Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 22:21:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

x86: Fix and improve percpu_cmpxchg{8,16}b_double()

Browse Source 
They had several problems/shortcomings:

Only the first memory operand was mentioned in the 2x32bit asm()
operands, and 2x64-bit version had a memory clobber. The first
allowed the compiler to not recognize the need to re-load the
data in case it had it cached in some register, and the second
was overly destructive.

The memory operand in the 2x32-bit asm() was declared to only be
an output.

The types of the local copies of the old and new values were
incorrect (as in other per-CPU ops, the types of the per-CPU
variables accessed should be used here, to make sure the
respective types are compatible).

The __dummy variable was pointless (and needlessly initialized
in the 2x32-bit case), given that local copies of the inputs
already exist.

The 2x64-bit variant forced the address of the first object into
%rsi, even though this is needed only for the call to the
emulation function. The real cmpxchg16b can operate on an
memory.

At once also change the return value type to what it really is -
'bool'.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/4EE86D6502000078000679FE@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Jan Beulich 2011-12-14 08:33:25 +00:00 committed by Ingo Molnar
parent 969df4b829
commit cebef5beed
1 changed files with 21 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
arch/x86/include/asm/percpu.h
View File

@ -451,23 +451,20 @@ do { \
#endif /* !CONFIG_M386 */
#ifdef CONFIG_X86_CMPXCHG64
#define percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) \
#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2) \
({ \
char __ret; \
typeof(o1) __o1 = o1; \
typeof(o1) __n1 = n1; \
typeof(o2) __o2 = o2; \
typeof(o2) __n2 = n2; \
typeof(o2) __dummy = n2; \
bool __ret; \
typeof(pcp1) __o1 = (o1), __n1 = (n1); \
typeof(pcp2) __o2 = (o2), __n2 = (n2); \
asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \
: "=a"(__ret), "=m" (pcp1), "=d"(__dummy) \
: "b"(__n1), "c"(__n2), "a"(__o1), "d"(__o2)); \
: "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
: "b" (__n1), "c" (__n2), "a" (__o1)); \
__ret; \
})
#define __this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
#define this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
#define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
#define __this_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double
#define this_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double
#define irqsafe_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double
#endif /* CONFIG_X86_CMPXCHG64 */
/*
@ -508,31 +505,23 @@ do { \
* it in software. The address used in the cmpxchg16 instruction must be
* aligned to a 16 byte boundary.
*/
#ifdef CONFIG_SMP
#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP3
#else
#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP2
#endif
#define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) \
#define percpu_cmpxchg16b_double(pcp1, pcp2, o1, o2, n1, n2) \
({ \
char __ret; \
typeof(o1) __o1 = o1; \
typeof(o1) __n1 = n1; \
typeof(o2) __o2 = o2; \
typeof(o2) __n2 = n2; \
typeof(o2) __dummy; \
alternative_io(CMPXCHG16B_EMU_CALL, \
"cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \
bool __ret; \
typeof(pcp1) __o1 = (o1), __n1 = (n1); \
typeof(pcp2) __o2 = (o2), __n2 = (n2); \
alternative_io("leaq %P1,%%rsi\n\tcall this_cpu_cmpxchg16b_emu\n\t", \
"cmpxchg16b " __percpu_arg(1) "\n\tsetz %0\n\t", \
X86_FEATURE_CX16, \
ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \
"S" (&pcp1), "b"(__n1), "c"(__n2), \
"a"(__o1), "d"(__o2) : "memory"); \
ASM_OUTPUT2("=a" (__ret), "+m" (pcp1), \
"+m" (pcp2), "+d" (__o2)), \
"b" (__n1), "c" (__n2), "a" (__o1) : "rsi"); \
__ret; \
})
#define __this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
#define this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
#define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
#define __this_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double
#define this_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double
#define irqsafe_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double
#endif