timers: fix TIMER_ABSTIME for process wide cpu timers

The POSIX timer interface allows for absolute time expiry values through the
TIMER_ABSTIME flag, therefore we have to synchronize the timer to the clock
every time we start it.

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

include/linux/sched.h

@@ -2201,18 +2201,7 @@ static inline int spin_needbreak(spinlock_t *lock)
  * Thread group CPU time accounting.
  */
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
-
-static inline
-void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
-{
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cputimer->lock, flags);
-	cputimer->running = 1;
-	*times = cputimer->cputime;
-	spin_unlock_irqrestore(&cputimer->lock, flags);
-}
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
 static inline void thread_group_cputime_init(struct signal_struct *sig)
 {

kernel/posix-cpu-timers.c

@@ -261,6 +261,40 @@ out:
 	rcu_read_unlock();
 }
 
+static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+{
+	if (cputime_gt(b->utime, a->utime))
+		a->utime = b->utime;
+
+	if (cputime_gt(b->stime, a->stime))
+		a->stime = b->stime;
+
+	if (b->sum_exec_runtime > a->sum_exec_runtime)
+		a->sum_exec_runtime = b->sum_exec_runtime;
+}
+
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct task_cputime sum;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cputimer->lock, flags);
+	if (!cputimer->running) {
+		cputimer->running = 1;
+		/*
+		 * The POSIX timer interface allows for absolute time expiry
+		 * values through the TIMER_ABSTIME flag, therefore we have
+		 * to synchronize the timer to the clock every time we start
+		 * it.
+		 */
+		thread_group_cputime(tsk, &sum);
+		update_gt_cputime(&cputimer->cputime, &sum);
+	}
+	*times = cputimer->cputime;
+	spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.