Bcc:
Subject: Re: [PATCH 2/2] local.h modifications (all arch support) Reply-To:
In-Reply-To: <20061201032458.GB32440@Krystal>
X-Editor: vi
X-Info: http://krystal.dyndns.org:8080
X-Operating-System: Linux/2.4.32-grsec (i686)
X-Uptime: 16:11:23 up 100 days, 18:19, 5 users, load average: 0.72, 0.62, 0.53
Hi,
I also completed the support for all atomic operations in local.h for all architectures. The local_t type is now identical on each architectures : it contains an atomic_long_t field, just like the asm-generic implementation.
Please review.
Mathieu
---BEGIN---
include/asm-alpha/local.h +102 -24
@@ -4,37 +4,115 @@ #define _ALPHA_LOCAL_H#include <linux/percpu.h> #include <asm/atomic.h> -typedef atomic64_t local_t ; +typedef struct +{ +atomic_long_t a; +}local_t ; -#define LOCAL_INIT (i) ATOMIC64_INIT(i) -#define local_read (v) atomic64_read(v) -#define local_set (v,i) atomic64_set(v,i) +#define LOCAL_INIT (i) { ATOMIC_LONG_INIT(i) } +#define local_read (l) atomic_long_read(&(l)->a) +#define local_set (l,i) atomic_long_set(&(l)->a, (i)) +#define local_inc (l) atomic_long_inc(&(l)->a) +#define local_dec (l) atomic_long_dec(&(l)->a) +#define local_add (i,l) atomic_long_add((i),(&(l)->a)) +#define local_sub (i,l) atomic_long_sub((i),(&(l)->a)) -#define local_inc (v) atomic64_inc(v) -#define local_dec (v) atomic64_dec(v) -#define local_add (i, v) atomic64_add(i, v) -#define local_sub (i, v) atomic64_sub(i, v) +static __inline__long local_add_return (long i,local_t * l) +{ +long temp, result; + __asm__ __volatile__( +"1: ldq_l %0,%1\n" +" addq %0,%3,%2\n" +" addq %0,%3,%0\n" +" stq_c %0,%1\n" +" beq %0,2f\n" +".subsection 2\n" +"2: br 1b\n" +".previous" + :"=&r" (temp),"=m" (l->a.counter),"=&r" (result) + :"Ir" (i),"m" (l->a.counter) :"memory" ); +return result; +} -#define __local_inc (v) ((v)->counter++) -#define __local_dec (v) ((v)->counter++) -#define __local_add (i,v) ((v)->counter+=(i)) -#define __local_sub (i,v) ((v)->counter-=(i)) +static __inline__long local_sub_return (long i,local_t * v) +{ +long temp, result; + __asm__ __volatile__( +"1: ldq_l %0,%1\n" +" subq %0,%3,%2\n" +" subq %0,%3,%0\n" +" stq_c %0,%1\n" +" beq %0,2f\n" +".subsection 2\n" +"2: br 1b\n" +".previous" + :"=&r" (temp),"=m" (l->a.counter),"=&r" (result) + :"Ir" (i),"m" (l->a.counter) :"memory" ); +return result; +} + +#define local_cmpxchg (l, old, new) \ + ((long)cmpxchg_local(&((l)->a.counter), old, new)) +#define local_xchg (l, new) (xchg_local(&((l)->a.counter), new)) + +/** +* 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) + +#define local_add_negative (a, l) (local_add_return((a), (l)) < 0) + +#define local_dec_return (l) local_sub_return(1,(l)) + +#define local_inc_return (l) local_add_return(1,(l)) + +#define local_sub_and_test (i,l) (local_sub_return((i), (l)) == 0) + +#define local_inc_and_test (l) (local_add_return(1, (l)) == 0) + +#define local_dec_and_test (l) (local_sub_return(1, (l)) == 0) + +/* Verify if faster than atomic ops */ +#define __local_inc (l) ((l)->a.counter++) +#define __local_dec (l) ((l)->a.counter++) +#define __local_add (i,l) ((l)->a.counter+=(i)) +#define __local_sub (i,l) ((l)->a.counter-=(i))/* Use these for per-cpu local_t variables: on some archs they are * much more efficient than these naive implementations. Note they take * a variable, not an address. */ -#define cpu_local_read (v) local_read(&__get_cpu_var(v)) -#define cpu_local_set (v, i) local_set(&__get_cpu_var(v), (i)) - -#define cpu_local_inc (v) local_inc(&__get_cpu_var(v)) -#define cpu_local_dec (v) local_dec(&__get_cpu_var(v)) -#define cpu_local_add (i, v) local_add((i), &__get_cpu_var(v)) -#define cpu_local_sub (i, v) local_sub((i), &__get_cpu_var(v)) - -#define __cpu_local_inc (v) __local_inc(&__get_cpu_var(v)) -#define __cpu_local_dec (v) __local_dec(&__get_cpu_var(v)) -#define __cpu_local_add (i, v) __local_add((i), &__get_cpu_var(v)) -#define __cpu_local_sub (i, v) __local_sub((i), &__get_cpu_var(v)) +#define cpu_local_read (l) local_read(&__get_cpu_var(l)) +#define cpu_local_set (l, i) local_set(&__get_cpu_var(l), (i)) + +#define cpu_local_inc (l) local_inc(&__get_cpu_var(l)) +#define cpu_local_dec (l) local_dec(&__get_cpu_var(l)) +#define cpu_local_add (i, l) local_add((i), &__get_cpu_var(l)) +#define cpu_local_sub (i, l) local_sub((i), &__get_cpu_var(l)) + +#define __cpu_local_inc (l) __local_inc(&__get_cpu_var(l)) +#define __cpu_local_dec (l) __local_dec(&__get_cpu_var(l)) +#define __cpu_local_add (i, l) __local_add((i), &__get_cpu_var(l)) +#define __cpu_local_sub (i, l) __local_sub((i), &__get_cpu_var(l))#endif /* _ALPHA_LOCAL_H */
include/asm-generic/local.h +23 -10
@@ -33,6 +33,19 @@ #define local_dec(l) atomic_long_dec(&(l#define local_add (i,l) atomic_long_add((i),(&(l)->a))#define local_sub (i,l) atomic_long_sub((i),(&(l)->a)) +#define local_sub_and_test (i, l) atomic_long_sub_and_test((i), (&(l)->a)) +#define local_dec_and_test (l) atomic_long_dec_and_test(&(l)->a) +#define local_inc_and_test (l) atomic_long_inc_and_test(&(l)->a) +#define local_add_negative (i, l) atomic_long_add_negative((i), (&(l)->a)) +#define local_add_return (i, l) atomic_long_add_return((i), (&(l)->a)) +#define local_sub_return (i, l) atomic_long_sub_return((i), (&(l)->a)) +#define local_inc_return (l) atomic_long_inc_return(&(l)->a) + +#define local_cmpxchg (l, old, new) atomic_long_cmpxchg((&(l)->a), (old), (new)) +#define local_xchg (l, new) atomic_long_xchg((&(l)->a), (new)) +#define local_add_unless (l, a, u) atomic_long_add_unless((&(l)->a), (a), (u)) +#define local_inc_not_zero (l) atomic_long_inc_not_zero(&(l)->a) +/* Non-atomic variants, ie. preemption disabled and won't be touched * in interrupt, etc. Some archs can optimize this case well. */ #define __local_inc (l) local_set((l), local_read(l) + 1)
@@ -44,19 +57,19 @@ #define __local_sub(i,l) local_set((l),* much more efficient than these naive implementations. Note they take * a variable (eg. mystruct.foo), not an address. */ -#define cpu_local_read (v) local_read(&__get_cpu_var(v)) -#define cpu_local_set (v, i) local_set(&__get_cpu_var(v), (i)) -#define cpu_local_inc (v) local_inc(&__get_cpu_var(v)) -#define cpu_local_dec (v) local_dec(&__get_cpu_var(v)) -#define cpu_local_add (i, v) local_add((i), &__get_cpu_var(v)) -#define cpu_local_sub (i, v) local_sub((i), &__get_cpu_var(v)) +#define cpu_local_read (l) local_read(&__get_cpu_var(l)) +#define cpu_local_set (l, i) local_set(&__get_cpu_var(l), (i)) +#define cpu_local_inc (l) local_inc(&__get_cpu_var(l)) +#define cpu_local_dec (l) local_dec(&__get_cpu_var(l)) +#define cpu_local_add (i, l) local_add((i), &__get_cpu_var(l)) +#define cpu_local_sub (i, l) local_sub((i), &__get_cpu_var(l))/* Non-atomic increments, ie. preemption disabled and won't be touched * in interrupt, etc. Some archs can optimize this case well. */ -#define __cpu_local_inc (v) __local_inc(&__get_cpu_var(v)) -#define __cpu_local_dec (v) __local_dec(&__get_cpu_var(v)) -#define __cpu_local_add (i, v) __local_add((i), &__get_cpu_var(v)) -#define __cpu_local_sub (i, v) __local_sub((i), &__get_cpu_var(v)) +#define __cpu_local_inc (l) __local_inc(&__get_cpu_var(l)) +#define __cpu_local_dec (l) __local_dec(&__get_cpu_var(l)) +#define __cpu_local_add (i, l) __local_add((i), &__get_cpu_var(l)) +#define __cpu_local_sub (i, l) __local_sub((i), &__get_cpu_var(l))#endif /* _ASM_GENERIC_LOCAL_H */
include/asm-i386/local.h +178 -27
252 lines not on this page · raw message
include/asm-ia64/local.h +1 -50
51 lines not on this page · raw message
include/asm-mips/local.h +1 -60
61 lines not on this page · raw message
include/asm-parisc/local.h +1 -40
41 lines not on this page · raw message
include/asm-powerpc/local.h +345 -1
346 lines not on this page · raw message
include/asm-s390/local.h +1 -58
59 lines not on this page · raw message
include/asm-sparc64/local.h +1 -40
41 lines not on this page · raw message
include/asm-x86_64/local.h +165 -31
241 lines not on this page · raw message
---END---
OpenPGP public key: http://krystal.dyndns.org:8080/key/compudj.gpg Key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68