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
  ...

11 files changed, 50 insertions, 49 deletions

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index d216a8f7bc22..33bb074d6941 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -347,7 +347,7 @@ static void __cache_size_refresh(void)
 	BUG_ON(!mutex_is_locked(&dm_bufio_clients_lock));
 	BUG_ON(dm_bufio_client_count < 0);
 
-	dm_bufio_cache_size_latch = ACCESS_ONCE(dm_bufio_cache_size);
+	dm_bufio_cache_size_latch = READ_ONCE(dm_bufio_cache_size);
 
 	/*
 	 * Use default if set to 0 and report the actual cache size used.
@@ -960,7 +960,7 @@ static void __get_memory_limit(struct dm_bufio_client *c,
 {
 	unsigned long buffers;
 
-	if (unlikely(ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) {
+	if (unlikely(READ_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) {
 		if (mutex_trylock(&dm_bufio_clients_lock)) {
 			__cache_size_refresh();
 			mutex_unlock(&dm_bufio_clients_lock);
@@ -1600,7 +1600,7 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp)
 
 static unsigned long get_retain_buffers(struct dm_bufio_client *c)
 {
-        unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
+        unsigned long retain_bytes = READ_ONCE(dm_bufio_retain_bytes);
         return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT);
 }
 
@@ -1647,7 +1647,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
 
-	return ACCESS_ONCE(c->n_buffers[LIST_CLEAN]) + ACCESS_ONCE(c->n_buffers[LIST_DIRTY]);
+	return READ_ONCE(c->n_buffers[LIST_CLEAN]) + READ_ONCE(c->n_buffers[LIST_DIRTY]);
 }
 
 /*
@@ -1818,7 +1818,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset);
 
 static unsigned get_max_age_hz(void)
 {
-	unsigned max_age = ACCESS_ONCE(dm_bufio_max_age);
+	unsigned max_age = READ_ONCE(dm_bufio_max_age);
 
 	if (max_age > UINT_MAX / HZ)
 		max_age = UINT_MAX / HZ;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 096fe9b66c50..8c5756e1df94 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -6,6 +6,7 @@
  * This file is released under the GPL.
  */
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/device-mapper.h>
 #include <linux/dm-io.h>
@@ -80,13 +81,13 @@ struct journal_entry {
 #define journal_entry_tag(ic, je)		((__u8 *)&(je)->last_bytes[(ic)->sectors_per_block])
 
 #if BITS_PER_LONG == 64
-#define journal_entry_set_sector(je, x)		do { smp_wmb(); ACCESS_ONCE((je)->u.sector) = cpu_to_le64(x); } while (0)
+#define journal_entry_set_sector(je, x)		do { smp_wmb(); WRITE_ONCE((je)->u.sector, cpu_to_le64(x)); } while (0)
 #define journal_entry_get_sector(je)		le64_to_cpu((je)->u.sector)
 #elif defined(CONFIG_LBDAF)
-#define journal_entry_set_sector(je, x)		do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); ACCESS_ONCE((je)->u.s.sector_hi) = cpu_to_le32((x) >> 32); } while (0)
+#define journal_entry_set_sector(je, x)		do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32((x) >> 32)); } while (0)
 #define journal_entry_get_sector(je)		le64_to_cpu((je)->u.sector)
 #else
-#define journal_entry_set_sector(je, x)		do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); ACCESS_ONCE((je)->u.s.sector_hi) = cpu_to_le32(0); } while (0)
+#define journal_entry_set_sector(je, x)		do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32(0)); } while (0)
 #define journal_entry_get_sector(je)		le32_to_cpu((je)->u.s.sector_lo)
 #endif
 #define journal_entry_is_unused(je)		((je)->u.s.sector_hi == cpu_to_le32(-1))
@@ -320,7 +321,7 @@ static void dm_integrity_io_error(struct dm_integrity_c *ic, const char *msg, in
 
 static int dm_integrity_failed(struct dm_integrity_c *ic)
 {
-	return ACCESS_ONCE(ic->failed);
+	return READ_ONCE(ic->failed);
 }
 
 static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned i,
@@ -1545,7 +1546,7 @@ retry_kmap:
 		smp_mb();
 		if (unlikely(waitqueue_active(&ic->copy_to_journal_wait)))
 			wake_up(&ic->copy_to_journal_wait);
-		if (ACCESS_ONCE(ic->free_sectors) <= ic->free_sectors_threshold) {
+		if (READ_ONCE(ic->free_sectors) <= ic->free_sectors_threshold) {
 			queue_work(ic->commit_wq, &ic->commit_work);
 		} else {
 			schedule_autocommit(ic);
@@ -1798,7 +1799,7 @@ static void integrity_commit(struct work_struct *w)
 	ic->n_committed_sections += commit_sections;
 	spin_unlock_irq(&ic->endio_wait.lock);
 
-	if (ACCESS_ONCE(ic->free_sectors) <= ic->free_sectors_threshold)
+	if (READ_ONCE(ic->free_sectors) <= ic->free_sectors_threshold)
 		queue_work(ic->writer_wq, &ic->writer_work);
 
 release_flush_bios:
@@ -1980,7 +1981,7 @@ static void integrity_writer(struct work_struct *w)
 	unsigned prev_free_sectors;
 
 	/* the following test is not needed, but it tests the replay code */
-	if (ACCESS_ONCE(ic->suspending))
+	if (READ_ONCE(ic->suspending))
 		return;
 
 	spin_lock_irq(&ic->endio_wait.lock);
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index cf2c67e35eaf..eb45cc3df31d 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -107,7 +107,7 @@ static void io_job_start(struct dm_kcopyd_throttle *t)
 try_again:
 	spin_lock_irq(&throttle_spinlock);
 
-	throttle = ACCESS_ONCE(t->throttle);
+	throttle = READ_ONCE(t->throttle);
 
 	if (likely(throttle >= 100))
 		goto skip_limit;
@@ -157,7 +157,7 @@ static void io_job_finish(struct dm_kcopyd_throttle *t)
 
 	t->num_io_jobs--;
 
-	if (likely(ACCESS_ONCE(t->throttle) >= 100))
+	if (likely(READ_ONCE(t->throttle) >= 100))
 		goto skip_limit;
 
 	if (!t->num_io_jobs) {
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 11f273d2f018..3f88c9d32f7e 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -366,7 +366,7 @@ static struct pgpath *choose_path_in_pg(struct multipath *m,
 
 	pgpath = path_to_pgpath(path);
 
-	if (unlikely(lockless_dereference(m->current_pg) != pg)) {
+	if (unlikely(READ_ONCE(m->current_pg) != pg)) {
 		/* Only update current_pgpath if pg changed */
 		spin_lock_irqsave(&m->lock, flags);
 		m->current_pgpath = pgpath;
@@ -390,7 +390,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 	}
 
 	/* Were we instructed to switch PG? */
-	if (lockless_dereference(m->next_pg)) {
+	if (READ_ONCE(m->next_pg)) {
 		spin_lock_irqsave(&m->lock, flags);
 		pg = m->next_pg;
 		if (!pg) {
@@ -406,7 +406,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 
 	/* Don't change PG until it has no remaining paths */
 check_current_pg:
-	pg = lockless_dereference(m->current_pg);
+	pg = READ_ONCE(m->current_pg);
 	if (pg) {
 		pgpath = choose_path_in_pg(m, pg, nr_bytes);
 		if (!IS_ERR_OR_NULL(pgpath))
@@ -473,7 +473,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 	struct request *clone;
 
 	/* Do we need to select a new pgpath? */
-	pgpath = lockless_dereference(m->current_pgpath);
+	pgpath = READ_ONCE(m->current_pgpath);
 	if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
 		pgpath = choose_pgpath(m, nr_bytes);
 
@@ -535,7 +535,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 	bool queue_io;
 
 	/* Do we need to select a new pgpath? */
-	pgpath = lockless_dereference(m->current_pgpath);
+	pgpath = READ_ONCE(m->current_pgpath);
 	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
 	if (!pgpath || !queue_io)
 		pgpath = choose_pgpath(m, nr_bytes);
@@ -1804,7 +1804,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	struct pgpath *current_pgpath;
 	int r;
 
-	current_pgpath = lockless_dereference(m->current_pgpath);
+	current_pgpath = READ_ONCE(m->current_pgpath);
 	if (!current_pgpath)
 		current_pgpath = choose_pgpath(m, 0);
 
@@ -1826,7 +1826,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	}
 
 	if (r == -ENOTCONN) {
-		if (!lockless_dereference(m->current_pg)) {
+		if (!READ_ONCE(m->current_pg)) {
 			/* Path status changed, redo selection */
 			(void) choose_pgpath(m, 0);
 		}
@@ -1895,9 +1895,9 @@ static int multipath_busy(struct dm_target *ti)
 		return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED);
 
 	/* Guess which priority_group will be used at next mapping time */
-	pg = lockless_dereference(m->current_pg);
-	next_pg = lockless_dereference(m->next_pg);
-	if (unlikely(!lockless_dereference(m->current_pgpath) && next_pg))
+	pg = READ_ONCE(m->current_pg);
+	next_pg = READ_ONCE(m->next_pg);
+	if (unlikely(!READ_ONCE(m->current_pgpath) && next_pg))
 		pg = next_pg;
 
 	if (!pg) {
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]);
 		}
 	}
 }
diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c
index 4c8de1ff78ca..8d0ba879777e 100644
--- a/drivers/md/dm-switch.c
+++ b/drivers/md/dm-switch.c
@@ -144,7 +144,7 @@ static unsigned switch_region_table_read(struct switch_ctx *sctx, unsigned long
 
 	switch_get_position(sctx, region_nr, &region_index, &bit);
 
-	return (ACCESS_ONCE(sctx->region_table[region_index]) >> bit) &
+	return (READ_ONCE(sctx->region_table[region_index]) >> bit) &
 		((1 << sctx->region_table_entry_bits) - 1);
 }
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 1e25705209c2..89e5dff9b4cf 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2431,7 +2431,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 	struct pool_c *pt = pool->ti->private;
 	bool needs_check = dm_pool_metadata_needs_check(pool->pmd);
 	enum pool_mode old_mode = get_pool_mode(pool);
-	unsigned long no_space_timeout = ACCESS_ONCE(no_space_timeout_secs) * HZ;
+	unsigned long no_space_timeout = READ_ONCE(no_space_timeout_secs) * HZ;
 
 	/*
 	 * Never allow the pool to transition to PM_WRITE mode if user
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index bda3caca23ca..fba93237a780 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -589,7 +589,7 @@ static void verity_prefetch_io(struct work_struct *work)
 		verity_hash_at_level(v, pw->block, i, &hash_block_start, NULL);
 		verity_hash_at_level(v, pw->block + pw->n_blocks - 1, i, &hash_block_end, NULL);
 		if (!i) {
-			unsigned cluster = ACCESS_ONCE(dm_verity_prefetch_cluster);
+			unsigned cluster = READ_ONCE(dm_verity_prefetch_cluster);
 
 			cluster >>= v->data_dev_block_bits;
 			if (unlikely(!cluster))
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4be85324f44d..8aaffa19b29a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -114,7 +114,7 @@ static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
 
 static int __dm_get_module_param_int(int *module_param, int min, int max)
 {
-	int param = ACCESS_ONCE(*module_param);
+	int param = READ_ONCE(*module_param);
 	int modified_param = 0;
 	bool modified = true;
 
@@ -136,7 +136,7 @@ static int __dm_get_module_param_int(int *module_param, int min, int max)
 unsigned __dm_get_module_param(unsigned *module_param,
 			       unsigned def, unsigned max)
 {
-	unsigned param = ACCESS_ONCE(*module_param);
+	unsigned param = READ_ONCE(*module_param);
 	unsigned modified_param = 0;
 
 	if (!param)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0ff1bbf6c90e..447ddcbc9566 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2651,7 +2651,7 @@ state_show(struct md_rdev *rdev, char *page)
 {
 	char *sep = ",";
 	size_t len = 0;
-	unsigned long flags = ACCESS_ONCE(rdev->flags);
+	unsigned long flags = READ_ONCE(rdev->flags);
 
 	if (test_bit(Faulty, &flags) ||
 	    (!test_bit(ExternalBbl, &flags) &&
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 928e24a07133..7d9a50eed9db 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6072,7 +6072,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
 	 */
 	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = ACCESS_ONCE(conf->disks[i].rdev);
+		struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev);
 
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags))
 			still_degraded = 1;