Add scaled time to taskstats based process accounting

This adds items to the taststats struct to account for user and system
time based on scaling the CPU frequency and instruction issue rates.

Adds account_(user|system)_time_scaled callbacks which architectures
can use to account for time using this mechanism.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 38 insertions, 2 deletions

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 09e9574..10e43fd 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -115,6 +115,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	tmp += timespec_to_ns(&ts);
 	d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
 
+	tmp = (s64)d->cpu_scaled_run_real_total;
+	cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts);
+	tmp += timespec_to_ns(&ts);
+	d->cpu_scaled_run_real_total =
+		(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;
+
 	/*
 	 * No locking available for sched_info (and too expensive to add one)
 	 * Mitigate by taking snapshot of values
diff --git a/kernel/fork.c b/kernel/fork.c
index 1232aac..2ce28f1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1059,6 +1059,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->utime = cputime_zero;
 	p->stime = cputime_zero;
 	p->gtime = cputime_zero;
+	p->utimescaled = cputime_zero;
+	p->stimescaled = cputime_zero;
 
 #ifdef CONFIG_TASK_XACCT
 	p->rchar = 0;		/* I/O counter: bytes read */
diff --git a/kernel/sched.c b/kernel/sched.c
index 92721d1..1253442 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3334,6 +3334,16 @@ void account_guest_time(struct task_struct *p, cputime_t cputime)
 }
 
 /*
+ * Account scaled user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in user space since the last update
+ */
+void account_user_time_scaled(struct task_struct *p, cputime_t cputime)
+{
+	p->utimescaled = cputime_add(p->utimescaled, cputime);
+}
+
+/*
  * Account system cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
@@ -3371,6 +3381,17 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 }
 
 /*
+ * Account scaled system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ */
+void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
+{
+	p->stimescaled = cputime_add(p->stimescaled, cputime);
+}
+
+/*
  * Account for involuntary wait time.
  * @p: the process from which the cpu time has been stolen
  * @steal: the cpu time spent in involuntary wait
diff --git a/kernel/timer.c b/kernel/timer.c
index 0735f0a..8521d10 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -826,10 +826,13 @@ void update_process_times(int user_tick)
 	int cpu = smp_processor_id();
 
 	/* Note: this timer irq context must be accounted for as well. */
-	if (user_tick)
+	if (user_tick) {
 		account_user_time(p, jiffies_to_cputime(1));
-	else
+		account_user_time_scaled(p, jiffies_to_cputime(1));
+	} else {
 		account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1));
+		account_system_time_scaled(p, jiffies_to_cputime(1));
+	}
 	run_local_timers();
 	if (rcu_pending(cpu))
 		rcu_check_callbacks(cpu, user_tick);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index c122131..4ab1b58 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -62,6 +62,10 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 	rcu_read_unlock();
 	stats->ac_utime	 = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC;
 	stats->ac_stime	 = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC;
+	stats->ac_utimescaled =
+		cputime_to_msecs(tsk->utimescaled) * USEC_PER_MSEC;
+	stats->ac_stimescaled =
+		cputime_to_msecs(tsk->stimescaled) * USEC_PER_MSEC;
 	stats->ac_minflt = tsk->min_flt;
 	stats->ac_majflt = tsk->maj_flt;