Re: [PATCH v5] x86/hpet: Reduce HPET counter read contention

[Waiman Long]

On 08/12/2016 05:38 PM, Dave Hansen wrote:
> On 08/12/2016 02:25 PM, Waiman Long wrote:
> > + * The lock and the hpet value are stored together and can be read in a
> > + * single atomic 64-bit read. It is explicitly assumed that the raw spinlock
> > + * size is 32-bit.
> So what happens when we have all the fun debugging options on?
>
> > typedef struct raw_spinlock {
> >          arch_spinlock_t raw_lock;
> > #ifdef CONFIG_GENERIC_LOCKBREAK
> >          unsigned int break_lock;
> > #endif
> > #ifdef CONFIG_DEBUG_SPINLOCK
> >          unsigned int magic, owner_cpu;
> >          void *owner;
> > #endif
> > #ifdef CONFIG_DEBUG_LOCK_ALLOC
> >          struct lockdep_map dep_map;
> > #endif
> > } raw_spinlock_t;

Sorry, it should be arch_spinlock_t instead. Will fix that.

Cheers,
Longman