linux-kernel - Re: [PATCH -tip 02/32] sched: Introduce sched_class::pick

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20201126090710.GF2414@hirez.programming.kicks-ass.net>
Date:   Thu, 26 Nov 2020 10:07:10 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Vincent Guittot <vincent.guittot@...aro.org>
Cc:     "Joel Fernandes (Google)" <joel@...lfernandes.org>,
        Nishanth Aravamudan <naravamudan@...italocean.com>,
        Julien Desfossez <jdesfossez@...italocean.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Vineeth Pillai <viremana@...ux.microsoft.com>,
        Aaron Lu <aaron.lwe@...il.com>,
        Aubrey Li <aubrey.intel@...il.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Ingo Molnar <mingo@...nel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Frederic Weisbecker <fweisbec@...il.com>,
        Kees Cook <keescook@...omium.org>,
        Greg Kerr <kerrnel@...gle.com>, Phil Auld <pauld@...hat.com>,
        Valentin Schneider <valentin.schneider@....com>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>,
        Paolo Bonzini <pbonzini@...hat.com>, vineeth@...byteword.org,
        Chen Yu <yu.c.chen@...el.com>,
        Christian Brauner <christian.brauner@...ntu.com>,
        Agata Gruza <agata.gruza@...el.com>,
        Antonio Gomez Iglesias <antonio.gomez.iglesias@...el.com>,
        graf@...zon.com, konrad.wilk@...cle.com, dfaggioli@...e.com,
        Paul Turner <pjt@...gle.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Patrick Bellasi <derkling@...gle.com>,
        Jiang Biao <benbjiang@...cent.com>,
        Alexandre Chartre <alexandre.chartre@...cle.com>,
        James Bottomley <James.Bottomley@...senpartnership.com>,
        OWeisse@...ch.edu, Dhaval Giani <dhaval.giani@...cle.com>,
        Junaid Shahid <junaids@...gle.com>, jsbarnes@...gle.com,
        "Hyser,Chris" <chris.hyser@...cle.com>,
        Ben Segall <bsegall@...gle.com>, Josh Don <joshdon@...gle.com>,
        Hao Luo <haoluo@...gle.com>,
        Tom Lendacky <thomas.lendacky@....com>,
        Aubrey Li <aubrey.li@...ux.intel.com>,
        "Paul E. McKenney" <paulmck@...nel.org>,
        Tim Chen <tim.c.chen@...el.com>
Subject: Re: [PATCH -tip 02/32] sched: Introduce sched_class::pick_task()

On Wed, Nov 25, 2020 at 05:28:36PM +0100, Vincent Guittot wrote:
> On Wed, 18 Nov 2020 at 00:20, Joel Fernandes (Google)

> > +#ifdef CONFIG_SMP
> > +static struct task_struct *pick_task_fair(struct rq *rq)
> > +{
> > +       struct cfs_rq *cfs_rq = &rq->cfs;
> > +       struct sched_entity *se;
> > +
> > +       if (!cfs_rq->nr_running)
> > +               return NULL;
> > +
> > +       do {
> > +               struct sched_entity *curr = cfs_rq->curr;
> > +
> > +               se = pick_next_entity(cfs_rq, NULL);
> 
> Calling pick_next_entity clears buddies. This is fine without
> coresched because the se will be the next one. But calling
> pick_task_fair doesn't mean that the se will be used

Urgh, nice one :/

> > +
> > +               if (curr) {
> > +                       if (se && curr->on_rq)
> > +                               update_curr(cfs_rq);
> > +
> 
> Shouldn't you check if cfs_rq is throttled ?

Hmm,... I suppose we do.

> > +                       if (!se || entity_before(curr, se))
> > +                               se = curr;
> > +               }
> > +
> > +               cfs_rq = group_cfs_rq(se);
> > +       } while (cfs_rq);
> > +
> > +       return task_of(se);
> > +}
> > +#endif

Something like so then?

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4354,6 +4354,8 @@ check_preempt_tick(struct cfs_rq *cfs_rq
 static void
 set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	clear_buddies(cfs_rq, se);
+
 	/* 'current' is not kept within the tree. */
 	if (se->on_rq) {
 		/*
@@ -4440,8 +4442,6 @@ pick_next_entity(struct cfs_rq *cfs_rq,
 		se = cfs_rq->last;
 	}
 
-	clear_buddies(cfs_rq, se);
-
 	return se;
 }
 
@@ -6982,20 +6982,29 @@ static void check_preempt_wakeup(struct
 #ifdef CONFIG_SMP
 static struct task_struct *pick_task_fair(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
-
+	struct cfs_rq *cfs_rq;
+       
+again:
+	cfs_rq = &rq->cfs;
 	if (!cfs_rq->nr_running)
 		return NULL;
 
 	do {
 		struct sched_entity *curr = cfs_rq->curr;
 
-		if (curr && curr->on_rq)
-			update_curr(cfs_rq);
+		/* When we pick for a remote RQ, we'll not have done put_prev_entity() */
+		if (curr) {
+			if (curr->on_rq)
+				update_curr(cfs_rq);
+			else
+				curr = NULL;
 
-		se = pick_next_entity(cfs_rq, curr);
+			if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+				goto again;
+		}
 
+		se = pick_next_entity(cfs_rq, curr);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);