mutex: preemption fixes

The problem is that dropping the spinlock right before schedule is a voluntary
preemption point and can cause a schedule, right after which we schedule again.

Fix this inefficiency by keeping preemption disabled until we schedule, do this
by explicity disabling preemption and providing a schedule() variant that
assumes preemption is already disabled.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 12 insertions, 4 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4cae9b81a1f8..9f0b372cfa6f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -328,6 +328,7 @@ extern signed long schedule_timeout(signed long timeout);
 extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
+asmlinkage void __schedule(void);
 asmlinkage void schedule(void);
 
 struct nsproxy;
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 357c6d221efe..524ffc33dc05 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -131,6 +131,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
         struct mutex_waiter waiter;
         unsigned long flags;
 
+        preempt_disable();
         spin_lock_mutex(&lock->wait_lock, flags);
 
         debug_mutex_lock_common(lock, &waiter);
@@ -170,13 +171,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                         spin_unlock_mutex(&lock->wait_lock, flags);
 
                         debug_mutex_free_waiter(&waiter);
+                        preempt_enable();
                         return -EINTR;
                 }
                 __set_task_state(task, state);
 
                 /* didnt get the lock, go to sleep: */
                 spin_unlock_mutex(&lock->wait_lock, flags);
-                schedule();
+                __schedule();
                 spin_lock_mutex(&lock->wait_lock, flags);
         }
 
@@ -193,6 +195,7 @@ done:
         spin_unlock_mutex(&lock->wait_lock, flags);
 
         debug_mutex_free_waiter(&waiter);
+        preempt_enable();
 
         return 0;
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index 8be2c13b50d0..b001c133c359 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4538,15 +4538,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 /*
  * schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+asmlinkage void __sched __schedule(void)
 {
         struct task_struct *prev, *next;
         unsigned long *switch_count;
         struct rq *rq;
         int cpu;
 
-need_resched:
-        preempt_disable();
         cpu = smp_processor_id();
         rq = cpu_rq(cpu);
         rcu_qsctr_inc(cpu);
@@ -4603,7 +4601,13 @@ need_resched_nonpreemptible:
 
         if (unlikely(reacquire_kernel_lock(current) < 0))
                 goto need_resched_nonpreemptible;
+}
 
+asmlinkage void __sched schedule(void)
+{
+need_resched:
+        preempt_disable();
+        __schedule();
         preempt_enable_no_resched();
         if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
                 goto need_resched;