summaryrefslogtreecommitdiff
path: root/include/linux/percpu-refcount.h
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2013-06-17 03:12:26 +0400
committerTejun Heo <tj@kernel.org>2013-06-17 03:12:26 +0400
commita4244454df1296e90cc961c1b636b1176ef0d9a0 (patch)
tree9be151f1e7a791dbf2d146fc5283ed246562d7f1 /include/linux/percpu-refcount.h
parentdbece3a0f1ef0b19aff1cc6ed0942fec9ab98de1 (diff)
downloadlinux-a4244454df1296e90cc961c1b636b1176ef0d9a0.tar.xz
percpu-refcount: use RCU-sched insted of normal RCU
percpu-refcount was incorrectly using preempt_disable/enable() for RCU critical sections against call_rcu(). 6a24474da8 ("percpu-refcount: consistently use plain (non-sched) RCU") fixed it by converting the preepmtion operations with rcu_read_[un]lock() citing that there isn't any advantage in using sched-RCU over using the usual one; however, rcu_read_[un]lock() for the preemptible RCU implementation - CONFIG_TREE_PREEMPT_RCU, chosen when CONFIG_PREEMPT - are slightly more expensive than preempt_disable/enable(). In a contrived microbench which repeats the followings, - percpu_ref_get() - copy 32 bytes of data into percpu buffer - percpu_put_get() - copy 32 bytes of data into percpu buffer rcu_read_[un]lock() used in percpu_ref_get/put() makes it go slower by about 15% when compared to using sched-RCU. As the RCU critical sections are extremely short, using sched-RCU shouldn't have any latency implications. Convert to RCU-sched. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Kent Overstreet <koverstreet@google.com> Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au>
Diffstat (limited to 'include/linux/percpu-refcount.h')
-rw-r--r--include/linux/percpu-refcount.h12
1 files changed, 6 insertions, 6 deletions
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index dd2a08600453..95961f0bf62d 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -105,7 +105,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
{
unsigned __percpu *pcpu_count;
- rcu_read_lock();
+ rcu_read_lock_sched();
pcpu_count = ACCESS_ONCE(ref->pcpu_count);
@@ -114,7 +114,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
else
atomic_inc(&ref->count);
- rcu_read_unlock();
+ rcu_read_unlock_sched();
}
/**
@@ -134,7 +134,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
unsigned __percpu *pcpu_count;
int ret = false;
- rcu_read_lock();
+ rcu_read_lock_sched();
pcpu_count = ACCESS_ONCE(ref->pcpu_count);
@@ -143,7 +143,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
ret = true;
}
- rcu_read_unlock();
+ rcu_read_unlock_sched();
return ret;
}
@@ -159,7 +159,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
{
unsigned __percpu *pcpu_count;
- rcu_read_lock();
+ rcu_read_lock_sched();
pcpu_count = ACCESS_ONCE(ref->pcpu_count);
@@ -168,7 +168,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
else if (unlikely(atomic_dec_and_test(&ref->count)))
ref->release(ref);
- rcu_read_unlock();
+ rcu_read_unlock_sched();
}
#endif