[PATCH] percpu: Revert ("percpu: Replace smp_read_barrier_depends() with lockless_dereference()")
From: Tejun Heo
Date: Wed May 25 2016 - 16:12:09 EST
lockless_dereference() is planned to grow a sanity check to ensure
that the input parameter is a pointer. __ref_is_percpu() passes in an
unsinged long value which is a combination of a pointer and a flag.
While it can be casted to a pointer lvalue, the casting looks messy
and it's a special case anyway. Let's revert back to open-coding
READ_ONCE() and explicit barrier.
This doesn't cause any functional changes.
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Pranith Kumar <bobby.prani@xxxxxxxxx>
Cc: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
So, something like this. Please feel free to include in the series.
include/linux/percpu-refcount.h | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 84f542d..1c7eec0 100644
@@ -136,14 +136,12 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
* used as a pointer. If the compiler generates a separate fetch
* when using it as a pointer, __PERCPU_REF_ATOMIC may be set in
* between contaminating the pointer value, meaning that
- * ACCESS_ONCE() is required when fetching it.
- * Also, we need a data dependency barrier to be paired with
- * smp_store_release() in __percpu_ref_switch_to_percpu().
- * Use lockless deref which contains both.
+ * READ_ONCE() is required when fetching it.
- percpu_ptr = lockless_dereference(ref->percpu_count_ptr);
+ percpu_ptr = READ_ONCE(ref->percpu_count_ptr);
+ /* paired with smp_store_release() in __percpu_ref_switch_to_percpu() */
* Theoretically, the following could test just ATOMIC; however,