Oleg Nesterov.
> 
> 7.	Add CONFIG_PROVE_RCU checks for rcu_sync, courtesy of Oleg Nesterov.
> 
> 8.	Introduce rcu_sync_dtor(), courtesy of Oleg Nesterov.
> 
> 9.	Make percpu_free_rwsem() after kzalloc() safe, courtesy of Oleg
> 	Nesterov.
> 
> 10.	Make percpu-rwsem make use of rcu_sync, courtesy of Oleg Nesterov.
> 
> 11.	Fix the comments outdated by rcu_sync, courtesy of Oleg Nesterov.
> 
> 12.	Clean up the lockdep annotations in percpu_down_read(), courtesy
> 	Peter Zijlstra and of Oleg Nesterov.
> 
> 13.	Cleanup the CONFIG_PROVE_RCU checks, courtesy of Oleg Nesterov.

For all 13:
Reviewed-by: Josh Triplett <josh@xxxxxxxxxxxxxxxx>

Regarding the rcu_sync infrastructure: odd that an atomic read
on the reader proves ligher weight than
rcu_read_lock()/rcu_read_unlock().
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/