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
  ...

3 files changed, 34 insertions, 52 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 310cf5781fa..3c720ef6c32 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -25,6 +25,7 @@ config IA64
         select HAVE_GENERIC_HARDIRQS
         select HAVE_MEMBLOCK
         select HAVE_MEMBLOCK_NODE_MAP
+        select HAVE_VIRT_CPU_ACCOUNTING
         select ARCH_DISCARD_MEMBLOCK
         select GENERIC_IRQ_PROBE
         select GENERIC_PENDING_IRQ if SMP
@@ -340,17 +341,6 @@ config FORCE_MAX_ZONEORDER
         default "17" if HUGETLB_PAGE
         default "11"
 
-config VIRT_CPU_ACCOUNTING
-        bool "Deterministic task and CPU time accounting"
-        default n
-        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.
-          If in doubt, say N here.
-
 config SMP
         bool "Symmetric multi-processing support"
         select USE_GENERIC_SMP_HELPERS
diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h
index cb2412fcd17..d38c7ea5eea 100644
--- a/arch/ia64/include/asm/switch_to.h
+++ b/arch/ia64/include/asm/switch_to.h
@@ -30,13 +30,6 @@ extern struct task_struct *ia64_switch_to (void *next_task);
 extern void ia64_save_extra (struct task_struct *task);
 extern void ia64_load_extra (struct task_struct *task);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next);
-# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n)
-#else
-# define IA64_ACCOUNT_ON_SWITCH(p,n)
-#endif
-
 #ifdef CONFIG_PERFMON
   DECLARE_PER_CPU(unsigned long, pfm_syst_info);
 # define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
@@ -49,7 +42,6 @@ extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct
          || PERFMON_IS_SYSWIDE())
 
 #define __switch_to(prev,next,last) do {                                                         \
-        IA64_ACCOUNT_ON_SWITCH(prev, next);                                                      \
         if (IA64_HAS_EXTRA_STATE(prev))                                                          \
                 ia64_save_extra(prev);                                                           \
         if (IA64_HAS_EXTRA_STATE(next))                                                          \
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index ecc904b33c5..80ff9acc5ed 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -83,32 +83,36 @@ static struct clocksource *itc_clocksource;
 
 extern cputime_t cycle_to_cputime(u64 cyc);
 
+static void vtime_account_user(struct task_struct *tsk)
+{
+        cputime_t delta_utime;
+        struct thread_info *ti = task_thread_info(tsk);
+
+        if (ti->ac_utime) {
+                delta_utime = cycle_to_cputime(ti->ac_utime);
+                account_user_time(tsk, delta_utime, delta_utime);
+                ti->ac_utime = 0;
+        }
+}
+
 /*
  * Called from the context switch with interrupts disabled, to charge all
  * accumulated times to the current process, and to prepare accounting on
  * the next process.
  */
-void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
+void vtime_task_switch(struct task_struct *prev)
 {
         struct thread_info *pi = task_thread_info(prev);
-        struct thread_info *ni = task_thread_info(next);
-        cputime_t delta_stime, delta_utime;
-        __u64 now;
+        struct thread_info *ni = task_thread_info(current);
 
-        now = ia64_get_itc();
-
-        delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp));
         if (idle_task(smp_processor_id()) != prev)
-                account_system_time(prev, 0, delta_stime, delta_stime);
+                vtime_account_system(prev);
         else
-                account_idle_time(delta_stime);
+                vtime_account_idle(prev);
 
-        if (pi->ac_utime) {
-                delta_utime = cycle_to_cputime(pi->ac_utime);
-                account_user_time(prev, delta_utime, delta_utime);
-        }
+        vtime_account_user(prev);
 
-        pi->ac_stamp = ni->ac_stamp = now;
+        pi->ac_stamp = ni->ac_stamp;
         ni->ac_stime = ni->ac_utime = 0;
 }
 
@@ -116,29 +120,32 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
  * Account time for a transition between system, hard irq or soft irq state.
  * Note that this function is called with interrupts enabled.
  */
-void account_system_vtime(struct task_struct *tsk)
+static cputime_t vtime_delta(struct task_struct *tsk)
 {
         struct thread_info *ti = task_thread_info(tsk);
-        unsigned long flags;
         cputime_t delta_stime;
         __u64 now;
 
-        local_irq_save(flags);
-
         now = ia64_get_itc();
 
         delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-        if (irq_count() || idle_task(smp_processor_id()) != tsk)
-                account_system_time(tsk, 0, delta_stime, delta_stime);
-        else
-                account_idle_time(delta_stime);
         ti->ac_stime = 0;
-
         ti->ac_stamp = now;
 
-        local_irq_restore(flags);
+        return delta_stime;
+}
+
+void vtime_account_system(struct task_struct *tsk)
+{
+        cputime_t delta = vtime_delta(tsk);
+
+        account_system_time(tsk, 0, delta, delta);
+}
+
+void vtime_account_idle(struct task_struct *tsk)
+{
+        account_idle_time(vtime_delta(tsk));
 }
-EXPORT_SYMBOL_GPL(account_system_vtime);
 
 /*
  * Called from the timer interrupt handler to charge accumulated user time
@@ -146,14 +153,7 @@ EXPORT_SYMBOL_GPL(account_system_vtime);
  */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-        struct thread_info *ti = task_thread_info(p);
-        cputime_t delta_utime;
-
-        if (ti->ac_utime) {
-                delta_utime = cycle_to_cputime(ti->ac_utime);
-                account_user_time(p, delta_utime, delta_utime);
-                ti->ac_utime = 0;
-        }
+        vtime_account_user(p);
 }
 
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */