Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 1 Dec 2020 13:38:21 -0500
From:   Joel Fernandes <joel@joelfernandes.org>
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Nishanth Aravamudan <naravamudan@digitalocean.com>,
        Julien Desfossez <jdesfossez@digitalocean.com>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        Vineeth Pillai <viremana@linux.microsoft.com>,
        Aaron Lu <aaron.lwe@gmail.com>,
        Aubrey Li <aubrey.intel@gmail.com>, tglx@linutronix.de,
        linux-kernel@vger.kernel.org, mingo@kernel.org,
        torvalds@linux-foundation.org, fweisbec@gmail.com,
        keescook@chromium.org, kerrnel@google.com,
        Phil Auld <pauld@redhat.com>,
        Valentin Schneider <valentin.schneider@arm.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
        Paolo Bonzini <pbonzini@redhat.com>, vineeth@bitbyteword.org,
        Chen Yu <yu.c.chen@intel.com>,
        Christian Brauner <christian.brauner@ubuntu.com>,
        Agata Gruza <agata.gruza@intel.com>,
        Antonio Gomez Iglesias <antonio.gomez.iglesias@intel.com>,
        graf@amazon.com, konrad.wilk@oracle.com, dfaggioli@suse.com,
        pjt@google.com, rostedt@goodmis.org, derkling@google.com,
        benbjiang@tencent.com,
        Alexandre Chartre <alexandre.chartre@oracle.com>,
        James.Bottomley@hansenpartnership.com, OWeisse@umich.edu,
        Dhaval Giani <dhaval.giani@oracle.com>,
        Junaid Shahid <junaids@google.com>, jsbarnes@google.com,
        chris.hyser@oracle.com, Ben Segall <bsegall@google.com>,
        Josh Don <joshdon@google.com>, Hao Luo <haoluo@google.com>,
        Tom Lendacky <thomas.lendacky@amd.com>,
        Aubrey Li <aubrey.li@linux.intel.com>,
        "Paul E. McKenney" <paulmck@kernel.org>,
        Tim Chen <tim.c.chen@intel.com>
Subject: Re: [PATCH -tip 22/32] sched: Split the cookie and setup per-task
 cookie on fork
Message-ID: <20201201183821.GA211031@google.com>
References: <20201117232003.3580179-1-joel@joelfernandes.org>
 <20201117232003.3580179-23-joel@joelfernandes.org>
 <20201125125447.GV2414@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20201125125447.GV2414@hirez.programming.kicks-ass.net>
Precedence: bulk

On Wed, Nov 25, 2020 at 01:54:47PM +0100, Peter Zijlstra wrote:
> On Tue, Nov 17, 2020 at 06:19:52PM -0500, Joel Fernandes (Google) wrote:
> > +/* Per-task interface */
> > +static unsigned long sched_core_alloc_task_cookie(void)
> > +{
> > +	struct sched_core_cookie *ptr =
> > +		kmalloc(sizeof(struct sched_core_cookie), GFP_KERNEL);
> > +
> > +	if (!ptr)
> > +		return 0;
> > +	refcount_set(&ptr->refcnt, 1);
> > +
> > +	/*
> > +	 * NOTE: sched_core_put() is not done by put_task_cookie(). Instead, it
> > +	 * is done after the stopper runs.
> > +	 */
> > +	sched_core_get();
> > +	return (unsigned long)ptr;
> > +}
> > +
> > +static bool sched_core_get_task_cookie(unsigned long cookie)
> > +{
> > +	struct sched_core_cookie *ptr = (struct sched_core_cookie *)cookie;
> > +
> > +	/*
> > +	 * NOTE: sched_core_put() is not done by put_task_cookie(). Instead, it
> > +	 * is done after the stopper runs.
> > +	 */
> > +	sched_core_get();
> > +	return refcount_inc_not_zero(&ptr->refcnt);
> > +}
> > +
> > +static void sched_core_put_task_cookie(unsigned long cookie)
> > +{
> > +	struct sched_core_cookie *ptr = (struct sched_core_cookie *)cookie;
> > +
> > +	if (refcount_dec_and_test(&ptr->refcnt))
> > +		kfree(ptr);
> > +}
> 
> > +	/*
> > +	 * NOTE: sched_core_get() is done by sched_core_alloc_task_cookie() or
> > +	 *       sched_core_put_task_cookie(). However, sched_core_put() is done
> > +	 *       by this function *after* the stopper removes the tasks from the
> > +	 *       core queue, and not before. This is just to play it safe.
> > +	 */
> 
> So for no reason what so ever you've made the code more difficult?

You're right, I could just do sched_core_get() in the caller. I changed it as in
the diff below:

---8<-----------------------

diff --git a/kernel/sched/coretag.c b/kernel/sched/coretag.c
index 800c0f8bacfc..75e2edb53a48 100644
--- a/kernel/sched/coretag.c
+++ b/kernel/sched/coretag.c
@@ -274,6 +274,7 @@ void sched_core_change_group(struct task_struct *p, struct task_group *new_tg)
 /* Per-task interface: Used by fork(2) and prctl(2). */
 static void sched_core_put_cookie_work(struct work_struct *ws);
 
+/* Caller has to call sched_core_get() if non-zero value is returned. */
 static unsigned long sched_core_alloc_task_cookie(void)
 {
 	struct sched_core_task_cookie *ck =
@@ -284,11 +285,6 @@ static unsigned long sched_core_alloc_task_cookie(void)
 	refcount_set(&ck->refcnt, 1);
 	INIT_WORK(&ck->work, sched_core_put_cookie_work);
 
-	/*
-	 * NOTE: sched_core_put() is not done by put_task_cookie(). Instead, it
-	 * is done after the stopper runs.
-	 */
-	sched_core_get();
 	return (unsigned long)ck;
 }
 
@@ -354,12 +350,6 @@ int sched_core_share_tasks(struct task_struct *t1, struct task_struct *t2)
 
 	mutex_lock(&sched_core_tasks_mutex);
 
-	/*
-	 * NOTE: sched_core_get() is done by sched_core_alloc_task_cookie() or
-	 *       sched_core_put_task_cookie(). However, sched_core_put() is done
-	 *       by this function *after* the stopper removes the tasks from the
-	 *       core queue, and not before. This is just to play it safe.
-	 */
 	if (!t2) {
 		if (t1->core_task_cookie) {
 			sched_core_put_task_cookie(t1->core_task_cookie);
@@ -370,7 +360,9 @@ int sched_core_share_tasks(struct task_struct *t1, struct task_struct *t2)
 		/* Assign a unique per-task cookie solely for t1. */
 
 		cookie = sched_core_alloc_task_cookie();
-		if (!cookie)
+		if (cookie)
+			sched_core_get();
+		else
 			goto out_unlock;
 
 		if (t1->core_task_cookie) {
@@ -401,7 +393,9 @@ int sched_core_share_tasks(struct task_struct *t1, struct task_struct *t2)
 
 		/* CASE 1. */
 		cookie = sched_core_alloc_task_cookie();
-		if (!cookie)
+		if (cookie)
+			sched_core_get();
+		else
 			goto out_unlock;
 
 		/* Add another reference for the other task. */