rcu: Deinline rcu_read_lock_sched_held() if DEBUG_LOCK_ALLOC

DEBUG_LOCK_ALLOC=y is not a production setting, but it is
not very unusual either. Many developers routinely
use kernels built with it enabled.

Apart from being selected by hand, it is also auto-selected by
PROVE_LOCKING "Lock debugging: prove locking correctness" and
LOCK_STAT "Lock usage statistics" config options.
LOCK STAT is necessary for "perf lock" to work.

I wouldn't spend too much time optimizing it, but this particular
function has a very large cost in code size: when it is deinlined,
code size decreases by 830,000 bytes:

    text     data      bss       dec     hex filename
85674192 22294776 20627456 128596424 7aa39c8 vmlinux.before
84837612 22294424 20627456 127759492 79d7484 vmlinux

(with this config: http://busybox.net/~vda/kernel_config)

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Lai Jiangshan <laijs@cn.fujitsu.com>
CC: Tejun Heo <tj@kernel.org>
CC: Oleg Nesterov <oleg@redhat.com>
CC: linux-kernel@vger.kernel.org
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

include/linux/rcupdate.h

@@ -469,46 +469,10 @@ int rcu_read_lock_bh_held(void);
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns 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
- * of preemption (including disabling irqs) counts as an RCU-sched
- * read-side critical section.  This is useful for debug checks in functions
- * that required that they be called within an RCU-sched read-side
- * critical section.
- *
- * 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.
- *
- * Similarly, we avoid claiming an SRCU read lock held if the current
- * CPU is offline.
+ * critical section unless it can prove otherwise.
  */
 #ifdef CONFIG_PREEMPT_COUNT
-static inline int rcu_read_lock_sched_held(void)
-{
-	int lockdep_opinion = 0;
-
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
-	if (debug_locks)
-		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
-	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
-}
+int rcu_read_lock_sched_held(void);
 #else /* #ifdef CONFIG_PREEMPT_COUNT */
 static inline int rcu_read_lock_sched_held(void)
 {

kernel/rcu/update.c

@@ -62,6 +62,55 @@ MODULE_ALIAS("rcupdate");
 
 module_param(rcu_expedited, int, 0);
 
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT)
+/**
+ * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns 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
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.  This is useful for debug checks in functions
+ * that required that they be called within an RCU-sched read-side
+ * critical section.
+ *
+ * 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.
+ *
+ * Similarly, we avoid claiming an SRCU read lock held if the current
+ * CPU is offline.
+ */
+int rcu_read_lock_sched_held(void)
+{
+	int lockdep_opinion = 0;
+
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	if (!rcu_is_watching())
+		return 0;
+	if (!rcu_lockdep_current_cpu_online())
+		return 0;
+	if (debug_locks)
+		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
+	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
+}
+EXPORT_SYMBOL(rcu_read_lock_sched_held);
+#endif
+
 #ifndef CONFIG_TINY_RCU
 
 static atomic_t rcu_expedited_nesting =