cdcd629869
Just like the per-CPU ones they had several problems/shortcomings: Only the first memory operand was mentioned in the asm() operands, and the 2x64-bit version didn't have a memory clobber while the 2x32-bit one did. The former allowed the compiler to not recognize the need to re-load the data in case it had it cached in some register, while the latter was overly destructive. The types of the local copies of the old and new values were incorrect (the types of the pointed-to variables should be used here, to make sure the respective old/new variable types are compatible). The __dummy/__junk variables were pointless, given that local copies of the inputs already existed (and can hence be used for discarded outputs). The 32-bit variant of cmpxchg_double_local() referenced cmpxchg16b_local(). At once also: - change the return value type to what it really is: 'bool' - unify 32- and 64-bit variants - abstract out the common part of the 'normal' and 'local' variants Signed-off-by: Jan Beulich <jbeulich@suse.com> Cc: Christoph Lameter <cl@linux.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/4F01F12A020000780006A19B@nat28.tlf.novell.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
234 lines
6.9 KiB
C
234 lines
6.9 KiB
C
#ifndef ASM_X86_CMPXCHG_H
|
|
#define ASM_X86_CMPXCHG_H
|
|
|
|
#include <linux/compiler.h>
|
|
#include <asm/alternative.h> /* Provides LOCK_PREFIX */
|
|
|
|
/*
|
|
* Non-existant functions to indicate usage errors at link time
|
|
* (or compile-time if the compiler implements __compiletime_error().
|
|
*/
|
|
extern void __xchg_wrong_size(void)
|
|
__compiletime_error("Bad argument size for xchg");
|
|
extern void __cmpxchg_wrong_size(void)
|
|
__compiletime_error("Bad argument size for cmpxchg");
|
|
extern void __xadd_wrong_size(void)
|
|
__compiletime_error("Bad argument size for xadd");
|
|
extern void __add_wrong_size(void)
|
|
__compiletime_error("Bad argument size for add");
|
|
|
|
/*
|
|
* Constants for operation sizes. On 32-bit, the 64-bit size it set to
|
|
* -1 because sizeof will never return -1, thereby making those switch
|
|
* case statements guaranteeed dead code which the compiler will
|
|
* eliminate, and allowing the "missing symbol in the default case" to
|
|
* indicate a usage error.
|
|
*/
|
|
#define __X86_CASE_B 1
|
|
#define __X86_CASE_W 2
|
|
#define __X86_CASE_L 4
|
|
#ifdef CONFIG_64BIT
|
|
#define __X86_CASE_Q 8
|
|
#else
|
|
#define __X86_CASE_Q -1 /* sizeof will never return -1 */
|
|
#endif
|
|
|
|
/*
|
|
* An exchange-type operation, which takes a value and a pointer, and
|
|
* returns a the old value.
|
|
*/
|
|
#define __xchg_op(ptr, arg, op, lock) \
|
|
({ \
|
|
__typeof__ (*(ptr)) __ret = (arg); \
|
|
switch (sizeof(*(ptr))) { \
|
|
case __X86_CASE_B: \
|
|
asm volatile (lock #op "b %b0, %1\n" \
|
|
: "+r" (__ret), "+m" (*(ptr)) \
|
|
: : "memory", "cc"); \
|
|
break; \
|
|
case __X86_CASE_W: \
|
|
asm volatile (lock #op "w %w0, %1\n" \
|
|
: "+r" (__ret), "+m" (*(ptr)) \
|
|
: : "memory", "cc"); \
|
|
break; \
|
|
case __X86_CASE_L: \
|
|
asm volatile (lock #op "l %0, %1\n" \
|
|
: "+r" (__ret), "+m" (*(ptr)) \
|
|
: : "memory", "cc"); \
|
|
break; \
|
|
case __X86_CASE_Q: \
|
|
asm volatile (lock #op "q %q0, %1\n" \
|
|
: "+r" (__ret), "+m" (*(ptr)) \
|
|
: : "memory", "cc"); \
|
|
break; \
|
|
default: \
|
|
__ ## op ## _wrong_size(); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
/*
|
|
* Note: no "lock" prefix even on SMP: xchg always implies lock anyway.
|
|
* Since this is generally used to protect other memory information, we
|
|
* use "asm volatile" and "memory" clobbers to prevent gcc from moving
|
|
* information around.
|
|
*/
|
|
#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "")
|
|
|
|
/*
|
|
* Atomic compare and exchange. Compare OLD with MEM, if identical,
|
|
* store NEW in MEM. Return the initial value in MEM. Success is
|
|
* indicated by comparing RETURN with OLD.
|
|
*/
|
|
#define __raw_cmpxchg(ptr, old, new, size, lock) \
|
|
({ \
|
|
__typeof__(*(ptr)) __ret; \
|
|
__typeof__(*(ptr)) __old = (old); \
|
|
__typeof__(*(ptr)) __new = (new); \
|
|
switch (size) { \
|
|
case __X86_CASE_B: \
|
|
{ \
|
|
volatile u8 *__ptr = (volatile u8 *)(ptr); \
|
|
asm volatile(lock "cmpxchgb %2,%1" \
|
|
: "=a" (__ret), "+m" (*__ptr) \
|
|
: "q" (__new), "0" (__old) \
|
|
: "memory"); \
|
|
break; \
|
|
} \
|
|
case __X86_CASE_W: \
|
|
{ \
|
|
volatile u16 *__ptr = (volatile u16 *)(ptr); \
|
|
asm volatile(lock "cmpxchgw %2,%1" \
|
|
: "=a" (__ret), "+m" (*__ptr) \
|
|
: "r" (__new), "0" (__old) \
|
|
: "memory"); \
|
|
break; \
|
|
} \
|
|
case __X86_CASE_L: \
|
|
{ \
|
|
volatile u32 *__ptr = (volatile u32 *)(ptr); \
|
|
asm volatile(lock "cmpxchgl %2,%1" \
|
|
: "=a" (__ret), "+m" (*__ptr) \
|
|
: "r" (__new), "0" (__old) \
|
|
: "memory"); \
|
|
break; \
|
|
} \
|
|
case __X86_CASE_Q: \
|
|
{ \
|
|
volatile u64 *__ptr = (volatile u64 *)(ptr); \
|
|
asm volatile(lock "cmpxchgq %2,%1" \
|
|
: "=a" (__ret), "+m" (*__ptr) \
|
|
: "r" (__new), "0" (__old) \
|
|
: "memory"); \
|
|
break; \
|
|
} \
|
|
default: \
|
|
__cmpxchg_wrong_size(); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
#define __cmpxchg(ptr, old, new, size) \
|
|
__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
|
|
|
|
#define __sync_cmpxchg(ptr, old, new, size) \
|
|
__raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
|
|
|
|
#define __cmpxchg_local(ptr, old, new, size) \
|
|
__raw_cmpxchg((ptr), (old), (new), (size), "")
|
|
|
|
#ifdef CONFIG_X86_32
|
|
# include "cmpxchg_32.h"
|
|
#else
|
|
# include "cmpxchg_64.h"
|
|
#endif
|
|
|
|
#ifdef __HAVE_ARCH_CMPXCHG
|
|
#define cmpxchg(ptr, old, new) \
|
|
__cmpxchg((ptr), (old), (new), sizeof(*ptr))
|
|
|
|
#define sync_cmpxchg(ptr, old, new) \
|
|
__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
|
|
|
|
#define cmpxchg_local(ptr, old, new) \
|
|
__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
|
|
#endif
|
|
|
|
/*
|
|
* xadd() adds "inc" to "*ptr" and atomically returns the previous
|
|
* value of "*ptr".
|
|
*
|
|
* xadd() is locked when multiple CPUs are online
|
|
* xadd_sync() is always locked
|
|
* xadd_local() is never locked
|
|
*/
|
|
#define __xadd(ptr, inc, lock) __xchg_op((ptr), (inc), xadd, lock)
|
|
#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX)
|
|
#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ")
|
|
#define xadd_local(ptr, inc) __xadd((ptr), (inc), "")
|
|
|
|
#define __add(ptr, inc, lock) \
|
|
({ \
|
|
__typeof__ (*(ptr)) __ret = (inc); \
|
|
switch (sizeof(*(ptr))) { \
|
|
case __X86_CASE_B: \
|
|
asm volatile (lock "addb %b1, %0\n" \
|
|
: "+m" (*(ptr)) : "ri" (inc) \
|
|
: "memory", "cc"); \
|
|
break; \
|
|
case __X86_CASE_W: \
|
|
asm volatile (lock "addw %w1, %0\n" \
|
|
: "+m" (*(ptr)) : "ri" (inc) \
|
|
: "memory", "cc"); \
|
|
break; \
|
|
case __X86_CASE_L: \
|
|
asm volatile (lock "addl %1, %0\n" \
|
|
: "+m" (*(ptr)) : "ri" (inc) \
|
|
: "memory", "cc"); \
|
|
break; \
|
|
case __X86_CASE_Q: \
|
|
asm volatile (lock "addq %1, %0\n" \
|
|
: "+m" (*(ptr)) : "ri" (inc) \
|
|
: "memory", "cc"); \
|
|
break; \
|
|
default: \
|
|
__add_wrong_size(); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
/*
|
|
* add_*() adds "inc" to "*ptr"
|
|
*
|
|
* __add() takes a lock prefix
|
|
* add_smp() is locked when multiple CPUs are online
|
|
* add_sync() is always locked
|
|
*/
|
|
#define add_smp(ptr, inc) __add((ptr), (inc), LOCK_PREFIX)
|
|
#define add_sync(ptr, inc) __add((ptr), (inc), "lock; ")
|
|
|
|
#define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2) \
|
|
({ \
|
|
bool __ret; \
|
|
__typeof__(*(p1)) __old1 = (o1), __new1 = (n1); \
|
|
__typeof__(*(p2)) __old2 = (o2), __new2 = (n2); \
|
|
BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long)); \
|
|
BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long)); \
|
|
VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long))); \
|
|
VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2)); \
|
|
asm volatile(pfx "cmpxchg%c4b %2; sete %0" \
|
|
: "=a" (__ret), "+d" (__old2), \
|
|
"+m" (*(p1)), "+m" (*(p2)) \
|
|
: "i" (2 * sizeof(long)), "a" (__old1), \
|
|
"b" (__new1), "c" (__new2)); \
|
|
__ret; \
|
|
})
|
|
|
|
#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \
|
|
__cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2)
|
|
|
|
#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
|
|
__cmpxchg_double(, p1, p2, o1, o2, n1, n2)
|
|
|
|
#endif /* ASM_X86_CMPXCHG_H */
|