rcu: Add support for consolidated-RCU reader checking

This commit adds RCU-reader checks to list_for_each_entry_rcu() and
hlist_for_each_entry_rcu().  These checks are optional, and are indicated
by a lockdep expression passed to a new optional argument to these two
macros.  If this optional lockdep expression is omitted, these two macros
act as before, checking for an RCU read-side critical section.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Update to eliminate return within macro and update comment. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>

include/linux/rculist.h

@@ -40,6 +40,24 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
  */
 #define list_next_rcu(list)	(*((struct list_head __rcu **)(&(list)->next)))
 
+/*
+ * Check during list traversal that we are within an RCU reader
+ */
+
+#define check_arg_count_one(dummy)
+
+#ifdef CONFIG_PROVE_RCU_LIST
+#define __list_check_rcu(dummy, cond, extra...)				\
+	({								\
+	check_arg_count_one(extra);					\
+	RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(),		\
+			 "RCU-list traversed in non-reader section!");	\
+	 })
+#else
+#define __list_check_rcu(dummy, cond, extra...)				\
+	({ check_arg_count_one(extra); })
+#endif
+
 /*
  * Insert a new entry between two known consecutive entries.
  *
@@ -343,13 +361,15 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the list_head within the struct.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as list_add_rcu()
  * as long as the traversal is guarded by rcu_read_lock().
  */
-#define list_for_each_entry_rcu(pos, head, member) \
-	for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
+#define list_for_each_entry_rcu(pos, head, member, cond...)		\
+	for (__list_check_rcu(dummy, ## cond, 0),			\
+	     pos = list_entry_rcu((head)->next, typeof(*pos), member);	\
 		&pos->member != (head);					\
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
@@ -616,13 +636,15 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the hlist_node within the struct.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as hlist_add_head_rcu()
  * as long as the traversal is guarded by rcu_read_lock().
  */
-#define hlist_for_each_entry_rcu(pos, head, member)			\
-	for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
+#define hlist_for_each_entry_rcu(pos, head, member, cond...)		\
+	for (__list_check_rcu(dummy, ## cond, 0),			\
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
 			typeof(*(pos)), member);			\
 		pos;							\
 		pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\

include/linux/rcupdate.h

@@ -221,6 +221,7 @@ int debug_lockdep_rcu_enabled(void);
 int rcu_read_lock_held(void);
 int rcu_read_lock_bh_held(void);
 int rcu_read_lock_sched_held(void);
+int rcu_read_lock_any_held(void);
 
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
@@ -241,6 +242,12 @@ static inline int rcu_read_lock_sched_held(void)
 {
 	return !preemptible();
 }
+
+static inline int rcu_read_lock_any_held(void)
+{
+	return !preemptible();
+}
+
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 #ifdef CONFIG_PROVE_RCU

kernel/rcu/Kconfig.debug

@@ -8,6 +8,17 @@ menu "RCU Debugging"
 config PROVE_RCU
 	def_bool PROVE_LOCKING
 
+config PROVE_RCU_LIST
+	bool "RCU list lockdep debugging"
+	depends on PROVE_RCU && RCU_EXPERT
+	default n
+	help
+	  Enable RCU lockdep checking for list usages. By default it is
+	  turned off since there are several list RCU users that still
+	  need to be converted to pass a lockdep expression. To prevent
+	  false-positive splats, we keep it default disabled but once all
+	  users are converted, we can remove this config option.
+
 config TORTURE_TEST
 	tristate
 	default n

kernel/rcu/update.c

@@ -61,9 +61,15 @@ module_param(rcu_normal_after_boot, int, 0);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 /**
- * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+ * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section?
+ * @ret:	Best guess answer if lockdep cannot be relied on
  *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * Returns true if lockdep must be ignored, in which case *ret contains
+ * the best guess described below.  Otherwise returns false, in which
+ * case *ret tells the caller nothing and the caller should instead
+ * consult lockdep.
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.  Note that disabling
@@ -75,30 +81,44 @@ module_param(rcu_normal_after_boot, int, 0);
  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
  *
- * Note that if the CPU is in the idle loop from an RCU point of
- * view (ie: that we are in the section between rcu_idle_enter() and
- * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
- * did an rcu_read_lock().  The reason for this is that RCU ignores CPUs
- * that are in such a section, considering these as in extended quiescent
- * state, so such a CPU is effectively never in an RCU read-side critical
- * section regardless of what RCU primitives it invokes.  This state of
- * affairs is required --- we need to keep an RCU-free window in idle
- * where the CPU may possibly enter into low power mode. This way we can
- * notice an extended quiescent state to other CPUs that started a grace
- * period. Otherwise we would delay any grace period as long as we run in
- * the idle task.
+ * Note that if the CPU is in the idle loop from an RCU point of view (ie:
+ * that we are in the section between rcu_idle_enter() and rcu_idle_exit())
+ * then rcu_read_lock_held() sets *ret to false even if the CPU did an
+ * rcu_read_lock().  The reason for this is that RCU ignores CPUs that are
+ * in such a section, considering these as in extended quiescent state,
+ * so such a CPU is effectively never in an RCU read-side critical section
+ * regardless of what RCU primitives it invokes.  This state of affairs is
+ * required --- we need to keep an RCU-free window in idle where the CPU may
+ * possibly enter into low power mode. This way we can notice an extended
+ * quiescent state to other CPUs that started a grace period. Otherwise
+ * we would delay any grace period as long as we run in the idle task.
  *
- * Similarly, we avoid claiming an SRCU read lock held if the current
+ * Similarly, we avoid claiming an RCU read lock held if the current
  * CPU is offline.
  */
+static bool rcu_read_lock_held_common(bool *ret)
+{
+	if (!debug_lockdep_rcu_enabled()) {
+		*ret = 1;
+		return true;
+	}
+	if (!rcu_is_watching()) {
+		*ret = 0;
+		return true;
+	}
+	if (!rcu_lockdep_current_cpu_online()) {
+		*ret = 0;
+		return true;
+	}
+	return false;
+}
+
 int rcu_read_lock_sched_held(void)
 {
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
 	return lock_is_held(&rcu_sched_lock_map) || !preemptible();
 }
 EXPORT_SYMBOL(rcu_read_lock_sched_held);
@@ -257,12 +277,10 @@ NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
  */
 int rcu_read_lock_held(void)
 {
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
 	return lock_is_held(&rcu_lock_map);
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_held);
@@ -284,16 +302,28 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_held);
  */
 int rcu_read_lock_bh_held(void)
 {
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
 	return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 
+int rcu_read_lock_any_held(void)
+{
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
+	if (lock_is_held(&rcu_lock_map) ||
+	    lock_is_held(&rcu_bh_lock_map) ||
+	    lock_is_held(&rcu_sched_lock_map))
+		return 1;
+	return !preemptible();
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_any_held);
+
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /**