Re: [PATCH 3/6] x86/ticketlock: Use C for __ticket_spin_unlock

[Nick Piggin]

On Tue, Jan 25, 2011 at 10:41 AM, Jeremy Fitzhardinge <jeremy@xxxxxxxx> wrote:
> From: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
>
> If we don't need to use a locked inc for unlock, then implement it in C.
>
> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
> ---
>  arch/x86/include/asm/spinlock.h |   32 +++++++++++++++++---------------
>  1 files changed, 17 insertions(+), 15 deletions(-)
>
> diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
> index f48a6e3..0170ba9 100644
> --- a/arch/x86/include/asm/spinlock.h
> +++ b/arch/x86/include/asm/spinlock.h
> @@ -33,9 +33,21 @@
>  * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
>  * (PPro errata 66, 92)
>  */
> -# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
> +static __always_inline void __ticket_unlock_release(struct arch_spinlock *lock)
> +{
> +       if (sizeof(lock->tickets.head) == sizeof(u8))
> +               asm (LOCK_PREFIX "incb %0"
> +                    : "+m" (lock->tickets.head) : : "memory");
> +       else
> +               asm (LOCK_PREFIX "incw %0"
> +                    : "+m" (lock->tickets.head) : : "memory");
> +
> +}
>  #else
> -# define UNLOCK_LOCK_PREFIX
> +static __always_inline void __ticket_unlock_release(struct arch_spinlock *lock)
> +{
> +       lock->tickets.head++;
> +}
>  #endif
>
>  /*
> @@ -93,14 +105,6 @@ static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
>
>        return tmp;
>  }
> -
> -static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
> -{
> -       asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
> -                    : "+m" (lock->slock)
> -                    :
> -                    : "memory", "cc");
> -}
>  #else
>  static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
>  {
> @@ -144,15 +148,13 @@ static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
>
>        return tmp;
>  }
> +#endif
>
>  static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
>  {
> -       asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
> -                    : "+m" (lock->slock)
> -                    :
> -                    : "memory", "cc");
> +       __ticket_unlock_release(lock);
> +       barrier();              /* prevent reordering into locked region */
>  }
> -#endif

The barrier is wrong.

What makes me a tiny bit uneasy is that gcc is allowed to implement
this any way it wishes. OK there may be a NULL intersection of possible
valid assembly which is a buggy unlock... but relying on gcc to implement
lock primitives is scary. Does this really help in a way that can't be done
with the assembly versions?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/