[PATCH] idle cputime accounting

The cpu time spent by the idle process actually doing something is
currently accounted as idle time. This is plain wrong, the architectures
that support VIRT_CPU_ACCOUNTING=y can do better: distinguish between the
time spent doing nothing and the time spent by idle doing work. The first
is accounted with account_idle_time and the second with account_system_time.
The architectures that use the account_xxx_time interface directly and not
the account_xxx_ticks interface now need to do the check for the idle
process in their arch code. In particular to improve the system vs true
idle time accounting the arch code needs to measure the true idle time
instead of just testing for the idle process.
To improve the tick based accounting as well we would need an architecture
primitive that can tell us if the pt_regs of the interrupted context
points to the magic instruction that halts the cpu.

In addition idle time is no more added to the stime of the idle process.
This field now contains the system time of the idle process as it should
be. On systems without VIRT_CPU_ACCOUNTING this will always be zero as
every tick that occurs while idle is running will be accounted as idle
time.

This patch contains the necessary common code changes to be able to
distinguish idle system time and true idle time. The architectures with
support for VIRT_CPU_ACCOUNTING need some changes to exploit this.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

5 files changed, 39 insertions, 15 deletions

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 4ee367817049..f0ebb342409d 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -93,7 +93,10 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
         now = ia64_get_itc();
 
         delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp));
-        account_system_time(prev, 0, delta_stime, delta_stime);
+        if (idle_task(smp_processor_id()) != prev)
+                account_system_time(prev, 0, delta_stime, delta_stime);
+        else
+                account_idle_time(delta_stime);
 
         if (pi->ac_utime) {
                 delta_utime = cycle_to_cputime(pi->ac_utime);
@@ -120,7 +123,10 @@ void account_system_vtime(struct task_struct *tsk)
         now = ia64_get_itc();
 
         delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-        account_system_time(tsk, 0, delta_stime, delta_stime);
+        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;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 51b201ddf9a1..fb7049c054c0 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -33,6 +33,7 @@
 #include <linux/mqueue.h>
 #include <linux/hardirq.h>
 #include <linux/utsname.h>
+#include <linux/kernel_stat.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 92650ccad2e1..3be355c1cfa7 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -256,7 +256,10 @@ void account_system_vtime(struct task_struct *tsk)
                 delta += sys_time;
                 get_paca()->system_time = 0;
         }
-        account_system_time(tsk, 0, delta, deltascaled);
+        if (in_irq() || idle_task(smp_processor_id()) != tsk)
+                account_system_time(tsk, 0, delta, deltascaled);
+        else
+                account_idle_time(delta);
         per_cpu(cputime_last_delta, smp_processor_id()) = delta;
         per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
         local_irq_restore(flags);
@@ -335,8 +338,12 @@ void calculate_steal_time(void)
         tb = mftb();
         purr = mfspr(SPRN_PURR);
         stolen = (tb - pme->tb) - (purr - pme->purr);
-        if (stolen > 0)
-                account_steal_time(current, stolen);
+        if (stolen > 0) {
+                if (idle_task(smp_processor_id()) != current)
+                        account_steal_time(stolen);
+                else
+                        account_idle_time(stolen);
+        }
         pme->tb = tb;
         pme->purr = purr;
 }
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 07283aea2e56..4a4a34caec55 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -55,13 +55,19 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
         cputime =  S390_lowcore.system_timer >> 12;
         S390_lowcore.system_timer -= cputime << 12;
         S390_lowcore.steal_clock -= cputime << 12;
-        account_system_time(tsk, HARDIRQ_OFFSET, cputime, cputime);
+        if (idle_task(smp_processor_id()) != current)
+                account_system_time(tsk, HARDIRQ_OFFSET, cputime, cputime);
+        else
+                account_idle_time(cputime);
 
         cputime = S390_lowcore.steal_clock;
         if ((__s64) cputime > 0) {
                 cputime >>= 12;
                 S390_lowcore.steal_clock -= cputime << 12;
-                account_steal_time(tsk, cputime);
+                if (idle_task(smp_processor_id()) != current)
+                        account_steal_time(cputime);
+                else
+                        account_idle_time(cputime);
         }
 }
 
@@ -87,7 +93,10 @@ void account_vtime(struct task_struct *tsk)
         cputime =  S390_lowcore.system_timer >> 12;
         S390_lowcore.system_timer -= cputime << 12;
         S390_lowcore.steal_clock -= cputime << 12;
-        account_system_time(tsk, 0, cputime, cputime);
+        if (idle_task(smp_processor_id()) != current)
+                account_system_time(tsk, 0, cputime, cputime);
+        else
+                account_idle_time(cputime);
 }
 
 /*
@@ -107,7 +116,10 @@ void account_system_vtime(struct task_struct *tsk)
         cputime =  S390_lowcore.system_timer >> 12;
         S390_lowcore.system_timer -= cputime << 12;
         S390_lowcore.steal_clock -= cputime << 12;
-        account_system_time(tsk, 0, cputime, cputime);
+        if (in_irq() || idle_task(smp_processor_id()) != current)
+                account_system_time(tsk, 0, cputime, cputime);
+        else
+                account_idle_time(cputime);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c9f7cda48ed7..732e52dc991a 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -132,8 +132,7 @@ static void do_stolen_accounting(void)
         *snap = state;
 
         /* Add the appropriate number of ticks of stolen time,
-           including any left-overs from last time.  Passing NULL to
-           account_steal_time accounts the time as stolen. */
+           including any left-overs from last time. */
         stolen = runnable + offline + __get_cpu_var(residual_stolen);
 
         if (stolen < 0)
@@ -141,11 +140,10 @@ static void do_stolen_accounting(void)
 
         ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
         __get_cpu_var(residual_stolen) = stolen;
-        account_steal_time(NULL, ticks);
+        account_steal_ticks(ticks);
 
         /* Add the appropriate number of ticks of blocked time,
-           including any left-overs from last time.  Passing idle to
-           account_steal_time accounts the time as idle/wait. */
+           including any left-overs from last time. */
         blocked += __get_cpu_var(residual_blocked);
 
         if (blocked < 0)
@@ -153,7 +151,7 @@ static void do_stolen_accounting(void)
 
         ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
         __get_cpu_var(residual_blocked) = blocked;
-        account_steal_time(idle_task(smp_processor_id()), ticks);
+        account_idle_ticks(ticks);
 }
 
 /*