Re: [PATCH v6] taskstats: fix data-race

[Christian Brauner]

On Mon, Oct 21, 2019 at 02:19:01PM +0200, Rasmus Villemoes wrote:
> On 21/10/2019 13.33, Christian Brauner wrote:
> > The first approach used smp_load_acquire() and smp_store_release().
> > However, after having discussed this it seems that the data dependency
> > for kmem_cache_alloc() would be fixed by WRITE_ONCE().
> > Furthermore, the smp_load_acquire() would only manage to order the stats
> > check before the thread_group_empty() check. So it seems just using
> > READ_ONCE() and WRITE_ONCE() will do the job and I wanted to bring this
> > up for discussion at least.
> > 
> > /* v6 */
> > - Christian Brauner <christian.brauner@xxxxxxxxxx>:
> >   - bring up READ_ONCE()/WRITE_ONCE() approach for discussion
> > ---
> >  kernel/taskstats.c | 26 +++++++++++++++-----------
> >  1 file changed, 15 insertions(+), 11 deletions(-)
> > 
> > diff --git a/kernel/taskstats.c b/kernel/taskstats.c
> > index 13a0f2e6ebc2..111bb4139aa2 100644
> > --- a/kernel/taskstats.c
> > +++ b/kernel/taskstats.c
> > @@ -554,25 +554,29 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
> >  static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
> >  {
> >  	struct signal_struct *sig = tsk->signal;
> > -	struct taskstats *stats;
> > +	struct taskstats *stats_new, *stats;
> >  
> > -	if (sig->stats || thread_group_empty(tsk))
> > -		goto ret;
> > +	/* Pairs with WRITE_ONCE() below. */
> > +	stats = READ_ONCE(sig->stats);
> > +	if (stats || thread_group_empty(tsk))
> > +		return stats;
> >  
> >  	/* No problem if kmem_cache_zalloc() fails */
> > -	stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
> > +	stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
> >  
> >  	spin_lock_irq(&tsk->sighand->siglock);
> > -	if (!sig->stats) {
> > -		sig->stats = stats;
> > -		stats = NULL;
> > +	if (!stats) {
> > +		stats = stats_new;
> > +		/* Pairs with READ_ONCE() above. */
> > +		WRITE_ONCE(sig->stats, stats_new);
> > +		stats_new = NULL;
> 
> No idea about the memory ordering issues, but don't you need to
> load/check sig->stats again? Otherwise it seems that two threads might
> both see !sig->stats, both allocate a stats_new, and both
> unconditionally in turn assign their stats_new to sig->stats. Then the
> first assignment ends up becoming a memory leak (and any writes through
> that pointer done by the caller end up in /dev/null...)

Trigger hand too fast. I guess you're thinking sm like:

diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e6ebc2..c4e1ed11e785 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,27 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
-	struct taskstats *stats;
+	struct taskstats *stats_new, *stats;
 
-	if (sig->stats || thread_group_empty(tsk))
-		goto ret;
+	stats = READ_ONCE(sig->stats);
+	if (stats || thread_group_empty(tsk))
+		return stats;
 
-	/* No problem if kmem_cache_zalloc() fails */
-	stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+	stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	if (!sig->stats) {
-		sig->stats = stats;
-		stats = NULL;
+	stats = READ_ONCE(sig->stats);
+	if (!stats) {
+		stats = stats_new;
+		WRITE_ONCE(sig->stats, stats_new);
+		stats_new = NULL;
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (stats)
-		kmem_cache_free(taskstats_cache, stats);
-ret:
-	return sig->stats;
+	if (stats_new)
+		kmem_cache_free(taskstats_cache, stats_new);
+
+	return stats;
 }