Hi Peter,
On Thu, Apr 26, 2018 at 05:53:35PM +0200, Peter Zijlstra wrote:
> On Thu, Apr 26, 2018 at 11:34:19AM +0100, Will Deacon wrote:
> > @@ -290,58 +312,50 @@ void queued_spin_lock_slowpath(struct qspinlock
> > *lock, u32 val)
> > }
> >
> > /*
> > + * If we observe any contention; queue.
> > + */
> > + if (val & ~_Q_LOCKED_MASK)
> > + goto queue;
> > +
> > + /*
> > * trylock || pending
> > *
> > * 0,0,0 -> 0,0,1 ; trylock
> > * 0,0,1 -> 0,1,1 ; pending
> > */
> > + val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
> > + if (!(val & ~_Q_LOCKED_MASK)) {
> > /*
> > + * we're pending, wait for the owner to go away.
> > + *
> > + * *,1,1 -> *,1,0
>
> Tail must be 0 here, right?
Not necessarily. If we're concurrently setting pending with another slowpath
locker, they could queue in the tail behind us, so we can't mess with those
upper bits.
> > + *
> > + * 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 is because not all
> > + * clear_pending_set_locked() implementations imply full
> > + * barriers.
> > */
> > + if (val & _Q_LOCKED_MASK) {
> > + smp_cond_load_acquire(&lock->val.counter,
> > + !(VAL & _Q_LOCKED_MASK));
> > + }
> >
> > /*
> > + * take ownership and clear the pending bit.
> > + *
> > + * *,1,0 -> *,0,1
> > */
>
> Idem.
Same here, hence why clear_pending_set_locked is either a 16-bit store or an
RmW (we can't just clobber the tail with 0).
> > + clear_pending_set_locked(lock);
> > return;
> > + }
> >
> > /*
> > + * If pending was clear but there are waiters in the queue, then
> > + * we need to undo our setting of pending before we queue ourselves.
> > */
> > + if (!(val & _Q_PENDING_MASK))
> > + clear_pending(lock);
>
> This is the branch for when we have !0 tail.
That's the case where "val" has a !0 tail, but I think the comments are
trying to talk about the status of the lockword in memory, no?
> > /*
> > * End of pending bit optimistic spinning and beginning of MCS
>
> > @@ -445,15 +459,15 @@ void queued_spin_lock_slowpath(struct qspinlock
> > *lock, u32 val)
> > * claim the lock:
> > *
> > * n,0,0 -> 0,0,1 : lock, uncontended
> > + * *,*,0 -> *,*,1 : lock, contended
> > *
> > + * If the queue head is the only one in the queue (lock value == tail)
> > + * and nobody is pending, clear the tail code and grab the lock.
> > + * Otherwise, we only need to grab the lock.
> > */
> > for (;;) {
> > /* In the PV case we might already have _Q_LOCKED_VAL set */
> > + if ((val & _Q_TAIL_MASK) != tail || (val & _Q_PENDING_MASK)) {
> > set_locked(lock);
> > break;
> > }
>
> This one hunk is terrible on the brain. I'm fairly sure I get it, but I
> feel that comment can use help. Or at least, I need help reading it.
>
> I'll try and cook up something when my brain starts working again.
Cheers. I think the code is a bit easier to read if you look at it after the
whole series is applied, but the comments could probably still be improved.
Will
