Don't pretend that the IO threads are in the same thread group, the only
case where that seems to be desired is for accounting purposes. Add
a special accounting function for that and make the scheduler side use it.
For signals and ptrace, we don't allow them to be treated as threads
anyway.
Reported-by: Stefan Metzmacher <metze@xxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
include/linux/sched/signal.h | 9 ++++++++-
kernel/sched/cputime.c | 2 +-
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3f6a0fcaa10c..4f621e386abf 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -668,11 +668,18 @@ static inline bool thread_group_leader(struct task_struct *p)
}
static inline
-bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
+bool same_thread_group_account(struct task_struct *p1, struct task_struct *p2)
{
return p1->signal == p2->signal;
}
+static inline
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
+{
+ return same_thread_group_account(p1, p2) &&
+ !((p1->flags | p2->flags) & PF_IO_WORKER);
+}
+
static inline struct task_struct *next_thread(const struct task_struct *p)
{
return list_entry_rcu(p->thread_group.next,
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5f611658eeab..625110cacc2a 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -307,7 +307,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
* those pending times and rely only on values updated on tick or
* other scheduler action.
*/
- if (same_thread_group(current, tsk))
+ if (same_thread_group_account(current, tsk))
(void) task_sched_runtime(current);
rcu_read_lock();
--
2.31.0
