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
  ...

4 files changed, 36 insertions, 44 deletions

diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 3b4b4a8da92..c1f267694ac 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -197,12 +197,6 @@ struct cpu_usage {
 
 DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
 
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING)
-#define account_process_vtime(tsk)              account_process_tick(tsk, 0)
-#else
-#define account_process_vtime(tsk)              do { } while (0)
-#endif
-
 extern void secondary_cpu_time_init(void);
 
 DECLARE_PER_CPU(u64, decrementers_next_tb);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1a1f2ddfb58..e9cb51f5f80 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -514,9 +514,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
         local_irq_save(flags);
 
-        account_system_vtime(current);
-        account_process_vtime(current);
-
         /*
          * We can't take a PMU exception inside _switch() since there is a
          * window where the kernel stack SLB and the kernel stack are out
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e49e93191b6..eaa9d0e6abc 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -291,13 +291,12 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
-void account_system_vtime(struct task_struct *tsk)
+static u64 vtime_delta(struct task_struct *tsk,
+                        u64 *sys_scaled, u64 *stolen)
 {
-        u64 now, nowscaled, delta, deltascaled;
-        unsigned long flags;
-        u64 stolen, udelta, sys_scaled, user_scaled;
+        u64 now, nowscaled, deltascaled;
+        u64 udelta, delta, user_scaled;
 
-        local_irq_save(flags);
         now = mftb();
         nowscaled = read_spurr(now);
         get_paca()->system_time += now - get_paca()->starttime;
@@ -305,7 +304,7 @@ void account_system_vtime(struct task_struct *tsk)
         deltascaled = nowscaled - get_paca()->startspurr;
         get_paca()->startspurr = nowscaled;
 
-        stolen = calculate_stolen_time(now);
+        *stolen = calculate_stolen_time(now);
 
         delta = get_paca()->system_time;
         get_paca()->system_time = 0;
@@ -322,35 +321,45 @@ void account_system_vtime(struct task_struct *tsk)
          * the user ticks get saved up in paca->user_time_scaled to be
          * used by account_process_tick.
          */
-        sys_scaled = delta;
+        *sys_scaled = delta;
         user_scaled = udelta;
         if (deltascaled != delta + udelta) {
                 if (udelta) {
-                        sys_scaled = deltascaled * delta / (delta + udelta);
-                        user_scaled = deltascaled - sys_scaled;
+                        *sys_scaled = deltascaled * delta / (delta + udelta);
+                        user_scaled = deltascaled - *sys_scaled;
                 } else {
-                        sys_scaled = deltascaled;
+                        *sys_scaled = deltascaled;
                 }
         }
         get_paca()->user_time_scaled += user_scaled;
 
-        if (in_interrupt() || idle_task(smp_processor_id()) != tsk) {
-                account_system_time(tsk, 0, delta, sys_scaled);
-                if (stolen)
-                        account_steal_time(stolen);
-        } else {
-                account_idle_time(delta + stolen);
-        }
-        local_irq_restore(flags);
+        return delta;
+}
+
+void vtime_account_system(struct task_struct *tsk)
+{
+        u64 delta, sys_scaled, stolen;
+
+        delta = vtime_delta(tsk, &sys_scaled, &stolen);
+        account_system_time(tsk, 0, delta, sys_scaled);
+        if (stolen)
+                account_steal_time(stolen);
+}
+
+void vtime_account_idle(struct task_struct *tsk)
+{
+        u64 delta, sys_scaled, stolen;
+
+        delta = vtime_delta(tsk, &sys_scaled, &stolen);
+        account_idle_time(delta + stolen);
 }
-EXPORT_SYMBOL_GPL(account_system_vtime);
 
 /*
  * Transfer the user and system times accumulated in the paca
  * by the exception entry and exit code to the generic process
  * user and system time records.
  * Must be called with interrupts disabled.
- * Assumes that account_system_vtime() has been called recently
+ * Assumes that vtime_account() has been called recently
  * (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
@@ -366,6 +375,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
         account_user_time(tsk, utime, utimescaled);
 }
 
+void vtime_task_switch(struct task_struct *prev)
+{
+        vtime_account(prev);
+        account_process_tick(prev, 0);
+}
+
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
 #endif
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 30fd01de6be..72afd2888ca 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,6 +1,7 @@
 config PPC64
         bool "64-bit kernel"
         default n
+        select HAVE_VIRT_CPU_ACCOUNTING
         help
           This option selects whether a 32-bit or a 64-bit kernel
           will be built.
@@ -337,21 +338,6 @@ config PPC_MM_SLICES
         default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
         default n
 
-config VIRT_CPU_ACCOUNTING
-        bool "Deterministic task and CPU time accounting"
-        depends on PPC64
-        default y
-        help
-          Select this option to enable more accurate task and CPU time
-          accounting.  This is done by reading a CPU counter on each
-          kernel entry and exit and on transitions within the kernel
-          between system, softirq and hardirq state, so there is a
-          small performance impact.  This also enables accounting of
-          stolen time on logically-partitioned systems running on
-          IBM POWER5-based machines.
-
-          If in doubt, say Y here.
-
 config PPC_HAVE_PMU_SUPPORT
        bool