Re: [PATCH 6.6] Revert "sched/core: Reduce cost of sched_move_task when config autogroup"

[Sasha Levin <sashal@kernel.org>]

[ Sasha's backport helper bot ]

Hi,

✅ All tests passed successfully. No issues detected.
No action required from the submitter.

The upstream commit SHA1 provided is correct: 76f970ce51c80f625eb6ddbb24e9cb51b977b598

WARNING: Author mismatch between patch and upstream commit:
Backport author: Hagar Hemdan<hagarhem@amazon.com>
Commit author: Dietmar Eggemann<dietmar.eggemann@arm.com>

Status in newer kernel trees:
6.13.y | Not found
6.12.y | Not found

Note: The patch differs from the upstream commit:
---
1:  76f970ce51c80 ! 1:  03098b8360be3 Revert "sched/core: Reduce cost of sched_move_task when config autogroup"
    @@
      ## Metadata ##
    -Author: Dietmar Eggemann <dietmar.eggemann@arm.com>
    +Author: Hagar Hemdan <hagarhem@amazon.com>
     
      ## Commit message ##
         Revert "sched/core: Reduce cost of sched_move_task when config autogroup"
     
    +    commit 76f970ce51c80f625eb6ddbb24e9cb51b977b598 upstream.
    +
         This reverts commit eff6c8ce8d4d7faef75f66614dd20bb50595d261.
     
         Hazem reported a 30% drop in UnixBench spawn test with commit
    @@ Commit message
         Tested-by: Hagar Hemdan <hagarhem@amazon.com>
         Cc: Linus Torvalds <torvalds@linux-foundation.org>
         Link: https://lore.kernel.org/r/20250314151345.275739-1-dietmar.eggemann@arm.com
    +    [Hagar: clean revert of eff6c8ce8dd7 to make it work on 6.6]
    +    Signed-off-by: Hagar Hemdan <hagarhem@amazon.com>
     
      ## kernel/sched/core.c ##
     @@ kernel/sched/core.c: void sched_release_group(struct task_group *tg)
    @@ kernel/sched/core.c: static struct task_group *sched_get_task_group(struct task_
      
      #ifdef CONFIG_FAIR_GROUP_SCHED
      	if (tsk->sched_class->task_change_group)
    -@@ kernel/sched/core.c: void sched_move_task(struct task_struct *tsk, bool for_autogroup)
    +@@ kernel/sched/core.c: void sched_move_task(struct task_struct *tsk)
      {
      	int queued, running, queue_flags =
      		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
     -	struct task_group *group;
    + 	struct rq_flags rf;
      	struct rq *rq;
      
    - 	CLASS(task_rq_lock, rq_guard)(tsk);
    - 	rq = rq_guard.rq;
    - 
    + 	rq = task_rq_lock(tsk, &rf);
     -	/*
     -	 * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
     -	 * group changes.
     -	 */
     -	group = sched_get_task_group(tsk);
     -	if (group == tsk->sched_task_group)
    --		return;
    +-		goto unlock;
     -
      	update_rq_clock(rq);
      
    - 	running = task_current_donor(rq, tsk);
    -@@ kernel/sched/core.c: void sched_move_task(struct task_struct *tsk, bool for_autogroup)
    + 	running = task_current(rq, tsk);
    +@@ kernel/sched/core.c: void sched_move_task(struct task_struct *tsk)
      	if (running)
      		put_prev_task(rq, tsk);
      
     -	sched_change_group(tsk, group);
     +	sched_change_group(tsk);
    - 	if (!for_autogroup)
    - 		scx_cgroup_move_task(tsk);
    + 
    + 	if (queued)
    + 		enqueue_task(rq, tsk, queue_flags);
    +@@ kernel/sched/core.c: void sched_move_task(struct task_struct *tsk)
    + 		resched_curr(rq);
    + 	}
    + 
    +-unlock:
    + 	task_rq_unlock(rq, tsk, &rf);
    + }
      
---

Results of testing on various branches:

| Branch                    | Patch Apply | Build Test |
|---------------------------|-------------|------------|
| stable/linux-6.6.y        |  Success    |  Success   |