On Fri, May 30, 2014 at 11:43:55AM -0400, Waiman Long wrote:
> Enabling this configuration feature causes a slight decrease the
> performance of an uncontended lock-unlock operation by about 1-2%
> mainly due to the use of a static key. However, uncontended lock-unlock
> operation are really just a tiny percentage of a real workload. So
> there should no noticeable change in application performance.
No, entirely unacceptable.
> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
> +/**
> + * queue_spin_trylock_unfair - try to acquire the queue spinlock unfairly
> + * @lock : Pointer to queue spinlock structure
> + * Return: 1 if lock acquired, 0 if failed
> + */
> +static __always_inline int queue_spin_trylock_unfair(struct qspinlock *lock)
> +{
> + union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
> +
> + if (!qlock->locked && (cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
> + return 1;
> + return 0;
> +}
> +
> +/**
> + * queue_spin_lock_unfair - acquire a queue spinlock unfairly
> + * @lock: Pointer to queue spinlock structure
> + */
> +static __always_inline void queue_spin_lock_unfair(struct qspinlock *lock)
> +{
> + union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
> +
> + if (likely(cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
> + return;
> + /*
> + * Since the lock is now unfair, we should not activate the 2-task
> + * pending bit spinning code path which disallows lock stealing.
> + */
> + queue_spin_lock_slowpath(lock, -1);
> +}
Why is this needed?
> +/*
> + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will
> + * jump to the unfair versions if the static key virt_unfairlocks_enabled
> + * is true.
> + */
> +#undef arch_spin_lock
> +#undef arch_spin_trylock
> +#undef arch_spin_lock_flags
> +
> +/**
> + * arch_spin_lock - acquire a queue spinlock
> + * @lock: Pointer to queue spinlock structure
> + */
> +static inline void arch_spin_lock(struct qspinlock *lock)
> +{
> + if (static_key_false(&virt_unfairlocks_enabled))
> + queue_spin_lock_unfair(lock);
> + else
> + queue_spin_lock(lock);
> +}
> +
> +/**
> + * arch_spin_trylock - try to acquire the queue spinlock
> + * @lock : Pointer to queue spinlock structure
> + * Return: 1 if lock acquired, 0 if failed
> + */
> +static inline int arch_spin_trylock(struct qspinlock *lock)
> +{
> + if (static_key_false(&virt_unfairlocks_enabled))
> + return queue_spin_trylock_unfair(lock);
> + else
> + return queue_spin_trylock(lock);
> +}
So I really don't see the point of all this? Why do you need special
{try,}lock paths for this case? Are you worried about the upper 24bits?
> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
> index ae1b19d..3723c83 100644
> --- a/kernel/locking/qspinlock.c
> +++ b/kernel/locking/qspinlock.c
> @@ -217,6 +217,14 @@ static __always_inline int try_set_locked(struct qspinlock *lock)
> {
> struct __qspinlock *l = (void *)lock;
>
> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
> + /*
> + * Need to use atomic operation to grab the lock when lock stealing
> + * can happen.
> + */
> + if (static_key_false(&virt_unfairlocks_enabled))
> + return cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0;
> +#endif
> barrier();
> ACCESS_ONCE(l->locked) = _Q_LOCKED_VAL;
> barrier();
Why? If we have a simple test-and-set lock like below, we'll never get
here at all.
> @@ -252,6 +260,18 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
>
> BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
>
> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
> + /*
> + * A simple test and set unfair lock
> + */
> + if (static_key_false(&virt_unfairlocks_enabled)) {
> + cpu_relax(); /* Relax after a failed lock attempt */
Meh, I don't think anybody can tell the difference if you put that in or
not, therefore don't.
> + while (!queue_spin_trylock(lock))
> + cpu_relax();
> + return;
> + }
> +#endif /* CONFIG_VIRT_UNFAIR_LOCKS */
If you're really worried about those upper 24bits, you can always clear
them when you get here.
On Wed, Jun 11, 2014 at 12:54:02PM +0200, Peter Zijlstra wrote:
> > @@ -252,6 +260,18 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
> >
> > BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
> >
> > +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
> > + /*
> > + * A simple test and set unfair lock
> > + */
> > + if (static_key_false(&virt_unfairlocks_enabled)) {
> > + cpu_relax(); /* Relax after a failed lock attempt */
>
> Meh, I don't think anybody can tell the difference if you put that in or
> not, therefore don't.
>
> > + while (!queue_spin_trylock(lock))
> > + cpu_relax();
> > + return;
> > + }
> > +#endif /* CONFIG_VIRT_UNFAIR_LOCKS */
>
> If you're really worried about those upper 24bits, you can always clear
> them when you get here.
I don't think its a problem at all; flipping the static_key requires
stop_machine, which guarantees us that there are no spinlocks held. So I
think you can actually BUG_ON() the upper 24bits.
On 6/11/2014 6:54 AM, Peter Zijlstra wrote:
> On Fri, May 30, 2014 at 11:43:55AM -0400, Waiman Long wrote:
>> Enabling this configuration feature causes a slight decrease the
>> performance of an uncontended lock-unlock operation by about 1-2%
>> mainly due to the use of a static key. However, uncontended lock-unlock
>> operation are really just a tiny percentage of a real workload. So
>> there should no noticeable change in application performance.
> No, entirely unacceptable.
>
>> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
>> +/**
>> + * queue_spin_trylock_unfair - try to acquire the queue spinlock unfairly
>> + * @lock : Pointer to queue spinlock structure
>> + * Return: 1 if lock acquired, 0 if failed
>> + */
>> +static __always_inline int queue_spin_trylock_unfair(struct qspinlock *lock)
>> +{
>> + union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
>> +
>> + if (!qlock->locked && (cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
>> + return 1;
>> + return 0;
>> +}
>> +
>> +/**
>> + * queue_spin_lock_unfair - acquire a queue spinlock unfairly
>> + * @lock: Pointer to queue spinlock structure
>> + */
>> +static __always_inline void queue_spin_lock_unfair(struct qspinlock *lock)
>> +{
>> + union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
>> +
>> + if (likely(cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
>> + return;
>> + /*
>> + * Since the lock is now unfair, we should not activate the 2-task
>> + * pending bit spinning code path which disallows lock stealing.
>> + */
>> + queue_spin_lock_slowpath(lock, -1);
>> +}
> Why is this needed?
I added the unfair version of lock and trylock as my original version
isn't a simple test-and-set lock. Now I changed the core part to use the
simple test-and-set lock. However, I still think that an unfair version
in the fast path can be helpful to performance when both the unfair lock
and paravirt spinlock are enabled. In this case, paravirt spinlock code
will disable the unfair lock code in the slowpath, but still allow the
unfair version in the fast path to get the best possible performance in
a virtual guest.
Yes, I could take that out to allow either unfair or paravirt spinlock,
but not both. I do think that a little bit of unfairness will help in
the virtual environment.
>> +/*
>> + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will
>> + * jump to the unfair versions if the static key virt_unfairlocks_enabled
>> + * is true.
>> + */
>> +#undef arch_spin_lock
>> +#undef arch_spin_trylock
>> +#undef arch_spin_lock_flags
>> +
>> +/**
>> + * arch_spin_lock - acquire a queue spinlock
>> + * @lock: Pointer to queue spinlock structure
>> + */
>> +static inline void arch_spin_lock(struct qspinlock *lock)
>> +{
>> + if (static_key_false(&virt_unfairlocks_enabled))
>> + queue_spin_lock_unfair(lock);
>> + else
>> + queue_spin_lock(lock);
>> +}
>> +
>> +/**
>> + * arch_spin_trylock - try to acquire the queue spinlock
>> + * @lock : Pointer to queue spinlock structure
>> + * Return: 1 if lock acquired, 0 if failed
>> + */
>> +static inline int arch_spin_trylock(struct qspinlock *lock)
>> +{
>> + if (static_key_false(&virt_unfairlocks_enabled))
>> + return queue_spin_trylock_unfair(lock);
>> + else
>> + return queue_spin_trylock(lock);
>> +}
> So I really don't see the point of all this? Why do you need special
> {try,}lock paths for this case? Are you worried about the upper 24bits?
No, as I said above. I was planning for the coexistence of unfair lock
in the fast path and paravirt spinlock in the slowpath.
>> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
>> index ae1b19d..3723c83 100644
>> --- a/kernel/locking/qspinlock.c
>> +++ b/kernel/locking/qspinlock.c
>> @@ -217,6 +217,14 @@ static __always_inline int try_set_locked(struct qspinlock *lock)
>> {
>> struct __qspinlock *l = (void *)lock;
>>
>> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
>> + /*
>> + * Need to use atomic operation to grab the lock when lock stealing
>> + * can happen.
>> + */
>> + if (static_key_false(&virt_unfairlocks_enabled))
>> + return cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0;
>> +#endif
>> barrier();
>> ACCESS_ONCE(l->locked) = _Q_LOCKED_VAL;
>> barrier();
> Why? If we have a simple test-and-set lock like below, we'll never get
> here at all.
Again, it is due the coexistence of unfair lock in fast path and
paravirt spinlock in the slowpath.
>> @@ -252,6 +260,18 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
>>
>> BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
>>
>> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
>> + /*
>> + * A simple test and set unfair lock
>> + */
>> + if (static_key_false(&virt_unfairlocks_enabled)) {
>> + cpu_relax(); /* Relax after a failed lock attempt */
> Meh, I don't think anybody can tell the difference if you put that in or
> not, therefore don't.
Yes, I can take out the cpu_relax() here.
-Longman
On Wed, Jun 11, 2014 at 09:37:55PM -0400, Long, Wai Man wrote:
>
> On 6/11/2014 6:54 AM, Peter Zijlstra wrote:
> >On Fri, May 30, 2014 at 11:43:55AM -0400, Waiman Long wrote:
> >>Enabling this configuration feature causes a slight decrease the
> >>performance of an uncontended lock-unlock operation by about 1-2%
> >>mainly due to the use of a static key. However, uncontended lock-unlock
> >>operation are really just a tiny percentage of a real workload. So
> >>there should no noticeable change in application performance.
> >No, entirely unacceptable.
> >
> >>+#ifdef CONFIG_VIRT_UNFAIR_LOCKS
> >>+/**
> >>+ * queue_spin_trylock_unfair - try to acquire the queue spinlock unfairly
> >>+ * @lock : Pointer to queue spinlock structure
> >>+ * Return: 1 if lock acquired, 0 if failed
> >>+ */
> >>+static __always_inline int queue_spin_trylock_unfair(struct qspinlock *lock)
> >>+{
> >>+ union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
> >>+
> >>+ if (!qlock->locked && (cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
> >>+ return 1;
> >>+ return 0;
> >>+}
> >>+
> >>+/**
> >>+ * queue_spin_lock_unfair - acquire a queue spinlock unfairly
> >>+ * @lock: Pointer to queue spinlock structure
> >>+ */
> >>+static __always_inline void queue_spin_lock_unfair(struct qspinlock *lock)
> >>+{
> >>+ union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
> >>+
> >>+ if (likely(cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
> >>+ return;
> >>+ /*
> >>+ * Since the lock is now unfair, we should not activate the 2-task
> >>+ * pending bit spinning code path which disallows lock stealing.
> >>+ */
> >>+ queue_spin_lock_slowpath(lock, -1);
> >>+}
> >Why is this needed?
>
> I added the unfair version of lock and trylock as my original version isn't
> a simple test-and-set lock. Now I changed the core part to use the simple
> test-and-set lock. However, I still think that an unfair version in the fast
> path can be helpful to performance when both the unfair lock and paravirt
> spinlock are enabled. In this case, paravirt spinlock code will disable the
> unfair lock code in the slowpath, but still allow the unfair version in the
> fast path to get the best possible performance in a virtual guest.
>
> Yes, I could take that out to allow either unfair or paravirt spinlock, but
> not both. I do think that a little bit of unfairness will help in the
> virtual environment.
When will you learn to like simplicity and stop this massive over
engineering effort?
There's no sane reason to have the test-and-set virt and paravirt locks
enabled at the same bloody time.
There's 3 distinct cases:
- native
- virt
- paravirt
And they do not overlap. Furthermore, if there is any possibility at all
of not polluting the native code, grab it with both hands.
Native performance is king, try your very utmost bestest to preserve
that, paravirt is a distant second and nobody sane should care about the
virt case at all.
If you want extra lock stealing in the paravirt case, put it in the
slowpath code before you start queueing.
On 06/12/2014 01:50 AM, Peter Zijlstra wrote:
> On Wed, Jun 11, 2014 at 09:37:55PM -0400, Long, Wai Man wrote:
>> On 6/11/2014 6:54 AM, Peter Zijlstra wrote:
>>> On Fri, May 30, 2014 at 11:43:55AM -0400, Waiman Long wrote:
>>>> Enabling this configuration feature causes a slight decrease the
>>>> performance of an uncontended lock-unlock operation by about 1-2%
>>>> mainly due to the use of a static key. However, uncontended lock-unlock
>>>> operation are really just a tiny percentage of a real workload. So
>>>> there should no noticeable change in application performance.
>>> No, entirely unacceptable.
>>>
>>>> +#ifdef CONFIG_VIRT_UNFAIR_LOCKS
>>>> +/**
>>>> + * queue_spin_trylock_unfair - try to acquire the queue spinlock unfairly
>>>> + * @lock : Pointer to queue spinlock structure
>>>> + * Return: 1 if lock acquired, 0 if failed
>>>> + */
>>>> +static __always_inline int queue_spin_trylock_unfair(struct qspinlock *lock)
>>>> +{
>>>> + union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
>>>> +
>>>> + if (!qlock->locked&& (cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
>>>> + return 1;
>>>> + return 0;
>>>> +}
>>>> +
>>>> +/**
>>>> + * queue_spin_lock_unfair - acquire a queue spinlock unfairly
>>>> + * @lock: Pointer to queue spinlock structure
>>>> + */
>>>> +static __always_inline void queue_spin_lock_unfair(struct qspinlock *lock)
>>>> +{
>>>> + union arch_qspinlock *qlock = (union arch_qspinlock *)lock;
>>>> +
>>>> + if (likely(cmpxchg(&qlock->locked, 0, _Q_LOCKED_VAL) == 0))
>>>> + return;
>>>> + /*
>>>> + * Since the lock is now unfair, we should not activate the 2-task
>>>> + * pending bit spinning code path which disallows lock stealing.
>>>> + */
>>>> + queue_spin_lock_slowpath(lock, -1);
>>>> +}
>>> Why is this needed?
>> I added the unfair version of lock and trylock as my original version isn't
>> a simple test-and-set lock. Now I changed the core part to use the simple
>> test-and-set lock. However, I still think that an unfair version in the fast
>> path can be helpful to performance when both the unfair lock and paravirt
>> spinlock are enabled. In this case, paravirt spinlock code will disable the
>> unfair lock code in the slowpath, but still allow the unfair version in the
>> fast path to get the best possible performance in a virtual guest.
>>
>> Yes, I could take that out to allow either unfair or paravirt spinlock, but
>> not both. I do think that a little bit of unfairness will help in the
>> virtual environment.
> When will you learn to like simplicity and stop this massive over
> engineering effort?
>
> There's no sane reason to have the test-and-set virt and paravirt locks
> enabled at the same bloody time.
>
> There's 3 distinct cases:
>
> - native
> - virt
> - paravirt
>
> And they do not overlap. Furthermore, if there is any possibility at all
> of not polluting the native code, grab it with both hands.
>
> Native performance is king, try your very utmost bestest to preserve
> that, paravirt is a distant second and nobody sane should care about the
> virt case at all.
The patch won't affect native performance unless the kernel is built
with VIRT_UNFAIR_LOCKS selected. The same is also true when
PARAVIRT_SPINLOCKS is selected. There is no way around that.
I do agree that I may over-engineer on this patch, but my main purpose
is to achieve the best possible performance and so may sacrifice
simplicity in some cases. Still allowing lock stealing in the fastpath
is already much simpler than what my original patch was doing with lock
stealing in the slowpath. If you still think it is too complex, I am
willing to take that out if it is what I need to get your approval.
Please also review the rests of the pvspinlock patches and let me know
if you have other comments. I would like to have one more version to go
and be done with it.
Thanks,
Longman
On Thu, Jun 12, 2014 at 05:08:28PM -0400, Waiman Long wrote:
> >Native performance is king, try your very utmost bestest to preserve
> >that, paravirt is a distant second and nobody sane should care about the
> >virt case at all.
>
> The patch won't affect native performance unless the kernel is built with
> VIRT_UNFAIR_LOCKS selected. The same is also true when PARAVIRT_SPINLOCKS is
> selected. There is no way around that.
VIRT_UNFAIR_LOCKS is an impossible switch to have; a distro cannot make
the right choice.
> I do agree that I may over-engineer on this patch,
Simple things first, then add complexity.