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

Pull scheduler changes from Ingo Molnar:
 "Continued quest to clean up and enhance the cputime code by Frederic
  Weisbecker, in preparation for future tickless kernel features.

  Other than that, smallish changes."

Fix up trivial conflicts due to additions next to each other in arch/{x86/}Kconfig

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  cputime: Make finegrained irqtime accounting generally available
  cputime: Gather time/stats accounting config options into a single menu
  ia64: Reuse system and user vtime accounting functions on task switch
  ia64: Consolidate user vtime accounting
  vtime: Consolidate system/idle context detection
  cputime: Use a proper subsystem naming for vtime related APIs
  sched: cpu_power: enable ARCH_POWER
  sched/nohz: Clean up select_nohz_load_balancer()
  sched: Fix load avg vs. cpu-hotplug
  sched: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW
  sched: Fix nohz_idle_balance()
  sched: Remove useless code in yield_to()
  sched: Add time unit suffix to sched sysctl knobs
  sched/debug: Limit sd->*_idx range on sysctl
  sched: Remove AFFINE_WAKEUPS feature flag
  s390: Remove leftover account_tick_vtime() header
  cputime: Consolidate vtime handling on context switch
  sched: Move cputime code to its own file
  cputime: Generalize CONFIG_VIRT_CPU_ACCOUNTING
  tile: Remove SD_PREFER_LOCAL leftover
  ...

11 files changed, 686 insertions, 705 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 2343c9eaaaf4..5a0e74d89a5a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1276,11 +1276,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
         p->irq_events = 0;
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-        p->hardirqs_enabled = 1;
-#else
         p->hardirqs_enabled = 0;
-#endif
         p->hardirq_enable_ip = 0;
         p->hardirq_enable_event = 0;
         p->hardirq_disable_ip = _THIS_IP_;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 173ea52f3af0..f06d249e103b 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
 obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3c4dec0594d6..c17747236438 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -740,126 +740,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
         dequeue_task(rq, p, flags);
 }
 
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-
-/*
- * There are no locks covering percpu hardirq/softirq time.
- * They are only modified in account_system_vtime, on corresponding CPU
- * with interrupts disabled. So, writes are safe.
- * 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 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);
-
-static DEFINE_PER_CPU(u64, irq_start_time);
-static int sched_clock_irqtime;
-
-void enable_sched_clock_irqtime(void)
-{
-        sched_clock_irqtime = 1;
-}
-
-void disable_sched_clock_irqtime(void)
-{
-        sched_clock_irqtime = 0;
-}
-
-#ifndef CONFIG_64BIT
-static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
-
-static inline void irq_time_write_begin(void)
-{
-        __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;
-
-        if (!sched_clock_irqtime)
-                return;
-
-        local_irq_save(flags);
-
-        cpu = smp_processor_id();
-        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
-         * in that case, so as not to confuse scheduler with a special task
-         * that do not consume any time, but still wants to run.
-         */
-        if (hardirq_count())
-                __this_cpu_add(cpu_hardirq_time, delta);
-        else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
-                __this_cpu_add(cpu_softirq_time, delta);
-
-        irq_time_write_end();
-        local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(account_system_vtime);
-
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
-{
-        if (unlikely(steal > NSEC_PER_SEC))
-                return div_u64(steal, TICK_NSEC);
-
-        return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
-
 static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
 /*
@@ -920,43 +800,6 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 #endif
 }
 
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-static int irqtime_account_hi_update(void)
-{
-        u64 *cpustat = kcpustat_this_cpu->cpustat;
-        unsigned long flags;
-        u64 latest_ns;
-        int ret = 0;
-
-        local_irq_save(flags);
-        latest_ns = this_cpu_read(cpu_hardirq_time);
-        if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
-                ret = 1;
-        local_irq_restore(flags);
-        return ret;
-}
-