[PATCH] delayacct: Preserve delay extrema when aggregating taskstats

[PATCH] delayacct: Preserve delay extrema when aggregating taskstats

[Hungyu Lin]

delayacct_add_tsk() adds each task's statistics to the accumulated TGID
statistics, but overwrites the delay maxima, minima and peak timestamps.
Consequently, the last task determines these fields, and a task with no
recorded delay can erase an earlier task's peak despite a nonzero total.

Keep the largest maximum and its associated timestamp, and combine the
minima with min_not_zero() since zero denotes an unrecorded delay. Apply
this to CPU delay and the seven delay types handled by UPDATE_DELAY().
Single-task queries still start with zeroed statistics and retain the
task's values.

Fixes: 658eb5ab916d ("delayacct: add delay max to record delay peak")
Fixes: f65c64f311ee ("delayacct: add delay min to record delay peak")
Cc: stable@vger.kernel.org
Signed-off-by: Hungyu Lin <dennylin0707@gmail.com>
---
 kernel/delayacct.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 479e860aff70..ea1424524654 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -12,14 +12,18 @@
 #include <linux/taskstats.h>
 #include <linux/sysctl.h>
 #include <linux/delayacct.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 
 #define UPDATE_DELAY(type) \
 do { \
-	d->type##_delay_max = tsk->delays->type##_delay_max; \
-	d->type##_delay_min = tsk->delays->type##_delay_min; \
-	d->type##_delay_max_ts.tv_sec = tsk->delays->type##_delay_max_ts.tv_sec; \
-	d->type##_delay_max_ts.tv_nsec = tsk->delays->type##_delay_max_ts.tv_nsec; \
+	if (tsk->delays->type##_delay_max > d->type##_delay_max) { \
+		d->type##_delay_max = tsk->delays->type##_delay_max; \
+		d->type##_delay_max_ts.tv_sec = tsk->delays->type##_delay_max_ts.tv_sec; \
+		d->type##_delay_max_ts.tv_nsec = tsk->delays->type##_delay_max_ts.tv_nsec; \
+	} \
+	d->type##_delay_min = min_not_zero(d->type##_delay_min, \
+					 tsk->delays->type##_delay_min); \
 	tmp = d->type##_delay_total + tsk->delays->type##_delay; \
 	d->type##_delay_total = (tmp < d->type##_delay_total) ? 0 : tmp; \
 	d->type##_count += tsk->delays->type##_count; \
@@ -174,10 +178,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 
 	d->cpu_count += t1;
 
-	d->cpu_delay_max = tsk->sched_info.max_run_delay;
-	d->cpu_delay_min = tsk->sched_info.min_run_delay;
-	d->cpu_delay_max_ts.tv_sec = tsk->sched_info.max_run_delay_ts.tv_sec;
-	d->cpu_delay_max_ts.tv_nsec = tsk->sched_info.max_run_delay_ts.tv_nsec;
+	if (tsk->sched_info.max_run_delay > d->cpu_delay_max) {
+		d->cpu_delay_max = tsk->sched_info.max_run_delay;
+		d->cpu_delay_max_ts.tv_sec = tsk->sched_info.max_run_delay_ts.tv_sec;
+		d->cpu_delay_max_ts.tv_nsec = tsk->sched_info.max_run_delay_ts.tv_nsec;
+	}
+	d->cpu_delay_min = min_not_zero(d->cpu_delay_min,
+					tsk->sched_info.min_run_delay);
 	tmp = (s64)d->cpu_delay_total + t2;
 	d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp;
 	tmp = (s64)d->cpu_run_virtual_total + t3;
-- 
2.43.0