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

Pull scheduler changes from Ingo Molnar:
 "Main changes:

   - scheduler side full-dynticks (user-space execution is undisturbed
     and receives no timer IRQs) preparation changes that convert the
     cputime accounting code to be full-dynticks ready, from Frederic
     Weisbecker.

   - Initial sched.h split-up changes, by Clark Williams

   - select_idle_sibling() performance improvement by Mike Galbraith:

        " 1 tbench pair (worst case) in a 10 core + SMT package:

          pre   15.22 MB/sec 1 procs
          post 252.01 MB/sec 1 procs "

  - sched_rr_get_interval() ABI fix/change.  We think this detail is not
    used by apps (so it's not an ABI in practice), but lets keep it
    under observation.

  - misc RT scheduling cleanups, optimizations"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  sched/rt: Add <linux/sched/rt.h> header to <linux/init_task.h>
  cputime: Remove irqsave from seqlock readers
  sched, powerpc: Fix sched.h split-up build failure
  cputime: Restore CPU_ACCOUNTING config defaults for PPC64
  sched/rt: Move rt specific bits into new header file
  sched/rt: Add a tuning knob to allow changing SCHED_RR timeslice
  sched: Move sched.h sysctl bits into separate header
  sched: Fix signedness bug in yield_to()
  sched: Fix select_idle_sibling() bouncing cow syndrome
  sched/rt: Further simplify pick_rt_task()
  sched/rt: Do not account zero delta_exec in update_curr_rt()
  cputime: Safely read cputime of full dynticks CPUs
  kvm: Prepare to add generic guest entry/exit callbacks
  cputime: Use accessors to read task cputime stats
  cputime: Allow dynamic switch between tick/virtual based cputime accounting
  cputime: Generic on-demand virtual cputime accounting
  cputime: Move default nsecs_to_cputime() to jiffies based cputime file
  cputime: Librarize per nsecs resolution cputime definitions
  cputime: Avoid multiplication overflow on utime scaling
  context_tracking: Export context state for generic vtime
  ...

Fix up conflict in kernel/context_tracking.c due to comment additions.

29 files changed, 462 insertions, 123 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 051e071a06e7..e8b1627ab9c7 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -566,6 +566,7 @@ out:
 void acct_collect(long exitcode, int group_dead)
 {
         struct pacct_struct *pacct = &current->signal->pacct;
+        cputime_t utime, stime;
         unsigned long vsize = 0;
 
         if (group_dead && current->mm) {
@@ -593,8 +594,9 @@ void acct_collect(long exitcode, int group_dead)
                 pacct->ac_flag |= ACORE;
         if (current->flags & PF_SIGNALED)
                 pacct->ac_flag |= AXSIG;
-        pacct->ac_utime += current->utime;
-        pacct->ac_stime += current->stime;
+        task_cputime(current, &utime, &stime);
+        pacct->ac_utime += utime;
+        pacct->ac_stime += stime;
         pacct->ac_minflt += current->min_flt;
         pacct->ac_majflt += current->maj_flt;
         spin_unlock_irq(&current->sighand->siglock);
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index d566aba7e801..65349f07b878 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -15,26 +15,13 @@
  */
 
 #include <linux/context_tracking.h>
+#include <linux/kvm_host.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
-#include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/export.h>
 
-struct context_tracking {
-        /*
-         * When active is false, probes are unset in order
-         * to minimize overhead: TIF flags are cleared
-         * and calls to user_enter/exit are ignored. This
-         * may be further optimized using static keys.
-         */
-        bool active;
-        enum {
-                IN_KERNEL = 0,
-                IN_USER,
-        } state;
-};
-
-static DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
+DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
         .active = true,
 #endif
@@ -70,7 +57,6 @@ void user_enter(void)
         local_irq_save(flags);
         if (__this_cpu_read(context_tracking.active) &&
             __this_cpu_read(context_tracking.state) != IN_USER) {
-                __this_cpu_write(context_tracking.state, IN_USER);
                 /*
                  * At this stage, only low level arch entry code remains and
                  * then we'll run in userspace. We can assume there won't be
@@ -78,7 +64,9 @@ void user_enter(void)
                  * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
                  * on the tick.
                  */
+                vtime_user_enter(current);
                 rcu_user_enter();
+                __this_cpu_write(context_tracking.state, IN_USER);
         }
         local_irq_restore(flags);
 }
@@ -104,16 +92,35 @@ void user_exit(void)
 
         local_irq_save(flags);
         if (__this_cpu_read(context_tracking.state) == IN_USER) {
-                __this_cpu_write(context_tracking.state, IN_KERNEL);
                 /*
                  * We are going to run code that may use RCU. Inform
                  * RCU core about that (ie: we may need the tick again).
                  */
                 rcu_user_exit();
+                vtime_user_exit(current);
+                __this_cpu_write(context_tracking.state, IN_KERNEL);
         }
         local_irq_restore(flags);
 }
 
+void guest_enter(void)
+{
+        if (vtime_accounting_enabled())
+                vtime_guest_enter(current);
+        else
+                __guest_enter();
+}
+EXPORT_SYMBOL_GPL(guest_enter);
+
+void guest_exit(void)
+{
+        if (vtime_accounting_enabled())
+                vtime_guest_exit(current);
+        else
+                __guest_exit();
+}
+EXPORT_SYMBOL_GPL(guest_exit);
+
 
 /**
  * context_tracking_task_switch - context switch the syscall callbacks
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3046a503242c..e5d5e8e1e030 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -224,11 +224,13 @@ void clear_tasks_mm_cpumask(int cpu)
 static inline void check_for_tasks(int cpu)
 {
         struct task_struct *p;
+        cputime_t utime, stime;
 
         write_lock_irq(&tasklist_lock);
         for_each_process(p) {
+                task_cputime(p, &utime, &stime);
                 if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&