[PATCH] taskstats: retain dead thread stats in TGID queries

[Yiyang Chen]

fill_stats_for_tgid() builds TGID stats from two sources: the cached
aggregate in signal->stats and a scan of the live threads in the group.

However, fill_tgid_exit() only accumulates delay accounting into
signal->stats. This means TGID queries lose the fields that
fill_stats_for_tgid() adds for live threads once a thread exits,
including ac_etime, ac_utime, ac_stime, nvcsw and nivcsw.

Factor the per-task TGID accumulation into a helper and use it in both
fill_stats_for_tgid() and fill_tgid_exit(). This keeps the fields
retained for dead threads aligned with the fields already accounted for
live threads, and follows the existing taskstats TGID aggregation model,
which already accumulates delay accounting in fill_tgid_exit() and
combines it with a live-thread scan in fill_stats_for_tgid().

Signed-off-by: Yiyang Chen <cyyzero16@xxxxxxxxx>
---
 kernel/taskstats.c | 62 ++++++++++++++++++++++++----------------------
 1 file changed, 33 insertions(+), 29 deletions(-)

diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 0cd680ccc7e5..2a0ab42e4edd 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -210,13 +210,39 @@ static int fill_stats_for_pid(pid_t pid, struct taskstats *stats)
 	return 0;
 }
 
+static void tgid_stats_add_task(struct taskstats *stats,
+				     struct task_struct *tsk, u64 now_ns)
+{
+	u64 delta, utime, stime;
+
+	/*
+	 * Each accounting subsystem calls its functions here to
+	 * accumulate its per-task stats for tsk, into the per-tgid structure
+	 *
+	 *	per-task-foo(tsk->signal->stats, tsk);
+	 */
+	delayacct_add_tsk(stats, tsk);
+
+	/* calculate task elapsed time in nsec */
+	delta = now_ns - tsk->start_time;
+	/* Convert to micro seconds */
+	do_div(delta, NSEC_PER_USEC);
+	stats->ac_etime += delta;
+
+	task_cputime(tsk, &utime, &stime);
+	stats->ac_utime += div_u64(utime, NSEC_PER_USEC);
+	stats->ac_stime += div_u64(stime, NSEC_PER_USEC);
+
+	stats->nvcsw += tsk->nvcsw;
+	stats->nivcsw += tsk->nivcsw;
+}
+
 static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
 {
 	struct task_struct *tsk, *first;
 	unsigned long flags;
 	int rc = -ESRCH;
-	u64 delta, utime, stime;
-	u64 start_time;
+	u64 now_ns;
 
 	/*
 	 * Add additional stats from live tasks except zombie thread group
@@ -233,30 +259,12 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
 	else
 		memset(stats, 0, sizeof(*stats));
 
-	start_time = ktime_get_ns();
+	now_ns = ktime_get_ns();
 	for_each_thread(first, tsk) {
 		if (tsk->exit_state)
 			continue;
-		/*
-		 * Accounting subsystem can call its functions here to
-		 * fill in relevant parts of struct taskstsats as follows
-		 *
-		 *	per-task-foo(stats, tsk);
-		 */
-		delayacct_add_tsk(stats, tsk);
-
-		/* calculate task elapsed time in nsec */
-		delta = start_time - tsk->start_time;
-		/* Convert to micro seconds */
-		do_div(delta, NSEC_PER_USEC);
-		stats->ac_etime += delta;
 
-		task_cputime(tsk, &utime, &stime);
-		stats->ac_utime += div_u64(utime, NSEC_PER_USEC);
-		stats->ac_stime += div_u64(stime, NSEC_PER_USEC);
-
-		stats->nvcsw += tsk->nvcsw;
-		stats->nivcsw += tsk->nivcsw;
+		tgid_stats_add_task(stats, tsk, now_ns);
 	}
 
 	unlock_task_sighand(first, &flags);
@@ -275,18 +283,14 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
 static void fill_tgid_exit(struct task_struct *tsk)
 {
 	unsigned long flags;
+	u64 now_ns;
 
 	spin_lock_irqsave(&tsk->sighand->siglock, flags);
 	if (!tsk->signal->stats)
 		goto ret;
 
-	/*
-	 * Each accounting subsystem calls its functions here to
-	 * accumalate its per-task stats for tsk, into the per-tgid structure
-	 *
-	 *	per-task-foo(tsk->signal->stats, tsk);
-	 */
-	delayacct_add_tsk(tsk->signal->stats, tsk);
+	now_ns = ktime_get_ns();
+	tgid_stats_add_task(tsk->signal->stats, tsk, now_ns);
 ret:
 	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
 	return;
-- 
2.43.0