Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Fix the irqtime code for 32bit
  sched: Fix the irqtime code to deal with u64 wraps
  nohz: Fix get_next_timer_interrupt() vs cpu hotplug
  Sched: fix skip_clock_update optimization
  sched: Cure more NO_HZ load average woes

3 files changed, 245 insertions, 52 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 3b159c5991b7..5447dc7defa9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -273,6 +273,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
         setup_thread_stack(tsk, orig);
         clear_user_return_notifier(tsk);
+        clear_tsk_need_resched(tsk);
         stackend = end_of_stack(tsk);
         *stackend = STACK_END_MAGIC;    /* for overflow detection */
 
diff --git a/kernel/sched.c b/kernel/sched.c
index dc91a4d09ac3..456c99054160 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -636,22 +636,18 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
 
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
 {
-        if (!rq->skip_clock_update) {
-                int cpu = cpu_of(rq);
-                u64 irq_time;
+        s64 delta;
 
-                rq->clock = sched_clock_cpu(cpu);
-                irq_time = irq_time_cpu(cpu);
-                if (rq->clock - irq_time > rq->clock_task)
-                        rq->clock_task = rq->clock - irq_time;
+        if (rq->skip_clock_update)
+                return;
 
-                sched_irq_time_avg_update(rq, irq_time);
-        }
+        delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+        rq->clock += delta;
+        update_rq_clock_task(rq, delta);
 }
 
 /*
@@ -1924,10 +1920,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
  * They are read and saved off onto struct rq in update_rq_clock().
  * This may result in other CPU reading this CPU's irq time and can
  * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
  */
 static DEFINE_PER_CPU(u64, cpu_hardirq_time);
 static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1945,19 +1940,58 @@ void disable_sched_clock_irqtime(void)
         sched_clock_irqtime = 0;
 }
 
-static u64 irq_time_cpu(int cpu)
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
 {
-        if (!sched_clock_irqtime)
-                return 0;
+        __this_cpu_inc(irq_time_seq.sequence);
+        smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+        smp_wmb();
+        __this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+        u64 irq_time;
+        unsigned seq;
 
+        do {
+                seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+                irq_time = per_cpu(cpu_softirq_time, cpu) +
+                           per_cpu(cpu_hardirq_time, cpu);
+        } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+        return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
         return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
 }
+#endif /* CONFIG_64BIT */
 
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
 void account_system_vtime(struct task_struct *curr)
 {
         unsigned long flags;
+        s64 delta;
         int cpu;
-        u64 now, delta;
 
         if (!sched_clock_irqtime)
                 return;
@@ -1965,9 +1999,10 @@ void account_system_vtime(struct task_struct *curr)
         local_irq_save(flags);
 
         cpu = smp_processor_id();
-        now = sched_clock_cpu(cpu);
-        delta = now - per_cpu(irq_start_time, cpu);
-        per_cpu(irq_start_time, cpu) = now;
+        delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+        __this_cpu_add(irq_start_time, delta);
+
+        irq_time_write_begin();
         /*
          * We do not account for softirq time from ksoftirqd here.
          * We want to continue accounting softirq time to ksoftirqd thread
@@ -1975,33 +2010,55 @@ void account_system_vtime(struct task_struct *curr)
          * that do not consume any time, but still wants to run.
          */
         if (hardirq_count())
-                per_cpu(cpu_hardirq_time, cpu) += delta;
+                __this_cpu_add(cpu_hardirq_time, delta);
         else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
-                per_cpu(cpu_softirq_time, cpu) += delta;
+                __this_cpu_add(cpu_softirq_time, delta);
 
+        irq_time_write_end();
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-        if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
-                u64 delta_irq = curr_irq_time - rq->prev_irq_time;
-                rq->prev_irq_time = curr_irq_time;
-                sched_rt_avg_update(rq, delta_irq);
-        }
+        s64 irq_delta;
+
+        irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+        /*
+         * Since irq_time is only updated on {soft,}irq_exit, we might run into
+         * this case when a previous update_rq_clock() happened inside a
+         * {soft,}irq region.
+         *
+         * When this happens, we stop ->clock_task and only update the
+         * prev_irq_time stamp to account for the part that fit, so that a next
+         * update will consume the rest. This ensures ->clock_task is
+         * monotonic.
+         *
+         * It does however cause some slight miss-attribution of {soft,}irq
+         * time, a more accurate solution would be to update the irq_time using
+         * the current rq->clock timestamp, except that would require using
+         * atomic ops.
+         */
+        if (irq_delta > delta)
+                irq_delta = delta;
+
+        rq->prev_irq_time += irq_delta;
+        delta -= irq_delta;
+        rq->clock_task += delta;