proc: Consider NO_HZ when printing idle and iowait times

show_stat handler of the /proc/stat file relies on kstat_cpu(cpu)
statistics when priting information about idle and iowait times.
This is OK if we are not using tickless kernel (CONFIG_NO_HZ) because
counters are updated periodically.
With NO_HZ things got more tricky because we are not doing idle/iowait
accounting while we are tickless so the value might get outdated.
Users of /proc/stat will notice that by unchanged idle/iowait values
which is then interpreted as 0% idle/iowait time. From the user space
POV this is an unexpected behavior and a change of the interface.

Let's fix this by using get_cpu_{idle,iowait}_time_us which accounts the
total idle/iowait time since boot and it doesn't rely on sampling or any
other periodic activity. Fall back to the previous behavior if NO_HZ is
disabled or not configured.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Dave Jones <davej@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Link: http://lkml.kernel.org/r/39181366adac1b39cb6aa3cd53ff0f7c78d32676.1314172057.git.mhocko@suse.cz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 34 insertions, 7 deletions

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 9758b65..42b274d 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -10,6 +10,7 @@
 #include <linux/time.h>
 #include <linux/irqnr.h>
 #include <asm/cputime.h>
+#include <linux/tick.h>
 
 #ifndef arch_irq_stat_cpu
 #define arch_irq_stat_cpu(cpu) 0
@@ -21,6 +22,35 @@
 #define arch_idle_time(cpu) 0
 #endif
 
+static cputime64_t get_idle_time(int cpu)
+{
+	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+	cputime64_t idle;
+
+	if (idle_time == -1ULL) {
+		/* !NO_HZ so we can rely on cpustat.idle */
+		idle = kstat_cpu(cpu).cpustat.idle;
+		idle = cputime64_add(idle, arch_idle_time(cpu));
+	} else
+		idle = usecs_to_cputime(idle_time);
+
+	return idle;
+}
+
+static cputime64_t get_iowait_time(int cpu)
+{
+	u64 iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+	cputime64_t iowait;
+
+	if (iowait_time == -1ULL)
+		/* !NO_HZ so we can rely on cpustat.iowait */
+		iowait = kstat_cpu(cpu).cpustat.iowait;
+	else
+		iowait = usecs_to_cputime(iowait_time);
+
+	return iowait;
+}
+
 static int show_stat(struct seq_file *p, void *v)
 {
 	int i, j;
@@ -42,9 +72,8 @@ static int show_stat(struct seq_file *p, void *v)
 		user = cputime64_add(user, kstat_cpu(i).cpustat.user);
 		nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
 		system = cputime64_add(system, kstat_cpu(i).cpustat.system);
-		idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle);
-		idle = cputime64_add(idle, arch_idle_time(i));
-		iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait);
+		idle = cputime64_add(idle, get_idle_time(i));
+		iowait = cputime64_add(iowait, get_iowait_time(i));
 		irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
 		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
@@ -76,14 +105,12 @@ static int show_stat(struct seq_file *p, void *v)
 		(unsigned long long)cputime64_to_clock_t(guest),
 		(unsigned long long)cputime64_to_clock_t(guest_nice));
 	for_each_online_cpu(i) {
-
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
 		user = kstat_cpu(i).cpustat.user;
 		nice = kstat_cpu(i).cpustat.nice;
 		system = kstat_cpu(i).cpustat.system;
-		idle = kstat_cpu(i).cpustat.idle;
-		idle = cputime64_add(idle, arch_idle_time(i));
-		iowait = kstat_cpu(i).cpustat.iowait;
+		idle = get_idle_time(i);
+		iowait = get_iowait_time(i);
 		irq = kstat_cpu(i).cpustat.irq;
 		softirq = kstat_cpu(i).cpustat.softirq;
 		steal = kstat_cpu(i).cpustat.steal;