percpu_ref: add PCPU_REF_DEAD

percpu_ref will be restructured so that percpu/atomic mode switching
and reference killing are dedoupled.  In preparation, add
PCPU_REF_DEAD and PCPU_REF_ATOMIC_DEAD which is OR of ATOMIC and DEAD.
For now, ATOMIC and DEAD are changed together and all PCPU_REF_ATOMIC
uses are converted to PCPU_REF_ATOMIC_DEAD without causing any
behavior changes.

percpu_ref_init() now specifies an explicit alignment when allocating
the percpu counters so that the pointer has enough unused low bits to
accomodate the flags.  Note that one flag was fine as min alignment
for percpu memory is 2 bytes but two flags are already too many for
the natural alignment of unsigned longs on archs like cris and m68k.

v2: The original patch had BUILD_BUG_ON() which triggers if unsigned
    long's alignment isn't enough to accomodate the flags, which
    triggered on cris and m64k.  percpu_ref_init() updated to specify
    the required alignment explicitly.  Reported by Fengguang.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: kbuild test robot <fengguang.wu@intel.com>

1 files changed, 5 insertions, 1 deletions

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 910e5f72055d..bd9483d390b4 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -57,6 +57,10 @@ typedef void (percpu_ref_func_t)(struct percpu_ref *);
 /* flags set in the lower bits of percpu_ref->percpu_count_ptr */
 enum {
 	__PERCPU_REF_ATOMIC	= 1LU << 0,	/* operating in atomic mode */
+	__PERCPU_REF_DEAD	= 1LU << 1,	/* (being) killed */
+	__PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD,
+
+	__PERCPU_REF_FLAG_BITS	= 2,
 };
 
 struct percpu_ref {
@@ -107,7 +111,7 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 	/* paired with smp_store_release() in percpu_ref_reinit() */
 	smp_read_barrier_depends();
 
-	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC))
+	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD))
 		return false;
 
 	*percpu_countp = (unsigned long __percpu *)percpu_ptr;