v2:
- Split into two patches per Peter's suggestion
- Patch 1: pure bug fix in sched_fork (restore timer_slack on reset)
- Patch 2: fix default_timer_slack_ns inheritance + init_task init

When an RT task with SCHED_RESET_ON_FORK creates child threads, the
children inherit timer_slack_ns=0 and can never recover a proper slack
value. This results in ~2x more timer interrupts than necessary.

Patch 1 fixes the immediate issue by restoring timer_slack_ns in
sched_fork() when resetting from RT to NORMAL policy.

Patch 2 fixes the root cause: copy_process() was overwriting the
child's default_timer_slack_ns with the parent's timer_slack_ns (0 for
RT), and init_task never initialized default_timer_slack_ns.

With both patches applied (RT parent, RESET_ON_FORK, 32 child threads
usleep(1)):
  Before: child slack=0, avg_sleep=38us, ~832K interrupts/s
  After:  child slack=50000, avg_sleep=88us, ~363K interrupts/s

Guanyou.Chen (2):
  sched: restore timer_slack_ns when resetting RT policy on fork
  fork: fix default_timer_slack_ns inheritance from RT parent

 init/init_task.c    | 1 +
 kernel/fork.c       | 2 --
 kernel/sched/core.c | 1 +
 3 files changed, 2 insertions(+), 2 deletions(-)

-- 
2.34.1