On Thu, Nov 01, 2007 at 04:46:36PM +0100, Ingo Molnar wrote:
>
> * Lee Schermerhorn <[EMAIL PROTECTED]> wrote:
>
> > > I guess it was done to make the "template" hacks eaiser. I don't
> > > really find that in good taste, especially for important core
> > > infrastructure. Anyway.
> >
> > Actu
* Lee Schermerhorn <[EMAIL PROTECTED]> wrote:
> > I guess it was done to make the "template" hacks eaiser. I don't
> > really find that in good taste, especially for important core
> > infrastructure. Anyway.
>
> Actually, what I had/have is a cond_resched_rwlock() that I needed to
> convert
On Thu, 2007-11-01 at 15:29 +0100, Nick Piggin wrote:
> On Thu, Nov 01, 2007 at 03:06:05PM +0100, Peter Zijlstra wrote:
> > On Thu, 2007-11-01 at 15:02 +0100, Nick Piggin wrote:
> >
> > > Rename need_lockbreak to spin_needbreak, make it use spin_is_contended to
> > > decouple it from the spinlock
On Thu, Nov 01, 2007 at 03:06:05PM +0100, Peter Zijlstra wrote:
> On Thu, 2007-11-01 at 15:02 +0100, Nick Piggin wrote:
>
> > Rename need_lockbreak to spin_needbreak, make it use spin_is_contended to
> > decouple it from the spinlock implementation, and make it typesafe (rwlocks
> > do not have an
On Thu, 2007-11-01 at 15:02 +0100, Nick Piggin wrote:
> Rename need_lockbreak to spin_needbreak, make it use spin_is_contended to
> decouple it from the spinlock implementation, and make it typesafe (rwlocks
> do not have any need_lockbreak sites -- why do they even get bloated up
> with that brea
The break_lock data structure and code for spinlocks is quite nasty.
Not only does it double the size of a spinlock but it changes locking to
a potentially less optimal trylock.
Put all of that under CONFIG_GENERIC_LOCKBREAK, and introduce a
__raw_spin_is_contended that uses the lock data itself
6 matches
Mail list logo