commit cba6d0d64ee53772b285d0c0c288deefbeaf7775
author Paul E. McKenney <paulmck@linux.vnet.ibm.com> Mon Jul 02 07:08:42 2012 -0700
committer Paul E. McKenney <paulmck@linux.vnet.ibm.com> Mon Jul 02 11:39:19 2012 -0700
tree b2d3de62d15a77d23708c1af6f188c86f0d87fb9
parent 6887a4131da3adaab011613776d865f4bcfb5678

Revert "rcu: Move PREEMPT_RCU preemption to switch_to() invocation"

This reverts commit 616c310e83b872024271c915c1b9ab505b9efad9.
(Move PREEMPT_RCU preemption to switch_to() invocation).
Testing by Sasha Levin <levinsasha928@gmail.com> showed that this
can result in deadlock due to invoking the scheduler when one of
the runqueue locks is held.  Because this commit was simply a
performance optimization, revert it.

Reported-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Sasha Levin <levinsasha928@gmail.com>

kernel/rcutree.c

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 38ecdda..4b97bba 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -201,6 +201,7 @@
 {
 	trace_rcu_utilization("Start context switch");
 	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch(cpu);
 	trace_rcu_utilization("End context switch");
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);

kernel/rcutree.h

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index ea05649..19b61ac 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -444,6 +444,7 @@
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,

kernel/rcutree_plugin.h

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 5271a02..3e48994 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@
  *
  * Caller must disable preemption.
  */
-void rcu_preempt_note_context_switch(void)
+static void rcu_preempt_note_context_switch(int cpu)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
@@ -164,7 +164,7 @@
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = __this_cpu_ptr(rcu_preempt_state.rda);
+		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@
 	 * means that we continue to block the current grace period.
 	 */
 	local_irq_save(flags);
-	rcu_preempt_qs(smp_processor_id());
+	rcu_preempt_qs(cpu);
 	local_irq_restore(flags);
 }
 
@@ -1002,6 +1002,14 @@
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
+ * Because preemptible RCU does not exist, we never have to check for
+ * CPUs being in quiescent states.
+ */
+static void rcu_preempt_note_context_switch(int cpu)
+{
+}
+
+/*
  * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */

kernel/sched/core.c

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d5594a4..eaead2d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2081,7 +2081,6 @@
 #endif
 
 	/* Here we just switch the register state and the stack. */
-	rcu_switch_from(prev);
 	switch_to(prev, next, prev);
 
 	barrier();