[PATCH v3 3/6] KVM-GST: KVM Steal time accounting

[Glauber Costa]

This patch accounts steal time time in kernel/sched.
I kept it from last proposal, because I still see advantages
in it: Doing it here will give us easier access from scheduler
variables such as the cpu rq. The next patch shows an example of
usage for it.

Since functions like account_idle_time() can be called from
multiple places, not only account_process_tick(), steal time
grabbing is repeated in each account function separatedely.

Signed-off-by: Glauber Costa <glommer@xxxxxxxxxx>
CC: Rik van Riel <riel@xxxxxxxxxx>
CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CC: Avi Kivity <avi@xxxxxxxxxx>
---
 include/linux/sched.h |    1 +
 kernel/sched.c        |   47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 0 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d747f94..5dbf509 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -302,6 +302,7 @@ long io_schedule_timeout(long timeout);
 extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
+extern u64 (*hypervisor_steal_time)(int cpu);
 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 18d38e4..60b0cf8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -524,6 +524,8 @@ struct rq {
 	u64 prev_irq_time;
 #endif
 
+	u64 prev_steal_ticks;
+
 	/* calc_load related fields */
 	unsigned long calc_load_update;
 	long calc_load_active;
@@ -1780,6 +1782,16 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dec_nr_running(rq);
 }
 
+u64 (*hypervisor_steal_time)(int cpu) = NULL;
+
+static u64 steal_time_clock(int cpu)
+{
+	if (!hypervisor_steal_time)
+		return 0;
+
+	return hypervisor_steal_time(cpu);
+}
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
 /*
@@ -3509,6 +3521,33 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p)
 }
 
 /*
+ * We have to at flush steal time information every time something else
+ * is accounted. Since the accounting functions are all visible to the rest
+ * of the kernel, it gets tricky to do them in one place. This helper function
+ * helps us.
+ *
+ * When the system is idle, the concept of steal time does not apply. We just
+ * tell the underlying hypervisor that we grabbed the data, but skip steal time
+ * accounting
+ */
+static int touch_steal_time(int is_idle)
+{
+	u64 steal, st;
+
+	steal = steal_time_clock(smp_processor_id());
+
+	st = steal / TICK_NSEC - this_rq()->prev_steal_ticks;
+
+	this_rq()->prev_steal_ticks += st;
+
+	if (!st || is_idle)
+		return 0;
+
+	account_steal_time(st);
+	return 1;
+}
+
+/*
  * Account 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
@@ -3520,6 +3559,9 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	if (touch_steal_time(0))
+		return;
+
 	/* Add user time to process. */
 	p->utime = cputime_add(p->utime, cputime);
 	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
@@ -3580,6 +3622,9 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	if (touch_steal_time(0))
+		return;
+
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
 		account_guest_time(p, cputime, cputime_scaled);
 		return;
@@ -3627,6 +3672,8 @@ void account_idle_time(cputime_t cputime)
 	cputime64_t cputime64 = cputime_to_cputime64(cputime);
 	struct rq *rq = this_rq();
 
+	touch_steal_time(1);
+
 	if (atomic_read(&rq->nr_iowait) > 0)
 		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
 	else
-- 
1.7.2.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/