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
  ...

5 files changed, 31 insertions, 16 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index dfdad67d8f6c..2b439a515c30 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1092,8 +1092,8 @@ config PROVE_LOCKING
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
 	select DEBUG_LOCK_ALLOC
-	select LOCKDEP_CROSSRELEASE if BROKEN
-	select LOCKDEP_COMPLETIONS if BROKEN
+	select LOCKDEP_CROSSRELEASE
+	select LOCKDEP_COMPLETIONS
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1179,6 +1179,21 @@ config LOCKDEP_COMPLETIONS
 	 A deadlock caused by wait_for_completion() and complete() can be
 	 detected by lockdep using crossrelease feature.
 
+config BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK
+	bool "Enable the boot parameter, crossrelease_fullstack"
+	depends on LOCKDEP_CROSSRELEASE
+	default n
+	help
+	 The lockdep "cross-release" feature needs to record stack traces
+	 (of calling functions) for all acquisitions, for eventual later
+	 use during analysis. By default only a single caller is recorded,
+	 because the unwind operation can be very expensive with deeper
+	 stack chains.
+
+	 However a boot parameter, crossrelease_fullstack, was
+	 introduced since sometimes deeper traces are required for full
+	 analysis. This option turns on the boot parameter.
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 4e53be8bc590..b77d51da8c73 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -39,7 +39,7 @@ begin_node:
 		/* Descend through a shortcut */
 		shortcut = assoc_array_ptr_to_shortcut(cursor);
 		smp_read_barrier_depends();
-		cursor = ACCESS_ONCE(shortcut->next_node);
+		cursor = READ_ONCE(shortcut->next_node);
 	}
 
 	node = assoc_array_ptr_to_node(cursor);
@@ -55,7 +55,7 @@ begin_node:
 	 */
 	has_meta = 0;
 	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
-		ptr = ACCESS_ONCE(node->slots[slot]);
+		ptr = READ_ONCE(node->slots[slot]);
 		has_meta |= (unsigned long)ptr;
 		if (ptr && assoc_array_ptr_is_leaf(ptr)) {
 			/* We need a barrier between the read of the pointer
@@ -89,7 +89,7 @@ continue_node:
 	smp_read_barrier_depends();
 
 	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
-		ptr = ACCESS_ONCE(node->slots[slot]);
+		ptr = READ_ONCE(node->slots[slot]);
 		if (assoc_array_ptr_is_meta(ptr)) {
 			cursor = ptr;
 			goto begin_node;
@@ -98,7 +98,7 @@ continue_node:
 
 finished_node:
 	/* Move up to the parent (may need to skip back over a shortcut) */
-	parent = ACCESS_ONCE(node->back_pointer);
+	parent = READ_ONCE(node->back_pointer);
 	slot = node->parent_slot;
 	if (parent == stop)
 		return 0;
@@ -107,7 +107,7 @@ finished_node:
 		shortcut = assoc_array_ptr_to_shortcut(parent);
 		smp_read_barrier_depends();
 		cursor = parent;
-		parent = ACCESS_ONCE(shortcut->back_pointer);
+		parent = READ_ONCE(shortcut->back_pointer);
 		slot = shortcut->parent_slot;
 		if (parent == stop)
 			return 0;
@@ -147,7 +147,7 @@ int assoc_array_iterate(const struct assoc_array *array,
 					void *iterator_data),
 			void *iterator_data)
 {
-	struct assoc_array_ptr *root = ACCESS_ONCE(array->root);
+	struct assoc_array_ptr *root = READ_ONCE(array->root);
 
 	if (!root)
 		return 0;
@@ -194,7 +194,7 @@ assoc_array_walk(const struct assoc_array *array,
 
 	pr_devel("-->%s()\n", __func__);
 
-	cursor = ACCESS_ONCE(array->root);
+	cursor = READ_ONCE(array->root);
 	if (!cursor)
 		return assoc_array_walk_tree_empty;
 
@@ -220,7 +220,7 @@ consider_node:
 
 	slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
 	slot &= ASSOC_ARRAY_FAN_MASK;
-	ptr = ACCESS_ONCE(node->slots[slot]);
+	ptr = READ_ONCE(node->slots[slot]);
 
 	pr_devel("consider slot %x [ix=%d type=%lu]\n",
 		 slot, level, (unsigned long)ptr & 3);
@@ -294,7 +294,7 @@ follow_shortcut:
 	} while (sc_level < shortcut->skip_to_level);
 
 	/* The shortcut matches the leaf's index to this point. */
-	cursor = ACCESS_ONCE(shortcut->next_node);
+	cursor = READ_ONCE(shortcut->next_node);
 	if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) {
 		level = sc_level;
 		goto jumped;
@@ -337,7 +337,7 @@ void *assoc_array_find(const struct assoc_array *array,
 	 * the terminal node.
 	 */
 	for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
-		ptr = ACCESS_ONCE(node->slots[slot]);
+		ptr = READ_ONCE(node->slots[slot]);
 		if (ptr && assoc_array_ptr_is_leaf(ptr)) {
 			/* We need a barrier between the read of the pointer
 			 * and dereferencing the pointer - but only if we are
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index 6a406fafb5d6..da4672a50a54 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -21,7 +21,7 @@ void dql_completed(struct dql *dql, unsigned int count)
 	unsigned int ovlimit, completed, num_queued;
 	bool all_prev_completed;
 
-	num_queued = ACCESS_ONCE(dql->num_queued);
+	num_queued = READ_ONCE(dql->num_queued);
 
 	/* Can't complete more than what's in queue */
 	BUG_ON(count > num_queued - dql->num_completed);
diff --git a/lib/llist.c b/lib/llist.c
index ae5872b1df0c..7062e931a7bb 100644
--- a/lib/llist.c
+++ b/lib/llist.c
@@ -41,7 +41,7 @@ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
 	struct llist_node *first;
 
 	do {
-		new_last->next = first = ACCESS_ONCE(head->first);
+		new_last->next = first = READ_ONCE(head->first);
 	} while (cmpxchg(&head->first, first, new_first) != first);
 
 	return !first;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 86c3385b9eb3..1746bae94d41 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -620,8 +620,8 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp
 
 	rcu_read_lock();
 	for (i = 0; i < depth; i++, d = p) {
-		p = ACCESS_ONCE(d->d_parent);
-		array[i] = ACCESS_ONCE(d->d_name.name);
+		p = READ_ONCE(d->d_parent);
+		array[i] = READ_ONCE(d->d_name.name);
 		if (p == d) {
 			if (i)
 				array[i] = "";