Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1494774 > unrolled thread

[RFC][PATCH 2/4] futex: Use smp_store_release() in mark_wake_futex()

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [RFC][PATCH 2/4] futex: Use smp_store_release() in mark_wake_futex() Peter Zijlstra <peterz@infradead.org> - 2016-10-03 11:30 +0200
    Re: [RFC][PATCH 2/4] futex: Use smp_store_release() in  mark_wake_futex() Steven Rostedt <rostedt@goodmis.org> - 2016-10-03 16:20 +0200
    Re: [RFC][PATCH 2/4] futex: Use smp_store_release() in  mark_wake_futex() Davidlohr Bueso <dave@stgolabs.net> - 2016-10-05 06:00 +0200
      Re: [RFC][PATCH 2/4] futex: Use smp_store_release() in  mark_wake_futex() Peter Zijlstra <peterz@infradead.org> - 2016-10-05 08:30 +0200

#1494774 — [RFC][PATCH 2/4] futex: Use smp_store_release() in mark_wake_futex()

Since the futex_q can dissapear the instruction after assigning NULL,
this really should be a RELEASE barrier. That stops loads from hitting
dead memory too.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/futex.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1288,8 +1288,7 @@ static void mark_wake_futex(struct wake_
 	 * memory barrier is required here to prevent the following
 	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
-	smp_wmb();
-	q->lock_ptr = NULL;
+	smp_store_release(&q->lock_ptr, NULL);
 }
 
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *top_waiter,

[toc] | [next] | [standalone]

#1494893 — Re: [RFC][PATCH 2/4] futex: Use smp_store_release() in mark_wake_futex()

On Mon, 03 Oct 2016 11:12:36 +0200
Peter Zijlstra <peterz@infradead.org> wrote:

> Since the futex_q can dissapear the instruction after assigning NULL,
> this really should be a RELEASE barrier. That stops loads from hitting
> dead memory too.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  kernel/futex.c |    3 +--
>  1 file changed, 1 insertion(+), 2 deletions(-)
> 
> --- a/kernel/futex.c
> +++ b/kernel/futex.c
> @@ -1288,8 +1288,7 @@ static void mark_wake_futex(struct wake_
>  	 * memory barrier is required here to prevent the following
>  	 * store to lock_ptr from getting ahead of the plist_del.
>  	 */
> -	smp_wmb();
> -	q->lock_ptr = NULL;
> +	smp_store_release(&q->lock_ptr, NULL);
>  }
>  
>  static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *top_waiter,
> 

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>

-- Steve

[toc] | [prev] | [next] | [standalone]

#1495688 — Re: [RFC][PATCH 2/4] futex: Use smp_store_release() in mark_wake_futex()

On Mon, 03 Oct 2016, Peter Zijlstra wrote:

>Since the futex_q can dissapear the instruction after assigning NULL,
>this really should be a RELEASE barrier. That stops loads from hitting
>dead memory too.
>
>Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
>---
> kernel/futex.c |    3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
>--- a/kernel/futex.c
>+++ b/kernel/futex.c
>@@ -1288,8 +1288,7 @@ static void mark_wake_futex(struct wake_
> 	 * memory barrier is required here to prevent the following
> 	 * store to lock_ptr from getting ahead of the plist_del.
> 	 */
>-	smp_wmb();
>-	q->lock_ptr = NULL;
>+	smp_store_release(&q->lock_ptr, NULL);
> }

Hmm, what if we relied on the implicit barrier in the wake_q_add()
above and got rid of the smp_wmb altogether? We'd obviously have to
move up __unqueue_futex(), but all we care about is the publishing
store to lock_ptr being the last operation, or at least the plist_del,
such that the wakeup order is respected; ie:

   __unqueue_futex(q);
   wake_q_add(wake_q, p);
   q->lock_ptr = NULL;

Thanks,
Davidlohr

[toc] | [prev] | [next] | [standalone]

#1495713 — Re: [RFC][PATCH 2/4] futex: Use smp_store_release() in mark_wake_futex()

On Tue, Oct 04, 2016 at 08:57:55PM -0700, Davidlohr Bueso wrote:
> On Mon, 03 Oct 2016, Peter Zijlstra wrote:
> 
> >Since the futex_q can dissapear the instruction after assigning NULL,
> >this really should be a RELEASE barrier. That stops loads from hitting
> >dead memory too.
> >
> >Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> >---
> >kernel/futex.c |    3 +--
> >1 file changed, 1 insertion(+), 2 deletions(-)
> >
> >--- a/kernel/futex.c
> >+++ b/kernel/futex.c
> >@@ -1288,8 +1288,7 @@ static void mark_wake_futex(struct wake_
> >	 * memory barrier is required here to prevent the following
> >	 * store to lock_ptr from getting ahead of the plist_del.
> >	 */
> >-	smp_wmb();
> >-	q->lock_ptr = NULL;
> >+	smp_store_release(&q->lock_ptr, NULL);
> >}
> 
> Hmm, what if we relied on the implicit barrier in the wake_q_add()
> above and got rid of the smp_wmb altogether? We'd obviously have to
> move up __unqueue_futex(), but all we care about is the publishing
> store to lock_ptr being the last operation, or at least the plist_del,
> such that the wakeup order is respected; ie:
> 
>   __unqueue_futex(q);
>   wake_q_add(wake_q, p);
>   q->lock_ptr = NULL;

Less obvious but would work I suppose, I didn't look too hard at the
ordering requirements on __unqueue_futex(), but an early morning glance
(without tea) doesn't show any obvious problems with that.

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web