sched: Simplify the reacquire_kernel_lock() logic

- Contrary to what 6d558c3a says, there is no need to reload
  prev = rq->curr after the context switch. You always schedule
  back to where you came from, prev must be equal to current
  even if cpu/rq was changed.

- This also means reacquire_kernel_lock() can use prev instead
  of current.

- No need to reassign switch_count if reacquire_kernel_lock()
  reports need_resched(), we can just move the initial assignment
  down, under the "need_resched_nonpreemptible:" label.

- Try to update the comment after context_switch().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100519125711.GA30199@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 3abd8f780dae98968bf4cf00d5c24ab1bc846268..f37a9618fac38e6c23679efa51168f9800390886 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3636,7 +3636,6 @@ need_resched:
        rq = cpu_rq(cpu);
        rcu_note_context_switch(cpu);
        prev = rq->curr;
-       switch_count = &prev->nivcsw;
 
        release_kernel_lock(prev);
 need_resched_nonpreemptible:
@@ -3649,6 +3648,7 @@ need_resched_nonpreemptible:
        raw_spin_lock_irq(&rq->lock);
        clear_tsk_need_resched(prev);
 
+       switch_count = &prev->nivcsw;
        if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                if (unlikely(signal_pending_state(prev->state, prev))) {
                        prev->state = TASK_RUNNING;
@@ -3689,8 +3689,10 @@ need_resched_nonpreemptible:
 
                context_switch(rq, prev, next); /* unlocks the rq */
                /*
-                * the context switch might have flipped the stack from under
-                * us, hence refresh the local variables.
+                * The context switch have flipped the stack from under us
+                * and restored the local variables which were saved when
+                * this task called schedule() in the past. prev == current
+                * is still correct, but it can be moved to another cpu/rq.
                 */
                cpu = smp_processor_id();
                rq = cpu_rq(cpu);
@@ -3699,11 +3701,8 @@ need_resched_nonpreemptible:
 
        post_schedule(rq);
 
-       if (unlikely(reacquire_kernel_lock(current) < 0)) {
-               prev = rq->curr;
-               switch_count = &prev->nivcsw;
+       if (unlikely(reacquire_kernel_lock(prev)))
                goto need_resched_nonpreemptible;
-       }
 
        preempt_enable_no_resched();
        if (need_resched())