[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 06 Jun 2014 12:08:46 -0700
From: Jason Low <jason.low2@...com>
To: Davidlohr Bueso <davidlohr@...com>
Cc: peterz@...radead.org, mingo@...nel.org, mpatocka@...hat.com,
torvalds@...ux-foundation.org, waiman.long@...com,
jejb@...isc-linux.org, paulmck@...ux.vnet.ibm.com,
dave.anglin@...l.net, aswin@...com, linux-kernel@...r.kernel.org,
linux-parisc@...r.kernel.org
Subject: Re: [PATCH 1/2] locking/rwsem: Add CONFIG_RWSEM_SPIN_ON_OWNER
On Fri, 2014-06-06 at 11:48 -0700, Davidlohr Bueso wrote:
> On Fri, 2014-06-06 at 11:12 -0700, Davidlohr Bueso wrote:
> > On Fri, 2014-06-06 at 10:13 -0700, Jason Low wrote:
> > > On Fri, 2014-06-06 at 08:55 -0700, Davidlohr Bueso wrote:
> > > > Just like with mutexes (CONFIG_MUTEX_SPIN_ON_OWNER),
> > > > encapsulate the dependencies for rwsem optimistic spinning.
> > > > No logical changes here as it continues to depend on both
> > > > SMP and the XADD algorithm variant.
> > > >
> > > > Signed-off-by: Davidlohr Bueso <davidlohr@...com>
> > > > ---
> > > > include/linux/rwsem.h | 4 ++--
> > > > kernel/Kconfig.locks | 4 ++++
> > > > kernel/locking/rwsem.c | 2 +-
> > > > 3 files changed, 7 insertions(+), 3 deletions(-)
> > >
> > > Do we also want to add an #ifdef CONFIG_RWSEM_SPIN_ON_OWNER in
> > > __init_rwsem() and in the optimistic spinning functions for rwsem-xadd?
> > >
> >
> > Not really, as we conditionally build rwsem-xadd.o based on
> > CONFIG_RWSEM_XCHGADD_ALGORITHM:
> >
> > obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
> > obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
> >
> > So leaving just SMP is ok there.
>
> Of course that's bogus when we add more dependencies (ie 2/2), so yeah,
> we need to add the whole CONFIG_RWSEM_SPIN_ON_OWNER option.
>
> Thanks.
> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> index dacc321..f6b5b96 100644
> --- a/kernel/locking/rwsem-xadd.c
> +++ b/kernel/locking/rwsem-xadd.c
> @@ -82,7 +82,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
> sem->count = RWSEM_UNLOCKED_VALUE;
> raw_spin_lock_init(&sem->wait_lock);
> INIT_LIST_HEAD(&sem->wait_list);
> -#ifdef CONFIG_SMP
> +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
> sem->owner = NULL;
> sem->osq = NULL;
> #endif
And should we also change that in the optimistic spinning functions so
that it defaults to:
static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
return false;
}
in the !CONFIG_RWSEM_SPIN_ON_OWNER case.
Thanks.
> diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
> index 42f806d..e2d3bc7 100644
> --- a/kernel/locking/rwsem.c
> +++ b/kernel/locking/rwsem.c
> @@ -12,7 +12,7 @@
>
> #include <linux/atomic.h>
>
> -#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM)
> +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
> static inline void rwsem_set_owner(struct rw_semaphore *sem)
> {
> sem->owner = current;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists