linux/arch/x86/include/asm/atomic.h

239 lines
5.3 KiB
C
Raw Normal View History

#ifndef _ASM_X86_ATOMIC_H
#define _ASM_X86_ATOMIC_H
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/processor.h>
#include <asm/alternative.h>
#include <asm/cmpxchg.h>
#include <asm/rmwcc.h>
#include <asm/barrier.h>
/*
* Atomic operations that C can't guarantee us. Useful for
* resource counting etc..
*/
#define ATOMIC_INIT(i) { (i) }
/**
* atomic_read - read atomic variable
* @v: pointer of type atomic_t
*
* Atomically reads the value of @v.
*/
static inline int atomic_read(const atomic_t *v)
{
return ACCESS_ONCE((v)->counter);
}
/**
* atomic_set - set atomic variable
* @v: pointer of type atomic_t
* @i: required value
*
* Atomically sets the value of @v to @i.
*/
static inline void atomic_set(atomic_t *v, int i)
{
v->counter = i;
}
/**
* atomic_add - add integer to atomic variable
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline void atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
: "ir" (i));
}
/**
* atomic_sub - subtract integer from atomic variable
* @i: integer value to subtract
* @v: pointer of type atomic_t
*
* Atomically subtracts @i from @v.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline void atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
: "ir" (i));
}
/**
* atomic_sub_and_test - subtract value from variable and test result
* @i: integer value to subtract
* @v: pointer of type atomic_t
*
* Atomically subtracts @i from @v and returns
* true if the result is zero, or false for all
* other cases.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
}
/**
* atomic_inc - increment atomic variable
* @v: pointer of type atomic_t
*
* Atomically increments @v by 1.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline void atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
}
/**
* atomic_dec - decrement atomic variable
* @v: pointer of type atomic_t
*
* Atomically decrements @v by 1.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline void atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
}
/**
* atomic_dec_and_test - decrement and test
* @v: pointer of type atomic_t
*
* Atomically decrements @v by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline int atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
}
/**
* atomic_inc_and_test - increment and test
* @v: pointer of type atomic_t
*
* Atomically increments @v by 1
* and returns true if the result is zero, or false for all
* other cases.
*/
static inline int atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
}
/**
* atomic_add_negative - add and test if negative
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v and returns true
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static inline int atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
}
/**
* atomic_add_return - add integer and return
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v and returns @i + @v
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline int atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
/**
* atomic_sub_return - subtract integer and return
* @v: pointer of type atomic_t
* @i: integer value to subtract
*
* Atomically subtracts @i from @v and returns @v - @i
*/
static inline int atomic_sub_return(int i, atomic_t *v)
{
return atomic_add_return(-i, v);
}
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))
static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
return cmpxchg(&v->counter, old, new);
}
static inline int atomic_xchg(atomic_t *v, int new)
{
return xchg(&v->counter, new);
}
/**
* __atomic_add_unless - add unless the number is already a given value
* @v: pointer of type atomic_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
*
* Atomically adds @a to @v, so long as @v was not already @u.
* Returns the old value of @v.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-21 05:27:11 +08:00
static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
int c, old;
c = atomic_read(v);
for (;;) {
if (unlikely(c == (u)))
break;
old = atomic_cmpxchg((v), c, c + (a));
if (likely(old == c))
break;
c = old;
}
return c;
}
/**
* atomic_inc_short - increment of a short integer
* @v: pointer to type int
*
* Atomically adds 1 to @v
* Returns the new value of @u
*/
static inline short int atomic_inc_short(short int *v)
{
asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
return *v;
}
/* These are x86-specific, used by some header files */
#define atomic_clear_mask(mask, addr) \
asm volatile(LOCK_PREFIX "andl %0,%1" \
: : "r" (~(mask)), "m" (*(addr)) : "memory")
#define atomic_set_mask(mask, addr) \
asm volatile(LOCK_PREFIX "orl %0,%1" \
: : "r" ((unsigned)(mask)), "m" (*(addr)) \
: "memory")
#ifdef CONFIG_X86_32
# include <asm/atomic64_32.h>
#else
# include <asm/atomic64_64.h>
#endif
#endif /* _ASM_X86_ATOMIC_H */