Messages in this thread Patch in this message | | | Date | Thu, 29 Dec 2005 22:03:36 +0100 | From | Ingo Molnar <> | Subject | [patch 03/13] mutex subsystem, add include/asm-i386/mutex.h |
| |
add the i386 version of mutex.h, optimized in assembly.
Signed-off-by: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
----
include/asm-i386/mutex.h | 140 +++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 140 insertions(+)
Index: linux/include/asm-i386/mutex.h =================================================================== --- /dev/null +++ linux/include/asm-i386/mutex.h @@ -0,0 +1,140 @@ +/* + * Assembly implementation of the mutex fastpath, based on atomic + * decrement/increment. + * + * started by Ingo Molnar: + * + * Copyright (C) 2004, 2005 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + */ +#ifndef _ASM_MUTEX_H +#define _ASM_MUTEX_H + +/** + * __mutex_fastpath_lock - try to take the lock by moving the count + * from 1 to a 0 value + * @count: pointer of type atomic_t + * @fn: function to call if the original value was not 1 + * + * Change the count from 1 to a value lower than 1, and call <fn> if it + * wasn't 1 originally. This function MUST leave the value lower than 1 + * even when the "1" assertion wasn't true. + */ +#define __mutex_fastpath_lock(count, fn_name) \ +do { \ + /* type-check the function too: */ \ + void fastcall (*__tmp)(atomic_t *) = fn_name; \ + unsigned int dummy; \ + \ + (void)__tmp; \ + typecheck(atomic_t *, count); \ + \ + __asm__ __volatile__( \ + LOCK " decl (%%eax) \n" \ + " js 2f \n" \ + "1: \n" \ + \ + LOCK_SECTION_START("") \ + "2: call "#fn_name" \n" \ + " jmp 1b \n" \ + LOCK_SECTION_END \ + \ + :"=a" (dummy) \ + : "a" (count) \ + : "memory", "ecx", "edx"); \ +} while (0) + + +/** + * __mutex_fastpath_lock_retval - try to take the lock by moving the count + * from 1 to a 0 value + * @count: pointer of type atomic_t + * @fn: function to call if the original value was not 1 + * + * Change the count from 1 to a value lower than 1, and call <fn> if it + * wasn't 1 originally. This function returns 0 if the fastpath succeeds, + * or anything the slow path function returns + */ +static inline int +__mutex_fastpath_lock_retval(atomic_t *count, + int fastcall (*fn_name)(atomic_t *)) +{ + if (unlikely(atomic_dec_return(count) < 0)) + return fn_name(count); + else + return 0; +} + +/** + * __mutex_fastpath_unlock - try to promote the mutex from 0 to 1 + * @count: pointer of type atomic_t + * @fn: function to call if the original value was not 0 + * + * try to promote the mutex from 0 to 1. if it wasn't 0, call <fn>. + * In the failure case, this function is allowed to either set the value + * to 1, or to set it to a value lower than 1. + * + * If the implementation sets it to a value of lower than 1, the + * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs + * to return 0 otherwise. + */ +#define __mutex_fastpath_unlock(count, fn_name) \ +do { \ + /* type-check the function too: */ \ + void fastcall (*__tmp)(atomic_t *) = fn_name; \ + unsigned int dummy; \ + \ + (void)__tmp; \ + typecheck(atomic_t *, count); \ + \ + __asm__ __volatile__( \ + LOCK " incl (%%eax) \n" \ + " jle 2f \n" \ + "1: \n" \ + \ + LOCK_SECTION_START("") \ + "2: call "#fn_name" \n" \ + " jmp 1b \n" \ + LOCK_SECTION_END \ + \ + :"=a" (dummy) \ + : "a" (count) \ + : "memory", "ecx", "edx"); \ +} while (0) + +#define __mutex_slowpath_needs_to_unlock() 1 + +/** + * __mutex_fastpath_trylock - try to acquire the mutex, without waiting + * + * @count: pointer of type atomic_t + * @fn: fallback function + * + * Change the count from 1 to a value lower than 1, and return 0 (failure) + * if it wasn't 1 originally, or return 1 (success) otherwise. This function + * MUST leave the value lower than 1 even when the "1" assertion wasn't true. + * Additionally, if the value was < 0 originally, this function must not leave + * it to 0 on failure. + */ +static inline int +__mutex_fastpath_trylock(atomic_t *count, int (*fn)(atomic_t *)) +{ + /* + * We have two variants here. The cmpxchg based one is the best one + * because it never induce a false contention state. It is included + * here because architectures using the inc/dec algorithms over the + * xchg ones are much more likely to support cmpxchg natively. + * + * If not we fall back to the spinlock based variant - that is + * just as efficient (and simpler) as a 'destructive' probing of + * the mutex state would be. + */ +#ifdef __HAVE_ARCH_CMPXCHG + if (likely(atomic_cmpxchg(count, 1, 0)) == 1) + return 1; + return 0; +#else + return fn(count); +#endif +} + +#endif - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |