On Wed, 20 Sep 2017, Andrea Parri wrote:
Instead, how about just removing the release from
atomic_long_sub_return_release()
such that the osq load is not hoisted over the atomic compound (along with
Peter's
comment):
This solution will actually enforce a stronger (full) ordering w.r.t. the
s
On 09/07/2017 08:00 PM, Prateek Sood wrote:
> If a spinner is present, there is a chance that the load of
> rwsem_has_spinner() in rwsem_wake() can be reordered with
> respect to decrement of rwsem count in __up_write() leading
> to wakeup being missed.
>
> spinning writer up_wri
On Wed, Sep 20, 2017 at 07:52:54AM -0700, Davidlohr Bueso wrote:
> On Thu, 07 Sep 2017, Prateek Sood wrote:
> > /*
> >+* __rwsem_down_write_failed_common(sem)
> >+* rwsem_optimistic_spin(sem)
> >+* osq_unlock(sem->osq)
> >+* ...
> >+* atomic_long_add_return(&sem->c
On Thu, 07 Sep 2017, Prateek Sood wrote:
/*
+ * __rwsem_down_write_failed_common(sem)
+ * rwsem_optimistic_spin(sem)
+ * osq_unlock(sem->osq)
+ * ...
+ * atomic_long_add_return(&sem->count)
+ *
+ * - VS -
+ *
+ *
On Thu, Sep 07, 2017 at 08:00:58PM +0530, Prateek Sood wrote:
> If a spinner is present, there is a chance that the load of
> rwsem_has_spinner() in rwsem_wake() can be reordered with
> respect to decrement of rwsem count in __up_write() leading
> to wakeup being missed.
>
> spinning writer
If a spinner is present, there is a chance that the load of
rwsem_has_spinner() in rwsem_wake() can be reordered with
respect to decrement of rwsem count in __up_write() leading
to wakeup being missed.
spinning writer up_write caller
---
On 08/24/2017 06:22 PM, Peter Zijlstra wrote:
> On Thu, Aug 24, 2017 at 02:33:04PM +0200, Peter Zijlstra wrote:
>> On Thu, Aug 24, 2017 at 01:29:27PM +0200, Peter Zijlstra wrote:
>>>
>>> WTH did you not Cc the people that commented on your patch last time?
>>>
>>> On Wed, Aug 23, 2017 at 04:58:55PM
On Thu, Aug 24, 2017 at 02:33:04PM +0200, Peter Zijlstra wrote:
> On Thu, Aug 24, 2017 at 01:29:27PM +0200, Peter Zijlstra wrote:
> >
> > WTH did you not Cc the people that commented on your patch last time?
> >
> > On Wed, Aug 23, 2017 at 04:58:55PM +0530, Prateek Sood wrote:
> > > If a spinner
On Thu, Aug 24, 2017 at 01:29:27PM +0200, Peter Zijlstra wrote:
>
> WTH did you not Cc the people that commented on your patch last time?
>
> On Wed, Aug 23, 2017 at 04:58:55PM +0530, Prateek Sood wrote:
> > If a spinner is present, there is a chance that the load of
> > rwsem_has_spinner() in rw
WTH did you not Cc the people that commented on your patch last time?
On Wed, Aug 23, 2017 at 04:58:55PM +0530, Prateek Sood wrote:
> If a spinner is present, there is a chance that the load of
> rwsem_has_spinner() in rwsem_wake() can be reordered with
> respect to decrement of rwsem count in __
If a spinner is present, there is a chance that the load of
rwsem_has_spinner() in rwsem_wake() can be reordered with
respect to decrement of rwsem count in __up_write() leading
to wakeup being missed.
spinning writer up_write caller
--- -
On Thu, Jul 27, 2017 at 01:47:52AM +0530, Prateek Sood wrote:
> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> index 34e727f..21c111a 100644
> --- a/kernel/locking/rwsem-xadd.c
> +++ b/kernel/locking/rwsem-xadd.c
> @@ -585,6 +585,40 @@ struct rw_semaphore *rwsem_wake(struc
On Thu, Aug 10, 2017 at 10:32:56AM +0200, Andrea Parri wrote:
> On Thu, Jul 27, 2017 at 11:48:53AM -0400, Waiman Long wrote:
> > On 07/26/2017 04:17 PM, Prateek Sood wrote:
> > > If a spinner is present, there is a chance that the load of
> > > rwsem_has_spinner() in rwsem_wake() can be reordered w
On Thu, Jul 27, 2017 at 11:48:53AM -0400, Waiman Long wrote:
> On 07/26/2017 04:17 PM, Prateek Sood wrote:
> > If a spinner is present, there is a chance that the load of
> > rwsem_has_spinner() in rwsem_wake() can be reordered with
> > respect to decrement of rwsem count in __up_write() leading
>
On Thu, Jul 27, 2017 at 11:48:53AM -0400, Waiman Long wrote:
> atomic_long_sub_return_release() is implmented.
I've not had time to really thing about the problem at hand, but this I
can answer:
TSO (x86, s390, sparc): fully serialized
PPC: lwsync; ll/sc (RCpc)
ARM64: ll/sc-release(RCsc)
On 07/26/2017 04:17 PM, Prateek Sood wrote:
> If a spinner is present, there is a chance that the load of
> rwsem_has_spinner() in rwsem_wake() can be reordered with
> respect to decrement of rwsem count in __up_write() leading
> to wakeup being missed.
>
> spinning writer up_writ
If a spinner is present, there is a chance that the load of
rwsem_has_spinner() in rwsem_wake() can be reordered with
respect to decrement of rwsem count in __up_write() leading
to wakeup being missed.
spinning writer up_write caller
---
17 matches
Mail list logo
