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

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Implement wraparound-safe refcount_t and kref_t types based on
     generic atomic primitives (Peter Zijlstra)

   - Improve and fix the ww_mutex code (Nicolai Hähnle)

   - Add self-tests to the ww_mutex code (Chris Wilson)

   - Optimize percpu-rwsems with the 'rcuwait' mechanism (Davidlohr
     Bueso)

   - Micro-optimize the current-task logic all around the core kernel
     (Davidlohr Bueso)

   - Tidy up after recent optimizations: remove stale code and APIs,
     clean up the code (Waiman Long)

   - ... plus misc fixes, updates and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  fork: Fix task_struct alignment
  locking/spinlock/debug: Remove spinlock lockup detection code
  lockdep: Fix incorrect condition to print bug msgs for MAX_LOCKDEP_CHAIN_HLOCKS
  lkdtm: Convert to refcount_t testing
  kref: Implement 'struct kref' using refcount_t
  refcount_t: Introduce a special purpose refcount type
  sched/wake_q: Clarify queue reinit comment
  sched/wait, rcuwait: Fix typo in comment
  locking/mutex: Fix lockdep_assert_held() fail
  locking/rtmutex: Flip unlikely() branch to likely() in __rt_mutex_slowlock()
  locking/rwsem: Reinit wake_q after use
  locking/rwsem: Remove unnecessary atomic_long_t casts
  jump_labels: Move header guard #endif down where it belongs
  locking/atomic, kref: Implement kref_put_lock()
  locking/ww_mutex: Turn off __must_check for now
  locking/atomic, kref: Avoid more abuse
  locking/atomic, kref: Use kref_get_unless_zero() more
  locking/atomic, kref: Kill kref_sub()
  locking/atomic, kref: Add kref_read()
  locking/atomic, kref: Add KREF_INIT()
  ...

kernel/exit.c

@@ -55,6 +55,7 @@
 #include <linux/shm.h>
 #include <linux/kcov.h>
 #include <linux/random.h>
+#include <linux/rcuwait.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -282,6 +283,35 @@ retry:
 	return task;
 }
 
+void rcuwait_wake_up(struct rcuwait *w)
+{
+	struct task_struct *task;
+
+	rcu_read_lock();
+
+	/*
+	 * Order condition vs @task, such that everything prior to the load
+	 * of @task is visible. This is the condition as to why the user called
+	 * rcuwait_trywake() in the first place. Pairs with set_current_state()
+	 * barrier (A) in rcuwait_wait_event().
+	 *
+	 *    WAIT                WAKE
+	 *    [S] tsk = current	  [S] cond = true
+	 *        MB (A)	      MB (B)
+	 *    [L] cond		  [L] tsk
+	 */
+	smp_rmb(); /* (B) */
+
+	/*
+	 * Avoid using task_rcu_dereference() magic as long as we are careful,
+	 * see comment in rcuwait_wait_event() regarding ->exit_state.
+	 */
+	task = rcu_dereference(w->task);
+	if (task)
+		wake_up_process(task);
+	rcu_read_unlock();
+}
+
 struct task_struct *try_get_task_struct(struct task_struct **ptask)
 {
 	struct task_struct *task;
@@ -468,12 +498,12 @@ assign_new_owner:
  * Turn us into a lazy TLB process if we
  * aren't already..
  */
-static void exit_mm(struct task_struct *tsk)
+static void exit_mm(void)
 {
-	struct mm_struct *mm = tsk->mm;
+	struct mm_struct *mm = current->mm;
 	struct core_state *core_state;
 
-	mm_release(tsk, mm);
+	mm_release(current, mm);
 	if (!mm)
 		return;
 	sync_mm_rss(mm);
@@ -491,7 +521,7 @@ static void exit_mm(struct task_struct *tsk)
 
 		up_read(&mm->mmap_sem);
 
-		self.task = tsk;
+		self.task = current;
 		self.next = xchg(&core_state->dumper.next, &self);
 		/*
 		 * Implies mb(), the result of xchg() must be visible
@@ -501,22 +531,22 @@ static void exit_mm(struct task_struct *tsk)
 			complete(&core_state->startup);
 
 		for (;;) {
-			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+			set_current_state(TASK_UNINTERRUPTIBLE);
 			if (!self.task) /* see coredump_finish() */
 				break;
 			freezable_schedule();
 		}
-		__set_task_state(tsk, TASK_RUNNING);
+		__set_current_state(TASK_RUNNING);
 		down_read(&mm->mmap_sem);
 	}
 	atomic_inc(&mm->mm_count);
-	BUG_ON(mm != tsk->active_mm);
+	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
-	task_lock(tsk);
-	tsk->mm = NULL;
+	task_lock(current);
+	current->mm = NULL;
 	up_read(&mm->mmap_sem);
 	enter_lazy_tlb(mm, current);
-	task_unlock(tsk);
+	task_unlock(current);
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
@@ -823,7 +853,7 @@ void __noreturn do_exit(long code)
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
 
-	exit_mm(tsk);
+	exit_mm();
 
 	if (group_dead)
 		acct_process();