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

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

   - Another attempt at enabling cross-release lockdep dependency
     tracking (automatically part of CONFIG_PROVE_LOCKING=y), this time
     with better performance and fewer false positives. (Byungchul Park)

   - Introduce lockdep_assert_irqs_enabled()/disabled() and convert
     open-coded equivalents to lockdep variants. (Frederic Weisbecker)

   - Add down_read_killable() and use it in the VFS's iterate_dir()
     method. (Kirill Tkhai)

   - Convert remaining uses of ACCESS_ONCE() to
     READ_ONCE()/WRITE_ONCE(). Most of the conversion was Coccinelle
     driven. (Mark Rutland, Paul E. McKenney)

   - Get rid of lockless_dereference(), by strengthening Alpha atomics,
     strengthening READ_ONCE() with smp_read_barrier_depends() and thus
     being able to convert users of lockless_dereference() to
     READ_ONCE(). (Will Deacon)

   - Various micro-optimizations:

        - better PV qspinlocks (Waiman Long),
        - better x86 barriers (Michael S. Tsirkin)
        - better x86 refcounts (Kees Cook)

   - ... plus other fixes and enhancements. (Borislav Petkov, Juergen
     Gross, Miguel Bernal Marin)"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  locking/x86: Use LOCK ADD for smp_mb() instead of MFENCE
  rcu: Use lockdep to assert IRQs are disabled/enabled
  netpoll: Use lockdep to assert IRQs are disabled/enabled
  timers/posix-cpu-timers: Use lockdep to assert IRQs are disabled/enabled
  sched/clock, sched/cputime: Use lockdep to assert IRQs are disabled/enabled
  irq_work: Use lockdep to assert IRQs are disabled/enabled
  irq/timings: Use lockdep to assert IRQs are disabled/enabled
  perf/core: Use lockdep to assert IRQs are disabled/enabled
  x86: Use lockdep to assert IRQs are disabled/enabled
  smp/core: Use lockdep to assert IRQs are disabled/enabled
  timers/hrtimer: Use lockdep to assert IRQs are disabled/enabled
  timers/nohz: Use lockdep to assert IRQs are disabled/enabled
  workqueue: Use lockdep to assert IRQs are disabled/enabled
  irq/softirqs: Use lockdep to assert IRQs are disabled/enabled
  locking/lockdep: Add IRQs disabled/enabled assertion APIs: lockdep_assert_irqs_enabled()/disabled()
  locking/pvqspinlock: Implement hybrid PV queued/unfair locks
  locking/rwlocks: Fix comments
  x86/paravirt: Set up the virt_spin_lock_key after static keys get initialized
  block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion()
  workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes
  ...

1 files changed, 18 insertions, 18 deletions

diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index a7868503d135..29bc51084c82 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -432,7 +432,7 @@ do_sync_free:
 		synchronize_rcu_expedited();
 		dm_stat_free(&s->rcu_head);
 	} else {
-		ACCESS_ONCE(dm_stat_need_rcu_barrier) = 1;
+		WRITE_ONCE(dm_stat_need_rcu_barrier, 1);
 		call_rcu(&s->rcu_head, dm_stat_free);
 	}
 	return 0;
@@ -640,12 +640,12 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
 		 */
 		last = raw_cpu_ptr(stats->last);
 		stats_aux->merged =
-			(bi_sector == (ACCESS_ONCE(last->last_sector) &&
+			(bi_sector == (READ_ONCE(last->last_sector) &&
 				       ((bi_rw == WRITE) ==
-					(ACCESS_ONCE(last->last_rw) == WRITE))
+					(READ_ONCE(last->last_rw) == WRITE))
 				       ));
-		ACCESS_ONCE(last->last_sector) = end_sector;
-		ACCESS_ONCE(last->last_rw) = bi_rw;
+		WRITE_ONCE(last->last_sector, end_sector);
+		WRITE_ONCE(last->last_rw, bi_rw);
 	}
 
 	rcu_read_lock();
@@ -694,22 +694,22 @@ static void __dm_stat_init_temporary_percpu_totals(struct dm_stat_shared *shared
 
 	for_each_possible_cpu(cpu) {
 		p = &s->stat_percpu[cpu][x];
-		shared->tmp.sectors[READ] += ACCESS_ONCE(p->sectors[READ]);
-		shared->tmp.sectors[WRITE] += ACCESS_ONCE(p->sectors[WRITE]);
-		shared->tmp.ios[READ] += ACCESS_ONCE(p->ios[READ]);
-		shared->tmp.ios[WRITE] += ACCESS_ONCE(p->ios[WRITE]);
-		shared->tmp.merges[READ] += ACCESS_ONCE(p->merges[READ]);
-		shared->tmp.merges[WRITE] += ACCESS_ONCE(p->merges[WRITE]);
-		shared->tmp.ticks[READ] += ACCESS_ONCE(p->ticks[READ]);
-		shared->tmp.ticks[WRITE] += ACCESS_ONCE(p->ticks[WRITE]);
-		shared->tmp.io_ticks[READ] += ACCESS_ONCE(p->io_ticks[READ]);
-		shared->tmp.io_ticks[WRITE] += ACCESS_ONCE(p->io_ticks[WRITE]);
-		shared->tmp.io_ticks_total += ACCESS_ONCE(p->io_ticks_total);
-		shared->tmp.time_in_queue += ACCESS_ONCE(p->time_in_queue);
+		shared->tmp.sectors[READ] += READ_ONCE(p->sectors[READ]);
+		shared->tmp.sectors[WRITE] += READ_ONCE(p->sectors[WRITE]);
+		shared->tmp.ios[READ] += READ_ONCE(p->ios[READ]);
+		shared->tmp.ios[WRITE] += READ_ONCE(p->ios[WRITE]);
+		shared->tmp.merges[READ] += READ_ONCE(p->merges[READ]);
+		shared->tmp.merges[WRITE] += READ_ONCE(p->merges[WRITE]);
+		shared->tmp.ticks[READ] += READ_ONCE(p->ticks[READ]);
+		shared->tmp.ticks[WRITE] += READ_ONCE(p->ticks[WRITE]);
+		shared->tmp.io_ticks[READ] += READ_ONCE(p->io_ticks[READ]);
+		shared->tmp.io_ticks[WRITE] += READ_ONCE(p->io_ticks[WRITE]);
+		shared->tmp.io_ticks_total += READ_ONCE(p->io_ticks_total);
+		shared->tmp.time_in_queue += READ_ONCE(p->time_in_queue);
 		if (s->n_histogram_entries) {
 			unsigned i;
 			for (i = 0; i < s->n_histogram_entries + 1; i++)
-				shared->tmp.histogram[i] += ACCESS_ONCE(p->histogram[i]);
+				shared->tmp.histogram[i] += READ_ONCE(p->histogram[i]);
 		}
 	}
 }