Re: [PATCH 1/4] sched/fair: free allocated memory on error in alloc_fair_sched_group()

[Aaron Lu <aaron.lu@intel.com>]

On Tue, Jul 18, 2023 at 11:13:12PM +0800, Chen Yu wrote:
> On 2023-07-18 at 21:41:17 +0800, Aaron Lu wrote:
> > There is one struct cfs_rq and one struct se on each cpu for a taskgroup
> > and when allocation for tg->cfs_rq[X] failed, the already allocated
> > tg->cfs_rq[0]..tg->cfs_rq[X-1] should be freed. The same for tg->se.
> > 
> > Signed-off-by: Aaron Lu <aaron.lu@intel.com>
> > ---
> >  kernel/sched/fair.c | 23 ++++++++++++++++-------
> >  1 file changed, 16 insertions(+), 7 deletions(-)
> > 
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index a80a73909dc2..0f913487928d 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -12443,10 +12443,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
> >  
> >  	tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL);
> >  	if (!tg->cfs_rq)
> > -		goto err;
> > +		return 0;
> >  	tg->se = kcalloc(nr_cpu_ids, sizeof(se), GFP_KERNEL);
> >  	if (!tg->se)
> > -		goto err;
> > +		goto err_free_rq_pointer;
> >  
> >  	tg->shares = NICE_0_LOAD;
> >  
> > @@ -12456,12 +12456,12 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
> >  		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
> >  				      GFP_KERNEL, cpu_to_node(i));
> >  		if (!cfs_rq)
> > -			goto err;
> > +			goto err_free;
> >  
> >  		se = kzalloc_node(sizeof(struct sched_entity_stats),
> >  				  GFP_KERNEL, cpu_to_node(i));
> >  		if (!se)
> > -			goto err_free_rq;
> > +			goto err_free;
> >  
> >  		init_cfs_rq(cfs_rq);
> >  		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
> > @@ -12470,9 +12470,18 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
> >  
> >  	return 1;
> >  
> > -err_free_rq:
> > -	kfree(cfs_rq);
> > -err:
> > +err_free:
> > +	for_each_possible_cpu(i) {
> > +		kfree(tg->cfs_rq[i]);
> > +		kfree(tg->se[i]);
> > +
> > +		if (!tg->cfs_rq[i] && !tg->se[i])
> > +			break;
> > +	}
> > +	kfree(tg->se);
> > +err_free_rq_pointer:
> > +	kfree(tg->cfs_rq);
> > +
> Not sure if I overlooked, if alloc_fair_sched_group() fails in sched_create_group(),
> would sched_free_group()->free_fair_sched_group() do the cleanup?

You are right, I overlooked... Thanks for pointing this out.