Messages in this thread | | | Date | Wed, 30 Apr 2014 09:33:34 -0700 | Subject | Re: [PATCH v2] rwsem: Support optimistic spinning | From | Jason Low <> |
| |
On Wed, Apr 30, 2014 at 2:04 AM, Peter Zijlstra <peterz@infradead.org> wrote: > On Mon, Apr 28, 2014 at 03:09:01PM -0700, Davidlohr Bueso wrote: >> +static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) >> +{ >> + int retval; > > And yet the return value is bool. > >> + struct task_struct *owner; >> + >> + rcu_read_lock(); >> + owner = ACCESS_ONCE(sem->owner); >> + >> + /* Spin only if active writer running */ >> + if (owner) >> + retval = owner->on_cpu; >> + else { >> + /* >> + * When the owner is not set, the sem owner may have just >> + * acquired it and not set the owner yet, or the sem has >> + * been released, or reader active. >> + */ >> + retval = false; >> + } > > And if you init the retval to false, you can leave this entire branch > out. > >> + rcu_read_unlock(); >> + >> + return retval; >> +} > > > Which yields the much shorter: > > static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) > { > struct task_struct *owner; > bool on_cpu = false;
Wouldn't we want to initialize on_cpu = true. For the !owner case, I would expect that we want to spin for the lock.
> rcu_read_lock(); > owner = ACCESS_ONCE(sem->owner); > if (owner) > on_cpu = owner->on_cpu; > rcu_read_unlock(); > > return on_cpu; > }
| |