percpu-refcount: make percpu_ref based on longs instead of ints

percpu_ref is currently based on ints and the number of refs it can
cover is (1 << 31).  This makes it impossible to use a percpu_ref to
count memory objects or pages on 64bit machines as it may overflow.
This forces those users to somehow aggregate the references before
contributing to the percpu_ref which is often cumbersome and sometimes
challenging to get the same level of performance as using the
percpu_ref directly.

While using ints for the percpu counters makes them pack tighter on
64bit machines, the possible gain from using ints instead of longs is
extremely small compared to the overall gain from per-cpu operation.
This patch makes percpu_ref based on longs so that it can be used to
directly count memory objects or pages.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>

1 files changed, 12 insertions, 12 deletions

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index ee8325122dbd..5df6784bd9d2 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -55,7 +55,7 @@ struct percpu_ref;
 typedef void (percpu_ref_func_t)(struct percpu_ref *);
 
 struct percpu_ref {
-	atomic_t		count;
+	atomic_long_t		count;
 	/*
 	 * The low bit of the pointer indicates whether the ref is in percpu
 	 * mode; if set, then get/put will manipulate the atomic_t.
@@ -97,7 +97,7 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
  * branches as it can't assume that @ref->pcpu_count is not NULL.
  */
 static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
-				    unsigned __percpu **pcpu_countp)
+				    unsigned long __percpu **pcpu_countp)
 {
 	unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr);
 
@@ -107,7 +107,7 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
 	if (unlikely(pcpu_ptr & PCPU_REF_DEAD))
 		return false;
 
-	*pcpu_countp = (unsigned __percpu *)pcpu_ptr;
+	*pcpu_countp = (unsigned long __percpu *)pcpu_ptr;
 	return true;
 }
 
@@ -119,14 +119,14 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
   */
 static inline void percpu_ref_get(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__pcpu_ref_alive(ref, &pcpu_count))
 		this_cpu_inc(*pcpu_count);
 	else
-		atomic_inc(&ref->count);
+		atomic_long_inc(&ref->count);
 
 	rcu_read_unlock_sched();
 }
@@ -142,7 +142,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
@@ -151,7 +151,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 		this_cpu_inc(*pcpu_count);
 		ret = true;
 	} else {
-		ret = atomic_inc_not_zero(&ref->count);
+		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
 	rcu_read_unlock_sched();
@@ -175,7 +175,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
@@ -199,13 +199,13 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
  */
 static inline void percpu_ref_put(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__pcpu_ref_alive(ref, &pcpu_count))
 		this_cpu_dec(*pcpu_count);
-	else if (unlikely(atomic_dec_and_test(&ref->count)))
+	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
@@ -219,11 +219,11 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 
 	if (__pcpu_ref_alive(ref, &pcpu_count))
 		return false;
-	return !atomic_read(&ref->count);
+	return !atomic_long_read(&ref->count);
 }
 
 #endif