From a075227948636e10aa2cc2d8725fbbab27681d4a Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 May 2007 00:34:44 -0700 Subject: [PATCH] local_t: i386 extension Signed-off-by: Mathieu Desnoyers Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-i386/local.h | 203 +++++++++++++++++++++++++++++++++----- include/asm-i386/system.h | 59 ++++++++++- 2 files changed, 235 insertions(+), 27 deletions(-) diff --git a/include/asm-i386/local.h b/include/asm-i386/local.h index 12060e22f7e..e13d3e98823 100644 --- a/include/asm-i386/local.h +++ b/include/asm-i386/local.h @@ -2,47 +2,198 @@ #define _ARCH_I386_LOCAL_H #include +#include +#include typedef struct { - volatile long counter; + atomic_long_t a; } local_t; -#define LOCAL_INIT(i) { (i) } +#define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } -#define local_read(v) ((v)->counter) -#define local_set(v,i) (((v)->counter) = (i)) +#define local_read(l) atomic_long_read(&(l)->a) +#define local_set(l,i) atomic_long_set(&(l)->a, (i)) -static __inline__ void local_inc(local_t *v) +static __inline__ void local_inc(local_t *l) { __asm__ __volatile__( "incl %0" - :"+m" (v->counter)); + :"+m" (l->a.counter)); } -static __inline__ void local_dec(local_t *v) +static __inline__ void local_dec(local_t *l) { __asm__ __volatile__( "decl %0" - :"+m" (v->counter)); + :"+m" (l->a.counter)); } -static __inline__ void local_add(long i, local_t *v) +static __inline__ void local_add(long i, local_t *l) { __asm__ __volatile__( "addl %1,%0" - :"+m" (v->counter) + :"+m" (l->a.counter) :"ir" (i)); } -static __inline__ void local_sub(long i, local_t *v) +static __inline__ void local_sub(long i, local_t *l) { __asm__ __volatile__( "subl %1,%0" - :"+m" (v->counter) + :"+m" (l->a.counter) :"ir" (i)); } +/** + * local_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @l: pointer of type local_t + * + * Atomically subtracts @i from @l and returns + * true if the result is zero, or false for all + * other cases. + */ +static __inline__ int local_sub_and_test(long i, local_t *l) +{ + unsigned char c; + + __asm__ __volatile__( + "subl %2,%0; sete %1" + :"+m" (l->a.counter), "=qm" (c) + :"ir" (i) : "memory"); + return c; +} + +/** + * local_dec_and_test - decrement and test + * @l: pointer of type local_t + * + * Atomically decrements @l by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __inline__ int local_dec_and_test(local_t *l) +{ + unsigned char c; + + __asm__ __volatile__( + "decl %0; sete %1" + :"+m" (l->a.counter), "=qm" (c) + : : "memory"); + return c != 0; +} + +/** + * local_inc_and_test - increment and test + * @l: pointer of type local_t + * + * Atomically increments @l by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __inline__ int local_inc_and_test(local_t *l) +{ + unsigned char c; + + __asm__ __volatile__( + "incl %0; sete %1" + :"+m" (l->a.counter), "=qm" (c) + : : "memory"); + return c != 0; +} + +/** + * local_add_negative - add and test if negative + * @l: pointer of type local_t + * @i: integer value to add + * + * Atomically adds @i to @l and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __inline__ int local_add_negative(long i, local_t *l) +{ + unsigned char c; + + __asm__ __volatile__( + "addl %2,%0; sets %1" + :"+m" (l->a.counter), "=qm" (c) + :"ir" (i) : "memory"); + return c; +} + +/** + * local_add_return - add and return + * @l: pointer of type local_t + * @i: integer value to add + * + * Atomically adds @i to @l and returns @i + @l + */ +static __inline__ long local_add_return(long i, local_t *l) +{ + long __i; +#ifdef CONFIG_M386 + unsigned long flags; + if(unlikely(boot_cpu_data.x86==3)) + goto no_xadd; +#endif + /* Modern 486+ processor */ + __i = i; + __asm__ __volatile__( + "xaddl %0, %1;" + :"+r" (i), "+m" (l->a.counter) + : : "memory"); + return i + __i; + +#ifdef CONFIG_M386 +no_xadd: /* Legacy 386 processor */ + local_irq_save(flags); + __i = local_read(l); + local_set(l, i + __i); + local_irq_restore(flags); + return i + __i; +#endif +} + +static __inline__ long local_sub_return(long i, local_t *l) +{ + return local_add_return(-i,l); +} + +#define local_inc_return(l) (local_add_return(1,l)) +#define local_dec_return(l) (local_sub_return(1,l)) + +#define local_cmpxchg(l, o, n) \ + (cmpxchg_local(&((l)->a.counter), (o), (n))) +/* Always has a lock prefix */ +#define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) + +/** + * local_add_unless - add unless the number is a given value + * @l: pointer of type local_t + * @a: the amount to add to l... + * @u: ...unless l is equal to u. + * + * Atomically adds @a to @l, so long as it was not @u. + * Returns non-zero if @l was not @u, and zero otherwise. + */ +#define local_add_unless(l, a, u) \ +({ \ + long c, old; \ + c = local_read(l); \ + for (;;) { \ + if (unlikely(c == (u))) \ + break; \ + old = local_cmpxchg((l), c, c + (a)); \ + if (likely(old == c)) \ + break; \ + c = old; \ + } \ + c != (u); \ +}) +#define local_inc_not_zero(l) local_add_unless((l), 1, 0) + /* On x86, these are no better than the atomic variants. */ #define __local_inc(l) local_inc(l) #define __local_dec(l) local_dec(l) @@ -56,27 +207,27 @@ static __inline__ void local_sub(long i, local_t *v) /* Need to disable preemption for the cpu local counters otherwise we could still access a variable of a previous CPU in a non atomic way. */ -#define cpu_local_wrap_v(v) \ +#define cpu_local_wrap_v(l) \ ({ local_t res__; \ preempt_disable(); \ - res__ = (v); \ + res__ = (l); \ preempt_enable(); \ res__; }) -#define cpu_local_wrap(v) \ +#define cpu_local_wrap(l) \ ({ preempt_disable(); \ - v; \ + l; \ preempt_enable(); }) \ -#define cpu_local_read(v) cpu_local_wrap_v(local_read(&__get_cpu_var(v))) -#define cpu_local_set(v, i) cpu_local_wrap(local_set(&__get_cpu_var(v), (i))) -#define cpu_local_inc(v) cpu_local_wrap(local_inc(&__get_cpu_var(v))) -#define cpu_local_dec(v) cpu_local_wrap(local_dec(&__get_cpu_var(v))) -#define cpu_local_add(i, v) cpu_local_wrap(local_add((i), &__get_cpu_var(v))) -#define cpu_local_sub(i, v) cpu_local_wrap(local_sub((i), &__get_cpu_var(v))) +#define cpu_local_read(l) cpu_local_wrap_v(local_read(&__get_cpu_var(l))) +#define cpu_local_set(l, i) cpu_local_wrap(local_set(&__get_cpu_var(l), (i))) +#define cpu_local_inc(l) cpu_local_wrap(local_inc(&__get_cpu_var(l))) +#define cpu_local_dec(l) cpu_local_wrap(local_dec(&__get_cpu_var(l))) +#define cpu_local_add(i, l) cpu_local_wrap(local_add((i), &__get_cpu_var(l))) +#define cpu_local_sub(i, l) cpu_local_wrap(local_sub((i), &__get_cpu_var(l))) -#define __cpu_local_inc(v) cpu_local_inc(v) -#define __cpu_local_dec(v) cpu_local_dec(v) -#define __cpu_local_add(i, v) cpu_local_add((i), (v)) -#define __cpu_local_sub(i, v) cpu_local_sub((i), (v)) +#define __cpu_local_inc(l) cpu_local_inc(l) +#define __cpu_local_dec(l) cpu_local_dec(l) +#define __cpu_local_add(i, l) cpu_local_add((i), (l)) +#define __cpu_local_sub(i, l) cpu_local_sub((i), (l)) #endif /* _ARCH_I386_LOCAL_H */ diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h index c3a58c08c49..e0454afb950 100644 --- a/include/asm-i386/system.h +++ b/include/asm-i386/system.h @@ -305,6 +305,9 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz #define sync_cmpxchg(ptr,o,n)\ ((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\ (unsigned long)(n),sizeof(*(ptr)))) +#define cmpxchg_local(ptr,o,n)\ + ((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\ + (unsigned long)(n),sizeof(*(ptr)))) #endif static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, @@ -367,6 +370,33 @@ static inline unsigned long __sync_cmpxchg(volatile void *ptr, return old; } +static inline unsigned long __cmpxchg_local(volatile void *ptr, + unsigned long old, unsigned long new, int size) +{ + unsigned long prev; + switch (size) { + case 1: + __asm__ __volatile__("cmpxchgb %b1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 2: + __asm__ __volatile__("cmpxchgw %w1,%2" + : "=a"(prev) + : "r"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 4: + __asm__ __volatile__("cmpxchgl %1,%2" + : "=a"(prev) + : "r"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + } + return old; +} + #ifndef CONFIG_X86_CMPXCHG /* * Building a kernel capable running on 80386. It may be necessary to @@ -403,6 +433,17 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, (unsigned long)(n), sizeof(*(ptr))); \ __ret; \ }) +#define cmpxchg_local(ptr,o,n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + if (likely(boot_cpu_data.x86 > 3)) \ + __ret = __cmpxchg_local((ptr), (unsigned long)(o), \ + (unsigned long)(n), sizeof(*(ptr))); \ + else \ + __ret = cmpxchg_386((ptr), (unsigned long)(o), \ + (unsigned long)(n), sizeof(*(ptr))); \ + __ret; \ +}) #endif #ifdef CONFIG_X86_CMPXCHG64 @@ -421,10 +462,26 @@ static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long l return prev; } +static inline unsigned long long __cmpxchg64_local(volatile void *ptr, + unsigned long long old, unsigned long long new) +{ + unsigned long long prev; + __asm__ __volatile__("cmpxchg8b %3" + : "=A"(prev) + : "b"((unsigned long)new), + "c"((unsigned long)(new >> 32)), + "m"(*__xg(ptr)), + "0"(old) + : "memory"); + return prev; +} + #define cmpxchg64(ptr,o,n)\ ((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\ (unsigned long long)(n))) - +#define cmpxchg64_local(ptr,o,n)\ + ((__typeof__(*(ptr)))__cmpxchg64_local((ptr),(unsigned long long)(o),\ + (unsigned long long)(n))) #endif /*