Linux Virtualization - Apr 2014 - [PATCH v9 05/19] qspinlock: Optimize for smaller NR_CPUS

* Waiman Long <waiman.long at hp.com> wrote:
> On 04/17/2014 11:58 AM, Peter Zijlstra wrote:
> >On Thu, Apr 17, 2014 at 11:03:57AM -0400, Waiman Long wrote:
> >>+static __always_inline void
> >>+clear_pending_set_locked(struct qspinlock *lock, u32 val)
> >>+{
> >>+	struct __qspinlock *l = (void *)lock;
> >>+
> >>+	ACCESS_ONCE(l->locked_pending) = 1;
> >>+}
> >>@@ -157,8 +251,13 @@ static inline int trylock_pending(struct
qspinlock *lock, u32 *pval)
> >>  	 * we're pending, wait for the owner to go away.
> >>  	 *
> >>  	 * *,1,1 ->  *,1,0
> >>+	 *
> >>+	 * this wait loop must be a load-acquire such that we match the
> >>+	 * store-release that clears the locked bit and create lock
> >>+	 * sequentiality; this because not all
try_clear_pending_set_locked()
> >>+	 * implementations imply full barriers.
> >You renamed the function referred in the above comment.
> >
> 
> Sorry, will fix the comments.
I suggest not renaming the function instead. 
try_clear_pending_set_locked() tells the intent in a clearer fashion.

Thanks,

	Ingo

On 04/18/2014 03:46 AM, Ingo Molnar wrote:
> * Waiman Long<waiman.long at hp.com>  wrote:
>
>> On 04/17/2014 11:58 AM, Peter Zijlstra wrote:
>>> On Thu, Apr 17, 2014 at 11:03:57AM -0400, Waiman Long wrote:
>>>> +static __always_inline void
>>>> +clear_pending_set_locked(struct qspinlock *lock, u32 val)
>>>> +{
>>>> +	struct __qspinlock *l = (void *)lock;
>>>> +
>>>> +	ACCESS_ONCE(l->locked_pending) = 1;
>>>> +}
>>>> @@ -157,8 +251,13 @@ static inline int trylock_pending(struct
qspinlock *lock, u32 *pval)
>>>>   	 * we're pending, wait for the owner to go away.
>>>>   	 *
>>>>   	 * *,1,1 ->   *,1,0
>>>> +	 *
>>>> +	 * this wait loop must be a load-acquire such that we match
the
>>>> +	 * store-release that clears the locked bit and create lock
>>>> +	 * sequentiality; this because not all
try_clear_pending_set_locked()
>>>> +	 * implementations imply full barriers.
>>> You renamed the function referred in the above comment.
>>>
>> Sorry, will fix the comments.
> I suggest not renaming the function instead.
> try_clear_pending_set_locked() tells the intent in a clearer fashion.
>
> Thanks,
>
> 	Ingo
I usually use the word "try" if there is a possibility of failure. 
However, the function will always succeed, albeit by waiting a bit in 
some cases. That is why I remove "try" from the name.

-Longman

* Waiman Long <waiman.long at hp.com> wrote:
> On 04/18/2014 03:46 AM, Ingo Molnar wrote:
> >* Waiman Long<waiman.long at hp.com>  wrote:
> >
> >>On 04/17/2014 11:58 AM, Peter Zijlstra wrote:
> >>>On Thu, Apr 17, 2014 at 11:03:57AM -0400, Waiman Long wrote:
> >>>>+static __always_inline void
> >>>>+clear_pending_set_locked(struct qspinlock *lock, u32 val)
> >>>>+{
> >>>>+	struct __qspinlock *l = (void *)lock;
> >>>>+
> >>>>+	ACCESS_ONCE(l->locked_pending) = 1;
> >>>>+}
> >>>>@@ -157,8 +251,13 @@ static inline int
trylock_pending(struct qspinlock *lock, u32 *pval)
> >>>>  	 * we're pending, wait for the owner to go away.
> >>>>  	 *
> >>>>  	 * *,1,1 ->   *,1,0
> >>>>+	 *
> >>>>+	 * this wait loop must be a load-acquire such that we
match the
> >>>>+	 * store-release that clears the locked bit and create
lock
> >>>>+	 * sequentiality; this because not all
try_clear_pending_set_locked()
> >>>>+	 * implementations imply full barriers.
> >>>You renamed the function referred in the above comment.
> >>>
> >>Sorry, will fix the comments.
> >I suggest not renaming the function instead.
> >try_clear_pending_set_locked() tells the intent in a clearer fashion.
> >
> >Thanks,
> >
> >	Ingo
> 
> I usually use the word "try" if there is a possibility of
failure.
> However, the function will always succeed, albeit by waiting a bit 
> in some cases. That is why I remove "try" from the name.
Fair enough!

Thanks,

	Ingo