sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full

getrusage(RUSAGE_THREAD) with nohz_full may return shorter utime/stime
than the actual time.

task_cputime_adjusted() snapshots utime and stime and then adjust their
sum to match the scheduler maintained cputime.sum_exec_runtime.
Unfortunately in nohz_full, sum_exec_runtime is only updated once per
second in the worst case, causing a discrepancy against utime and stime
that can be updated anytime by the reader using vtime.

To fix this situation, perform an update of cputime.sum_exec_runtime
when the cputime snapshot reports the task as actually running while
the tick is disabled. The related overhead is then contained within the
relevant situations.

Reported-by: Hasegawa Hitomi <hasegawa-hitomi@fujitsu.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Hasegawa Hitomi <hasegawa-hitomi@fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Acked-by: Phil Auld <pauld@redhat.com>
Link: https://lore.kernel.org/r/20211026141055.57358-3-frederic@kernel.org

diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 6c9f19a..ce3c582 100644 (file)
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -18,15 +18,16 @@
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void task_cputime(struct task_struct *t,
+extern bool task_cputime(struct task_struct *t,
                         u64 *utime, u64 *stime);
 extern u64 task_gtime(struct task_struct *t);
 #else
-static inline void task_cputime(struct task_struct *t,
+static inline bool task_cputime(struct task_struct *t,
                                u64 *utime, u64 *stime)
 {
        *utime = t->utime;
        *stime = t->stime;
+       return false;
 }
 
 static inline u64 task_gtime(struct task_struct *t)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 872e481..9392aea 100644 (file)
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
                .sum_exec_runtime = p->se.sum_exec_runtime,
        };
 
-       task_cputime(p, &cputime.utime, &cputime.stime);
+       if (task_cputime(p, &cputime.utime, &cputime.stime))
+               cputime.sum_exec_runtime = task_sched_runtime(p);
        cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
        struct vtime *vtime = &t->vtime;
        unsigned int seq;
        u64 delta;
+       int ret;
 
        if (!vtime_accounting_enabled()) {
                *utime = t->utime;
                *stime = t->stime;
-               return;
+               return false;
        }
 
        do {
+               ret = false;
                seq = read_seqcount_begin(&vtime->seqcount);
 
                *utime = t->utime;
@@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
                if (vtime->state < VTIME_SYS)
                        continue;
 
+               ret = true;
                delta = vtime_delta(vtime);
 
                /*
@@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
                else
                        *utime += vtime->utime + delta;
        } while (read_seqcount_retry(&vtime->seqcount, seq));
+
+       return ret;
 }
 
 static int vtime_state_fetch(struct vtime *vtime, int cpu)