[RFC,v2,4/7] change kernel accounting to include steal time

Commit Message

Glauber Costa Aug. 30, 2010, 5:06 p.m. UTC

None

Patch

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0478888..e571ddd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -312,6 +312,7 @@  long io_schedule_timeout(long timeout);
 extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
+extern cputime_t (*hypervisor_steal_time)(void);
 extern void scheduler_tick(void);
 
 extern void sched_show_task(struct task_struct *p);
diff --git a/kernel/sched.c b/kernel/sched.c
index f52a880..9695c92 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3157,6 +3157,16 @@  unsigned long long thread_group_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
+cputime_t (*hypervisor_steal_time)(void) = NULL;
+
+static inline cputime_t get_steal_time_from_hypervisor(void)
+{
+	if (!hypervisor_steal_time)
+		return 0;
+	return hypervisor_steal_time();
+}
+
+
 /*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
@@ -3169,6 +3179,12 @@  void account_user_time(struct task_struct *p, cputime_t cputime,
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	tmp = get_steal_time_from_hypervisor();
+	if (tmp) {
+		account_steal_time(tmp);
+		return;
+	}
+
 	/* Add user time to process. */
 	p->utime = cputime_add(p->utime, cputime);
 	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
@@ -3234,6 +3250,12 @@  void account_system_time(struct task_struct *p, int hardirq_offset,
 		return;
 	}
 
+	tmp = get_steal_time_from_hypervisor();
+	if (tmp) {
+		account_steal_time(tmp);
+		return;
+	}
+
 	/* Add system time to process. */
 	p->stime = cputime_add(p->stime, cputime);
 	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
@@ -3276,6 +3298,13 @@  void account_idle_time(cputime_t cputime)
 	cputime64_t cputime64 = cputime_to_cputime64(cputime);
 	struct rq *rq = this_rq();
 
+	/*
+	 * if we're idle, we don't account it as steal time, since we did
+	 * not want to run anyway. We do call the steal function, however, to
+	 * give the guest the chance to flush its internal buffers
+	 */
+	get_steal_time_from_hypervisor();
+
 	if (atomic_read(&rq->nr_iowait) > 0)
 		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
 	else