Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking changes from Ingo Molnar:
 "Various updates:

   - Futex scalability improvements: remove page lock use for shared
     futex get_futex_key(), which speeds up 'perf bench futex hash'
     benchmarks by over 40% on a 60-core Westmere.  This makes anon-mem
     shared futexes perform close to private futexes.  (Mel Gorman)

   - lockdep hash collision detection and fix (Alfredo Alvarez
     Fernandez)

   - lockdep testing enhancements (Alfredo Alvarez Fernandez)

   - robustify lockdep init by using hlists (Andrew Morton, Andrey
     Ryabinin)

   - mutex and csd_lock micro-optimizations (Davidlohr Bueso)

   - small x86 barriers tweaks (Michael S Tsirkin)

   - qspinlock updates (Waiman Long)"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  locking/csd_lock: Use smp_cond_acquire() in csd_lock_wait()
  locking/csd_lock: Explicitly inline csd_lock*() helpers
  futex: Replace barrier() in unqueue_me() with READ_ONCE()
  locking/lockdep: Detect chain_key collisions
  locking/lockdep: Prevent chain_key collisions
  tools/lib/lockdep: Fix link creation warning
  tools/lib/lockdep: Add tests for AA and ABBA locking
  tools/lib/lockdep: Add userspace version of READ_ONCE()
  tools/lib/lockdep: Fix the build on recent kernels
  locking/qspinlock: Move __ARCH_SPIN_LOCK_UNLOCKED to qspinlock_types.h
  locking/mutex: Allow next waiter lockless wakeup
  locking/pvqspinlock: Enable slowpath locking count tracking
  locking/qspinlock: Use smp_cond_acquire() in pending code
  locking/pvqspinlock: Move lock stealing count tracking code into pv_queued_spin_steal_lock()
  locking/mcs: Fix mcs_spin_lock() ordering
  futex: Remove requirement for lock_page() in get_futex_key()
  futex: Rename barrier references in ordering guarantees
  locking/atomics: Update comment about READ_ONCE() and structures
  locking/lockdep: Eliminate lockdep_init()
  locking/lockdep: Convert hash tables to hlists
  ...

2 files changed, 3 insertions, 4 deletions

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 48f5aab117ae..a27f4f17c382 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -263,8 +263,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * In contrast to ACCESS_ONCE these two macros will also work on aggregate
  * data types like structs or unions. If the size of the accessed data
  * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
- * compile-time warning.
+ * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at
+ * least two memcpy()s: one for the __builtin_memcpy() and then one for
+ * the macro doing the copy of variable - '__u' allocated on the stack.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 4dca42fd32f5..d026b190c530 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -261,7 +261,6 @@ struct held_lock {
 /*
  * Initialization, self-test and debugging-output methods:
  */
-extern void lockdep_init(void);
 extern void lockdep_info(void);
 extern void lockdep_reset(void);
 extern void lockdep_reset_lock(struct lockdep_map *lock);
@@ -392,7 +391,6 @@ static inline void lockdep_on(void)
 # define lockdep_set_current_reclaim_state(g)	do { } while (0)
 # define lockdep_clear_current_reclaim_state()	do { } while (0)
 # define lockdep_trace_alloc(g)			do { } while (0)
-# define lockdep_init()				do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)