* Paolo Bonzini ([email protected]) wrote:
> For now, only the version returning void is used.  Also, I am not
> providing PPC versions because I would be unable to test it right
> now.

merged, thanks!

Mathieu

> 
> Signed-off-by: Paolo Bonzini <[email protected]>
> ---
>  compat_arch_x86.c       |   25 ++++++++++++
>  tests/test_uatomic.c    |    6 ++-
>  urcu/uatomic_arch_x86.h |   63 ++++++++++++++++++++++++++++++
>  urcu/uatomic_generic.h  |   97 
> +++++++++++++++++++++++++++++++++++++++++++++++
>  4 files changed, 189 insertions(+), 2 deletions(-)
> 
> diff --git a/compat_arch_x86.c b/compat_arch_x86.c
> index 5342c7b..33bf13d 100644
> --- a/compat_arch_x86.c
> +++ b/compat_arch_x86.c
> @@ -201,6 +201,31 @@ unsigned long _compat_uatomic_cmpxchg(void *addr, 
> unsigned long old,
>       return retval;
>  }
>  
> +void _compat_uatomic_or(void *addr, unsigned long v, int len)
> +{
> +     sigset_t mask;
> +
> +     mutex_lock_signal_save(&compat_mutex, &mask);
> +     switch (len) {
> +     case 1:
> +             *(unsigned char *)addr |= (unsigned char)v;
> +             break;
> +     case 2:
> +             *(unsigned short *)addr |= (unsigned short)v;
> +             break;
> +     case 4:
> +             *(unsigned int *)addr |= (unsigned int)v;
> +             break;
> +     default:
> +             /*
> +              * generate an illegal instruction. Cannot catch this with
> +              * linker tricks when optimizations are disabled.
> +              */
> +             __asm__ __volatile__("ud2");
> +     }
> +     mutex_lock_signal_restore(&compat_mutex, &mask);
> +}
> +
>  unsigned long _compat_uatomic_add_return(void *addr, unsigned long v, int 
> len)
>  {
>       sigset_t mask;
> diff --git a/tests/test_uatomic.c b/tests/test_uatomic.c
> index 5682655..37f95a6 100644
> --- a/tests/test_uatomic.c
> +++ b/tests/test_uatomic.c
> @@ -33,8 +33,10 @@ do {                                               \
>       assert(uatomic_read(ptr) == 23);                \
>       uatomic_dec(ptr);                       \
>       assert(uatomic_read(ptr) == 22);                \
> -     v = uatomic_add_return(ptr, 100);       \
> -     assert(v == 122);                       \
> +     v = uatomic_add_return(ptr, 74);        \
> +     assert(v == 96);                        \
> +     assert(uatomic_read(ptr) == 96);        \
> +     uatomic_or(ptr, 58);                    \
>       assert(uatomic_read(ptr) == 122);       \
>       v = uatomic_sub_return(ptr, 1);         \
>       assert(v == 121);                       \
> diff --git a/urcu/uatomic_arch_x86.h b/urcu/uatomic_arch_x86.h
> index 30418c8..c3b5333 100644
> --- a/urcu/uatomic_arch_x86.h
> +++ b/urcu/uatomic_arch_x86.h
> @@ -231,6 +231,60 @@ unsigned long __uatomic_add_return(void *addr, unsigned 
> long val,
>                                                 (unsigned long)(v),   \
>                                                 sizeof(*(addr))))
>  
> +/* uatomic_or */
> +
> +static inline __attribute__((always_inline))
> +void __uatomic_or(void *addr, unsigned long val, int len)
> +{
> +     switch (len) {
> +     case 1:
> +     {
> +             __asm__ __volatile__(
> +             "lock; orb %1, %0"
> +                     : "=m"(*__hp(addr))
> +                     : "iq" ((unsigned char)val)
> +                     : "memory");
> +             return;
> +     }
> +     case 2:
> +     {
> +             __asm__ __volatile__(
> +             "lock; orw %1, %0"
> +                     : "=m"(*__hp(addr))
> +                     : "ir" ((unsigned short)val)
> +                     : "memory");
> +             return;
> +     }
> +     case 4:
> +     {
> +             __asm__ __volatile__(
> +             "lock; orl %1, %0"
> +                     : "=m"(*__hp(addr))
> +                     : "ir" ((unsigned int)val)
> +                     : "memory");
> +             return;
> +     }
> +#if (CAA_BITS_PER_LONG == 64)
> +     case 8:
> +     {
> +             __asm__ __volatile__(
> +             "lock; orq %1, %0"
> +                     : "=m"(*__hp(addr))
> +                     : "er" ((unsigned long)val)
> +                     : "memory");
> +             return;
> +     }
> +#endif
> +     }
> +     /* generate an illegal instruction. Cannot catch this with linker tricks
> +      * when optimizations are disabled. */
> +     __asm__ __volatile__("ud2");
> +     return;
> +}
> +
> +#define _uatomic_or(addr, v)                                            \
> +     (__uatomic_or((addr), (unsigned long)(v), sizeof(*(addr))))
> +
>  /* uatomic_add */
>  
>  static inline __attribute__((always_inline))
> @@ -428,6 +482,13 @@ extern unsigned long _compat_uatomic_cmpxchg(void *addr, 
> unsigned long old,
>                                               (unsigned long)(_new),         \
>                                               sizeof(*(addr))))
>  
> +extern unsigned long _compat_uatomic_or(void *addr,
> +                                     unsigned long _new, int len);
> +#define compat_uatomic_or(addr, v)                                  \
> +     ((__typeof__(*(addr))) _compat_uatomic_or((addr),              \
> +                                               (unsigned long)(v),  \
> +                                               sizeof(*(addr))))
> +
>  extern unsigned long _compat_uatomic_add_return(void *addr,
>                                               unsigned long _new, int len);
>  #define compat_uatomic_add_return(addr, v)                                  \
> @@ -454,6 +515,8 @@ extern unsigned long _compat_uatomic_add_return(void 
> *addr,
>               UATOMIC_COMPAT(cmpxchg(addr, old, _new))
>  #define uatomic_xchg(addr, v)                        \
>               UATOMIC_COMPAT(xchg(addr, v))
> +#define uatomic_or(addr, v)          \
> +             UATOMIC_COMPAT(or(addr, v))
>  #define uatomic_add_return(addr, v)          \
>               UATOMIC_COMPAT(add_return(addr, v))
>  
> diff --git a/urcu/uatomic_generic.h b/urcu/uatomic_generic.h
> index 347e73f..556846f 100644
> --- a/urcu/uatomic_generic.h
> +++ b/urcu/uatomic_generic.h
> @@ -87,6 +87,39 @@ unsigned long _uatomic_cmpxchg(void *addr, unsigned long 
> old,
>                                               sizeof(*(addr))))
>  
>  
> +/* uatomic_or */
> +
> +#ifndef uatomic_or
> +static inline __attribute__((always_inline))
> +void _uatomic_or(void *addr, unsigned long val,
> +              int len)
> +{
> +     switch (len) {
> +#ifdef UATOMIC_HAS_ATOMIC_BYTE
> +     case 1:
> +             __sync_or_and_fetch_1(addr, val);
> +#endif
> +#ifdef UATOMIC_HAS_ATOMIC_SHORT
> +     case 2:
> +             __sync_or_and_fetch_2(addr, val);
> +#endif
> +     case 4:
> +             __sync_or_and_fetch_4(addr, val);
> +#if (CAA_BITS_PER_LONG == 64)
> +     case 8:
> +             __sync_or_and_fetch_8(addr, val);
> +#endif
> +     }
> +     _uatomic_link_error();
> +     return 0;
> +}
> +
> +#define uatomic_or(addr, v)                  \
> +     (_uatomic_or((addr),                    \
> +                  (unsigned long)(v),        \
> +                  sizeof(*(addr))))
> +#endif
> +
>  /* uatomic_add_return */
>  
>  #ifndef uatomic_add_return
> @@ -186,6 +219,70 @@ unsigned long _uatomic_exchange(void *addr, unsigned 
> long val, int len)
>  
>  #else /* #ifndef uatomic_cmpxchg */
>  
> +#ifndef uatomic_or
> +/* uatomic_or */
> +
> +static inline __attribute__((always_inline))
> +void _uatomic_or(void *addr, unsigned long val, int len)
> +{
> +     switch (len) {
> +#ifdef UATOMIC_HAS_ATOMIC_BYTE
> +     case 1:
> +     {
> +             unsigned char old, oldt;
> +
> +             oldt = uatomic_read((unsigned char *)addr);
> +             do {
> +                     old = oldt;
> +                     oldt = _uatomic_cmpxchg(addr, old, old | val, 1);
> +             } while (oldt != old);
> +     }
> +#endif
> +#ifdef UATOMIC_HAS_ATOMIC_SHORT
> +     case 2:
> +     {
> +             unsigned short old, oldt;
> +
> +             oldt = uatomic_read((unsigned short *)addr);
> +             do {
> +                     old = oldt;
> +                     oldt = _uatomic_cmpxchg(addr, old, old | val, 2);
> +             } while (oldt != old);
> +     }
> +#endif
> +     case 4:
> +     {
> +             unsigned int old, oldt;
> +
> +             oldt = uatomic_read((unsigned int *)addr);
> +             do {
> +                     old = oldt;
> +                     oldt = _uatomic_cmpxchg(addr, old, old | val, 4);
> +             } while (oldt != old);
> +     }
> +#if (CAA_BITS_PER_LONG == 64)
> +     case 8:
> +     {
> +             unsigned long old, oldt;
> +
> +             oldt = uatomic_read((unsigned long *)addr);
> +             do {
> +                     old = oldt;
> +                     oldt = _uatomic_cmpxchg(addr, old, old | val, 8);
> +             } while (oldt != old);
> +     }
> +#endif
> +     }
> +     _uatomic_link_error();
> +     return 0;
> +}
> +
> +#define uatomic_or(addr, v)          \
> +     (uatomic_or((addr),             \
> +                 (unsigned long)(v), \
> +                 sizeof(*(addr))))
> +#endif /* #ifndef uatomic_or */
> +
>  #ifndef uatomic_add_return
>  /* uatomic_add_return */
>  
> -- 
> 1.7.4.4
> 
> 
> 
> _______________________________________________
> ltt-dev mailing list
> [email protected]
> http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev
> 

-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com

_______________________________________________
ltt-dev mailing list
[email protected]
http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev

Reply via email to