sched/cputime, powerpc/vtime: Accumulate cputime and account only on tick/task switch

Currently CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y accounts the cputime on
any context boundary: irq entry/exit, guest entry/exit, context switch,
etc...

Calling functions such as account_system_time(), account_user_time()
and such can be costly, especially if they are called on many fastpath
such as twice per IRQ. Those functions do more than just accounting to
kcpustat and task cputime. Depending on the config, some subsystems can
perform unpleasant multiplications and divisions, among other things.

So lets accumulate the cputime instead and delay the accounting on ticks
and context switches only.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1483636310-6557-8-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 714313ebf030daf4771e9d378df56c609aa99939..4255e6930ac1dff1524bf063a52c37fae2e99045 100644 (file)
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -280,17 +280,10 @@ void accumulate_stolen_time(void)
 
 static inline u64 calculate_stolen_time(u64 stop_tb)
 {
-       u64 stolen = 0;
-       struct cpu_accounting_data *acct = &local_paca->accounting;
-
-       if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
-               stolen = scan_dispatch_log(stop_tb);
-               acct->stime -= stolen;
-       }
+       if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
+               return scan_dispatch_log(stop_tb);
 
-       stolen += acct->steal_time;
-       acct->steal_time = 0;
-       return stolen;
+       return 0;
 }
 
 #else /* CONFIG_PPC_SPLPAR */
@@ -306,27 +299,26 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * or soft irq state.
  */
 static unsigned long vtime_delta(struct task_struct *tsk,
-                                unsigned long *sys_scaled,
-                                unsigned long *stolen)
+                                unsigned long *stime_scaled,
+                                unsigned long *steal_time)
 {
        unsigned long now, nowscaled, deltascaled;
-       unsigned long udelta, delta, user_scaled;
+       unsigned long stime;
+       unsigned long utime, utime_scaled;
        struct cpu_accounting_data *acct = get_accounting(tsk);
 
        WARN_ON_ONCE(!irqs_disabled());
 
        now = mftb();
        nowscaled = read_spurr(now);
-       acct->stime += now - acct->starttime;
+       stime = now - acct->starttime;
        acct->starttime = now;
        deltascaled = nowscaled - acct->startspurr;
        acct->startspurr = nowscaled;
 
-       *stolen = calculate_stolen_time(now);
+       *steal_time = calculate_stolen_time(now);
 
-       delta = acct->stime;
-       acct->stime = 0;
-       udelta = acct->utime - acct->utime_sspurr;
+       utime = acct->utime - acct->utime_sspurr;
        acct->utime_sspurr = acct->utime;
 
        /*
@@ -339,39 +331,54 @@ static unsigned long vtime_delta(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;
-       user_scaled = udelta;
-       if (deltascaled != delta + udelta) {
-               if (udelta) {
-                       *sys_scaled = deltascaled * delta / (delta + udelta);
-                       user_scaled = deltascaled - *sys_scaled;
+       *stime_scaled = stime;
+       utime_scaled = utime;
+       if (deltascaled != stime + utime) {
+               if (utime) {
+                       *stime_scaled = deltascaled * stime / (stime + utime);
+                       utime_scaled = deltascaled - *stime_scaled;
                } else {
-                       *sys_scaled = deltascaled;
+                       *stime_scaled = deltascaled;
                }
        }
-       acct->utime_scaled += user_scaled;
+       acct->utime_scaled += utime_scaled;
 
-       return delta;
+       return stime;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-       unsigned long delta, sys_scaled, stolen;
+       unsigned long stime, stime_scaled, steal_time;
+       struct cpu_accounting_data *acct = get_accounting(tsk);
+
+       stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+
+       stime -= min(stime, steal_time);
+       acct->steal_time += steal_time;
 
-       delta = vtime_delta(tsk, &sys_scaled, &stolen);
-       account_system_time(tsk, 0, delta);
-       tsk->stimescaled += sys_scaled;
-       if (stolen)
-               account_steal_time(stolen);
+       if ((tsk->flags & PF_VCPU) && !irq_count()) {
+               acct->gtime += stime;
+               acct->utime_scaled += stime_scaled;
+       } else {
+               if (hardirq_count())
+                       acct->hardirq_time += stime;
+               else if (in_serving_softirq())
+                       acct->softirq_time += stime;
+               else
+                       acct->stime += stime;
+
+               acct->stime_scaled += stime_scaled;
+       }
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-       unsigned long delta, sys_scaled, stolen;
+       unsigned long stime, stime_scaled, steal_time;
+       struct cpu_accounting_data *acct = get_accounting(tsk);
 
-       delta = vtime_delta(tsk, &sys_scaled, &stolen);
-       account_idle_time(delta + stolen);
+       stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+       acct->idle_time += stime + steal_time;
 }
 
 /*
@@ -385,16 +392,45 @@ void vtime_account_idle(struct task_struct *tsk)
  */
 void vtime_account_user(struct task_struct *tsk)
 {
-       cputime_t utime, utimescaled;
        struct cpu_accounting_data *acct = get_accounting(tsk);
 
-       utime = acct->utime;
-       utimescaled = acct->utime_scaled;
+       if (acct->utime)
+               account_user_time(tsk, acct->utime);
+
+       if (acct->utime_scaled)
+               tsk->utimescaled += acct->utime_scaled;
+
+       if (acct->gtime)
+               account_guest_time(tsk, acct->gtime);
+
+       if (acct->steal_time)
+               account_steal_time(acct->steal_time);
+
+       if (acct->idle_time)
+               account_idle_time(acct->idle_time);
+
+       if (acct->stime)
+               account_system_index_time(tsk, acct->stime, CPUTIME_SYSTEM);
+
+       if (acct->stime_scaled)
+               tsk->stimescaled += acct->stime_scaled;
+
+       if (acct->hardirq_time)
+               account_system_index_time(tsk, acct->hardirq_time, CPUTIME_IRQ);
+
+       if (acct->softirq_time)
+               account_system_index_time(tsk, acct->softirq_time, CPUTIME_SOFTIRQ);
+
        acct->utime = 0;
        acct->utime_scaled = 0;
        acct->utime_sspurr = 0;
-       account_user_time(tsk, utime);
-       tsk->utimescaled += utimescaled;
+       acct->gtime = 0;
+       acct->steal_time = 0;
+       acct->idle_time = 0;
+       acct->stime = 0;
+       acct->stime_scaled = 0;
+       acct->hardirq_time = 0;
+       acct->softirq_time = 0;
 }
 
 #ifdef CONFIG_PPC32
@@ -409,8 +445,6 @@ void arch_vtime_task_switch(struct task_struct *prev)
 
        acct->starttime = get_accounting(prev)->starttime;
        acct->startspurr = get_accounting(prev)->startspurr;
-       acct->stime = 0;
-       acct->utime = 0;
 }
 #endif /* CONFIG_PPC32 */