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

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

   - Updates to use cond_resched() instead of cond_resched_rcu_qs()
     where feasible (currently everywhere except in kernel/rcu and in
     kernel/torture.c). Also a couple of fixes to avoid sending IPIs to
     offline CPUs.

   - Updates to simplify RCU's dyntick-idle handling.

   - Updates to remove almost all uses of smp_read_barrier_depends() and
     read_barrier_depends().

   - Torture-test updates.

   - Miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  torture: Save a line in stutter_wait(): while -> for
  torture: Eliminate torture_runnable and perf_runnable
  torture: Make stutter less vulnerable to compilers and races
  locking/locktorture: Fix num reader/writer corner cases
  locking/locktorture: Fix rwsem reader_delay
  torture: Place all torture-test modules in one MAINTAINERS group
  rcutorture/kvm-build.sh: Skip build directory check
  rcutorture: Simplify functions.sh include path
  rcutorture: Simplify logging
  rcutorture/kvm-recheck-*: Improve result directory readability check
  rcutorture/kvm.sh: Support execution from any directory
  rcutorture/kvm.sh: Use consistent help text for --qemu-args
  rcutorture/kvm.sh: Remove unused variable, `alldone`
  rcutorture: Remove unused script, config2frag.sh
  rcutorture/configinit: Fix build directory error message
  rcutorture: Preempt RCU-preempt readers more vigorously
  torture: Reduce #ifdefs for preempt_schedule()
  rcu: Remove have_rcu_nocb_mask from tree_plugin.h
  rcu: Add comment giving debug strategy for double call_rcu()
  tracing, rcu: Hide trace event rcu_nocb_wake when not used
  ...

2 files changed, 16 insertions, 29 deletions

diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index b77d51da8c73..c6659cb37033 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -38,12 +38,10 @@ begin_node:
 	if (assoc_array_ptr_is_shortcut(cursor)) {
 		/* Descend through a shortcut */
 		shortcut = assoc_array_ptr_to_shortcut(cursor);
-		smp_read_barrier_depends();
-		cursor = READ_ONCE(shortcut->next_node);
+		cursor = READ_ONCE(shortcut->next_node); /* Address dependency. */
 	}
 
 	node = assoc_array_ptr_to_node(cursor);
-	smp_read_barrier_depends();
 	slot = 0;
 
 	/* We perform two passes of each node.
@@ -55,15 +53,12 @@ begin_node:
 	 */
 	has_meta = 0;
 	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
-		ptr = READ_ONCE(node->slots[slot]);
+		ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */
 		has_meta |= (unsigned long)ptr;
 		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
-			 * actually going to dereference it.
+			/* We need a barrier between the read of the pointer,
+			 * which is supplied by the above READ_ONCE().
 			 */
-			smp_read_barrier_depends();
-
 			/* Invoke the callback */
 			ret = iterator(assoc_array_ptr_to_leaf(ptr),
 				       iterator_data);
@@ -86,10 +81,8 @@ begin_node:
 
 continue_node:
 	node = assoc_array_ptr_to_node(cursor);
-	smp_read_barrier_depends();
-
 	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
-		ptr = READ_ONCE(node->slots[slot]);
+		ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */
 		if (assoc_array_ptr_is_meta(ptr)) {
 			cursor = ptr;
 			goto begin_node;
@@ -98,16 +91,15 @@ continue_node:
 
 finished_node:
 	/* Move up to the parent (may need to skip back over a shortcut) */
-	parent = READ_ONCE(node->back_pointer);
+	parent = READ_ONCE(node->back_pointer); /* Address dependency. */
 	slot = node->parent_slot;
 	if (parent == stop)
 		return 0;
 
 	if (assoc_array_ptr_is_shortcut(parent)) {
 		shortcut = assoc_array_ptr_to_shortcut(parent);
-		smp_read_barrier_depends();
 		cursor = parent;
-		parent = READ_ONCE(shortcut->back_pointer);
+		parent = READ_ONCE(shortcut->back_pointer); /* Address dependency. */
 		slot = shortcut->parent_slot;
 		if (parent == stop)
 			return 0;
@@ -147,7 +139,7 @@ int assoc_array_iterate(const struct assoc_array *array,
 					void *iterator_data),
 			void *iterator_data)
 {
-	struct assoc_array_ptr *root = READ_ONCE(array->root);
+	struct assoc_array_ptr *root = READ_ONCE(array->root); /* Address dependency. */
 
 	if (!root)
 		return 0;
@@ -194,7 +186,7 @@ assoc_array_walk(const struct assoc_array *array,
 
 	pr_devel("-->%s()\n", __func__);
 
-	cursor = READ_ONCE(array->root);
+	cursor = READ_ONCE(array->root);  /* Address dependency. */
 	if (!cursor)
 		return assoc_array_walk_tree_empty;
 
@@ -216,11 +208,9 @@ jumped:
 
 consider_node:
 	node = assoc_array_ptr_to_node(cursor);
-	smp_read_barrier_depends();
-
 	slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
 	slot &= ASSOC_ARRAY_FAN_MASK;
-	ptr = READ_ONCE(node->slots[slot]);
+	ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */
 
 	pr_devel("consider slot %x [ix=%d type=%lu]\n",
 		 slot, level, (unsigned long)ptr & 3);
@@ -254,7 +244,6 @@ consider_node:
 	cursor = ptr;
 follow_shortcut:
 	shortcut = assoc_array_ptr_to_shortcut(cursor);
-	smp_read_barrier_depends();
 	pr_devel("shortcut to %d\n", shortcut->skip_to_level);
 	sc_level = level + ASSOC_ARRAY_LEVEL_STEP;
 	BUG_ON(sc_level > shortcut->skip_to_level);
@@ -294,7 +283,7 @@ follow_shortcut:
 	} while (sc_level < shortcut->skip_to_level);
 
 	/* The shortcut matches the leaf's index to this point. */
-	cursor = READ_ONCE(shortcut->next_node);
+	cursor = READ_ONCE(shortcut->next_node); /* Address dependency. */
 	if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) {
 		level = sc_level;
 		goto jumped;
@@ -331,20 +320,18 @@ void *assoc_array_find(const struct assoc_array *array,
 		return NULL;
 
 	node = result.terminal_node.node;
-	smp_read_barrier_depends();
 
 	/* If the target key is available to us, it's has to be pointed to by
 	 * the terminal node.
 	 */
 	for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
-		ptr = READ_ONCE(node->slots[slot]);
+		ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */
 		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
 			 * actually going to dereference it.
 			 */
 			leaf = assoc_array_ptr_to_leaf(ptr);
-			smp_read_barrier_depends();
 			if (ops->compare_object(leaf, index_key))
 				return (void *)leaf;
 		}
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index fe03c6d52761..30e7dd88148b 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -197,10 +197,10 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 	atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
 
 	/*
-	 * Restore per-cpu operation.  smp_store_release() is paired with
-	 * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
-	 * that the zeroing is visible to all percpu accesses which can see
-	 * the following __PERCPU_REF_ATOMIC clearing.
+	 * Restore per-cpu operation.  smp_store_release() is paired
+	 * with READ_ONCE() in __ref_is_percpu() and guarantees that the
+	 * zeroing is visible to all percpu accesses which can see the
+	 * following __PERCPU_REF_ATOMIC clearing.
 	 */
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(percpu_count, cpu) = 0;