sched: Add TASK_WAKING

We're going to want to drop rq->lock in try_to_wake_up() for a
longer period of time, however we also want to deal with concurrent
waking of the same task, which is currently handled by holding
rq->lock.

So introduce a new TASK state, namely TASK_WAKING, which indicates
someone is already waking the task (other wakers will fail p->state
& state).

We also keep preemption disabled over the whole ttwu().

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

2 files changed, 16 insertions, 16 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5d3c9900943e..3b0ca66bd6ce 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -190,6 +190,7 @@ extern unsigned long long time_sync_thresh;
 /* in tsk->state again */
 #define TASK_DEAD               64
 #define TASK_WAKEKILL           128
+#define TASK_WAKING             256
 
 /* Convenience macros for the sake of set_task_state */
 #define TASK_KILLABLE           (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
diff --git a/kernel/sched.c b/kernel/sched.c
index 32b7a81230c2..fc6fda881d2e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2310,7 +2310,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 {
         int cpu, orig_cpu, this_cpu, success = 0;
         unsigned long flags;
-        long old_state;
         struct rq *rq;
 
         if (!sched_feat(SYNC_WAKEUPS))
@@ -2332,11 +2331,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
         }
 #endif
 
+        this_cpu = get_cpu();
+
         smp_wmb();
         rq = task_rq_lock(p, &flags);
         update_rq_clock(rq);
-        old_state = p->state;
-        if (!(old_state & state))
+        if (!(p->state & state))
                 goto out;
 
         if (p->se.on_rq)
@@ -2344,27 +2344,25 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 
         cpu = task_cpu(p);
         orig_cpu = cpu;
-        this_cpu = smp_processor_id();
 
 #ifdef CONFIG_SMP
         if (unlikely(task_running(rq, p)))
                 goto out_activate;
 
+        /*
+         * In order to handle concurrent wakeups and release the rq->lock
+         * we put the task in TASK_WAKING state.
+         */
+        p->state = TASK_WAKING;
+        task_rq_unlock(rq, &flags);
+
         cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, sync);
-        if (cpu != orig_cpu) {
+        if (cpu != orig_cpu)
                 set_task_cpu(p, cpu);
-                task_rq_unlock(rq, &flags);
-                /* might preempt at this point */
-                rq = task_rq_lock(p, &flags);
-                old_state = p->state;
-                if (!(old_state & state))
-                        goto out;
-                if (p->se.on_rq)
-                        goto out_running;
 
-                this_cpu = smp_processor_id();
-                cpu = task_cpu(p);
-        }
+        rq = task_rq_lock(p, &flags);
+        WARN_ON(p->state != TASK_WAKING);
+        cpu = task_cpu(p);
 
 #ifdef CONFIG_SCHEDSTATS
         schedstat_inc(rq, ttwu_count);
@@ -2422,6 +2420,7 @@ out_running:
 #endif
 out:
         task_rq_unlock(rq, &flags);
+        put_cpu();
 
         return success;
 }