rcu: Don't disable preemption for Tiny and Tree RCU readers

Because preempt_disable() maps to barrier() for non-debug builds,
it forces the compiler to spill and reload registers.  Because Tree
RCU and Tiny RCU now only appear in CONFIG_PREEMPT=n builds, these
barrier() instances generate needless extra code for each instance of
rcu_read_lock() and rcu_read_unlock().  This extra code slows down Tree
RCU and bloats Tiny RCU.

This commit therefore removes the preempt_disable() and preempt_enable()
from the non-preemptible implementations of __rcu_read_lock() and
__rcu_read_unlock(), respectively.  However, for debug purposes,
preempt_disable() and preempt_enable() are still invoked if
CONFIG_PREEMPT_COUNT=y, because this allows detection of sleeping inside
atomic sections in non-preemptible kernels.

However, Tiny and Tree RCU operates by coalescing all RCU read-side
critical sections on a given CPU that lie between successive quiescent
states.  It is therefore necessary to compensate for removing barriers
from __rcu_read_lock() and __rcu_read_unlock() by adding them to a
couple of the RCU functions invoked during quiescent states, namely to
rcu_all_qs() and rcu_note_context_switch().  However, note that the latter
is more paranoia than necessity, at least until link-time optimizations
become more aggressive.

This is based on an earlier patch by Paul E. McKenney, fixing
a bug encountered in kernels built with CONFIG_PREEMPT=n and
CONFIG_PREEMPT_COUNT=y.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

1 files changed, 9 insertions, 0 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b9d9e0249e2f..93c0f23c3e45 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -337,12 +337,14 @@ static void rcu_momentary_dyntick_idle(void)
  */
 void rcu_note_context_switch(void)
 {
+	barrier(); /* Avoid RCU read-side critical sections leaking down. */
 	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs();
 	rcu_preempt_note_context_switch();
 	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
 	trace_rcu_utilization(TPS("End context switch"));
+	barrier(); /* Avoid RCU read-side critical sections leaking up. */
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
@@ -353,12 +355,19 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
  * RCU flavors in desperate need of a quiescent state, which will normally
  * be none of them).  Either way, do a lightweight quiescent state for
  * all RCU flavors.
+ *
+ * The barrier() calls are redundant in the common case when this is
+ * called externally, but just in case this is called from within this
+ * file.
+ *
  */
 void rcu_all_qs(void)
 {
+	barrier(); /* Avoid RCU read-side critical sections leaking down. */
 	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
 	this_cpu_inc(rcu_qs_ctr);
+	barrier(); /* Avoid RCU read-side critical sections leaking up. */
 }
 EXPORT_SYMBOL_GPL(rcu_all_qs);